双重背景感知相关滤波算法

Dual background-aware correlation filtering algorithm

针对传统的判别式核相关滤波器在相似背景下导致跟踪失败的问题,提出了一种双重背景感知相关滤波算法。该算法依据背景感知相关滤波算法对目标及背景信息进行建模;并在此基础上,通过提取目标周围背景信息作为负样本,将其加入到跟踪器的学习中去,从而对背景信息进行抑制,增大目标与背景的区分性,进一步提高算法对目标检测的准确性。在OTB100公开视频序列上与6种当前主流跟踪算法进行对比实验,所提算法的跟踪精度和成功率分别为84.2%和63.4%,相比于其它算法表现出了较好的准确性。所提算法能够很好的应对复杂环境下的跟踪任务,具有较高的鲁棒性。

In order to solve the problem of tracking failure caused by traditional discriminating kernel correlation filter under similar background,this paper proposes a dual background-aware correlation filter algorithm.The algorithm models the target and the background information according to the background-aware correlation filter algorithm.On this basis,the background information around the target is extracted as a negative sample and added to the learning of the tracker,so as to suppress the background information,increase the distinction between the target and the background,and further improve the accuracy of the algorithm in target detection.Comparison experiment was conducted between the public video sequence OTB100 and 6 current mainstream tracking algorithms.The tracking accuracy and success rate of the proposed algorithm were 84.2%and 63.4%respectively,which shows better accuracy compared with other algorithms.The proposed algorithm can deal with the tracking task under the complex environment well and has high robustness.