Gotowa bibliografia na temat „Pore segmentation”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Zobacz listy aktualnych artykułów, książek, rozpraw, streszczeń i innych źródeł naukowych na temat „Pore segmentation”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Artykuły w czasopismach na temat "Pore segmentation"
1
Liu, Lei, Qiaoling Han, Yue Zhao, and Yandong Zhao. "A Novel Method Combining U-Net with LSTM for Three-Dimensional Soil Pore Segmentation Based on Computed Tomography Images." Applied Sciences 14, no. 8 (2024): 3352. http://dx.doi.org/10.3390/app14083352.
Pełny tekst źródłaStreszczenie:
The non-destructive study of soil micromorphology via computed tomography (CT) imaging has yielded significant insights into the three-dimensional configuration of soil pores. Precise pore analysis is contingent on the accurate transformation of CT images into binary image representations. Notably, segmentation of 2D CT images frequently harbors inaccuracies. This paper introduces a novel three-dimensional pore segmentation method, BDULSTM, which integrates U-Net with convolutional long short-term memory (CLSTM) networks to harness sequence data from CT images and enhance the precision of pore segmentation. The BDULSTM method employs an encoder–decoder framework to holistically extract image features, utilizing skip connections to further refine the segmentation accuracy of soil structure. Specifically, the CLSTM component, critical for analyzing sequential information in soil CT images, is strategically positioned at the juncture of the encoder and decoder within the U-shaped network architecture. The validation of our method confirms its efficacy in advancing the accuracy of soil pore segmentation beyond that of previous deep learning techniques, such as U-Net and CLSTM independently. Indeed, BDULSTM exhibits superior segmentation capabilities across a diverse array of soil conditions. In summary, BDULSTM represents a state-of-the-art artificial intelligence technology for the 3D segmentation of soil pores and offers a promising tool for analyzing pore structure and soil quality.
2
Fu, Yinkai, Zihan Huang, Yue Zhao, Benye Xi, Yandong Zhao, and Qiaoling Han. "A weakly supervised soil pore segmentation method based on traditional segmentation algorithm." CATENA 249 (February 2025): 108660. https://doi.org/10.1016/j.catena.2024.108660.
Pełny tekst źródła
3
Silva, Italo Francyles Santos da, Alan de Carvalho Araújo, João Dallyson Sousa de Almeida, Anselmo Cardoso de Paiva, Aristófanes Corrêa Silva, and Deane Roehl. "Soil Structure Analysis with Attention: A Deep Deep-Learning-Based Method for 3D Pore Segmentation and Characterization." AgriEngineering 7, no. 2 (2025): 27. https://doi.org/10.3390/agriengineering7020027.
Pełny tekst źródłaStreszczenie:
The pore structure plays a crucial role in soil systems. It affects a range of processes essential for soil ecological functions, such as the transport and retention of water and nutrients, as well as gas exchanges. The mechanical and hydrological characteristics of soil are predominantly determined by the three-dimensional pore pore-space structure. A precise analysis of pore structure can help specialists understand how these shapes impact plant root activity, leading to better cultivation practices. X-ray computed tomography provides detailed information without destroying the sample. However, manually delineating pore structure and estimating porosity are challenging tasks. This work proposes an automated method for 3D pore segmentation and characterization using convolutional neural networks with attention mechanisms. The method introduces a novel approach that combines attention at both channel and spatial levels, enhancing the segmentation and property estimation, providing valuable insights for a more detailed study of soil conditions. In experiments conducted with a private dataset, the segmentation results achieved mean Dice values of 99.10% ± 0.0004 and mean IoU values of 98.23% ± 0.0008. Additionally, in tests with Phaeozem Albic, the automatic method provided porosity estimates comparable to those obtained by a method based on integral geometry and morphology.
4
Berg, Steffen, Nishank Saxena, Majeed Shaik, and Chaitanya Pradhan. "Generation of ground truth images to validate micro-CT image-processing pipelines." Leading Edge 37, no. 6 (2018): 412–20. http://dx.doi.org/10.1190/tle37060412.1.
Pełny tekst źródłaStreszczenie:
Digital rock technology and pore-scale physics have become increasingly relevant topics in a wide range of porous media with important applications in subsurface engineering. This technology relies heavily on images of pore space and pore-level fluid distribution determined by X-ray microcomputed tomography (micro-CT). Digital images of pore space (or pore-scale fluid distribution) are typically obtained as gray-level images that first need to be processed and segmented to obtain the binary images that uniquely represent rock and pore (including fluid phases). This processing step is not trivial. Rock complexity, image quality, noise, and other artifacts prohibit the use of a standard processing workflow. Instead, an array of strategies of increasing sophistication has been developed. Typical processing pipelines consist of filtering, segmentation, and postprocessing steps. For each step, various choices and different options exist. This makes selection and validation of an optimum processing pipeline difficult. Using Darcy-scale quantities as a benchmark is not a good option because of rock heterogeneity and different scales of observation. Here, we present a conceptual workflow where noisy images are derived from a ground truth by systematically including typical image artifacts and noise. Artifacts and noise are not simply added to the images. Instead, tomographic forward projection and reconstruction steps are used to incorporate the artifacts in a physically correct way. A proof of concept of this workflow is demonstrated by comparing seven different image-segmentation pipelines ranging from absolute thresholding to a machine-learning approach (Trainable Weka Segmentation). The Trainable Weka Segmentation showed the best performance of the tested methods.
5
Yang, Eomzi, Dong Hun Kang, and Tae Sup Yun. "Reliable estimation of hydraulic permeability from 3D X-ray CT images of porous rock." E3S Web of Conferences 205 (2020): 08004. http://dx.doi.org/10.1051/e3sconf/202020508004.
Pełny tekst źródłaStreszczenie:
The hydraulic permeability is a key parameter for simulating the flow-related phenomenon so that its accurate estimation is crucial in both experimental and numerical simulation studies. 3D pore structure can be readily taken by X-ray computed tomography (CT) and it often serves as a flow domain for pore-scale simulation. However, one encounters the challenges in segmenting the authentic pore structure owing to the finite size of image resolution and segmentation methods. Therefore, the loss of structural information in pore space seems unavoidable to result in the unreliable estimation of permeability. In this study, we propose a novel framework to overcome these limitations by using a flexible ternary segmentation scheme. Given the pore size distribution curve and porosity, three phases of pore, solid, and gray regions are segmented by considering the partial volume effect which holds the composition information of unresolved objects. The resolved objects such as solid and pore phases are taken to equivalently solve Stokes equation while the fluid flow through unresolved objects is simultaneously solved by Stokes-Brinkmann equation. The proposed numerical scheme to obtain the permeability is applied to Indiana limestone and Navajo sandstone. The results show that the computed hydraulic permeability is similar to the experimentally obtained value without being affected by image resolution. This approach has advantages of achieving consistent permeability values, less influenced by segmentation methods.
