基于增强语义与多注意力机制学习的深度相关跟踪

doi:10.19678/j.issn.1000-3428.0053954

计算机工程 ›› 2020, Vol. 46 ›› Issue (2): 279-285. doi: 10.19678/j.issn.1000-3428.0053954

基于增强语义与多注意力机制学习的深度相关跟踪

周双双^1,2, 宋慧慧^1,2, 张开华^1,2, 樊佳庆^1,2

1. 南京信息工程大学自动化学院, 南京 210044;
2. 江苏省大数据分析技术重点实验室, 南京 210044

收稿日期:2019-02-19 修回日期:2019-04-04 发布日期:2020-02-12
作者简介:周双双(1988-),男,硕士研究生,主研方向为目标跟踪;宋慧慧、张开华,教授、博士;樊佳庆,硕士研究生。
基金资助:
国家自然科学基金（61872189，61876088）；江苏省自然科学基金（BK20170040）。

Deep Correlation Tracking Based on Reinforced Semantic and Multi-attention Mechanism Learning

ZHOU Shuangshuang^1,2, SONG Huihui^1,2, ZHANG Kaihua^1,2, FAN Jiaqing^1,2

1. School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China;
2. Jiangsu Key Laboratory of Big Data Analysis Technology, Nanjing 210044, China

Received:2019-02-19 Revised:2019-04-04 Published:2020-02-12

摘要/Abstract

摘要： 在基准可判别相关滤波器网络（DCFNet）目标跟踪过程中，遮挡和运动模糊情况会导致目标发生漂移。针对该问题，结合增强语义与多注意力机制深度学习，设计一种端到端的相关滤波器网络RACFNet。由EDNet网络得到高级语义信息弥补单独低级特征表示的不足，同时加入通道和空间残差注意力机制，使网络能够对不同的跟踪对象提取出更具针对性的表观信息。在此基础上，通过添加相关滤波层并输出响应图最大值推测目标位置。在OTB-2013和OTB-2015基准测试集上的实验结果表明，RACFNet跟踪速度平均可达92帧/s，跟踪成功率较DCFNet分别提高8.20%和10.69%。

关键词: 增强语义, 注意力机制, 相关滤波, 傅里叶域计算, 目标跟踪

Abstract: In baseline tracker Discriminant Correlation Filter Network(DCFNet),occlusion and motion blur often cause target drift.To address the problem,this paper proposes a correlation filtering network of end to end structure,RACFNet.First,EDNet is used to obtain high-level semantic information to make up for low-level feature representation.Then both channel-wise and spatial residual attention mechanism are introduced to enable the network to extract more specific information for different tracking objects.At last,correlation filters are utilized to estimate the target locations according to the output maximum response value.Experimental results on OTB-2013 and OTB-2015 benchmarking datasets show that RACFNet runs at an average speed of 92 frame/s.The success rate of tracking is improved by 8.20% and 10.69% compared with DCFNet.

Key words: reinforced semantic, attention mechanism, correlation filtering, Fourier domain calculation, object tracking

中图分类号:

TP391

周双双, 宋慧慧, 张开华, 樊佳庆. 基于增强语义与多注意力机制学习的深度相关跟踪[J]. 计算机工程, 2020, 46(2): 279-285.

ZHOU Shuangshuang, SONG Huihui, ZHANG Kaihua, FAN Jiaqing. Deep Correlation Tracking Based on Reinforced Semantic and Multi-attention Mechanism Learning[J]. Computer Engineering, 2020, 46(2): 279-285.

