[1]吴贵山,林淑彬,钟江华,等.区域损失函数的孪生网络目标跟踪[J].智能系统学报,2020,15(4):722-731.[doi:10.11992/tis.201910005]
　WU Guishan,LIN Shubin,ZHONG Jianghua,et al.Regional loss function based siamese network for object tracking[J].CAAI Transactions on Intelligent Systems,2020,15(4):722-731.[doi:10.11992/tis.201910005]
点击复制

区域损失函数的孪生网络目标跟踪

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 15 期数: 2020年第4期 页码: 722-731 栏目: 学术论文—机器学习 出版日期: 2020-07-05
Title:
Regional loss function based siamese network for object tracking
作者:
吴贵山1,2, 林淑彬1,2, 钟江华3, 杨文元1,2
1. 闽南师范大学 计算机学院，福建 漳州 363000;
2. 闽南师范大学 福建省粒计算及其应用重点实验室，福建 漳州 363000;
3. 闽南师范大学 信息与网络中心，福建 漳州 363000
Author(s):
WU Guishan1,2, LIN Shubin1,2, ZHONG Jianghua3, YANG Wenyuan1,2
1. School of Computer Science, Minnan Normal University, Zhangzhou 363000, China;
2. Fujian Key Laboratory of Granular Computing and Application, Minnan Normal University, Zhangzhou 363000, China;
3. Information and Network Center, Minnan Normal University, Zhangzhou 363000, China
关键词:
计算机视觉; 目标跟踪; 区域损失; 深度特征; 孪生网络; 卷积神经网络; 反向传播; VGG网络
Keywords:
computer vision; object tracking; regional loss; depth features; siamese network; convolutional neural network; back propagation; VGG network
分类号:
TP391.4
DOI:
10.11992/tis.201910005
摘要:
针对预训练卷积神经网络提取的深度特征空间分辨率低，快速运动造成运动目标空间细节信息丢失等问题，提出用区域损失函数构建孪生网络的目标跟踪，进一步降低深度特征通道之间的冗余性，并减少高层信息丢失。利用线下预训练的VGG-16卷积神经网络提取深度特征，构成初始深度特征空间。通过区域损失函数构建特征和尺度选择网络，根据反向传播的梯度大小进行特征选择。对筛选后的特征进行拼接，融入到孪生网络中匹配跟踪。在OTB-2013、OTB-2015、VOT2016、TempleColor数据集上与其他算法对比。实验结果表明，该算法在快速运动、低分辨率等场景中表现出较好的跟踪精度和鲁棒性。
Abstract:
Due to the low spatial resolution of deep features extracted by pre-trained convolutional neural network, fast motion causes loss of spatial details of a moving object. This paper proposes a method to construct a siamese network for object tracking, so as to reduce the redundancy between the deep feature channels and the loss of high-level information. First, the VGG-16 convolutional neural network is trained offline to extract deep features and form the initial deep feature space. And then, the regional loss function is used to construct the feature and scale selection network. The feature is selected according to the gradient size of back propagation. Further, the selected features are spliced and integrated into the siamese network for matching tracking. By comparing OTB-2013, OTB-2015, VOT2016 and TempleColor benchmark datasets with other algorithms, it shows that the algorithm has preferable precision and robustness in the challenging scenarios such as fast motion and low resolution.
参考文献/References:
[1] ZHANG Shengping, YAO Hongxun, SUN Xin, et al. Sparse coding based visual tracking: review and experimental comparison[J]. Pattern recognition, 2013, 46(7): 1772-1788.
[2] FIAZ M, MAHMOOD A, JAVED S, et al. Handcrafted and deep trackers: recent visual object tracking approaches and trends[J]. ACM computing surveys, 2018, 52(2): 43.
[3] TANG Siyu, ANDRILUKA M, ANDRES B, et al. Multiple people tracking by lifted Multicut and person re-identification[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 3701-3710.
[4] LEE K H, HWANG J N. On-road pedestrian tracking across multiple driving recorders[J]. IEEE transactions on multimedia, 2015, 17(9): 1429-1438.
[5] 彭文亮, 梁祝, 李智峰. 基于机器视觉的无人机识别系统算法分析[J]. 电子设计工程, 2019, 27(11): 150-153
PENG Wenliang, LIANG Zhu, LI Zhifeng. Algorithm analysis of UAV recognition system based on machine vision[J]. Electronic design engineering, 2019, 27(11): 150-153
[6] 王杰, 蒋明敏, 花晓慧, 等. 基于投影直方图匹配的双目视觉跟踪算法[J]. 智能系统学报, 2015, 10(5): 775-782
WANG Jie, JIANG Mingmin, HUA Xiaohui, et al. Binocular object tracking method using projection histogram matching[J]. CAAI transactions on intelligent systems, 2015, 10(5): 775-782
[7] SONG Yibing, MA Chao, GONG Lijun, et al. CREST: convolutional residual learning for visual tracking[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 2574-2583.
[8] TENG Zhu, XING Junliang, WANG Qiang, et al. Robust object tracking based on temporal and spatial deep networks[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 1153-1162.
[9] SUN Chong, WANG Dong, LU Huchuan, et al. Correlation tracking via joint discrimination and reliability learning[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 489-497.
[10] SUN Chong, WANG Dong, LU Huchuan, et al. Learning spatial-aware regressions for visual tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 8962-8970.
[11] 宁欣, 李卫军, 田伟娟, 等. 一种自适应模板更新的判别式KCF跟踪方法[J]. 智能系统学报, 2019, 14(1): 121-126
NING Xin, LI Weijun, TIAN Weijuan, et al. Adaptive template update of discriminant KCF for visual tracking[J]. CAAI transactions on intelligent systems, 2019, 14(1): 121-126
[12] BERTINETTO L, VALMADRE J, HENRIQUES J F, et al. Fully-convolutional Siamese networks for object tracking[C]//Proceedings of European Conference on Computer Vision. Amsterdam, the Netherlands, 2016: 850-865.
[13] GUO Qing, FENG Wei, ZHOU Ce, et al. Learning dynamic Siamese network for visual object tracking[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 1781-1789.
[14] 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. Honolulu, USA, 2017: 5000-5008.
[15] NAM H, HAN B. Learning multi-domain convolutional neural networks for visual tracking[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 4293-4302.
[16] DANELLJAN M, H?GER G, KHAN F S, et al. Learning spatially regularized correlation filters for visual tracking[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015: 4310-4318.
[17] DANELLJAN M, BHAT G, KHAN FS, et al. ECO: efficient convolution operators for tracking[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 6931-6939.
[18] HUANG Chen, LUCEY S, RAMANAN D. Learning policies for adaptive tracking with deep feature cascades[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 105-114.
[19] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. 2015: arXiv: 1409.1556v6.
[20] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 770-778.
[21] LI Bo, YAN Junjie, WU Wei, et al. High performance visual tracking with Siamese region proposal network[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake, USA, 2018: 8971-8980.
[22] WANG Qiang, ZHANG Li, BERTINETTO L, et al. Fast online object tracking and segmentation: a unifying approach[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019: 1328-1338.
[23] WU Yi, LIM J, YANG M H. Online object tracking: a benchmark[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013: 2411-2418.
[24] WU Yi, LIM J, YANG M H. Object Tracking Benchmark[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(9): 1834-1848.
[25] KRISTAN M, LEONARDIS A, MATAS J, et al. The visual object tracking VOT2016 challenge results[C]//Proceedings of European Conference on Computer Vision. Amsterdam, The Netherlands, 2016: 777-823.
[26] LIANG Pengpeng, BLASCH E, LING Haibin. Encoding color information for visual tracking: algorithms and benchmark[J]. IEEE transactions on image processing, 2015, 24(12): 5630-5644.
