Dissertations / Theses on the topic 'Perception of Occlusion'

La reconnaissance faciale est une technologie importante en vision par ordinateur, avec un rôle central en biométrie, interface homme-machine, contrôle d’accès, indexation multimédia, etc. L’occultation partielle, qui change complétement l’apparence d’une partie du visage, ne provoque pas uniquement une dégradation des performances en reconnaissance faciale, mai peut aussi avoir des conséquences en termes de sécurité. Dans cette thèse, nous concentrons sur le problème des occultations en reconnaissance faciale en environnements non contrôlés. Nous proposons une séquence qui consiste à analyser de manière explicite les occultations et à fiabiliser la reconnaissance faciale soumises à diverses occultations. Nous montrons dans cette thèse que l’approche proposée est plus efficace que les méthodes de l’état de l’art opérant sans traitement explicite dédié aux occultations. Nous identifions deux nouveaux types d’occultations, à savoir éparses et dynamiques. Des solutions sont introduites pour gérer ces problèmes d’occultation nouvellement identifiés dans un contexte de vidéo surveillance avancé. Récemment, le nouveau capteur Kinect a été utilisé avec succès dans de nombreuses applications en vision par ordinateur. Nous introduisons ce nouveau capteur dans le contexte de la reconnaissance faciale, en particulier en présence d’occultations, et démontrons son efficacité par rapport aux caméras traditionnelles. Finalement, nous proposons deux approches basées 2D et 3D permettant d’améliorer les techniques de base en reconnaissance de visages. L’amélioration des méthodes de base peut alors générer un impact positif sur les résultats de reconnaissance en présence d’occultations
Face recognition is an important technology in computer vision, which often acts as an essential component in biometrics systems, HCI systems, access control systems, multimedia indexing applications, etc. Partial occlusion, which significantly changes the appearance of part of a face, cannot only cause large performance deterioration of face recognition, but also can cause severe security issues. In this thesis, we focus on the occlusion problem in automatic face recognition in non-controlled environments. Toward this goal, we propose a framework that consists of applying explicit occlusion analysis and processing to improve face recognition under different occlusion conditions. We demonstrate in this thesis that the proposed framework is more efficient than the methods based on non-explicit occlusion treatments from the literature. We identify two new types of facial occlusions, namely the sparse occlusion and dynamic occlusion. Solutions are presented to handle the identified occlusion problems in more advanced surveillance context. Recently, the emerging Kinect sensor has been successfully applied in many computer vision fields. We introduce this new sensor in the context of face recognition, particularly in presence of occlusions, and demonstrate its efficiency compared with traditional 2D cameras. Finally, we propose two approaches based on 2D and 3D to improve the baseline face recognition techniques. Improving the baseline methods can also have the positive impact on the recognition results when partial occlusion occurs

Objective: The purpose was to compare orthodontists’ and parents’ perception of orthodontic treatment outcomes in the anterior-posterior (AP) dimension. Assessment of treatment time and compliance were also investigated. Material and Methods: Parallel surveys for orthodontists (n=1000) and parents (n=750) displayed occlusions from 3 mm Class III (Cl III:3) to 3 mm Class II. Participants rated occlusal relationships on a 100 mm VAS from least to most acceptable (0-100). Results: 233 orthodontists (23%) and 243 parents (32%) responded. Orthodontists (mean=93.9, 25.9) and parents (mean=80.7, 40.9) rated Class I (Cl I) occlusion most and Cl III:3 least acceptable. No significant difference was found between outcomes at 18 months versus 24 months. For all cases, parents were willing to extend treatment duration longer than orthodontists. Conclusions: Orthodontists and parents viewed treatment outcomes in the AP dimension differently, rating Cl I as most acceptable. Parents were willing to extend treatment longer than orthodontists.

