Multi-scale target detection method based on self-attention mechanism

Abstract

The invention discloses a multi-scale target detection method based on a self-attention mechanism. By adopting a bottom-to-top and top-to-bottom multi-scale feature fusion mode based on a self-attention feature selection module, low-level features and high-level features of a target can be combined, the representation capability of a feature map and the capability of capturing context informationare enhanced, and the stability and robustness of a target detection stage are improved. Moreover, the self-attention module is used for re-calibrating the features, the calculated amount is smaller,the detection precision and speed are both considered, and the method has important significance for solving the detection problems of dense objects, small targets, shielded targets and the like in target detection.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a multi-scale target detection method based on a self-attention mechanism. Background technique [0002] Target detection is a basic problem in the field of computer vision. The purpose is to find objects of interest in images or videos, and determine their category, location and size. There are important researches in the fields of pedestrian detection, safety inspection and unmanned driving. and application value. With the rapid development of deep convolutional networks, the accuracy of object detection algorithms continues to improve. The current mainstream target detection algorithms are mainly divided into two categories: the detection algorithm based on the region proposal (Region Proposal) and the detection algorithm based on the bounding box regression. [0003] The idea of ​​the target detection algorithm based on candidate regions is to first use...

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects, the present invention provides a multi-scale target detection method based on the self-attention mechanism. The multi-scale feature fusion based on the self-attention mechanism in the present invention can make full use of the context information in the multi-scale features and improve the accuracy of the feature map. The ability to express and capture context information has higher detection accuracy, which solves the problems of high missed detection rate and low detection accuracy in dense small target scenes

Images