多特征融合的Camshift运动目标跟踪算法

doi:10.11896／j.issn.1002-137X.2018.07.044

摘要/Abstract

摘要： 传统的Camshift算法以颜色直方图为特征对目标进行跟踪,对刚性目标的跟踪具有较强的鲁棒性。当目标受到颜色相近的干扰物干扰或者部分遮挡时,其跟踪效果和准确度不太理想。为此,提出一种多特征融合的Camshift目标跟踪算法。首先,对目标的颜色特征、边缘特征和空间信息进行提取和处理,得到颜色空间直方图和空间边缘方向直方图;然后,分别在Camshift算法框架下得到目标匹配中心位置,采用每一帧图像的相似度向量得到权值系数,通过自适应加权融合的方法得到最优中心位置。实验结果表明,相较于传统的Camshift目标跟踪算法和改进的复杂特征融合的Meanshift算法,所提方法能够更有效地克服颜色干扰、目标重叠遮挡对跟踪效果的影响,避免了目标在跟踪过程中丢失的问题,突破了传统方法的局限性。

关键词: Camshift算法, 多特征, 空间边缘方向直方图, 颜色空间直方图

Abstract: Traditional Camshift algorithm tracks target characterized by the color histogram,with strong robustness for rigid target tracking.However,the tracking effects and accuracy may not be ideal when they are interfered by the objects with similar color.In view of this,a Camshift tracking algorithm of multi-feature fusion was proposed.Firstly,by extracting and processing the color feature,edge feature as well as the spatial information of target,the color space histogram and spatial edge orientation histogram are obtained.Then the central locations of target matching are obtained respectively under the framework of Camshift algorithm and the weight coefficient is obtained by using the similarity vectors of each image.The optimal central location is obtained through the method of adaptive weighted fusion.The experimental results show that compared with the traditional Camshift target tracking and the improved Meanshift algorithm based on complex feature fusion,the proposed method can effectively overcome the problems of color interference and overlapping occlusion that hamper tracking effects.It can avoid the target loss in the process of tracking which breaks throughthe limitations of traditional methods.

Key words: Camshift algorithm, Color space histogram, Multi-feature, Spatial edge orientation histogram

中图分类号:

TP391.4

吴玮,郑娟毅,杜乐. 多特征融合的Camshift运动目标跟踪算法[J]. 计算机科学, 2018, 45(7): 252-258. https://doi.org/10.11896／j.issn.1002-137X.2018.07.044

WU Wei, ZHENG Juan-yi ,DU Le. Camshift Tracking Moving Target Algorithm Based on Multi-feature Fusion[J]. Computer Science, 2018, 45(7): 252-258. https://doi.org/10.11896／j.issn.1002-137X.2018.07.044

参考文献

[1]YILMAZ A,JAVED O,SHAH M.Object tracking:A survey[J].ACM Computing Surveys,2006,38(4):1-45.
[2]杨杰,张翔.视频目标检测和跟踪及其应用[M].上海:上海交通大学出版社,2012.
[3]BRADSKI G R.Computer vision face tracking for use in a perceptual user interface[C]∥IEEE Workshop on Applications of Computer Vision.1998:214-219.
[4]SIRIKUNTAMAT N,SATOH S,CHALIDABHONGSE T H.Vehicle tracking in low hue contrast based on CAMShift and background subtraction[C]∥International Joint Conference on Computer Science and Software Engineering.IEEE,2015:58-62.
[5]XIU C,BA F.Target tracking based on the improved Camshift method[C]∥Chinese Control and Decision Conference.IEEE,2016:3600-3604.
[6]ZHU Y,XU B.A robust object tracking method combiningshape descriptor and adaptive background camshift[C]∥International Conference on Natural Computation.IEEE,2015:930-933.
[7]HAN Z,ZHANG R,WEN L,et al.Moving Object TrackingMethod Based on Improved Camshift Algorithm[C]∥International Conference on Industrial Informatics－Computing Technology,Intelligent Technology,Industrial Information Integration.IEEE,2016:91-95.
[8]YANG X,FEI S M,LI G,et al.Improved Mean shift tracking algorithm based on complicated feature fusion.Control and Decision,2014,29(7):1297-1300.(in Chinese)
杨欣,费树岷,李刚,等.基于复杂特征融合的改进Meanshift目标跟踪[J].控制与决策,2014,29(7):1297-1300.
[9]LIU W J,ZHANG Y J.Edge-color-histogram and Kalman filter-based real-time object tracking .Journal of Tsinghua University Science and Technology,2008,48(7):1104-1107.(in Chinese)
刘惟锦,章毓晋.基于Kalman滤波和边缘直方图的实时目标跟踪[J].清华大学学报自然科学版,2008,48(7):1104-1107.
[10]YIMIT A,HAGIHARA Y,MIYOSHI T,et al.2-D direction histogram based entropic thresholding[J].Neurocomputing,2013,120(10):287-297.
[11]SHEN X M,ZHOU J X,XU T W.Minority Costume Image Retrieval by Fusion of Color Histogram and Edge Orientation Histogram∥International Conference on Computer and Information Science.IEEE,2016:1-7.
[12]KATJA N,ESTHER K M.Object tracking with an adaptive color-based particle filter[C]∥Proceedings of the 24th DAGM Symposium on Pattern Recognition.2002:353-360.
[13]NAVNEET D,BILL T.Histograms of oriented gradients for human detection[C]∥Computer Society Conference on Computer Vision & Pattern Recognition.2005:886-893.
[14]HAN B,LUO Y.Accurate face detection by combining multiple classifiers using locally assembled histograms of orientedgra-dients[C]∥International Conference on Audio.2012:106-111.
[15]ZHANG Y K,LI Y F,SUN J G.Image retrieval based on multi-feature fusion[J].Journal of Computer Applications,2015,35(2):495-498.(in Chinese)
张永库,李云峰,孙劲光.基于多特征融合的图像检索[J].计算机应用,2015,35(2):495-498.
[16]QU J B.Convergence analysis of kernel based Camshift algorithm.Journal on Numerical Methods and Computer Applications,2011,32(2):148-158.(in Chinese)
曲巨宝.基于核函数的Camshift算法的收敛性分析[J].数值计算与计算机应用,2011,32(2):148-158.
[17]XU W J,HOU Z Q,YU W S, et al. Fusing mulit feature object tracking algorithm based on background weighting .Journal of Air Fouce Engineering Universitu(Natrnal Science Edition),2015,16(3):71-76.(in Chinese)
许婉君,侯志强,余旺盛,等.背景加权的多特征融合目标跟踪算法[J].空军工程大学学报(自然科学版),2015,16(3):71-76.

