Computer Science ›› 2018, Vol. 45 ›› Issue (6): 291-295.doi: 10.11896/j.issn.1002-137X.2018.06.051

• Graphics, Image & Pattern Recognition • Previous Articles     Next Articles

Moving Shadow Removal Algorithm Based on Multi-feature Fusion

CHEN Rong, LI Peng, HUANG Yong   

  1. College of Information Engineering,Xiangtan University,Xiangtan,Hunan 411105,China
  • Received:2017-06-24 Online:2018-06-15 Published:2018-07-24

Abstract: Aiming at the problem of the moving cast shadow in the video surveillance,this paper proposed an shadow removal algorithm which combines color feature,normalized vector distance and intensity ratio.First,the background picture is built according to Gaussian mixture model,and motion region is acquired by background subtraction.Then,serial fusion method is adapted to detect and remove shadow pixels.Based on shadow detection according to the color consistent feature in RGB color space,the normalized vector distance distribution histogram is implemented to detect sha-dow pixels further.Finally,in view of the mistaken identification in the testing process,the illumination model of pixel is built and the intensity ratio of shadow pixel and background pixel is calculated to rule out the mistakenly identified foreground pixels according to the confidence interval.The results of experiment show that the proposed method can overcome the limitation of single feature method,and is able to detect and remove shadow under various circumstances efficiently.The adaptability and robustness of this algorithm are validated,and its processing time is moderate.

Key words: Color feature, Intensity model, Multi-feature fusion, Normalized vector distance, Shadow removal

CLC Number: 

