Remote sensing image target detection method based on dense connection and feature enhancement

Abstract

The invention relates to a remote sensing image target detection method based on dense connection and feature enhancement, and the method comprises the following steps: building a remote sensing image data set, and inputting the remote sensing image data set into a remote sensing image detection model for training, inputting a remote sensing image to be detected into a trained remote sensing image detection model to obtain a target detection result, wherein the remote sensing image detection model comprises a feature extraction unit, a feature enhancement unit, a feature pyramid unit and a predictor. An input image of the remote sensing image detection model is sequentially processed by the feature extraction unit, the feature enhancement unit, the feature pyramid unit and the predictor to obtain a target detection result. Compared with the prior art, the method has the advantages that the feature extraction capability of the network is improved, the resolution of the input image is increased, and low-latitude feature information is reserved while parameters are reduced so as to adapt to detection of a model on a remote sensing image target.

Description

technical field [0001] The invention relates to the field of remote sensing image detection, in particular to a remote sensing image target detection method based on dense connection and feature enhancement. Background technique [0002] With the rapid development of remote sensing technology and the emergence of high-resolution optical remote sensing images, remote sensing images have been widely valued at home and abroad because of their large observation area, wide range, strong continuity, good intuitive effect, and not limited by national boundaries and geographical conditions. , and target detection technology for remote sensing images has also become a hot research issue. The traditional remote sensing image detection method is to use artificial design features to extract feature information to train classifiers, obtain image regions in the form of sliding windows, and finally output prediction results through classifiers. This detection method not only consumes a lo...

AI Technical Summary

Problems solved by technology

The target detection algorithm based on deep learning has become the mainstream in the field of remote sensing image detection, but compared with the detection of natural images, remote sensing image detection still has a large room for improvement.

There are mainly the following problems in remote sensing image detection: 1) The resolution of remote sensing images is low, the information of the detected target is less, and the influence of background noise is greater, so that the general target detection algorithm cannot accurately extract the feature information in the original image, It causes classification and positioning difficulties, and the detection effect is poor; 2) The target scale in remote sensing images is generally small and densely distributed. Smaller targets are easily ignored in the network learning process, resulting in insufficient learning of small targets by the network , reducing the accuracy of detection

First of all, in terms of basic network, ResNet is not enough to deal with the problems of low resolution of remote sensing images and small target scale.

Second, existing techniques do not pay enough attention to shallow feature maps, resulting in a drop in detection accuracy

Images