Human detection and tracking over camera networks: A review

Abstract

Achieving precise and robust human detection and tracking over camera networks is a very challenging task in the research of intelligent video surveillance. Its difficulties mainly result from abrupt human object motion, object occlusion and object scale change, and changing object appearance due to changes in illumination and viewpoint, non-rigid deformations, intra-class variability in shape and posture, and potential camera movement, non-overlapping field of views between cameras. This paper surveys the frameworks of human detection and tracking systems over camera networks with non-overlapping field of views. There are three crucial functional modules discussed in this survey paper, namely, human detection under a single camera, human tracking under a single camera as well as human tracking across multiple cameras with non-overlapping field of views. Existing problems, challenges and future research directions are also addressed based on the analyses of the research status of each function module.