6
Li, Mingjiang, Pan Zhang, and Tao Hai. "Pore extraction method of rock thin section based on Attention U-Net." Journal of Physics: Conference Series 2467, no. 1 (2023): 012016. http://dx.doi.org/10.1088/1742-6596/2467/1/012016.
Pełny tekst źródłaStreszczenie:
Abstract This paper proposes a solution to the shortcomings of traditional segmentation methods. The labeling method uses the incomplete labeling method in weakly supervised labeling to simplify labeling and combines transfer learning to initialize the weight of the network in advance. According to the above ideas, an end-to-end deep learning model is trained. The fine rock particles have a greater segmentation impact, and in addition to that, when compared with the popular deep learning semantic segmentation approaches, they also have a significant improvement. The next phase is to continue improving the network by optimizing the parameters, with the number of network layers and the total number of parameters remaining unaltered. This requirement must be satisfied before moving on to the next stage. The capability of generalization enhances the impact of segmentation on particles as well as their accuracy. Experiments show that this method is significantly better than the traditional method for segmenting rock flakes with manual operation and has better results in the segmentation and extraction of fine particles compared with the mainstream convolutional neural network.
7
Idowu, N. A. A., C. Nardi, H. Long, T. Varslot, and P. E. E. Øren. "Effects of Segmentation and Skeletonization Algorithms on Pore Networks and Predicted Multiphase-Transport Properties of Reservoir-Rock Samples." SPE Reservoir Evaluation & Engineering 17, no. 04 (2014): 473–83. http://dx.doi.org/10.2118/166030-pa.
Pełny tekst źródłaStreszczenie:
Summary Networks of large pores connected by narrower throats (pore networks) are essential inputs into network models that are routinely used to predict transport properties from digital rock images. Extracting pore networks from microcomputed-tomography (micro-CT) images of rocks involves a number of steps: filtering, segmentation, skeletonization, and others. Because of the amount of clay and its distribution, the segmentation of micro-CT images is not trivial, and different algorithms exist for achieving this. Similarly, several methods are available for skeletonizing the segmented images and for extracting the pore networks. The nonuniqueness of these processes raises questions about the predictive power of network models. In the present work, we evaluate the effects of these processes on the computed petrophysical and multiphase-flow properties of reservoir-rock samples. By use of micro-CT images of reservoir sandstones, we first apply three different segmentation algorithms and assess the effects of the different algorithms on estimated porosity, amount of clay, and clay distribution. Single-phase properties are computed directly on the segmented images and compared with experimental data. Next, we extract skeletons from the segmented images by use of three different algorithms. On the pore networks generated from the different skeletons, we simulate two-phase oil/ water and three-phase gas/oil/water displacements by use of a quasistatic pore-network model. Analysis of the segmentation results shows differences in the amount of clay, in the total porosity, and in the computed singlephase properties. Simulated results show that there are differences in the network-predicted single-phase properties as well. However, predicted multiphase-transport properties from the different networks are in good agreement. This indicates that the topology of the pore space is well preserved in the extracted skeleton. Comparison of the computed capillary pressure and relative permeability curves for all networks with available experimental data shows good agreements. By use of a segmentation that captures porosity and microporosity, we show that the extracted networks can be used to reliably predict multiphase-transport properties, irrespective of the algorithms used.
8
Lu, An Qun, Shou Zhi Zhang, and Qian Tian. "Matlab Image Processing Technique and Application in Pore Structure Characterization of Hardened Cement Pastes." Advanced Materials Research 785-786 (September 2013): 1374–79. http://dx.doi.org/10.4028/www.scientific.net/amr.785-786.1374.
Pełny tekst źródłaStreszczenie:
Based on Matlab image processing technique and backscattered electron image analysis method, a characterization method is set up to make quantitative analysis on pore structure of hardened cement pastes. Adopt Matlab to acquire images, and carry out gradation and binarization processing for them; use the combination method of local threshold segmentation and histogram segmentation to obtain pore structure characteristics. The results showed that evolution law of pore structure of fly ash cement pastes via Matlab image analysis method is similar to the conclusion obtained through BET and DVS. Selecting different angle of backscattered electron images in the same sample, its statistic results are more representative.
9
Liu, Yifei, and Dong-Sheng Jeng. "Pore Structure of Grain-Size Fractal Granular Material." Materials 12, no. 13 (2019): 2053. http://dx.doi.org/10.3390/ma12132053.
Pełny tekst źródłaStreszczenie:
Numerous studies have proven that natural particle-packed granular materials, such as soil and rock, are consistent with the grain-size fractal rule. The majority of existing studies have regarded these materials as ideal fractal structures, while few have viewed them as particle-packed materials to study the pore structure. In this study, theoretical analysis, the discrete element method, and digital image processing were used to explore the general rules of the pore structures of grain-size fractal granular materials. The relationship between the porosity and grain-size fractal dimension was determined based on bi-dispersed packing and the geometric packing theory. The pore structure of the grain-size fractal granular material was proven to differ from the ideal fractal structure, such as the Menger sponge. The empirical relationships among the box-counting dimension, lacunarity, succolarity, grain-size fractal dimension, and porosity were provided. A new segmentation method for the pore structure was proposed. Moreover, a general function of the pore size distribution was developed based on the segmentation results, which was verified by the soil-water characteristic curves from the experimental database.
10
Zel, Ivan, Murat Kenessarin, Sergey Kichanov, Kuanysh Nazarov, Maria Bǎlǎșoiu, and Denis Kozlenko. "Pore Segmentation Techniques for Low-Resolution Data: Application to the Neutron Tomography Data of Cement Materials." Journal of Imaging 8, no. 9 (2022): 242. http://dx.doi.org/10.3390/jimaging8090242.
Pełny tekst źródłaStreszczenie:
The development of neutron imaging facilities provides a growing range of applications in different research fields. The significance of the obtained structural information, among others, depends on the reliability of phase segmentation. We focused on the problem of pore segmentation in low-resolution images and tomography data, taking into consideration possible image corruption in the neutron tomography experiment. Two pore segmentation techniques are proposed. They are the binarization of the enhanced contrast data using the global threshold, and the segmentation using the modified watershed technique—local threshold by watershed. The proposed techniques were compared with a conventional marker-based watershed on the test images simulating low-quality tomography data and on the neutron tomography data of the samples of magnesium potassium phosphate cement (MKP). The obtained results demonstrate the advantages of the proposed techniques over the conventional watershed-based approach.
Rozprawy doktorskie na temat "Pore segmentation"
1
Ding, Nan. "3D Modeling of the Lamina Cribrosa in OCT Data." Electronic Thesis or Diss., Sorbonne université, 2024. http://www.theses.fr/2024SORUS148.
