Aerial image classification by learning quality-aware spatial pyramid model

Abstract

Recognizing aerial image categories is of great significance in computer vision, which is widely utilized in geological analysis, agricultural production and urban planning. However, conventional approaches cannot explicitly exploit spatial information of aerial images, i.e., spatial relations among different components. To solve this problem, we propose a novel aerial image classification algorithm based on the well-known spatial pyramid model, where saliency maps are utilized for discriminative regions selection, and a visual quality model is leveraged to alleviate the impact of image distortion. More specifically, we first partition each aerial image into several fine subregions, each of which is represented using the computed spatial pyramid-based local features. Afterwards, each image is characterized by the most representative features engineered by the saliency map and quality assessment module. Subsequently, a regularized topic model based probabilistic learning is designed for recognizing different types of aerial images. Extensive experiments have demonstrated the effectiveness of our proposed method.