Adaptive Moving Cast Shadow Detection by Integrating Multiple Cues

LING Zhigang; LU Xiao; WANG Yaonan; HE Xi

Article Contents

Article Navigation > Chinese Journal of Electronics > 2013 > 22(4): 757-762

LING Zhigang, LU Xiao, WANG Yaonan, et al., “Adaptive Moving Cast Shadow Detection by Integrating Multiple Cues,” Chinese Journal of Electronics, vol. 22, no. 4, pp. 757-762, 2013,

Citation:

LING Zhigang, LU Xiao, WANG Yaonan, et al., “Adaptive Moving Cast Shadow Detection by Integrating Multiple Cues,” Chinese Journal of Electronics, vol. 22, no. 4, pp. 757-762, 2013,

LING Zhigang, LU Xiao, WANG Yaonan, et al., “Adaptive Moving Cast Shadow Detection by Integrating Multiple Cues,” Chinese Journal of Electronics, vol. 22, no. 4, pp. 757-762, 2013,

Citation:

LING Zhigang, LU Xiao, WANG Yaonan, et al., “Adaptive Moving Cast Shadow Detection by Integrating Multiple Cues,” Chinese Journal of Electronics, vol. 22, no. 4, pp. 757-762, 2013,

PDF( 310 KB)

Adaptive Moving Cast Shadow Detection by Integrating Multiple Cues

College of Electrical and Information Engineering, Hunan University, Changsha 410082, China

Funds: This work is supported by the National High Technology Research and Development Program of China (863 Program) (No.2012AA112312), the National Natural Science Foundation of China (No.61175075) and Science and Technology Project of Ministry of Transport of China (No.201231849A70).

More Information

Corresponding author: LING Zhigang, LU Xiao, HE Xi
Received Date: 2012-08-01
Rev Recd Date: 2012-12-01
Publish Date: 2013-09-25

Abstract

Abstract

Moving cast shadow detection and removal is a key step for accurate object detection in intelligent transportation system. This paper proposes a robust cast shadow detection algorithm by integrating multiple cues. Firstly, a weak shadow detector is adopted to detect these potential shadow pixels; Then three adaptive shadow estimators are designed and cascaded to integrate texture, chromaticity, brightness as well as spatial-temporal context for eliminating the object pixels so that this algorithm can robustly detect the moving cast shadow in the various environments; Lastly, spatial adjustment is employed to verify the shadow detection results of these three shadow estimators. Experimental results on indoor and outdoor video sequences show that this proposed algorithm can robustly detect moving cast shadow and rapidly adapt to variations in traffic surveillance scenarios.
- Multiple cues,
- Adaptive shadow estimators,
- Texture difference,
- Chromaticity and brightness distortion,
- Moving cast shadow detection

FullText(HTML)

References(18)

References

C. Grana, M. Piccardi, A. Prati, “Detecting moving objects,g hosts and shadows in video stream”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.25, No.10,p p.1337-1342, 2003.

S. Nadimi, B. Bhanu, “Physical models for moving shadow ando bject detection in video”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.26, No.8, pp.1079-1087,2 004.

N. Martel-Brisson, A. Zaccarin, “Learning and removing casts hadows through a multidistribution approach”, IEEE Transactionso n Pattern Analysis and Machine Intelligence, Vol.29,N o.7, pp.1133-1146, 2007.

A.J. Joshi, N.P. Papanikolopoulos, “Learning to detect movings hadows in dynamic environments”, IEEE Transactionso n Pattern Analysis and Machine Intelligence, Vol.30, No.11,p p.2055-2063, 2008.

M.T. Yang, K.H. Lo, C.C. Chiang et al., “Moving cast shadowd etection by exploiting multiple cues”, IET Image Processing,Vol.2, No.2, pp.95-104, 2008.

Y.Wang, “Real-time moving vehicle detection with cast shadowr emoval in video based on conditional random field”, IEEET ransactions on Circuits and Systems for Video Technology,Vol.19, No.3, pp.437-441, 2009.

J. Huang, C. Chen, “Moving cast shadow detection usingp hysics-based features”, Proc. of IEEE Conference on Computer Vision and Pattern Recogntion, Miami, Florida, USA,p p.2310-2317, 2009.

J. Choi, Y.J. Yoo, J.Y. Choi, “Adaptive shadow estimator forr emoving shadow of moving object”, Computer Vision and ImageU nderstanding, No.114, pp.1017-1029, 2010.

L. Zhou, H. Kaiqi, T. Tieniu, “Cast shadow removal in a hierarchicalm anner using MRF”, IEEE Transactions on Circuits andS ystems for Video Technology, Vol.22, No.1, pp.56-66, 2012.

A. Amato, M.G. Mozerov, A.D. Bagdanov et al., “Accuratem oving cast shadow suppression based on local color constancyd etection”, IEEE Transaction on Image Processing, Vol.20,N o.10, pp.2954-2966, 2011.

W. Zhang, X.Z. Fang, X.K. Yang et al., “Moving cast shadowsd etection using ratio edge”, IEEE Transactions on Multimedia,Vol.6, No.9, pp.1202-1214, 2007.

A. Leone, C. Distante, “Shadow detection for moving objectsb ased on texture analysis”, Pattern Recognition, No.40,p p.1222-1233, 2007.

G. Yepeng, G. Weikang, “Automatic and robust shadows egmentation from two-dimensional scenes”, Acta ElectronicaS inica, Vol.34, No.4, pp.624-627, 2006. (in Chinese)

A. Prati, I. Mikic, M.M. Trivedi et al., “Detecting moving shadows:A lgorithms and evaluation”, IEEE Transactions on PatternA nalysis and Machine Intelligence, Vol.25, No.7, pp.918-9 23, 2003.

A. Sanin, C. Sanderson, B.C. Lovell, “Shadow detection: As urvey and comparative evaluation of recent methods”, PatternR ecognition, No.45, pp.1684-1695, 2012.

A. Sanin, C. Sanderson, B.C. Lovell, “Improved shadow removalf or robust person tracking in surveillance scenarios”, Proc. of2 0th International Conference on Pattern Recognition (ICPR),I stanbul, Turkey, pp.141-144, 2010.

B. Sun, S.T. Li, “Moving cast shadow detection of vehicle usingc ombined color models”, Proc. of Chinese Conference on Pattern Recognition (CCPR), Chongqing, China, pp.1-5, 2010.

J. Hsieh, W. Hu, C. Chang et al., “Shadow elimination for effectivem oving object detection by Gaussian shadow modeling”,I mage and Vision Computing, Vol.21, No.6, pp.505-516, 2003.

Relative Articles

Supplements(0)

Cited By

Proportional views