[1]胡光龙,秦世引.动态成像条件下基于SURF和Mean shift的运动目标高精度检测[J].智能系统学报,2012,7(01):61-68.
 HU Guanglong,QIN Shiyin.High precision detection of a mobile object under dynamic imaging based on SURF and Mean shift[J].CAAI Transactions on Intelligent Systems,2012,7(01):61-68.
点击复制

动态成像条件下基于SURF和Mean shift的运动目标高精度检测(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第7卷
期数:
2012年01期
页码:
61-68
栏目:
出版日期:
2012-02-25

文章信息/Info

Title:
High precision detection of a mobile object under dynamic imaging based on SURF and Mean shift
文章编号:
1673-4785(2012)01-0061-08
作者:
胡光龙秦世引
北京航空航天大学 自动化科学与电气工程学院,北京 100191
Author(s):
HU Guanglong QIN Shiyin
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China
关键词:
SURF图像配准Mean shift图像分割动态背景目标检测
Keywords:
speededup robust features(SURF) image registration Mean shift image segmentation dynamic background object detection
分类号:
TP391.41
文献标志码:
A
摘要:
针对动态成像条件下运动目标检测的难点问题,提出了一种将SURF特征和Mean shift图像分割相结合的高精度运动目标检测方法.首先利用SURF特征进行图像配准,以补偿背景图像的运动漂移;然后利用差分求积二值化和形态学滤波方法检测出运动目标区域;最后结合Mean shift图像分割方法实现运动目标的精确检测.通过一系列实拍视频的运动目标检测实验验证了此算法的有效性和可行性.实验结果表明,此方法能精确检测出动态成像条件下所形成的动态背景中的运动目标,而且具有良好的鲁棒性和抗噪能力,对于光照条件和亮度变化等不利因素也有较强的适应能力.
Abstract:
Taking into account the difficulty of movingobject detection with a dynamic background caused by camera motion, a new method was proposed based on speededup robust features (SURF) and Mean shift. First, the image registration based on SURF was applied to compensate the background motion, and then binarization of quadrature by difference method and morphological filters was carried out to detect the movingobject’s area so that the accurate detection and segmentation of the moving object was accomplished with Mean shift. Finally, the effectiveness and satisfactory performance were validated through a series of experiments of dynamic videos. The results indicate that the proposed algorithm is characterized by high precision, low false detection, and strong robustness to noises, and thus can be extended to application in practical engineering.

参考文献/References:

