光子学报, 2014, 43 (7): 0710002, 网络出版: 2014-08-18   

连续帧间差分与背景差分相融合的运动目标检测方法

Combined Continuous Frame Difference with Background Difference Method for Moving Object Detection
作者单位
陕西师范大学 物理与信息技术学院,西安 710119
摘要
为了克服背景差分法和帧间差分法的不足,有效提高运动目标检测的准确性、实时性和检测效率,提出了一种将连续帧间差分法与背景差分法相结合的运动目标检测方法.首先通过连续帧间差分法获得连续帧差图像,然后分别通过线性的自适应滤波、非线性的中值滤波获得背景图像进行差分,之后再利用阈值分割技术实现运动目标的增强,从而有效解决背景差分法和帧间差分法中都可能出现的无法检测目标的现象.实验表明,该算法可以有效避免漏检、误检等情况,提高运动目标检测的效率和准确性.
Abstract
In order to overcome the disadvantage of the background difference method and the frame difference method and improve the accuracy, realtime and detection efficiency for the detection of moving target, a method was presented that combines the continuous frame difference method with the background difference method. The proposed method firstly used continuous frame difference method to obtain continuous difference images. Then a linear adaptive filter or an nonlinear median filter was adopted to obtain the background image and get them subtraction. Finally a threshold segmentation technology was used to enhance the detected moving target. Experiment results demonstrate that the proposed algorithm can effectively avoids the phenomenon of the “missed” and “false alarms”, etc., and the detection efficiency and accuracy are improved greatly.
参考文献

[1] 刘皞, 赵峰民, 陈望达. 一种基于背景自适应的运动目标检测与跟踪算法[J]海军航空工程学院学报, 2012, 27(1): 15-18.

    LIU Hao, ZHAO Fengmin, CHEN Wangda. A moving object detection and tracking method based on adaptive background image[J].Journal of Naval Aeronautical And Astronautical University , 2012, 27(1): 15-18.

[2] 张雨丝. 基于背景差分的光照鲁棒性运动目标检测与跟踪技术研究[D]. 四川:西南交通大学,2011.

    ZHANG Yusi. Research on moving objects detection and tracking based on background subtraction with illumination robustness[D]. Sichuan: Southwest Jiaotong University, 2011.

[3] 陈磊, 邹北骥. 基于动态阈值对称差分和背景差法的运动对象检测算法[J]. 计算机应用研究, 2008, 25(2): 488-494.

    CHEN Lei, ZOU Beiji, New algorithm for detecting moving object based on adaptive background subtraction and symmetrical differenceing[J]. Application Research of Computers, 2008, 25(2): 488-494.

[4] 魏志强, 纪筱鹏, 冯业伟. 基于自适应背景图像更新的运动目标检测方法[J]. 电子学报, 2005, 33(12): 2261-2264.

    WEI Zhiqiang, JI Xiaopeng, FENG Yewei, A moving object detection method based on selfadaptive updating of background[J]. Acta Electronic Sinica, 2005, 33(12): 2261-2264.

[5] DENMAN S, CHANDRAN V, SRIDHARAN S. An adaptive optical flow technique for person tracking system[J]. Pattern Recognition Letters, 2007, 28(10): 1232-1239.

[6] JAYABALAN E, KRISHNAN Dr A, PUGAZENDI R. Non rigid object tracking in aerial videos by combined snaked and optical flow technique[J]. Computer Graphics, Imaging and Visualisation, 2007, 21(6): 388-396.

[7] HARITAOGLU D. Realtime surveillance of people and their activities[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22(7): 809-830.

[8] COLLINS R, LIPTON A, KANADE T, et al. A system for video surveillance and monitoring: VSAM final report[R]. America: Carnegie Mellon University, Technical Report: CMU RI TR 0012, 2000.

[9] 张玲. 基于视频的改进帧差法在车流量检测中的应用[J]. 重庆大学学报, 2004, 27(5): 32-34.

    ZHANG Ling. Application of an improved framedifference method based on video in traffic flow measurement[J]. Journal of Chongqin University, 2004, 27(5): 32-34.

