Full cycle visual SLAM algorithm using CNNs feature detection

A feature detection, full-cycle technology, applied in computing, computer components, instruments, etc., can solve the problems of inability to build trajectories and maps, unreliable results, etc., achieve simple visual odometer, express image information sufficient, online computing speed fast effect

Active Publication Date: 2019-02-15
BEIHANG UNIV
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Errors will inevitably accumulate over time, causing cumulative errors in the entire system, and long-term estimation results will be unreliable. In other words, we cannot build globally consistent trajectories and maps

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
  • Full cycle visual SLAM algorithm using CNNs feature detection
  • Full cycle visual SLAM algorithm using CNNs feature detection
  • Full cycle visual SLAM algorithm using CNNs feature detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0021] The present invention adopts the visual SLAM algorithm of CNNs feature detection in the whole cycle, such as figure 1 shown, including the following steps:

[0022] Step 1: scan surrounding environment information;

[0023] Use the binocular camera to move along the square area, collect the environmental image information of the real scene, and transmit the obtained video stream to the host computer in real time. The number of moving circles of the binocular camera is 1 to 2 circles, forming a closed loop, which facilitates the subsequent closed-loop detection link to compensate for the accumulated error. The above process is repeated, and a part of the multiple video streams collected is used as a training data set, and a part is used as a testing data set.

[0024] Step 2: Pre-train the training data set in the video stream collected in step 1 by ...

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 full-cycle visual SLAM algorithm using CNNs feature detection. First, in the front end, the original image data is pre-trained by an unsupervised model, and then the pre-trained data is used through CNN network architecture to correlate the joint representation of motion and depth with the changes in local velocity and direction, thus executing the visual odometry. Finally, the path prediction is performed. The invention also uses the OverFeat neural network model for loop detection to eliminate the accumulated errors caused by the front end and constructs a visual SLAM architecture based on deep learning. At the same time, a time and space continuity filter is constructed to verify the matching results, improve the matching accuracy and eliminate mismatching. Theinvention has tremendous advantages and potentials in improving the accuracy of visual odometry and the correct rate of closed-loop detection.

Description

technical field [0001] The invention belongs to the technical field of simultaneous positioning and map construction (slam) algorithms in computer vision, and in particular relates to a visual SLAM algorithm using CNNs feature detection in a full cycle. Background technique [0002] The Chinese name of SLAM (Simultaneous Localization and Mapping) is "simultaneous positioning and map construction". SLAM is a fascinating field of research with wide-ranging applications in robotics, navigation, and many other applications. Visual SLAM basically involves estimating camera motion and trying to build a map of the surrounding environment based on visual sensor information, such as a sequence of frames from one or more cameras. The current research methods for SLAM problems are mainly to estimate the motion information of the robot body and the characteristic information of the unknown environment by installing multiple types of sensors on the robot body, and use information fusion...

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): G01C21/32G06K9/62
CPCG01C21/32G06F18/22G06F18/241G06F18/214
Inventor 赵永嘉张宁雷小永戴树岭
Owner BEIHANG 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