High-resolution optical remote sensing image target detection method based on rotation invariant HOG feature

Abstract

The invention relates to a high-resolution optical remote sensing image target detection method based on a rotation invariant HOG feature. The method comprises steps of: firstly, selecting a target image and a background image to obtain an initial training sample set, rotating the initial training samples according to given rotation transformation, and merging un-rotated training sample set with the rotated training sample set to obtain a total training sample set; training a rotation invariant HOG feature extraction module and a target classifier by learning a three-layer fully connected network, wherein a conventional HOG feature is the input of the first layer, the second layer is used for computing the rotation invariant HOG feature, and the third layer is a softmax classifier. The method solves a problem, by learning rotation invariant HOG feature, that it is difficult for the conventional HOG feature to process remote sensing image target rotation changes, can realize remote sensing image target detection, and achieves high detection precision.

Description

technical field [0001] The invention belongs to the technical field of optical remote sensing image processing and analysis, and relates to a high-resolution optical remote sensing image target detection method based on rotation-invariant HOG features. Background technique [0002] With the continuous development of remote sensing technology, we can obtain more and more high-resolution optical remote sensing images. How to build a detection system that can quickly and accurately detect targets from high-resolution optical remote sensing images is a hot and difficult issue in the field of optical remote sensing image processing. Since object detection usually operates in feature space, it is particularly important to design an effective feature representation. [0003] At present, the Histogram of Oriented Gradients (HOG) feature has achieved great success in the field of natural image processing, but there are some problems in processing remote sensing images. Objects in n...

AI Technical Summary

Problems solved by technology

[0005] In order to avoid the shortcomings of the existing technology, the present invention proposes a high-resolution optical remote sensing image target detection method based on rotation-invariant HOG features, which effectively solves the problem that traditional HOG features are difficult to deal with target rotation changes, and has great advantages. High target detection accuracy

Images