Target detection method and device based on attention mechanism deep learning network

Abstract

The invention provides a target detection method based on an attention mechanism deep learning network. The method is characterized by comprising: extracting a feature map of an image to be detected through a target detection model containing an attention mechanism module, detecting the position and the category of a target from the feature map, and the attention mechanism module comprising at least one attention module M1 used for generating an attention weight matrix with the same size according to the feature map and acting on the feature map; at least one attention receptive field module M2 used for carrying out feature extraction on the feature map; and at least one attention feature fusion module M3 used for fusing the features of different levels of the network. According to the target detection method, high detection speed is ensured on the basis of high detection accuracy, and meanwhile, the model is simple in structure and small in calculated amount.

Description

technical field [0001] The invention belongs to the technical field of computer vision and artificial intelligence, and relates to a method and device for detecting a specific target in a complex life scene, in particular to a target detection method and device based on an attention mechanism deep learning network. Background technique [0002] In the current field of computer vision, deep learning has been developed rapidly. The model method based on convolutional neural network is widely used in various fields of computer vision, such as target detection, image classification, semantic segmentation, instance segmentation and other tasks. Among them, target detection is a very important and challenging task. The target detection task can be divided into two key subtasks: target classification and target localization. [0003] Target classification refers to: the target object contained in a picture, the target object is one or more, and its use method is used to correctly ...

AI Technical Summary

Problems solved by technology

For the one-stage model, its advantage is that the detection speed is fast, but the accuracy rate needs to be improved; on the contrary, for the two-stage model, its advantage is that the accuracy rate is high, but the detection speed is very slow

[0006] In the one-stage model, in order to improve the accuracy of target detection, the most commonly used method is to increase the complexity of the neural network model

However, the problems brought about by increasing the complexity of the neural network are also very large. On the one hand, it limits its speed advantage to a certain extent; high

Images