  • TP391.9
[1]SANIN A,SANDERSON C,LOVELL B C.Shadow detection:A survey and comparative evaluation of recent methods [J].Pattern Recognition,2012,45(4):1684-1695.
[2]ZIVKOVIC Z.Improved adaptive Gaussian mixture model for background subtraction[C]//The 17th International Conference on pattern Recognition.2004:28-31.
[3]ONOGUCHI K.Shadow elimination method for moving object detection[C]//Proceedings of International Conference on Pattern Recognition.1998:583-587.
[4]ZHAO L,YU H M.Vehicle detecton based on shape priors and level set[J].Journal of Zhejiang University (Engineering Scien-ce),2010,44(1):124-130.(in Chinese)
赵璐,于慧敏.基于先验形状信息和水平集方法的车辆检测[J].浙江大学大学学报,2010,44(1):124-130.
[5]GAO X J,WAN Y C,YANG Y W,et al.Automatic Shadow Detection and Automatic Compensation in High Resolution Remote Sensing Images[J].Acta Automatica Sinca,2014,40(8):1709-1720.(in Chinese)
高贤君,万幼川,杨元维,等.高分辨率遥感影像的自动检测与自动补偿[J].自动化学报,2014,40(8):1709-1720.
[6]CHEN C T,SU C Y,KAO W C.An enhanced segmentation on vision-based shadow removal for vehicle detection[C]//Procee-dings of the International Green Circuits and Systems.2010:679-682.
[7]SALVADOR E,CAVALLARO A,EBRAHIMI T.Cast shadow segmentation using invariant color features[J].Computer Vision and Image Understanding,2004,95(2):238-259.
[8]HAN Y X,ZHANG Z S.Shadowd detection based on texture feature in gray sequence images[J].Optics and Precision Engineering,2013,21(11):2931-2942.(in Chinese)
韩延祥,张志胜.灰度序列图像中基于纹理特征的移动阴影检测[J].光学精密工程,2013,21(11):2931-2942.
[9]CAO J,CHEN H Q,ZHANG K,et al.Moving cast shadow detection based onregion color and texture[J].Robot,2011,33(5):638-633.(in Chinese)
曹健,陈红倩,张凯,等.结合区域颜色和纹理的运动阴影检测方法[J].机器人,2011,33(5):638-633.
[10]QI M,DAI J Y,ZHANG Q,et al.Cascaded cast shadow detection method in surveillance scenes[J].Optik,2014,125(3):1396-1400.
[11]TANG C,AHMAD M O,WANG C Y.An efficient method of cast shadow removal using multiple features[J].Signal,Image and Video Processing,2013,4(7):695-703.
[12]NAKAGAMI K,NISHITANI T.The study on shadow removal on transform domain GMM foreground segmentation [C]//Proceedings of International Symposium on Communication and Information Technologies.2010:867-872.
[13]ZHANG L,ZHANG Q,XIA C X.Shadow Remover:Image Shadow Removal Based on Illumination Recovering Optimization[J].IEEE Transactions on Image Processing,2015,24(11):4623-4636.
[14]CAO X J,WANG W T,SONG X L,et al.Vehicle shadow detection and Vehicle tracking algorithm based on multiple information fusio[J].Journal of Central South University (Science and Technology),2015,46(11):4049-4055.(in Chinese)
曹晓娟,王文涛,宋晓琳,等.基于多信息融合的车辆检测与车辆跟踪算法[J].中南大学学报(自然科学版),2015,46(11):4049-4055.
[15]HIGASHI K,FUKUI S,ADACHI Y,et al.New feature for shadow detection by combination of two features roust to illumination changes[C]//20th International Conference on Knowledge Based and Intelligent Information and Engineering Systems.2016:896-903.
[16]NADIMI S,BHANU B.Physical model for moving shadow and object detection in video[J].IEEE Transactions on Pattern Analysis and Machine,2004,26(8):1079-1087.
[17]PRATI A,MIKIC I,TRIVEDI M M,et al.Detecting moving shadows:algorithms and evaluation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):918-923.
[18]YANG L,SU L H,WU B G,et al.Targe Detection Algorithm of Hyperspectral Remote Sensing Imagery Combined with CEM[J].Journal of Chongqing University of Technology(Natural Science),2017,31(12):146-150,172.(in Chinese)
杨磊,苏令华,吴宝刚,等.一种结合CEM的高光谱遥感影像目标检测算法[J].重庆理工大学学报(自然科学),2017,31(12):146-150,172.
[1] YU Shu-hao, ZHOU Hui, YE Chun-yang, WANG Tai-zheng. SDFA:Study on Ship Trajectory Clustering Method Based on Multi-feature Fusion [J]. Computer Science, 2022, 49(6A): 256-260.
[2] LI Peng-zu, LI Yao, Ibegbu Nnamdi JULIAN, SUN Chao, GUO Hao, CHEN Jun-jie. Construction and Classification of Brain Function Hypernetwork Based on Overlapping Group Lasso with Multi-feature Fusion [J]. Computer Science, 2022, 49(5): 206-211.
[3] NIU Fu-sheng, GUO Yan-bu, LI Wei-hua, LIU Wen-yang. Protein Solubility Prediction Based on Sequence Feature Fusion [J]. Computer Science, 2022, 49(1): 285-291.
[4] WANG Chun-jing, LIU Li, TAN Yan-yan, ZHANG Hua-xiang. Image Retrieval Method Based on Fuzzy Color Features and Fuzzy Smiliarity [J]. Computer Science, 2021, 48(8): 191-199.
[5] SHI Heng, ZHANG Ling. Image Shadow Removal Algorithm Based on Generative Adversarial Network [J]. Computer Science, 2021, 48(6): 145-152.
[6] LYU Jin-na, XING Chun-yu , LI Li. Video Character Relation Extraction Based on Multi-feature Fusion and Fine-granularity Analysis [J]. Computer Science, 2021, 48(4): 117-122.
[7] LUAN Xiao, LI Xiao-shuang. Face Anti-spoofing Algorithm Based on Multi-feature Fusion [J]. Computer Science, 2021, 48(11A): 409-415.
[8] YUAN Xiao-pei, CHEN Xiao-feng, LIAN Ming. Improved Multi-feature Fusion Algorithm for Target Detection Based on Haar-like and LBP [J]. Computer Science, 2021, 48(11): 219-225.
[9] HU Yu-jia, GAN Wei, ZHU Min. Enhancer-Promoter Interaction Prediction Based on Multi-feature Fusion [J]. Computer Science, 2020, 47(5): 64-71.
[10] 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.
[11] JIN Kun, CHEN Shao-chang. Status and Development of Gait Recognition [J]. Computer Science, 2019, 46(6A): 30-34.
[12] WU Fan, LI Shou-shan, ZHOU Guo-dong. Movie Review Professionalism Classification Using LSTM and Features Fusion [J]. Computer Science, 2019, 46(6A): 74-79.
[13] WANG Xiao, ZOU Ze-wei, LI Bo-bo, WANG Jing. Target Detection in Colorful Imaging Sonar Based on Multi-feature Fusion [J]. Computer Science, 2019, 46(6A): 177-181.
[14] ZENG Fan-zhi, ZHOU Yan, YU Jia-hao, LUO Yue, QIU Teng-da, QIAN Jie-chang. End-to-End Retrieval Algorithm of Two-dimensional Engineering CAD Model Based on Unsupervised Learning [J]. Computer Science, 2019, 46(12): 298-305.
[15] WANG Wei-hong, CHEN Xiao, WU Wei, GAO Xing-yu. Method of Automatically Extracting Urban Water Bodies from High-resolution Images with Complex Background [J]. Computer Science, 2019, 46(11): 277-283.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!