Image detection method and device, electronic equipment and storage medium

Abstract

The invention discloses an image detection method and device, electronic equipment and a storage medium, which can be applied to various scenes such as cloud technology, artificial intelligence, intelligent traffic, auxiliary driving and the like, and the method comprises the following steps: determining a first vector sequence according to an image block sequence corresponding to a to-be-processed image; sequentially carrying out attention coding on the first vector sequence based on a plurality of attention coding layers to obtain a first feature map; obtaining a first attention distribution diagram based on the target attention features corresponding to the classification embedding vectors; performing negation on the first attention distribution map and then fusing the negated first attention distribution map with the first feature map to obtain a second feature map; and performing target object detection according to the first feature map, the first attention distribution map and the second feature map to obtain category information and position information of a target object in the to-be-processed image. The accuracy of the position information in the detection result is improved.

Description

technical field [0001] The present invention relates to the field of computer technology, and in particular, to an image detection method, an apparatus, an electronic device and a storage medium. Background technique [0002] Target detection can give the location information and category information of the target of interest in the image, and it is the pre-basic task of subsequent computer vision tasks. [0003] In the related art, the method of convolutional neural network CNN (Convolutional Neural Networks) is usually used to detect the target of the image, that is, the deep-level semantic feature map of the image is first extracted by the convolutional neural network, and the deep-level semantic feature map is globally pooled. After the transformation, the local information with category discrimination is integrated through the fully connected layer and given to the classification layer for classification, and the positioning frame is determined in combination with the c...

AI Technical Summary

Problems solved by technology

Since the convolutional neural network only extracts local features, the related technology only focuses on the most discriminative features of the target, resulting in poor positioning accuracy of target detection, and the position information in the detection results is not accurate enough.

Images