一种检测范围自适应的目标跟踪算法
PDF下载 (330)黄元捷,赵杰煜 *,程婷婷,陈普强.一种检测范围自适应的目标跟踪算法[J].宁波大学学报(理工版),2015,28(04):36-41.DOI:
HUANG Yuan-jie,ZHAO Jie-yu *,CHENG Ting-ting,CHEN Pu-qiang.An Adaptive Approach for Generating Detective Range in Visual Object Tracking[J].Journal of Ningbo University(Natural Science & Engineering Edition),2015,28(04):36-41.DOI:
| Title: | An Adaptive Approach for Generating Detective Range in Visual Object Tracking |
| 作者: | 黄元捷, 赵杰煜 *, 程婷婷, 陈普强 |
| Author(s): | HUANG Yuan-jie, ZHAO Jie-yu *, CHENG Ting-ting, CHEN Pu-qiang |
| 关键词: | 目标跟踪; 目标运动预估; 卡尔曼滤波器; P-N学习 |
| Keywords: | visual object tracking; target moving prediction; Kalman filter; P-N learning |
| 分类号: | TP391.4 |
| 文献标识码: | A |
| 摘要: | 为处理目标的消失重现、形变及环境变化等问题, 要求跟踪算法有一定的检测与学习能力. 针对全局检测方法因冗余检测而造成检测效率低下的问题, 在基于P-N学习的跟踪框架的基础上, 提出一种自适应生成检测范围的目标跟踪算法. 通过引入卡尔曼滤波器(Kalman filter)对目标位置、尺度以及两者的变化速度进行预估, 在检测前根据预估信息自适应生成检测范围, 提高检测效率. 在公开的CoGD数据集上进行实验, 结果证明该算法较原始算法在准确度基本不变的基础上, 速度得到显著改善. |
| Abstract: | Visual object tracking is a highly challenging task due to the fact that it suffers from many intrinsic problems, such as object disappearance, reappearance, deformation and environment variation. A tracking algorithm is required to have the ability of detecting and learning. Given the fact that the global detector would generate certain redundant detections, we propose an approach that adaptively generates the detective range for visual object tracking based on the framework of P-N learning. We introduce a Kalman filter to predict the location, the object scale as well as their changing rate. Then we utilize the predicted information to reduce the scope of detecting. Our experimental results on the pubic CoGD dataset show that our method increases the speed dramatically while without compromising the accuracy. |
| 参考文献 /References: | [1] Lepetit V, Lagger P, Fua P. Randomized trees for real-time keypoint recognition[C]//Proceedings of the Computer Vision and Pattern Recognition (CVPR), San Diego CA, 2005:775-781. [2] Andriluka M, Roth S, Schiele B. People-tracking-by- detection and people-detection-by-tracking[C]//Proceedings of the Computer Vision and Pattern Recognition (CVPR), Anchorage AK, 2008:1-8. [3] Ramanan D, Forsyth D A, Zisserman A. Strike a pose: Tracking people by finding stylized poses[C]//Proceedings of the Computer Vision and Pattern Recognition (CVPR), San Diego CA, 2005:271-278. [4] Ross D A, Lim J, Lin R S, et al. Incremental learning for robust visual tracking[J]. International Journal of Computer Vision, 2008, 77(1/3):125-141. [5] Kwon J, Lee K M. Visual tracking decomposition[C]// Proceedings of the Computer Vision and Pattern Recognition (CVPR), San Francisco CA, 2010:1269- 1276. [6] Yang M, Wu Y, Hua G. Context-aware visual tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(7):1195-1209. [7] Grabner H, Matas J, Van G L, et al. Tracking the invisible: Learning where the object might be[C]// Proceedings of the Computer Vision and Pattern Recognition (CVPR), San Francisco CA, 2010:1285- 1292. [8] Collins R T, Liu Y, Leordeanu M. Online selection of discriminative tracking features[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1631-1643. [9] Avidan S. Ensemble tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(2): 261-271. [10] Grabner H, Bischof H. On-line boosting and vision[C]// Proceedings of the Computer Vision and Pattern Recognition (CVPR), New York NY, 2006:260-267. [11] Babenko B, Yang M H, Belongie S. Visual tracking with online multiple instance learning[C]//Proceedings of the Computer Vision and Pattern Recognition (CVPR), Miami FL, 2009:983-990. [12] Tang F, Brennan S, Zhao Q, et al. Co-tracking using semi-supervised support vector machines[C]//Proceedings of the the 11th International Conference on Computer Vision, Rio de Janeiro, 2007:1-8. [13] Yu Q, Dinh T B, Medioni G. Online tracking and reacquisition using co-trained generative and discriminative trackers[M]. Berlin Heidelberg: Springer, 2008:678-691. [14] Grabner H, Leistner C, Bischof H. Semi-supervised on-line boosting for robust tracking[M]. Berlin Heidelberg: Springer, 2008:234-247. [15] Kalal Z, Mikolajczyk K, Matas J. Tracking-learning- detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7):1409-1422. [16] Kalal Z, Mikolajczyk K, Matas J. Forward-backward error: Automatic detection of tracking failures[C]// Proceedings of the 20th International Conference on Pattern Recognition (ICPR), Istanbul, 2010:2756-2759. [17] 周鑫, 钱秋朦, 叶永强, 等. 改进后的TLD视频目标跟踪方法[J]. 中国图象图形学报, 2013, 9:1115-1123. [18] Kalman R E. A new approach to linear filtering and prediction problems[J]. Journal of Basic Engineering, 1960, 82(1):35-45. |
| 备注/Memo: | 收稿日期: 2015-02-06. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/ 基金项目: 国家自然科学基金（61175026）; 科技部国际科技合作专项（2013DFG12810）; 浙江省国际科技合作专项（2013C24027）. 第一作者: 黄元捷（1988－）, 男, 浙江宁波人, 在读硕士研究生, 主要研究方向: 计算机视觉. E-mail: yuangyuanjie@msn.com *通信作者: 赵杰煜（1965－）, 男, 浙江宁波人, 博士/教授, 主要研究方向: 计算机视觉与机器学习. E-mail: zhao_jieyu@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
