基于颜色-纹理特征的目标跟踪

J4 ›› 2014, Vol. 36 ›› Issue (08): 1581-1587.

基于颜色-纹理特征的目标跟踪

姚原青,李峰,周书仁

（长沙理工大学计算机与通信工程学院，湖南长沙 410004）

收稿日期:2012-11-09 修回日期:2013-04-10 出版日期:2014-08-25 发布日期:2014-08-25
基金资助:
国家自然科学基金资助项目(60973113)；湖南省自然科学基金资助项目(12JJ6057)；长沙市科技计划资助项目(K120301511)；湖南省标准化战略项目(2011031)

Target tracking based on color and the texture feature

YAO Yuanqing,LI Feng,ZHOU Shuren

(School of Computer and Communication Engineering,
Changsha University of Science and Technology,Changsha 410004,China)

Received:2012-11-09 Revised:2013-04-10 Online:2014-08-25 Published:2014-08-25

摘要/Abstract

摘要：

针对传统的基于颜色特征目标跟踪算法在一些复杂场景中存在的跟踪不稳定性，提出一种基于颜色纹理特征的目标跟踪算法；在传统的基于颜色Meanshift的目标跟踪算法中加入纹理特征,在提取目标颜色特征的同时提取目标的纹理特征,并且采取串接原则，在搜索目标新位置时仍然沿用传统的基于颜色的均值漂移跟踪算法，但在每一次迭代过程搜寻目标最佳的位置点即特征相似最大的区域时，利用纹理特征来实现，并且采用八邻域搜索法（候选区域周围扩大八个大小相等的区域）来解决部分遮挡的问题。通过对比实验表明，该算法在复杂场景中表现出的实时性和鲁棒性较好。关键词：

关键词: 目标跟踪, 颜色特征, 均值漂移, 纹理特征

Abstract:

In some complex scenes of tracking, the traditional color feature based target tracking algorithm may have the unstable tracking. To solve this problem, a color and texture feature based target tracking algorithm is proposed. The texture feature is added in the traditional color Meanshift based target tracking algorithm, and both the texture and the color features are extracted together. According to the sequence principle, the traditional color based mean drift tracking algorithm is still used to search the new position of the target, but, in each iteration process, the texture feature is used to search the optimal target position which has the largest similar feature. And the eight neighborhood search method (8 areas with the same size are expanded around the candidate area) is applied to solve the problem of partial occlusion. The comparative experiments show that the algorithm has better robustness and realtime performance in complex scenes.

Key words: target tracking;color features;Mean-shift;texture feature

姚原青,李峰,周书仁. 基于颜色-纹理特征的目标跟踪[J]. J4, 2014, 36(08): 1581-1587.

YAO Yuanqing,LI Feng,ZHOU Shuren. Target tracking based on color and the texture feature [J]. J4, 2014, 36(08): 1581-1587.

参考文献［10］

［1］	Wang Liang, Hu Weiming, Tan Tieniu. Recent developments in human motion analysis［J］. Pattern Recognition, 2003, 36(3):585601.
［2］	Sheng Zhiyuan. An adaptive target tracking algorithm based on multifeature fusion［C］∥Proc of International Conference on Biomedical Engineering and Computer Science, 2010:14.
［3］	Fukunaga K, Hostetler L D. The estimation of the gradient of a density function with applications in pattern recognition［J］.IEEE Transactions on Information Theory, 1975,21(1):3240.
［4］	Cheng Yizong. Mean shift, mode seeking, and clustering［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8):790799.
［5］	Comaniciu D, Meer P. Mean shift analysis and applications［C］∥Proc of the the 7th IEEE International Conference on Computer Vision, 1999:11971203.
［6］	Avidan S. Ensemble tracking［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29 (2):261271.
［7］	Pouladzadeh P, Semsarzadeh M, Hariri B, et al. An enhanced Meanshift and LBPbased face tracking method［C］∥Proc of 2011 IEEE International Conference on VCIMS 2011,2011:14.
［8］	Li Peihua. Image sequences moving target tracking method［M］. Beijing:Science Press,2010.(in Chinese)
［9］	Zhao Chunhui, Pan Quan, Liang Yan, et al. Video imagery moving targets analysis［M］. Beijing:National Defense Industry Press,2011.(in Chinese)
［10］	Chen Hengxin,Tang Yuanyan,Fang Bin,et al. For changes in illumination for face recognition the LBP improved method［J］. Computer Engineering and Applications, 2011,47(3):3031.(in Chinese)
［11］	Maenpaa T, Pietikainen M. Texture analysis with local binary patterns［M］∥Handbook of Pattern Recognition and Computer Vision 3 rd ed. Washington:World Scientific,2005:197216.
［12］	Ojala T,Pietikinen M. Multiresolution grayscale and rotation invariant texture classification with local binary patterns［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7):971987.
	附中文参考文献：
［8］	李培华.序列图像中运动目标跟踪方法［M］.北京:科学出版社,2010.
［9］	赵春晖,潘泉,梁彦,等.视频图像运动目标分析［M］.北京:国防工业出版社,2011.
［10］	陈恒鑫,唐远炎,房斌,等.用于变化光照下人脸识别的LBP改进方法［J］.计算机工程与应用,2011,47(3):3031.

