分布统计特征的孪生网络目标跟踪方法

doi:10.3778/j.issn.1002-8331.2211-0435

摘要/Abstract

摘要： 尽管基于孪生网络的跟踪器取得了巨大成功，但在边界模糊这类复杂场景下的跟踪性能仍然较差。大多数现有方法对于目标的定位均采用不灵活的狄克拉分布，由于缺少对边界框的不确定性估计，使其在边界模糊下无法准确定位。为了解决上述问题，基于SiamBAN模型进行改进，利用目标边界框的分布统计特征与其实际的定位质量高度相关这一特性，将边界框的回归值由狄克拉分布转为一定范围内的任意概率分布，将分布统计特征经过分布引导质量预测器生成较高的定位质量估计得分，将分类与定位质量估计联合表示，克服了训练和测试阶段分类与回归不一致问题。在VOT2018、VOT2019、OTB100、UAV123、LaSOT、TrackingNet和GOT-10k数据集上的实验结果表明，对比SiamBAN在准确度和EAO指标上提升了3.3%~10%。

关键词: 孪生网络, 定位质量, 不确定性估计, 分布统计特性, 分布引导质量预测器

Abstract: Although siamese trackers have achieved great success, the tracking performance is inferior in complex scenes such as ambiguous boundaries. Most of the existing methods use the inflexible Dirac distribution for target localization. Due to the lack of uncertainty estimation of the bounding box, the target cannot be accurately located under the ambiguous boundaries. For this purpose, this paper improves SiamBAN. Firstly, the representation of the bounding box is changed from Dirac distribution to the general distribution within a certain range with the help of the characteristics that distribution statistics of the bounding box are highly correlated with the actual localization quality. Secondly, a higher localization quality estimation score is generated by putting the distribution statistics into distribution guided quality predictor. Finally, classification and localization quality estimation are represented jointly which can overcome the problem of inconsistency between classification and localization in training and testing stages. Extensive experiments on visual tracking datasets including VOT2018, VOT2019, OTB100, UAV123, LaSOT, TrackingNet, and GOT-10k demonstrate that the performance of proposed method surpass SiamBAN by 3.3%~10% in terms of accuracy and EAO.

Key words: siamese network, localization quality, uncertainty estimation, distribution statistics, distribution guided quality predictor

李俊, 曹林, 张帆, 杜康宁, 郭亚男. 分布统计特征的孪生网络目标跟踪方法[J]. 计算机工程与应用, 2024, 60(8): 213-224.

LI Jun, CAO Lin, ZHANG Fan, DU Kangning, GUO Yanan. Siamese Networks for Object Tracking on Statistical Characteristics of Distributions[J]. Computer Engineering and Applications, 2024, 60(8): 213-224.

