Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A monocular vision odometer method based on recurrent convolution neural network

A neural network and monocular vision technology, which is applied in the fields of image processing, computer vision and deep learning, can solve problems such as irreversible and poor positioning accuracy, and achieve the effects of improving accuracy, reducing dependence and good adaptability

Inactive Publication Date: 2019-01-25
ROCKET FORCE UNIV OF ENG
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But the system cannot recover absolute scale and has poor localization accuracy

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
  • A monocular vision odometer method based on recurrent convolution neural network
  • A monocular vision odometer method based on recurrent convolution neural network
  • A monocular vision odometer method based on recurrent convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only It is an embodiment of a part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0018] It should be noted that the terms "first" and "second" in the description and claims of the present invention and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate ...

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 monocular vision odometer method based on a recurrent convolution neural network. Firstly, the feature of image is extracted by depth convolution neural network, and then therelationship between image sequences is modeled by recurrent neural network. Simultaneous use of convolution-deconvolution network realizes the depth restoration of the image. The view synthesis error is obtained by matching the corresponding pixels between binocular image pairs. The left-right parallax consistency error is obtained by using the estimated depth map. The camera posture consistencyerror is obtained by using the left and right image sequences. The left-eye image sequence and the right-eye image sequence are matched with each other in time to obtain the sequence view synthesis error and minimize the error so as to obtain the optimal neural network model parameters. The invention tests a plurality of publicly released image data set sequences and verifies the effectiveness and superiority of the invention by comparing with the existing method.

Description

technical field [0001] The invention belongs to the technical fields of image processing, computer vision and deep learning, and in particular relates to a monocular visual odometer method based on a recursive convolutional neural network. Background technique [0002] Odometer technology is the key technology for mobile robots to use sensors to realize their own real-time positioning, and is the basic requirement for path planning, autonomous navigation and other tasks. In general, odometry information can be obtained from sensors such as rotary encoders, inertial measurement units (IMUs), and GPS, but this is not applicable when the wheels are slipping and there is no GPS signal. In terms of visual odometry, there are many excellent geometric structure-based methods, including feature point method, direct method and semi-direct method. The processing flow of the traditional visual odometry method based on the feature point method is: feature extraction, feature matching, ...

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): G06T7/00G06T7/73G06T7/50G06N3/04
CPCG06T7/0002G06T7/50G06T7/73G06T2207/20081G06T2207/10016G06N3/045
Inventor 鲍振强李艾华王涛崔智高苏延召张金明
Owner ROCKET FORCE UNIV OF ENG
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com