Surveillance video analytics for large camera networks

Abstract

Extensive networks of surveillance cameras are increasingly deployed in public and private facilities, with tremendous potential value for safety and security. However, because manual monitoring of large numbers of video sources is not feasible, surveillance imagery is often simply directed to massstorage devices, to be used only forensically and for data mining. On-line computer-based video analysis represents an alternative to this traditional approach. This new paradigm continually apprises security personnel of who is on site, where they are, and what they are doing. It offers the prospect of increased productivity and highly advanced sitewide security. Our approach to video analytics for security starts by establishing camera geometry. We determine the relative location of each camera with respect to a world coordinate system, and so can readily coordinate observations from different cameras. The next step is to detect people under a variety of imaging conditions, including both crowds and situations with dynamic backgrounds. Reliable detection of individuals on a frame-by-frame basis enables tracking over time. However, gaps in camera coverage require reacquisition of individuals to be tracked as they move between discontinuous regions of coverage. In our work with automatic camera calibration, we assume a dominant ground plane and, further, that people walking on it are of some nominal height. We have shown that—even in the presence of significant noise—camera position, orientation, and focal length can be estimated by simple observation of individuals walking on site.1 If the background is relatively static, moving foreground objects can be detected and classified as either human or non-human.2 Where such foregroundbackground segmentation is not possible, methods can be employed to continually scan an image for persons.3Wehave found Figure 1. Observations of individuals enable automatic estimates of focal length, camera height, pan and tilt angles.