https://www.ecice06.com/CN/Y2020/V46/I2/279

图/表 10

20200218144354

20200218144357

20200218144400

20200218144404

20200218144407

20200218144410

20200218144414

20200218144417

20200218144420

20200218144423

参考文献

[1] DANELLJAN M,BHAT G,KHAN F S,et al.ECO:efficient convolution operators for tracking[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Computer Society,2017:6638-6646.
[2] PU Shi,SONG Yibing,MA Chao,et al.Deep attentive tracking via reciprocative learning[C]//Proceedings of NIPS’18.New York,USA:MIT Press,2018:1935-1945.
[3] VALMADRE J,BERTINETTO L,HENRIQUES J,et al.End-to-end representation learning for correlation filter based tracking[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Computer Society,2017:2805-2813.
[4] BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Computer Society,2010:2544-2550.
[5] GE Baoyi,ZUO Xianzhang,HU Yongjiang,et al.Object tracking algorithm based on two-step correlation filter[J].Infrared and Laser Engineering,2018,47(12):388-397.(in Chinese) 葛宝义,左宪章,胡永江,等.基于双步相关滤波的目标跟踪算法[J].红外与激光工程,2018,47(12):388-397.
[6] ZHANG Yuanqiang,BI Duyan,ZHA Yufei.Robust object tracking by maximum margin correlation filter[J].Journal of Air Force Engineering University(Natural Science Edition),2017,18(2):67-73.(in Chinese) 张园强,毕笃彦,查宇飞,等.一种利用最大间隔相关滤波的鲁棒目标跟踪算法[J].空军工程大学学报(自然科学版),2017,18(2):67-73.
[7] GUO Wen,YOU Sisi,ZHANG Tianzhu,et al.Object tracking via low-rank redetection based multiple feature fusion spatio-temporal context learning[J].Journal of Software,2018,29(4):1017-1028.(in Chinese) 郭文,游思思,张天柱,等.低秩重检测的多特征时空上下文的视觉跟踪[J].软件学报,2018,29(4):1017-1028.
[8] 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,2015,37(3):583-596.
[9] DANELLJAN M,HÄGER G,KHAN F S,et al.Accurate scale estimation for robust visual tracking[C]//Proceedings of British Machine Vision Conference.Nottingham,UK:BMVA Press,2014:1-5.
[10] DANELLJAN M,HAGER G,KHAN F S,et al.Learning spatially regularized correlation filters for visual tracking[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Computer Society,2015:4310-4318.
[11] DANELLJAN M,HAGER G,KHAN F S,et al.Convolutional features for correlation filter based visual tracking[C]//Proceedings of 2015 IEEE International Conference on Computer Vision Workshops.Washington D.C.,USA:IEEE Computer Society,2015:58-66.
[12] BERTINETTO L,VALMADRE J,GOLODETZ S,et al.Staple:complementary learners for real-time tracking[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Computer Society,2016:1401-1409.
[13] LI Daxiang,WU Lingfeng,LI Na,et al.Improved SAMF object tracking algorithm[J].Computer Engineering,2019,45(2):258-264.(in Chinese) 李大湘,吴玲风,李娜,等.改进的SAMF目标跟踪算法[J].计算机工程,2019,45(2):258-264.
[14] XIONG Changzhen,WANG Runling.Real-time visual tracking algorithm based on correlation filters and sparse convolutional features[J].Journal of Computer Applications,2018,38(8):2175-2179.(in Chinese) 熊昌镇,车满强,王润玲.基于稀疏卷积特征和相关滤波的实时视觉跟踪算法[J].计算机应用,2018,38(8):2175-2179.
[15] BERTINETTO L,VALMADRE J,HENRIQUES J F,et al.Fully-convolutional Siamese networks for object tracking[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2016:850-865.
[16] WANG Qiang,GAO Jin,XING Junliang,et al.DCFNet:discriminant correlation filters network for visual tracking[EB/OL].[2019-01-05].https://arxiv.org/pdf/1704.04057.pdf.
[17] HU J,SHEN L,ALBANIE S.Squeeze-and-excitation networks[EB/OL].[2019-01-05].https://arxiv.org/pdf/1709.01507.pdf.
[18] 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.
[19] WU Y,LIM J,YANG M H.Online object tracking:a benchmark[C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Computer Society,2013:2411-2418.
[20] WU Y,LIM J,YANG M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[21] SONG Yibing,MA Chao,GONG Lijun,et al.Crest:convolutional residual learning for visual tracking[C]//Proceedings of 2017 International Conference on Computer Visio.Washington D.C.,USA:IEEE Computer Society,2017:2574-2583.

选择文件类型/文献管理软件名称

选择包含的内容

基于增强语义与多注意力机制学习的深度相关跟踪

Deep Correlation Tracking Based on Reinforced Semantic and Multi-attention Mechanism Learning

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王炼红, 林飞鹏, 李潇瑶, 谌桂枝, 周莉. 融入课程知识图谱的KMAKT预测[J]. 计算机工程, 2024, 50(7): 23-31.
[2]	张朋, 严盼盼, 乔凤杰. 基于长时跟踪的滑雪教学姿态辅助矫正方法[J]. 计算机工程, 2024, 50(7): 79-86.
[3]	钱来, 赵卫伟. 基于对比学习和注意力机制的文本分类方法[J]. 计算机工程, 2024, 50(7): 104-111.
[4]	刘建敏, 林晖, 汪晓丁. 基于图注意力机制的无地图场景轨迹预测方法[J]. 计算机工程, 2024, 50(7): 144-153.
[5]	屠乃威, 焦猛, 阎馨. 复杂环境下输电线路鸟巢目标图像检测模型[J]. 计算机工程, 2024, 50(7): 216-226.
[6]	肖慈, 徐杨, 张永丹, 冯明文, 黄易仟. 结合注意力和低光增强的夜间语义分割[J]. 计算机工程, 2024, 50(7): 271-281.
[7]	张锡英, 孙守东, 于海浩, 边继龙. 基于空间传播的多视图三维重建[J]. 计算机工程, 2024, 50(7): 293-302.
[8]	贵向泉, 刘世清, 李立, 秦庆松, 李唐艳. 基于改进YOLOv8的景区行人检测算法[J]. 计算机工程, 2024, 50(7): 342-351.
[9]	程腾腾, 姚春龙, 于晓强, 李旭, 王庆丰. 基于多头注意力机制融合常识知识的共情对话生成[J]. 计算机工程, 2024, 50(6): 94-101.
[10]	更藏措毛, 黄鹤鸣, 杨毅杰. 融合多尺度特征与上下文信息的语音增强方法[J]. 计算机工程, 2024, 50(6): 138-147.
[11]	贺姗, 蔺素珍, 王彦博, 李大威. 基于特征融合的多波段图像描述生成方法[J]. 计算机工程, 2024, 50(6): 236-244.
[12]	杨硕, 王一丁. 基于改进薄板样条运动模型的人脸动画算法[J]. 计算机工程, 2024, 50(6): 255-265.
[13]	陈晓玉, 沈晨, 沈阅, 孔德明. 基于改进SwiftNet的堆场图像实时分割网络[J]. 计算机工程, 2024, 50(6): 296-303.
[14]	游奔, 李晓红, 姚锦, 冯绍杰. 基于多粒度图与注意力机制的半监督短文本分类[J]. 计算机工程, 2024, 50(5): 83-90.
[15]	代巍, 王丰羽, 冀常鹏. 基于情感增强与双图卷积网络的方面级情感分析[J]. 计算机工程, 2024, 50(5): 120-127.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于增强语义与多注意力机制学习的深度相关跟踪

Deep Correlation Tracking Based on Reinforced Semantic and Multi-attention Mechanism Learning

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献

相关文章 15

编辑推荐

Metrics

本文评价