[1]于晓明,李思颖.多步预测融Mean-Shift的运动目标跟踪算法研究[J].红外技术,2018,40(12):1182-1187.[doi:10.11846/j.issn.1001_8891.201812011]
 YU Xiaoming,LI Siying.Study on Motion Target Tracking Algorithm Based on Mean-Shift and Multi-step Prediction[J].Infrared Technology,2018,40(12):1182-1187.[doi:10.11846/j.issn.1001_8891.201812011]
点击复制

多步预测融Mean-Shift的运动目标跟踪算法研究
分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
40
期数:
2018年第12期
页码:
1182-1187
栏目:
出版日期:
2018-12-21

文章信息/Info

Title:
Study on Motion Target Tracking Algorithm Based on Mean-Shift and Multi-step Prediction
文章编号:
1001-8891(2018)2-1182-06
作者:
于晓明李思颖
陕西科技大学 电气与信息工程学院,陕西 西安710021
Author(s):
YU XiaomingLI Siying
 School of Electrical and Information Engineering, Shaanxi University of Science and Technology, Xian 710021, China
关键词:
Mean-Shift算法Bhattacharyya coefficient多步预测运动目标跟踪
Keywords:
Mean-Shift algorithmBhattacharyya coefficientmulti-step predictionmotion target tracking
分类号:
TP391
DOI:
10.11846/j.issn.1001_8891.201812011
文献标志码:
A
摘要:
对运动目标跟踪时,主流Mean-Shift(均值偏移)算法对环境的影响较为敏感。针对目标遮挡时准确跟踪这一问题,提出了多步预测融Mean-Shift的优化运动目标跟踪算法。在目标跟踪的过程当中采取Bhattacharyya coefficient(巴氏系数)辨别目标是否出现了遮挡。当目标产生遮挡的情况,采取多步预测算法,根据目标前一帧的特征信息对下一帧中目标位置信息进行判断。当运动目标离开遮挡时,则继续采取Mean-Shift实施后续跟踪。通过对不同场景下的视频序列实行测试,其结果表明该算法可以对发生遮挡后的目标进行连续、稳健的跟踪。
Abstract:
The mainstream Mean-Shift(mean shift) algorithm is more sensitive to environmental impacts when tracking moving targets. Aiming at the resolution of the problem of accurately tracking target occlusion, an optimal moving target tracking algorithm based on multi-step prediction fusion mean shift is proposed. In the process of target tracking, the Bhattacharyya coefficient is used to discern whether the target has occlusion. In the case of target occlusion, a multi-step prediction algorithm is adopted to determine the target position information in the next frame according to the feature information of the previous frame of the target. When the target leaves the occlusion, the algorithm continues to follow Mean-Shift for subsequent tracking. The video sequences in different environments are tested, and the results show that the algorithm can continuously and robustly track the target after occlusion

参考文献/References:

[1] 储珺, 朱陶, 缪君, 等. 基于遮挡检测和时空上下文信息的目标跟踪算法[J]. 模式识别与人工智能, 2017, 30(8): 718-727.
CHU Jun, ZHU Tao, MIAO Jun, et al. Target tracking algorithm based on occlusion detection and temporal and spatial context information[J]. Pattern Recognition and Human Intelligence, 2017, 30(8): 718-727.
[2] Fu Kunage K, Hostetler L D. The estimation of the gradient of a density function, with application in pattern recognition[J]. IEEE Transactions on Information Theory, 1975, 21(1): 32-40.
[3] Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean shift[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York: IEEE Press, 2000: 142-149.
[4] 王梦斐. 基于Mean Shift的视频图像目标检测与跟踪[D]. 上海: 上海师范大学, 2015.
WANG Mengfei. Video Image Target Detection and tracking based on Mean Shift[D]. Shanghai: Shanghai Normal University, 2015.
[5] 王长有, 刘皓, 张海强, 等. 基于灰色预测和Mean-Shift的抗遮挡跟踪算法[J]. 控制工程, 2017, 24(7): 1323-1328.
WANG Changyou, LIU Hao, ZHANG Haiqiang, et al. Anti-occlusion tracking algorithm based on grey prediction and Mean-Shift[J]. Control Engineering, 2017, 24(7): 1323-1328.
[6] 丁晓凤, 尚振宏, 刘辉, 等. 基于Mean Shift的多模板目标跟踪算法[J]. 计算机工程与应用, 2017, 53(6): 141-144, 173.
DING Xiaofeng, SHANG Zhenhong, LIU Hui, et al. Multi-template target tracking algorithm based on Mean Shift[J]. Computer Engineering and Application, 2017, 53(6): 141-144, 173.
[7] 江二华, 王汇源. 一种改进的运动目标跟踪算法[J]. 计算机工程与应用, 2015, 51(22): 168-171.
JIANG Erhua, WANG Huiyuan. An improved method for tracking moving targets[J]. Computer Engineering and Application, 2015, 51(22): 168-171.
[8] 郑浩, 董明利, 潘志康. 基于背景加权的尺度方向自适应均值漂移算法[J]. 计算机工程与应用, 2016, 52(22): 192-197.
ZHENG Hao, DONG Mingli, PAN Zhikang. An adaptive mean-shift algorithm based on background weighting in scale square direction[J]. Computer Engineering and Application, 2016, 52(22): 192-197.
[9] 李熵. 基于视频监控系统的运动目标跟踪算法研究[D]. 成都: 电子科技大学, 2015.
LI Shang. Research on moving Target Tracking Algorithm based on Video Surveillance System[D]. Chengdu: University of Electronic Science and Technology of China, 2015.
[10] 李超. 基于OpenCV的运动目标检测与跟踪算法的研究[D]. 阜新: 辽宁工程技术大学, 2015.
LI Chao. Research on Moving Target Detection and Tracking Algorithm based on OpenCV[D]. Fuxin: Liaoning Project Technology University, 2015.
[11] 耿盛涛, 刘国栋. 一种稳健的移动机器人目标跟踪算法[J]. 传感器与微系统, 2011, 30(6): 112-115.
GENG Shengtao, LIU Guoliang. A robust target tracking algorithm for mobile robot[J]. Transducer and Microsystem Technologies, 2011, 30(6): 112-115.
[12] DU Hailiang, Leonard A Smith. Pseudo-orbit data assimilation, part I: the perfect model scenario[J]. Atmos. Sci., 2014, 71(2): 469-482.
[13] Marjan Firouznia, Karim Faez, Hamidreza Amindavar, et al. Multi-step prediction method for robust object tracking[J]. Digital Signal Processing, 2017, 70: 94-104.

备注/Memo

备注/Memo:
收稿日期:2018-03-09;修订日期:2018-05-31.
作者简介:于晓明(1965-),女,副教授/博士,研究方向:智能信息处理、智能检测、图形图像处理。E-mail:494636031@qq.com。
基金项目:陕西省科技厅居家养老模式若干关键技术研究(No.2014KRM80)。
更新日期/Last Update: 2018-12-19