國立虎尾科技大學 |

Face Recognition in Video Surveillance from a Single Reference Sample Through Domain Adaptation = = Reconnaissance de visages en videosurveillance a partir d'un echantillon de reference unique a par l'adaptation de domaine.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Face Recognition in Video Surveillance from a Single Reference Sample Through Domain Adaptation =/
其他題名:	Reconnaissance de visages en videosurveillance a partir d'un echantillon de reference unique a par l'adaptation de domaine.
其他題名:	Reconnaissance de visages en videosurveillance a partir d'un echantillon de reference unique a par l'adaptation de domaine.
作者:	Bashbaghi, Saman.
面頁冊數:	1 online resource (175 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
Contained By:	Dissertation Abstracts International79-08B(E).
標題:	Artificial intelligence. -
電子資源:	click for full text (PQDT)
ISBN:	9780355811803

Face Recognition in Video Surveillance from a Single Reference Sample Through Domain Adaptation = = Reconnaissance de visages en videosurveillance a partir d'un echantillon de reference unique a par l'adaptation de domaine.
Bashbaghi, Saman.

Face Recognition in Video Surveillance from a Single Reference Sample Through Domain Adaptation =Reconnaissance de visages en videosurveillance a partir d'un echantillon de reference unique a par l'adaptation de domaine.Reconnaissance de visages en videosurveillance a partir d'un echantillon de reference unique a par l'adaptation de domaine. - 1 online resource (175 pages)

Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.

Thesis (D.Eng.)--Ecole de Technologie Superieure (Canada), 2017.

Includes bibliographical references

Face recognition (FR) has received significant attention during the past decades in many applications, such as law enforcement, forensics, access controls, information security and video surveillance (VS), due to its covert and non-intrusive nature. FR systems specialized for VS seek to accurately detect the presence of target individuals of interest over a distributed network of video cameras under uncontrolled capture conditions. Therefore, recognizing faces of target individuals in such environment is a challenging problem because the appearance of faces varies due to changes in pose, scale, illumination, occlusion, blur, etc. The computational complexity is also an important consideration because of the growing number of cameras, and the processing time of state-of-the-art face detection, tracking and matching algorithms.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355811803Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

Face Recognition in Video Surveillance from a Single Reference Sample Through Domain Adaptation = = Reconnaissance de visages en videosurveillance a partir d'un echantillon de reference unique a par l'adaptation de domaine.
LDR:06790ntm a2200385Ki 4500 001 916877
005 20180928111502.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355811803
035 $a (MiAaPQ)AAI10752469
035 $a (MiAaPQ)etsmh:11001
035 $a AAI10752469
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Bashbaghi, Saman. $3 1190737
245 1 0 $a Face Recognition in Video Surveillance from a Single Reference Sample Through Domain Adaptation = $b Reconnaissance de visages en videosurveillance a partir d'un echantillon de reference unique a par l'adaptation de domaine.
246 3 1 $a Reconnaissance de visages en videosurveillance a partir d'un echantillon de reference unique a par l'adaptation de domaine.
264 0 $c 2017
300 $a 1 online resource (175 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
500 $a Advisers: Eric Granger; Robert Sabourin.
502 $a Thesis (D.Eng.)--Ecole de Technologie Superieure (Canada), 2017.
504 $a Includes bibliographical references
520 $a Face recognition (FR) has received significant attention during the past decades in many applications, such as law enforcement, forensics, access controls, information security and video surveillance (VS), due to its covert and non-intrusive nature. FR systems specialized for VS seek to accurately detect the presence of target individuals of interest over a distributed network of video cameras under uncontrolled capture conditions. Therefore, recognizing faces of target individuals in such environment is a challenging problem because the appearance of faces varies due to changes in pose, scale, illumination, occlusion, blur, etc. The computational complexity is also an important consideration because of the growing number of cameras, and the processing time of state-of-the-art face detection, tracking and matching algorithms.
520 $a In this thesis, adaptive systems are proposed for accurate still-to-video FR, where a single (or very few) reference still or a mug-shot is available to design a facial model for the target individual. This is a common situation in real-world watch-list screening applications due to the cost and feasibility of capturing reference stills, and managing facial models over time. The limited number of reference stills can adversely affect the robustness of facial models to intra-class variations, and therefore the performance of still-to-video FR systems. Moreover, a specific challenge in still-to-video FR is the shift between the enrollment domain, where high-quality reference faces are captured under controlled conditions from still cameras, and the operational domain, where faces are captured with video cameras under uncontrolled conditions. To overcome the challenges of such single sample per person (SSPP) problems, 3 new systems are proposed for accurate still-to-video FR that are based on multiple face representations and domain adaptation. In particular, this thesis presents 3 contributions. These contributions are described with more details in the following statements.
520 $a In Chapter 3, a multi-classifier framework is proposed for robust still-to-video FR based on multiple and diverse face representations of a single reference face still. During enrollment of a target individual, the single reference face still is modeled using an ensemble of SVM classifiers based on different patches and face descriptors. Multiple feature extraction techniques are applied to patches isolated in the reference still to generate a diverse SVM pool that provides robustness to common nuisance factors (e.g., variations in illumination and pose). The estimation of discriminant feature subsets, classifier parameters, decision thresholds, and ensemble fusion functions is achieved using the high-quality reference still and a large number of faces captured in lower quality video of non-target individuals in the scene. During operations, the most competent subset of SVMs are dynamically selected according to capture conditions. Finally, a head-face tracker gradually regroups faces captured from different people appearing in a scene, while each individual-specific ensemble performs face matching. The accumulation of matching scores per face track leads to a robust spatio-temporal FR when accumulated ensemble scores surpass a detection threshold. Experimental results obtained with the Chokepoint and COX-S2V datasets show a significant improvement in performance w.r.t. reference systems, especially when individual-specific ensembles (1) are designed using exemplar-SVMs rather than one-class SVMs, and (2) exploit score-level fusion of local SVMs (trained using features extracted from each patch), rather than using either decision-level or feature-level fusion with a global SVM (trained by concatenating features extracted from patches).
520 $a In Chapter 4, an efficient multi-classifier system (MCS) is proposed for accurate still-to-video FR based on multiple face representations and domain adaptation (DA). An individual-specific ensemble of exemplar-SVM (e-SVM) classifiers is thereby designed to improve robustness to intra-class variations. During enrollment of a target individual, an ensemble is used to model the single reference still, where multiple face descriptors and random feature subspaces allow to generate a diverse pool of patch-wise classifiers. To adapt these ensembles to the operational domains, e-SVMs are trained using labeled face patches extracted from the reference still versus patches extracted from cohort and other non-target stills mixed with unlabeled patches extracted from the corresponding face trajectories captured with surveillance cameras. During operations, the most competent classifiers per given probe face are dynamically selected and weighted based on the internal criteria determined in the feature space of e-SVMs. This chapter also investigates the impact of using different training schemes for DA, as well as, the validation set of non-target faces extracted from stills and video trajectories of unknown individuals in the operational domain. The results indicate that the proposed system can surpass state-of-the-art accuracy, yet with a significantly lower computational complexity...
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Computer engineering. $3 569006
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Ecole de Technologie Superieure (Canada). $b Departement de genie de la production automatisee. $3 1179220
773 0 $t Dissertation Abstracts International $g 79-08B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10752469 $z click for full text (PQDT)