文章快速检索 高级检索
RGB和HSI颜色空间的一种改进的阴影消除算法

1. 济南大学 信息科学与工程学院, 山东 济南 250022;
2. 山东省网络环境智能计算技术重点实验室, 山东 济南 250022

An improved shadow removal algorithm based on RGB and HSI color spaces
HAN Yanbin1,2, GUO Xiaopeng1, WEI Yanwen1,2, LI Hengjian1,2
1. School of Information Science and Engineering, University of Jinan, Jinan 250022, China;
2. Shandong Provincial Key Laboratory of Network Based Intelligent Computing, Jinan 250022, China
Abstract: It is critical to exactly extract moving targets in intelligent video surveillance. There are many moving target detection algorithms, but for all the effects of shadow elimination are not ideal. In order to remove the shadow, an improved shadow removal algorithm based on RGB and HSI color spaces is presented. The analysis of the pixels in videoes shows that the hue is approximately consistent before and after the pixels are shaded, and there exists a linear relation between this approximate consistency and the value of luminance. On this basis, by utilizing the proportion of each color component in the color spaces and the relative change rates of brightness, the shadow of a moving object can be removed. The experimental results show that the shadow removal effect of this algorithm is better than that of the algorithm with (r, g, I) color space. In addition, it can also cope with holes in moving targets and is a supplement to the moving object detection algorithm.
Key words: target detection     shadow removal     color space     hole phenomenon     video analysis

1 阴影分析和颜色空间选取 1.1 阴影分析

1.2 颜色空间的选取

2 改进的阴影去除算法

 图 1 孔洞现象 Fig. 1 Holes phenomenon

1) 对场景进行背景建模，获取背景模型图像xb

2)根据式(3)提取背景图像的混合颜色空间各分量 rgI

3)从视频当中获取每帧图像，并计算混合颜色空间分量rgI

4)用式(6)取代式(4),计算当前像素点和背景图像颜色信息差值，进一步判定当前像素是否属于目标图像像素。

3 实验结果及分析

 图 2 (r,g,I)算法和(r，g,ΔI)室内阴影去除效果比较 Fig. 2 Comparison of shadow removal results between (r,g,I) algorithm and (r，g，ΔI) algorithm indoor

 图 3 (r,g,I)算法和(r,g,ΔI)算法室外阴影去除效果比较 Fig. 3 Comparison of shadow removal results between(r,g,I) algorithm and (r,g, ΔI) algorithm outdoor

