Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)
电气工程     
实时的静止目标与鬼影检测及判别方法
叶芳芳1,2,许力1
1.浙江大学 电气工程学院,浙江 杭州 310027; 2.江苏大学 电气信息工程学院,江苏 镇江 210023
Real-time detection and discrimination of static objects and ghosts
YE Fang-fang1, 2, XU Li1
1.College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China；2.College of Electronic and Information Engineering, Jiangsu University, Zhenjiang 210023, China
 全文: PDF(1523 KB)   HTML
摘要：

针对视频安全监控中出现的鬼影干扰现象,提出静止目标与鬼影的实时检测及判别方法.建立双背景模型检测出静止前景区域,通过证据累积图像和允许遮挡时间参数减少虚警及处理遮挡问题.采用canny算子提取静止前景的边缘,分别计算静止前景边缘在当前帧与背景帧中的边界颜色对比度.通过对比边界颜色对比度的大小区分静止目标与鬼影.在不同复杂度的视频场景下的实验表明,采用该方法能够有效地从复杂场景中检测出静止目标,并快速判别鬼影,极大地降低了计算耗时且准确率较高.对于图像大小为 352×288 的视频序列,该算法的平均运行速度约为50 帧/s,能够满足实时的监控任务需求.
Abstract:

A real-time detection method was proposed for static objects and ghosts detection and discrimination in order to solve the interference of ghost in video-based security surveillance. Two backgrounds were constructed to detect static foregrounds. Then an evidence aggregate image and a permitted occlusion time parameter were introduced in order to reduce  false alarms and handle occlusions. Canny edge operator was applied to extract the edge of the static foregrounds region, and boundary spatial color contrast in the background and current frame was computed. The static objects and ghosts were discriminated by comparing the boundary spatial color contrast. Experimental results over a heterogeneous dataset demonstrate that the approach can effectively detect stationary foregrounds from complex scenes and rapidly discriminate static objects and ghosts with a high accuracy, greatly reduce the computational cost of the discrimination task. The method runs average around 50 frames per second for a sequence with an image resolution of 352×288, which can be applied to real-time surveillance tasks．
出版日期: 2018-06-06
:  TP 391  
基金资助:

国家自然科学基金资助项目(61004032)；江苏省自然科学基金资助项目(BK201240801)
通讯作者: 许力，男，教授，博导     E-mail: xupower@zju.edu.cn
作者简介: 叶芳芳（1980-），女，讲师，博士生，从事智能控制﹑模式识别的研究.E-mail: cliney@zju.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

叶芳芳,许力. 实时的静止目标与鬼影检测及判别方法[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008-973X.2015.01.026.

YE Fang-fang, XU Li. Real-time detection and discrimination of static objects and ghosts. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008-973X.2015.01.026.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2015.01.026    或    http://www.zjujournals.com/eng/CN/Y2015/V49/I1/181

