Dissertations / Theses on the topic 'Hough algorithm'

A new algorithm is proposed which uses the Hough Transform to recognize two dimensional objects independent of their orientations, sizes and locations. The binary image of an object is represented by a set of straight lines. Features of the straight lines, namely the lengths and the angles of their normals, their lengths and the end point positions are extracted using the Hough Transform. A data structure for the extracted lines is constructed so that it is efficient to match the features of the lines of one object to those of another object, and determine if one object is a rotated and/or scaled version of the other. Finally a generalized Hough Transform is used to match the end points of the two sets of lines. The simulation experiments show good results for objects with significant linear features .

Ces travaux de recherche visaient à développer un système d'aide à la mobilité pour les personnes ayant une déficience visuelle (VIP ‘Visually Impaired Person’) appelé ‘Smart Environment Explorer Stick (SEES)’. Le but particulier de cette recherche était de développer de nouveaux algorithmes pour améliorer la précision de la détection de la présence de poteaux de la canne SEE-stick en utilisant la méthode de calcul de distance et la recherche de paires de lignes verticales basées sur l'optimisation de la technique de détection de contour de Canny. Désormais, l'algorithme de détection des poteaux est appelé l’algorithme YuRHoS. Le SEES développé comme système de support d'aide à la mobilité VIP a été intégré avec succès à plusieurs dispositifs tels que le serveur distant dénommé iSEE, le serveur local embarqué dénommé SEE-phone et la canne intelligente dénommée SEE-stick. Les performances de SEE-stick ont été améliorées grâce à l'algorithme YuRHoS qui permet de discriminer avec précision les objets (obstacles) en forme de poteau parmi les objets détectés. La comparaison des résultats de détection des poteaux avec ceux des autres algorithmes a conclu que l'algorithme YuRHoS était plus efficace et précis. Le lieu et la couleur des poteaux de test d’évaluation étaient deux des facteurs les plus importants qui influaient sur la capacité du SEE-stick à détecter leur présence. Le niveau de précision de SEE-stick est optimal lorsque le test d’évaluation est effectué à l'extérieur et que les poteaux sont de couleur argentée. Les statistiques montrent que la performance de l'algorithme YuRHoS à l'intérieur était 0,085 fois moins bonne qu'à l'extérieur. De plus, la détection de la présence de poteaux de couleur argentée est 11 fois meilleure que celle de poteaux de couleur noir<br>This research aimed to develop a technology system of mobility aid for Visually Impaired Person (VIP) called Smart Environment Explorer Stick (SEES).Particular purpose of this research was developing new algorithm in improving accuracy of SEE-stick for pole detection using distance calculation method and vertical line pair search based on Canny edge detection optimization and Hough transform. Henceforth, the pole detection algorithm was named as YuRHoS algorithm.The developed SEES as supporting system of VIP mobility aid had been successfully integrated several devices such as global remote server (iSEE), embedded local server (SEE-phone) and smart stick (SEE-stick). Performance of SEE-stick could be improved through YuRHoS algorithm, which was able to fix the accuracy of SEE-stick in detecting pole. Test comparison of pole detection results among others algorithm concluded that YuRHoS algorithm had better accuracy in pole detection.Two most significant factors affecting SEE-stick ability in detecting pole was test location and pole color. Level of accuracy of SEE-stick would be optimum once the test location was performed outdoor and pole color was silver. Statistics result shown that YuRHoS algorithm performance indoor was 0.085 times worse than outdoor. Meanwhile, silver-pole-color as object detection could increase YuRHoS algorithm performance as much as 11 times better compare to black-pole-color

