马聪杰,何秋生,孙宏,刘思超

• 1:太原科技大学电子信息工程学院

摘要(Abstract)：

针对目标发生快速移动导致跟踪精度不高甚至跟踪失败的情况，研究了一种改进ECO-HC的目标跟踪算法。首先，将不同的图像目标尺寸进行缩放以确定目标搜索区域，从而计算得到初始标度下的目标尺寸大小。其次，提取图像目标的HOG特征和CN特征并进行融合，将融合后的目标特征进行降维并加入样本空间模型。然后，提出一种扩充样本块的更新策略，对滤波响应函数进行优化，完成跟踪过程。最后，在OTB100标准数据集上进行实验验证，并与其他相关滤波类算法进行对比。实验结果表明：算法的跟踪精度为87.0%,跟踪成功率为65.3%,均优于其他算法。

关键词(KeyWords)： 目标跟踪;特征融合;样本空间模型

Abstract:

Keywords:

基金项目(Foundation): 山西省研究生教育改革研究课题(2019JG175);; 山西省研究生教育创新项目(2020SY421)

作者(Author): 马聪杰,何秋生,孙宏,刘思超

参考文献(References)：

• [1] 张可，杨灿坤，周春平，等.无人机视频图像运动目标检测算法综述[J].液晶与显示，2019,34(1):98-109.
• [2] 孟晓燕，段建民.基于相关滤波的目标跟踪算法研究综述[J].北京工业大学学报，2020,46(12):83-106.
• [3] HENRIQUES J F,CASEIROR,MARTINS P,et al.High-speed tracking with kernelized correlation filters[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(3):583-596.
• [4] HENRIQUES J F,CASEIRO R,MARTINS P,et al.Exploiting the circulant structure of Tracking-by-Detection with Kernels[C]//Proceedings of the 2012 European Conference on Computer Vision.Berlin,Germany:Springer,2012:702-715.
• [5] DANELLJIAN M,KHAN F S,FELSBERG M,et al.Adaptive color attributes for real-time visual tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2014:1090-1097.
• [6] LI Y,ZHU J.A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration[C]//Proceedings of the 2014 European Conference on Computer Vision,Zurich,Switzerland,September,2014:254-265.
• [7] DANELLJAN M,H GER G,KHAN F S,et al.Learning Spatially Regularized Correlation Filters for Visual Tracking[C]// Proceedings of the IEEE International Conference on Computer Vision.Washing-ton,USA:IEEE,2015:4310-4318.
• [8] DANELLJAN M,BHAT G,KHAN F S,et al.ECO:Efficient Convolution Operators for Tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Hawaii,USA:IEEE,2017:21-26.
• [9] LUKEZIC A,VOJIR T,CEHOVIN L,MATAS J,et al.Discriminative Correlation Filter Tracker with Channel and Spatial Reliability[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2017:4847-4856.
• [10] LIN T L .Regularized Background Adaptation:A Novel Learning Rate Control Scheme for Gaussian Mixture Modeling[J].Image Processing,IEEE Transactions on,2011,20(3):822-836.
• [11] WU Y ,LIM J ,YANG M H .Object Tracking Benchmark[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,37(9):1834-1848.
• [12] DANELLJAN M,H GER G,KHAN F S,et al.Learning Spatially Regularized Correlation Filters for Visual Tracking[C]// Proceedings of the IEEE International Conference on Computer Vision.Washing-ton,USA:IEEE,2015:4310-4318.
• [13] CHAO M,YANG X,ZHANG C,et al.Long-term correlation tracking[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Hawaii,USA:IEEE,2015:863-874.
• [14] BERTINETTO L,VALMADRE J,GULODETZ S,et al.Staple:Complementary Learners for Real-time Tracking[C]// Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition.Washing-ton,USA:IEEE,2016:1401-1409.
• [15] WANG M,LIU Y,HUANG Z.Large Margin Object Tracking with Circulant Feature Maps[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Hawaii,USA:IEEE,2017:2437-2446.
• [16] DANELLJAN M,HAGER,GUSTAV,et al.Adaptive Decontamination of the Training Set:A Unified Formulation for Discriminative Visual Tracking[J].2016,25(2):423-436.