Pełny tekst źródłaStreszczenie:
La lame criblée (LC), située dans la tête du nerf optique, joue un rôle crucial dans le diagnostic et l'étude du glaucome, la deuxième cause de cécité. Il s'agit d'un maillage collagénique 3D formé de pores, par lesquels les fibres nerveuses passent pour atteindre le cerveau. L'observation 3D in vivo des pores de la LC est désormais possible grâce aux progrès de l'imagerie de tomographie de cohérence optique (OCT). Dans cette étude, nous visons à réaliser automatiquement la reconstruction 3D des pores à partir de volumes OCT, afin d'étudier le remodelage de la LC au cours du glaucome. La résolution limitée de l'OCT conventionnel ainsi que le faible rapport signal à bruit (SNR) posent des problèmes pour caractériser les chemins axonaux avec suffisamment de fiabilité et de précision, sachant qu'il est difficile, même pour des experts, d'identifier les pores dans une seule image en-face. Ainsi, notre première contribution est une méthode innovante de recalage et de fusion de deux volumes OCT 3D orthogonaux pour l'amélioration de la qualité d'image et le rehaussement des pores, ce qui, à notre connaissance, n'avait jamais été réalisé. Les résultats expérimentaux démontrent que notre algorithme est robuste et conduit à un alignement précis. Notre deuxième contribution est la conception d'un réseau de neurones profond, de type attention U-net, pour segmenter les pores de la LC dans les images 2D en-face. Il s'agit de la première tentative de résolution de ce problème par apprentissage profond, les défis posés relevant de l'incomplétude des annotations pour l'apprentissage, et du faible contraste et de la mauvaise résolution des pores. L'analyse comparative avec d'autres méthodes montre que notre approche conduit aux meilleurs résultats. La fusion des volumes OCT et la segmentation des pores dans les images en-face constituent les deux étapes préliminaires à la reconstruction 3D des trajets axonaux, notre troisième contribution. Nous proposons une méthode de suivi des pores fondée sur un algorithme de contour actif paramétrique appliqué localement. Notre modèle intègre les caractéristiques de faible intensité et de régularité des pores. Combiné aux cartes de segmentation 2D, il nous permet de reconstituer plan par plan les chemins axonaux en 3D. Ces résultats ouvrent la voie au calcul de biomarqueurs et facilitent l'interprétation médicale<br>The lamina cribrosa (LC) is a 3D collagenous mesh in theoptic nerve head that plays a crucial role in themechanisms and diagnosis of glaucoma, the second leading cause of blindness in the world. The LC is composed of so-called “pores”, namely axonal paths within the collagenous mesh, through which the axons pass to reach the brain. In vivo 3D observation of the LC pores is now possible thanks to advances in Optical Coherence Tomography (OCT) technology. In this study, we aim to automatically perform the 3D reconstruction of pore paths from OCT volumes, in order to study the remodeling of the lamina cribrosa during glaucoma and better understand this disease.The limited axial resolution of conventional OCT as well as the low signal to noise ratio (SNR) poses challenges for the robust characterization of axonal paths with enough reliability, knowing that it is difficult even for experts to identify the pores in a single en-face image. To this end, our first contribution introduces an innovative method to register and fuse 2 orthogonal 3D OCT volumes in order to enhance the pores. This is, to our knowledge, the first time that orthogonal OCT volumes are jointly exploited to achieve better image quality. Experimental results demonstrate that our algorithm is robust and leads to accurate alignment.Our second contribution presents a context-aware attention U-Net method, a deep learning approach using partial points annotation for the accurate pore segmentation in every 2D en-face image. This work is also, to the best of our knowledge, the first attempt to look into the LC pore reconstruction problem using deep learning methods. Through a comparative analysis with other state-of-the-art methods, we demonstrate the superior performance of the proposed approach.Our robust and accurate pore registration and segmentation methods provide a solid foundation for 3D reconstruction of axonal pathways, our third contribution. We propose a pore tracking method based on a locally applied parametric active contour algorithm. Our model integrates the characteristics of low intensity and regularity of pores. Combined with the 2D segmentation maps, it enables us to reconstruct the axonal paths in 3D plane by plane. These results pave the way for the calculation of biomarkers characterizing the LC and facilitate medical interpretation
2
Wagh, Ameya Yatindra. "A Deep 3D Object Pose Estimation Framework for Robots with RGB-D Sensors." Digital WPI, 2019. https://digitalcommons.wpi.edu/etd-theses/1287.
Pełny tekst źródłaStreszczenie:
The task of object detection and pose estimation has widely been done using template matching techniques. However, these algorithms are sensitive to outliers and occlusions, and have high latency due to their iterative nature. Recent research in computer vision and deep learning has shown great improvements in the robustness of these algorithms. However, one of the major drawbacks of these algorithms is that they are specific to the objects. Moreover, the estimation of pose depends significantly on their RGB image features. As these algorithms are trained on meticulously labeled large datasets for object's ground truth pose, it is difficult to re-train these for real-world applications. To overcome this problem, we propose a two-stage pipeline of convolutional neural networks which uses RGB images to localize objects in 2D space and depth images to estimate a 6DoF pose. Thus the pose estimation network learns only the geometric features of the object and is not biased by its color features. We evaluate the performance of this framework on LINEMOD dataset, which is widely used to benchmark object pose estimation frameworks. We found the results to be comparable with the state of the art algorithms using RGB-D images. Secondly, to show the transferability of the proposed pipeline, we implement this on ATLAS robot for a pick and place experiment. As the distribution of images in LINEMOD dataset and the images captured by the MultiSense sensor on ATLAS are different, we generate a synthetic dataset out of very few real-world images captured from the MultiSense sensor. We use this dataset to train just the object detection networks used in the ATLAS Robot experiment.
3
Seguin, Guillaume. "Analyse des personnes dans les films stéréoscopiques." Thesis, Paris Sciences et Lettres (ComUE), 2016. http://www.theses.fr/2016PSLEE021/document.