In the next 10 years, a radical upgrade is expected for the Large Hadron Collider focused in achieving the highest values in the instantaneous and integrated luminosity. Both the subdetectrors of the experiments and their data acquisition systems will need an upgrade. For the Phase-II upgrade of the Trigger and Data Acquisition System (TDAQ) of the ATLAS experiment a common platform has been created to share the common firmware, software and tools that are ongoing and that will come in the next years within the ATLAS TDAQ collaboration. The environment includes a set of design procedures, a virtual machine as repository for the firmware and some automatic tools for the continuous integration and versioning. The platform is under testing, as the firmware will be tested on the TDAQ upgraded, it will also be used for the prototype cards that will be produced as demonstrator for the ATLAS Hardware Tracking for the Trigger (HTT) system. For the HTT project a physical environment is being prepared, exploiting Peripheral Component Interconnect express (PCIe) and ACTA crates. My personal work has been the design of a part of track-fitting algorithms, in particular the one using the Hough Transform. This implementation has been required by the ATLAS experiment as an alternative solution to the baseline proposal accepted and described in the TDAQ Upgrade Technical Design Report (TDR). I have developed and tested a set of pattern vectors used not only in the simulation and validation of the algorithm, but also in the hadware integration on a FPGA based hardware accelerator. The used technology is based on high-performance Xilinx Ultrascale+ FPGA, implemented on VCU1525 board. This work is going to be validated by the ATLAS collaboration very soon, so to understand how we can proceed in the future upgrade. Bologna is the only Italian institute which participates in the integration of a tracking algorithm in the ATLAS trigger upgrade, using high performance FPGA-based hardware.

This Master Thesis discusses the Phase-II upgrade of the Trigger and Data Acquisition system of the detector called A Toroidal LHC ApparatuS (ATLAS). An R&D program, which has included the creation of two task forces, was launched in the 2021 Spring with the aim to produce one engineered solution for the track reconstruction at the Event Filter (EF) level. The Electronic group of the University of Bologna is taking part in the proposal of the heterogeneous commodity task force, which consists of the previous project called Hardware Tracking for the Trigger. The heterogeneous solution is based on a mixed commodity platform of classic processors and accelerators, where track reconstruction is expected to be performed via the use of mathematical functions, for example through the implementation of Hough Transform algorithm on the FPGA which will be part of the EF of ATLAS Phase-II. The R&D activities performed until now include the development of the firmware for the HT. Final goal of this Master Thesis is the creation of a hardware demonstrator able to test the ongoing firmware design. To fulfill this purpose, a new firmware architecture is exploited and it relies on a manageable Peripheral Component Interconnect Express transmission. The integration of the two firmware designs is realized with the development of a two first-in-first-out structure. In this way it is demonstrated the correct implementation of the ongoing Hough Transform firmware design.

