Adaptive Adjustment Object Detection Algorithm under Multiple Mechanisms Based on GAN

Zemin Qiu,Feng Wang,Zhihong Pan,Chenxi Huang

doi:10.1155/2021/5875320

Abstract

Target tracking is prone to problems such as target loss and identity jump when the target is occluded and the attitude is changed. In order to solve this phenomenon, this paper proposes the adaptive adjustment object detection algorithm under multiple mechanisms based on GAN. This algorithm introduces a gradient penalty mechanism to the discriminator and uses the relative discriminator structure to reconstruct the discriminator, so as to improve the discriminatory ability of the discriminator. Then, through the feedback mechanism, the obtained data is fed back to the generator network in time, and the genetic mechanism is used to speed up the positioning of the key areas of the image. Experimental results show that compared with other existing algorithms, this algorithm can effectively locate and distinguish under different environments. And, the target still maintains a high resolution. When the target is occluded, it can effectively avoid the phenomenon of target loss and identity jump.

Highlights

Target detection is one of the important research directions in the field of computer vision
E other is one-stage algorithms such as Yolo and SSD [3,4,5], which use the convolutional neural network (CNN) to extract image features and establish detection models to classify and locate targets
The target in the image often has problems such as being occluded and deformed, making the extracted target feature insignificant or lacking part of the feature information, leading to classification errors and tracking failures, and prone to the problem of identity jump. erefore, we are comparing the advantages and disadvantages of existing algorithms; this paper adopts the generative confrontation network in the second type of algorithm. is model is a unique network structure that captures potential data distribution. e true and false confrontation error design based on game theory construction makes it possible to deal with different types of tasks [6, 7]

Summary

Introduction

Target detection is one of the important research directions in the field of computer vision. E other is one-stage algorithms such as Yolo and SSD [3,4,5], which use the convolutional neural network (CNN) to extract image features and establish detection models to classify and locate targets. By observing the structure of the generative confrontation network, GAN is mainly composed of two parts: generation network (G) and discriminant network (D) It uses a competing mechanism [11,12,13]; the purpose is to enable the generator to generate data similar to the real data distribution, which made the GAN achieve the effect of being fake. GAN can generate samples that are similar to the real data distribution, but it has problems such as difficulty in training, difficulty in network convergence, and mode collapse

The Discriminator Network Introduces a Gradient Penalty Mechanism

Generating Network Scoring Mechanism

Evaluation

Findings

14 Traditional algorithm based on YOLO 8