计算机科学 ›› 2016, Vol. 43 ›› Issue (Z11): 201-204.doi: 10.11896/j.issn.1002-137X.2016.11A.045
张润东,张凤元
ZHANG Run-dong and ZHANG Feng-yuan
摘要： 相关核滤波器跟踪是工程实际中非常实用的跟踪算法,它的算法简单,只需要在下一帧进行一个样本的密集采样就能对目标进行跟踪,但是对于有尺度变化的目标跟踪的适用性不足。采用了尺度补偿的相关核滤波器跟踪算法,对相关核滤波器跟踪进行了改进。首先使用了点跟踪补偿机制对相关核滤波器尺度和位移进行补偿；其次采用了压缩感知提取的特征建立模板对目标进行建模,在关键帧进行目标的重检测来防止尺度估计带来的跟踪误差。通过实验对提出的算法进行了标准视频库的测试,并在中心点误差和实际跟踪覆盖率两个指标上与原算法进行了对比分析。实验结果表明,提出的具有尺度补偿的跟踪算法提高了相关核滤波器跟踪在有尺度属性变化视频序列中的准确率和实用性。
| [1] Comaniciu D,Ramesh V,Meer P.Real-time tracking of non-rigid objects using mean shift[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2000.IEEE,2000:142-149 [2] Zhang Kai-hua,Zhang Lei,Yang M S.Real-time compressivetracking [C]∥Proc of 12th European Conference on Computer Vision.2012:864-877 [3] Zhang Kai-hua,Zhang Lei,Yang M H.Fast Compressive Trac-king[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,6(10):2002-2015 [4] Henriques J F,Caseiro R,Martins P,et al.High-Speed Trackingwith Kernelized Correlation Filters[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(3):583-596 [5] Grabner H,Bischof H.On-line Boosting and Vision[C]∥2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2006:260-267 [6] Kalal Z,Mikolajczyk K,Matas J.Tracking-Learning-Detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,4(7):1409-1422 [7] Babenko B,Yang M H,Belongie S.Visual Tracking with Online Multiple Instance Learning[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2009:983-990 [8] Nummiaro K,Koller-Meier E,Van Gool L.An adaptive color-based particle filter[J].Image and Vision Computing,2003,1(1):99-110 [9] Hare S,Saffari A,Torr P H S.Struck:Structured Output Tr-acking with Kernels[J].IEEE International Conference on Computer Vision,2011,23(5):263-270 [10] Zhang Jian-ming,Ma Shu-gao, Sclaroff S.MEEM:Robust Tr-acking via Multiple Experts Using Entropy Minimization[M]∥Computer Vision-ECCV.2014,2014:188-203 [11] Danelljan M,Hger G,Khan F S,et al.Accurate Scale Estimation for Robust Visual Tracking[C]∥British Machine Vision Conference.Nottingham,2014 [12] Henriques J F,Caseiro R,Martins P,et al.Exploiting the Circulant Structure of Tracking-by-detection with Kernels[C]∥Computer Vision-ECCV 2012.2012:702-715 [13] Zhang Peng,Peng Jing.SVM vs Regularized Least Squares Classification[C]∥Proceedings of the 17th International Conference on Pattern Recognition.2004:176-179 [14] Rifkin R,Yeo G,Poggio T.Regularized least-squares classi_ca-tion[J].Nato Science Series Sub Series III:Computer and Systems Sciences,2003,190:131-154 [15] Kalal Z,Mikolajczyk K,Matas J.Forward-backward error:Automatic detection of tracking failures[C]∥2010 20th International Conference on Pattern Recognition (ICPR).IEEE,2010:2756-2759 |
| No related articles found! |
|
||
首页