自适应内容感知空间正则化相关滤波跟踪算法

Adaptive content aware spatially-regularized correlation filter for object tracking

为解决相关滤波跟踪算法循环移位采样产生的边界效应,提高跟踪性能,本文提出了一种自适应内容感知空间正则化相关滤波算法。首先,提取真实的背景区域作为负样本训练滤波器,降低目标区域循环移位生成的假负样本所引起的滤波器退化问题;其次,提取目标区域的局部敏感直方图特征作为前景特征,并与空间正则化项结合,根据不同目标的外观动态更新空间正则化权值;再次,采用交替方向乘子法优化求解,将模型的优化问题分解为两个子问题,并在迭代中结合动态局部敏感直方图特征求解子问题的最优解;最后,在5个公开基准数据集上对算法进行评估。实验结果表明,本文方法在OTB50数据集上的精确率和成功率分别为90.3%和66.1%,超过其他相关滤波算法;在OTB100数据集上的精确率和成功率分别为92.2%和69.2%,其中精确率在所有算法中排名第一,成功率则领先其他相关滤波算法。

In order to solve the annoying boundary effects in correlation filter(CF)trackers induced by cyclic shift when sampling training patches,and improve the tracking performance,an adaptive content aware spatially regularized correlation filter(ACSRCF)is proposed.Firstly,real negative samples are generated from the background area around the target object,so as to alleviate the filter degradation induced by the fake negative samples generated from the circularly shifted object patches.Secondly,the locality sensitive histogram(LSH)based foreground feature is extracted and incorporated with the spatial regularization weight which is updated adaptively according to the varied object-oriented appearances.Thirdly,the CF model is optimized using the alternative direction method of multipliers(ADMM)in which the model is decomposed into two sub-problems and the LSH-based features are used in iteration for obtaining the optimal solutions.Finally,the proposed method is evaluated on 5 public benchmark datasets.The experimental results show that the accuracy and success rate scores of our method on OTB50 dataset are 90.3% and 66.1%,respectively,exceeding the other CF trackers.The data on the OTB100 dataset are 92.2% and 69.2%,and the accuracy ranks first among all the trackers,while the success rate is ahead of other CF trackers.