[1]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):984-993.[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(5):984-993.[doi:10.11992/tis.202211043]
点击复制
JIANG Wentao,ZHANG Dapeng.Research on weak object tracking based on Siamese network with optimized classification[J].CAAI Transactions on Intelligent Systems,2023,18(5):984-993.[doi:10.11992/tis.202211043]
优化分类的弱目标孪生网络跟踪研究
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
18
期数:
2023年第5期
页码:
984-993
栏目:
学术论文—机器学习
出版日期:
2023-09-05
- Title:
- Research on weak object tracking based on Siamese network with optimized classification
- Keywords:
- computer vision; object tracking; weak object; deformable convolution; prior spatial score; localization quality score; feature extraction; convolutional neural network; siamese network
- 分类号:
- TP391.4
- 摘要:
- 针对传统孪生网络算法对模糊、低分辨率等弱目标跟踪效果不佳的问题，提出了优化分类预测的孪生网络算法。首先通过引入可变形卷积模块，提高骨干网络特征提取能力，其次在分类分支中引入位置信息，提升算法对于目标的识别能力，最后使用轻量级的卷积神经网络进行分类预测和边界预测任务，在规避多尺度测试的同时，进一步利用了图像的语义信息，使跟踪结果具有较高的可信度。在OTB2015、VOT2018公共数据集上进行的大量实验表明，本文算法综合表现优于主流同类算法，对模糊、形变、快速运动等多种复杂场景具有较好的适应性。
- Abstract:
- To address the problem that traditional Siamese networks are poor in tracking weak objects in blurry and low resolution, this study proposed a Siamese network with optimized classification prediction. First, the feature extraction ability of the backbone network was improved by introducing a deformable convolution module. Second, this algorithm enhances the ability of the backbone network to extract features by introducing the location information in the classification branch. Finally, a lightweight convolutional neural network was used for the prediction of classification and boundary to further utilize the semantic information of the images while avoiding multiscale testing, making the tracking results more reliable. Many experiments have analyzed OTB2015 and VOT2018 datasets, and the results show that the comprehensive performance of this algorithm is better than those of the mainstream similar algorithms, demonstrating excellent adaptability to complex scenes such as motion blur, deformation, and fast motion.
- 参考文献/References:
-
[1] 李家宁, 田永鸿. 神经形态视觉传感器的研究进展及应用综述[J]. 计算机学报, 2021, 44(6): 1258-1286
LI Jianing, TIAN Yonghong. Recent advances in neuromorphic vision sensors: a survey[J]. Chinese journal of computers, 2021, 44(6): 1258-1286
[2] 朱向雷, 王海弛, 尤翰墨, 等. 自动驾驶智能系统测试研究综述[J]. 软件学报, 2021, 32(7): 2056-2077
ZHU Xianglei, WANG Haichi, YOU Hanmo, et al. Survey on testing of intelligent systems in autonomous vehicles[J]. Journal of software, 2021, 32(7): 2056-2077
[3] 韩玉仁, 李铁军, 杨冬. 增强现实中三维跟踪注册技术概述[J]. 计算机工程与应用, 2019, 55(21): 26-35
HAN Yuren, LI Tiejun, YANG Dong. Overview of 3D tracking registration technology in augmented reality[J]. Computer engineering and applications, 2019, 55(21): 26-35
[4] 王梦来, 李想, 陈奇, 等. 基于CNN的监控视频事件检测[J]. 自动化学报, 2016, 42(6): 892-903
WANG Menglai, LI Xiang, CHEN Qi, et al. Surveillance event detection based on CNN[J]. Acta automatica sinica, 2016, 42(6): 892-903
[5] TANG Siyu, ANDRILUKA M, ANDRES B, et al. Multiple people tracking by lifted multicut and person re-identification[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 3701?3710.
[6] ZHU Zheng, WU Wei, ZOU Wei, et al. End-to-end flow correlation tracking with spatial-temporal attention[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 548?557.
[7] 张长弓, 杨海涛, 王晋宇, 等. 基于深度学习的视觉单目标跟踪综述[J]. 计算机应用研究, 2021, 38(10): 2888-2895
ZHANG Changgong, YANG Haitao, WANG Jinyu, et al. Survey on visual single object tracking based on deep learning[J]. Application research of computers, 2021, 38(10): 2888-2895
[8] BERTINETTO L, VALMADRE J, HENRIQUES J F, et al. Fully-convolutional Siamese networks for object tracking[C]//European Conference on Computer Vision. Cham: Springer, 2016: 850?865.
[9] LI Bo, YAN Junjie, WU Wei, et al. High performance visual tracking with Siamese region proposal network[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 8971?8980.
[10] 刘如浩, 张家想, 金辰曦, 等. 基于可变形卷积的孪生网络目标跟踪算法[J]. 控制与决策, 2022, 37(8): 2049-2055
LIU Ruhao, ZHANG Jiaxiang, JIN Chenxi, et al. Target tracking based on deformable convolution Siamese network[J]. Control and decision, 2022, 37(8): 2049-2055
[11] DAI Jifeng, QI Haozhi, XIONG Yuwen, et al. Deformable convolutional networks[C]//2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 764?773.
[12] 尚欣茹, 温尧乐, 奚雪峰, 等. 孪生导向锚框RPN网络实时目标跟踪[J]. 中国图象图形学报, 2021, 26(2): 415-424
SHANG Xinru, WEN Yaole, XI Xuefeng, et al. Target tracking system based on the Siamese guided anchor region proposal network[J]. Journal of image and graphics, 2021, 26(2): 415-424
[13] TIAN Zhi, SHEN Chunhua, CHEN Hao, et al. FCOS: fully convolutional one-stage object detection[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2020: 9626?9635.
[14] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2999?3007.
[15] LI Xiang, WANG Wenhai, WU Lijun, et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection[J]. Advances in neural information processing systems, 2020, 33: 21002-21012.
[16] REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2020: 658?666.
[17] JIANG Borui, LUO Ruixuan, MAO Jiayuan, et al. Acquisition of localization confidence for accurate object detection[C]//European Conference on Computer Vision. Cham: Springer, 2018: 816?832.
[18] XU Yinda, WANG Zeyu, LI Zuoxin, et al. SiamFC++: towards robust and accurate visual tracking with target estimation guidelines[EB/OL]. (2019?11?14)[2021?01?01]. https://doi.org/10.48550/arXiv.1911.06188.
[19] DANELLJAN M, H?GER G, KHAN F S, et al. Convolutional features for correlation filter based visual tracking[C]//2015 IEEE International Conference on Computer Vision Workshop. Santiago: IEEE, 2016: 621?629.
[20] DANELLJAN M, BHAT G, KHAN F S, et al. ATOM: accurate tracking by overlap maximization[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2020: 4655?4664.
[21] ZHU Zheng, WANG Qiang, LI Bo, et al. Distractor-aware Siamese networks for visual object tracking[C]//European Conference on Computer Vision. Cham: Springer, 2018: 103?119.
[22] ZHANG Zhipeng, PENG Houwen. Deeper and wider Siamese networks for real-time visual tracking[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2020: 4586?4595.
[23] HE Anfeng, LUO Chong, TIAN Xinmei, et al. A twofold Siamese network for real-time object tracking[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4834?4843.
[24] WANG Qiang, ZHANG Li, BERTINETTO L, et al. Fast online object tracking and segmentation: a unifying approach[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2020: 1328?1338.
[25] NAM H, HAN B. Learning multi-domain convolutional neural networks for visual tracking[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 4293?4302.
- 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]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.[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():722.[doi:10.11992/tis.201910005]
[13]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]
[14]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]
[15]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]
[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:2022-11-30。
基金项目:国家自然科学基金项目（61172144）；辽宁省自然科学基金项目（20170540426）；辽宁省教育厅基金项目（LJYL049）.
作者简介:姜文涛，副教授，博士，主要研究方向为图像处理、模式识别、人工智能。参与国家及省级项目2项，发表学术论文20余篇;张大鹏，硕士研究生，主要研究方向为图像处理、模式识别、人工智能
通讯作者:姜文涛.E-mail：lntuwulue@163.com
更新日期/Last Update:
1900-01-01