基于二阶池化网络的鲁棒视觉跟踪算法

doi:10.3969/j.issn.0372-2112.2020.08.003

电子学报 ›› 2020, Vol. 48 ›› Issue (8): 1472-1478.DOI: 10.3969/j.issn.0372-2112.2020.08.003

基于二阶池化网络的鲁棒视觉跟踪算法

蒲磊¹, 冯新喜², 侯志强³, 余旺盛²

1. 空军工程大学研究生院, 陕西西安 710077;
2. 空军工程大学信息与导航学院, 陕西西安 710077;
3. 西安邮电大学计算机学院, 陕西西安 710121

收稿日期:2019-11-17 修回日期:2020-02-21 出版日期:2020-08-25
- 通讯作者:
- 蒲磊
- 作者简介:
- 冯新喜 男,1964年10月出生,陕西富平人1991年获西北工业大学博士学位,现为空军工程大学信息与导航学院教授、博士研究生导师,主要研究领域为信息融合,信号处理,目标跟踪等. E-mail:fengxinxi2005@aliyun.com
- 基金资助:
- 国家自然科学基金 (No.61571458，No.61703423）

Robust Visual Tracking Based on Second Order Pooling Network

PU Lei¹, FENG Xin-xi², HOU Zhi-qiang³, YU Wang-sheng²

1. Graduate College, Air Force Engineering University, Xi'an, Shaaxi 710077, China;
2. Institute of Information and Navigation, Air Force Engineering University, Xi'an, Shaaxi 710077, China;
3. School of Computer Science and Technology, Xian University of Posts and Telecommunications, Xi'an, Shaaxi 710121, China

Received:2019-11-17 Revised:2020-02-21 Online:2020-08-25 Published:2020-08-25
- Corresponding author:
- PU Lei
- Supported by:
- National Natural Science Foundation of China (No.61571458, No.61703423)

摘要/Abstract

摘要： 针对低分辨率、遮挡以及相似物体干扰等复杂场景下目标易丢失的问题，本文提出了基于二阶池化网络的视觉跟踪算法.已有的方法大多采用一阶池化网络，使得对低分辨目标和相似目标间的区分性不足.对此，本文首先在VGG16网络结构的基础上，将网络最后的一阶池化层替换为二阶协方差池化层，接着在ImageNet和CUB200-2011数据集上对网络进行重新训练.在跟踪阶段，为了减少运算负担，仅提取预训练网络的第四层卷积特征作为目标的外观表征.最后将提取的特征与已有的相关滤波算法进行结合.实验结果表明，本文算法在跟踪精度和成功率上均取得了优异的性能表现.

关键词: 视觉跟踪, 二阶池化网络, 深度特征, 相关滤波

Abstract: Aiming at the problem that the target is easy to lose in the complex scene such as low resolution, occlusion, the interference of similar objects, this paper proposes a visual tracking algorithm based on second-order pooling network. Most of the existing methods use the first-order pooling network, which makes the difference between similar targets insufficient. In this paper, based on the VGG16 network structure, the last first-order pooling layer is replaced by the second-order covariance pooling layer, and then the network is retrained on ImageNet and CUB200-2011 image data sets. In order to reduce the computational burden, only the fourth convolution feature of the pre-training network is extracted as the appearance representation of the target. Finally, the extracted features are combined with the existing correlation filtering algorithm. The experimental results show that the algorithm achieves excellent performance in tracking accuracy and success rate.

Key words: visual tracking, second-order pooling network, deep features, correlation filter

中图分类号:

TP391.4

蒲磊, 冯新喜, 侯志强, 等. 基于二阶池化网络的鲁棒视觉跟踪算法[J]. 电子学报, 2020, 48(8): 1472-1478.

PU Lei, FENG Xin-xi, HOU Zhi-qiang, et al. Robust Visual Tracking Based on Second Order Pooling Network[J]. Acta Electronica Sinica, 2020, 48(8): 1472-1478.