Pełny tekst źródłaStreszczenie:
Les humains sont au coeur de nombreux problèmes de vision par ordinateur, tels que les systèmes de surveillance ou les voitures sans pilote. Ils sont également au centre de la plupart des contenus visuels, pouvant amener à des jeux de données très larges pour l’entraînement de modèles et d’algorithmes. Par ailleurs, si les données stéréoscopiques font l’objet d’études depuis longtemps, ce n’est que récemment que les films 3D sont devenus un succès commercial. Dans cette thèse, nous étudions comment exploiter les données additionnelles issues des films 3D pour les tâches d’analyse des personnes. Nous explorons tout d’abord comment extraire une notion de profondeur à partir des films stéréoscopiques, sous la forme de cartes de disparité. Nous évaluons ensuite à quel point les méthodes de détection de personne et d’estimation de posture peuvent bénéficier de ces informations supplémentaires. En s’appuyant sur la relative facilité de la tâche de détection de personne dans les films 3D, nous développons une méthode pour collecter automatiquement des exemples de personnes dans les films 3D afin d’entraîner un détecteur de personne pour les films non 3D. Nous nous concentrons ensuite sur la segmentation de plusieurs personnes dans les vidéos. Nous proposons tout d’abord une méthode pour segmenter plusieurs personnes dans les films 3D en combinant des informations dérivées des cartes de profondeur avec des informations dérivées d’estimations de posture. Nous formulons ce problème comme un problème d’étiquetage de graphe multi-étiquettes, et notre méthode intègre un modèle des occlusions pour produire une segmentation multi-instance par plan. Après avoir montré l’efficacité et les limitations de cette méthode, nous proposons un second modèle, qui ne repose lui que sur des détections de personne à travers la vidéo, et pas sur des estimations de posture. Nous formulons ce problème comme la minimisation d’un coût quadratique sous contraintes linéaires. Ces contraintes encodent les informations de localisation fournies par les détections de personne. Cette méthode ne nécessite pas d’information de posture ou des cartes de disparité, mais peut facilement intégrer ces signaux supplémentaires. Elle peut également être utilisée pour d’autres classes d’objets. Nous évaluons tous ces aspects et démontrons la performance de cette nouvelle méthode<br>People are at the center of many computer vision tasks, such as surveillance systems or self-driving cars. They are also at the center of most visual contents, potentially providing very large datasets for training models and algorithms. While stereoscopic data has been studied for long, it is only recently that feature-length stereoscopic ("3D") movies became widely available. In this thesis, we study how we can exploit the additional information provided by 3D movies for person analysis. We first explore how to extract a notion of depth from stereo movies in the form of disparity maps. We then evaluate how person detection and human pose estimation methods perform on such data. Leveraging the relative ease of the person detection task in 3D movies, we develop a method to automatically harvest examples of persons in 3D movies and train a person detector for standard color movies. We then focus on the task of segmenting multiple people in videos. We first propose a method to segment multiple people in 3D videos by combining cues derived from pose estimates with ones derived from disparity maps. We formulate the segmentation problem as a multi-label Conditional Random Field problem, and our method integrates an occlusion model to produce a layered, multi-instance segmentation. After showing the effectiveness of this approach as well as its limitations, we propose a second model which only relies on tracks of person detections and not on pose estimates. We formulate our problem as a convex optimization one, with the minimization of a quadratic cost under linear equality or inequality constraints. These constraints weakly encode the localization information provided by person detections. This method does not explicitly require pose estimates or disparity maps but can integrate these additional cues. Our method can also be used for segmenting instances of other object classes from videos. We evaluate all these aspects and demonstrate the superior performance of this new method
4
Madadi, Meysam. "Human segmentation, pose estimation and applications." Doctoral thesis, Universitat Autònoma de Barcelona, 2017. http://hdl.handle.net/10803/457900.
Pełny tekst źródłaStreszczenie:
El análisis automático de seres humanos en fotografías o videos tiene grandes aplicaciones dentro de la visión por computador, incluyendo diagnóstico médico, deportes, entretenimiento, edición de películas y vigilancia, por nombrar sólo algunos. El cuerpo, la cara y la mano son los componentes más estudiados de los seres humanos. El cuerpo tiene muchas variabilidades en la forma y la ropa junto con altos grados de libertad en pose. La cara está compuesta por multitud de músculos, causando muchas deformaciones visibles, diferentes formas, y variabilidad en cabello. La mano es un objeto pequeño, que se mueve rápido y tiene altos grados de libertad. La adición de características humanas a todas las variabilidades antes mencionadas hace que el análisis humano sea una tarea muy difícil.
En esta tesis, desarrollamos la segmentación humana en diferentes modalidades. En un primer escenario, segmentamos el cuerpo humano y la mano en imágenes de profundidad utilizando la forma basada en la deformación de forma. Desarrollamos un descriptor de forma basado en el contexto de forma y las probabilidades de clase de regiones de forma para extraer vecinos más cercanos. Consideramos entonces la alineación afın rígida frente a la deformación de forma iterativa no rígida. En un segundo escenario, segmentamos la cara en imágenes RGB usando redes neuronales convolucionales (CNN). Modelamos los Conditional Random Field con redes neuronales recurrentes. En nuestro modelo, los núcleos de pares no son fijos y aprendidos durante el entrenamiento. Hemos entrenado la red de extremo-a-extremo utilizando redes adversarias que mejoraron la segmentación del pelo con un alto margen.
También hemos trabajado en la estimación de pose de manos 3D en imágenes de profundidad. En un enfoque generativo, se ajustó un modelo de dedo por separado para cada dedo. Minimizamos una función de energía basada en el área de superposición, la discrepancia de profundidad y las colisiones de los dedos. También se aplican modelos lineales en el espacio de la trayectoria articular para refinar las articulaciones ocluidas basadas en el error de las articulaciones visibles y la suavidad de la trayectoria invisible de las articulaciones. En un enfoque basado en CNN, desarrollamos una red de estructura de árbol para entrenar características específicas para cada dedo y las fusionamos para la consistencia de la pose global. También formulamos restricciones físicas y de apariencia como funciones de pérdida de la red.
Finalmente, desarrollamos una serie de aplicaciones que consisten en mediciones biométricas humanas y retextura de prendas de vestir. También hemos generado algunos conjuntos de datos en esta tesis sobre diferentes tópicos del análisis de personas, que incluyen problemas de segmentación, manos sintéticas, ropa para retextura, y reconocimiento de gestos.<br>Automatic analyzing humans in photographs or videos has great potential applications in computer vision containing medical diagnosis, sports, entertainment, movie editing and surveillance, just to name a few. Body, face and hand are the most studied components of humans. Body has many variabilities in shape and clothing along with high degrees of freedom in pose. Face has many muscles causing many visible deformity, beside variable shape and hair style. Hand is a small object, moving fast and has high degrees of freedom. Adding human characteristics to all aforementioned variabilities makes human analysis quite a challenging task.
In this thesis, we developed human segmentation in different modalities. In a first scenario, we segmented human body and hand in depth images using example-based shape warping. We developed a shape descriptor based on shape context and class probabilities of shape regions to extract nearest neighbors. We then considered rigid affine alignment vs. non-rigid iterative shape warping. In a second scenario, we segmented face in RGB images using convolutional neural networks (CNN). We modeled conditional random field with recurrent neural networks. In our model pair-wise kernels are not fixed and learned during training. We trained the network end-to-end using adversarial networks which improved hair segmentation by a high margin.
We also worked on 3D hand pose estimation in depth images. In a generative approach, we fitted a finger model separately for each finger based on our example-based rigid hand segmentation. We minimized an energy function based on overlapping area, depth discrepancy and finger collisions. We also applied linear models in joint trajectory space to refine occluded joints based on visible joints error and invisible joints trajectory smoothness. In a CNN-based approach, we developed a tree-structure network to train specific features for each finger and fused them for global pose consistency. We also formulated physical and appearance constraints as loss functions.
