Motion based vehicle surround analysis using an omni-directional camera

Omni-directional cameras which give 360 degree panoramic view of the surroundings and have recently been used in many applications such as robotics, navigation and surveillance. This paper describes the application of motion estimation on omni camera to perform surround analysis using an automobile mounted camera. The system detects and tracks the surrounding vehicles by compensating the ego-motion and detecting objects having independent motion. Prior knowledge about ego-motion and calibration is optimally combined with the information from the image gradients to get better motion compensation.