结合全局光流的孪生区域提名网络目标跟踪算法

基于孪生网络的跟踪器受限于孪生网络跟踪框架固有的跟踪机制和搜索区域选择机制,当目标处在被遮挡、快速运动和出视野等困难场景下时,如何稳定、鲁棒地进行目标跟踪始终是孪生网络跟踪器亟需解决的问题。为此,文章提出一种结合光流的孪生区域提名网络目标跟踪算法（GOF-SiamRPN）。通过全局光流对目标的运动趋势信息进行补充,该方法可以有效地解决在这些困难场景下的跟踪问题。在VOT2019和UAV123上的实验结果表明,相比基准方法,该算法分别取得了2.0%和1.8%的性能提升。与其他先进的跟踪器相比,该算法也取得了有竞争力的跟踪效果。

Abstract

The Siamese network-based trackers are limited by the inherent tracking mechanism and search area selection mechanism of the Siamese network tracking framework. When the object is under challenging scenarios such as occlusion, fast motion, and out-of-view, how to perform stable and obust object tracking is always an urgent problem for Siamese trackers. To this end, in this paper, an object-tracking algorithm that combines the Siamese region proposal network with the global optical flow (GOF-SiamRPN) is proposed. By assisting the motion trend information of the object with global optical flow, the proposed method could effectively solve the potential tracking issues in these challenging scenarios. Extensive experimental results on VOT2019 and UAV123 show that the proposed method achieves a performance gain of 2.0% and 1.8% compared with the baseline method. It also achieves a competing performance compared to other state-of-the-art trackers.

参考文献

[1] Su K, Li J, Fu H. Smart city and the applications[C]// 2011 Inter. Conf. on Electronics, Communications and Control (ICECC), 2011: 1028-1031.

[2] Marvasti-Zadeh S M, Cheng L, Ghanei-Yakhdan H, et al. Deep learning for visual tracking: A comprehensive survey[J]. IEEE Trans. on Intelligent Transportation Systems, 2022, 23(5): 3943-3968.

[3] Smeulders A W M, Chu D M, Cucchiara R, et al. Visual tracking: An experimental survey[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2014, 36(7): 1442-1468.

[4] Yu Q, Dinh T B, Medioni G. Online tracking and reacquisition using co-trained generative and discriminative trackers[C]// Computer Vision-ECCV 2008, 2008: 678-691.

[5] Hager G, Belhumeur P. Efficient region tracking with parametric models of geometry and illumination[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998, 20(10): 1025-1039.

[6] Zhang T, Bibi A, Ghanem B. In defense of sparse tracking: Circulant sparse tracker[C]// 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016: 3880-3888.

[7] Zhong W, Lu H, Yang M H. Robust object tracking via sparsity-based collaborative model[C]// 2012 IEEE Conf. on Computer Vision and Pattern Recognition, 2012: 1838-1845.

[8] Kristan M, Matas J, Leonardis A, et al. The seventh visual object tracking VOT2019 challenge results[C]// 2019 IEEE/CVF Inter. Conf. on Computer Vision Workshop (ICCVW), 2019: 2206-2241.

[9] Mueller M, Smith N, Ghanem B. A benchmark and simulator for UAV tracking[C]// Computer Vision-ECCV 2016, 2016: 445-461.

[10] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Commun. ACM, 2017, 60(6): 84-90.

[11] Danelljan M, Hger G, Khan F S, et al. Convolutional features for correlation filter based visual tracking[C]// 2015 IEEE Inter. Conf. on Computer Vision Workshop (ICCVW), 2015: 621-629.

[12] Danelljan M, Robinson A, Shahbaz Khan F, et al. Beyond correlation filters: Learning continuous convolution operators for visual tracking[C]// Computer Vision-ECCV 2016, 2016: 472-488.

[13] Danelljan M, Bhat G, Khan F S, et al. Eco: Efficient convolution operators for tracking[C]// 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2017: 6931-6939.

[14] Wang L, Ouyang W, Wang X, et al. Visual tracking with fully convolutional networks[C]// 2015 IEEE Inter. Conf. on Computer Vision (ICCV), 2015: 3119-3127.

[15] Wang L, Ouyang W, Wang X, et al. Stct: Sequentially training convolutional networks for visual tracking[C]// 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016: 1373-1381.

[16] Jung I, Son J, Baek M, et al. Real-time mdnet[C]// Computer Vision-ECCV 2018, 2018: 89-104.

[17] Park E, Berg A C. Meta-tracker: Fast and robust online adaptation for visual object trackers[C]// Computer Vision-ECCV 2018, 2018: 587-604.

[18] Wang G, Luo C, Sun X, et al. Tracking by instance detection: A meta-learning approach[C]// 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2020: 6287-6296.