Thesis (Ph.D.)--Boston University
PLEASE NOTE: Boston University Libraries did not receive an Authorization To Manage form for this thesis or dissertation. It is therefore not openly accessible, though it may be available by request. If you are the author or principal advisor of this work and would like to request open access for it, please contact us at open-help@bu.edu. Thank you.
Freezing is an effective defense strategy for some prey, because their predators rely on visual motion to distinguish objects from their surroundings. An object moving over a background progressively covers (deletes) and uncovers (accretes) background texture while simultaneously producing discontinuities in the optic flow field. These events unambiguously specify kinetic occlusion and can produce a crisp edge, depth perception, and figure-ground segregation between identically textured surfaces -- percepts which all disappear without motion. Given two abutting regions of uniform random texture with different motion velocities, one region will appear to be situated farther away and behind the other (i.e., the ground), if its texture is accreted or deleted at the boundary between the regions, irrespective of region and boundary velocities. Consequently, a region with moving texture appears farther away than a stationary region if the boundary is stationary, but it appears closer (i.e. the figure) if the boundary is moving coherently with the moving texture. The perception of kinetic occlusion requires the detection of an unexpected onset or offset of otherwise predictably moving or stationary contrast patches. A computational model of directional selectivity in visual cells is here extended to also detect motion onsets and offsets. The connectivity of these model cells not only affords the detection of local texture accretion and deletion events but also explains results showing that human reaction times differ for motion onsets versus offsets. These theorized cells are placed into a larger computational model of visual areas V1 and V2 to show how interactions between orientation- and direction-selective cells first create a motion-defined boundary and then signal texture accretion or deletion at that boundary. A weak speed-depth bias brings faster-moving texture regions forward in depth. This is consistent with percepts: the faster of two surfaces appears closer when moving parallel to the resulting emergent boundary between them (shearing motion). Activation of model occlusion detectors tuned to a particular velocity results in the model assigning the adjacent surface with a matching velocity to the far depth. These processes together reproduce human psychophysical reports of depth ordering for a representative set of all kinetic occlusion displays.
2031-01-01

Calculating visual perception of entities in simulations requires complex intersection tests between the line of sight and the virtual world. In this study, we focus on outdoor environments which consist of a terrain and various objects located on terrain. Using hardware capabilities of graphics cards, such as occlusion queries, provides a fast method for implementing these tests. In this thesis, we introduce an approach for better load balancing of visibility detection and target acquisition calculations by the use of occlusion queries. Our results show that, the proposed approach is 1.5 to 2 times more efficient than the existing algorithms on the average.

In humans breathing is an essential behaviour for life. It is recognized that humans and animals can perceive or sense their breathing, although the actual cortical and sub cortical structures by which this occurs remains unknown. The processing of sensations presumably arise from afferent information originating from mechanoreceptors within the muscles of the upper and lower airways, lungs and chest wall. This information is integrated by the central nervous system, which leads to a perception of respiratory sensations at th~ cortex, although the specific contnbutions of these sources remain unknown. In addition, distressing respiratory sensations such as breathlessness (dyspnoea) . and hyperinflation occur in individuals exhibiting pulmonary disease, such as asthma and chronic obstructive pulmonary disease (COPD). In response to these sensations, individuals can also voluntarily or behaviourally adjust their breathing. Hence, the aim of this thesis was to investigate: (i) the modulation of respiratory related sensory activity measured from the cortex in humans, using electroencephalography in response to applications of transient inspiratory occlusions (TIas) during hyperinflation, voluntary breathing and in tracheostomy patients' who lack an upper airway and (ii) the cortical and subcortical structures mediating the response to the TIO by using functional magnetic resonance imaging (fMRI). The results of these studies show that (i) voluntary breathing modulates respiratory perception, whereas perception is unaffected in tracheostomy patients and in hyperinflated states in response to TIas; and (ii) TIas can also generate cortical and sub cortical activity specifically activating sensory - motor structures including the, primary motor cortex, primary somatosensory cortex, supplementary motor area, inferior parietal areas, thalamus and cerebellum. In conclusion, respiratory perception (i) is altered by voluntary breathing; (ii) is unaffected .in hyperinflated and tracheostomized states; and (iii) can be investigated . using fMRl through the application of TIOs.

Diverses études ont montré que l'identification des occlusives repose sur l'utilisation de nombreux et redondants indices qui sont essentiellement fournis par le bruit d'explosion et les transitions formantiques. Néanmoins, dans les systèmes de reconnaissance de la parole existants, les taux de reconnaissance des palato-vélaires en contexte antérieur et des dentales en contexte labialise ne sont pas encore satisfaisants. Cette thèse a consisté en une étude acoustico-perceptive en vue d'une meilleure compréhension et connaissance du pouvoir de discrimination du bruit d'explosion par rapport à la reconnaissance du lieu d'articulation consonantique. Cette étude est constituée de trois parties. Expériences de perception du bruit d'explosion extrait d'occlusives sourdes du français. Notre objectif était de tester les performances des auditeurs dans l'identification du lieu d'articulation consonantique indépendamment de la voyelle qui suit. Nous nous sommes tout particulièrement intéressés aux caractéristiques spectrales du bruit d'explosion et à l'effet de la connaissance explicite de la voyelle sur les performances auditives. Description acoustique des principaux indices acoustiques fournis par le bruit d'explosion. Notre but était de tester la robustesse de chacun de ces indices vis-à-vis des variations contextuelles et individuelles. Pour ce faire, nous avons développe une base de données acoustico-phonétiques multi-locuteurs contenant tous les contextes vocaliques. Mise en œuvre d'un décodeur acoustico-phonétique d'occlusives hybride intégrant les résultats obtenus dans les deux parties précédentes

