Method and device for identifying camouflage person by carrying multispectral camera on unmanned aerial vehicle, and medium

Abstract

The embodiment of the invention discloses a method and device for recognizing a camouflage person through a multi-spectral camera carried by an unmanned aerial vehicle, and a medium. The method comprises the following steps: preprocessing a DN value original image collected by a multispectral camera to complete band registration and radiation correction, and obtaining a preprocessed reflectivity image corresponding to the DN value original image; generating an original feature set based on the preprocessed reflectivity image; screening from the original feature set through cross validation based on a Relief algorithm to obtain an optimal feature subset; based on a preset data set, training the candidate supervised classifier models to obtain classification evaluation results corresponding to the candidate supervised classifier models, and selecting an optimal model from all the candidate supervised classifier models; classifying the preprocessed reflectivity image through an optimal model to obtain a predicted binary image; and identifying a camouflage person target from the prediction binary image, and determining the position of the identified target according to the position information in the DN value original image.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of battlefield search, and in particular to a method, device and medium for identifying disguised personnel by a drone equipped with a multispectral camera. Background technique [0002] At present, the search and rescue technology for the wounded in the battlefield environment usually uses UAVs equipped with RGB high-definition cameras combined with thermal infrared imagers for low-altitude search. The detection target, the camouflaged target has no obvious features and edges, so it is difficult to find the wounded only by relying on airborne vision; in addition, the thermal infrared imaging technology has a small field of view and poor resolution, which is affected by the flying height of the drone. In addition, the low precision of mixed pixels has a great influence on the ambient temperature. Usually, there are many heat sources on the battlefield and the ambient temperature is high...

AI Technical Summary

Problems solved by technology

[0002] At present, the search and rescue technology for the wounded in the battlefield environment usually uses UAVs equipped with RGB high-definition cameras combined with thermal infrared imagers for low-altitude search. The detection target, the camouflaged target has no obvious features and edges, so it is difficult to find the wounded only by relying on airborne vision; in addition, the thermal infrared imaging technology has a small field of view and poor resolution, which is affected by the flying height of the drone. In addition, the low precision of the mixed pixel environment has a great influence on the temperature. Usually, there are many heat sources on the battlefield and the ambient temperature is higher than 30°C. It is easy to cause false detection and cannot accurately detect the thermal signal of the human body.

Images