Finally, we developed a number of applications consisting of human soft biometrics measurement and garment retexturing. We also generated some datasets in this thesis consisting of human segmentation, synthetic hand pose, garment retexturing and Italian gestures.
5
Chen, Daniel Chien Yu. "Image segmentation and pose estimation of humans in video." Thesis, Queensland University of Technology, 2014. https://eprints.qut.edu.au/66230/1/Daniel_Chen_Thesis.pdf.
Pełny tekst źródłaStreszczenie:
This thesis introduces improved techniques towards automatically estimating the pose of humans from video. It examines a complete workflow to estimating pose, from the segmentation of the raw video stream to extract silhouettes, to using the silhouettes in order to determine the relative orientation of parts of the human body. The proposed segmentation algorithms have improved performance and reduced complexity, while the pose estimation shows superior accuracy during difficult cases of self occlusion.
6
Sandhu, Romeil Singh. "Statistical methods for 2D image segmentation and 3D pose estimation." Diss., Georgia Institute of Technology, 2010. http://hdl.handle.net/1853/37245.
Pełny tekst źródłaStreszczenie:
The field of computer vision focuses on the goal of developing techniques to exploit and extract information from underlying data that may represent images or other multidimensional data. In particular, two well-studied problems in computer vision are the fundamental tasks of 2D image segmentation and 3D pose estimation from a 2D scene.
In this thesis, we first introduce two novel methodologies that attempt to independently solve 2D image segmentation and 3D pose estimation separately. Then, by leveraging the advantages of certain techniques from each problem, we couple both tasks in a variational and non-rigid manner through a single energy functional. Thus, the three theoretical components and contributions of this thesis are as follows:
Firstly, a new distribution metric for 2D image segmentation is introduced. This is employed within the geometric active contour (GAC) framework.
Secondly, a novel particle filtering approach is proposed for the problem of estimating the pose of two point sets that differ by a rigid body transformation.
Thirdly, the two techniques of image segmentation and pose estimation are coupled in a single energy functional for a class of 3D rigid objects.
After laying the groundwork and presenting these contributions, we then turn to their applicability to real world problems such as visual tracking. In particular, we present an example where we develop a novel tracking scheme for 3-D Laser RADAR imagery. However, we should mention that the proposed contributions are solutions for general imaging problems and therefore can be applied to medical imaging problems such as extracting the prostate from MRI imagery
7
DELERUE, JEAN FRANCOIS. "Segmentation 3d, application a l'extraction de reseaux de pores et a la caracterisation hydrodynamique des sols." Paris 11, 2001. http://www.theses.fr/2001PA112141.
Pełny tekst źródłaStreszczenie:
Le sol et les materiaux poreux en general, peuvent etre vus comme l'union de deux parties : la partie solide, constituee de differents materiaux (argile, roche etc. ) et la partie vide (espace poral) par ou peuvent s'ecouler des fluides. Une connaissance precise de la structure 3d de la partie vide devrait permettre une meilleure comprehension des phenomenes d'ecoulement, voire meme une prevision des proprietes hydriques de ces materiaux. Les recents progres dans les domaines de l'acquisition d'image rendent de plus en plus abordable l'obtention d'images volumiques de sol, notamment grace a la tomographie a rayon x. Mon travail a consiste a adapter des algorithmes d'analyse d'image existants, et a en developper de nouveaux afin de decrire les structures des parties vides dans des images volumiques de sol. Pour mener a bien cette description, je propose differents algorithmes originaux : un algorithme de calcul de diagramme de voronoi sur espace discret, un algorithme de squelettisation par selection des points de frontieres de voronoi et un algorithme de segmentation par croissance de region utilisant des distances de type geodesique. Ces differents algorithmes forment une suite qui, appliquee a un objet quelconque, permet de le decomposer suivant des criteres de taille locale. Dans le cas d'une image de sol, la partie vide du sol est segmentee en regions correspondant a des pores (parties elementaires de l'espace poral d'ouverture homogene) et un reseau de pores est cree. A partir de ce reseau, il est possible par analogie avec les reseaux electriques de calculer la conductivite hydrique equivalente pour l'image etudiee. De facon generale, je propose un ensemble de procedures permettant entre autre, de simuler des processus d'intrusion et d'extrusion de fluide dans l'espace poral, de simuler la porosimetrie au mercure et de calculer des distributions d'ouvertures. Bien que concu pour l'etude des sols, ce travail d'imagerie 3d pourrait etre applique a d'autres domaines.
8
Hewa, Thondilege Akila Sachinthani Pemasiri. "Multimodal Image Correspondence." Thesis, Queensland University of Technology, 2022. https://eprints.qut.edu.au/235433/1/Akila%2BHewa%2BThondilege%2BThesis%281%29.pdf.
Pełny tekst źródłaStreszczenie:
Multimodal images are used across many application areas including medical and surveillance. Due to the different characteristics of different imaging modalities, developing image processing algorithms for multimodal images is challenging. This thesis proposes effective solutions for the challenging problem of multimodal semantic correspondence where the connections between similar components across images from different modalities are established. The proposed methods which are based on deep learning techniques have been applied for several applications including epilepsy type classification and 3D reconstruction of human hand from visible and X-ray image. These proposed algorithms can be adapted to many other imaging modalities.
9
Calzavara, Ivan. "Human pose augmentation for facilitating Violence Detection in videos: a combination of the deep learning methods DensePose and VioNetHuman pose augmentation for facilitating Violence Detection in videos: a combination of the deep learning methods DensePose and VioNet." Thesis, Mittuniversitetet, Institutionen för informationssystem och –teknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-40842.
Pełny tekst źródłaStreszczenie:
In recent years, deep learning, a critical technology in computer vision, has achieved remarkable milestones in many fields, such as image classification and object detection. In particular, it has also been introduced to address the problem of violence detection, which is a big challenge considering the complexity to establish an exact definition for the phenomenon of violence. Thanks to the ever increasing development of new technologies for surveillance, we have nowadays access to an enormous database of videos that can be analyzed to find any abnormal behavior. However, by dealing with such huge amount of data it is unrealistic to manually examine all of them. Deep learning techniques, instead, can automatically study, learn and perform classification operations. In the context of violence detection, with the extraction of visual harmful patterns, it is possible to design various descriptors to represent features that can identify them. In this research we tackle the task of generating new augmented datasets in order to try to simplify the identification step performed by a violence detection technique in the field of Deep Learning. The novelty of this work is to introduce the usage of DensePose model to enrich the images in a dataset by highlighting (i.e. by identifying and segmenting) all the human beings present in them. With this approach we gained knowledge of how this algorithm performs on videos with a violent context and how the violent detection network benefit from this procedure. Performances have been evaluated from the point of view of segmentation accuracy and efficiency of the violence detection network, as well from the computational point of view. Results shows how the context of the scene is the major indicator that brings the DensePose model to correct segment human beings and how the context of violence does not seem to be the most suitable field for the application of this model since the common overlap of bodies (distinctive aspect of violence) acts as disadvantage for the segmentation. For this reason, the violence detection network does not exploit its full potential. Finally, we understood how such augmented datasets can boost up the training speed by reducing the time needed for the weights-update phase, making this procedure a helpful adds-on for implementations in different contexts where the identification of human beings still plays the major role.
