[1]王俊[],王文中[][],汤进[][]. 基于几何投影的运动阴影去除方法[J].计算机技术与发展,2015,25(12):37-40.
　WANG Jun[],WANG Wen-zhong[][],TANG Jin[][]. A Moving Shadow Removal Method Based on Geometric Projection[J].,2015,25(12):37-40.
点击复制

 基于几何投影的运动阴影去除方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
25
期数:
2015年12期
页码:
37-40
栏目:
智能、算法、系统工程
出版日期:
2015-12-10

文章信息/Info

Title:
 A Moving Shadow Removal Method Based on Geometric Projection
文章编号:
1673-629X（2015)12-0037-04
作者:
 王俊[1]; 王文中[1][2] ; 汤进[1][2]
 1.安徽大学 计算机科学与技术学院；2.安徽省工业图像处理与分析重点实验室
Author(s):
 WANG Jun[1] ; WANG Wen-zhong[1][2]; TANG Jin[1][2]
关键词:
 ; 运动目标检测; 图像主方向; 几何投影; 阴影去除
Keywords:
 ; moving object detection; principal image direction; geometric projection; shadow removal
分类号:
TP391.4
文献标志码:
A
摘要:
 由于在使用图像差分法检测运动目标时,运动目标阴影会被当成运动目标而检测出,因此文中针对固定场景的运动目标阴影问题,提出了一种简单有效的基于几何投影的阴影去除方法. 首先,根据图像灭点理论,通过场景先验知识计算场景图像的主方向. 其次,结合帧差法和背景差法检测运动前景,把前景像素点在场景图像主方向的垂线方向上进行几何投影. 根据目标轮廓和阴影轮廓的主方向与场景图像主方向的可区分特性,通过阈值化投影值则可分割出目标区域和阴影区域,进而去除阴影区域. 最后,考虑到光照、目标自身大小、目标运动方向以及运动目标速度等因素对阴影的影响,文中在不同条件的视频上进行了实验,通过与原图对比和实验间相互对比验证了文中算法的有效性.
Abstract:
 As the image difference method were used to detect moving targets,moving targets shadow was detected as a motion target,so for the shadow problem of moving object detection under the fixed scene,proposed a simple and effective shadow removal approach based on geometric projection. Firstly,the principal image direction of the scene is computed by utilizing the vanishing point theory and scene prior knowledge. Secondly,combined the frames subtraction with the background subtraction,detect the foreground pixels and geometri-cally project them on the direction that is vertical to the computed principal direction. According to the fact that the principal directions of the target and shadow contours are distinguishable with the principal image direction of the scene,segment the shadow regions from the detected foreground pixels and remove it by thresholding the projection values. Finally,considering the influence of the light,their own size of targets,the direction of the target moving and moving target speed and other factors on the shadow,make the experiment on some videos with different conditions,and demonstrate the effectiveness of the proposed approach.

相似文献/References:

