This paper proposes an object-tracking algorithm with multiple randomlygenerated\nfeatures. We mainly improve the tracking performance which is\nsometimes good and sometimes bad in compressive tracking. In compressive\ntracking, the image features are generated by random projection. The resulting\nimage features are affected by the random numbers so that the results of\neach execution are different. If the obvious features of the target are not captured,\nthe tracker is likely to fail. Therefore the tracking results are inconsistent\nfor each execution. The proposed algorithm uses a number of different\nimage features to track, and chooses the best tracking result by measuring the\nsimilarity with the target model. It reduces the chances to determine the target\nlocation by the poor image features. In this paper, we use the Bhattacharyya\ncoefficient to choose the best tracking result. The experimental results show\nthat the proposed tracking algorithm can greatly reduce the tracking errors.\nThe best performance improvements in terms of center location error,\nbounding box overlap ratio and success rate are from 63.62 pixels to 15.45\npixels, from 31.75% to 64.48% and from 38.51% to 82.58%, respectively.
Loading....