基于加速鲁棒特征和多示例学习的目标跟踪算法

doi:10.11772/j.issn.1001-9081.2016.11.2974

计算机应用 ›› 2016, Vol. 36 ›› Issue (11): 2974-2978.DOI: 10.11772/j.issn.1001-9081.2016.11.2974

• 第十六届中国粗糙集与软计算联合学术会议(CRSSC 2016)论文 • 上一篇下一篇

基于加速鲁棒特征和多示例学习的目标跟踪算法

白晓红¹, 温静¹, 赵雪¹, 陈金广²

1. 山西大学计算机与信息技术学院, 太原 030006;
2. 西安工程大学计算机科学学院, 西安 710048

收稿日期:2016-04-25 修回日期:2016-05-30 出版日期:2016-11-10 发布日期:2016-11-12
通讯作者: 温静
作者简介:白晓红(1989-),女,山西大同人,硕士研究生,主要研究方向:计算机视觉;温静(1982-),女,山西晋中人,副教授,博士,CCF会员,主要研究方向:计算机视觉、图像处理、模式识别;赵雪(1992-),女,山西晋中人,硕士研究生,主要研究方向:计算机视觉;陈金广(1977-),男,河南镇平人,副教授,博士,主要研究方向:多源信息融合、目标跟踪。
基金资助:
国家自然科学基金资助项目（61201453，61201118）；山西省基础研究计划项目（2014021022-2）；山西省高等学校科技创新项目（2015108）。

target tracking algorithm based on the speeded up robust features and multi-instance learning

BAI Xiaohong¹, WEN Jing¹, ZHAO Xue¹, CHEN Jinguang²

1. School of Computer and Information Technology, Shanxi University, Taiyuan Shanxi 030006, China;
2. School of Computer Science, Xi'an Polytechnic University, Xi'an Shaanxi 710048, China

Received:2016-04-25 Revised:2016-05-30 Online:2016-11-10 Published:2016-11-12
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61201453, 61201118), the Basic Research Project in Shanxi Province (2014021022-2), the Higher School Science and Technology Innovation Project in Shanxi Province (2015108).

摘要/Abstract

摘要： 针对照明变化、形状变化、外观变化和遮挡对目标跟踪的影响，提出一种基于加速鲁棒特征（SURF）和多示例学习（MIL）的目标跟踪算法。首先，提取目标及其周围图像的SURF特征；然后，将SURF描述子引入到MIL中作为正负包中的示例；其次，将提取到的所有SURF特征采用聚类算法实现聚类，建立视觉词汇表；再次，通过计算视觉字在多示例包的重要程度，建立“词-文档”矩阵，并且求出包的潜在语义特征通过潜在语义分析（LSA）；最后，通过包的潜在语义特征训练支持向量机（SVM），使得MIL问题可以依照有监督学习问题进行解决，进而判断是否为感兴趣目标，最终实现视觉跟踪的目的。通过实验，明确了所提算法对于目标的尺度缩放以及短时局部遮挡的情况都有一定的鲁棒性。

关键词: 加速鲁棒特征, 多示例学习, 潜在语义分析, 目标跟踪, 支持向量机

Abstract: Concerning the influence of changing light, shape, appearance, as well as occlusion on target tracking, a target tracking algorithm based on Speeded Up Robust Feature (SURF) and Multi-Instance Learning (MIL) was proposed. Firstly, the SURF features of the target and its surrounding image were extracted. Secondly, SURF descriptor was introduced to the MIL as the examples in positive and negative bags. Thirdly, all the extracted SURF features were clustered, and a visual vocabulary was established. Fourthly, a "word document" matrix was establish by calculating the importance of the visual words in bag, and the latent semantic features of the bag was got by Latent Semantic Analysis (LSA). Finally, Support Vector Machine (SVM) was trained with the latent semantic features of the bag, so that MIL problem could be handled in accordance with the supervised learning problem. The experimental results show that the robustness and efficiency of the proposed algorithm under the variation of scale, gesture and appearance, as well as short-term partial occlusion.

Key words: Speeded Up Robust Feature (SURF), Multi-Instance Learning (MIL), Latent Semantic Analysis (LSA), target tracking, Support Vector Machine (SVM)

中图分类号:

TP391.4

白晓红, 温静, 赵雪, 陈金广. 基于加速鲁棒特征和多示例学习的目标跟踪算法[J]. 计算机应用, 2016, 36(11): 2974-2978.

BAI Xiaohong, WEN Jing, ZHAO Xue, CHEN Jinguang. target tracking algorithm based on the speeded up robust features and multi-instance learning[J]. Journal of Computer Applications, 2016, 36(11): 2974-2978.

