Method for constructing image blurring degree evaluation model

Abstract

The invention provides a construction method of an image blurring degree evaluation model. The construction method of the image blurring degree evaluation model comprises the following steps: adding a detection frame for an original image by using a detection network; cutting a target image from the original image according to the detection frame; processing the target image into a standard image with a preset size; adding a fuzzy degree label to the standard image according to a Laplacian operator to obtain a sample image; feeding the sample image into the initial learning network to obtain a target learning network; and combining the target learning network and the Laplacian algorithm module to obtain an image blur degree evaluation model. The invention further provides an image fuzzy degree evaluation model, an image fuzzy degree evaluation method, a computer readable storage medium and intelligent driving equipment. The image blurring degree evaluation model is obtained through the method, the model is used for judging the blurring degree of the image obtained in the vehicle-mounted auxiliary driving system, and the accurate blurring degree of the target in the image is obtained.

Description

technical field [0001] The present invention relates to the field of automatic driving, in particular to a method for constructing an image blur degree evaluation model, an image blur degree evaluation model, an image blur degree evaluation method, a computer-readable storage medium, and an intelligent driving device. Background technique [0002] In the vehicle assisted driving system, we need to accurately judge the position and motion state of various targets such as vehicles and pedestrians on the road ahead. According to the conventional process, we first need to detect the targets on the road through the detection network, and then analyze the refined attributes of the detected targets, including the position information of the target, the state information of the target, the unique attributes of the target, and so on. Although the neural network has a high accuracy in judging the target category, location and other information, factors such as rain and snow, strong ba...

AI Technical Summary

Problems solved by technology

Image blurring reduces the clarity of the image, seriously affects the image quality, and leads to difficulties or even failure in image analysis and processing. Therefore, it is necessary to use an effective blur evaluation method to control the use of blurred images, thereby improving the overall performance of the system.

Images