Target object detection method and device, computer equipment and storage medium

Abstract

The invention relates to a target object detection method and device, computer equipment and a storage medium. The method comprises the steps of performing feature extraction on a to-be-detected imageto obtain initial image features; performing feature enhancement processing on the initial image feature to obtain a first image feature; performing first-level prediction processing for a target object according to the first image feature to obtain an initial prediction box for identifying the target object; performing feature splicing on the initial image features and the first image features,and performing feature enhancement processing on the spliced image features to obtain second image features; and performing second-level prediction processing for the target object according to the second image feature and the initial prediction box so as to adjust the initial prediction box, and identifying the target object in the to-be-detected image according to the adjusted prediction box. Byadopting the method, the detection accuracy of the target object can be effectively improved.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a target object detection method, device, computer equipment and storage medium. Background technique [0002] With the rapid development of computer technology and the wide application of computer vision principles, the use of computer image processing technology to detect objects is becoming more and more popular, especially in the applications of face recognition and human detection. For images of complex scenes, it is very challenging to accurately locate the target. For example, due to the small size of the face itself and the large changes in the pose of the face, it is difficult to accurately locate the face target in complex scenes. [0003] The current target detection methods usually use preset frame classification and detection frame regression prediction. For example, first extract features from the image, and then perform target detection at ...

AI Technical Summary

Problems solved by technology

However, the scale of the detection target in the actual scene may be relatively small. At present, the classification confidence of the detection frame predicted by this method is not high, resulting in a decrease in the accuracy of target positioning, and the detection accuracy of small-scale targets is low.

Images