Expert video-surveillance system for real-time detection of suspicious behaviors in shopping malls
作者：
Highlights：
• Tracking-by-detection based on segmentation, Kalman predictions and LSAP association.
• Occlusion management: SVM kernel metric for GCH + LBP + HOG image features.
• Overall performance near to 85% while tracking under occlusions in CAVIAR dataset.
• Human behavior analysis (exits, loitering, etc.) in naturalistic scenes in shops.
• Real-time multi-camera performance with a processing capacity near to 50 fps/camera.
摘要
•Tracking-by-detection based on segmentation, Kalman predictions and LSAP association.•Occlusion management: SVM kernel metric for GCH + LBP + HOG image features.•Overall performance near to 85% while tracking under occlusions in CAVIAR dataset.•Human behavior analysis (exits, loitering, etc.) in naturalistic scenes in shops.•Real-time multi-camera performance with a processing capacity near to 50 fps/camera.
论文关键词：Video-surveillance in shopping malls,Background subtraction,Human tracking,Occlusion management,Appearance features,Behavioral analysis
论文评审过程：Available online 19 June 2015, Version of Record 6 July 2015.
论文官网地址：https://doi.org/10.1016/j.eswa.2015.06.016
