Abstract In order to reduce the influence of target deformation, illumination, motion blur and target rotation on the tracking effect in target tracking, a multi-scale correlation filtering tracking algorithm based on adaptive feature fusion is proposed on the basis of correlation filtering KCF. Firstly, the features of conv2-2, conv3-4 and conv5-4 layers and CN features in vgg19 network are extracted, and CN features are added to conv2-2 layer. Then, the three features are used to replace the hog feature for filtering learning, and three pairs of response diagrams are obtained. Then, the weighted fusion of the three response maps is carried out to predict the target position.Finally, multi-scale correlation filter is introduced to determine the scale.Compared with KCF tracking algorithm, the accuracy and success rate of this algorithm are improved by 13.6% and 11.8% respectively.Compared with several existing excellent tracking algorithms, the algorithm has better tracking effect in dealing with motion blur, background clutter, target deformation and plane rotation.
［1］李康, 李亚敏, 胡学敏, 等. 基于卷积神经网络的鲁棒高精度目标跟踪算法［J］. 电子学报, 2018, 46 (9): 2087-2093.
Li K, Li Y M, Hu X M, et al. Robust and high precision target tracking algorithm based on convolution neural network ［J］. Journal of Electronics, 2018,46 (9): 2087-2093.
［2］孟琭, 杨旭. 目标跟踪算法综述［J］. 自动化学报, 2019, 45 (7): 1244-1260.
Meng B, Yang X. Overview of target tracking algorithm［J］. Journal of Automation, 2019, 45 (7): 1244-1260.
［3］Yang H, Ling S, Feng Z, et al. Recent advances and trends in visual tracking: A review［J］. Neurocomputing, 2011, 74 (18): 3823-3831.
［4］Smeulders A W M, Cucchiara R, Dehghan A. Visual Tracking: An Experimental Survey［J］. Pattern Analysis and Machine Intelligence, 2014, 36 (7): 1442-1468.
［5］翟敬梅, 刘坤. 特征点辅助的时空上下文目标跟踪与定位［J］. 仪器仪表学报, 2017, 38 (11): 2839-2848.
Zhai J M, Liu K. Feature point-assisted space-time context target tracking and positioning［J］. Journal of Instruments and Instruments, 2017, 38 (11): 2839-2848.
［6］程淑红, 王迎. 遮挡和光照变化下的单鱼目标跟踪［J］. 计量学报, 2021, 42 (2): 171-177.
Cheng S H, Wang Y. Single fish target tracking under cover and light change ［J］. Acta Metrologica Sinica, 2021, 42 (2): 171-177.
［7］沈秋, 严小乐, 刘霖枫, 等. 基于自适应特征选择的多尺度相关滤波跟踪［J］. 光学学报, 2017, 37 (5): 174-183.
Shen Q, Yan X L, Liu L F, et al. Multi-scale correlation filter tracking based on adaptive feature selection ［J］. Acta Optica Sinica, 2017, 37 (5): 174-183.
［8］白中浩, 朱磊, 李智强. 基于多模型融合和重新检测的高精度鲁棒目标跟踪［J］. 仪器仪表学报, 2019, 40 (9): 132-141.
Bai Z H, Zhu L, Li Z Q. Robust target tracking with high precision based on Multi-model fusion and re-detection［J］. Journal of Instruments and Instruments, 2019, 40 (9): 132-141.
［9］Bolme D S, Beveridge J R, Draper B A, et al. Visual object tracking using adaptive correlation filters［C］//IEEE. The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010. San Francisco, USA, 2010: 2-6.
［10］Henriques J F, Caseiro R, Martins P, et al. Exploiting the Circulant Structure of Tracking-by-Detection with Kernels［C］//Proceedings of the 12th European conference on Computer Vision-Volume Part IV. Springer, Berlin, Heidelberg, 2012: 2-4.
［11］Henriques Joo F, Caseiro Rui, Martins Pedro, et al. High-Speed Tracking with Kernelized Correlation Filters ［J］. IEEE transactions on pattern analysis and machine intelligence, 2015, 37 (3):583-596.
［12］Danelljan M, Hager G, Shahbaz Khan F, et al. Learning spatially regularized correlation filters for visual tracking［C］//Proceedings of the IEEE international conference on computer vision. 2015: 4310-4318.
［13］Danelljan M, Khan F S, Felsberg M, et al. Adaptive Color Attributes for Real-Time Visual Tracking［C］//IEEE. IEEE Conference on Computer Vision & Pattern Recognition. 2014: 1090-1097.
［14］Danelljan M, Hger G, Khan F, et al. Accurate scale estimation for robust visual tracking ［C］//British Machine Vision Conference. Nottingham, UK, 2014: 2-5.
［15］梁硕, 陈金勇, 吴金亮, 等. 基于KCF框架的长时间视频目标跟踪算法［J］. 无线电通信技术, 2017, 43 (2): 55-58.
Liang S, Chen J Y, Wu J L, et al. Long-time video target tracking algorithm based on KCF framework［J］. Radio Communications Technology, 2017, 43 (2): 55-58.
［16］Van De Weijer J, Schmid C, Verbeek J. Learning color names from real-world images［C］//IEEE. 2007 IEEE Conference on Computer Vision and Pattern Recognition. 2007: 1-8.
［17］Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition［EB］. http: //dio. org110. 485501 arXiv: 1409. 1556, 2014.
［18］Ma C, Huang J B, Yang X, et al. Hierarchical convolutional features for visual tracking［C］//Proceedings of the IEEE international conference on computer vision. Santiago, Chile, 2015: 3074-3082.
［19］Wu Y, Lim J, Yang M H . Object Tracking Benchmark［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 37 (9): 1834-1848.
［20］Yang F, Lu H, Yang M H . Robust Visual Tracking via Multiple Kernel Boosting With Affinity Constraints［J］. IEEE Transactions on Circuits & Systems for Video Technology, 2014, 24 (2): 242-254.
［21］陈卫东, 陈磊, 邓志巍, 等. 基于混合相关滤波信息融合再检测的目标跟踪算法［J］. 计量学报, 2019, 40 (6): 1006-1012.
Chen W D, Chen L, Deng Z W, et al. Target tracking algorithm based on mixed correlation filter information fusion and re-detection［J］. Acta Metrologica Sinica, 2019, 40 (6): 1006-1012.
［22］孙航, 李晶, 杜博, 等. 基于多阶段学习的相关滤波目标跟踪［J］. 电子学报, 2017, 45(10): 27-32.
Sun H, Li J, Du B, et al. Relevant filter target tracking based on multistage learnin［J］. Acta Electronica Sinica, 2017, 45(10): 27-32.
2022, Vol. 43 
