首页 > 论文 > 激光与光电子学进展 > 54卷 > 9期(pp:91006--1)

基于隐马尔可夫模型和分块特征匹配的目标跟踪算法

Object Tracking Algorithm Based on Hidden Markov Model and Block Feature Matching

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为解决运动目标跟踪过程中由于遮挡、光照变化、尺度变化等因素导致的目标易丢失以及传统Camshift跟踪算法中跟踪窗口易发散等问题, 提出一种融合优化的隐马尔可夫模型(HMM)和分块特征匹配的运动目标跟踪算法。首先, 利用主成分分析(PCA)结合特征位置对目标仿射尺度不变特征变换(ASIFT)特征进行降维生成PCA-ASIFT特征, 保留目标关键信息; 其次, 采用粒子滤波最优特征位置优化目标PCA-ASIFT特征的HMM参数; 最后, 通过HSV直方图模型建立目标分块, 赋予不同目标分块相应权重并结合分块特征匹配以改善Camshift算法实现运动目标跟踪。实验结果表明, 在自然场景下, 本文算法能够取得较好的运动目标跟踪效果, 对遮挡、尺度变化等具有较好的稳健性。

Abstract

In the process of moving object tracking, in order to solve the problems that the object is easy to loss because of the occlusion, illumination fluctuation, scale variation and other factors, and the tracking window of the traditional Camshift algorithm is easy to diverge, a moving object tracking algorithm is proposed based on the fusion of optimized hidden Markov model (HMM) and the block feature matching. Firstly, the principal component analysis (PCA) combined with the feature position is used to reduce the dimension of the affine scale invariant feature transformation (ASIFT) features to generate PCA-ASIFT features which can retain the key information of the object. Then, the of the PCA-ASIFT features can be optimized by using the optimal feature positions of the particle filter. Finally, the object blocks are established by HSV histogram model and the different weights are assigned to different blocks and the integration block features matching, which can improve the Camshift algorithm to accomplish the moving object tracking. The experimental results show that the proposed algorithm can achieve better tracking effect of moving object in natural scenes, and it has bette robustness to occlusion, scale variation and so on.

投稿润色
补充资料

中图分类号:TP391.4

DOI:10.3788/lop54.091006

所属栏目:图像处理

基金项目:江苏省自然科学基金(BK20140265)、常州市科技计划项目(CJ20160010)

收稿日期:2017-04-26

修改稿日期:2017-05-08

网络出版日期:--

作者单位    点击查看

陆兵:常州轻工职业技术学院信息工程系, 江苏 常州 213164
顾苏杭:常州轻工职业技术学院信息工程系, 江苏 常州 213164

联系人作者:陆兵(lub@czili.edu.cn)

备注:陆兵(1967-), 男, 本科, 副教授, 主要从事计算机测量与控制方面的研究。

【1】Wang Jing, Song Ce, Yang Libao. Grabcut combined particle filter algorithm for tracking target[J]. Chinese Journal of Scientific Instrument, 2014, 35(12): 20-27.
王 晶, 宋 策, 杨立保. 融合GrabCut的粒子滤波目标跟踪算法[J]. 仪器仪表学报, 2014, 35(12): 20-27.

【2】Xiu Chunbo, Wei Shian. Camshift tracking with saliency histogram[J]. Optics and Precision Engineering, 2015, 23(6): 1749-1757.
修春波, 魏世安. 显著性直方图模型的Camshift跟踪方法[J]. 光学 精密工程, 2015, 23(6): 1749-1757.

【3】Li Yanping, Lin Jianhui, Yang Ningxue. Algorithm of moving target tracking based on SIFT feature optical flow[J]. Computer Science, 2015, 42(11): 305-309.
李艳萍, 林建辉, 杨宁学. 一种基于SIFT特征光流的运动目标跟踪算法[J]. 计算机科学, 2015, 42(11): 305-309.

【4】Jiang Shan, Zhang Rui, Han Guangliang, et al. Moving object tracking based on multi-feature fusion in the complex background gray image[J]. Chinese Optics, 2016, 9(3): 320-328.
江 山, 张 锐, 韩广良, 等. 复杂背景灰度图像下的多特征融合运动目标跟踪[J]. 中国光学, 2016, 9(3): 320-328.

【5】He Tingting, Rui Jianwu, Wen La. Accelerating ASIFT based on CPU/GPU synergetic parallel computing[J]. Computer Science, 2014, 41(5): 14-19.
何婷婷, 芮建武, 温 腊. CPU-GPU协同计算加速ASIFT算法[J]. 计算机科学, 2014, 41(5): 14-19.

【6】Zhu Bo, Dai Xianzhong, Li Xinde, et al. An ASIFT algorithm with masks for feature extraction[J]. Chinese Journal of Computers, 2015, 38(6): 1202-1211.
朱 博, 戴先中, 李新德, 等. 一种带有“遮罩”的ASIFT特征提取算法[J]. 计算机学报, 2015, 38(6): 1202-1211.

【7】Dong Wenhui, Chang Faliang, Li Tianping. Adaptive fragments-based target tracking method fusing color histogram and SIFT features[J]. Journal of Electronics & Information Technology, 2013, 35(4): 770-776.
董文会, 常发亮, 李天平. 融合颜色直方图及SIFT特征的自适应分块目标跟踪方法[J]. 电子与信息学报, 2013, 35(4): 770-776.

