基于四通道不可分小波的均值漂移目标跟踪方法

刘斌; 郑凯凯

doi:doi:10.3969/j.issn.1007-5461. 2018.01.003

量子电子学报, 2018, 35 (1): 13, 网络出版: 2018-01-30

基于四通道不可分小波的均值漂移目标跟踪方法

Mean shift object tracking method based on four channel non-separable wavelets

论文大纲

刘斌 ^*郑凯凯

作者单位

湖北大学计算机与信息工程学院, 湖北武汉 430062

图像处理计算机视觉目标跟踪不可分小波图像分割 image processing computer vision object tracking non-separable wavelets image segmentation

摘要

针对均值漂移跟踪算法中目标模型更新误差累计导致的后续跟踪误差变大,提出了一种基于四通道不可分小波的均值漂移目标跟踪方法。基于不可分小波对目标图像的分解,利用高频子图分割出准确的目标区域,将此区域的高频与低频特征值融合,进行均值漂移跟踪。在跟踪过程中使用基于目标轮廓的尺度与模型更新,并用子特征相关系数对目标特征模型进行自适应更新。结果表明提出的方法在跟踪场景和目标外观变化时具有实时性与准确性。与未进行图像分割的跟踪方法相比,提出的方法具有更好的跟踪精准度；与使用条件随机场(CRF)的跟踪方法相比,其具有更好的处理速度与精确性。

Abstract

In order to solve the problem that the cumulative error caused by model updating on mean shift object tracking becomes larger in the following tracking, a mean shift object tracking method based on four channel non-separable wavelets is presented. Based on the decomposition of target image by non-separable wavelets, the accurate target region is segmented by using high frequency sub-images. The high and low frequency characteristic values of this region are fused, and mean shift tracking is carried out. During tracking, the scale and model updating based on the target contour are used, and the adaptive updating of target feature model is carried out by using correlation coefficient of the sub-features. Results show that the proposed method has both real-time ability and accuracy in tracking the change of scene and target shape. Compared with the tracking methods without image segmentation, the proposed method has better tracking accuracy. Compared with the tracking method using conditional random field (CRF), it has better processing speed and accuracy.

参考文献

[1] Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean shift[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2000: 2142.

[2] Collins R, Liu Y. On-line selection of discriminative tacking features[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1631-1643.

[3] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619.

[4] Nummiaro K, Koller Meier E, Gool L V. An adaptive color-based particle filter[J]. Image and Vision Computing, 2003, 21(1): 99-110.

[5] Ning J, Zhang L, Zhang D, et al. Robust mean-shift tracking with corrected background-weighted histogram[J]. IET Computer Vision, 2012,(1): 62-69.

[6] Chu H X, Xie Z Y, Wang J X, et al. Mean shift target tracking with spatiogram corrected background-weighted histogram[J]. Control and Decision, 2014, 29(3): 528-532.

[7] Gao Lin, Tang Peng, Sheng Peng. Visual object tracking based on foreground segmentation and adaptive feature space selection[J]. Control and Decision(控制与决策), 2010, 25(2): 207-212(in Chinese).

[8] Ning J, Zhang L, Zhang D, et al. Scale and orientation adaptive mean shift tracking[J]. IET Computer Vision, 2012,(1): 52-61.

[9] Wang Yong, Tan Yihua, Tian Jinwen. New tracking algorithm based on mean shift with adaptive bandwidth of Kernel function[J]. Journal of Data Acquisition and Processing(数据采集与处理), 2009, 24(6): 762-76(in Chinese).

[10] Peng Ningsong, Yang Jie, et al. Automatic selection of Kernel-bandwidth for mean shift object tracking[J]. Journal of Software(软件学报), 2005, 1(9): 1542-1550(in Chinese).

[11] Quast K, Kaup A. Scale and shape adaptive mean shift object tracking in video sequences[C]. European Signal Processing Conference, 2015: 1-4.

[12] Zou Qingzhi, Huang Shan. Fast tracking algorithm based on mean shift algorithm[J]. Computer Science(计算机科学), 2017, 44(3) : 278-282(in Chinese).

[13] Chen Dingkun, Yang Yan. An improved mean-shift algorithm for moving targets tracking[J]. Semiconductor Optoelectronics(半导体光电), 2015, 3(1): 160-164(in Chinese).

[14] Chen Q, Micchelli C A, Peng S, et al. Multivariate filter banks having matrix factorizations[J]. Siam Journal on Matrix Analysis and Applications, 2003, 25(2): 517-531.

[15] Zhao Y, Liu Y, Wu X, et al. Retinal vessel segmentation: An efficient graph cut approach with retinex and local phase[J]. Plos One, 2015, 10(4): e0122332.

[16] Li G, Chen X, Shi F, et al. Automatic liver segmentation based on shape constraints and deformable graph cut in CT images[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5315.

[17] Wang Junming, Gao Lixin, Zhao Li. Grab-cut algorithm based on watershed presegmention[J]. Technical Acoustics(声学技术), 2008, 27(4): 179-182(in Chinese).

[18] Liu Bin, Peng Jiaxiong. Fusion method of multi-spectral image and panchromatic image based on four channels non-separable additive wavelets[J]. Chinese Journal of Computers(计算机学报), 2009, 32(2): 350-35(in Chinese).

刘斌, 郑凯凯. 基于四通道不可分小波的均值漂移目标跟踪方法[J]. 量子电子学报, 2018, 35(1): 13. LIU Bin, ZHENG Kaikai. Mean shift object tracking method based on four channel non-separable wavelets[J]. Chinese Journal of Quantum Electronics, 2018, 35(1): 13.

基于四通道不可分小波的均值漂移目标跟踪方法

关于本站 Cookie 的使用提示

全站搜索

基于四通道不可分小波的均值漂移目标跟踪方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索