基于原型注意力的多域网络目标跟踪方法

doi:10.3778/j.issn.1002-8331.2103-0098

摘要/Abstract

摘要： 为了解决预训练集和跟踪视频的域不一致性导致跟踪模型判别能力不足的问题，提出了一种基于原型注意力的多域网络目标跟踪方法。以实时多域网络目标跟踪方法为研究对象，在训练过程中引入原型网络提取注意力特征。基于支撑集正负样本得到目标与背景的域特定原型注意力，将其与待跟踪视频的特征图进行逐通道自适应融合，使得模型在大型数据集上得到判别力更强的目标表示，从而增强跟踪算法的性能。在OTB100和TrackingNet两个基准数据集上的实验结果表明，提出方法的精度和成功率优于现有的代表性跟踪方法。

关键词: 原型网络, 注意力机制, 目标跟踪, 元学习

Abstract: A multi-domain network object tracking method, which based on prototype attention is proposed to solve the problem that the domain inconsistency between the pre-training datasets and the tracking video results in insufficient discriminant ability of the tracking model. It takes the real-time multi-domain network target tracking method as the research object, and introduces the prototype network to extract attention features during training. Based on the positive and negative samples generated by support set, the domain-specific prototype attention of the target and background is obtained, and it performs channel-wise adaptive fusion with the feature map of the video sequence to be tracked, which trains the model to get a more discriminant target representation on a large dataset, which enhances the performance of the tracking algorithm. On the two benchmarks of OTB100 and TrackingNet, the proposed Proto-MDNet tracking method performs better than the existing representative tracking methods in both success rate and precision rate.

Key words: prototype network, attention mechanism, object tracking, meta learning

刘满, 胡磊, 宁纪锋, 刘扬. 基于原型注意力的多域网络目标跟踪方法[J]. 计算机工程与应用, 2022, 58(20): 206-211.

LIU Man, HU Lei, NING Jifeng, LIU Yang. Multi-Domain Network Target Tracking Method Based on Prototype Attention[J]. Computer Engineering and Applications, 2022, 58(20): 206-211.

参考文献

[1] 李玺，查宇飞，张天柱，等.深度学习的目标跟踪算法综述[J].中国图象图形学报，2019，24（12）：2057-2080.
LI X，ZHA Y F，ZHANG T Z，et al.Survey of visual object tracking algorithms based on deep learning[J].Journal of Image and Graphics，2019，24（12）：2057-2080.
[2] NAM H，HAN B.Learning multi-domain convolutional neural networks for visual tracking[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition.Piscataway，NJ：IEEE Press，2016：4293-4302.
[3] 王殿伟，方浩宇，刘颖，等.一种基于改进RT-MDNet的全景视频目标跟踪算法[J].哈尔滨工业大学学报，2020，52（10）：152-160.
WANG D W，FANG H Y，LIU Y，et al.Improved RT-MDNet for panoramic video target tracking[J].Journal of Harbin Institute of Technology，2020，52（10）：152-160.
[4] BERTINETTO L，VALMADRE J，HENRIQUES J F，et al.Fully-convolutional siamese networks for object tracking[C]//Proc of European Conference on Computer Vision.Cham：Springer，2016：850-865.
[5] LUKE?I? A，VOJí? T，?EHOVIN Z L，et al.Discriminative correlation filter tracker with channel and spatial reliability[J].Int J Comput Vis，2018，126：671-688.
[6] 王思奎，刘云鹏，亓琳，等.基于背景约束与卷积特征的目标跟踪方法[J].计算机工程与应用，2020，56（8）：205-214.
WANG S K，LIU Y P，QI L，et al.Object tracking method based on background constraints and convolutional features[J].Computer Engineering and Applications，2020，56（8）：205-214.
[7] 卢湖川，李佩霞，王栋.目标跟踪算法综述[J].模式识别与人工智能，2018，31（1）：61-76.
LU H C，LI P X，WANG D.Visual object tracking：a survey[J].Pattern Recognition and Artificial Intelligence，2018，31（1）：61-76.
[8] JUNG I，SON J，BAEK M，et al.Real-time MDNet[C]//Proc of European Conference on Computer Vision.Cham：Springer，2018：89-104.
[9] WANG Guangting，LUO Chong，SUN Xiaoyan，et al.Tracking by instance detection：a meta-learning approach[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition.Piscataway，NJ：IEEE Press，2020：6288-6297.
[10] FINN C，ABBEEL P，LEVINE S.Model-agnostic meta-learning for fast adaptation of deep networks[C]//Proc of the 34th International Conference on Machine Learning，2017：1126-1135.
[11] YAN Xiaopeng，CHEN Ziliang，XU Anni，et al.Meta R-CNN：towards general solver for instance-level low-shot learning[C]//Proc of IEEE International Conference on Computer Vision.Piscataway，NJ：IEEE Press，2019：9577-9586.
[12] WU Y，LIM J，YANG M H.Object tracking benchmark[J].IEEE Trans on Pattern Analysis and Machine Intelligence，2015，37（9）：1834-1848.
[13] MATTHIAS M，ADEL B，SILVIO G，et al.TrackingNet：a large-scale dataset and benchmark for object tracking in the wild[C]//Proc of European Conference on Computer Vision.Cham：Springer，2018：310-327.
[14] SNELL J，SWERSKY K，ZEMEL R.Prototypical networks for few-shot learning[C]//Proc of the 31st Conference on Neural Information Processing Systems，2017：4077-4087.
[15] WOO S，PARK J，LEE J Y，et al.CBAM：convolutional block attention module[C]//Proc of European Conference on Computer Vision.Cham：Springer，2018：3-19.
[16] JIANG B，LUO R，MAO J，et al.Acquisition of localization confidence for accurate object detection[C]//Proc of European Conference on Computer Vision.Cham：Springer，2018：816-832.
[17] FAN H，LIN L，YANG F，et al.LaSOT：a high-quality benchmark for large-scale single object tracking[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition.Piscataway，NJ：IEEE Press，2019：5369-5378.
[18] DANELLJAN M，BHAT G，KHAN F S，et al.ECO：efficient convolution operators for tracking.[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition，2017：6931-6939.
[19] DANELLJAN M，H?GER G，KHAN F S，et al.Learning spatially regularized correlation filters for visual tracking[C]//Proc of IEEE International Conference on Computer Vision，2015：4310-4318.
[20] HONG Z，CHEN Z，WANG C，et al.MUlti-store tracker（MUSTer）：a cognitive psychology inspired approach to object tracking[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition，2015：749-758.
[21] ZHANG J，MA S，SCLAROFF S.MEEM：robust tracking via multiple experts using entropy minimization[C]//Proc of European Conference on Computer Vision.Cham：Springer，2014：188-203.
[22] HENRIQUES J F，CASEIRO R，MARTINS P，et al.High-speed tracking with kernelized correlation filters[J].IEEE Trans on Pattern Analysis and Machine Intelligence，2015，37（3）：583-596.
[23] DANELLJAN M，H?GER G，KHAN F S，et al.Accurate scale estimation for robust visual tracking[C]//Proc of British Machine Vision Conference.Guildford：BMVA Press，2014：471-482.
[24] VALMADRE J，BERTINETTO L，HENRIQUES J，et al.End-to-end representation learning for correlation filter based tracking[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017：5000-5008.