[1]李劲菊,朱青,王耀南.一种复杂背景下运动目标检测与跟踪方法[J].仪器仪表学报, 2010, 31(10): 22422247.
LI Jinju, ZHU Qing, WANG Yaonan. Detecting and tracking method of moving target in complex environment[J]. Chinese Journal of Scientific Instrument, 2010, 31(10): 22422247.
[2]郝久月,李超,高磊,等.智能监控场景中运动目标轨迹聚类算法[J].北京航空航天大学学报, 2009, 35(9): 10831087.
 HAO Jiuyue, LI Chao, GAO Lei, et al. Moving object trajectory clustering method in intelligent surveillance video[J]. Journal of Beijing University of Aeronautics and Astronautics, 2009, 35(9): 10831087.
[3]HE L, PENG Z, EVERDING B, et al. A comparative study of deformable contour methods on medical image segmentation[J]. Image and Vision Computing, 2008, 26(2): 141163.
[4]BONINFONT F, ORTIZ A, OLIVER G. Visual navigation for mobile robots: a survey[J]. Journal of Intelligent & Robotics Systems, 2008, 53(3): 263296.
[5]谢凤英,赵丹培.Visual C++ 数字图像处理[M].北京:电子工业出版社, 2008: 449463.
[6]YILMAZ A, JAVED O, SHAH M. Object tracking: a survey[J]. ACM Computing Surveys, 2006, 38(4): 145.
[7]KIM I S, CHOI H S, YI K M, et al. Intelligent visual surveillance: a survey[J]. International Journal of Control, Automation, and Systems, 2010, 8(5): 926939.
[8]ZITOVA B, FLUSSER J. Image registration methods: a survey[J]. Image and Vision Computing, 2003, 21(11): 9771000.
[9]BAY H, TUYTELAARS T, GOOL L V. SURF: speeded up robust features[C]//Proceedings of the European Conference on Computer Vision. Graz, Austria, 2006: 404417.
[10]张锐娟,张建奇,杨翠.基于SURF的图像配准方法研究[J].红外与激光工程, 2009, 38(1): 160165.
ZHANG Ruijuan, ZHANG Jianqi, YANG Cui. Image registration approach based on SURF[J]. Infrared and Laser Engineering, 2009, 38(1): 160165.
[11]谢凡,秦世引.基于SIFT的单目移动机器人宽基线立体匹配[J].仪器仪表学报, 2008, 29(11): 22472252.
XIE Fan, QIN Shiyin. Wide baseline stereo vision matching approach for monocular mobile robot based on SIFT[J]. Chinese Journal of Scientific Instrument, 2008, 29(11): 22472252.
[12]卜珂.基于SURF的图像配准与拼接技术研究[D].大连:大连理工大学, 2009: 3358.
BO Ke. Research on image registration and mosaic based on SURF[D]. Dalian: Dalian University of Technology, 2009: 3358.
[13]COMANICIU D, MEER P. Mean shift : a robust approach toward feature space analysis[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603619.
[14]周许超,屠大维,陈勇,等.基于相位相关和差分求积二值化的动态背景下运动目标检测[J].仪器仪表学报, 2010, 31(5): 980983.
ZHOU Xuchao, TU Dawei, CHEN Yong, et al. Moving object detection under dynamic background based on phasecorrelation and differential multiplication[J]. Chinese Journal of Scientific Instrument, 2010, 31(5): 980983.
[15]王梅,屠大维,周许超.SIFT特征匹配和差分求积二值化融合的运动目标检测[J].光学精密工程, 2011, 19(4): 892899.
 WANG Mei, TU Dawei, ZHOU Xuchao. Moving object detection by combining SIFT and differential multiplication[J]. Optics and Precision Engineering, 2011, 19(4): 892899.
[16]XIAO Jiangjian, YANG Changjiang, HAN Feng, et al. Vehicle and person tracking in aerial videos [M]//Multimodal Technologies for Perception of Humans. Berlin/Heidelberg: SpringerVerlag, 2008: 203214.
[17]赵文哲,秦世引.一种高精度视频目标检测与分割新方法[J].北京航空航天大学学报, 2010, 36(12): 14901494.
 ZHAO Wenzhe, QIN Shiyin. Novel approach to video object detection and precise segmentation[J]. Journal of Beijing University of Aeronautics and Astronautics, 2010, 36(12): 14901494.
[18]BROWN M, LOWE D G. Invariant features from interest point groups[C]//British Machine Vision Conference. Cardiff, UK, 2002: 656665.
[19]FISCHLER M A, BOLLES R C. Random sample consensus: a paradigm for model fitting with application to image automated cartography[J]. Communication of the ACM, 1981, 24(6): 381395.
[20]王晏,孙怡.自适应Mean shift算法的彩色图像平滑与分割算法[J].自动化学报, 2010, 36(12): 16371644.
 WANG Yan, SUN Yi. Adaptive Mean shift based image smoothing and segmentation[J]. Acta Automatica Sinica, 2010, 36(12): 16371644.

相似文献/References:

[1]许可乐,唐涛,蒋咏梅.一种SAR图像稳健特征点提取方法[J].智能系统学报,2013,8(04):287.[doi:10.3969/j.issn.1673-4785.201304038]
 XU Kele,TANG Tao,JIANG Yongmei.A stable feature point extraction approach for SAR image registration[J].CAAI Transactions on Intelligent Systems,2013,8(01):287.[doi:10.3969/j.issn.1673-4785.201304038]

备注/Memo

备注/Memo:
收稿日期: 2011-07-13.
基金项目:国家自然科学基金资助项目(60875072);北京市自然科学基金资助项目(4112035);中澳国际合作项目(2007DFA11530).
通信作者:胡光龙.         E-mail: hgllgh007@163.com.
作者简介:
胡光龙,男,1988年生,硕士研究生,主要研究方向为运动目标检测与跟踪、机器人技术.
 秦世引,男,1955年生,教授,博士生导师,主要研究方向为复杂系统的智能控制、图像处理与模式识别等.作为负责人主持完成(或在研)国家攀登计划项目的子课题、国家“973”计划项目的子课题、国家“863”计划项目、国家自然科学基金项目等20余项.1999年获全国优秀科技图书奖暨科技进步奖(科技著作)一等奖,同年获国家第5届工程设计优秀软件金奖.发表学术论文180余篇,出版学术著作1部、研究生教材1部、译著2部.
更新日期/Last Update: 2012-05-07