［1］ HASSAN W, MITRA B, CHATWIN C, et al. Illumination invariant method to detect and track left luggage in public areas ［C］∥ International Society for Optical Engineering. Brussels:SPIE,2010．
［2］ FERRYMAN K, HOGG J, SOCHMAN D, et al. Robust abandoned object detection integrating wide area visual surveillance and social context ［J］. Pattern Recognition Letters, 2013, 34 (7): 789-798 ．
［3］ PORIKLI F, IVANOV Y, HAGA T. Robust abandoned object detection using dual foregrounds ［J］. EURASIP Journal on Advances in Signal Process, 2008(30): 110．
［4］ XU Li-li, ZHANG Chao, ZHANG Duo. Abandoned objects detection using double illumination invariant foreground masks ［C］∥International Conference on Pattern Recognition. Istanbul: IEEE, 2010: 436-439．
［5］ TIAN Ying-li, FERIS RS, LIU Hao-wei, et al. Robust detection of abandoned and removed objects in complex surveillance videos ［J］. IEEE Transactions on Systems, Man, and Cybernetics, 2011(9): 565-576．
［6］ STAUFFER C, GRIMSON W E L. Adaptive background mixture models for real-time tracking ［C］∥Proceeding of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington D C: IEEE, 1999: 245-252．
［7］ CUUCHIARA R, GRANA C, PICCARDI M, et al. Detecting moving objects, ghosts, and shadows in video streams ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25 (10): 1337-1342．
［8］ SPAGNOLO P, CAROPPO A, LEO M, et al.An abandoned / removed objects detection algorithm and its evaluation on PETS datasets ［C］∥International Conference on Advanced Video and Signal Based Surveillance. Australia: IEEE, 2006: 17-21．
［9］ VENEIANER P, ZHANG Z, YIN W, et al. Stationary target detection using the object video surveillance system ［C］∥International Conference on Advanced Video and Signal Based Surveillance. London: IEEE, 2007(9): 242-247．
［10］ FERRANDO S, GERA G, REGAZZONI C. Classification of unattended and stolen objects in video surveillance system ［C］∥International Conference on Advanced Video and Signal Based Surveillance. Australia: IEEE, 2006: 21-27．
［11］ LU S, ZHANG J, FENG D. Detecting ghost and left objects in video surveillance ［J］. International Journal of Pattern Recognition and Artificial Intelligence, 2009, 23(7): 1503-1525．
［12］ CARO L, SANMIGUEL J C, MARTINEZ J M. Discrimination of abandoned and stolen object based on active contours ［C］∥International Conference on Advanced Video and Signal Based Surveillance. Klagenfurt: IEEE, 2011: 101-106．
［13］ YANG Tao, LI Stan-zi, PAN Quan, et al. Real-time and accurate segmentation of moving objects in dynamic scene ［C］∥Proceedings of ACM Multimedia-2nd International Workshop on Video Surveillance and Sensor Networks. New York: ACM, 2004: 136-143．
［14］ ERDEM C E, SANKUR B, TEKALP M. Performance measures for video object segmentation and tracking ［J］. IEEE Transactions on Image Process, 2004, 13(7):937-951．
［15］ AVSS2007\[EB/OL\].\[2013-10-09\].http:∥www-vpu.eps.uam.es/ASODd.　　
[1] 何雪军, 王进, 陆国栋, 刘振宇, 陈立, 金晶. 基于三角网切片及碰撞检测的工业机器人三维头像雕刻[J]. 浙江大学学报(工学版), 2017, 51(6): 1104-1110.
[2] 王桦, 韩同阳, 周可. 公安情报中基于关键图谱的群体发现算法[J]. 浙江大学学报(工学版), 2017, 51(6): 1173-1180.
[3] 尤海辉, 马增益, 唐义军, 王月兰, 郑林, 俞钟, 吉澄军. 循环流化床入炉垃圾热值软测量[J]. 浙江大学学报(工学版), 2017, 51(6): 1163-1172.
[4] 毕晓君, 王佳荟. 基于混合学习策略的教与学优化算法[J]. 浙江大学学报(工学版), 2017, 51(5): 1024-1031.
[5] 黄正宇, 蒋鑫龙, 刘军发, 陈益强, 谷洋. 基于融合特征的半监督流形约束定位方法[J]. 浙江大学学报(工学版), 2017, 51(4): 655-662.
[6] 蒋鑫龙, 陈益强, 刘军发, 忽丽莎, 沈建飞. 面向自闭症患者社交距离认知的可穿戴系统[J]. 浙江大学学报(工学版), 2017, 51(4): 637-647.
[7] 王亮, 於志文, 郭斌. 基于双层多粒度知识发现的移动轨迹预测模型[J]. 浙江大学学报(工学版), 2017, 51(4): 669-674.
[8] 廖苗, 赵于前, 曾业战, 黄忠朝, 张丙奎, 邹北骥. 基于支持向量机和椭圆拟合的细胞图像自动分割[J]. 浙江大学学报(工学版), 2017, 51(4): 722-728.
[9] 穆晶晶, 赵昕玥, 何再兴, 张树有. 基于凹凸变换与圆周拟合的重叠气泡轮廓重构[J]. 浙江大学学报(工学版), 2017, 51(4): 714-721.
[10] 戴彩艳, 陈崚, 李斌, 陈伯伦. 复杂网络中的抽样链接预测[J]. 浙江大学学报(工学版), 2017, 51(3): 554-561.
[11] 刘磊, 杨鹏, 刘作军. 采用多核相关向量机的人体步态识别[J]. 浙江大学学报(工学版), 2017, 51(3): 562-571.
[12] 郭梦丽, 达飞鹏, 邓星, 盖绍彦. 基于关键点和局部特征的三维人脸识别[J]. 浙江大学学报(工学版), 2017, 51(3): 584-589.
[13] 王海军, 葛红娟, 张圣燕. 基于核协同表示的快速目标跟踪算法[J]. 浙江大学学报(工学版), 2017, 51(2): 399-407.
[14] 张亚楠, 陈德运, 王莹洁, 刘宇鹏. 基于增量图形模式匹配的动态冷启动推荐方法[J]. 浙江大学学报(工学版), 2017, 51(2): 408-415.
[15] 刘宇鹏, 乔秀明, 赵石磊, 马春光. 统计机器翻译中大规模特征的深度融合[J]. 浙江大学学报(工学版), 2017, 51(1): 46-56.