Le détecteur MINOS a été développé jusqu'à mi-2013 pour la spectroscopie γ prompte de noyaux très exotiques à partir de réactions d’arrachage de protons. Il est composé d'une cible épaisse d'hydrogène liquide pour augmenter la luminosité et d’une chambre à projection temporelle (TPC) pour reconstruire la position du vertex de réaction et de compenser l'effet de la cible épaisse sur la correction Doppler.La chambre à projection temporelle a été développée avec l'expertise du CEA-Irfu sur les détecteurs gazeux de type Micromegas. Dans un premier temps, différentes solutions pour la TPC ont été testées dans une chambre d'essai avec une source α et des mesures de rayons cosmiques. Des muons cosmiques ont été détectés pour la première fois en utilisant la chambre d'essai en début 2013 et ont validé l'utilisation d'un plan de détection Micromegas. Le premier prototype de TPC a été achevé en mai 2013 et nous avons utilisé un banc de rayons cosmiques pour estimer l’efficacité de la TPC.MINOS a ensuite été expédié au Japon et un test de performance sous faisceau a été réalisée à l'installation médicale HIMAC (Chiba, Japon) avec deux cibles minces au lieu de la cible épaisse d'hydrogène pour valider l'algorithme de reconstruction et la résolution de la position du vertex. Un algorithme de reconstruction de traces basé sur la transformée de Hough a été mis au point pour l'analyse des données, testé avec ces données, et comparé à des simulations.La première campagne de physique avec MINOS a eu lieu en mai 2014, avec SEASTAR. Elle s’est concentrée sur la première spectroscopie des ⁶ ⁶ Cr, ⁷⁰,⁷²Fe et ⁷⁸Ni. L'analyse de la spectroscopie du ⁶ ⁶Cr a révélé deux transitions, assignées aux deux premiers états excités. Une interprétation avec des calculs de modèle en couches montre que le maximum de collectivité quadripolaire se produit à N = 40 le long de la chaîne isotopique de chrome.Le ⁶ ⁶Cr est toujours placé dans la région de l’Îlot d’Inversion à N = 40 et les calculs de modèle en couches ainsi que la comparaison avec des calculs basés sur HFB suggèrent une extension de cet Îlot d’Inversion vers N = 50 en dessous du ⁷⁸Ni. L'analyse des ⁷⁰,⁷²Fe effectuée par C. Louchart (TU Darmstadt, Allemagne) révèle la même tendance que pour les isotopes de chrome. Les données et notre interprétation par le modèle en couches suggère une grande collectivité les Cr et Fe riches en neutrons, éventuellement jusqu'à N = 50, ce qui remettrait en cause la solidité de la fermeture de couche N = 50 en dessous du ⁷⁸Ni<br>The MINOS device has been developed until mid-2013 for in-beam γ spectroscopy of very exotic nuclei from proton knockout reactions. It is composed of a thick liquid hydrogen target to achieve higher luminosities and a Time Projection Chamber (TPC) to reconstruct the vertex position and compensate for the thick target effect on the Doppler correction.The Time Projection Chamber has been developed with the expertise of CEA-IRFU in gas detectors and Micromegas detectors. At first, different solutions for the TPC were tested in a test chamber with an α source and cosmic-ray measurements. Cosmic rays were detected for the first time using the test chamber in early 2013 and validated the use of a Micromegas detection plane. The first TPC prototype was finished in May 2013, and we used a cosmic-ray bench to estimate the effiiciency of the TPC. The MINOS device was then shipped to Japan and an in-beam performance test was performed at the HIMAC medical facility (Chiba, Japan) with two thin targets instead of the thick hydrogen target to validate the tracking algorithm and the vertex position resolution. A tracking algorithm for the offline analysis based on the Hough transform has been developed, tested with the data, and compared with simulations.The first physics campaign using MINOS took place in May 2014 with SEASTAR. It focused on the first spectroscopy of ⁶ ⁶ Cr, ⁷⁰,⁷²Fe, and ⁷⁸Ni. The analysis of the ⁶⁶Cr spectroscopy revealed two transitions, assigned to the two first excited states. An interpretation with shell model calculations shows that the maximum of quadrupole collectivity occurs at N=40 along the Cr isotopic chain.⁶⁶Cr is still placed in the Island of Inversion region of N=40 and the shell model calculations as well as comparison with HFB-based calculations suggest an extension of this Island of Inversion towards N=50 below ⁷⁸Ni. The analysis of ⁷⁰,⁷²Fe performed by C. Louchart (TU Darmstadt, Germany) reveals the same trend as for Cr isotopes, with a maximum of deformation at N=42. The full data set and our shell-model interpretation suggests a large collectivity for neutron-rich Cr and Fe, possibly up to N=50, questioning the robustness of the N=50 shell closure below ⁷⁸Ni

The thesis introduces methods used for an ellipse detection. Each method is theoretically described in current subsection. The description includes methods like Hough transform, Random Hough transform, RANSAC, Genetic Algorithm and improvements with optimalization. Further there are described modifications of current procedures in the thesis to reach better results. Next to the last chapter represents testing parameters of speed, quality and accuracy of implemented algorithms. There is a conclusion of testing and a result discussion at the end.

This thesis is focused on optical character recognition and its processing. The goal of this application is to make it possible easily track daily expenses. It can be used by an individual or by a company as a monitoring tool. The main principle is to make this tool most as user friendly as it can be. The application gets its input from hardware, such as a scanner or camera, and analyzes the content of the cash voucher for further processing. To analyze the voucher, the application employs different optical character recognition methods. The result is subsequently parsed. Detailed explanations of used methods are inside the document. The application output is a filled database with cash voucher details. Another part of the work is an information system with the main purpose of displaying the collected data.