[1]张玉荣 涂铮铮 罗斌.基于帧差和小波包分析算法的运动目标检测[J].计算机技术与发展,2008,(01):136.
　ZHANG Yu-rong,TU Zheng-zheng,LUO Bin.Moving Object Detection Method Based on Frame- Difference and Wavelet Packets Analysis[J].,2008,(12):136.
[2]郭旭 张丽杰.运动目标检测视频监控软件的设计与实现[J].计算机技术与发展,2010,(08):199.
　GUO Xu,ZHANG Li-jie.Design and Implementation of Moving Target Detection Video Surveillance Software[J].,2010,(12):199.
[3]王陈阳 周明全 耿国华.基于自适应背景模型运动目标检测[J].计算机技术与发展,2007,(04):21.
　WANG Chen-yang,ZHOU Ming-quan,GENG Guo-hua.Moving Object Detection Based on Adaptive Background Model[J].,2007,(12):21.
[4]夏伟才 曾致远.一种基于卡尔曼滤波的背景更新算法[J].计算机技术与发展,2007,(10):134.
　XIA Wei-cai,ZENG Zhi-yuan.Background Update Algorithm Based on Kalman Filtering[J].,2007,(12):134.
[5]侯宏录 李宁鸟 刘迪迪 陈杰.智能视频监控中运动目标检测的研究[J].计算机技术与发展,2012,(02):49.
　HOU Hong-lu,LI Ning-niao,LIU Di-di,et al.Research on Moving Target Detection of Intelligent Video Surveillance[J].,2012,(12):49.
[6]王天召,徐克虎,黄大山.动态背景下的运动目标检测[J].计算机技术与发展,2013,(07):104.
　WANG Tian-zhao,XU Ke-hu,HUANG Da-shan.Moving Object Detection under Dynamic Background[J].,2013,(12):104.
[7]黄景星,吴伟隆,龙楚君,等.基于OpenCV的视频运动目标检测及其应用研究[J].计算机技术与发展,2014,24(03):15.
　HUANG Jing-xing,WU Wei-long,Long Chu-jun,et al.Study of Moving Object Detection in Video and Its Application Based on OpenCV[J].,2014,24(12):15.
[8]张志宏,吴庆波,邵立松,等.基于飞腾平台TOE协议栈的设计与实现[J].计算机技术与发展,2014,24(07):1.
　ZHANG Zhi-hong,WU Qing-bo,SHAO Li-song,et al. Design and Implementation of TCP/IP Offload Engine Protocol Stack Based on FT Platform[J].,2014,24(12):1.
[9]梁文快,李毅. 改进的基因表达算法对航班优化排序问题研究[J].计算机技术与发展,2014,24(07):5.
　LIANG Wen-kuai,LI Yi. Research on Optimization of Flight Scheduling Problem Based on Improved Gene Expression Algorithm[J].,2014,24(12):5.
[10]黄静,王枫,谢志新,等. EAST文档管理系统的设计与实现[J].计算机技术与发展,2014,24(07):13.
　HUANG Jing,WANG Feng,XIE Zhi-xin,et al. Design and Implementation of EAST Document Management System[J].,2014,24(12):13.
[11]杨磊,任衍允,蔡纪源. 一种基于深度数据的高斯模型运动目标检测方法[J].计算机技术与发展,2015,25(09):27.
　YANG Lei,REN Yan-yun,CAI Ji-yuan. A Gaussian Model Moving Target Detection Method Based on Depth Data[J].,2015,25(12):27.
[12]冯璞,李玉恵,李勃,等. 基于纹理特征的混合高斯背景建模算法研究[J].计算机技术与发展,2016,26(05):22.
　FENG Pu,LI Yu-hui,LI Bo,et al. Research on Gaussian Mixture Background Modeling Algorithm Based on Texture Feature[J].,2016,26(12):22.
[13]祝加祥[],胡鹏程[],何璇[],等. 基于滑动窗非负矩阵分解的运动目标检测方法[J].计算机技术与发展,2017,27(01):20.
　ZHU Jia-xiang[],HU Peng-cheng[],HE Xuan[],et al. Moving Target Detection Method Based on Non-negative Matrix Factorization of Sliding Window[J].,2017,27(12):20.
[14]张应辉,刘养硕. 基于帧差法和背景差法的运动目标检测[J].计算机技术与发展,2017,27(02):25.
　ZHANG Ying-hui,LIU Yang-shuo. Moving Object Detection Based on Method of Frame Difference and Background Subtraction[J].,2017,27(12):25.
[15]李强[],陈光化[],余渊[]. 基于随机游走和混合高斯模型的运动目标检测[J].计算机技术与发展,2017,27(06):11.
　LI Qiang[],CHEN Guang-hua[],YU Yuan[]. Moving Target Detection Based on Random Walk and GaussianMixture Model[J].,2017,27(12):11.
[16]傅赟,王桂丽,周旭廷,等. 交通监控系统中视频运动目标检测算法研究[J].计算机技术与发展,2017,27(08):156.
　FU Yun,WANG Gui-li,ZHOU Xu-ting,et al. Investigation on Video Moving Target Detection Algorithm in Traffic Monitoring System[J].,2017,27(12):156.

更新日期/Last Update: 2016-01-28