Face Tracking and Recognition in Video

Chellappa, Rama; Du, Ming; Turaga, Pavan; Zhou, S. Kevin

doi:10.1007/978-0-85729-932-1_13

Cited by 20 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use one as gallery and the rest as probes. This database is double the size of its previous versions [58] [59] in terms of the number of videos. To test the robustness of our recognition system, we have arranged the time span that separated the sessions to be up to 6 months.…”

Section: Video-based Recognitionmentioning

confidence: 99%

Robust Face Recognition From Multi-View Videos

Sankaranarayanan

Chellappa

2014

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Abstract-Multi-view face recognition has become an active research area in the last few years. In this paper, we present an approach for video-based face recognition in camera networks. Our goal is to handle pose variations by exploiting the redundancy in multi-view video data. However, unlike traditional approaches that explicitly estimate the pose of the face, we propose a novel feature for robust face recognition in the presence of diffuse lighting and pose variations. The proposed feature is developed using the spherical harmonic representation of the face texture-mapped onto a sphere; the texture map itself is generated by back-projecting the multi-view video data. Video plays an important role in this scenario. First, it provides an automatic and efficient way for feature extraction. Second, the data redundancy renders the recognition algorithm more robust. We measure the similarity between feature sets from different videos using the Reproducing Kernel Hilbert Space. We demonstrate that the proposed approach outperforms traditional algorithms on a multi-view video database.

show abstract

Section: Video-based Recognitionmentioning

confidence: 99%

Robust Face Recognition From Multi-View Videos

Sankaranarayanan

Chellappa

2014

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Accurate and timely responses are required to recognize faces captured under semi-controlled and uncontrolled conditions, as found at various security checkpoints, inspection lanes, portals, etc. Faces captured under these conditions are subject to a variety of nuisance factors, including changes in illumination, pose, scale, expression, occlusion, and blur [2], and to camera interoperability issues. Despite these challenges, it is generally possible to exploit spatiotemporal information (e.g., tracking and multi-frame fusion) and camera arrays to improve robustness and accuracy in VS applications [1].…”

Section: Introductionmentioning

confidence: 99%

“…Spatiotemporal FR systems rely on tracking to capture temporal information, and have been shown to improved performance over the traditional FR systems in VS [1,2]. Face tracking (FT) can play two important functions in video FR -(1) regroup ROIs of a person and integrate evidence (e.g., matching scores) from each frame and from multiple cameras of a video stream in order to reduce ambiguity of predictions [1,2]; (2) confirm the detection of highly confident facial regions in a frame for the segmentation process [10].…”

Section: Introductionmentioning

confidence: 99%

“…Face tracking (FT) can play two important functions in video FR -(1) regroup ROIs of a person and integrate evidence (e.g., matching scores) from each frame and from multiple cameras of a video stream in order to reduce ambiguity of predictions [1,2]; (2) confirm the detection of highly confident facial regions in a frame for the segmentation process [10]. Though many algorithms have been proposed for object tracking in general, ones based on adaptive appearance modeling are well suited for FT.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive appearance model tracking for still-to-video face recognition

Dewan

Granger

Marcialis

et al. 2016

Pattern Recognition

View full text Add to dashboard Cite

Systems for still-to-video face recognition (FR) seek to detect the presence of target individuals based on reference facial still images or mug-shots. These systems encounter several challenges in video surveillance applications due to variations in capture conditions (e.g., pose, scale, illumination, blur and expression) and to camera inter-operability. Beyond these issues, few reference stills are available during enrollment to design representative facial models of target individuals. Systems for still-to-video FR must therefore rely on adaptation, multiple face representation, or synthetic generation of reference stills to enhance the intra-class variability of face models. Moreover, many FR systems only match high quality faces captured in video, which further reduces the probability of detecting target individuals. Instead of matching faces captured through segmentation to reference stills, this paper exploits Adaptive Appearance Model Tracking (AAMT) to gradually learn a track-face-model for each individual appearing in the scene. The Sequential Karhunen-Loeve technique is used for online learning of these track-face-models within a particle filter-based face tracker. Meanwhile, these models are matched over successive frames against the reference still images of each target individual enrolled to the system, and then matching scores are accumulated over several frames for robust spatiotemporal recognition. A target individual is recognized if scores accumulated for a track-face-model over a fixed time surpass some decision threshold. The main advantage of AAMT over traditional still-to-video FR systems is the greater diversity of facial representation that may be captured during operations, and this can lead to better discrimination for spatiotemporal recognition. Compared to state-of-the-art adaptive biometric systems, the proposed method selects facial captures to update an individual's face model more reliably because it relies on information from tracking. Simulation results obtained with the Chokepoint video dataset indicate that the proposed method provides a significantly higher level of performance compared state-of-the-art systems when a single reference still per individual is available for matching. This higher level of performance is achieved when the diverse facial appearances that are captured in video through AAMT correspond to that of reference stills.

show abstract

“…It is used to locate and follow faces of different individuals in motion, and regroup the facial information for spatiotemporal face recognition. This information is useful to generate reliable facial models; mitigate effects of non-cooperative capture conditions; model facial behaviour; generate better facial models from multiple views; and accumulate decision on multiple frames to achieve improved recognition [1]. However, variations in pose, scale, expression, and illumination, and the occlusions in cluttered scenes can degrade tracking performance.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Adaptive Appearance Methods for Tracking Faces in Video Surveillance

Dewan

Granger

Roli

et al. 2013

5th International Conference on Imaging for Crime Detection and Prevention (ICDP 2013)

View full text Add to dashboard Cite

Face recognition is increasingly employed by public safety organizations in decision support systems for video surveillance, to detect the presence of individuals of interest. In the context of spatiotemporal face recognition, tracking is an important function used to locate, follow and regroup faces of different individuals in a scene. Techniques for face tracking in video surveillance should be robust to changes in pose, expression and illumination, as well as occlusion in cluttered scenes. Given these challenges, trackers based on adaptive appearance modelling (AAM) typically improve target's state estimation because they initiate and update an internal face model per individual according to changes in facial appearance. In this paper, the performance of three AAM trackers -Incremental Visual Tracking (IVT), Tracking Learning Detection (TLD) and Discriminative Sparse Coding based Tracking (DSCT) -are compared for face tracking with video surveillance applications in mind. These methods are evaluated according to area overlap error, tracking error and time complexity using Chokepoint videos collected in uncontrolled video-surveillance environments, where individuals walk through portals. Results indicate that IVT outperforms the others in its ability to accurately track faces in the presence of occlusion, and under variations in pose, scale and lighting. Further characterization of IVT indicates that using a small batch size and forgetting factor during update provide better tracking accuracy when face tracks changes in their capture conditions. When conditions change more gradually, IVT benefits from assessing facial quality before updating face models.

show abstract

Face Tracking and Recognition in Video

Cited by 20 publications

References 26 publications

Robust Face Recognition From Multi-View Videos

Robust Face Recognition From Multi-View Videos

Adaptive appearance model tracking for still-to-video face recognition

A Comparison of Adaptive Appearance Methods for Tracking Faces in Video Surveillance

Contact Info

Product

Resources

About