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

Synchronous positioning and map-constructing method for mobile robot facing indoor dynamic environment

A mobile robot, synchronous positioning technology, applied in the fields of instruments, image enhancement, image analysis, etc., can solve the problems of low real-time performance of algorithms and inability to take into account accuracy and real-time performance.

Active Publication Date: 2019-02-26
NORTHEASTERN UNIV
View PDF7 Cites 54 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The advantage of this type of algorithm is that it is basically not affected by camera motion, and the map points can be eliminated more thoroughly by using the segmented image. The disadvantage is that the algorithm is not real-time, and it can even be completed with the help of GPU acceleration.
[0006] To sum up, for the SLAM problem in a dynamic environment, the existing SLAM algorithms all assume a static environment. Even if a static model of map points is added or a dense optical flow segmentation algorithm is used, accuracy and real-time performance cannot be considered. The fusion of high frame rate semi-direct SLAM algorithm and image motion detection algorithm can effectively solve this problem

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
  • Synchronous positioning and map-constructing method for mobile robot facing indoor dynamic environment
  • Synchronous positioning and map-constructing method for mobile robot facing indoor dynamic environment
  • Synchronous positioning and map-constructing method for mobile robot facing indoor dynamic environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0115] In view of the fact that the existing SLAM algorithm cannot effectively solve the problem of solving the camera pose in a dynamic scene, the present invention improves the real-time performance of the SLAM algorithm, and adds the image motion detection result to provide a semi-direct RGB- D SLAM algorithm (that is, the method of synchronous positioning and composition of mobile robots for indoor dynamic environments). The invention can effectively solve the positioning and mapping problems in SLAM, and provides an effective solution for the positioning and navigation problems of robots in dynamically changing indoor scenes.

[0116] On the one hand, after the camera pose is preliminarily solved by using the semi-direct method visual odometry, the outliers caused by moving objects in the local sparse map are eliminated with the help of the results of image motion detection, thereby effectively improving the positioning accuracy of the entire system .

[0117] On the oth...

Embodiment 2

[0206] In the method of this embodiment, the hardware configuration is Intel E3-1230CPU, the main frequency is 3.30GHz, the memory is 12G, GPU acceleration is not used, and the tested system is Ubuntu14.04. The camera used is a first-generation Kinect. The structural diagram of the present invention is as figure 1 Shown:

[0207] Step 1: Collect an image I with a resolution of 640*480RGB from the Kinect camera, and extract 200 FAST corner points on I. The process of extracting corner points can be simply described as: first divide the image into 8*8 image blocks, and then extract FAST corner points in each image block separately, and only select the corner points with the highest response value. If the texture in some areas of the image is not rich enough, and the corner points may not be extracted, just skip it directly. Finally, among all the selected corner points, select the corner point whose response value is in the top 200 as the corner point to be tracked by the sys...

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 provides a synchronous positioning and map-constructing method for a mobile robot facing an indoor dynamic environment, wherein the method can effectively solve the problem of positioning and navigation map construction for mobile robots in indoor dynamic environment. Specifically, the initial estimation of a camera pose is achieved by minimizing the photometric error of an image. Then, the motion compensation of the image is estimated, and a moving object in the image is segmented, local map points projected in the moving area of the image are eliminated, and the camera pose isfurther optimized. Finally, a TSDF dense map is constructed by using the optimized camera pose and camera image information, and real-time updating of the map in the dynamic environment is completed by using motion detection in image and map levels. Experimental results show that in the indoor dynamic environment, the method can effectively improve the positioning accuracy of the camera, realizesreal-time updating of the dense map, improves the robustness of the system and enriches the environmental information perceived by the robot.

Description

technical field [0001] The invention relates to the field of digital image processing and computer vision, in particular to a method for synchronous positioning and composition of mobile robots facing indoor dynamic environments. Background technique [0002] Visual SLAM (Simultaneous Localization and Mapping, simultaneous positioning and map construction) is a method for estimating the pose of a robot using a continuous image sequence output by a single or multiple cameras. In order to achieve real-time and accurate positioning of mobile robots, vision-based real-time positioning and mapping systems have been widely used. [0003] Especially the SLAM system based on RGB-D camera can directly use the color and depth information provided by the camera to realize the positioning of the camera and the perception of environmental information. In order to simplify the problem, most of the visual SLAM systems at this stage assume that the environment where the camera is located i...

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): G01C21/20G06T7/11G06T7/70
CPCG01C21/206G06T7/11G06T7/70G06T2207/10004
Inventor 张云洲高成强王晓哲邓毅姜浩
Owner NORTHEASTERN UNIV
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