Aeroplane detection from high-resolution remotely sensed imagery using bag-of-visual-words based hough forests

摘要

This paper presents a rotation-invariant method for detecting aeroplanes from high-resolution remotely sensed images. First, a superpixel-based strategy is proposed to generate salient and distinctive feature regions. Second, a bag-of-visual-words representation is adopted to characterize spectral statistical features of feature regions. Third, a multi-scale rotation-invariant Hough forest with embedded scale factors and orientation information is trained to cast rotation-invariant votes for estimating aeroplane centroids. Quantitative evaluations on the images collected from Google Earth service show that a completeness, correctness, quality, and F-1-measure of 0.980, 0.973, 0.954, and 0.976, respectively, are obtained. Comparative studies with five existing methods also demonstrate the superior performance of the proposed method in accurately and correctly detecting arbitrarily-orientated and varying-sized aeroplanes.