La tesi si concentra sullo studio della tecnica denominata "Circle Hough Transform" ed ha come obiettivo principale quello di dimostrare attraverso l’implementazione in linguaggio Java l’utilità e la validità dell’algoritmo trattato, mostrandone l’efficacia e il funzionamento generale di ogni sua sezione.

Nella mia tesi è presentato lo studio dell'algoritmo di Hough, utilizzato per l'identificazione di linee rette nelle immagini digitali. Nella tesi viene proposta l'implementazione della versione seriale dell'algoritmo di Hough; successivamente vengono analizzate diverse soluzioni che permettono la parallelizzazione del problema e ne vengono studiate le prestazioni.

Steered Response Power based algorithms are widely used for finding sound source location using microphone array systems. SRCP-PHAT is one such algorithm that has a robust performance under noisy and reverberant conditions. The algorithm creates a likelihood function over the field of view. This thesis employs image processing methods on SRCP-PHAT images, to exploit the difference in power levels and pixel patterns to discriminate between sound source and background pixels. Hough Transform based ellipse detection is used to identify the sound source locations by finding the centers of elliptical edge pixel regions typical of source patterns. Monte Carlo simulations of an eight microphone perimeter array with single and multiple sound sources are used to simulate the test environment and area under receiver operating characteristic (ROCA) curve is used to analyze the algorithm performance. Performance was compared to a simpler algorithm involving Canny edge detection and image averaging and an algorithms based simply on the magnitude of local maxima in the SRCP image. Analysis shows that Canny edge detection based method performed better in the presence of coherent noise sources.

Táto práca popisuje niekoľko vybraných algoritmov, ktoré boli primárne vyvinuté pre CPU procesory, avšak vzhľadom k vysokému dopytu po ich vylepšeniach sme sa rozhodli ich využiť v prospech GPGPU (procesorov grafického adaptéra). Modifikácia týchto algoritmov bola zároveň cieľom nášho výskumu, ktorý  bol prevedený pomocou CUDA rozhrania. Práca je členená podľa troch skupín algoritmov, ktorým sme sa venovali: detekcia objektov v reálnom čase, spektrálna analýza obrazu a detekcia čiar v reálnom čase. Pre výskum detekcie objektov v reálnom čase sme zvolili použitie LRD a LRP funkcií.  Výskum spektrálnej analýzy obrazu bol prevedný pomocou PCA a NTF algoritmov. Pre potreby skúmania detekcie čiar v reálnom čase sme používali dva rôzne spôsoby modifikovanej akumulačnej schémy Houghovej transformácie. Pred samotnou časťou práce venujúcej sa konkrétnym algoritmom a predmetu skúmania, je v úvodných kapitolách, hneď po kapitole ozrejmujúcej dôvody skúmania vybranej problematiky, stručný prehľad architektúry GPU a GPGPU. Záverečné kapitoly sú zamerané na konkretizovanie vlastného prínosu autora, jeho zameranie, dosiahnuté výsledky a zvolený prístup k ich dosiahnutiu. Súčasťou výsledkov je niekoľko vyvinutých produktov.

Cette thèse porte sur la segmentation supervisée d'un flux vidéo en fragments correspondant à des activités de la vie quotidienne. En différenciant geste, action et activité, cette thèse s'intéresse aux activités à haut niveau sémantique telles que "Cuisiner" ou "Prendre son repas" par opposition à des actions comme "Découper un aliment". Pour cela, elle s'appuie sur l'algorithme DOHT (Deeply Optimized Hough Transform), une méthode de l'état de l'art utilisant un paradigme de vote (par transformée de Hough). Dans un premier temps, nous adaptons l'algorithme DOHT pour fusionner les informations en provenance de différents capteurs à trois niveaux différents de l'algorithme. Nous analysons l'effet de ces trois niveaux de fusion et montrons son efficacité par une évaluation sur une base de données composée d'actions de la vie quotidienne. Ensuite, une étude des jeux de données existant est menée. Constatant le manque de vidéos adaptées à la segmentation et classification (détection) d'activités à haut niveau sémantique, une nouvelle base de données est proposée. Enregistrée dans un environnement réaliste et dans des conditions au plus proche de l'application finale, elle contient des vidéos longues et non découpées adaptées à un contexte de détection. Dans un dernier temps, nous proposons une approche hiérarchique à partir d'algorithmes DOHT pour reconnaître les activités à haut niveau sémantique. Cette approche à deux niveaux décompose le problème en une détection non-supervisée d'actions pour ensuite détecter les activités désirées<br>This thesis focuses on supervised activity segmentation from video streams within application context of smart homes. Three semantic levels are defined, namely gesture, action and activity, this thesis focuses mainly on the latter. Based on the Deeply Optimized Hough Transform paridigm, three fusion levels are introduced in order to benefit from various modalities. A review of existing action based datasets is presented and the lack of activity detection oriented database is noticed. Then, a new dataset is introduced. It is composed of unsegmented long time range daily activities and has been recorded in a realistic environment. Finaly, a hierarchical activity detection method is proposed aiming to detect high level activities from unsupervised action detection

