doi: 10.7763/IJFCC.2014.V3.280
An Adaptive Cast Shadow Detection with Combined Texture and Color Models
- Communication & Information Security Lab, Shenzhen Graduate School, Peking University, China.
Abstract
Cast shadows of moving foreground objects cancause miss tracking problem in object detection and tracking,thus shadow detection is an important step used after a movingforeground object is detected. Most of current methods have asignificant trade-off between the shadow detection rate and theshadow discrimination rate. In this paper, an effective andadaptive method with combined texture and color models isproposed in order to achieve good shadow detection rate andshadow discrimination rate as well. Firstly, Scale InvariantLocal Ternary Pattern (SILTP) is used to select a candidateshadow region. Then HSV color model is employed to detect anew candidate shadow region by using maximum likelihoodestimation (MLE) to estimate the thresholds of HSV colormodel adaptively. Finally the two regions are combined bylogical operation and a new shadow region can be obtained.Our experimental results show that the proposed methodachieves a better performance in both shadow detection rateand discrimination rate compared to the other current methods.Moreover, the proposed method runs at 100 frames per secondand is suitable for the real-time detection and tracking.
Keywords
- Shadow detection
- SILTP
- HSV color space
- adaptive thresholds
How to Cite
Peiwen Liu and Yuesheng Zhu, "An Adaptive Cast Shadow Detection with Combined Texture and Color Models," International Journal of Future Computer and Communication, vol. 3, no. 2, pp. 113-118, 2014. https://doi.org/ 10.7763/IJFCC.2014.V3.280
Copyright & License
Copyright © 2014 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).