Due to the natural, non-intrusive, easily collectible, widespread applicability, machine-based face recognition has received significant attention from the biometrics community over the past three decades. Compared with traditional appearance-based (2D) face recognition, shape-based (3D) face recognition is more stable to illumination variations, small head pose changes, and varying facial cosmetics. However, 3D face scans captured in unconstrained conditions may lead to various difficulties, such as non-rigid deformations caused by varying expressions, data missing due to self occlusions and external occlusions, as well as low-quality data as a result of some imperfections in the scanning technology. In order to deal with those difficulties and to be useful in real-world applications, in this thesis, we propose two 3D face recognition approaches: one is focusing on handling various expression changes, while the other one can recognize people in the presence of large facial expressions, occlusions and large pose various. In addition, we provide a provable and practical surface meshing algorithm for data-quality improvement. To deal with expression issue, we assume that different local facial region (e.g. nose, eyes) has different intra-expression/inter-expression shape variability, and thus has different importance. Based on this assumption, we design a learning strategy to find out the quantification importance of local facial regions in terms of their discriminating power. For facial description, we propose a novel shape descriptor by encoding the micro-structure of multi-channel facial normal information in multiple scales, namely, Multi-Scale and Multi-Component Local Normal Patterns (MSMC-LNP). It can comprehensively describe the local shape changes of 3D facial surfaces by a set of LNP histograms including both global and local cues. For face matching, Weighted Sparse Representation-based Classifier (W-SRC) is formulated based on the learned quantification importance and the LNP histograms. The proposed approach is evaluated on four databases: the FRGC v2.0, Bosphorus, BU-3DFE and 3D-TEC, including face scans in the presence of diverse expressions and action units, or several prototypical expressions with different intensities, or facial expression variations combine with strong facial similarities (i.e. identical twins). Extensive experimental results show that the proposed 3D face recognition approach with the use of discriminative facial descriptors can be able to deal with expression variations and perform quite accurately over all databases, and thereby has a good generalization ability. To deal with expression and data missing issues in an uniform framework, we propose a mesh-based registration free 3D face recognition approach based on a novel local facial shape descriptor and a multi-task sparse representation-based face matching process. [...]

Cette thèse traite de l’acquisition des occlusives sourdes /p t k/ et sonores /b d g/ du français par 11 locutrices taïwanaises de niveau intermédiaire à avancé. La situation de Taïwan est qualifiée de diglossique, les locuteurs parlent généralement deux langues dont les principales sont le chinois mandarin et le taïwanais. Le chinois mandarin possède les occlusives /p t k ph th kh/ tandis que le taïwanais possède les occlusives /b g p t k ph th kh/. L’analyse acoustique des logatomes CVCVCVC où C=/b d g p t k/ et V=/a i u/ révèle une grande hétérogénéité entre les locutrices : les indices des natifs du français pour opposer entre sourdes et sonores sont parfois utilisés par les non-natifs, parfois non. On note l’influence du chinois mandarin. Un test de perception révèle une moins bonne discrimination des paires de consonnes /b p/, /d t/ et /g k/ en syllabe CV si V=/a/, comparé à /i u/. Ces résultats suggèrent une tendance générale chez ces auditrices à mieux discriminer les occlusives du français lorsque le VOT des sourdes est plus long et à ne pas tenir compte du VOT négatif des voisées. En perception, les indices pour discriminer les occlusives aspirées et non-aspirées du chinois mandarin semblent ainsi également être utilisés en français. Nous n’avons pas relevé de signe d’une influence du taïwanais, où l’opposition de voisement existe cependant
This dissertation deals with the acquisition of French voiceless stops /p t k/ and voiced stops /b d g/ by 11 Taiwanese intermediate or advanced learners of L2 French. The linguistic situation in Taiwan is described as diglossia. Most speakers speak two languages, mainly Mandarin Chinese and Taiwanese. Mandarin Chinese has plosives /p t k ph th kh/ while Taiwanese has /b g p t k ph th kh/. An acoustic analysis of CVCVCVC logatoms where C = /b d g p t k/ and V = /a i u/ shows important heterogeneity among speakers. The cues used by French native speakers to oppose voiceless and voiced stops are irregularly used by non-native speakers. The influence of Mandarin Chinese is noted. A perception test shows poorer discrimination among pairs of consonants (/b p/, /d t/ and /g k/) in CV syllable when V = /a/, as compared to /i u/. The results show that non-native listeners tend to, firstly, better discriminate the voiceless plosives of French when the VOT is longer and secondly, ignore the negative VOT of voiced stops. As regards perception, the cues used in Mandarin Chinese to discriminate between aspirated and non-aspirated stops consonants seem to be used in French too. No clue to the influence of Taiwanese has been found, although the opposition of voicing exists

