期刊文献+

基于超像素的单目标跟踪算法研究

Study of Single Target Tracking Algorithm Based on Superpixel
下载PDF
导出
摘要 超像素能够降低图像的冗余信息,减少图像后续处理的复杂度,已受到了国内外学者的广泛关注。为了降低运动目标跟踪过程中受内外因素影响而发生漂移的概率,本文提出了一种单目标跟踪算法。首先分析了运动目标跟踪算法和超像素分割算法的概念原理和发展现状,然后基于SLIC超像素分割算法和粒子滤波算法构建运动目标跟踪算法。本算法能够较好地实现判别式跟踪,具有较好的鲁棒性和准确性。 Superpixels can reduce the redundant information of images, and it can also reduce the complexity of the subsequent im-age processing. So up to now superpixels have been widely concerned by scholars at home and abroad. In order to reduce the proba-bility of drifting in the process of moving target tracking which may be affected by internal and external factors, one single targettracking algorithm is proposed in this paper. Firstly, the concept and development of moving target tracking algorithm and superpix-el segmentation algorithm are analyzed. Then, a moving object tracking algorithm is constructed based on SLIC superpixel segmen-tation algorithm and particle filter algorithm. The algorithm can achieve discrimitive tracking better, and has better robustness andaccuracy.
作者 邱晓荣
出处 《电脑知识与技术》 2018年第11Z期201-202,共2页 Computer Knowledge and Technology
基金 江苏高校品牌专业建设工程资助项目(PPZY2015C240) 无锡职业技术学院校级科研项目(ZK201704)
关键词 超像素 图像分割 SLIC 目标跟踪 Superpixel Image Segmentation SLIC Target Tracking
  • 相关文献

参考文献6

二级参考文献71

  • 1王超,侯丽敏.一种新的高斯混合模型参数估计算法[J].上海大学学报(自然科学版),2005,11(5):475-480. 被引量:3
  • 2侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,32(4):603-617. 被引量:255
  • 3毛晓波,谢晓芳,张晓林.消除运动物体阴影的最大色度差分检测法[J].电子技术应用,2007,33(1):61-63. 被引量:9
  • 4KORNPROBST P,DERICHE R,AUBERT G. Image sequence analysis via partial difference equations[ J]. Mathematical Imaging and Vision, 1999,11 ( 1 ) :5- 26.
  • 5ELGAMMAL A, DURAISWAMI R, HARWOOD D, et al. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance [ J]. Proceedings of the IEEE, 2002,90(7) :1151- 1163.
  • 6TANG Yi, LIU Wei-Ming, XIONG Liang. Improving robustness and accuracy in moving object detection using section-distribution background model[ C ]//Proc of the 4th International Conference on Natural Computation. 2008 : 167- 174.
  • 7STAUFFER C, GRIMSON W E L. Adaptive background mixture models for real-time tracking[ C ]//Proc of IEEE Conference on Computer Vision and Pattern Recogniton. 1999:246-252.
  • 8STAUFFER C, GRIMSON W E L. Learning patterns of activity using real-time tracking[J]. IEEE Trans on Pattern Analysis and Machine intelligence, 2000,22 ( 8 ) :747- 757.
  • 9MAGEE D. Tracking multiple vehicle using foreground, background and motion models [ J ]. image and Vision Computing, 2004,22 (2) :143- 155.
  • 10陈宜稳,王威,王润生.分块建模和点建模联合的背景重建方法[C]//全国第18届计算机技术与应用(CACIS)学术会议论文集:计算机技术与应用进展.2007:1007-1010.

共引文献231

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部