Comparative Study : The Evaluation of Shadow Detection Methods

Shadow detection is critical for robust and reliable video surveillance systems. In the presence of shadow, the performance of the video surveillance system degrades. If objects are merged together due to shadow then tracking and counting cannot be performed accurately. Many shadow detection methods have been developed for indoor and outdoor environments with different illumination conditions. Mainly shadow detection methods can be partitioned in three categories. This work performs comparative study for three representative works of shadow detection methods each one selected from different category: the first one based on intensity information, the second one based on photometric invariants information, and the last one uses color and statistical information to detect shadow. In this paper, we discuss these shadow detection approaches and compare them critically. The comparison of three methods is performed using different performance metrics. From experiments, the method based on photometric invariants information showed superior performance comparing to other two methods. It combines color and texture features with spatial and temporal consistencies proving it excellent features for shadow detection.

[1]  Zhenjiang Miao,et al.  Fast Background Subtraction and Shadow Elimination Using Improved Gaussian Mixture Model , 2007, 2007 IEEE International Workshop on Haptic, Audio and Visual Environments and Games.

[2]  Mau-Tsuen Yang,et al.  Shadow Removal for Foreground Segmentation , 2006, PSIVT.

[3]  Soraia Raupp Musse,et al.  A Background Subtraction Model Adapted to Illumination Changes , 2006, 2006 International Conference on Image Processing.

[4]  Yang Wang,et al.  A probabilistic approach for foreground and shadow segmentation in monocular image sequences , 2005, Pattern Recognit..

[5]  Reinhard Koch,et al.  A Color Similarity Measure for Robust Shadow Removal in Real Time , 2003, VMV.

[6]  Touradj Ebrahimi,et al.  Shadow identification and classification using invariant color models , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[7]  Wei Zhang,et al.  Moving cast shadows detection based on ratio edge , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[8]  Soraia Raupp Musse,et al.  Background Subtraction and Shadow Detection in Grayscale Video Sequences , 2005, XVIII Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI'05).

[9]  Jörn Ostermann,et al.  Detection of Moving Cast Shadows for Object Segmentation , 1999, IEEE Trans. Multim..

[10]  Xuelong Li,et al.  Cast shadow detection in video segmentation , 2005, Pattern Recognit. Lett..

[11]  Tieniu Tan,et al.  Cast Shadow Removal Combining Local and Global Features , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Rita Cucchiara,et al.  Detecting Moving Objects, Ghosts, and Shadows in Video Streams , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Max Lu,et al.  Robust and efficient foreground analysis for real-time video surveillance , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Tim J. Ellis,et al.  Image Difference Threshold Strategies and Shadow Detection , 1995, BMVC.

[15]  Touradj Ebrahimi,et al.  Cast shadow segmentation using invariant color features , 2004, Comput. Vis. Image Underst..

[16]  Nicolas Martel-Brisson,et al.  Moving cast shadow detection from a Gaussian mixture shadow model , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).