Weak and small target intelligent detection and identification method

Abstract

The invention relates to an intelligent detection and recognition method for a weak and small target, belongs to the technical field of image recognition, and solves the problems of inaccurate recognition result and low recognition speed of an infrared weak and small target in the prior art. Comprising the following steps: extracting semantic information of multiple types of images, and constructing a conditional adversarial variational auto-encoder based on the semantic information; constructing an improved YOLOV3 model through a forward scale detection structure and an adjustment convolution structure; performing denoising processing on the received infrared image to obtain a denoised image, and adding the denoised image into a noiseless image set; inputting the noiseless image set into the constructed conditional adversarial variational auto-encoder to obtain an extended image set, and dividing the extended image set into a training set and a test set; based on the training set, training the improved YOLOV3 model to obtain a target recognition model; and inputting the test set into the target identification model to obtain an identification result of the target in the infrared image, including the position and the type of the target. And accurate and rapid identification of weak and small targets is realized.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an intelligent detection and recognition method for weak and small targets. Background technique [0002] With the continuous improvement of the speed of offensive weapons such as aircraft and missiles, it is required that the infrared optical system can search for incoming targets at a relatively long distance, so as to provide sufficient early warning time for our countermeasure system. However, when the target is far away, the system receives a weak signal in a complex background, which not only has a complex background, weak target signal, low signal-to-noise ratio, and small size, but also has no shape and texture information. How to realize the reliable detection and recognition of weak and small targets in complex backgrounds has become a hot topic widely studied at home and abroad. [0003] For the detection and recognition of weak and small targets in the infr...

AI Technical Summary

Problems solved by technology

[0005] In view of the above analysis, the embodiment of the present invention aims to provide an intelligent detection and recognition method for weak and small targets to solve the problems of inaccurate recognition results and slow recognition speed of existing infrared weak and small targets

Images