空-频域联合投票的交通视频阴影去除方法

doi:10.11896/jsjkx.190400040

计算机科学 ›› 2020, Vol. 47 ›› Issue (5): 129-136.doi: 10.11896/jsjkx.190400040

• 计算机图形学&多媒体 • 上一篇下一篇

空-频域联合投票的交通视频阴影去除方法

宋传鸣, 洪旭, 王相海

辽宁师范大学计算机与信息技术学院辽宁大连116029

收稿日期:2019-04-08 出版日期:2020-05-15 发布日期:2020-05-19
通讯作者: 宋传鸣(chmsong@lnnu.edu.cn)
基金资助:
大连市高层次人才创新支持计划项目(2015R069)

Shadow Removal of Traffic Surveillance Video by Joint Voting in Spatial-Frequency Domain

SONG Chuan-ming, HONG Xu, WANG Xiang-hai

School of Computer and Information Technology,Liaoning Normal University,Dalian,Liaoning 116029,China

Received:2019-04-08 Online:2020-05-15 Published:2020-05-19
About author:SONG Chuan-ming,born in 1980,associate professor,is a member of CCF.His main research interests include ima-ge and video coding,and traffic surveillance video processing.
Supported by:
This work was supported by the Dalian Foundation for Youth Science and Technology Star(2015R069).

摘要/Abstract

摘要： 交通场景中的静止或运动阴影往往会降低车辆目标跟踪的精度,因此有效地去除阴影是交通监控视频处理的重要环节之一。然而,目前尚无一种能够同时发掘阴影的空间域和频率域特性且抵抗静止和运动阴影干扰的阴影去除方法。为此,提出了一种基于空-频域联合投票策略的交通视频阴影去除方法。首先,将视频帧从RGB颜色空间转换到HSV颜色空间,再进行非下采样剪切波变换;其次,假设变换系数服从高斯分布,采用变换系数的均值和标准差计算每个尺度的加权掩码;然后,根据多尺度变换系数的零树分布特性,利用粗尺度的加权掩码校正细尺度的加权掩码,将各个尺度、各个颜色通道的加权掩码进行线性组合后得到一个公共掩码,再采用基于最小二乘法拟合的最大熵方法计算自适应分割阈值,对公共掩码进行二值化;最后,联合频率域加权掩码、S通道和V通道的掩码进行投票,进而确定去除阴影后的运动车辆区域。实验结果表明,该算法可有效去除交通监控视频中的静态/运动阴影,抑制阴影的干扰,将传统Meanshift算法的输出车辆轨迹与真实轨迹间的平均欧氏距离缩小95%,且未出现目标丢失的现象,增强了智能分析算法的鲁棒性。研究结果说明,该算法有效联合交通监控视频的空间域和频率域表示,充分发掘了运动车辆区域与阴影区域之间的纹理特性和颜色特性差异,有利于获得更精确的阴影去除结果,进而提高车辆目标跟踪的精度。

关键词: 多尺度加权掩码, 非下采样剪切波, 交通监控视频, 联合投票, 阴影去除

Abstract: The static or moving shadows in traffic scenes tend to reduce the accuracy of vehicle target tracking.Thus,it is an important step to effectively remove the shadows in the processing of traffic surveillance videos.However,there hardly is an efficient shadow removal method yet at present,which resists both static and moving shadows by simultaneously exploring the spatial and frequency characteristics of shadows.Under such a circumstance,this study proposed a shadow removal method for traffic video by using a joint voting strategy in spatial-frequency domain.The surveillance video is converted from RGB space into HSV space and then performed non-subsampled shearlet transform (NSST).Assuming that NSST coefficients follows the Gaussian distribution,the mean and standard deviation of coefficients is used to compute the weighted mask for each scale.Subsequently,the weighted mask at coarse scale is employed to adjust the mask at fine scale,according to the zerotree characteristics of multiscale coefficients.The weighted masks of different scales and color channels are thus linearly combined to form a unified mask,which is then binarized by an adaptive threshold calculated by the maximum entropy segmentation based on the least square method.Finally,the moving vehicle area after shadow removal is determined by a joint voting strategy by using the weighted frequency-domain mask,the S-channel mask and the V-channel mask respectively.Experimental results show that the proposed algorithm can effectively remove the static and moving shadows in traffic surveillance video.It reduces the average Euclidean distance by 95% between the ideal trajectory and the output vehicle trajectory of traditional mean shift algorithm,suppressing the interfe-rence of shadows.Meanwhile,the proposed algorithm enhances the robustness of the intelligent analysis and avoids the phenomenon of losing the target.Our research indicates that it is conducive to obtaining more accurate shadow removal result to effectively combine the representation of traffic surveillance video in spatial and frequency domains,and to fully explore the differences of texture features and color features between moving vehicle areas and shadow areas.The accuracy of vehicle target tracking will be therefore improved.