Le travail de cette thèse s'inscrit dans le cadre de la vision 3D et se consacre plus spécialement à la reconstitution de scènes à partir d'une séquence d'images monoculaires saisie par une caméra en mouvement. Il s'agit de reconstruire les éléments 3D du type segments de droite d'une scène en utilisant la connaissance du mouvement de la caméra. L'étude a été faite dans le contexte de la géométrie projective, ce qui a permis, dans le cas d'une translation, le développement d'une approche basée sur le principe de dualité projective. L'idée consiste à résoudre le problème en trois phases séquentielles : - Diviser les droites de la scène en groupes de droites parallèles via un groupement correspondant de leurs images et déterminer la direction de chaque groupe. - Reconstruire les droites groupe par groupe. - Retrouver les segments portés par chacune des droites reconstruites. Dans l'optique de la dualité projective, chacune des deux premières phases revient à représenter les primitives 2D, droites support des segments extraits des images, par des points dans un plan projectif et a mettre en évidence de l'alignement des points qui correspond a un groupe de droites parallèles pour la première phase ou a une seule droite de la scène pour la seconde. Un ensemble d'algorithmes dont le principe se fond essentiellement sur la transformation de Hough a été développé pour réaliser les trois phases. Cette approche privilégie le traitement de longues et denses séquences d'images. Des résultats expérimentaux ont été présentés en vue de montrer sa performance.

碩士<br>國立臺北科技大學<br>電機工程系碩士班<br>90<br>Hardness value of material has been found to be very important in industrial. It is related to tensile strength of many metals and is also an indicator of wear resistance and ductility. Usually the hardness value is measured by an operator via microscopy. It is not only time-consuming but also requires an experienced and skillful operator to ensure the accuracy. The test result may be different for different operators due to eye fatigue and long working time. Automatic hardness measurement can efficiently solve this problem for operators. In order to overcome the unavoidable affects of vertex detection due to surface contaminations or specimen texture, a novel automatic Vickers hardness measuring method called Hough fuzzy vertices detection algorithm (HFVDA) is proposed. HFVDA transforms all the candidate pixels on the indentation edge lines into Hough space. Within Hough space, a weighted fuzzy c-means algorithm along with local maximum detection is proposed to find the transformed indentation edge lines. It will be shown that HFVDA is able to find the indentation vertices and calculate the hardness number with high accuracy for either specular-polished or rough-polished specimens.

碩士<br>國立臺灣師範大學<br>工業教育學系<br>99<br>Region of interest (ROI) for the lane detection is a commonly used approach to reduce the computational complexity. However, the traditional ROI in the Hough parameter space is prone to result in vibrated lane markings. To solve this problem, this study presents an elliptic ROI in the Hough parameter space. The proposed ROI not only can increase the accuracy of lane detection but also can further reduce the computational complexity of Hough transform. Besides, this study also presents two auxiliary systems. One is the assistant lane detection, which is used to solve the problem that one side of lane-markings is disappeared. The other one is the lane changing system, which can be used to warn the driver that the car is going to leave the track. Experimental results show that the proposed algorithm results in more accurate and satisfying lane-marking detection.