10
Karabagli, Bilal. "Vérification automatique des montages d'usinage par vision : application à la sécurisation de l'usinage." Phd thesis, Université Toulouse le Mirail - Toulouse II, 2013. http://tel.archives-ouvertes.fr/tel-01018079.
Pełny tekst źródłaStreszczenie:
Le terme "usinage à porte fermée", fréquemment employé par les PME de l'aéronautique et de l'automobile, désigne l'automatisation sécurisée du processus d'usinage des pièces mécaniques. Dans le cadre de notre travail, nous nous focalisons sur la vérification du montage d'usinage, avant de lancer la phase d'usinage proprement dite. Nous proposons une solution sans contact, basée sur la vision monoculaire (une caméra), permettant de reconnaitre automatiquement les éléments du montage (brut à usiner, pions de positionnement, tiges de fixation,etc.), de vérifier que leur implantation réelle (réalisée par l'opérateur) est conforme au modèle 3D numérique de montage souhaité (modèle CAO), afin de prévenir tout risque de collision avec l'outil d'usinage.
Książki na temat "Pore segmentation"
1
Shiffrar, Maggie. The Aperture Problem. Oxford University Press, 2017. http://dx.doi.org/10.1093/acprof:oso/9780199794607.003.0076.
Pełny tekst źródłaStreszczenie:
The accurate visual perception of an object’s motion requires the simultaneous integration of motion information arising from that object along with the segmentation of motion information from other objects. When moving objects are seen through apertures, or viewing windows, the resultant illusions highlight some of the challenges that the visual system faces as it balances motion segmentation with motion integration. One example is the barber pole Illusion, in which lines appear to translate orthogonally to their true direction of emotion. Another is the illusory perception of incoherence when simple rectilinear objects translate or rotate behind disconnected apertures. Studies of these illusions suggest that visual motion processes frequently rely on simple form cues.
2
Castellani, Claudia, and Marianne Wootton. Crustacea: Introduction. Oxford University Press, 2017. http://dx.doi.org/10.1093/oso/9780199233267.003.0021.
Pełny tekst źródłaStreszczenie:
This chapter provides an introduction to the Crustacea, one of the most abundant and diverse components of the plankton. Within a single net-haul, the vast diversity within this group, coupled with the large number of species and the morphological similarity both between species and between developmental stages, can often pose a significant identification challenge even to experienced taxonomists. Although all Crustacea originally share a common body plan, their morphology can differ quite markedly due to different degrees of expression of body segmentation patterns and as a result of the loss or morphological modifications of paired appendages. There is also considerable variation between groups in the structure and function of the appendages on different body regions.
Części książek na temat "Pore segmentation"
1
Jiqun, Zhang, Hu Chungjin, Liu Xin, He Dongmei, and Li Hua. "An Algorithm for Rock Pore Image Segmentation." In Lecture Notes in Electrical Engineering. Springer Berlin Heidelberg, 2015. http://dx.doi.org/10.1007/978-3-662-46578-3_28.
Pełny tekst źródła
2
Ramon Soria, Pablo, Fouad Sukkar, Wolfram Martens, B. C. Arrue, and Robert Fitch. "Multi-view Probabilistic Segmentation of Pome Fruit with a Low-Cost RGB-D Camera." In ROBOT 2017: Third Iberian Robotics Conference. Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-70836-2_27.
Pełny tekst źródła
3
Kang, Wenrui, Xu Wang, Jixia Zhang, Xiaoming Hu, and Qin Li. "Two-Way Perceived Color Difference Saliency Algorithm for Image Segmentation of Port Wine Stains." In Communications in Computer and Information Science. Springer Singapore, 2021. http://dx.doi.org/10.1007/978-981-16-1160-5_5.
Pełny tekst źródła
4
Lu, Siwei, Xiaofang Zhao, Huazhu Liu, and Hongjie Liang. "Semiconductor Material Porosity Segmentation in Flame Retardant Materials SEM Images Using Data Augmentation and Transfer Learning." In Advances in Transdisciplinary Engineering. IOS Press, 2024. http://dx.doi.org/10.3233/atde240011.
Pełny tekst źródłaStreszczenie:
Non-halogenated flame retardants are becoming the trend in the development of polymer flame retardant materials due to their high flame retardant efficiency and low generation of toxic smoke gases. Non-halogenated flame retardants achieve flame retardancy by forming a dense char layer and generating non-combustible gases, with the micro-porous structure of the char residue being crucial for studying the flame retardant mechanism. This study focuses on the segmentation of pores in scanning electron microscopy (SEM) images of the combustion char layer of non-halogenated flame retardant materials, which are cropped and labeled to form a unified dataset. We investigate the SEM image pore segmentation using data augmentation and transfer learning, addressing the challenge of limited sample size. We explore the impact of different data augmentation techniques and transfer learning on model performance. Additionally, we compare convolutional neural network (CNN) segmentation algorithms with traditional segmentation methods. Experimental results demonstrate that CNN segmentation algorithms outperform traditional methods in terms of segmentation accuracy. Offline data augmentation enhances model stability compared to online data augmentation, and adopting transfer learning significantly improves model performance metrics. Specifically, when training with VGG backbone weights through transfer learning, the average pixel accuracy and average intersection over union reach 94.49% and 89.88%, respectively.
5
Martin, Vincent, and Monique Thonnat. "A Learning Approach for Adaptive Image Segmentation." In Scene Reconstruction Pose Estimation and Tracking. I-Tech Education and Publishing, 2007. http://dx.doi.org/10.5772/4946.
Pełny tekst źródła
6
Vetrivel, S. C., T. P. Saravanan, V. P. Arun, and R. Maheswari. "Innovative Approaches to Market Segmentation Using AI in Emerging Economies." In Advances in Marketing, Customer Relationship Management, and E-Services. IGI Global, 2024. http://dx.doi.org/10.4018/979-8-3693-7122-0.ch017.
