多特征融合的Camshift算法及其进一步改进

doi:10.3724/SP.J.1087.2012.02814

计算机应用 ›› 2012, Vol. 32 ›› Issue (10): 2814-2816.DOI: 10.3724/SP.J.1087.2012.02814

多特征融合的Camshift算法及其进一步改进

林建华,刘党辉,邵显奎

装备学院航天装备系,北京101416

收稿日期:2012-04-19 修回日期:2012-05-25 发布日期:2012-10-23 出版日期:2012-10-01
通讯作者: 林建华
作者简介:林建华(1987-),男,山东寿光人,硕士研究生,主要研究方向：图像处理、机器视觉;
刘党辉(1972-),男,陕西武功人,副教授,主要研究方向：图像处理、模式识别；
邵显奎（1987-）,男,山东聊城人,硕士研究生,主要研究方向：信号检测与处理。

Multi-feature fusion Camshift algorithm and its further improvement

LIN Jian-hua,LIU Dang-hui,SHAO Xian-kui

Department of Aerospace Equipment, Institute of Equipment, Beijing 101416, China

Received:2012-04-19 Revised:2012-05-25 Online:2012-10-23 Published:2012-10-01
Contact: LIN Jian-hua

摘要/Abstract

摘要： 基于颜色核的Camshift算法可以有效实现简单场景下的目标跟踪,但在光线变化明显或目标与背景颜色相近的场景下易受干扰。为此,采用颜色、边缘梯度、纹理等多个特征自适应融合的方式改进算法,提高算法应对光线变化的能力；并通过修正特征直方图、设置合理搜索范围对算法进行进一步改进,解决相似背景的干扰问题。实验结果显示,在光照变化明显或目标与背景特征相近的场景中,改进的算法与传统算法相比具有更高的跟踪精度。

关键词: 目标跟踪, Camshift算法, 多特征融合, 特征直方图, 纹理特征

Abstract: The Camshift algorithm based on color-kernel can effectively track objects in a simple background, but it is easy to be interfered by illumination variation or the similar color object in the background. To improve the algorithms ability to respond to illumination variation, a multi-feature adaptive fusion scheme based on color, shape and texture was proposed. And further improvements have been proposed through modifying feature histogram and setting a reasonable search region to solve the problem of similar background. The experimental results show that the improved algorithm has higher tracking accuracy than traditional algorithm in the scene with illumination variation or similar background.

Key words: object tracking, Camshift algorithm, multi-feature fusion, feature histogram, texture feature

中图分类号:

TP391.41

林建华刘党辉邵显奎. 多特征融合的Camshift算法及其进一步改进[J]. 计算机应用, 2012, 32(10): 2814-2816.

LIN Jian-hua LIU Dang-hui SHAO Xian-kui. Multi-feature fusion Camshift algorithm and its further improvement[J]. Journal of Computer Applications, 2012, 32(10): 2814-2816.

参考文献

［1］徐萧萧. 基于特征学习与特征联想的视觉跟踪算法研究［D］. 合肥: 中国科学技术大学, 2010. ［2］ FASHING M, TORNASI C. Mean shift is a bound optimization［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 471-474. ［3］ BRADSKI G R. Computer vision face tracking for use in a perceptual user interface［J］. Intel Technology Journal, 1998,2(2):1-15. ［4］ ZOU TENGYUE, TANG XIAOQI, SONG BAO. Improved Camshift tracking algorithm based on silhouette moving detection［C］ // 2011 Third International Conference on Multimedia Information Networking and Security. Washington,DC: IEEE Computer Society, 2011: 11-15. ［5］ EXNER D. Fast and robust Camshift tracking［C］// 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2010: 9-16. ［6］ STOLKIN R, FLORESCU I, KAMBEROV G. An adaptive background model for Camshaft tracking with a moving camera［C］// Proceedings of the Sixth International Conference. Kolkata: Indian Statistical Institute, 2007: 147-151. ［7］ STOLKIN R, FLORESCU I, BARON M, et al.Efficient visual servoing with the ABC shift tracking algorithm［C］ // Proceedings of the IEEE International Conference on Robotics and Automation. Pasadena: IEEE Computer Society, 2008: 3219-3224. ［8］ ALLEN J G, XU R Y D, JIN J S. Object tracking using Camshift algorithm and multiple quantized feature spaces［C］ // Proceedings of the Pan-Sydney Area Workshop on Visual Information Processing. Darlinghurst, Australia: ACM Press, 2003: 3-7. ［9］李巍,赵英凯,钱厚亮. 一种基于颜色和纹理的运动目标跟踪方法［J］. 计算机仿真, 2011, 28(1): 273-276. ［10］ COLLINS R T, LIU YANXI, LEORDEANU M. Online selection of discriminative tracking features［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1631-1643. ［11］ TAN XIAOYANG, TRIGGS B. Enhanced local texture feature sets for face recognition under difficult lighting conditions［C］ //Analysis and Modeling of Face and Gestures. Berlin: Springer-Verlag, 2007: 168-182. ［12］ BROX T, ROUSSON M, DERICHE R,et al. Colour, texture, and motion in level set based segmentation and tracking［J］. Image and Vision Computing, 2010,28(3):376-390.

[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]	蒋考林, 白玮, 张磊, 陈军, 潘志松, 郭世泽. 基于多通道图像深度学习的恶意代码检测[J]. 计算机应用, 2021, 41(4): 1142-1147.
[3]	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.
[4]	郭可心, 张宇翔. 基于多层次空间注意力的图文评论情感分析方法[J]. 计算机应用, 2021, 41(10): 2835-2841.
[5]	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.
[6]	余英东, 杨怡, 林澜. 结合纹理特征分析的图像风格转换网络[J]. 计算机应用, 2020, 40(3): 638-644.
[7]	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.
[8]	石国强, 赵霞. 基于联合优化的强耦合孪生区域推荐网络的目标跟踪算法[J]. 计算机应用, 2020, 40(10): 2822-2830.
[9]	杨博, 蔺素珍, 禄晓飞, 李大威, 秦品乐, 左健宏. 基于多特征融合与分层数据关联的空中红外多目标跟踪方法[J]. 计算机应用, 2020, 40(10): 3075-3080.
[10]	俞皓芳, 孙力帆, 付主木. 基于改进K-means++聚类的多扩展目标跟踪算法[J]. 计算机应用, 2020, 40(1): 271-277.
[11]	何祥宇, 于斌, 夏玉杰. 粒子概率假设密度平滑器异常平滑问题的解决方法[J]. 计算机应用, 2020, 40(1): 299-303.
[12]	郎大鹏, 丁巍, 姜昊辰, 陈志远. 基于多特征融合的恶意代码分类算法[J]. 计算机应用, 2019, 39(8): 2333-2338.
[13]	贾永超, 何小卫, 郑忠龙. 融合重检测机制的卷积回归网络目标跟踪算法[J]. 计算机应用, 2019, 39(8): 2247-2251.
[14]	刘玉珍, 蒋政权, 赵娜. 基于近邻三值模式和协作表示的三维掌纹识别[J]. 计算机应用, 2019, 39(6): 1690-1695.
[15]	韩玉兰, 韩崇昭. 非线性系统的多扩展目标跟踪算法[J]. 计算机应用, 2019, 39(5): 1318-1324.

多特征融合的Camshift算法及其进一步改进

Multi-feature fusion Camshift algorithm and its further improvement

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