An Image Matching Method for Matching Matrix in Monocular Vision Positioning of Unmanned Vehicles

Abstract

The invention relates to an image matching method for a matching matrix in monocular vision positioning of an unmanned vehicle. The method comprises the following steps: 1) performing global feature description on all input test images and positioning map images through a deep convolutional neural network DCNN , extracting the third convolutional layer as the feature vector; 2) using the principal component analysis method to reduce the dimensionality of all the feature vectors; 3) constructing a matching matrix according to the feature vectors after the dimensionality reduction of the test image and the positioning map image, that is, the matching image; 4 ) Perform OTSU binarization processing on the matching image to obtain the processed binarized image; 5) After performing morphological processing on the binarized image, perform straight line fitting on the image; 6) Corresponding on the fitted straight line The test image and the positioning map image are the matching corresponding images. Compared with the prior art, the present invention has the advantages of convenient algorithm design, good visualization effect, faster calculation speed, lower hardware requirements and the like.

Description

technical field [0001] The invention relates to the field of unmanned vehicle positioning, in particular to an image matching method for matching matrices in unmanned vehicle monocular vision positioning. Background technique [0002] Most of the existing technologies have the following two problems: [0003] 1. Most technologies do not perform data compression processing on image features, but directly use a certain layer of deep network features (such as the third convolutional layer), which requires a huge amount of data calculation, takes a long time and requires high hardware requirements. [0004] 2. Some technologies use the method of direct image compression to reduce the amount of computation. For example, the SeqSLAM algorithm does not use the deep learning network to extract features but directly compresses the image by 64*32 or 32*24. There is no screening of information in this process , but to intercept a certain area, it is easy to miss important information....

AI Technical Summary

Problems solved by technology

[0003] 1. Most technologies do not perform data compression processing on image features, but directly use a certain layer of deep network features (such as the third convolutional layer), which has a huge amount of data calculation, takes a long time and requires high hardware requirements

[0004] 2. Some technologies use the method of direct image compression to reduce the amount of computation. For example, the SeqSLAM algorithm does not use the deep learning network to extract features but directly compresses the image by 64*32 or 32*24. There is no screening of information in this process , but to intercept a certain area, it is easy to miss important information

Images