Sparse Representation for No-Reference Quality Assessment of Satellite Stereo Images

Abstract

Different from natural image quality assessment methods, satellite stereo images have different requirements on quality in different application scenarios, which poses a huge challenge to establish a suitable objective evaluation model. In this paper, we focus on the quality evaluation of high resolution panchromatic (satellite stereo) images in specific application scenarios of building detection. First, we build a new satellite stereo image database (SSID), which consists of 400 distorted source satellite stereo images (SSIs) generated from the 20-source SSIs with two distortion types and 10-distortion strengths. We use detection accuracy scores to represent the quality of the SSIs, which is obtained through building detection, not subjective testing. We then propose an objective evaluation model based on joint dictionary learning. In the training phase, we bridge the features of the SSIs and the corresponding detection accuracy scores through joint dictionary learning. In the testing phase, we used sparse coding to get the quality of the testing image. The experimental results demonstrate the effectiveness of the proposed method.