[10] 袁国武, 陈志强, 龚健,等. 一种结合光流法与三帧差分法的运动目标检测算法[J]. 小型微型计算机系统, 2013, 34(3): 669-671.

    YUAN Guowu, CHEN Zhiqiang, GONG Jian, et al. A moving object detection algorithm based on a combination of optical flow and threeframe difference[J]. Journal of Chinese Computer Systems, 2013, 34(3): 669-671.

[11] 邬大鹏, 程卫平, 于盛林. 基于帧间差分和运动估计的Camshift目标跟踪算法[J]. 光电工程, 2010, 37(1): 55-60.

    WU Dapeng, CHENG Weiping, YU Shenglin. Camshift object tracking algorithm based on interframe difference and motion prediction[J]. Optoelectronic Engineering, 2010, 37(1): 55-60.

[12] 陈俊超, 张俊豪, 刘诗佳,等. 基于背景建模与帧间差分的目标检测改进算法[J]. 计算机工程, 2011, 37: 171-173.

    CHEN Junchao, ZHANG Junhao, LIU Shijia, et al. Improved target detection algorithm based on background modeling and frame difference[J]. Computer Engineering, 2011, 37: 171-173.

[13] 王振亚, 曾黄麟. 一种基于帧间差分和光流技术结合的运动车辆检测和跟踪新算法[J]. 计算机应用与软件, 2012, 29(5): 117-120.

    WANG Zhenya, ZENG Huanglin. A new algorithm of moving vehicle detection and tracking based on combining frame difference method with optical flow technique[J]. Computer Applications and Software, 2012, 29(5): 117-120.

[14] 李鹏, 陈钱, 郑海鸥,等. 基于复杂背景的红外小目标图像预处理方法[J]. 红外与激光工程, 2011, 40(5): 958-962.

    LI Peng, CHEN Qian, ZHEN Haiou, et al. Pretreatment method of small targets infrared image based on complex background[J]. Infrared and Laser Engineering, 2011, 40(5): 958-962.

[15] 张德丰. 数字图像处理[M]. 北京: 机械工业出版社, 2009: 186-194.

[16] 苏礼坤, 陈怀新. 中值滤波的视频背景更新[J]. 光电工程, 2010, 37(1): 131-135.

    SU Likun, CHEN Huaixin. Videobackground update based on median filtering[J]. Optoelectronic Engineering, 2010, 37(1): 131-135.

[17] 张起贵, 张光伟. 一种视频序列中运动目标检测算法[J]. 昆明理工大学学报, 2010, 35(8): 67-70.

    ZHANG Qigui, ZHANG Guangwei. A moving target detection algorithm in video sequences[J]. Journal of Kunming University of Science and Technology, 2010, 35(8): 67-70.

[18] 许悦雷, 左继章. 一种累积帧差视频对象的分割算法[J]. 光电工程, 2004, 31(7): 149-150.

    XU Yuelei, ZUO Jizhang. A video segmentation algorithm based on accumulated frame differences[J]. Optoelectronic Engineering, 2004, 31(7): 149-150.

[19] 左凤艳, 高胜发, 韩建宇. 基于加权累计差分的运动目标检测与跟踪[J].计算机工程, 2009, 35(22): 159-161.

    ZUO Fengyan, GAO Shengfa, HAN Jianyu. Moving object detection and tracking based on weighted accumulative difference[J]. Computer Engineering, 2009, 35(22): 159-161.

[20] 徐军. 红外图像中小目标检测技术研究[D] 西安: 西安电子科技大学, 2001.

    XU Jun. Research on the detection of small and dim targets in infrared images[D]. Xi′an: Xidian University, 2001.

[21] WENG Tzelun, WANG Yiying, HO Zongying, et al. Weatheradaptive flying target detection and tracking from infrared video sequences[J]. Expert Systems with Applications, 2010, 37: 1666-1675.

屈晶晶, 辛云宏. 连续帧间差分与背景差分相融合的运动目标检测方法[J]. 光子学报, 2014, 43(7): 0710002. QU Jingjing, XIN Yunhong. Combined Continuous Frame Difference with Background Difference Method for Moving Object Detection[J]. ACTA PHOTONICA SINICA, 2014, 43(7): 0710002.

本文已被 3 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!