A picture processing method, device, equipment and storage medium

Abstract

The invention discloses a picture processing method, device, equipment and storage medium. The method includes: acquiring an original picture and auxiliary information of the original picture. The original picture is input into the main path of the first visual task processing model to obtain the object feature map, and the auxiliary information is input into the branch path of the first visual task processing model to obtain the auxiliary feature map. The object feature map and the auxiliary feature map are fused into the main path of the first visual task processing model to obtain the response map of the original image. The implementation of the present invention involves the auxiliary information of the original picture in the process of generating the response graph of the original picture, because the auxiliary information of the original picture can provide strong prior knowledge, and the prior knowledge is helpful to solve the problems affecting the visual task processing model The prediction accuracy of the scene is complex and changeable and / or objects are difficult to recognize, which improves the prediction accuracy of the visual task processing model.

Description

technical field [0001] Embodiments of the present invention relate to computer vision technology, and in particular to an image processing method, device, equipment, and storage medium. Background technique [0002] Computer vision is a science that studies how to use machines to simulate human and biological visual processing functions. Specifically, it is to use a camera instead of the human eye to collect visual information, and use a computer instead of the brain to process and analyze the information, thereby completing tasks such as image classification, image segmentation, object detection, key point positioning, pose estimation, and face recognition. [0003] With the improvement of computer hardware performance and the emergence of large-scale image data, deep learning has been widely used in the field of computer vision. Deep learning originated from the research of artificial neural network and is an important branch of machine learning. It has formed a new end-t...

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the inventors found that there are at least the following problems in the prior art: although deep learning has been widely used in image classification, image segmentation, object detection, key point positioning, pose estimation and face recognition, etc., due to There are situations such as complex and changeable scenes and / or objects that are difficult to recognize, so that the visual task processing model generated based on deep learning training has low prediction accuracy when processing visual tasks

Images