Key words: Joint voting, Multiscale weighted mask, Non-subsampled Shearlet transform, Shadow removal, Traffic surveillance video

中图分类号:

TP399

宋传鸣, 洪旭, 王相海. 空-频域联合投票的交通视频阴影去除方法[J]. 计算机科学, 2020, 47(5): 129-136. https://doi.org/10.11896/jsjkx.190400040

SONG Chuan-ming, HONG Xu, WANG Xiang-hai. Shadow Removal of Traffic Surveillance Video by Joint Voting in Spatial-Frequency Domain[J]. Computer Science, 2020, 47(5): 129-136. https://doi.org/10.11896/jsjkx.190400040

参考文献

[1]TOYAMA K,KRUMM J,BRUMITT B,et al.Wallflower:principles and practice of background maintenance[C]//Proceedings of the IEEE International Conference on Computer Vision.New York:IEEE Press,1999:255-261.
[2]BOUWMANS T.Traditional and recent approaches in back-ground modeling for foreground detection:an overview [J].Computer Science Review,2014,11-12(1):31-66.
[3]GUO L L.Research on motion target detection technology for complex scenes [D].Kunming:Yunnan University,2017.
[4]CUCCHIARA R,GRANA C,NERI G,et al.The sakbot system for moving object detection and tracking[C]//Proceedings of the European Workshop on Advanced Video-Based Surveillance Systems.Boston:Springer Press,2001:145-157.
[5]DENG Y L,WU L F,LI Y T.An effective shadow removal approach [J].Signal Processing,2011,27(11):1724-172.
[6]CHOI J M,YOO Y J,CHOI J Y.Adaptive shadow estimator for removing shadow of moving object [J].Computer Vision and Image Understanding,2010,114(9):1017-1029.
[7]XIANG J H,FAN H,LIAO H H,et al.Moving object detection and shadow removing under changing illumination condition [J/OL].https://doi.org/10.1155/2014/827461.
[8]OUIVIRACH K,DAILEY M N.Extracting the object from the shadows:maximum likelihood object/shadow discrimination[C]//Proceedings of the IEEE International Conference on Electrical Engineering/ Electronics,Computer,Telecommunications and Information Technology.New York:IEEE Press,2013:1-5.
[9]LIU Z,HUANG K,TAN T.Cast shadow removal in a hierarchical manner using MRF [J].IEEE Transactions on Circuits and Systems for Video Technology,2012,22(1):56-66.
[10]SALVADOR E,CAVALLARO A,EBRAHIMI T.Cast shadow segmentation using invariant color features [J].Computer Vision and Image Understanding,2004,95(2):238-259.
[11]CHEN R,LI P,HUANG Y.Motion shadow removal algorithm based on multi-feature fusion [J].Computer Science,2012,45(6):291-295.
[12]TIAN J,ZHU L,TANG Y.Outdoor shadow detection by combining tricolor attenuation and intensity [J].EURASIP Journal on Advances in Signal Processing,2012,2012:116-123.
[13]GUAN Y.Unsupervised motion detection with background update and shadow suppression [J].Journal of Control Theory & Applications,2012,10(4):517-522.
[14]KHARE M,SRIVASTAVA R K,KHARE A.Dual tree complex wavelet transform based shadow detection and removal from moving objects[C]//Proceedings of the SPIE 9029,Visual Information Processing and Communication V.Bellingham:SPIE Press,2014.
[15]WANG X H,WANG K,LIU M Y,et al.Zero-tree waveletbased vehicle motion shadow filtering method for traffic video [J].Pattern Recognition And Artificial Intelligence,2016,29(12):1104-1113.
[16]XU M L,ZHU J J,LV P,et al.Learning-based shadow recognition and removal from monochromatic natural images [J].IEEE Transactions on Image Processing,2017,26(12):5811-5824.
[17]NUR S A,IBRAHIM M M,ALI N M,et al.Vehicle detection based on underneath vehicle shadow using edge features[C]//Proceedings of the IEEE International Conference on Control System,Computing and Engineering (ICCSCE).New York:IEEE Press,2016:407-412.
[18]LV J.Research and implementation of target detection and shadowsuppression algorithm in video monitoring system [D].Shen-yang:Northeast University,2010.
[19]WANG X H,NI P G,SU X,et al.The nonsubsampled Contourlet HMT model [J].SCIENCE CHINA Information Sciences,2013,43(11):1431-1444.
[20]WANG X H,LIU M Y,SU Y H,et al.Traffic video vehicletracking algorithm based on Contourlet and MeanShift [J].Journal of Liaoning Normal University (Natural Science Edition),2017,40(2):192-198.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

空-频域联合投票的交通视频阴影去除方法

Shadow Removal of Traffic Surveillance Video by Joint Voting in Spatial-Frequency Domain

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

Metrics

本文评价

推荐阅读 0

[1]	王卫红, 陈骁, 吴炜, 高星宇. 高分影像复杂背景下的城市水体自动提取方法 Method of Automatically Extracting Urban Water Bodies from High-resolution Images with Complex Background 计算机科学, 2019, 46(11): 277-283. https://doi.org/10.11896/jsjkx.181001985
[2]	侯瑞超,周冬明,聂仁灿,刘栋,郭晓鹏. 结合视觉显著性与Dual-PCNN的红外与可见光图像融合 Infrared and Visible Images Fusion Using Visual Saliency and Dual-PCNN 计算机科学, 2018, 45(6A): 162-166.
[3]	陈嵘, 李鹏, 黄勇. 基于多特征融合的运动阴影去除算法 Moving Shadow Removal Algorithm Based on Multi-feature Fusion 计算机科学, 2018, 45(6): 291-295. https://doi.org/10.11896/j.issn.1002-137X.2018.06.051
[4]	杨利素, 王雷, 郭全. 基于NSST与自适应PCNN的多聚焦图像融合方法 Multi-focus Image Fusion Method Based on NSST and Adaptive PCNN 计算机科学, 2018, 45(12): 217-222. https://doi.org/10.11896／j.issn.1002-137X.2018.12.036
[5]	臧继昆,喻剑. 基于事件密集度的交通监控视频存储方法 Traffic Surveillance Video Storage in HDFS Based on Event Density 计算机科学, 2015, 42(5): 221-224. https://doi.org/10.11896/j.issn.1002-137X.2015.05.044