4 结束语

 [1] MARTEL-BRISSON N, ZACCARIN A. Moving cast shadow detection from a Gaussian mixture shadow model[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005: 643-648. [2] WANG Yang, LOE K F, WU Jiankang. A dynamic conditional random field model for foreground and shadow segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(2): 279-289. [3] PORIKLI F, THOMTON J. Shadow flow: A recursive method to learn moving cast shadows[C]//Proceedings of Tenth IEEE International Conference on Computer Vision. Beijing, China, 2005: 891-898. [4] 褚一平, 叶修梓, 黄叶珏,等. 融合时空信息的前景/阴影视频分割算法[J]. 模式识别与人工智能, 2008, 21(4): 546-550. CHU Yiping, YE Xiuzi, HUANG Yejue, et al. A spatiotemporal algorithm for video foreground and shadow segmentation[J]. Pattern Recognition and Artificial Intelligence, 2008, 21(4): 546-550. [5] 王彬, 冯远静, 郭海峰, 等. 交通场景中车辆的运动检测与阴影消除[J]. 中国图象图形学报, 2012, 17(11): 1391-1399.WANG Bin, FENG Yuanjing, GUO Haifeng, et al. Adaptive background updating and shadow detection in traffic scenes[J]. Journal of Image and Graphics, 2012, 17(11): 1391-1399. [6] SALVADOR E, CAVALLARO A, EBRAHIMI T. Cast shadow segmentation using invariant color features[J]. Computer Vision and Image Understanding, 2004, 95(2): 238-259. [7] 董蓉, 李勃, 陈启美. 路况视频中HSV彩色不变量阴影检测法研究与改进[J]. 中国图象图形学报, 2009, 14(12): 2483-2487.DONG Rong, LI Bo, CHEN Qimei. Research and improvement on shadow detection in expressway videos using HSV color model[J]. Journal of Image and Graphics, 2009, 14(12): 2483-2487. [8] KUMAR P, SENGUPTA K, LEE A. A comparative study of different color spaces for foreground and shadow detection for traffic monitoring system[C]//Proceedings of the IEEE 5th International Conference on Intelligent Transportation Systems. Washington DC, USA, 2002: 100-105. [9] LEONE A, DISTANTE C. Shadow detection for moving objects based on texture analysis[J]. Pattern Recognition, 2007, 40(4): 1222-1233. [10] 万峻甫, 刘建伟, 向怀坤, 等. 交通视频序列阴影检测算法研究[J]. 中国图象图形学报, 2008, 13(3): 467-471.WAN Junfu, LIU Jianwei, XIANG Huaikun, et al. Research on shadow detection in grayscale video sequence for traffic images[J]. Journal of Image and Graphics, 2008, 13(3): 467-471. [11] 肖梅, 韩崇昭. 室内视频中基于边缘的运动阴影去除算法[J]. 模式识别与人工智能, 2006, 19(5): 640-644.XIAO Mei, HAN Chongzhao. Edge-based moving shadow removal algorithm for indoor video sequence[J]. Pattern Recognition and Artificial Intelligence, 2006, 19(5): 640-644. [12] 柏柯嘉, 刘伟铭, 汤义. 基于Gabor小波和颜色模型的阴影检测算法[J]. 华南理工大学学报:自然科学版. 2009, 37(1): 64-68.BAI Kejia, LIU Weimim, TANG Yi. Shadow detection algorithm based on Gabor wavelet and color model[J]. Journal of South China University of Technology:Natural Science Edition, 2009, 37(1): 64-68. [13] 郭利生, 郭立, 焦荣惠, 等. 一种基于运动阴影的目标检测算法[J]. 模式识别与人工智能, 2007, 20(2): 180-184.GUO Lisheng, GUO Li, JIAO Ronghui, et al. An object detection algorithm based on moving shadow[J]. Pattern Recognition and Artificial Intelligence, 2007, 20(2): 180-184. [14] 查宇飞, 楚瀛, 王勋, 等. 一种基于Boosting判别模型的运动阴影检测方法[J]. 计算机学报, 2007, 30(8): 1295-1301.ZHA Yufei, CHU Ying, WANG Xun, et al. A boosting discriminative model for moving cast shadow detection[J]. Chinese Journal of Computers, 2007, 30(8): 1295-1301. [15] GALLEGO J, PARDS M, HARO G. Enhanced foreground segmentation and tracking combining Bayesian background, shadow and foreground modeling[J]. Pattern Recognition Letters, 2012, 33(12): 1558-1568. [16] SONG Kaitai, TAI Jenchao. Image-based traffic monitoring with shadow suppression[J]. Proceedings of the IEEE, 2007, 95(2): 413-426. [17] JACQUES C S, JUNG C R, MUSSE S R. Background subtraction and shadow detection in grayscale video sequences[C]//Proceedings of the IEEE International Conference on Computer Graphics and Image Processing. Natal, Brazil, 2005: 189-196. [18] LI Jingping, QIN Min, XIA Yingjie, et al. Remarks on a novel statistical histogram—Average scene cumulative histogram[C]//IEEE International Conference on Granular Computing (GrC 2012). Hangzhou, China, 2012: 310-314. [19] 王真, 李金屏, 刘林, 等. 利用多颜色信息融合的自适应肤色建模[J]. 计算机工程与应用, 2011, 47(30): 210-214.WANG Zhen, LI Jinping, LIU Lin, et al. Adaptive shin color modeling based on color information fusion[J]. Computer Engineering and Applications, 2011, 47(30): 210-214. [20] 刘林, 李金屏, 王真. 基于多颜色空间和累计场均直方图的视频场景分类[J]. 中国体视学与图像分析, 2011, 16(1): 67-74.LIU Lin, LI Jinping, WANG Zhen. Video scene classification based on multiple color space and average scene histogram[J]. Chinese Journal of Stereology and Image Analysis, 2011, 16(1): 67-74. [21] 张中方, 李金屏, 拜佩. 基于多颜色空间融合的移动目标检测算法[J]. 济南大学学报: 自然科学版, 2011, 25(2): 191-195.ZHANG Zhongfang, LI Jinping, BAI Pei. Mobile object detection algorithm based on information fusion of multiple color spaces[J]. Journal of University of Jinan: Science and Technology, 2011, 25(2): 191-195. [22] WNAG Hanzi, SUTER D. A re-evaluation of mixture of Gaussian background modeling[C]//IEEE International Conference on Acoustics, Speech, and Signal Proceedings. Philadelphia, USA, 2005: 1017-1020. [23] 陈焕钟, 李榕, 程剑光. 基于混合高斯模型的运动目标检测[J]. 激光杂志, 2009, 3(4): 32-33.CHEN Huanzhong, LI Rong, CHENG Jianguang. Moving objects detection based on Gaussian mixture models[J]. Laser Journal, 2009, 3(4): 32-33. [24] WANG Hanzi, DAVID S. A consensus-based method for tracking: modelling background scenario and foreground appearance[J]. Pattern Recognition, 2007, 40(3): 1091-1105. [25] ZENG Huanglin, WANG Zhenya. A new algorithm of an improved detection of moving vehicles[M]//Advances in Swarm Intelligence. Berlin/Heidelberg: Springer, 2010: 688-693. [26] JIANG Caixia, WARD M O. Shadow identification[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Champaign, USA, 1992: 606-612.
DOI: 10.11992/tis.201410010

0

#### 文章信息

HAN Yanbin, GUO Xiaopeng, WEI Yanwen, LI Hengjian
RGB和HSI颜色空间的一种改进的阴影消除算法
An improved shadow removal algorithm based on RGB and HSI color spaces

CAAI Transactions on Intelligent Systems, 2015, 10(05): 769-774.
DOI: 10.11992/tis.201410010