计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230200096-9.doi: 10.11896/jsjkx.230200096
孟庆姣, 姜文涛
MENG Qingjiao, JIANG Wentao
摘要: 针对正则化滤波器预先定义正则化项,但无法实时抑制非目标区域学习的缺点,提出了一种多特征感知的时空自适应相关滤波目标跟踪的新方法。首先在目标函数中引入空间局部响应变化量实现空间正则化,使滤波器专注于学习对象中值得信任的部分,从而得到响应模型;其次根据全局响应变化决定滤波器的更新率;最后通过级联颜色直方图(Colour Name,CN)与降维后的梯度直方图(Fast Histogram of Oriented Gradient,fHOG)特征实现非卷积特征层面的融合,采用ImageNet-VGG-2048的Conv1,Conv5层提取目标的空间轮廓以及语义信息,并使用ReLU函数拟合训练数据,在保留主要信息的同时提高速率。在数据集DTB70上的精确率(0.747)和成功率(0.789)相较于STRCF算法的精确率(0.737)和成功率(0.760)分别提高了1%和2.9%。大量实验证明该算法在复杂背景、物体遮挡、快速运动等多种场景下基本能满足实时性需求。
中图分类号:
[1]PU L,WEI Z H,HOU Z Q,et al.Twin network visual trackingalgorithm based on asymmetric convolution[J].Journal of Electronics and Information,2022,44(8):2957-2965. [2]JAVED S,MAHMOOD A,DIAS J,et al.Hierarchical Spatio-temporal Graph Regularized Discriminative Correlation Filter for Visual Object Tracking[J].IEEETransactions on Cybernetics,2022,52(11):12259-12274. [3]BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//Proceedings of 2010 IEEE Computer Society Conference on Compu-ter Vision and Pattern Recognition.San Francisco,USA:IEEE,2010:2544-2550. [4]HENRIQUES J F,CASEIRO R,MARTINS P,et al.Exploitingthe circulant structure of tracking-by-detection with kernels[C]//Proceedings of the 12th European Conference on Computer Vision.Florence,Italy:Springer,2012:702-715. [5]HENRIQUES J F,CASEIRO R,MARTINS P,et al.High-speed tracking with kernelized correlation filters[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,37(3):583-596. [6]GALOOGAHI H K,SIM T,LUCEY S.Correlation filters with limited boundaries[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston,MA,USA:IEEE,2014:4630-4638. [7]DANELLJAN M,HÄGER G,KHAN F S,et al.Accurate scale estimation for robust visual tracking[C]//Proceedings of 2014 British Machine Vision Conference.Nottingham,UK:BMVA Press,2014:1-11. [8]DANELLJAN M,HÄGER G,KHAN F S,et al.Adaptive decontamination of the training set:a unified formulation for discrimination visual tracking[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,USA:IEEE,2016:1430-1438. [9]MUELLER M,SMITH N,GHANEM B.Context-aware correlation filter tracking[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017:1387-1395. [10]LI Y,FU C,F DING,et al.AutoTrack:Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR),2020. [11]QING L B,WU M F,LIU G,et al.Image restoration algorithm based on wavelet domain ADMM depth network[J].Enginee-ring Science and Technology,2022,54(5):257-267. [12]BERTINETTO L,VALMADRE J,GOLODETZ S,et al.Sta-ple:complementary learners for real-time tracking[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,USA:IEEE,2016:1401-1409. [13]MA C,HUANG J B,YANG X K,et al.Hierarchical convolu-tional features for visual tracking[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Santiago,Chile:IEEE,2015:3074-3082. [14]DANELLJAN M,ROBINSON A,KHAN F S,et al.Beyond correlation filters:learning continuous convolution operators for visual tracking[C]//Proceedings of the 14th European Confe-rence on Computer Vision.Amsterdam,the Netherlands:Sprin-ger,2016:472-488. [15]LI F,TIAN C,ZUO W M,et al.Learning spatial-temporal regularized correlation filters for visual tracking[C]//CVPR.2018:4904-4913. [16]HOU Z Q,GUO H,MA S G,et al.An anchor free target detection algorithm based on dual branch feature fusion[J].Journal of Electronics and Information,2022,44(6):2175-2183. [17]LIU Y,DU Y M,GUAN Y,et al.An improved algorithm ofacoustic signal weighting based on frequency domain[J].Journal of Chengdu University of Information Engineering,2021,36(1):68-72. [18]JIANG W T,LIU X X,TU C,et al.Target tracking of adaptive spatial anomaly[J].Journal of Electronics and Information,2022,44(2):523-533. [19]XU J P,WANG F.Image classification method based on im-proved S-ReLU activation function[J].Science,Technology and Engineering,2022,22(29):963-968. [20]JIANG W T,MENG Q J.Adaptive spatiotemporal regularization based correlation filtering for target tracking[J].Journal of Intelligent Systems,2023,18(4):754-763. [21]XU T,FENG Z H,WU X J,et al.Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking[J].IEEE Transactions on Image Processing,2019,28(11):5596-5609. [22]YE X Y,GUO W F,ZENG M S,et al.Image steganography detection based on multi-layer perceptual convolution and channel weighting[J].Journal of Electronics and Information,2022,44(8):2949-2956. [23]SHI C Y,SUN Q,LU J P,et al.Image edge detection based on deep fusion convolution neural network[J].Modern Electronic Technology,2022,45(24):141-144. [24]WIDYANINGRUM E,BAI Q,FAJARI M K,et al.Air-borne laser scanning point cloud classification using the DGCNN deep learning method[J].Remote Sensing,2021,13(5):859. [25]ZHANG Y L,QIAN X Y,GE H J,et al.Adaptive multi feature fusion correlation filtering target tracking[J].Chinese Journal of Image Graphics,2020,25(6):1160-1170. |
|