遮挡环境下采用在线Boosting的目标跟踪

颜佳; 吴敏渊

doi:10.3788/OPE.20122002.0439

您当前的位置：

首页 >

文章列表页 >

遮挡环境下采用在线Boosting的目标跟踪

信息科学 | 更新时间：2020-08-12

- 遮挡环境下采用在线Boosting的目标跟踪
- On-line boosting based target tracking under occlusion
- 光学精密工程 2012年20卷第2期页码：439-446
- 作者机构：
  
  武汉大学电子信息学院,湖北武汉 430079
- 作者简介：
- 基金信息：
  
  国家自然科学基金面上项目(No.61072135)()
- DOI：10.3788/OPE.20122002.0439
  中图分类号： TP391
- 收稿日期：2011-09-19，
  
  修回日期：2011-11-10，
  
  网络出版日期：2012-02-25，
  
  纸质出版日期：2012-02-25
- 稿件说明：
移动端阅览
颜佳, 吴敏渊. 遮挡环境下采用在线Boosting的目标跟踪[J]. 光学精密工程, 2012,20(2): 439-446

YAN Jia, WU Min-yuan. On-line boosting based target tracking under occlusion[J]. Editorial Office of Optics and Precision Engineering, 2012,20(2): 439-446
颜佳, 吴敏渊. 遮挡环境下采用在线Boosting的目标跟踪[J]. 光学精密工程, 2012,20(2): 439-446 DOI： 10.3788/OPE.20122002.0439.

YAN Jia, WU Min-yuan. On-line boosting based target tracking under occlusion[J]. Editorial Office of Optics and Precision Engineering, 2012,20(2): 439-446 DOI： 10.3788/OPE.20122002.0439.

摘要

针对被跟踪目标在发生严重遮挡时采用基于自学习方法的在线Boosting算法易导致错误累积而产生"漂移"甚至目标丢失的问题

提出了一种基于子区域分类器的在线Boosting算法。首先

将特征池划分为多个子区域分类器对应的子区域特征池;然后

在跟踪过程中自适应地选取子区域分类器来组成强分类器以剔除被遮挡子区域对目标定位的影响;最后

采用对子区域特征池进行部分更新的方法有效解决了特征在线更新时的错误累积问题。对不同视频序列测试的结果表明

当目标大面积被遮挡时本算法能准确定位目标

目标大小为36 pixel40 pixel时的处理帧率为15 frame/s。与传统在线Boosting算法相比

本算法对发生严重遮挡的目标仍能进行准确跟踪。

Abstract

A new on-line boosting algorithm based on sub-regional classifiers was presented to solve the problem that traditional on-line boosting based tracking algorithm often leads to drifting or failure due to the accumulated error during on-line updating under serious occlusions. Firstly

the feature pool was divided into a number of sub-regional feature pools to correspond to their sub-regional classifiers. Then

the sub-regional classifiers were selected adaptively into a strong classifier to eliminate the influence of occluded sub-regions on the target location when occlusions took place. Finally

the sub-regional feature pools were updated partly to solve the problem of accumulated error during on-line learning. The proposed algorithm was tested with variant video sequences and results show that proposed algorithm achieves exact tracking for the object occluded

and the average computing frame rate is 15 frame/s when the object scale is 36 pixel40 pixel. In conclusion

the algorithm can satisfy the requirements of stability under occlusion as compared with the original on-line boosting algorithm.

关键词

Keywords

references

颜佳,陈淑珍,吴敏渊,等. 应用Mean Shift和分块的抗遮挡跟踪[J]. 光学精密工程, 2010, 18(6):1413-1419. YAN J, CHEN SH ZH, WU M Y, et al.. Anti-occlusion tracking algorithm based on Mean Shift and fragments[J]. Opt. Precision Eng., 2010, 18(6):1413-1419.(in Chinese)[2] 王国良,刘金国. 基于粒子滤波的多自由度运动目标跟踪[J]. 光学精密工程, 2011, 19(4):864-869. WANG G L, LIU J G. Moving object tracking with multi-degree-of-freedom based on particle filters[J]. Opt. Precision Eng., 2011,19(4):864-869.(in Chinese)[3] COLLINS R, YANX L, LEORDEANU M. Online selection of discriminative tracking features[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10):1631-1643.[4] AVIDAN S. Ensemble tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(2):261-271. [5] GRABNER H, GRABNER M, BISCHOF H. Real-time tracking via on-line boosting . Proceedings of British Machine Vision Conference, 2006,1:47-56.[6] 程有龙,李斌,张文聪,等. 融合先验知识的自适应行人跟踪算法[J]. 模式识别与人工智能, 2009, 22(5):704-708. CHENG Y L, LI B, ZHANG W C, et al.. An adaptive pedestrian tracking algorithm with prior knowledge[J]. Pattern Recognition and Artificial Intelligence, 2009, 22(5):704-708.(in Chinese)[7] TAKAYOSHI Y, HIRONOBU F, SHIHONG L, et al.. Human tracking based on soft decision feature and online real boosting . 19th International Conference on Pattern Recognition,2008:1-4. [8] GRABNER H, LEISTNER C, BISCHOF H. Semi-supervised on-line boosting for robust tracking . Proceedings of Europear Conference on Computer Vision, 2008:234-247.[9] GODEC M, GRABNER H, LEISTNER C, et al.. Speeding up semi-supervised on-line boosting for tracking . Proceedings of the Austrian Association for Pattern Recognition,2009:1-12. [10] TANG F, BRENNAN S, ZHAO Q, et al.. Co-tracking using semi-supervised support Vector Machines . Computer Vision and Pattern Recognition, IEEE Computer Society Conference,2009:1-8. [11] BABENKO B, MING-HSUAN Y, BELONGIE S. Visual tracking with online multiple instance learning . Computer Vision and Pattern Recognition, IEEE Computer Society Conference,2009:983-990. [12] FATIH P. Integral histogram: a fast way to extract histograms in Cartesian spaces . Computer Vision and Pattern Recognition, IEEE Computer Society Conference, 2005:829-836.[13] ADAM A, RIVLIN E, SHIMSHONI I. Robust fragments-based tracking using the integral histogram . Computer Vision and Pattern Recognition, IEEE Computer Society Conference, 2006,1:798-805.

浏览量

255

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

应用Mean Shift和分块的抗遮挡跟踪

数据驱动的多模复合制导信息融合及其试验验证

基于非机动单站的目标运动状态无偏估计

地基大口径望远镜动态目标跟踪中压电式快速反射镜迟滞效应的补偿

基于级联滑模控制的高精度光电跟踪与捕获