Unmanned aerial vehicle image target detection method and system based on deep denoising autocoder

Abstract

The invention provides an unmanned aerial vehicle image target detection method and system based on a deep denoising autocoder. The method comprises: firstly, extracting radial gradient features of anunmanned aerial vehicle image; sending the extracted gradient features to a deep denoising autocoder; by the autocoder, adding random white Gaussian noise to the extracted radial gradient features; through multi-layer coding, generating high-level features of an unmanned aerial vehicle image with strong representation capability, using a back propagation algorithm to minimize a reconstruction error of the deep denoising autocoder solving model parameters, using a softmax classifier to classify the high-level features, and obtaining a high-precision and high-robustness target detection result.

Description

technical field [0001] The invention belongs to the field of unmanned aerial vehicle image target detection, in particular to a method and system for unmanned aerial vehicle image target detection based on a depth denoising automatic encoder. Background technique [0002] UAVs have the characteristics of strong mobility, high efficiency, low cost, and reusability. The demand for industrial and commercial applications is becoming stronger and stronger. UAVs are equipped with high-precision cameras to carry out aerial inspections of ground scene areas. Obtain the image data of the scene covered by the inspection for target detection, so as to obtain accurate and real-time image analysis information of the detection area, which can be applied in traffic flow analysis, urban architectural planning, transmission line inspection, oil pipeline inspection, border inspection and other fields . [0003] Compared with traditional image target detection and analysis, during the shootin...

AI Technical Summary

Problems solved by technology

[0003] Compared with traditional image target detection and analysis, during the shooting process of UAV images, the images affected by the vibration of the body often have noise interference. In addition, the ground background is often complex, and the appearance of similar targets is also affected by the illumination and imaging angle. There may be various differences, and these unfavorable factors make object detection difficult, making efficient, robust and accurate object detection in UAV imagery remains a challenging problem

When the UAV images the same area twice before and after, not only may there be a large difference in imaging angle of view between the two images, but also there may be a large overall or partial difference between the images due to different imaging conditions such as weather and light. difference in brightness

Images