Pełny tekst źródłaStreszczenie:
This chapter explores innovative approaches to market segmentation using artificial intelligence (AI) in emerging economies. Traditional market segmentation techniques often fall short in dynamic and rapidly evolving markets, where diverse consumer behaviors and limited data availability pose significant challenges. AI, with its advanced data processing and pattern recognition capabilities, offers new possibilities for more accurate and actionable market segmentation. In emerging economies, AI-driven segmentation can harness big data from various sources, including social media, mobile usage, and transactional data to identify and understand distinct consumer segments. Machine learning algorithms can analyze these vast datasets to uncover hidden patterns and predict future consumer behaviors, enabling businesses to tailor their marketing strategies effectively. The chapter highlights case studies where AI has been successfully implemented for market segmentation in emerging markets, demonstrating improvements in targeting accuracy, customer engagement, and overall marketing efficiency.
7
Han, Dongil. "Real-Time Object Segmentation of the Disparity Map Using Projection-Based Region Merging." In Scene Reconstruction Pose Estimation and Tracking. I-Tech Education and Publishing, 2007. http://dx.doi.org/10.5772/4924.
Pełny tekst źródła
8
Babu, Tina, Rekha R. Nair, Judeson Antony Kovilpaillai, and Mano Antony Shankari. "Generative Adversarial Networks in Object Detection and Segmentation in Remote Sensing Images." In Advances in Geospatial Technologies. IGI Global, 2025. https://doi.org/10.4018/979-8-3693-6900-5.ch006.
Pełny tekst źródłaStreszczenie:
GANs are revolutionizing computer vision, especially in remote sensing through satellite and aerial imagery. These images pose unique challenges: they're complex and contain objects of various sizes, making segmentation difficult. This paper explores how GANs overcome these challenges by generating realistic synthetic data, particularly when labeled data is scarce. We examine specialized variants like cGANs and SegGANs, which excel in land use analysis, urban structure detection, and environmental monitoring. Our approach combines GANs with traditional machine learning to improve object detection accuracy beyond current standards. While acknowledging cost and interpretability challenges, we highlight GANs' potential in multi-spectral and hyperspectral imaging applications.
9
Engemann, Heiko, Shengzhi Du, Stephan Kallweit, Chuanfang Ning, and Saqib Anwar. "AutoSynPose: Automatic Generation of Synthetic Datasets for 6D Object Pose Estimation." In Machine Learning and Artificial Intelligence. IOS Press, 2020. http://dx.doi.org/10.3233/faia200770.
Pełny tekst źródłaStreszczenie:
We present an automated pipeline for the generation of synthetic datasets for six-dimension (6D) object pose estimation. Therefore, a completely automated generation process based on predefined settings is developed, which enables the user to create large datasets with a minimum of interaction and which is feasible for applications with a high object variance. The pipeline is based on the Unreal 4 (UE4) game engine and provides a high variation for domain randomization, such as object appearance, ambient lighting, camera-object transformation and distractor density. In addition to the object pose and bounding box, the metadata includes all randomization parameters, which enables further studies on randomization parameter tuning. The developed workflow is adaptable to other 3D objects and UE4 environments. An exemplary dataset is provided including five objects of the Yale-CMU-Berkeley (YCB) object set. The datasets consist of 6 million subsegments using 97 rendering locations in 12 different UE4 environments. Each dataset subsegment includes one RGB image, one depth image and one class segmentation image at pixel-level.
10
Bhandari, Vedant, Tyson Phillips, and Ross McAree. "Novel Approaches for Point Cloud Analysis with Evidential Methods: A Multifaceted Approach to Object Pose Estimation, Point Cloud Odometry, and Sensor Registration." In Point Cloud Generation and Its Applications [Working Title]. IntechOpen, 2024. http://dx.doi.org/10.5772/intechopen.1004467.
Pełny tekst źródłaStreszczenie:
Autonomous agents must understand their environment to make decisions. Perception systems often interpret point cloud measurements to extract beliefs about their surroundings. A common strategy is to seek beliefs that are least likely to be false, commonly known as cost-based approaches. These metrics have limitations in practical applications, such as in the presence of noisy measurements, dynamic objects, and debris. Modern solutions integrate additional stages such as segmentation to counteract these limitations, thereby increasing the complexity of the algorithms while being internally flawed. An alternative strategy is to extract beliefs that are best supported by the data. We call these evidence-based methods. This difference allows for robustness to the limitations of using cost-based methods without needing complex additional stages. Essential perception tasks such as object pose estimation, point cloud odometry, and sensor registration are solved using evidence-based methods. The demonstrated approaches are simple, require minimum configuration and tuning, and circumvents the need for additional processing stages.
Streszczenia konferencji na temat "Pore segmentation"
1
He, Chongyu, Zhiwu Xie, Yinlin Chen, and Edward A. Fox. "Nuclear Pore Segmentation in 3D FIB-SEM Images with Dynamic Cyclical Data Augmentation." In 2024 IEEE International Conference on Big Data (BigData). IEEE, 2024. https://doi.org/10.1109/bigdata62323.2024.10825445.
Pełny tekst źródła
2
Li, Haotian, Billal Aslam, and Bicheng Yan. "Enhanced 3D Pore Segmentation and Multi-Model Pore-Scale Simulation by Deep Learning." In SPE Annual Technical Conference and Exhibition. SPE, 2024. http://dx.doi.org/10.2118/220838-ms.
Pełny tekst źródłaStreszczenie:
Abstract Rock permeability characterization is crucial to understanding fluid flow in subsurface geological formations. It contributes to accurately simulating such processes that can address challenges like sustainable hydrocarbon production and geological CO2 sequestration. Recent advancements in deep learning have facilitated efficient permeability prediction in digital rock. However, existing methods often struggle to predict core-scale properties due to limitations in accommodating larger sub-volumes. This study introduces novel approaches integrating deep learning and physics-constrained methods to enhance rock segmentation, permeability prediction and upscaling. We first propose a 3D Inception U-Net model for 3D pore segmentation, which leverages the capability of the Inception block to capture multi-scale features in porous media and thus enhances segmentation accuracy. Further, we develop two different upscaling methods for permeability prediction. The first method is direct upscaling using deep learning, which directly predicts permeability across multiple scales by training with a combination of various sizes of sub-volumes; the second method is physics-constrained upscaling using deep learning, which imposes additional physical constraints on permeability predictions. We evaluate our deep-learning-based segmentation and upscaling approaches on diverse datasets, including Bentheimer, Leopard, and Parker sandstones. Our 3D Inception U-Net model achieves 0.99 accuracy for 3D pore segmentation. In upscaling, the direct upscaling using deep learning achieves R2 scores of 0.94, 0.83, and 0.84 at sub-volume sizes of 1503, 3003, and 6003, respectively, which demonstrates its potential to generalize permeability prediction across multiple sub-volume scales. On the other hand, with the permeability prediction of the base sub-volumes (size 1503) through the Lattice-Boltzman Method (LBM), the physics-constrained upscaling using deep learning achieves R2 values of 0.98 after upscaling from 1503 to 3003 sub-volumes, and further increases R2 to 0.99 after upscaling from 3003 to 6003 sub-volumes. Furthermore, when using 3D CNN-predicted permeability of 1503 sub-volumes, the second upscaling method achieves R2 scores of 0.96 and 0.94 for these two upscaling stages, respectively, highlighting its stable accuracy across scales. This research highlights the potential of integrating advanced deep learning with physics-constrained approaches to advance rapid and precise permeability prediction in digital rock physics, offering a promising framework for future core-scale applications and research endeavors.
