Remote sensing image target detection method based on new frame regression loss function

Abstract

The invention provides a remote sensing image target detection method based on a new frame regression loss function. The method comprises the following steps: training a candidate region generation network through employing a high-resolution remote sensing image as a training sample, and enabling the frame regression loss function of the candidate region generation network to employ the new loss function; obtaining a candidate target frame as a target initial position training region detection network through the trained candidate region generation network, wherein a new frame regression lossfunction is adopted as a frame regression loss function of the region detection network; alternately training a candidate region generation network and a region detection network; and sharing backbonenetworks of the candidate region generation network and the region detection network, combining the trained candidate region generation network and the region detection network to construct a detection model, and obtaining the position and the category of the interested target of the to-be-detected high-resolution remote sensing image. By improving the frame regression loss function of target detection, the target detection precision of the high-resolution remote sensing image can be effectively improved.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a remote sensing image target detection method based on a new frame regression loss function. Background technique [0002] Target detection in high-resolution remote sensing images is one of the most important tasks in the field of optical remote sensing image processing. It is dedicated to locating and identifying high-value ground objects in high-resolution remote sensing images. With the implementation of the high-score major project (one of the 16 major projects in the national science and technology development medium and long-term plan), my country's remote sensing data acquisition technology has developed rapidly, and the mining of remote sensing big data has become a key link in the high-score major project. High-resolution remote sensing image target detection is one of the key technologies of remote sensing big data mining, and also one of the core issues in appli...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the technical problem that the loss function of the existing high-resolution remote sensing image target detection method cannot directly optimize the evaluation index, the present invention proposes a remote sensing image target detection method based on a new bounding box regression loss function, which can combine the loss function and the evaluation index Directly establish a connection, and can adaptively change the gradient during the optimization process, thereby further improving the accuracy of target detection in high-resolution remote sensing images

Images