Loading...
Please wait, while we are loading the content...
Similar Documents
Electronic Letters on Computer Vision and Image Analysis 6(3):30-41, 2007 Intelligent CCTV for Mass Transport Security: Challenges and Opportunities for Video and Face Processing (2000)
| Content Provider | CiteSeerX |
|---|---|
| Author | Berglund, Erik Chen, Shaokang Shan, Ting Lovell, Brian C. Conrad, S. Bigdeli, Abbas |
| Abstract | CCTV surveillance systems have long been promoted as being effective in improving public safety. However due to the amount of cameras installed, many sites have abandoned expensive human monitoring and only record video for forensic purposes. One of the sought-after capabilities of an automated surveil-lance system is “face in the crowd ” recognition, in public spaces such as mass transit centres. Apart from accuracy and robustness to nuisance factors such as pose variations, in such surveillance situations the other important factors are scalability and fast performance. We evaluate recent approaches to the recognition of faces at large pose angles from a gallery of frontal images and propose novel adaptations as well as mod-ifications. We compare and contrast the accuracy, robustness and speed of an Active Appearance Model (AAM) based method (where realistic frontal faces are synthesized from non-frontal probe faces) against bag-of-features methods. We show a novel approach where the performance of the AAM based technique is increased by side-stepping the image synthesis step, also resulting in a considerable speedup. Addition-ally, we adapt a histogram-based bag-of-features technique to face classification and contrast its properties to a previously proposed direct bag-of-features method. We further show that the two bag-of-features ap-proaches can be considerably sped up, without a loss in classification accuracy, via an approximation of the |
| File Format | |
| Publisher Date | 2000-01-01 |
| Access Restriction | Open |
| Subject Keyword | Surveillance Situation Novel Adaptation Surveil-lance System Forensic Purpose Histogram-based Bag-of-features Technique Considerable Speedup Fast Performance Active Appearance Model Many Site Mass Transport Security Direct Bag-of-features Method Intelligent Cctv Record Video Non-frontal Probe Frontal Image Pose Variation Bag-of-features Method Realistic Frontal Mass Transit Centre Public Safety Face Processing Bag-of-features Ap-proaches Expensive Human Monitoring Electronic Letter Crowd Recognition Image Synthesis Step Sought-after Capability Cctv Surveillance System Large Pose Angle |
| Content Type | Text |