【8】Hou Zhiqiang, Huang Anqi, Yu Wangsheng, et al. Non-rigid object tracking based on joint matching of SIFT features[J]. Systems Engineering and Electronics, 2015, 37(6): 1417-1423.
侯志强, 黄安奇, 余旺盛, 等. 利用SIFT特征联合匹配的非刚体目标跟踪算法[J]. 系统工程与电子技术, 2015, 37(6): 1417-1423.

【9】Codreanu V, Dong F, Liu B Q, et al. GPU-ASIFT: a fast fully affine-invariant feature extraction algorithm[C]. 2013 International Conference on High Performance Computing and Simulation(HPCS), 2013: 474-481.

【10】Gan Ling, Zou Kuanzhong, Liu Xiao. Pedestrian detection based on PCA dimension reduction of multi-feature cascade[J]. Computer Science, 2016, 43(6): 308-311.
甘 玲, 邹宽中, 刘 肖. 基于PCA降维的多特征级联的行人检测[J]. 计算机科学, 2016, 43(6): 308-311.

【11】Zhang Zhiyu, Meng Linghui, Lei Tao. Adaptive gradient reconstruction for watershed based image segmentation[J]. Journal of Image and Graphics, 2014, 19(10): 1430-1437.
张志禹, 孟令辉, 雷 涛. 自适应梯度重建分水岭分割算法[J]. 中国图象图形学报, 2014, 19(10): 1430-1437.

【12】Qi W, Hou Y X, Wu L F, et al. A pose robust face recognition approach by combining PCA-ASIFT and SSIM[C]Proceedings of 9th Chinese Conference on Biometric Recognition, 2014, 8833: 163-172.

【13】Chen Hongda, Pu Hanye, Wang Bin, et al. Image euclidean distance-based manifold dimensionality reduction algorithm for hyperspectral imagery[J]. Journal of Infrared and Millimeter Waves, 2013, 32(5): 450-455.
陈宏达, 普晗晔, 王 斌, 等. 基于图像欧式距离的高光谱图像流形降维算法[J]. 红外与毫米波学报, 2013, 32(5): 450-455.

【14】Zhang Wenda, Xu Yuelei, Ni Jiacheng, et al. Image target recognition method based on multi-scale block convolutional neural network[J]. Journal of Computer Applications, 2016, 36(4): 1033-1038.
张文达, 许悦雷, 倪嘉成, 等. 基于多尺度分块卷积神经网络的图像目标识别算法[J]. 计算机应用, 2016, 36(4): 1033-1038.

【15】Xue Mengxia, Peng Hui, Liu Shirong, et al. Scene object recognition based on visual saliency[J]. Control Engineering of China, 2016, 23(5): 687-692.
薛梦霞, 彭 晖, 刘士荣, 等. 基于视觉显著性的场景目标识别[J]. 控制工程, 2016, 23(5): 687-692.

【16】Zhang Ruyun, Xu Mingyan, Jiang Tao. Partial CSI based affinity propagation dynamic clustering algorithm[J]. Application Research of Computers, 2013, 30(5): 1455-1457.
张汝云, 许明艳, 江 涛. 一种基于隐马尔可夫模型的目标轨迹跟踪算法[J]. 计算机应用研究, 2013, 30(5): 1455-1457.

【17】Wang Xiuhui, Yan Ke. Human gait recognition using continuous density hidden Markov models[J]. Pattern Recognition & Artificial Intelligence, 2016, 29(8): 709-716.
王修晖, 严 珂. 基于连续密度隐马尔可夫模型的人体步态识别[J]. 模式识别与人工智能, 2016, 29(8): 709-716.

【18】Zhou Zhiping, Zhou Mingzhu, Li Wenhui. Object tracking algorithm based on hybrid particle filter and sparse representation[J]. Pattern Recognition & Artificial Intelligence, 2016, 29(1): 22-30.
周治平, 周明珠, 李文慧. 基于混合粒子滤波和稀疏表示的目标跟踪算法[J]. 模式识别与人工智能, 2016, 29(1): 22-30.

【19】Xu Weicun, Zhao Qingjie, Wang Yuxia, et al. Object tracking arithmetic based on importance ordering Monte Carlo particle filtering[J]. Journal of Beijing Institute of Technology, 2016, 36(1): 105-110.
许伟村, 赵清杰, 王宇霞, 等. 基于重要性排序蒙特卡洛粒子滤波的物体跟踪算法[J]. 北京理工大学学报, 2016, 36(1): 105-110.

【20】Huang Bin. Motion tracking algorithm based on adaptive observing particle filter[J]. Bulletin of Science and Technology, 2016, 32(3): 145-148.
黄 斌. 基于自适应观测粒子滤波的运动跟踪算法[J]. 科技通报, 2016, 32(3): 145-148.

【21】Godec M, Roth P M, Bischof H. Hough-based tracking of non-rigid objects[J]. Computer Vision and Image Understanding, 2013, 117(10): 1245-1256.

【22】Gu Suhang, Lu Bing, Rong Hailong. Moving target detection and tracking algorithm based on contour and ASIFT feature matching[J]. Computer Measurement & Control, 2016, 24(8): 267-271.
顾苏杭, 陆 兵, 戎海龙. 基于阈值判断的Camshift目标跟踪算法[J]. 计算机测量与控制, 2016, 24(8): 267-271.

引用该论文

Lu Bing,Gu Suhang. Object Tracking Algorithm Based on Hidden Markov Model and Block Feature Matching[J]. Laser & Optoelectronics Progress, 2017, 54(9): 091006

陆兵,顾苏杭. 基于隐马尔可夫模型和分块特征匹配的目标跟踪算法[J]. 激光与光电子学进展, 2017, 54(9): 091006

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF