Target positioning method for double-flow convolutional neural network regression learning based on depth image

A convolutional neural network and depth image technology, applied in biological neural network models, image analysis, image enhancement, etc., can solve the problem of low image positioning accuracy, achieve stable positioning regression results, improve target positioning accuracy, and reduce complexity Effect

Active Publication Date: 2019-11-12
NANJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to propose a target positioning method based on depth images to solve the problem of low accuracy of traditional image-based positioning

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Target positioning method for double-flow convolutional neural network regression learning based on depth image
  • Target positioning method for double-flow convolutional neural network regression learning based on depth image
  • Target positioning method for double-flow convolutional neural network regression learning based on depth image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Specific embodiments of the present invention are described in detail below, but it should be understood that the protection scope of the present invention is not limited by specific embodiments.

[0034] Unless expressly stated otherwise, throughout the specification and claims, the term "comprise" or variations thereof such as "includes" or "includes" and the like will be understood to include the stated elements or constituents, and not Other elements or other components are not excluded.

[0035] A target positioning algorithm based on depth image regression learning, the method comprises the following steps:

[0036] S1, at each reference position, a binocular camera collects a grayscale image and its corresponding depth image;

[0037] S2 uses image preprocessing technology, and the grayscale image and depth image are converted into three-channel images; in S2, the image preprocessing technology is specifically: input two three-channel images of different modalit...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a target positioning method for double-flow convolutional neural network regression learning based on a depth image. In the offline stage, at each reference position, the grayscale image and the depth image corresponding to the grayscale image are collected by a binocular camera. By using image preprocessing techniques, the grayscale image and the depth image are convertedinto three-channel images. Then, the double-flow CNN with the shared weight coefficient is used for offline regression learning. Finally, a regression model based on the distance is obtained. In the online stage, after the obtained grayscale image and depth image are preprocessed, the final distance is estimated through a regression model based on the distance.

Description

Technical field: [0001] The invention relates to a method for target positioning, specifically a method for using pictures taken by a binocular camera and learning through a dual-stream convolutional neural network to perform target positioning, and belongs to the technical field of positioning and navigation. Background technique: [0002] Image-based positioning algorithm is an interdisciplinary technology that integrates computer vision, machine learning, multi-view geometry, image retrieval and many other scientific research fields. It has wide application prospects and great research value. However, the traditional image positioning algorithm uses image retrieval to deal with the positioning problem, which cannot meet the positioning accuracy requirements of some typical applications. [0003] The existing technology includes: an indoor positioning system based on image recognition (patent application number: CN201710157566.9, patent publication number: CN108629384A). ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/73G06T5/00G06T5/50G06N3/04
CPCG06T7/75G06T5/009G06T5/50G06N3/045
Inventor 颜俊张艺梅康彬杨孟渭
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap