Aerial photography vehicle detection method and detection system based on multi-scale small samples

Abstract

The invention discloses an aerial photography vehicle detection method based on a multi-scale small sample, and the method comprises the steps: firstly enlarging a collected data set through employing a data enhancement method, and enabling a deep learning model to extract universal features for targets of different sizes through employing a multi-scale adaptation algorithm; extracting shallow layer features by using small sample learning to generate weighted feature parameters with small sample information; and finally, combining and inputting the two parts of features into a subsequent deep learning model to obtain a detection frame, and extracting a final result by comprehensively using a Gaussian mixture model method, classification confidence and a soft intersection-to-union ratio (Soft-IoU) algorithm. According to the technical scheme, the technical problems of multiple scales, small samples and high density in aerial vehicle image detection are effectively solved.

Description

technical field [0001] The present invention relates to the technical field of computer vision, and more specifically, to an aerial vehicle detection method based on multi-scale small samples. Background technique [0002] In recent years, the target detection algorithm based on deep learning is a very popular research direction in the field of computer vision. At present, the target detection algorithm based on deep learning is mainly divided into one-stage regression-based detection algorithm and two-stage candidate frame-based detection algorithm. Both types of algorithms are based on deep learning network technology. By inputting the optical camera image to the network model, the position of the preset classification in the optical image is detected. Object detection is a pivotal science and technology in the field of artificial intelligence, which has received extensive attention from industry and academia. Artificial intelligence technology has achieved very good res...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the three major technical difficulties encountered in aerial vehicle image detection: multi-scale problems caused by aerial heights and angles; high-density single-target detection loss of many detection frames; aerial images cannot be trained using conventional data sets Small sample problem, the present invention proposes an aerial vehicle detection method based on multi-scale small samples

Images