[1]	崔克彬, 崔叶微. 基于卷积和Transformer的断路器动触头跟踪方法研究[J]. 计算机工程与科学, 2023, 45(07): 1236-1244.
[2]	杨冬英, 贺江鹏 . 针对机动目标的改进型交互多模型跟踪算法研究[J]. 计算机工程与科学, 2022, 44(04): 686-691.
[3]	冯琪堯, 张惊雷, . 基于混合注意力机制的目标跟踪算法[J]. 计算机工程与科学, 2022, 44(02): 276-282.
[4]	方梦华, 姜添, . 基于无监督学习的无人机目标跟踪[J]. 计算机工程与科学, 2021, 43(06): 1024-1031.
[5]	张晓丽, 张龙信, 肖满生, 左国才. 快速多域卷积神经网络和光流法融合的目标跟踪[J]. 计算机工程与科学, 2020, 42(12): 2217-2222.
[6]	徐亮, 张江, 张晶, 杨亚琦. 基于VGG网络的鲁棒目标跟踪算法[J]. 计算机工程与科学, 2020, 42(08): 1406-1413.
[7]	张晶, 黄浩淼, 王健敏, 保峻嵘. 融合CN跟踪算法改进的TLD实时目标跟踪算法[J]. 计算机工程与科学, 2020, 42(07): 1215-1225.
[8]	李星辰，柳晓鸣，成晓男. 融合YOLO检测的多目标跟踪算法[J]. 计算机工程与科学, 2020, 42(04): 665-672.
[9]	王杨1,2，向秀梅1,2，卢嘉1,2，郁振鑫1,2. 基于双目融合的无参考立体图像质量评价[J]. 计算机工程与科学, 2020, 42(03): 510-516.
[10]	黄云明1，张晶1,2，喻小惠1，陶涛3，龚力波4. 改进STC和SURF特征联合优化的目标跟踪算法[J]. 计算机工程与科学, 2019, 41(10): 1795-1802.
[11]	严春满，郝有菲，张迪，陈佳辉. 混合特征下最优阈值预测的图像匹配[J]. 计算机工程与科学, 2019, 41(10): 1803-1808.
[12]	火元莲，曹鹏飞，董俊松，石明. 基于融合特征的多尺度快速相关滤波跟踪算法[J]. 计算机工程与科学, 2019, 41(03): 559-566.
[13]	张晶，王旭,范洪博. 自适应目标变化的时空上下文抗遮挡跟踪算法[J]. 计算机工程与科学, 2018, 40(09): 1653-1661.
[14]	刘辉，代照坤，王龙. 基于Hu-GLCM的手势识别方法研究[J]. 计算机工程与科学, 2018, 40(03): 525-532.
[15]	秦煜1，吴静静1,2，安伟1,2，张美娟3. 基于融合特征的SURF配准算法[J]. 计算机工程与科学, 2017, 39(10): 1890-1895.