[27] FAN Heng, LING Haibin. Parallel tracking and verifying: a framework for real-time and high accuracy visual tracking[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 5487-5495.
[28] GALOOGAHI H K, FAGG A, LUCEY S. Learning background-aware correlation filters for visual tracking[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 1144-1152.
[29] 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. Las Vegas, USA, 2016: 1401-1409.
[30] LI Yang, ZHU Jianke, HOI S C H, et al. Robust estimation of similarity transformation for visual object tracking[C]//Proceedings of AAAI Conference on Artificial Intelligence. Hawaii, USA, 2019: 8666-8673.
[31] DANELLJAN M, ROBINSON A, KHAN F S, et al. Beyond correlation filters: learning continuous convolution operators for visual tracking[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherlands, 2016: 472-488.
[32] ZHANG Tianzhu, XU Changsheng, YANG M H. Multi-task correlation particle filter for robust object tracking[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 4819-4827.
[33] MA Chao, HUANG Jiabin, YANG Xiaokang, et al. Hierarchical convolutional features for visual tracking[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015: 3074-3082.
相似文献/References:
[1]夏 凡,王 宏.基于局部异常行为检测的欺骗识别研究[J].智能系统学报,2007,2(5):12.
　XIA Fan,WANG Hong.Methodologies for deception detection based on abnormal b ehavior[J].CAAI Transactions on Intelligent Systems,2007,2():12.
[2]王绍钰 蔡自兴,陈爱斌.改进的粒子滤波器目标跟踪方法[J].智能系统学报,2008,3(3):189.
　WANG Shao-yu,CAI Zi-xing,CHEN Ai-bin.Improved object tracking method for particle filters[J].CAAI Transactions on Intelligent Systems,2008,3():189.
[3]刘 清,吴志刚,窦 琴,等.粒子滤波的视频目标跟踪算法研究[J].智能系统学报,2009,4(6):538.[doi:10.3969/j.issn.1673-4785.2009.06.012]
　LIU Qing,WU Zhi-gang,DOU Qin,et al.A particle filtering algorithm for tracking moving objects in videos[J].CAAI Transactions on Intelligent Systems,2009,4():538.[doi:10.3969/j.issn.1673-4785.2009.06.012]
[4]伍 明,孙继银.一种机器人未知环境下动态目标跟踪交互多模滤波算法[J].智能系统学报,2010,5(2):127.
　WU Ming,SUN Ji-yin.An interacting multiple model filtering algorithm for mobile robots to improve tracking of moving objects in unknown environments[J].CAAI Transactions on Intelligent Systems,2010,5():127.
[5]杨 戈,刘 宏.视觉跟踪算法综述[J].智能系统学报,2010,5(2):95.
　YANG Ge,LIU Hong.Survey of visual tracking algorithms[J].CAAI Transactions on Intelligent Systems,2010,5():95.
[6]李 金,胡文广.基于颜色的快速人体跟踪及遮挡处理[J].智能系统学报,2010,5(4):353.
　LI Jin,HU Wen-guang.Tracking fast movement using colors while accommodating occlusion[J].CAAI Transactions on Intelligent Systems,2010,5():353.
[7]刘宏,李哲媛,许超.视错觉现象的分类和研究进展[J].智能系统学报,2011,6(1):1.
　LIU Hong,LI Zheyuan,XU Chao.The categories and research advances of visual illusions[J].CAAI Transactions on Intelligent Systems,2011,6():1.
[8]刘侠,陶冶,邢春.统计差分与自启动的Camshift跟踪算法[J].智能系统学报,2011,6(4):355.
　LIU Xia,TAO Ye,XING Chun.An objective tracking Camshift algorithm based onautomatic startup and the statistical differential method[J].CAAI Transactions on Intelligent Systems,2011,6():355.
[9]叶果,程洪,赵洋.电影中吸烟活动识别[J].智能系统学报,2011,6(5):440.
