Rating Whole-Body Suspiciousness Factors in Automated Surveillance of a Public Area
Rowe, Neil C.
Chan, Alex L.
MetadataShow full item record
We tested clues to automated detection of suspicious behavior of pedestrians in image sequences of 71,236 images in 106 sequences, developed at the U.S. Army Research Laboratory for testing surveillance systems. We achieved a 66% success rate at identifying suspicious behavior on infrared video and 64% on color video using just clues obtained from the overall body motion without attempting to classify further what people were doing. We used seven clues including the norm of the acceleration vector as measured at different granularities, atypicality of location, speed, atypicality of the velocity vector with historical data, relative size of the object, length of the track, and "contagion" from nearby suspicious tracks. The acceleration norm averaged over different time scales significantly outperformed the other clues on the dataset, and our conclusion is that it should be the primary focus of systems assessing suspicious behavior in video.
This paper appeared in the 2011 Intl. Conf. on Image Processing, Computer Vision, and Pattern Recognition, Las Vegas, NV, July 2011.
Showing items related by title, author, creator and subject.
Schaub, Erika Ann; Darken, Christian J. (2007);Sociological models (e.g., social network analysis, small-group dynamics and gang models) have historically been used to predict the behavior of terrorist groups. However, they may not be the most appropriate method for ...
Boundary conditions of the emotional exhaustion-unsafe behavior link: the dark side of group norms and personal control Ju, Dong; Qin, Xin; Xu, Minya; DiRenzo, Marco S. (Springer, 2016);This study focuses on the conditions under which emotional exhaustion leads to employee unsafe behavior. In a sample of 592 construction workers nested in 33 groups, we found that both emotional exhaustion and unsafe ...
Auguston, Mikhail; Whitcomb, Clifford; Giammarco, Kristin (2012-10-10);This paper suggests a new approach to formal system and software architecture specification based on behavior models. The behavior of the system is defined as a set of events (event trace) with two basic relations: precedence ...