Use of shadows for extracting buildings in aerial images
Computer Vision, Graphics, and Image Processing
Detecting Moving Shadows: Algorithms and Evaluation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Moving Cast Shadow Elimination for Robust Vehicle Extraction Based on 2D Joint Vehicle/Shadow Models
AVSS '03 Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance
A Shadow Elimination Method for Vehicle Analysis
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Cast shadow segmentation using invariant color features
Computer Vision and Image Understanding
Moving Cast Shadow Detection from a Gaussian Mixture Shadow Model
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
A Texture-Based Method for Modeling the Background and Detecting Moving Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning and Removing Cast Shadows through a Multidistribution Approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
Study on color space selection for detecting cast shadows in video surveillance: Articles
International Journal of Imaging Systems and Technology - Special Issue on Applied Color Image Processing
Moving Cast Shadows Detection Using Ratio Edge
IEEE Transactions on Multimedia
Detecting moving objects, ghosts, and shadows in video streams
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
A novel algorithm is developed to detect moving objects and remove cast shadows by exploiting textural and spatial-temporal features. Multi-scale wavelet transformation is used to segment moving objects based on spatial property. Textural and spectral features color ratio differences between two adjacent pixels in four different directions are used to remove cast shadows. RGB color space is selected instead of introducing complex color models to segment moving objects and eliminate shadows. The proposal requires much less efforts compared with currently available methods. It does not require any complex supervised training phase, and does not require manual calibration or makes any hypothesis. Experiments have highlighted that the proposal is robust and efficient to segment moving objects and suppress shadow by comparisons.