　YE Guo,CHENG Hong,ZHAO Yang.moking recognition in movies[J].CAAI Transactions on Intelligent Systems,2011,6():440.
[10]史晓鹏,何为,韩力群.采用Hough变换的道路边界检测算法[J].智能系统学报,2012,7(1):81.
　SHI Xiaopeng,HE Wei,HAN Liqun.A road edge detection algorithm based on the Hough transform[J].CAAI Transactions on Intelligent Systems,2012,7():81.
[11]刘威,靳宝,周璇,等.基于特征融合及自适应模型更新的相关滤波目标跟踪算法[J].智能系统学报,2020,15(4):714.[doi:10.11992/tis.201803036]
　LIU Wei,JIN Bao,ZHOU Xuan,et al.Correlation filter target tracking algorithm based on feature fusion and adaptive model updating[J].CAAI Transactions on Intelligent Systems,2020,15():714.[doi:10.11992/tis.201803036]
[12]林椹尠,郑兴宁,吴成茂.结合模糊特征检测的鲁棒核相关滤波跟踪法[J].智能系统学报,2021,16(2):323.[doi:10.11992/tis.201912010]
　LIN Zhenxian,ZHENG Xingning,WU Chengmao.Robust KCF tracking algorithm combined with fuzzy feature detection[J].CAAI Transactions on Intelligent Systems,2021,16():323.[doi:10.11992/tis.201912010]
[13]周士琪,王耀南,钟杭.融合视觉显著性再检测的孪生网络无人机目标跟踪算法[J].智能系统学报,2021,16(3):584.[doi:10.11992/tis.202101035]
　ZHOU Shiqi,WANG Yaonan,ZHONG Hang.Siamese network combined with visual saliency re-detection for UAV object tracking[J].CAAI Transactions on Intelligent Systems,2021,16():584.[doi:10.11992/tis.202101035]
[14]林淑彬,吴贵山,姚文勇,等.基于光照自适应动态一致性的无人机目标跟踪[J].智能系统学报,2022,17(6):1093.[doi:10.11992/tis.202110023]
　LIN Shubin,WU Guishan,YAO Wenyong,et al.Unmanned aerial vehicles object tracking based on illumination adaptive dynamic consistency[J].CAAI Transactions on Intelligent Systems,2022,17():1093.[doi:10.11992/tis.202110023]
[15]姜文涛,张大鹏.优化分类的弱目标孪生网络跟踪研究[J].智能系统学报,2023,18(5):984.[doi:10.11992/tis.202211043]
　JIANG Wentao,ZHANG Dapeng.Research on weak object tracking based on Siamese network with optimized classification[J].CAAI Transactions on Intelligent Systems,2023,18():984.[doi:10.11992/tis.202211043]
[16]黄昱程,肖子旺,武丹凤,等.时空融合与判别力增强的孪生网络目标跟踪方法[J].智能系统学报,2024,19(5):1218.[doi:10.11992/tis.202306005]
　HUANG Yucheng,XIAO Ziwang,WU Danfeng,et al.Spatiotemporal fusion and discriminative augmentation for improved Siamese tracking[J].CAAI Transactions on Intelligent Systems,2024,19():1218.[doi:10.11992/tis.202306005]

备注/Memo

收稿日期:2019-10-09。
基金项目:国家自然科学青年基金项目（61703196）；福建省自然科学基金项目（2018J01549）
作者简介:吴贵山，高级讲师，主要研究方向为计算机视觉和机器学习。发表学术论文7篇;林淑彬，讲师，主要研究方向为计算机视觉和模式识别;杨文元，副教授，博士，主要研究方向为计算机视觉、模式识别和机器学习
通讯作者:杨文元.E-mail:yangwycn@163.com

更新日期/Last Update: 2020-07-25
Copyright © 《 智能系统学报》 编辑部
地址：（150001）黑龙江省哈尔滨市南岗区南通大街145-1号楼 电话：0451- 82534001、82518134　邮箱：tis@vip.sina.com