| 69 | 4 | 3748 |
| 下载次数 | 被引频次 | 阅读次数 |
视频目标搜索是智能视频监控领域一大挑战,提出一种基于灰度图像区域边缘直方图的目标搜索算法.首先,在固定场景的视频数据中,对选定目标进行特征提取,即区域边缘直方图(REH)特征向量;接着在同一场景的未知视频数据中进行前景检测并提取前景目标的特征向量;经滤波处理后,与选定目标特征向量进行匹配,通过相似性度量评判是否搜索成功.实验得到了最佳72.4%的匹配成功率,验证了32维的区域边缘特征向量为最佳描述特征.实验结果表明,本算法能有效地实现目标搜索.
Abstract：Video object searching is a challenge in the field of intelligent video surveillance.An object searching algorithm based on the region edge histogram(REH)of gray images was introduced.Features of the selected objects were first extracted in a stationary scene video,namely,the region edge statistical feature vector.Then,in an unknown video data about the same stationary scene,a foreground detection was processed and the feature vector of the object was extracted.After filtering processing,the foreground feature vector was matched with that of the selected object to judge if the searching was successful or not.We achieved a best success rate of 72.4% and proved that the best dimension of feature vector was 32.The results of the experiment show that the algorithm can effectively achieve object searching.
[1] 黄凯奇,陈晓棠,康运锋.智能视频监控技术[J].计算机学报,2014,37(49):1093-1118.HUANG Kaiqi,CHEN Xiaotang,KANG Yunfeng.Intelligent visual surveillance:a review[J].Chinese Journal of Computers,2014,37(49):1093-1118.
[2] 黄凯奇,任伟强,谭铁牛.图像物体分类与检测算法综述[J].计算机学报,2014,37(6):1225-1240.HUANG Kaiqi,REN Weiqiang,TAN Tieniu.A review on image object classification and detection[J].Chinese Journal of Computers,2014,37(6):1225-1240.
[3] BIRCHFIELD S T,RANGARAJAN S.Spatial histograms for region-based tracking[J].ETRI Journal,2007,29(5):697-699.
[4] LEVI K,WEISS Y.Learning object detection from a small number of examples:the importance of good features[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington DC,USA:IEEE,2004:53-60.
[5] DALAL B,TRIGGS B.Histograms of oriented gradients for human detection[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego,USA:IEEE,2005:886-893.
[6] 余旺盛,田孝华,侯志强.基于区域边缘统计的图像特征描述新方法[J].计算机学报,2014,37(6):1398-1410.YU Wangsheng,TIAN Xiaohua,HOU Zhiqiang.A new image feature based on region edge statistical[J].Chinese Journal of Computers,2014,37(6):1398-1410.
[7] LI Yongqiang,CHEN Wanzhong,JIANG Rui.The integration adjacent frame difference of improved ViBe for foreground object detection[C]//Proceedings of the WiCOM2011International Conference.China:IEEE Antennas and Propagation Society,2011:1-4.
[8] 陈亮,陈晓竹,范振涛.基于Vibe的鬼影抑制算法[J].中国计量学院学报,2013,24(4):425-429.CHEN Liang,CHEN Xiaozhu,FAN Zhentao.Ghost suppression algorithm based on Vibe[J].Journal of China University of Metrology,2013,24(4):425-429.
[9] 陈亮,陈晓竹,胡正东.用于鬼影抑制的区域检测算法[J].中国计量学院学报,2015,26(1):115-122.CHEN Liang,CHEN Xiaozhu,HU Zhengdong.Region detection algorithm for ghost suppression[J].Journal of China University of Metrology,2015,26(1):115-122.
[10] 蒋建国,王涛,齐美彬,等.基于vibe的车流量统计算法[J].电子测量与仪器学报,2012,26(6):558-563.JIANG Janguo,WANG Tao,QI Meibin,et al.Statistical algorithm for traffic flow based on ViBe[J].Journal of Electronic Measurement and Instrument,2012,26(6):558-563.
[11] 张磊,傅志中,周岳平.基于HSV颜色空间和Vibe算法的运动目标检测[J].计算机工程与应用,2014,50(4):181-185.ZHANG Lei,FU Zhizhong,ZHOU Yueping.Moving objects detection based on HSV color space and Vibe algorithm[J].Computer Engineering and Applications,2014,50(4):181-185.
[12] VAN D M,PAQUOT O.Background subtraction:experiments and improvements for ViBe[C]//Computer Vision and Pattern Recognition Workshops(CVPRW).Providence,RI:IEEE,2012:32-37.
基本信息:
DOI：
中图分类号:TP391.41
引用信息:
[1]胡正东,陈晓竹,丁宁.区域边缘直方图的目标搜索算法[J],2016,27(02):210-215.
基金信息: