基于改进巴氏指标和模型更新的视觉跟踪算法

黄安奇, 侯志强, 余旺盛, 刘翔

黄安奇, 侯志强, 余旺盛, 刘翔. 基于改进巴氏指标和模型更新的视觉跟踪算法[J]. 应用光学, 2015, 36(1): 52-57. DOI: 10.5768/JAO201536.0102001
引用本文: 黄安奇, 侯志强, 余旺盛, 刘翔. 基于改进巴氏指标和模型更新的视觉跟踪算法[J]. 应用光学, 2015, 36(1): 52-57. DOI: 10.5768/JAO201536.0102001
Huang An-qi, Hou Zhi-qiang, Yu Wang-sheng, Liu Xiang. Visual tracking algorithm based on improved Bhattacharyya coefficient and model update strategy[J]. Journal of Applied Optics, 2015, 36(1): 52-57. DOI: 10.5768/JAO201536.0102001
Citation: Huang An-qi, Hou Zhi-qiang, Yu Wang-sheng, Liu Xiang. Visual tracking algorithm based on improved Bhattacharyya coefficient and model update strategy[J]. Journal of Applied Optics, 2015, 36(1): 52-57. DOI: 10.5768/JAO201536.0102001

基于改进巴氏指标和模型更新的视觉跟踪算法

基金项目: 

国家自然科学基金项目(61175029,61473309);陕西省自然科学基金(2011JM8015)

详细信息
    作者简介:

    黄安奇(1988-),男,河北香河人,硕士研究生,主要从事图像处理、视觉跟踪方面的研究工作。 Email:13319270512@163.com

    通讯作者:

    黄安奇(1988-),男,河北香河人,硕士研究生,主要从事图像处理、视觉跟踪方面的研究工作。 Email:13319270512@163.com

  • 中图分类号: TN919.22; TP391.41

Visual tracking algorithm based on improved Bhattacharyya coefficient and model update strategy

  • 摘要: 传统的Mean Shift算法采用巴氏系数度量模型与候选模型之间的统计特征相似性,但是由于背景特征的影响,有时应用巴氏指标进行匹配得到最优解的位置并不一定是目标的实际位置,在跟踪过程中可能导致目标定位出现偏差。该文提出一种改进的巴氏系数相似度指标,指标由于引入了前景/背景置信值,能够有效抑制待匹配区域中背景特征的影响,突出目标特征的权重,与原始的巴氏指标相比,明显提高了目标匹配的准确性。基于改进的巴氏指标,对目标与背景区域双模型相似度系数进行综合分析,合理地判断干扰目标匹配的原因,从而采取相应的模型更新策略。采用4段具有挑战性的视频序列对5种跟踪算法进行了测试,通过定量实验分析可知,文中算法处理1帧视频所需的平均时间为75.76 ms,实时性仅次于原始的Mean Shift跟踪算法,同时跟踪误差在5种跟踪算法中取得了最优结果。实验结果表明,该算法能够有效抑制背景干扰和避免模型漂移,在不同的复杂场景下都具有一定的鲁棒性。
    Abstract: In the traditional mean shift tracking algorithm, the Bhattacharyya coefficient is an efficient method in image statistical feature matching;however, due to the influence of background feature, the optimal location obtained by Bhattacharyya coefficient may not be the exact target location. Thus, biased or even wrong location may be got in visual tracking. We presented an improved Bhattacharyya coefficient based on target-background confidence .The new coefficient effectively reduced the influence of background feature and emphasized the importance of target feature, which obviously improved the target matching accuracy compared to the original coefficient. In order to get an effective model update strategy, we synthetically analyzed the similarity of target model and background model, and estimated the reason of the disturbance. We used 4 challenging video sequences to test 5 tracking algorithms. The quantitative experimental analysis shows that the proposed algorithm has good real-time performance, it only takes 75.76 ms to track one frame and exceeds the other trackers in tracking precision. The experimental result shows the proposed algorithm can well restrain background disturbance, while effectively update the model and overcome the problem of model drifting, and the tracking algorithm is effective and robust.
  • [1]Wu Y, Lim J, Yang M H. Online object tracking: a benchmark [C]. Portland, United Stater:Proc. of Computer Vision and Pattern Recognition, 2013: 2411-2418.
    [2]Yang C J, Duraiswami R, Davis L. Efficient mean-shift tracking via anew similarity measure[C]. San Diego:Proc. of Computer Vision and Pattern Recognition, 2005: 176-183.
    [3]Khalid M, Malik M. Biased nature of Bhattacharyya coefficient in correlation of gray-scale objects[C]. Zagreb Croatia:International Symposium on Image and Signal Processing and Analysis, IEEE, 2005:209-214.
    [4]Liu Rongli, Jing Zhongliang. Robust kernel-based tracking algorithm with background contrasting[J]. Chinese Optics Letters, 2012,10(2): 021001.
    [5]Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577.
    [6]Jeyakar J, Babu R, Ramakrishnan K R. Robust object tracking with background-weighted local kernels[J]. Comput. Vis. Image Underst., 2009, 112(3): 296-309.
    [7]Chen Aibin, Cai Zixing, Dong Deyi. A tracking method based on weighted object and background[J]. Control and Decision, 2010, 25(8): 1246-1250.
    陈爱斌, 蔡自兴, 董德毅. 一种基于目标和背景加权的目标跟踪方法[J]. 控制与决策, 2010, 25(8): 1246-1250.
    [8]Ning J, Zhang L, Zhang D, et al. Robust mean shift tracking with corrected background-weighted histogram[J]. IET Computer Vision, 2012, 6(1): 62-69.
    [9]Wang Q, Chen F, Xu W L, et al. Object tracking via partial least squares analysis[J]. IEEE Transactions on Image Processing, 2012, 21(10): 4454-4465.
    [10]Matthews I, Ishikawa T, Baker S. The template update problem[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004,26(6): 810-815.
    [11]Qin Jian, Zeng Xiaoping, Zeng Hao. Dual template algorithm for mean-shift template update[J]. Application Research of Computers, 2009, 26(7): 2771-2774.
    覃剑, 曾孝平, 曾浩. 均值漂移跟踪的双模板更新算法[J]. 计算机应用研究, 2009, 26(7): 2771-2774.
    [12]Comaniciu D, Ramesh V, Meer P. Realtime tracking of non-rigid objects using mean shift[C]. Hilton Head Island, USA:Proc. of Computer Vision and Pattern Recognition, 2000:142-149.
  • 期刊类型引用(2)

    1. 王伟,周刚. 一种基于改进的巴氏系数的协同过滤推荐算法. 计算机应用研究. 2020(12): 3569-3571 . 百度学术
    2. 范舜奕,管桦,侯志强,余旺盛,戴铂. 利用选择性模型不定时更新的视觉跟踪算法. 中国图象图形学报. 2016(06): 745-755 . 百度学术

    其他类型引用(1)

计量
  • 文章访问数:  1617
  • HTML全文浏览量:  54
  • PDF下载量:  142
  • 被引次数: 3
出版历程
  • 刊出日期:  2015-01-14

目录

    /

    返回文章
    返回