参考文献

[1] 刘艺, 李蒙蒙, 郑奇斌, 等. 视频目标跟踪算法综述[J]. 计算机科学与探索, 2022, 16(7): 1504-1515.
LIU Y, LI M M, ZHENG Q B, el at. Survey on video object tracking algorithms[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(7): 1504-1515.
[2] 陈云芳, 吴懿, 张伟. 基于孪生网络结构的目标跟踪算法综述[J]. 计算机工程与应用, 2020, 56(6): 10-18.
CHEN Y F, WU Y, ZHANG W. Survey of target tracking algorithm based on siamese network structure[J]. Computer Engineering and Applications, 2020, 56(6): 10-18.
[3] BERTINETTO L, VALMADRE J, HENRIQUES J F, et al. Fully-convolutional siamese networks for object tracking[C]//Proceedings of the 14th European Conference on Computer Vision, 2016: 850-865.
[4] ZHU B J, WANG J F, JIANG Z K, et al. AutoAssign: differentiable label assignment for dense object detection[J]. arXiv:2007. 03496, 2020.
[5] LI B, YAN J J, WU W, et al. High performance visual tracking with siamese region proposal network[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8971-8980.
[6] LI B, WU W, WANG Q, et al. SiamRPN++: evolution of siamese visual tracking with very deep networks[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, 2019: 4282-4291.
[7] ZHANG Z P, PENG H W. Deeper and wider siamese networks for real-time visual tracking[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, 2019: 4591-4600.
[8] TIAN Z, SHEN C H, CHEN H, et al. FCOS: fully convolutional one-stage object detection[C]//Proceedings of the 2019 IEEE International Conference on Computer Vision, 2019: 9626-9635.
[9] CHEN Z D, ZHONG B, LI G R, et al. Siamese box adaptive network for visual tracking[C]//Proceedings of the 2020 IEEE Conference on Computer Vision and Pattern Recognition, 2020.
[10] CAO, CHEN K, LOY C C, et al. Prime sample attention in object detection[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020: 11580-11588.
[11] XU Y D, WANG Z Y, LI Z X, et al. SiamFC++: towards robust and accurate visual tracking with target estimation guidelines[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 12549-12556.
[12] LI X, WANG W H, WU L J, et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection[C]//Proceedings of the 34th Conference on Neural Information Processing Systems, 2020.
[13] 赵运基, 范存良, 张新良. 融合多特征和通道感知的目标跟踪算法[J]. 计算机科学与探索, 2022, 16(6): 1417-1428.
ZHAO Y J, FAN C L, ZHANG X L. Object tracking algorithm with fusion of multi-feature and channel awareness[J]. Journal of Frontiers of Computer Science & Technology, 2022, 16(6): 1417-1428.
[14] 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.
[15] BHAT G, JOHNANDER J, DANELLJAN M, et al. Unveiling the power of deep tracking[C]//Proceedings of the European Conference on Computer Vision, 2018.
[16] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3): 211-252.
[17] LAW H, DENG J. Cornernet: detecting objects as paired keypoints[C]//Proceedings of the 15th European Conference on Computer Vision, 2018: 5880-5891.
[18] DUAN K W, BAI S, XIE L X, et al. Centernet: keypoint triplers for object detection[C]//Proceedings of the 2019 IEEE International Conference on Computer Vision, 2019: 9656-9665.
[19] CHOI J, CHUN D Y, KIM H, et al. Gaussian yolov3: an accurate and fast object detector using localization uncertainty for autonomous driving[C]//Proceedings of the 2019 IEEE International Conference on Computer Vision, 2019: 502-511.
[20] WU Y, LIM J W, YANG M H. Online object tracking: a benchmark[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2013: 2411-2418.
[21] MüLLER M, BIBI A, GIANCOLA S, et al. TrackingNet: a large-scale dataset and benchmark for object tracking in the wild[C]//Proceedings of the 15th European Conference on Computer Vision, 2018: 310-327.
[22] HUANG L H, ZHAO X, HUANG K Q . Got-10k: a large high-diversity benchmark for generic object tracking in the wild[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 43（5）：1562-1577.
[23] FAN H, LIN L T, YANG F, et al. LaSOT: a high-quality benchmark for large-scale single object tracking[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, 2019: 5374-5383.
[24] 张伟俊, 钟胜, 徐文辉, 等. 融合显著性与运动信息的相关滤波跟踪算法[J]. 自动化学报, 2021, 47(7): 1572-1588.
ZHANG W J, ZHONG S, XU W H, el at. Correlation filter based visual tracking integrating saliency and motion cues[J]. Acta Automatica Sinica, 2021, 47(7): 1572-1588.
[25] DANELLJAN M, BHAT G, KHAN F S, et al. ATOM: accurate tracking by overlap maximization[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, 2019: 4660-4669.
[26] FU Z H, LIU Q J, FU Z H, et al. STMTrack: template-free visual tracking with space-time memory networks[C]//Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition, 2021: 13774-13783.
[27] ZHANG Z P, PENG H W, FU J L. Ocean: object-aware anchor-free tracking[C]//Proceedings of the 16th European Conference on Computer Vision, 2020：771-787.
[28] PENG J L, JIANG Z K, GU Y Y, et al. SiamRCR: reciprocal classification and regression for visual object tracking[C]//Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition, 2021: 952-958.
[29] GUO D Y, WANG J, CUI Y, et al. SiamCAR: siamese fully convolutional classification and regression for visual tracking[C]//Proceedings of the 2020 IEEE Conference on Computer Vision and Pattern Recognition, 2020: 6269-6277.
[30] KE W, ZHANG T L, HUANG Z Y, et al. Multiple anchor learning for visual object detection[C]//Proceedings of the 2020 IEEE Conference on Computer Vision and Pattern Recognition, 2020: 10203-10212.
[31] HE Y H, ZHU C C, WANG J R, et al. Bounding box regression with uncertainty for accurate object detection[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, 2019: 2888-2897.
[32] REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, 2019: 658-666.
[33] BHAT G, DANELLJAN M, GOOL L, et al. Learning discriminative model prediction for tracking[C]//Proceedings of the 2019 IEEE International Conference on Computer Vision, 2019: 6181-6190.