基于改进的Heaviside核函数新的目标模型追踪算法
PDF下载 (354)吴 盈,陈 恳 *.基于改进的Heaviside核函数新的目标模型追踪算法[J].宁波大学学报(理工版),2014,27(04):33-37.DOI:
WU Ying,CHEN Ken *.New Target Model Based on Heaviside Kernel Function for Tracking[J].Journal of Ningbo University(Natural Science & Engineering Edition),2014,27(04):33-37.DOI:
| Title: | New Target Model Based on Heaviside Kernel Function for Tracking |
| 作者: | 吴 盈, 陈 恳 * |
| Author(s): | WU Ying, CHEN Ken * |
| 关键词: | Heaviside核函数; 新的目标模型; 颜色纹理直方图; 目标追踪 |
| Keywords: | Heaviside function; new target model; color-texture histogram; object tracking |
| 分类号: | TN919.8 |
| 文献标识码: | A |
| 摘要: | 为更好地解决前景和背景相似程度较大或目标运动较为复杂的问题, 提出了基于改进的Heaviside核函数新的目标模型追踪算法. 在初始帧中, 使用改进的Heaviside核函数来表示目标区域, 然后分别计算目标区域前景和背景元素的颜色纹理直方图特征分布, 并通过前景和背景特征分布差异建立新的目标模型, 它可更好地代表目标. 对于候选模型, 结合传统Epanechnikov核对目标模型建模, 通过Bhattacharyya系数进行迭代搜索, 最终收敛的位置即为下一帧的目标中心. 实验结果表明: 提出的算法和传统的Mean-shift算法和基于颜色纹理直方图的Mean-shift算法相比较精确度高、速度快、鲁棒性强. |
| Abstract: | In order to better solve the tracking problem with compromised target identification arising from the similarity between foreground and background or higher motion mobility, a new target model is put forward based on the modified Heaviside function. The target region is first represented by the proposed function, then the background and foreground color-texture histograms is constructed respectively in the region in the initial frame, in so doing the new target model is built through comparing the difference between the foreground and background model. In the candidate target area, the traditional Epanechnikov kernel is adopted in modeling target, and the target center is determined in the next frame using the Bhattacharyya coefficient. The experimental results show that the new algorithm performs better in accuracy and robustness than the traditional Mean-shift tracker and the existing color-texture-combined histograms based Mean shift. |
| 参考文献 /References: | [1] Comaniciu D, Ramesh V, Meer P. Kernel-Based Object Tracking[J]. IEEE Transcations on Pattern Analysis and Machine Intelligence, 2003, 25(5):564-575. [2] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis[J]. IEEE Trans on Pattern Analysis and Machine Itelligence, 2002, 24(5):603-619. [3] Jeyakar J, Babu R, Ramakrishnan K R. Robust object tracking with background-weighted local kernels[J]. Computer Vision and Image Understanding, 2009, 112(3): 296-309. [4] Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(7):971-987. [5] Heikkila M, Pietikainen M. A texture-based method for modeling the background and detecting moving objects[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2006, 28(4):657-662. [6] 宁纪锋, 吴成柯. 一种基于纹理模型的Mean-shift目标跟踪算法[J]. 模式识别与人工智能, 2007, 20(5):612- 618. [7] Ning J, Zhang L, Zhang D, et al. Robust object tracking using joint color-texture histogram[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2009, 23(7):1245-1263. [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] 宋晓琳, 王文涛, 张伟伟, 等. 基于LBP纹理和改进Camshift算子的车辆检测与跟踪[J]. 湖南大学学报: 自然科学版, 2013, 40(8):52-57. [10] Ning J, Zhang L, Zhang D, et al. Joint registration and active contour segmentation for object tracking[J]. IEEE Transactions on Circuits and Systems for Video Techno- logy, 2013, 23(9):1589-1597. |
| 备注/Memo: | 收稿日期: 2014-05-12. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/基金项目: 浙江省自然科学基金（Y1111061）; 宁波市自然科学基金（2014A610065）; 宁波大学学科项目（XKXL1308）.第一作者: 吴盈（1988－）, 女, 河南驻马店人, 在读硕士研究生, 主要研究方向: 视频目标跟踪及图像处理. E-mail: alina22@126.com*通信作者: 陈恳（1962－）, 男, 重庆人, 博士/副教授, 主要研究方向: 图像与视频分析处理及智能控制. E-mail: chenken@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