参考文献

[1] 单勇,王润生. 适应灰度和光照变化的运动目标跟踪方法[J]. 计算机辅助设计与图形学学报,2006,18(2):283-288.(SHAN Y, WANG R S. Tracking of moving objects with intensity and luminance changes[J]. Journal of Computer-Aided Design & Computer Graphics, 2006,18(2):283-288.)
[2] 郑增国,宣士斌,桑高丽,等. 一种改进的Mean Shift目标跟踪算法——针对视频对象部分遮挡和光照变化[J]. 广西民族大学学报(自然科学版),2012,18(1):50-54.(ZHENG Z G,XUAN S B,SANG G L, et al. A robust mean shift algorithm for target tracking-under partial occlusion and illumination variations[J]. Journal of Guangxi University for Nationalities (Natural Science Edition),2012,18(1):50-54.)
[3] 林明秀,刘伟佳,张达旭, 等. 适应光照变化的车辆目标跟踪算法[C]//2007中国控制与决策学术年会论文集.沈阳:控制与决策,2007:4.(LIN M X,LIU W J,ZHANG D X, et al. Algorithm of vehicle tracking adapting light changing[C]//Proceedings of the 2007 Chinese Control and Decision Conference. Shenyang:Control and Decision, 2007:4.)
[4] 左军毅,赵春晖,梁彦,等. 一种具有跟踪外观变化目标能力的均值漂移算法[J]. 计算机科学,2007,34(10):244-246.(ZUO J Y, ZHAO C H, LIANG Y, et al. A mean shift tracker with the ability to track object with changing appearance[J]. Computer Science,2007, 34(10):244-246.)
[5] 贾旭. 基于局部外观模型的目标跟踪方法研究[D]. 大连:大连理工大学,2013:1-49.(JIA X. Research of object tracking based on local appearance model[D]. Dalian:Dalian University of Technology,2013:1-49.)
[6] 王漫. 基于改进主动形状模型的目标跟踪方法研究[D]. 合肥:中国科学技术大学, 2010:1-44.(WANG M. Target tracking method based on improved active shape model research[D]. Hefei:University of Science and Technology of China, 2010:1-44.)
[7] 史久根, 王祥澍, 韩江洪. 基于形状感应的运动目标跟踪算法[J]. 计算机工程, 2011,37(22):143-144.(SHI J G, WANG X S, HAN J H. Moving object tracking algorithm based on shape induction[J]. Computer Engineering, 2011,37(22):143-144.)
[8] 彭勃兴.图像序列跟踪中的遮挡问题研究[D]. 西安:西安电子科技大学, 2014:1-46.(PENG B X. Research on occlusion in image sequence tracking[D].Xi'an:Xidian University,2014:1-46.)
[9] 薛陈,朱明,刘春香. 遮挡情况下目标跟踪算法综述[J]. 中国光学与应用光学,2009,2(5):388-394.(XUE C, ZHU M,LIU C X. Review of tracking algorithms under occlusions[J]. Chinese Journal of Optics and Applied Optics, 2009,2(5):388-394.)
[10] MA L. The shade problem study in target tracking[D]. Jinan:Shandong University, 2006:1-58.(马丽. 目标跟踪中的遮挡问题研究[D]. 济南:山东大学, 2006:1-58.)
[11] KOLLER D, DANⅡLIDIS K, NAGEL H. Model-based object tracking in monocular image sequences of road traffic scenes[J]. International Journal of Computer Vision,1993,10(3):257-281.
[12] 邢藏菊,曲延锋,王守觉. 静态灰度图像中的人脸快速检测[J]. 计算机辅助设计与图形学学报,2002,14(5):401-403.(XING C J,QU Y F,WANG S J. Face detection on gray-scale static image with complex background[J]. Journal of Computer Aided Design & Computer Graphics, 2002,14(5):401-403.)
[13] HARRIS C G, STEPHENS M J. A combined corner and edge detector[C]//Processing of the 4th Alvey Vision Conference. Plessey Research Roke Manor, UK:The Plessey Company, 1988:147-151.
[14] SMITH S M, BRADY J M. SUSAN-a new approach to low level image processing[J]. International Journal of Computer Vision,1997,23(1):45-78.
[15] MIKOLAJCZYK K, SCHMID C. Scale & affine invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86.
[16] SHI J B, TOMASI C. Good features to track[C]//Proceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 1994:593-600.
[17] TOMMASINI T,FUSIELLO A, TRUCCO E, et al. Making good features track better[C]//Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 1998:178-183.
[18] 刘静寒,钟辉.基于特征点匹配的自适应目标跟踪算法[J]. 微型机与应用, 2015,38(8):17-19. (LIU J H, ZHONG H. An adaptive object tracking algorithm based on feature-points matching[J]. Microcomputer & Its Applications, 2015, 38(8):17-19.)
[19] BAY H, TUYTELAARS T, GOOL L V. SURF:speeded up robust features[J]. Computer Vision & Image Understanding, 2006, 110(3):404-417.
[20] 梅振顺,战荫伟,钟左峰.基于SURF特征的目标跟踪[J].中国体视学与图像分析,2011,16(1):28-32.(MEI Z S, ZHAN Y W, ZHONG Z F. Video object tracking based on SURF features[J]. Chinese Journal of Stereology and Image Analysis, 2011,16(1):28-32.)
[21] 李大湘,赵小强,刘颖,等. 融合SIFT和MIL的红外人脸识别方法[J]. 西安邮电学院学报, 2012,17(4):15-20.(LI D X, ZHAO X Q, LIU Y, et al. Infrared face recognition method by integration of SIFT and MIL[J]. Journal of Xi'an University of Posts and Telecommunications, 2012,17(4):15-20.)
[22] WU Y, LIM J, YANG M H. Online object tracking:a benchmark[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2013:2411-2418.
[23] KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-learning-detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,34(7):1409-1422.
[24] BABENKO B, YANG M H, BELONGIE S. Robust object tracking with online multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33(8):1619-1632.
[25] ZHANG K, ZHANG L, YANG M H. Real-time compressive tracking[C]//Proceedings of the 12th European Conference on Computer Vision. Berlin:Springer-Verlag, 2012:864-877.