参考文献

[1] Smeulders A W M,CHu D M,Cucchiara R,et al.Visual tracking:An experimental survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,36(7):1442-1468.
[2] Wang Naiyan,SHi Jianping,Yeung Dityan,et al.Understanding and diagnosing visual tracking systems[A].IEEE International Conference on Computer Vision[C].Santiago,Chile:2015.3101-3109.
[3] Rawat W,Wang Z.Deep convolutional neural networks for image classification:A comprehensive review[J].Neural computation,2017,29(9):2352-2449.
[4] Girshick R,Donahue J,Darrell T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[A].Proceedings of the IEEE conference on computer vision and pattern recognition.Columbus[C].America:2014.580-587.
[5] Long J,Shelhamer E,Darrell T.Fully convolutional networks for semantic segmentation[A].Proceedings of the IEEE conference on computer vision and pattern recognition[C].Boston,America:2015.3431-3440.
[6] He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Las Vegas,America:2016.770-778.
[7] Ma Chao,Huang Jiabin,YANG Xiaokang,et al.Hierarchical convolutional features for visual tracking[A].IEEE International Conference on Computer Vision[C].Santiago,Chile:2015.3074-3082.
[8] Qi Yuankai,Zhang Shenging,Qin Lei,et al.Hedged deep tracking[A].Proceedings of the IEEE conference on computer vision and pattern recognition[C].Las Vegas,America:2016.4303-4311.
[9] Danelljan M,Hager G,Shahbaz Khan F,et al.Convolutional features for correlation filter based visual tracking[A].Proceedings of the IEEE International Conference on Computer Vision Workshops[C].Santiago,Chile:2015.58-66.
[10] Nam H,Han B.Learning multi-domain convolutional neural networks for visual tracking[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].2016.4293-4302.
[11] Bertinetto L,Valmadre J,Henriques J F,et al.Fully-convolutional siamese networks for object tracking[A].European conference on computer vision[C].Springer,Cham:2016.850-865.
[12] Gao Z,Xie J,Wang Q,et al.Global second-order pooling convolutional networks[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Los Angeles,USA:2019.3024-3033.
[13] Carreira J,Caseiro R,Batista J,et al.Semantic segmentation with second-order pooling[A].European Conference on Computer Vision[C].Berlin,Heidelberg:Springer,2012.430-443.
[14] Chen B,Deng W,Hu J.Mixed high-order attention network for person re-identification[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Angeles,USA:2019.371-381.
[15] Li P,Xie J,Wang Q,et al.Is second-order information helpful for large-scale visual recognition? [A].In Proceedings of the IEEE International Conference on Computer Vision[C].Venice:2017.2070-2078.
[16] Krizhevsky A,Sutskever I,Hinton G.Imagenet classification with deep convolutional neural networks[A].International Conference on Neural Information Processing Systems[C].Lake Tahoe,Spain:2012,25(2):809-817.
[17] Li Feng,Tian Cheng,Zuo Wangmeng,et al.Learning spatial-temporal regularized correlation filters for visual tracking[A].Computer Vision and Pattern Recognition[C].Salt Lake City,USA:2018.4904-4913.
[18] Vedaldi A,Lenc K.Matconvnet:Convolutional neural networks for matlab[A].Proceedings of the 23rd ACM international conference on Multimedia.Brisbane[C].Australia:2015.689-692.
[19] Simonyan K,Zisserman A.Very deep convolutional networks for large-scale image recognition[A].International Conference on Learning Representations[C].San Diego,USA:2015.563-567.
[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] T Zhang,C Xu,M Yang.Learning multi-task correlation particle filters for visual tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,41(2):365-378.
[22] LI P,CHEN B,OUYANG W,et al.GradNet:Gradient-guided network for visual object tracking [A].Proceedings of the IEEE International Conference on Computer Vision[C].Venice:2019.6162-6171.
[23] Li B,Yan J,Wu W,et al.High performance visual tracking with siamese region proposal network[A].Computer Vision and Pattern Recognition[C].Salt Lake City,USA:2018.8971-8980.
[24] Liang Pengpeng,Erik B,Ling Haibin.Encoding color information for visual tracking:Algorithms and benchmark[J].IEEE Transactions on Image Processing,2015,24(12):5630-5644.
[25] Danelljan M,Robinson A,Khan F S,et al.Beyond correlation filters:Learning continuous convolution operators for visual tracking[A].European Conference on Computer Vision.Springer[C].Cham:2016.472-488.

基于二阶池化网络的鲁棒视觉跟踪算法

Robust Visual Tracking Based on Second Order Pooling Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李豪, 袁广林, 秦晓燕, 琚长瑞, 朱虹. 基于空间加权对数似然比相关滤波与Deep Snake的目标轮廓跟踪[J]. 电子学报, 2023, 51(1): 105-116.
[2]	苏兆品, 吴张倩, 岳峰, 武钦芳, 张国富. 自然环境背景噪声下基于低维深度特征的手机来源识别[J]. 电子学报, 2021, 49(4): 637-646.
[3]	陈丹, 姚伯羽. 运动模型引导的自适应核相关目标跟踪方法[J]. 电子学报, 2021, 49(3): 550-558.
[4]	仇祝令, 查宇飞, 吴敏, 王青. 基于注意力学习的正则化相关滤波跟踪算法[J]. 电子学报, 2020, 48(9): 1762-1768.
[5]	金泽芬芬, 侯志强, 余旺盛, 王鑫, 寇人可. 基于量子遗传算法的视觉目标跟踪[J]. 电子学报, 2020, 48(8): 1493-1501.
[6]	蒲磊, 冯新喜, 侯志强, 查宇飞, 余旺盛. 基于深度空间正则化的相关滤波跟踪算法[J]. 电子学报, 2020, 48(10): 2025-2032.
[7]	范舜奕, 管桦, 侯志强, 余旺盛, 戴铂. 基于多表观特征子模型更新的鲁棒视觉跟踪[J]. 电子学报, 2018, 46(2): 440-446.
[8]	孙巧, 张胜修, 张正新, 曹立佳, 李小锋. 基于加权重叠率的单目标视觉跟踪评价指标[J]. 电子学报, 2017, 45(3): 753-761.
[9]	宋涛, 李鸥, 刘广怡, 崔弘亮. 基于改进协作目标外观模型的在线视觉跟踪[J]. 电子学报, 2017, 45(2): 384-393.
[10]	余旺盛, 李卫华, 侯志强. 分层结构直方图及其应用[J]. 电子学报, 2017, 45(11): 2617-2624.
[11]	宋涛, 李鸥, 刘广怡. 基于置信区域内多级动态层表达的类贯序蒙特卡洛视觉跟踪方法[J]. 电子学报, 2016, 44(6): 1355-1361.
[12]	薛模根, 朱虹, 袁广林. 在线鲁棒判别式字典学习视觉跟踪[J]. 电子学报, 2016, 44(4): 838-845.
[13]	袁广林, 薛模根. 基于主分量寻踪的鲁棒视觉跟踪[J]. 电子学报, 2015, 43(3): 417-423.
[14]	余旺盛, 田孝华, 侯志强, 查宇飞. 基于局部分块学习的在线视觉跟踪[J]. 电子学报, 2015, 43(1): 74-78.
[15]	余旺盛, 田孝华, 侯志强, 黄安奇, 刘翔. 基于关键区域特征匹配的视觉跟踪算法[J]. 电子学报, 2014, 42(11): 2150-2156.