Abstract:
In this paper, we proposes a novel tracking algorithm combining Kalman Filter with mean-shift. Kalman Filter predicts the vehicle position in the next frame. Mean-shift f...View moreMetadata
Abstract:
In this paper, we proposes a novel tracking algorithm combining Kalman Filter with mean-shift. Kalman Filter predicts the vehicle position in the next frame. Mean-shift finds the best candidate which has maximum similarity with the tracked vehicle in the predicted area. Kalman Filter updates its state value of vehicle position with the position of the best candidate from the mean-shift tracker. As a result, the proposed algorithm tracks the vehicle without local maximum problem of mean-shift tracker. The proposed algorithm is very fast because it does not perform the redetection process, and it has no detection misses because it finds the best candidate which has maximum similarity with the tracked vehicle in the predicted area. Also, the proposed algorithm has deleting and adding policies for the tracking list management. If a vehicle was consecutively detected in the previous frames, the proposed algorithm assumes that the vehicle exists although the vehicle is not detected in the predicted region at the current frame. If a vehicle was not detected in the previous frames consecutively, the proposed algorithm assumes that the vehicle does not exist although the vehicle is detected in the current frame. We evaluated the performance of the proposed algorithm in terms of processing time and detection ratio. At target board, the proposed algorithm has 40 frames per second, which meets the real time requirements of the ADAS systems. The detection ratio and processing time of the proposed algorithm outperformed our former work.
Date of Conference: 05-08 July 2016
Date Added to IEEE Xplore: 11 August 2016
ISBN Information:
Electronic ISSN: 2165-8536