Remote sensing target detection method based on boundary constraint CenterNet

Abstract

The invention provides a remote sensing target detection method based on boundary constraint CenterNet, which is used for solving the technical problems of relatively low detection precision and recall rate of dense small targets in the prior art. The method comprises the following implementation steps: obtaining a training sample set; the method comprises the following steps: constructing a boundary constraint CenterNet network; obtaining a prediction label and an embedded vector of the training sample set; calculating the loss of the boundary constraint CenterNet network; carrying out the training of a boundary constraint CenterNet network; and obtaining a target detection result based on the trained boundary constraint CenterNet network. Through performing maximum pooling in the constrained pooling area through the corner constraint pooling layer, the fine features around the target are extracted, the detection precision and recall rate of dense small targets are effectively improved, meanwhile, the boundary constraint label generated by the boundary constraint convolutional network is utilized to constrain the prediction box, a more accurate target prediction box is obtained, and the detection precision of the target is further improved.

Description

technical field [0001] The invention belongs to the technical field of machine vision and relates to an image target detection method, in particular to a boundary-constrained CenterNet-based target detection method, which can be used for target detection in optical remote sensing images. Background technique [0002] The target detection method is one of the core research contents in the field of machine vision. It is a technique for regressing and classifying all the targets of interest in the image by extracting and processing image features, and determining their positions and categories. It is widely used in Object Detection in Optical Remote Sensing Images. The technical indicators of target detection methods include detection accuracy, recall rate, and detection speed. In remote sensing images, affected by the image resolution, there are a large number of dense small targets. The small ratio in the whole image makes it difficult to accurately detect the existence of d...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, and propose a target detection method based on boundary constraints CenterNet, which is used to solve the technical problems of low detection accuracy and low recall rate of dense small targets in the prior art

Images