基于加速鲁棒特征和多示例学习的目标跟踪算法

target tracking algorithm based on the speeded up robust features and multi-instance learning

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]	姬张建, 任兴旺. 带旋转与尺度估计的全卷积孪生网络目标跟踪算法[J]. 计算机应用, 2021, 41(9): 2705-2711.
[2]	贾鹤鸣, 姜子超, 李瑶, 孙康健. 基于改进斑点鬣狗优化算法的同步优化特征选择[J]. 计算机应用, 2021, 41(5): 1290-1298.
[3]	袁芊芊, 邓洪敏, 王晓航. 基于超像素快速模糊C均值聚类与支持向量机的柑橘病虫害区域分割[J]. 计算机应用, 2021, 41(2): 563-570.
[4]	钟莎, 黄玉清. 基于孪生区域候选网络的无人机指定目标跟踪[J]. 计算机应用, 2021, 41(2): 523-529.
[5]	李凯, 李洁. 基于pinball损失的结构模糊多分类支持向量机算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3104-3112.
[6]	童林, 官铮. 改进鲸鱼优化支持向量机的交通流量模糊粒化预测[J]. 计算机应用, 2021, 41(10): 2919-2927.
[7]	陆荣秀, 陈明明, 杨辉, 朱建勇. 基于溶液图像时序特征的元素组分含量动态监测系统[J]. 计算机应用, 2021, 41(10): 3075-3081.
[8]	张杰, 常天庆, 戴文君, 郭理彬, 张雷. 基于相关滤波与颜色概率模型的目标跟踪算法[J]. 计算机应用, 2020, 40(6): 1774-1782.
[9]	张健铭, 施元昊, 徐正蓺, 魏建明. 基于误差预测的自适应UWB/PDR融合定位算法[J]. 计算机应用, 2020, 40(6): 1755-1762.
[10]	黄功, 赵永平, 谢云龙. 基于局部密度的加权一类支持向量机算法及其在涡轴发动机故障检测中的应用[J]. 计算机应用, 2020, 40(3): 917-924.
[11]	王杨, 赵红东. 基于改进粒子群优化的支持向量机与情景感知的人体活动识别[J]. 计算机应用, 2020, 40(3): 665-671.
[12]	赵一, 段兴, 谢仕义, 梁春林. 面向特定目标自识别的交通图像语义检索方法[J]. 计算机应用, 2020, 40(2): 553-560.
[13]	何祥宇, 李静, 杨数强, 夏玉杰. 基于ET-PHD滤波器和变分贝叶斯近似的扩展目标跟踪算法[J]. 计算机应用, 2020, 40(12): 3701-3706.
[14]	李卉, 杨志霞. 基于Rescaled Hinge损失函数的多子支持向量机[J]. 计算机应用, 2020, 40(11): 3139-3145.
[15]	牛晓可, 黄伊鑫, 徐华兴, 蒋震阳. 基于听皮层神经元感受野的强噪声环境下说话人识别[J]. 计算机应用, 2020, 40(10): 3034-3040.