Cast Shadow Removal in a Real-Time Environment

Abstract:

The cast shadows on the background of the object will distinctly affect the recognition of the foreground objects. Due to the limitation of shadow removal methods utilizing texture, a novel algorithm based on Gaussian Mixture Model (GMM) and HSV color space is proposed. Firstly, moving regions are detected using GMM. Secondly, we make two pre-classifiers accurate and adaptive to the change of shadow by using the features of shadow in RGB and HSV color space. Experimental results show that the proposed method is efficient and robust.

• Periodical: Applied Mechanics and Materials (Volumes 275-277)
• Pages: 2548-2554
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.275-277.2548
• Online since: January 2013
• Authors: Hong Ying Zhang, Hong Li, Yi Gang Sun
• Keywords: Gaussian Mixture Model, HSV Color Space, RGB Color Space, Shadow Removal

References

[1] Qin Rui, Liao Shengcai, Lei Zhen, and Stan Z. Li: Moving Cast Shadow Removal Based on Local Descriptors. Proceedings of International Conference on Pattern Recognition, 2010, pp.1377-1380.

DOI: 10.1109/icpr.2010.340

[2] Yang Wang: Real-time moving vehicle detection with cast shadow removal in video based on conditional random field. IEEE Transactions on circuit and systems for video technology, Vol. 19, NO. 3, Mar. 2009, pp.437-441.

DOI: 10.1109/tcsvt.2009.2013500

[3] S. Lakshmi and V. Sankaranarayanan: Cast shadow detection and removal in a real-time environment. Trendz in information sciences & computing, Dec. 2010, pp.245-247.

DOI: 10.1109/tisc.2010.5714648

[4] Shih-Chieh Wang, Te-Feng Su, and Shang-Hong Lai: Detecting moving objects from dynamic background with shadow removal. IEEE International Conference on Acoustics, Speech and Signal Processing, May. 2011, pp.925-928.

DOI: 10.1109/icassp.2011.5946556

[5] Yun-Ho Ko, Jong-Won Park, and Hyun-Soo Kang: Robust shadow removal algorithm for accurate object detection based on background subtraction method. IEEE International Conference on Consumer Electronics, Jan. 2012, pp.143-144.

DOI: 10.1109/icce.2012.6161780

[6] Choi J M, YooY J, and Choi J Y: Adaptive Shadow Estimator for Removing Shadow of Moving Object. Computer Vision and Image Understanding, Vol. 114, NO. 9, 2010, pp.1017-1029.

DOI: 10.1016/j.cviu.2010.06.003

[7] Jaime Gallego and Montse Pardas: Enhanced Bayesian Foreground Segmentation using Brightness and Color Distortion Region-Based Model for Shadow Removal. Proceeding of International Conference on Image Processing, 2010, pp.3449-3452.

DOI: 10.1109/icip.2010.5653897

[8] Sanin Andres, Sanderson Conrad, and Lovell Brian C: Improved Shadow Removal for Robust Person Tracking in Surveillance Scenarios. Proceeding of International Conference on Pattern Recognition, 2010, pp.141-144.

DOI: 10.1109/icpr.2010.43

[9] Liu Zhou, Huang Kaiqi, and Tan Tieniu: Cast Shadow Removal in a Hierarchical Manner Using MRF. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 22, NO. 1, 2012, pp.56-66.

DOI: 10.1109/tcsvt.2011.2158335

[10] C. Stauffer and W. Grimson: Adaptive Background Mixture Models for Real-time Tracking. Proceedings of IEEE conference on Computer Vision and Pattern Recognition, 1999, pp.246-252.

DOI: 10.1109/cvpr.1999.784637

[11] Prati A, Mikic I, Trivedi M M, and Cucchiara R: Detecting moving shadows: Algorithms and evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, NO. 7, 2003, pp.918-923.

DOI: 10.1109/tpami.2003.1206520