Six object tracking algorithms: A comparative study

To compare five different objects tracking algorithms performance wise with the proposed algorithm and to find out the best one among them for tracking of an object in occlusion and Background clutter condition i.e. when background contains target features. Methods/Analysis: In the proposed algorithm, the object’s position is obtained by Mean Shift tracking and then the prediction of object’s position is done through Kalman Filter. The Proposed method has Kalman Filter which consists of an adaptive system matrix and adaptive process error covariance and measurement error covariance matrices respectively. Adaptive system matrix of Kalman Filter is getting updated online depending on the quality of observation by Mean Shift algorithm and adaptive process and measurement noise covariance matrices are getting updated according to the variation in Bhattacharya Coefficient respectively. Findings: Proposed algorithm has a maximum value (0.2177 and 0.4821) of tracking efficiency metric i.e. Bhattacharya Coefficient in both video dataset among all the algorithms and it is taking less execution time (0.002761 sec and 0.005431 sec) than other Kalman filter based tracking algorithms. Applications/Improvements: Proposed algorithm is able to track the target in occlusion and background variation condition with more efficiency and less execution time than rest of the algorithms