Remote sensing image small target detection method based on feedback type multi-scale training

Abstract

The invention discloses a remote sensing image small target detection method based on feedback type multi-scale training, and the method comprises the steps of building a feedback type multi-scale convolution neural network which consists of a detection module and a feedback multi-scale training module, inputting original image data, and carrying out the training of the original image data in an end-to-end mode; enabling the feedback multi-scale training module to calculate the proportion value of the small target according to the loss of the current iteration process output by the detection module; comparing the calculated proportion value of the small target with a preset threshold value, and when the proportion value is smaller than the preset threshold value, using the spliced image data as the input of the next iteration, otherwise, using the original image data as the input; and obtaining a trained feedback type multi-scale convolutional neural network, inputting a to-be-detectedremote sensing image, and outputting an identification result. The detection capability of the small target in the remote sensing image is enhanced, the over-fitting phenomenon and the category imbalance phenomenon are inhibited, and the method has better effect and robustness for detecting the small target in the remote sensing image.

Description

technical field [0001] The invention relates to the technical field of remote sensing image target detection, in particular to remote sensing image target detection using a neural network model, and in particular to a remote sensing image small target detection method based on feedback multi-scale training. Background technique [0002] Object detection in remote sensing images has always been an important research direction in the field of computer vision and pattern recognition. Although many deep learning algorithms based on target detection have appeared in recent years, which have also brought powerful improvements to target detection, there are still many areas that need to be improved for small target detection in remote sensing images. [0003] Since complex backgrounds in remote sensing images may introduce more false positives, the model performance will deteriorate. Meanwhile, the detection performance of small objects (less than 32*32 pixels) in remote sensing i...

AI Technical Summary

Problems solved by technology

Although many deep learning algorithms based on target detection have appeared in recent years, which have also brought powerful improvements to target detection, there are still many areas for improvement for small target detection in remote sensing images.

[0003] Due to the complex background in remote sensing images may introduce more false positives, making the model performance worse

At the same time, the detection performance of small targets (less than 32*32 pixels) in remote sensing images is the least satisfactory

Images