Target detection method, device, equipment and readable storage medium

Abstract

Embodiments of the invention provide a target detection method, a device, equipment and a readable storage medium. The method comprises the steps of obtaining center point data of a to-be-detected target in a pixel coordinate system and point cloud data of the to-be-detected target in a camera coordinate system; obtaining conversion data of the central point data in a camera coordinate system; determining a point set associated with the center point data under a camera coordinate system according to the conversion data and the center point data; generating a corresponding three-dimensional anchor frame by taking each point in the point set as a central point; and performing target detection on the point cloud data falling in the three-dimensional anchor point frame. According to the methodprovided by the embodiment of the invention, the generation of the three-dimensional anchor point boxes only in part of the camera space is limited, so that the number of the generated three-dimensional anchor point boxes is reduced, the matching calculation amount of the later anchor point boxes and the real target detection box is reduced, the matching speed is increased, and the target detection efficiency is improved.

Description

technical field [0001] The embodiments of the present invention relate to the field of target detection, and in particular, to a method, device, equipment and readable storage medium for target detection. Background technique [0002] With the development of computer technology and the wide application of computer vision principles, the research on target detection using computer image processing technology is becoming more and more popular. Target detection is used in intelligent transportation systems, intelligent monitoring systems, military target detection, medical care and other fields. It has wide application value. [0003] The target detection methods in the prior art all adopt the means of pre-generated anchor frame, compare the anchor frame with the real target detection frame, label each anchor frame, and divide the anchor frame into positive class and Negative class, then input the feature map of the target to be detected into the classification model, and then...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a method, device, device, and readable storage medium for object detection, which are used to solve the problem that the number of anchor frames generated in the three-dimensional space in the existing object detection method is huge, causing the later anchor frames to be inconsistent with the real object. The matching calculation of the detection frame is huge, the matching speed is not fast, and the target detection efficiency is not high.

Images