Three-dimensional object recognition method based on multi-view double-attention network

Abstract

The invention provides a three-dimensional object recognition method based on a multi-view double-attention network, and the method comprises the following steps: 1, projecting an original three-dimensional object from n views to a two-dimensional plane, rendering the original three-dimensional object to obtain n views, and carrying out the feature extraction of the n views through a basic CNN model, and correspondingly obtaining n visual features; 2, inputting the n visual features into a view space attention module for processing to obtain a visual space descriptor; 3, inputting the n visual features into a view channel attention module for processing to obtain visual channel descriptors; and 4, combining the visual space descriptor and the visual channel descriptor to obtain a three-dimensional shape descriptor, and inputting the three-dimensional shape descriptor into a full-connection network to complete object identification so as to obtain a prediction identification classification result of the original three-dimensional object.

Description

technical field [0001] The invention relates to a three-dimensional object recognition method, in particular to a three-dimensional object recognition method based on a multi-view double attention network. Background technique [0002] In recent years, with the development of 3D imaging sensors and 3D reconstruction technology, people can easily capture a large amount of 3D object structure information from daily life. The recognition of 3D objects has become one of the most fundamental problems in the fields of computer vision and artificial intelligence. With the rapid development of large-scale 3D databases and deep learning, various methods have been proposed for 3D object recognition. 3D object recognition research is mainly divided into two categories according to different methods: early traditional methods and recent deep learning methods. Early 3D object recognition generally uses artificially designed 3D data description features and machine learning methods for ...

AI Technical Summary

Problems solved by technology

However, compared with the traditional two-dimensional image classification, there is still a lot of room for improvement in the accuracy of multi-view 3D object recognition and classification, which needs further in-depth research.

Images