Small object detection method based on sensing generation adversarial network

Abstract

The invention provides a small object detection method based on a sensing generation adversarial network. The method includes the following steps: generating an adversarial network, a condition generation network architecture and a verification network architecture. The process is composed of two sub-networks, namely a generator network and a sensing verification network. The generator network converts the expression of a small object to the super-resolution expression of an original object which is similar with a big object. Residual expression between the big object and the small object is generated through residual learning. The verification network inputs the super-resolution expression, and transmits the input to an adversarial branch and a sensing branch. The generator network is excited to generate super-resolution expression which has high detection precision. According to the invention, the method herein, by reducing the expression difference between small object and big object, improves small object detection, provides more comprehensive monitoring, is conductive to detection, and realizes successful detection of traffic signs and pedestrians.

Description

technical field [0001] The invention relates to the field of target detection, in particular to a small target detection method based on perceptual generative confrontation network. Background technique [0002] With the development of computer technology and the wide application of computer vision principles, the use of computer image processing technology to conduct real-time tracking of small targets is becoming more and more popular. Dynamic real-time tracking and positioning of small targets is widely used in intelligent transportation systems, intelligent monitoring systems, military It has wide application value in target detection and surgical instrument positioning in medical navigation surgery. For example, it is used in traffic sign detection, pedestrian detection, and vehicle detection in traffic systems; it is used in reconnaissance, guidance, and alarm systems in the military field. Generative confrontation network has become more and more popular in recent ye...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the time-consuming problem of training and testing, the purpose of the present invention is to provide a small target detection method based on perceptual generative confrontation network, which consists of two sub-networks of generator network and perceptual discrimination network. The generator network represents a small target Transform into a super-resolution representation of the original target similar to the large target, and generate a residual representation between the large target and the small target through residual learning. The discriminator network takes the generated super-resolution representation as input and passes it to the confrontation branch and perception branch, which motivates the generator network to generate super-resolution representations with high detection accuracy

Images