基于超像素和局部颜色恒常性的自适应阴影去除

doi:10.11772/j.issn.1001-9081.2016.10.2837

计算机应用 ›› 2016, Vol. 36 ›› Issue (10): 2837-2841.DOI: 10.11772/j.issn.1001-9081.2016.10.2837

基于超像素和局部颜色恒常性的自适应阴影去除

兰丽, 何小海, 吴晓红, 滕奇志

四川大学电子信息学院, 成都 610065

收稿日期:2016-05-05 修回日期:2016-06-06 发布日期:2016-10-10
通讯作者: 何小海,E-mail:hxh@scu.edu.cn
作者简介:兰丽(1990—),女,四川广安人,硕士研究生,主要研究方向:数字图像处理、模式识别;何小海(1964—),男,四川绵阳人,教授,博士,主要研究方向:图像处理、视频通信;吴晓红(1970—),女,四川射洪人,副教授,博士,主要研究方向:图像处理、模式识别;滕奇志(1962—),女,四川成都人,教授,博士,主要研究方向:图像处理、三维重建。
基金资助:
国家自然科学基金委员会和中国工程物理研究院联合基金资助项目（11176018）；特殊环境机器人技术四川省重点实验室开放基金资助项目（14zxtk03）；成都市科技惠民项目（2015-HM01-00293-SF）。

Adaptive shadow removal based on superpixel and local color constancy

LAN Li, HE Xiaohai, WU Xiaohong, TENG Qizhi

College of Electronic Information Engineering, Sichuan University, Chengdu Sichuan 610065, China

Received:2016-05-05 Revised:2016-06-06 Published:2016-10-10
Supported by:
BackgroundThis work is partially supported by the Joint Fund of the National Natural Science Foundation of China and the China Academy of Engineering Physics (11176018), the Open Fund of Robot Technology used for Special Environment Key Laboratory of Sichuan Province (14zxtk03), the Technology Program of Public Wellbeing of Chengdu (2015-HM01-00293-SF).

摘要/Abstract

摘要： 为快速有效地去除监控视频中运动目标的投射阴影，提出了一种基于超像素和阴影区域的局部颜色恒常性的自适应阴影去除算法。首先采用改进的简单线性迭代聚类算法将视频图像中的运动前景分割为互不重叠的超像素；然后计算了RGB颜色空间中背景与运动前景的亮度比率，并分析了阴影区域的局部颜色恒常性；在此基础上，以超像素为基本处理单元，计算亮度比率的标准差，并利用阴影区域标准差的特征及其分布规律提出基于拐点的自适应阈值算法检测并去除阴影。实验结果表明，该算法可以适用于多种真实场景下的阴影检测，且阴影检测率与目标识别率均超过85%；基于超像素处理可以大幅度降低算法的计算复杂度，该算法每帧平均处理时间为20 ms。该算法可以同时满足阴影去除对准确度、实时性和鲁棒性的要求。

关键词: 超像素分割, 运动目标检测, 阴影去除, 局部颜色恒常性, 标准差, 自适应阈值

Abstract: In order to remove the moving cast shadow in the surveillance video quickly and efficiently, an adaptive shadow elimination method based on superpixel and local color constancy of shaded area was proposed. First, the improved simple linear iterative clustering algorithm was used to divide the moving area in the video image into non-overlapping superpixels. Then, the luminance ratio of background and the moving foreground in the RGB color space was calculated, and the local color constancy of shaded area was analyzed. Finally, the standard deviation of the luminance ratio was computed by taking superpixel as basic processing unit, and an adaptive threshold algorithm based on turning point according to the characteristic and distribution of the standard deviation of the shadowed region was proposed to detect and remove the shadow. Experimental results show that the proposed method can process shadows in different scenarios, the shadow detection rate and discrimination rate are both more than 85%; meanwhile, the computational cost is greatly reduced by using the superpixel, and the average processing time per frame is 20 ms. The proposed algorithm can satisfy the shadow removal requirements of higher precision, real-time and robustness.

Key words: superpixel division, moving target detection, shadow removal, local color constancy, standard deviation, adaptive threshold

中图分类号:

TP391.4

兰丽, 何小海, 吴晓红, 滕奇志. 基于超像素和局部颜色恒常性的自适应阴影去除[J]. 计算机应用, 2016, 36(10): 2837-2841.

LAN Li, HE Xiaohai, WU Xiaohong, TENG Qizhi. Adaptive shadow removal based on superpixel and local color constancy[J]. Journal of Computer Applications, 2016, 36(10): 2837-2841.

