Target detection method and system based on target detection model

Abstract

The invention provides a target detection method and system based on a target detection model; the method comprises the following steps: obtaining an image data set, and dividing the image data set into a training set A and a verification set B; establishing a target detection model framework, wherein the target detection model framework adopts a YOLOv4 model configured with a Fish activation function in a CSPDarknet53 network module; and training the target detection model framework through the training set A, and testing the target detection model framework through the verification set B to generate a target detection model. Under the same condition, the training time is saved by 2.26% by using the Fish activation function compared with the training time by using the Mish activation function, the total loss is reduced by 4.32%, the Val loss is reduced by 6.37%, and the detection confidence is improved on the actual detection result.

Description

technical field [0001] The present invention relates to computer vision, in particular to a target detection method and system based on a target detection model. Background technique [0002] Object detection is an important branch of computer vision and has a wide range of applications. It can be simply regarded as a combination of image classification and regression positioning. Usually, an image is given, and the object of interest in the image is framed by a rectangular frame using a target detection algorithm, and the classification result of the object in the frame is given. Therefore, it can be seen that the target detection task is more complicated than the image classification task. [0003] With the rapid development of deep learning in recent years, a large number of convolutional neural networks have been used in target detection algorithms. For example, the face recognition verification at the entrance ticket gate of the railway station mainly uses a two-stage...

AI Technical Summary

Problems solved by technology

[0005] However, due to the long training time of the target detection model and the high requirements for equipment, it is difficult for users who do not have sufficient hardware resources to use it.

Images