3
Wang, Hangjun, Guangqun Zhang, Hengnian Qi, and Lingfei Ma. "Multi-objective Optimization on Pore Segmentation." In 2009 Fifth International Conference on Natural Computation. IEEE, 2009. http://dx.doi.org/10.1109/icnc.2009.572.
Pełny tekst źródła
4
Wang, Hangjun, Hengnian Qi, Wenzhu Li, Guangqun Zhang, and Paoping Wang. "A GA-based automatic pore segmentation algorithm." In the first ACM/SIGEVO Summit. ACM Press, 2009. http://dx.doi.org/10.1145/1543834.1543989.
Pełny tekst źródła
5
Qi, Heng-Nian, Feng-Nong Chen, and Ling-Fei Ma. "Pore Feature Segmentation Based on Mathematical Morphology." In IECON 2007 - 33rd Annual Conference of the IEEE Industrial Electronics Society. IEEE, 2007. http://dx.doi.org/10.1109/iecon.2007.4460248.
Pełny tekst źródła
6
Seo, Sunyong, Sangwook Yoo, Semin Kim, Daeun Yoon, and Jongha Lee. "Facial Pore Segmentation Algorithm using Shallow CNN." In 2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS). IEEE, 2022. http://dx.doi.org/10.1109/cbms55023.2022.00062.
Pełny tekst źródła
7
Malathi, S., S. Uma Maheswari, and C. Meena. "Fingerprint pore extraction based on Marker controlled Watershed Segmentation." In 2nd International Conference on Computer and Automation Engineering (ICCAE 2010). IEEE, 2010. http://dx.doi.org/10.1109/iccae.2010.5451426.
Pełny tekst źródła
8
Ma, Zongfang, Ming Duan, Chao Liu, et al. "Better Semantic Segmentation For 3D Printing Concrete Surface Pore Detection." In 2023 42nd Chinese Control Conference (CCC). IEEE, 2023. http://dx.doi.org/10.23919/ccc58697.2023.10239802.
Pełny tekst źródła
9
Joshi, R. M. "Self-Consistent Approximation for Porosity Segmentation." In Indonesian Petroleum Association - 46th Annual Convention & Exhibition 2022. Indonesian Petroleum Association, 2022. http://dx.doi.org/10.29118/ipa22-g-121.
Pełny tekst źródłaStreszczenie:
Carbonate reservoirs have been known to be a major source of hydrocarbons; it is well known that approximately 60% of the oil and 40% of the gas reserves in the world are found in carbonates, yet the understanding of the carbonate reservoir poses a significant challenge in exploration and exploitation. Presence of secondary porosity which differentiates it from clastic reservoirs brings its own set of complexity primarily owing to the poro-perm relationship. Carbonate fields in Bombay offshore (Western offshore of India) are no different. In order to understand the poro-perm complexity of one such field in Bombay offshore, the core samples obtained from wells went through Scanning Electron Microscopy (SEM). This study incorporates the results of experiments performed on core samples to determine the pore size distribution and the porosity of the samples at the given depth. The Self-Consistent Approximation (SCA) approach is applied on Scanning Electron Microscope (SEM) image data to determine the elastic properties of rocks and porosity partitioning of carbonate reservoir located in the western offshore region, India. The perquisites for this SCA modelling approach were sonic derived logs and SEM data extracted from core samples. The SEM images of cores from ten different depths and two different wells are analyzed by an algorithm to quantify the type of pores into cracks, inter-particle, and stiff defined by their aspect ratios. The sonic velocities were inverted using optimization technique for the entire depth range of the one well log. Machine learning algorithm was used to estimate the pore aspect ratio’s probability density. This study attempts to achieve porosity partitioning in carbonate reservoirs using SCA that will help in understanding the complex porosity system of these reservoirs and to develop a petro-physical and rock physics model to deduce the scalability of its different properties, not only in Bombay offshore but anywhere else.
10
Mohammad, Rafiq Darwis, Deepak Devegowda, Chandra Rai, Mark Curtis, Sanjana Mudduluru, and Sai Kiran Maryada. "Self-Supervised Learning Using Vision Transformer Architecture for Rock Image Segmentation." In SPE Europe Energy Conference and Exhibition. SPE, 2025. https://doi.org/10.2118/225609-ms.
Pełny tekst źródłaStreszczenie:
Abstract The segmentation of microstructural features in Scanning Electron Microscopy (SEM) images of shale samples is critical for petrophysical analyses, including mineralogy quantification, pore network analysis, and pore system identification. However, processing these images efficiently and accurately typically requires supervised deep learning-based methods, such as semantic segmentation algorithms. Semantic segmentation classifies each pixel in an image into a predefined category (e.g., organic material, inorganic material, pore), regardless of the number of times that category appears in the image. This type of segmentation enables the detailed quantification of microstructural features in shales, but supervised methods require large, manually annotated datasets. The creation of these datasets, particularly for SEM images, is resource-intensive, both in terms of time and cost. Self-supervised semantic segmentation, on the other hand, learns useful features from the image itself without needing manual annotation, significantly reducing the time and cost involved in dataset preparation. The specific algorithm in this work is based on a Vision Transformer architecture. Our dataset comprises of FIB-SEM images from 22 shale plays across North and South America. We first begin with careful image augmentation, which is especially critical for self-supervised semantic segmentation algorithms, to avoid generating trivial solutions while also enabling the algorithm to focus on global details as well as local variations in an image. In this work, our data augmentation tasks include generating random crops of each image and enhancing the contrast. This is followed by training a self-supervised segmentation algorithm on a subset of images from our augmented dataset. Finally, we use the trained model to segment the image into 12 sub-classes which are subsequently grouped into the primary classes of organic, and inorganic material and pores. This approach enables the model to capture subtle differences in grayscale shades within each primary class, resulting in more refined image segmentation. We evaluate the self-supervised model across several complex scenarios to test its accuracy and robustness and show that the model reliably segments organic, inorganic, and pore regions in these images, allowing for large-scale analyses of shale images and eliminating the dependence on large, expensively annotated datasets. However, while our approach is promising, we also document instances with poor segmentation performance, which occurs in about 5% of the images we test. Nevertheless, considering the rapidity and fidelity of this approach, especially for instances where labeled data is scarce and expensive to acquire, self-supervised segmentation has the potential to streamline the analyses of microstructural features in shales, making it a valuable tool for subsequent petrophysical and geological applications.