参考文献

[1] YUAN X, EBNER M, WANG Z. Single-image shadow detection and removal using local colour constancy computation[J]. IET Image Processing, 2015, 9(2): 118-126.
[2] PRATI I M, TRIVEDI M, CUCCHIARA R. Detecting moving shadows: algorithms and evaluation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(7):918-923.
[3] SANIN A, SANDERSON C, LOVELL B C. Shadow detection: a survey and comparative evaluation of recent methods[J]. Pattern Recognition, 2013, 45(4):1684-1695.
[4] NICOLAS H, PINEL J M. Joint moving cast shadows segmentation and light source detection in video sequences[J]. Signal Processing: Image Communication, 2006, 21(1):22-43.
[5] MARTEL-BRISSON N, ZACCARIN A. Kernel-based learning of cast shadows from a physical model of light sources and surfaces for low-level segmentation[C]//CVPR 2008: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2008:1-8.
[6] HSIEH J W, HU W F, CHANG C J, et al. Shadow elimination for effective moving object detection by Gaussian shadow modeling[J]. Image & Vision Computing, 2003, 21(3):505-516.
[7] SERRA M, PENACCHIO O, BENAVENTE R, et al. Names and shades of color for intrinsic image estimation[C]//CVPR 2012: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2012: 278-285.
[8] AMATO A, MOZEROV M G, BAGDANOV A D, et al. Accurate moving cast shadow suppression based on local color constancy detection[J]. IEEE Transactions on Image Processing, 2011, 20(10): 2954-2966.
[9] SANIN A, SANDERSON C, LOVELL B C. Improved shadow removal for robust person tracking in surveillance scenarios[C]//ICPR 2010: Proceedings of the 2010 20th International Conference on Pattern Recognition. Piscataway, NJ: IEEE, 2010:141-144.
[10] LEONE A, DISTANTE C. Shadow detection for moving objects based on texture analysis[J]. Pattern Recognition, 2007, 40(4):1222-1233.
[11] WANG J, YAGI Y. Pedestrian detection based on appearance, motion, and shadow information[C]//SMC 2012: Proceedings of the 2012 IEEE International Conference on Systems, Man, and Cybernetics. Piscataway, NJ: IEEE, 2012:750-755.
[12] LALONDE J F, EFROS A A, NARASIMHAN S G. Detecting ground shadows in outdoor consumer photographs[C]//Proceedings of the 11th European Conference on Computer Vision. Berlin: Springer, 2010: 322-335.
[13] 朱周, 路小波, 卫朋, 等. 基于超像素和支持向量机的车辆阴影检测算法[J]. 东南大学学报(自然科学版), 2015(3):443-447.(ZHU Z, LU X B, WEI P, et al. Vehicle shadow detection algorithm based on superpixel and SVM[J]. Journal of Southeast University (Natural Science Edition), 2015(3):443-447.)
[14] BARNICH O, VAN DROOGENBROECK M. ViBe: a universal background subtraction algorithm for video sequences[J]. IEEE Transactions on Image Processing, 2011, 20(6):1709-1724.
[15] ACHANTA R, SHAJI A, SMITH K, et al. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282.
[16] MORERIO P, GEORGIU G C, MARCENARO L, et al. Optimizing superpixel clustering for real-time egocentric-vision applications[J]. IEEE Signal Processing Letters, 2015, 22(4):469-473.
[17] SALVADOR E, CAVALLARO A, EBRAHIMI T. Cast shadow segmentation using invariant color features[J]. Computer Vision and Image Understanding, 2004, 95(2): 238-259.

基于超像素和局部颜色恒常性的自适应阴影去除

Adaptive shadow removal based on superpixel and local color constancy

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	王思鹏, 杜昌平, 叶志贤, 宋广华, 郑耀. 基于多步神经网络观测器的扑翼飞行器缓变故障检测[J]. 计算机应用, 2020, 40(8): 2449-2454.
[2]	张淑萍, 吴文, 万毅. 基于多阶段生成对抗网络的单幅图像阴影去除方法[J]. 计算机应用, 2020, 40(8): 2378-2385.
[3]	张皓然, 王学渊, 李小霞. 基于自适应阈值活动语音检测和最小均方误差对数谱幅度估计的低信噪比降噪算法[J]. 计算机应用, 2020, 40(6): 1763-1768.
[4]	王忠锋, 徐志远, 宋纯贺, 张宏宇, 蔡颖凯. 基于梯度的深度网络剪枝算法[J]. 计算机应用, 2020, 40(5): 1253-1259.
[5]	王彤, 王巍, 崔益豪, 朱天宇. 基于颜色布局描述子的改进ViBe算法[J]. 计算机应用, 2020, 40(3): 812-818.
[6]	王书朋, 赵瑶. 基于自适应分割的多曝光图像融合算法[J]. 计算机应用, 2020, 40(1): 252-257.
[7]	王治忠, 李泓毅, 韩闯. 基于香农能量与自适应阈值的心电QRS复合波检测算法[J]. 计算机应用, 2020, 40(1): 304-310.
[8]	廖斌, 谭道强, 吴文. 基于衰减式生成对抗网络的单幅图像阴影去除[J]. 计算机应用, 2019, 39(9): 2712-2718.
[9]	丁莲静, 刘光帅, 李旭瑞, 陈晓文. 加权信息熵与增强局部二值模式结合的人脸识别[J]. 计算机应用, 2019, 39(8): 2210-2216.
[10]	姚学练, 贺福强, 平安, 罗红, 万思路. 基于HSI颜色空间与灰度波动相结合的复杂桥梁蜂窝麻面的图像分割[J]. 计算机应用, 2019, 39(3): 882-887.
[11]	廖斌, 吴文. 区域配对引导的光照传播视频阴影去除方法[J]. 计算机应用, 2019, 39(2): 556-563.
[12]	李登刚, 陈香香, 李华丽, 王忠美. 基于超像素的流形正则化稀疏约束NMF混合像元分解算法[J]. 计算机应用, 2019, 39(10): 3100-3106.
[13]	刘宇, 金伟正, 范赐恩, 邹炼. 使用超像素分割与图割的网状遮挡物检测算法[J]. 计算机应用, 2018, 38(1): 238-245.
[14]	徐苏, 周颖玥. 基于图像分割的非局部均值去噪算法[J]. 计算机应用, 2017, 37(7): 2078-2083.
[15]	彭政, 陈东方, 王晓峰. 正则化超分辨率重建过程的自适应阈值去噪[J]. 计算机应用, 2017, 37(7): 2084-2088.