基于位置敏感模型的深度跟踪算法研究

doi:10.3969/j.issn.0372-2112.2019.10.008

电子学报 ›› 2019, Vol. 47 ›› Issue (10): 2076-2082.DOI: 10.3969/j.issn.0372-2112.2019.10.008

基于位置敏感模型的深度跟踪算法研究

查宇飞¹, 吴敏², 库涛³, 陈兵³, 张园强³

1. 西北工业大学计算机学院, 陕西西安 710072;
2. 95894部队, 北京 10200;
3. 空军工程大学航空工程学院, 陕西西安 710038

收稿日期:2018-06-15 修回日期:2019-04-09 出版日期:2019-10-25
- 通讯作者:
- 吴敏
- 作者简介:
- 查宇飞 男,1979年出生,湖北人.副教授,硕士生导师,主要从事机器学习、计算机视觉、目标跟踪、目标检测及人工智能等方面的研究.
- 基金资助:
- 国家自然科学基金 (No.61472442，No.61773397，No.61701524）; 陕西省科技新星资助 (No.2015kjxx-46）

Deep Tracking Algorithm Research Based on Location-Sensitive Model

ZHA Yu-fei¹, WU Min², KU Tao³, CHEN Bin³, ZHANG Yuan-qiang³

1. School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi 710072, China;
2. 95894 Troops, Beijing 10200, China;
3. Aeronautics Engineering College, Air Force Engineering University, Xi'an, Shaanxi 710038, China

Received:2018-06-15 Revised:2019-04-09 Online:2019-10-25 Published:2019-10-25
- Corresponding author:
- WU Min
- Supported by:
- National Natural Science Foundation of China (No.61472442, No.61773397, No.61701524); Funded by Science and Technology Nova Program of Shaanxi Province (No.2015kjxx-46)

摘要/Abstract

摘要： 视觉目标跟踪旨在寻找与跟踪目标具有相同语义信息的样本，并在视频中精确定位样本的位置.最近，深度分类模型被用来提取跟踪目标的深度嵌入式特征，然而，由于深度分类模型给予相同类别的样本一样的标签，这样容易导致跟踪模糊，甚至失败.为了解决这个问题，本文将样本的空间位置信息加入深度分类模型中，提出位置敏感损失函数.本文所提出的损失函数不仅继承了分类损失函数的特性，并根据样本的空间位置信息对相同标签的样本进行了排序.也就是说，本文的损失函数可以同时实现类间可分和类内排序.相比于分类损失函数，本文的损失函数更适合目标跟踪任务.本文在OTB100^[1]和VOT2016^[2]上进行了测试，结果表明本文算法可以实现较好的跟踪性能.

关键词: 目标跟踪, 深度学习, 位置敏感模型, 类内排序

Abstract: Visual target tracking is to find samples that have the same semantic information as the tracking target and pinpoint the position of the sample in the video. Recently, the deep classification model is used to extract the deep embedded features of the tracking target. However, since the deep classification model gives the same class of sample labels, it can easily lead to tracking and even failure. In order to solve this problem, we add the spatial location information of the sample to the deep classification model and propose a location-sensitive loss function. The proposed loss function not only inherits the characteristics of classification loss, but also sorts samples of the same label according to the spatial location information of samples. In other words, the loss function in this paper can also encourage the classification between classes and classes. Compared with the classification loss function, the loss function in this paper is more suitable for the task of target tracking. In this paper, OTB100 and VOT2016 were tested, the results show that this algorithm can achieve better tracking performance.

Key words: target tracking, deep learning, location-sensitive model, intra-class ordering

中图分类号:

TP391

查宇飞, 吴敏, 库涛, 等. 基于位置敏感模型的深度跟踪算法研究[J]. 电子学报, 2019, 47(10): 2076-2082.

ZHA Yu-fei, WU Min, KU Tao, et al. Deep Tracking Algorithm Research Based on Location-Sensitive Model[J]. Acta Electronica Sinica, 2019, 47(10): 2076-2082.