碩士<br>國立臺灣科技大學<br>電子工程系<br>106<br>This thesis is related to the hardware/software codesign and implementation of a linked-list-based Hough-transform algorithmic processor for line detection. The research includes four parts: The first part is to analyze the property of the algorithm and, after considering that the embedded systems have limited memory resources, a linked-list-based Hough-transform algorithm for line detection has been developed. Also the C language is used to write the program for implementing and verifying the proposed algorithm. The second part is to design and develop a linked-list-based Hough-transform algorithmic processor for line detection. This algorithmic processor consists of a control unit, a source data buffer, a valid-pixel logic, a coordinate-and-address generator, a Hough-parameter generator, and a linked-list-based Hough-transform algorithmic subprocessor. The algorithmic processor is integrated onto a SOPC-based chip and implemented on an Altera FPGA development board. The third part is about the hardware/software codesign of a linked-list-based Hough-transform algorithmic processor for line detection. Software and driver programs are developed by using the NIOS II integrated development environment to verify and analyze the function of this algorithmic processor. The fourth part is to evaluate the performance of the algorithm and the algorithmic processor. In conclusion, the goal of this thesis is: (1) to develop a linked-list-based Hough-transform algorithm for line detection; (2) to finish the hardware/software codesign and implementation of the HT-based algorithmic processor. Finally, by implementing this algorithmic processor on an FPGA development board, both the modified algorithm and the related algorithmic processor are proved to be more memory-efficient and have better performance.

碩士<br>國立臺灣科技大學<br>電子工程系<br>99<br>This thesis is related to the hardware/software co-design and verification of an algorithmic processor for an HT-based (Hough- Transform-based) two-stage line detection algorithm. The related research work includes four parts: The first part is about software design of the HT-based line detection algorithm for binary images. After analyzing the property of the HT-based algorithm and considering about the limited hardware resources in the embedded system, a two-stage HT-based algorithm for line detection has been developed. The second part is to design and implement a two-stage algorithmic processor for HT-based line detection. SDARM is used to store the whole binary images. Therefore the processor consists of source data fetching sub-processor, Hough transform sub-processor, and local max finding sub-processor. Finally, the above hardware modules are integrated into an SOPC-based system and implemented on an Altera FPGA development board. The third part is to write the related drivers for the algorithmic processor. Then the function of the algorithmic processor is verified through using a RPC-based verification system. The fourth part is about the verification and the evaluation of the run-time performance of the algorithmic processor. On the whole, the goal of this thesis is to do researches on the development of an HT-based two-stage line detection algorithm and its hardware processor. Then the related algorithmic processor is developed and implemented on the FPGA development board. After being verified by using various images, the algorithm developed in this thesis has shown very good performance. Meanwhile, it also shows that the hardware/software co-design method presented can improve the efficiency of both the design and verification flows.

碩士<br>國立臺灣科技大學<br>電子工程系<br>106<br>This thesis is related to the hardware/software codesign and implementation of a two-stage block-based algorithmic processing system for the circular Hough transform. The related research work includes four parts: The first part is about the software design of a two-stage block-based circular Hough transform algorithm. After analyzing the property of the circular Hough transform algorithm and considering about the limited memory resources in the embedded systems, a two-stage block-based circular Hough transform algorithm has been developed. In this part, C language is used to write the program for verifying this proposed algorithm. The second part is to design and implement an algorithmic processor for the two-stage block-based circular Hough transform. The processor consists of a control unit, a source-data-buffer module, a coordinate-generator module, a votes-generator module, a voting module, and a local-max module. The custom hardware is integrated into a system on a programmable chip and implemented on the Altera FPGA development board. The third part is related to the implementation and verification of the hardware/software codesign for an algorithmic processing system. Here, with NIOS II IDE, driver and firmware programs are written to verify and analyze the functionality of the system. The fourth part is to evaluate the performance of the algorithmic processor. On the whole, the goal of this thesis is to do research on a two-stage block-based algorithm for the circular Hough transform and to design and implement an algorithmic processing system for it. Meanwhile, this algorithmic processing system has been implemented on an FPGA development board to compare and prove that the algorithm and hardware processor developed in this thesis have nice performance.