首页 > 论文 > 激光与光电子学进展 > 55卷 > 9期(pp:91506--1)

一种针对抖动视频序列的运动目标检测算法

A Moving Object Detection Algorithm Aiming at Jitter Video Sequence

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对自然环境中因摄像机抖动造成无法准确检测运动目标的问题, 提出一种结合分块灰度投影、背景差分与连续帧间差分法的运动目标检测算法。该算法通过将图像帧进行分块处理, 结合离散化决策机制去除灰度梯度变化低及存在局部运动的目标区域, 提高全局运动矢量估计精度。根据块区域灰度投影曲线进行互相关计算, 完成抖动序列校正。通过对校正后的序列帧提出使用背景差分与连续三帧差分法的融合策略处理, 增强运动目标区域。通过将融合差分图像平滑处理并使用Otsu法进行自适应阈值分割, 检测前景运动目标。用公共抖动视频序列实验, 并与不同算法对比验证后可得:该算法可以准确检测出摄像机抖动场景中运动目标, 保证较好检测效果的同时检测速度较快。

Abstract

To solve the problem that jitter video moving object detection is not accurate, we propose a moving object detection method based on block gray projection, background difference and continuous inter-frame difference. By dividing the image frames into block processing, the algorithm combines the discrete decision mechanism to remove the target regions with low gray gradient and the local motion, so as to improve the accuracy of global motion vector estimation. A cross correlation calculation is done for the gray projection of the block area and the image correction is completed. For the corrected sequence frames, we propose a fusion strategy based on background difference and continuous three frame difference method, which can deal with and enhance the moving target area. The selfadaptive thresholding segmentation for the differential image smoothing fusion processing and Otsu method is used to detect foreground moving targets. In jitter video sequence experiment, compared with different algorithms, the proposed algorithm can effectively detect moving targets in the jitter scene, and ensure better detection results and faster detecting speed.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/lop55.091506

所属栏目:机器视觉

基金项目:国网浙江省电力有限公司科技项目(5211HZ17000F)、国家自然科学基金(51405286)、上海市自然科学基金资助项目(13ZR1417800)、上海市电站自动化技术重点实验室(13DZ2273800)

收稿日期:2018-03-20

修改稿日期:2018-03-27

网络出版日期:2018-04-02

作者单位    点击查看

薛阳:上海电力学院自动化工程学院, 上海 200090
张亚飞:上海电力学院自动化工程学院, 上海 200090
杨天宇:上海电力学院自动化工程学院, 上海 200090
徐云炯:国网绍兴供电公司, 浙江 绍兴 312000
孙伟:国网绍兴供电公司, 浙江 绍兴 312000

联系人作者:张亚飞(zyf826220734@163.com)

【1】Sajid H, Cheung S. Universal multimode background subtraction[J]. Proceedings of the IEEE, 2017, 26(7): 3249-3260.

【2】Celik T, Kusetogullari H. Solar-powered automated road surveillance system for speed violation detection[J]. Proceedings of the IEEE, 2010, 57(9): 3216-3227.

【3】St-Charles P L, Bilodeau G A, Bergevin R. SuBSENSE: a universal change detection method with local adaptive sensitivity[J]. Proceedings of the IEEE, 2015, 24(1): 359-373.

【4】Liao J, Dong R, Li B, et al. A non-parametric motion model for foreground detection in camera jitter scenes[J]. IEEE Signal Processing Letters, 2014, 21(6): 677-681.

【5】Mo S W, Deng X P, Wang S, et al. Motion object detection algorithm based on improved visual background extractor[J]. Acta Optica Sinica, 2016, 36(6): 0615001.
莫邵文, 邓新蒲, 王帅, 等. 基于改进视觉背景提取的运动目标检测算法[J]. 光学学报, 2016, 36(6): 0615001.

【6】Zhang S P, Qi Y K, Jiang F, et al. Point-to-set distance metric learning on deep representations for visual tracking[J]. Proceedings of the IEEE, 2018, 19(1): 187-198.

【7】Huynh-The T, Banos O, Lee S, et al. NIC: a robust background extraction algorithm for foreground detection in dynamic scenes[J]. Proceedings of the IEEE, 2017, 27(7): 1478-1490.

【8】Tu L F, Peng Q, Zhong S D. A moving object detection method adapted to camera jittering[J]. Journal of Electronics and Information Technology, 2013, 35(8): 1914-1920.
屠礼芬, 彭祺, 仲思东. 一种适应相机抖动的运动目标检测方法[J]. 电子与信息学报, 2013, 35(8): 1914-1920.

【9】Wu H, Deng H B. A video stabilization method based on sub-block gray projection[J]. Acta Armamentarii, 2013, 34(4): 406-411.
吴浩, 邓宏彬. 一种基于分块灰度投影运动估计的视频稳像方法[J]. 兵工学报, 2013, 34(4): 406-411.

【10】Tang Y C, Yang X D. A method of moving target detection based on scaling background[C]∥International Conference on Intelligent and Interactive Systems and Applications. Cham:Springer, 2017: 337-344.

【11】Chen Q, Sheng H X, Zhang Z, et al. Moving object detection under infrared light mutation[J]. Laser & Optoelectronics Progress, 2016, 53(11): 111005.
陈强, 盛惠兴, 张卓, 等. 红外光照突变下的运动目标检测[J]. 激光与光电子学进展, 2016, 53(11): 111005.

【12】Xue Y, Jiang T B, Zhang X Y. Vision based extraction method for navigation line of substation inspection robot[J]. Guangdong Electric Power, 2015, 28(12): 13-18.
薛阳, 江天博, 张晓宇. 基于视觉的变电站巡检机器人导航线提取方法[J]. 广东电力, 2015, 28(12): 13-18.

【13】Barnich O, van Droogenbroeck M. ViBe: a universal background subtraction algorithm for video sequences[J]. Proceedings of the IEEE, 2011, 20(6): 1709-1724.

【14】Gan M G, Chen J, Liu J, et al. Moving object detection algorithm based on three-frame-differencing and edge information[J]. Journal of Electronics and Information Technology, 2010, 32(4): 894-897.
甘明刚, 陈杰, 刘劲, 等. 一种基于三帧差分和边缘信息的运动目标检测方法[J]. 电子与信息学报, 2010, 32(4): 894-897.

【15】Wang Z H, Liao K, Xiong J L, et al. Moving object detection based on temporal information[J]. IEEE Signal Processing Letters, 2014, 21(11): 1403-1407.

【16】Kirichuk V S, Kosykh V P, Popov S A, et al. Suppression of a quasi-stationary background in a sequence of images by means of interframe processing[J]. Optoelectronics Instrumentation and Data Processing, 2014, 50(2): 109-117.

【17】Chen H Y, Qie L Z, Yang D D, et al. Visual background extraction algorithm based on superpixel information feedback[J]. Acta Optica Sinica, 2017, 37(7): 0715001.
陈海永, 郄丽忠, 杨德东, 等. 基于超像素信息反馈的视觉背景提取算法[J]. 光学学报, 2017, 37(7): 0715001.

引用该论文

Xue Yang,Zhang Yafei,Yang Tianyu,Xu Yunjiong,Sun Wei. A Moving Object Detection Algorithm Aiming at Jitter Video Sequence[J]. Laser & Optoelectronics Progress, 2018, 55(9): 091506

薛阳,张亚飞,杨天宇,徐云炯,孙伟. 一种针对抖动视频序列的运动目标检测算法[J]. 激光与光电子学进展, 2018, 55(9): 091506

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF