多尺度通道注意与孪生网络的目标跟踪算法

doi:10.3778/j.issn.1002-8331.2204-0136

摘要/Abstract

摘要： 在全卷积分类和回归的Siamese目标跟踪算法的基础上，提出了一种融合多尺度通道注意力的目标跟踪算法（Siamese multi-scale channel attention，SiamMCA）。算法基于Siamese网络架构，以多尺度通道注意力融合改进后的ResNet50作为骨干网络进行特征提取与增强，并利用深度互相关网络对特征图进行解码和跟踪，最终成功进行融合、分类和回归。SiamMCA通过充分利用多尺度通道注意力的语义信息整合功能，整合了空间信息和运动信息，提升了跟踪器的性能。最终分别在OTB100、VOT2016数据集上和LaSOT长期基准上的实验表明，SiamMCA与其他先进的跟踪器相比取得了更高的精度、成功率和性能表现，尤其是在快速运动、遮挡、相似性干扰、尺度变化等复杂场景中。

关键词: Siamese, 多尺度, 通道注意力, 特征增强

Abstract: Based on the Siamese object tracking algorithm of fully convolutional classification and regression, a target tracking algorithm fused with multi-scale channel attention（SiamMCA） is proposed. Firstly, the algorithm is based on the Siamese network architecture. The backbone network ResNet50 is improved, which conbined with multi-scale channel attention for feature extraction and enhancement. Then, the deep cross-correlation network is adopted to decode and track the feature map. At last, it performs fusion, classification and regression successfully. By making full use of the semantic information integration function of multi-scale channel attention, spatial information and motion information are integrated, which improves the performance of the tracker. Finally, experiments on OTB100, LaSOT long-term benchmarks, and VOT2016 datasets show that SiamMCA achieves higher accuracy, success rate, and performance than other state-of-the-art trackers. Compared with other trackers, the success rate and accuracy are higher in complex scenes, especially in fast motion, occlusion, similarity interference and scale changes.

Key words: Siamese, multi-scale, channel attention, feature enhancement

王淑贤, 葛海波, 李文浩. 多尺度通道注意与孪生网络的目标跟踪算法[J]. 计算机工程与应用, 2023, 59(14): 142-150.

WANG Shuxian, GE Haibo, LI Wenhao. Object Tracking Algorithm for Multi-Scale Channel Attention and Siamese Network[J]. Computer Engineering and Applications, 2023, 59(14): 142-150.

参考文献

[1] MA J，CHEN J，YANG C.Using optimized Gaussian mixture model rules and global tracking graph for feature extraction and tracking in time-varying data[J].The Visual Computer，2022（1）：1-24.
[2] AMIRI M，SOLEIMANI S.A hybrid atmospheric satellite image-processing method for dust and horizontal visibility detection through feature extraction and machine learning techniques[J].Journal of the Indian Society of Remote Sensing，2022，50（3）：523-532.
[3] WU Z，YANG R，ZHENG L，et al.Safe learning-based feedback linearization tracking control for nonlinear system with event-triggered model update[J].IEEE Robotics and Automation Letters，2022，7（2）：3286-3293.
[4] ZONG S，CHEN S，ALINIZZI M，et al.Leveraging UAV capabilities for vehicle tracking and collision risk assessment at road intersections[J].Sustainability，2022，14（7）：1-20.
[5] ZHANG L，JAGANNADAN V，PONNUTHURAI N S，et al.Robust visual tracking using oblique random forests[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），Honolulu，HI，Jul 21-26，2017.Piscataway：IEEE，2017：5825-5834.
[6] DANELLJAN M，BHAT G，KHAN F S，et al.ATOM：accurate tracking by overlap maximization[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），Long Beach，CA，Jun 15-20，2019.Piscataway：IEEE，2019：4655-4664.
[7] BOLME D，BEVERIDGE J，DRAPER B，et al.Visual object tracking using adaptive correlation filters[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition，San Francisco，CA，Jun 13-18，2010.Piscataway：IEEE，2010：2544-2550.
[8] DANELLJAN M，H?GER G，KHAN F S，et al.Discriminative scale space tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（8）：1561-1575.
[9] 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.
[10] LI F，YAO Y J，LI P H，et al.Integrating boundary and center correlation filters for visual tracking with aspect ratio variation[C]//2017 IEEE International Conference on Computer Vision Workshops（ICCVW），Venice，Italy，Oct 22-29，2017.Piscataway：IEEE，2017：2001-2009.
[11] ZHANG T Z，XU C S，YANG M H.Multi-task correlation particle filter for robust object tracking[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），Honolulu，HI，Jul 21-26，2017.Piscataway：IEEE，2017：4819-4827.
[12] LIU T，WANG G，YANG Q，et al.Part-based tracking via discriminative correlation filters[J].IEEE Transactions on Circuits & Systems for Video Technology，2016.
[13] BERTINETTO L，VALMADRE J，HENRIQUES J F，et al.Fully-convolutional siamese networks for object tracking[C]//2016 European Conference on Computer Vision（ECCV），Amsterdam，Oct 8-16，2016.Cham：Springer，2016：850-865.
[14] GUO Q，FENG W，ZHOU C，et al.Learning dynamic siamese network for visual object tracking[C]//2017 IEEE International Conference on Computer Vision（ICCV），Venice，Italy，Oct 22-29，2017.Piscataway：IEEE，2017：1781-1789.
[15] LI B，YAN J，WU W，et al.High performance visual tracking with Siamese region proposal network[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，Salt Lake City，UT，Jun 18-23，2018.Piscataway：IEEE，2018：8971-8980.
[16] LI B，WU W，WANG Q，et al.SiamRPN++：evolution of siamese visual tracking with very deep networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），Long Beach，CA，Jun 15-20，2019.Piscataway：IEEE，2019：4282-4291.
[17] ZHANG Z P，PENG H W.Deeper and wider Siamese networks for real-time visual tracking[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），Long Beach，CA，Jun 15-20，2019.Piscataway：IEEE，2019：4586-4595.
[18] GUO D Y，WANG J，CUI Y，et al.SiamCAR：siamese fully convolutional classification and regression for visual tracking[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），Seattle，WA，Jun 13-19，2020.Piscataway：IEEE，2020：6268-6276.
[19] VASWANI A，SHAZEER N，PARMAR N，et al.Attention is all you need[C]//Advances in Neural Information Processing Systems，2017.
[20] CHEN X，YAN B，ZHU J，et al.Transformer tracking[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），Nashville，TN，Jun 20-25，2021.Piscataway：IEEE，2021：8122-8131.
[21] WANG Q，TENG Z，XING J L，et al.Learning attentions：residual attentional siamese network for high performance online visual tracking[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，Salt Lake City，UT，Jun 18-23，2018.Piscataway：IEEE，2018：4854-4863.
[22] YU Y C，XIONG Y L，HUANG W L，et al.Deformable siamese attention networks for visual object tracking[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），Seattle，WA，Jun 13-19，2020.Piscataway：IEEE，2020：6728-6737.
[23] ZHAO X，LIU Y，HAN G.Cooperative use of recurrent neural network and siamese region proposal network for robust visual tracking[J].IEEE Access，2021（9）：57704-57715.
[24] 韩明，王景芹，王敬涛，等.级联特征融合孪生网络目标跟踪算法研究[J].计算机工程与应用，2022，58（6）：208-218.
HAN M，WANG J Q，WANG J T，et al.Research on object tracking algorithm based on cascading feature fusion of siamese network[J].Computer Engineering and Applications，2022，58（6）：208-218.
[25] NAIR V，HINTON G E.Rectified linear units improve restricted Boltzmann machines[C]//The 27th International Conference on Machine Learning（ICML），Haifa，Israel，Jun 21-24，2010.Piscataway：IEEE，2010：807-814.
[26] SINGH B，NAJIBI M，DAVIS L S.SNIPER：efficient multi-scale training[C]//The Annual Conference on Neural Information Processing Systems（NeurIPS），Montreal，Dec 2-8，2018.Piscataway：IEEE，2018：9333-9343.
[27] SINGH B，DAVIS L S.An analysis of scale invariance in object detection-SNIP[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，Salt Lake City，UT，Jun 18-23，2018.Piscataway：IEEE，2018：3578-3587.
[28] LIN T Y，MAIRE M，BELONGIE S，et al.Microsoft COCO：common objects in context[C]//European Conference on Computer Vision，Sep 6-12，Zurich，Switzerland.Cham：Springer，2014：740-755.
[29] DAI Y，GIESEKE F，OEHMCKE S，et al.Attentional feature fusion[C]//The 2021 IEEE Winter Conference on Applications of Computer Vision（WACV），Waikoloa，HI，Jan 3-8，2021.Piscataway：IEEE，2021：3559-3568.
[30] YU J，JIANG Y，WANG Z，et al.Unitbox：an advanced object detection network[C]//Proceedings of the 24th ACM International Conference on Multimedia，Amsterdam，Oct 15-19，2016.New York：Association for Computing Machinery，2016：516-520.
[31] TIAN Z，SHEN C H，CHEN H，et al.Fcos：fully convolutional one-stage object detection[C]//The 2019 IEEE/CVF International Conference on Computer Vision（ICCV），Seoul，Oct 27-Nov 2，2019.Piscataway：IEEE，2019：9626-9635.
[32] FELSBERG M，KRISTAN M，MATAS J，et al.The thermal infrared visual object tracking VOT-TIR2016 challenge results[C]//The 14th European Conference on Computer Vision，Amsterdam，Oct 8-16，2016.Cham：Springer，2016：824-843.