| Paper: | MA-P4.7 |
| Session: | Biometrics II: Human Activity, Gait, Gaze Analysis |
| Time: | Monday, September 17, 09:50 - 12:30 |
| Presentation: |
Poster
|
| Title: |
HIGH SPEED VISUAL SALIENCY COMPUTATION ON GPU |
| Authors: |
Bo Han; Peking University | | |
| | Bingfeng Zhou; Peking University | | |
| Abstract: |
Visual saliency analysis provides a power tool for many applications. In this paper, we propose a practical and high performance GPU-based visual saliency computational model. Moreover, several novel ideas are introduced for saliency computations, such as feature extraction as signed difference values in the LAB color space and the feature fusion method based on the information theory. Besides the programmable shaders, we fully exploit other computational resources on the GPU to accelerate the computations. Our experimental results demonstrate the effectiveness of our saliency maps and indicate an order of magnitude speedup over the CPU-based mplementation. |
