摘要：

为解决基于空间的视觉注意计算模型存在的注意目标不完整、容易转移到无意义区域等问题，提出一种结合空间显著性的基于物体的视觉注意计算模型。检测图像的边缘信息，根据空间视觉显著性度量结果，提取显著值高的封闭边缘，得到感知物体的轮廓。根据各感知物体的大小、位置和显著程度计算其注意度。注意焦点按照注意度递减的顺序在各感知物体之间进行转移。在多幅自然图像上进行实验验证，实验结果表明该模型具有和人类视觉特性相符合的注意效果。

关键词: 基于物体的视觉注意, 感知物体, 空间显著性, 边缘, 著图

Abstract:

To solve the problems that exitst in computational model of space-based visual attention, a computational model for object-based visual attention using spatial visual saliency is proposed in this paper. Edges are extracted from the input image and salient edges are obtained according to the edge saliency. Then these salient edges are organized to get the boundary of the perceptual objects. Attention value of each perceptual object is computed according to the area, location and saliency. Focus of attention is shifted among these perceptual objects in terms of the attention value. The proposed model is tested on many natural images. Experimental results show that the proposed model is valid and the attention results are consistent with human visual system.

Key words: object-based visual attention, perceptual object, spatial saliency, edge, saliency map

中图分类号: 

• TP391