Image detection method, device and computer-readable storage medium

Abstract

The embodiment of the present invention discloses an image detection method, device, and computer-readable storage medium; the embodiment of the present invention can input an image to be detected, and perform feature extraction on the image to be detected to obtain image feature information, and according to the image feature information Carry out target prediction on the image to be detected, generate the key point heat map and center point heat map of the target according to the prediction results, and predict the offset of the key point heat map, obtain the offset prediction map, and calculate the key point heat map According to the probability that each pixel in the target belongs to the target, multiple probability peak points are selected from each pixel according to the probability, and the target key points are determined from the multiple probability peak points based on the heat map of the central point, and the target key points are used to generate The target prediction area of ​​the image to be detected is determined based on the target prediction area and the offset prediction map, and an image marked with the target area is output; this solution can effectively improve the accuracy of image detection.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to an image detection method, device and computer-readable storage medium. Background technique [0002] With the rapid development of science and technology, object detection based on artificial intelligence plays an important role in computer-aided detection. Object detection is a popular direction in computer vision and digital image processing. It is widely used in robot navigation, intelligent video surveillance, industrial inspection, aerospace and many other fields. It has important practical significance to reduce the consumption of human capital through computer vision. Therefore, target detection has become a research hotspot in theory and application in recent years. It is an important branch of image processing and computer vision, and it is also the core part of intelligent monitoring system. Due to the widespread use of deep learning, target detection a...

AI Technical Summary

Problems solved by technology

However, the frame obtained in this way cannot accurately obtain the target area. For small targets, too much background noise will be introduced. For large targets, the frame may not completely cover the target area.

A very effective solution to this problem has not yet been proposed

Images