关键词: 信息处理技术, 遥感图像, 视觉显著性, 特征, 目标检测

Abstract: A hierarchical object detection method based on vision saliency was proposed for automatic remote sensing image interpretation. A bias function for each single feature was defined, and a compound bias function for synthesis of vision saliency image computed by each function was also defined. For the low resolution original image, each bias function was used to generate a vision saliency image corresponding to a certain feature. Then synthesized vision saliency image was computed using the compound bias function from these vision saliency images. Furthermore, the area where the compound bias function was maximum was located as the most promising object area. These three steps were repeated over the located areas in higher resolution level image until the objects were found or assuredly absent. Experiments show that this method can skip over the region where there is no object as early as possible, get better detection result compared with traditional methods, and cost much less computational expenditure, which proves to be a good basis for later object recognition.

Key words: information processing technology, remote sensing image, vision saliency, feature, object detection