相关文章 15

[1]	张源, 康乐, 宫朝辉, 张志鸿. 基于Bi-LSTM的期货市场关联交易行为检测方法 Related Transaction Behavior Detection in Futures Market Based on Bi-LSTM 计算机科学, 2022, 49(7): 31-39. https://doi.org/10.11896/jsjkx.210400304
[2]	程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[3]	郁舒昊, 周辉, 叶春杨, 王太正. SDFA:基于多特征融合的船舶轨迹聚类方法研究 SDFA:Study on Ship Trajectory Clustering Method Based on Multi-feature Fusion 计算机科学, 2022, 49(6A): 256-260. https://doi.org/10.11896/jsjkx.211100253
[4]	李鹏祖, 李瑶, Ibegbu Nnamdi JULIAN, 孙超, 郭浩, 陈俊杰. 基于多特征融合的重叠组套索脑功能超网络构建及分类 Construction and Classification of Brain Function Hypernetwork Based on Overlapping Group Lasso with Multi-feature Fusion 计算机科学, 2022, 49(5): 206-211. https://doi.org/10.11896/jsjkx.210300049
[5]	瞿中, 陈雯. 基于空洞卷积和多特征融合的混凝土路面裂缝检测 Concrete Pavement Crack Detection Based on Dilated Convolution and Multi-features Fusion 计算机科学, 2022, 49(3): 192-196. https://doi.org/10.11896/jsjkx.210100164
[6]	牛富生, 郭延哺, 李维华, 刘文洋. 基于序列特征融合的蛋白质可溶性预测 Protein Solubility Prediction Based on Sequence Feature Fusion 计算机科学, 2022, 49(1): 285-291. https://doi.org/10.11896/jsjkx.201100117
[7]	张曼, 李杰, 朱新忠, 沈霁, 成昊天. 基于改进DCGAN算法的遥感数据集增广方法 Augmentation Technology of Remote Sensing Dataset Based on Improved DCGAN Algorithm 计算机科学, 2021, 48(6A): 80-84. https://doi.org/10.11896/jsjkx.200700185
[8]	吕金娜, 邢春玉, 李莉. 基于多特征融合的细粒度视频人物关系抽取 Video Character Relation Extraction Based on Multi-feature Fusion and Fine-granularity Analysis 计算机科学, 2021, 48(4): 117-122. https://doi.org/10.11896/jsjkx.200800160
[9]	栾晓, 李晓双. 基于多特征融合的人脸活体检测算法 Face Anti-spoofing Algorithm Based on Multi-feature Fusion 计算机科学, 2021, 48(11A): 409-415. https://doi.org/10.11896/jsjkx.210100181
[10]	原晓佩, 陈小锋, 廉明. 基于Haar-like和LBP的多特征融合目标检测算法 Improved Multi-feature Fusion Algorithm for Target Detection Based on Haar-like and LBP 计算机科学, 2021, 48(11): 219-225. https://doi.org/10.11896/jsjkx.201100174
[11]	吴宏涛, 刘力源, 孟颖, 荣亚鹏, 李路凯. 动态多特征融合的道路遗洒物威胁度分析方法 Novel Threat Degree Analysis Method for Scattered ObJects in Road Traffic Based on Dynamic Multi-feature Fusion 计算机科学, 2020, 47(6A): 196-205. https://doi.org/10.11896/JsJkx.190900066
[12]	胡宇佳, 甘伟, 朱敏. 基于多特征融合的增强子-启动子相互作用预测综述 Enhancer-Promoter Interaction Prediction Based on Multi-feature Fusion 计算机科学, 2020, 47(5): 64-71. https://doi.org/10.11896/jsjkx.191100027
[13]	金堃, 陈少昌. 步态识别现状与发展 Status and Development of Gait Recognition 计算机科学, 2019, 46(6A): 30-34.
[14]	吴璠, 李寿山, 周国栋. 基于LSTM和多特征组合的电影评论专业程度分类 Movie Review Professionalism Classification Using LSTM and Features Fusion 计算机科学, 2019, 46(6A): 74-79.
[15]	王晓, 邹泽伟, 李勃勃, 王静. 基于多特征融合的彩色图像声呐目标检测 Target Detection in Colorful Imaging Sonar Based on Multi-feature Fusion 计算机科学, 2019, 46(6A): 177-181.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed