High Speed Visual Saliency Computation on GPU

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. Several novel ideas are introduced for saliency computations, such as the feature extraction as signed difference values in the lab color space and the feature fusion based on the information theory. For our implementation on the GPU, 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 implementation.