参考文献

[1] WU Y,LIM J,YANG M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[2] CEHOVIN L,LEONARDIS A,KRISTAN M.Visual object tracking performance measures revisited[J].IEEE Transactions on Image Processing,2016,25(3):1-1.
[3] 孙航,等.基于多阶段学习的相关滤波目标跟踪[J].电子学报,2017,45(10):2337-2342. SUN Hang,et al.Correlation filtering target tracking based on online multi-lifespan learning[J].Acta Electronica Sinica,2017,45(10):2337-2342.(in Chinese)
[4] 李康,李亚敏,等.基于卷积神经网络的鲁棒高精度目标跟踪算法[J].电子学报,2018,46(9):2087-2093. LI Kang,LI Ya-min,et al.A robust and accurate object tracking algorithm based on convolutional neural network[J].Acta Electronica Sinica,2018,46(9):2087-2093.
[5] REN S,HE K,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[J].IEEE Transactions on Image Processing,2017,39(6):1137-1149.
[6] MA C,HUANG J B,YANG X,et al.Hierarchical convolutional features for visual tracking[A].The 2015 IEEE International Conference on Computer Vision (ICCV)[C].US:IEEE,2015.3074-3082.
[7] JIA Y,SHELHAMER E,DONAHUE J,et al.Caffe:Convolutional architecture for fast feature embedding[A].Proceedings of the 22nd ACM International Conference on Multimedia[C].US:ACM,2014.675-678.
[8] 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].US:IEEE,2016.4293-4302.
[9] VEDALDI A,LENC K.Matconvnet:Convolutional neural networks for matlab[A].Proceedings of the 23rd ACM International Conference on Multimedia[C].US:ACM,2015.689-692.
[10] 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,2014,36(7):1442-1468.
[11] WU Y,LIM J,YANG M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,37(9):1834-1848.
[12] NAM H,BAEK M,HAN B.Modeling and propagating cnns in a tree structure for visual tracking[OL].arXiv Preprint,2016.arXiv:1608.07242.
[13] MARTIN D,ANDREAS R,FAHAD S,et al.Beyond correlation filters:learning continuous convolution operators for visual tracking[A].Proceedings of the European Conference on Computer Vision[C].Netherlands:Springer,2016.472-488.
[14] BERTINETTO L,VALMADRE J,et al.Staple:Complementary learners for real-time tracking[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].US:IEEE,2016.1401-1409.
[15] DANELLJAN M,HAGER G,SHAHBAZ KHAN F,et al.Adaptive decontamination of the training set:A unified formulation for discriminative visual tracking[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].US:IEEE,2016.1430-1438.
[16] ZHU G,PORIKLI F,LI H.Beyond local search:Tracking objects everywhere with instance-specific proposals[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].US:IEEE,2016.943-951.
[17] POSSEGGER H,MAUTHNER T,BISCHOF H.In defense of color-based model-free tracking[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].US:IEEE,2015.2113-2120.
[18] DANELLJAN M,HÄGER G,KHAN F S,et al.Discriminative scale space tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(8):1561-1575.
[19] JIN G,HAIBIN L,et al.Transfer learning based visual tracking with gaussian process regression[A].Proceedings of the European Conference on Computer Vision[C].Zurich,Switzerland:Springer,2014.188-203.
[20] SEVILLA-LARA L,LEARNED-MILLER E.Distribution fields for tracking[A].The 2012 IEEE Conference on Computer Vision and Pattern Recognition[C].US:IEEE,2012.1910-1917.

基于位置敏感模型的深度跟踪算法研究

Deep Tracking Algorithm Research Based on Location-Sensitive Model

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]	李钦, 刘伟, 牛朝阳, 宝音图, 惠周勃. 低信噪比下基于分裂EfficientNet网络的雷达信号调制方式识别[J]. 电子学报, 2023, 51(3): 675-686.
[2]	范兵兵, 何庭建, 张聪炫, 陈震, 黎明. 联合遮挡约束与残差补偿的特征金字塔光流计算方法[J]. 电子学报, 2023, 51(3): 648-657.
[3]	张聿远, 闫文君, 张立民. 基于多模态特征融合网络的空时分组码识别算法[J]. 电子学报, 2023, 51(2): 489-498.
[4]	许新征, 李杉. 基于特征膨胀卷积模块的轻量化技术研究[J]. 电子学报, 2023, 51(2): 355-364.
[5]	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.
[6]	张永梅, 孙捷. 基于动静态特征双输入神经网络的咳嗽声诊断COVID-19算法[J]. 电子学报, 2023, 51(1): 202-212.
[7]	袁海英, 成君鹏, 曾智勇, 武延瑞. Mobile_BLNet：基于Big-Little Net的轻量级卷积神经网络优化设计[J]. 电子学报, 2023, 51(1): 180-191.
[8]	王神龙, 雍宇, 吴晨睿. 基于伪孪生神经网络的低纹理工业零件6D位姿估计[J]. 电子学报, 2023, 51(1): 192-201.
[9]	李滔, 董秀成, 林宏伟. 基于深监督跨尺度注意力网络的深度图像超分辨率重建[J]. 电子学报, 2023, 51(1): 128-138.
[10]	郭晓轩, 冯其波, 冀振燕, 郑发家, 杨燕燕. 多线激光光条图像缺陷分割模型研究[J]. 电子学报, 2023, 51(1): 172-179.
[11]	贾童瑶, 卓力, 李嘉锋, 张菁. 基于深度学习的单幅图像去雾研究进展[J]. 电子学报, 2023, 51(1): 231-245.
[12]	何滢婕, 刘月峰, 边浩东, 郭威, 张小燕. 基于Informer的电池荷电状态估算及其稀疏优化方法[J]. 电子学报, 2023, 51(1): 50-56.
[13]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[14]	李雪莹, 王田路, 梁鹏, 王翀. 基于系统模型的用户评论中非功能需求的自动分类[J]. 电子学报, 2022, 50(9): 2079-2089.
[15]	琚长瑞, 秦晓燕, 袁广林, 李豪, 朱虹. 尺度敏感损失与特征融合的快速小目标检测方法[J]. 电子学报, 2022, 50(9): 2119-2126.