[19] Bertinetto L, Valmadre J, Henriques J F, et al. Fullyconvolutional siamese networks for object tracking[C]// Computer Vision-ECCV 2016, 2016: 850-865.

[20] Held D, Thrun S, Savarese S. Learning to track at 100 fps with deep regression networks[C]// Computer Vision-ECCV 2016, 2016: 749-765.

[21] Valmadre J, Bertinetto L, Henriques J, et al. End-to-end representation learning for correlation filter based tracking[C]// 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2017: 5000-5008.

[22] Li B, Yan J, Wu W, et al. High performance visual tracking with siamese region proposal network[C]// 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, 2018: 8971-8980.

[23] Fan H, Ling H. Siamese cascaded region proposal networks for real-time visual tracking[C]// 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2019: 7944-7953.

[24] Wang Q, Zhang L, Bertinetto L, et al. Fast online object tracking and segmentation: A unifying approach[C]// 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2019: 1328-1338.

[25] Li B, Wu W, Wang Q, et al. Siamrpn++: Evolution of siamese visual tracking with very deep networks[C]// 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2019: 4277-4286.

[26] Zhang Z, Peng H. Deeper and wider siamese networks for real-time visual tracking[C]// 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2019: 4586-4595.

[27] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[EB/OL]. arXiv, 2017. http://arxiv.org/abs/1706.03762.

[28] Lin L, Fan H, Xu Y, et al. Swintrack: A simple and strong baseline for transformer tracking[EB/OL]. arXiv, 2021. http://arXiv.org/abs/2112.00995.

[29] Wang N, Zhou W, Wang J, et al. Transformer meets tracker: Exploiting temporal context for robust visual tracking[C]// 2021 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2021: 1571-1580.

[30] Pfister T, Charles J, Zisserman A. Flowing convnets for human pose estimation in videos[C]// 2015 IEEE Inter. Conf. on Computer Vision (ICCV), 2015: 1913-1921.

[31] Patraucean V, Handa A, Cipolla R. Spatio-temporal video autoencoder with differentiable memory[EB/OL]. arXiv, 2015. http://arxiv.org/abs/1511.06309.

[32] Zhu X, Xiong Y, Dai J, et al. Deep feature flow for video recognition[C]// 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2017: 4141-4150.

[33] Zhu X, Wang Y, Dai J, et al. Flow-guided feature aggregation for video object detection[C]// 2017 IEEE Inter. Conf. on Computer Vision (ICCV), 2017: 408-417.

[34] Gladh S, Danelljan M, Khan F S, et al. Deep motion features for visual tracking[C]// 2016 23rd Inter. Conf. on Pattern Recognition (ICPR), 2016: 1243-1248.

[35] Zhu Z, Wu W, Zou W, et al. End-to-end flow correlation tracking with spatial-temporal attention[C]// 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, 2018: 548-557.

[36] Zhou L, Yao X, Zhang J. Accurate positioning siamese network for real-time object tracking[J]. IEEE Access, 2019, 7: 84209-84216.

[37] Ilg E, Mayer N, Saikia T, et al. Flownet 2.0: Evolution of optical flow estimation with deep networks[C]// 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2017: 1647-1655.

[38] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]// 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016: 770-778.

[39] Wu F, Zhang J, Xu Z. Stably adaptive anti-occlusion siamese region proposal network for real-time object tracking[J]. IEEE Access, 2020, 8: 161349-161360.

[40] Teed Z, Deng J. Raft: Recurrent all-pairs field transforms for optical flow[C]// Computer Vision-ECCV 2020, 2020: 402-419.

[41] He A, Luo C, Tian X, et al. A twofold siamese network for real-time object tracking[C]// 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, 2018: 4834-4843.

[42] Zhu Z, Wang Q, Li B, et al. Distractor-aware siamese networks for visual object tracking[C]// Computer Vision-ECCV 2018, 2018: 103-119.

[43] Danelljan M, Hger G, Khan F S, et al. Learning spatially regularized correlation filters for visual tracking[C]// 2015 IEEE Inter. Conf. on Computer Vision (ICCV), 2015: 4310-4318.

吴非, 张建林. 结合全局光流的孪生区域提名网络目标跟踪算法[J]. 半导体光电, 2023, 44(3): 422. WU Fei, ZHANG Jianlin. Siamese Region Proposal Network Object Tracking Algorithm with Global Optical Flow[J]. Semiconductor Optoelectronics, 2023, 44(3): 422.

结合全局光流的孪生区域提名网络目标跟踪算法

关于本站 Cookie 的使用提示

全站搜索

结合全局光流的孪生区域提名网络目标跟踪算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索