Abstract:
Increasing use of CCTV for city and building surveillance has given rise to an environment where an object (a
person) might traverse through the field of vi>vv of many cameras. In this paper we explore the problem of tracking
multiple objects in a multi camera environment, which is a highly addressed area in computer vision. Our research
involves real time tracking of objects while they are moving in a multi camera environment with non-overlapping
field of v/ewjr and detecting them when they re-uppear in the same or another camera in the same system. Previous
methods of using offline trained classifiers with huge databases are time consuming and have the drawback of
incapability of detecting arbitrarily selected objects. We address this issue by online training with the initial sample
given and is based on the TLD (Tracking, Learning, Detection) framework. We extend the idea to formulate our
methodology to create a framework that can track multiple objects in multiple video streams in real time. We have
developed upper layers as a thread based architecture in order to incorporate multiple video feeds and to handle
multiple objects. We have integrated CUDA (Computer Unified Device Architecture) programming model to add
parallelism to independent processes and execute compute intensive algorithms. GPU computing offers an ideal
computing environment to improve our framework. Our optimization of the algorithms, careful usage of parallel
computing and proper utilization of GPU resources have contributed in achieving a processing time of less than
60ms for multi objects in multi camera environment.
