RGB-D visual odometer based on GMS characteristic matching and sliding window pose graph optimization

A RGB-D, visual odometry technology, applied in the field of computer vision, can solve problems such as multi-computation, reduce system real-time performance, etc., to achieve the effect of improving robustness, high real-time performance, and improving accuracy

Active Publication Date: 2019-07-05
SUN YAT SEN UNIV
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

By designing a more complex photometric error calculation method, the cumulative error can be effectively reduced, but at the sa

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
  • RGB-D visual odometer based on GMS characteristic matching and sliding window pose graph optimization
  • RGB-D visual odometer based on GMS characteristic matching and sliding window pose graph optimization
  • RGB-D visual odometer based on GMS characteristic matching and sliding window pose graph optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] like figure 1 As shown, an RGB-D visual odometry based on GMS feature matching and sliding window pose graph optimization includes the following steps:

[0041] Step 1. Read and obtain the first frame of RGB image as a reference frame through the RGB-D camera, read the first frame of depth image as the depth information of the reference frame, extract feature points for the reference frame and calculate the ORB feature descriptor; the extracted features Point is the pixel position of the FAST (Fast Segment Test Feature) corner point in the image. The ORB feature compares the brightness value of the corner point with the brightness of the surrounding 128 pixels, and records it as 1 if it is brighter than the key point, and records it as 0 otherwise, and finally generates a 128-dimensional binary vector as the feature descriptor of the key point.

[0042] Step 2. Read the next frame of RGB image as the current frame, read the next frame of depth image as the depth inform...

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 belongs to the computer vision field and especially relates to an RGB-D visual odometer based on GMS characteristic matching and sliding window pose graph optimization. A GMS (grid motion statistics) algorithm is used to replace a commonly used distance threshold + RANSAC (random sample consistency) algorithm in the prior art to carry out mismatching rejection. When relative motion between images is large and brightness changes greatly, a sufficient number of correct matching point pairs can still be screened, which improves robustness of the system. A sliding window pose graph optimization technology is used to reduce a cumulative error of pose estimation. Compared with the prior art scheme in which a local map is maintained or a more complex objective function is designed,by using the odometer of the invention, higher real-time performance is possessed and at the same time accuracy of the visual odometer can be ensured.

Description

technical field [0001] The invention belongs to the field of computer vision, and more specifically relates to an RGB-D visual odometer based on GMS feature matching and sliding window pose graph optimization. Background technique [0002] Visual odometry refers to the real-time estimation of the robot's pose by analyzing relevant image sequences through machine vision technology, which can overcome the shortcomings of traditional odometers and perform more accurate positioning, and can operate in an environment that cannot be covered by GPS (Global Positioning System) , such as indoor environments, interstellar exploration, etc. Visual odometry has received extensive attention and applications in the field of mobile robot localization and navigation. [0003] At present, the two mainstream methods of visual odometry are feature point method and direct method. The feature point method mainly uses three steps, namely, feature extraction, feature matching, and minimizing the...

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
IPC IPC(8): G01C22/00G06T7/246G06T7/73
CPCG01C22/00G06T2207/10024G06T7/248G06T7/74
Inventor 陈佩谢晓明
Owner SUN YAT SEN UNIV
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