碩士
國立臺灣大學
資訊網路與多媒體研究所
103
We can find many interactive displays in both public and private environments. Most of these interactive displays utilize technologies such as liquid-crystal display (LCD), plasma displays or projected images. Sometimes, the depth perception of these displays is weak hence some depth cues are missing. The lake of depth perception may decrease observer’s immersion especially in some applications which require the strong depth experience. In present work, we proposed to improve depth perception of interactive display with motion parallax and occlusion. To create motion parallax effect, we tracked observer’s head position by using kinect2. Construct a 3d scene in unity3D, adapt the position of virtual camera to the head position of observer to create a head coupled or head perspective displays. In applications, we introduce two interactive displays, interactive window and interactive wall-Smiling Buddha and the reason why we enhance the depth perception of these two displays. Besides, we conduct some experiments to evaluate whether motion parallax effect actually enhance the depth perception of these two applications. The results in present work showed that motion parallax not only enhance depth perception of interactive display, but also attract observer’s more attention to the visual contents and invoke their interactive motivation.

博士
國立臺灣大學
資訊工程學研究所
107
Multi-Target tracking is a key ability for many intelligent systems in lots of applications. In order to accomplish the multi-target tracking, the measurements from the perceptive sensor plays a very important role. It is impossible to perform the multi-target tracking without sensory data especially such as occlusion situation, which increases the difficulty of the tracking task. Moreover, in the urban traffic situation, occlusion decreases the driving safety; and in the case of human joint tracking, occlusion may fails the estimates and leads to wrong judgement for evaluating the performance of rehabilitation activities. Here, two frameworks are presented and described for a stationary 2D LIDAR and for heterogeneous sensors. The first framework introduces the virtual measurement model with interacting object tracking scheme to tackle the effects of the occlusion in crowded urban environments. The second framework applies the heterogeneous sensor simultaneous localization, tracking, and modeling algorithm to fuse heterogeneous sensors and to provide estimates within occlusion for motion evaluation in stroke rehabilitation process. The ample experimental results of the first application show that the interact object tracking scheme tracks over 57% of occluded moving object for the daunting task in an urban intersection. While the results of the second application with synthetic data and collected from ten subjects reveal that the proposed approach yields 4.6 cm error in observed cases and 18.1 cm error during burst occlusion. We successfully demonstrate the capability to resolve issues and effects in occlusion for both urban and indoor environments.

Diese Dissertation untersucht motorische und kognitive Leistungen in der Kindheit am Beispiel des Erlernens einer sportlichen Fertigkeit. Dafür wurde eine Methode zur Messung mentaler Vorstellungen von Bewegungen bei Vorschulkindern entwickelt. Diese basiert auf dem Prinzip räumlicher Verdeckung. Es wurden damit sowohl verschiedene kognitive Leistungen wie die Wahrnehmung und Vorstellung von Bewegungen miteinander verglichen als auch in Beziehung zum Bewegungslernen gesetzt. Außerdem wurde in einer quasi-experimentellen Studie u.a. der Einfluss von Erfahrung, Geschlecht und Versuchsbedingung auf Wahrnehmungs- und Vorstellungsleistungen per Experten-Novizen-Paradigma untersucht. Es wurde geschlussfolgert, dass die Methode hinsichtlich des Geschlechts auch in jungen Jahren differenziert. Das bedeutet, dass Mädchen und Jungen im Vorschulalter möglicherweise unterschiedlich bei der Lösung der Aufgaben vorgehen. Damit kann die Methode - im Gegensatz zur Methode der Mentalen Rotation - auch für die Diagnostik von Vorstellungen von Bewegungen ab einem Alter von 4 Jahren eingesetzt werden.