OBJECT TRACKING IN PANORAMIC IMAGES

Abstract

Computer vision needs to play its role to lessen the burden of security problems. Image tracking over critical areas will help a lot in that regard. A lot of work has already been done on image tracking but the problem is with speed processing of images. We used such algorithms that will not only provide fast tracking but also greater field of view. One main consideration lies with the use of hardware, for that we have tested our both algorithms on several machines with different operating system. The fastest and accurate result was produced with beagle board under Linux Angstrom. Uniqueness of work lies in introduction of tracking over stitched images which will increase the view of environment being processed though cameras.