Unlock instant, AI-driven research and patent intelligence for your innovation.

A method for building raster maps using infrared, depth and binocular camera fusion

A technology of binocular camera and grid map, which is applied in the field of image processing and computer vision, to achieve the effect of simple program, easy implementation, finer and more accurate construction of grid map

Active Publication Date: 2021-07-02
DALIAN UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The combination of the three can overcome problems such as non-textured areas and lighting effects

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 method for building raster maps using infrared, depth and binocular camera fusion
  • A method for building raster maps using infrared, depth and binocular camera fusion
  • A method for building raster maps using infrared, depth and binocular camera fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention proposes a method for constructing a grid map by fusion of infrared, depth and binocular cameras, which is described in detail in conjunction with the accompanying drawings and embodiments as follows:

[0030] The overall process is as figure 1 , first obtain the depth maps of the three sensors, such as Figure 5 , 6 and 7, then update the weight of the depth value in the GPU, and fuse the depth value to construct a grid map, and finally display the grid map on the PC. The method of the present invention comprises the following steps:

[0031] 1) Sensor Registration

[0032] Such as figure 2 For the former, first use a mixed-material calibration plate, an infrared camera and a binocular camera to collect enough image data, and then adopt Zhang Zhengyou’s calibration method to obtain the sensor pose as T. Then use the calibration object to further correct T, use two sensors to shoot the calibration object to obtain a depth map, and then the in...

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 method for constructing a grid map by fusion of infrared, depth and binocular cameras, belonging to the fields of image processing and computer vision. Use rigorous registration strategies to complete sensor registration and improve system efficiency from the hardware level. Use GPU to build a high-performance computing platform, and build a high-performance solution algorithm to build a raster map. The system is easy to build, the program is simple, and it is easy to implement; the infrared camera, depth camera and binocular camera are used to fuse to build a map, which can be used around the clock, and the algorithm is robust and accurate.

Description

technical field [0001] The invention belongs to the fields of image processing and computer vision. Utilize the characteristics of infrared, depth and binocular cameras to make up for each other's defects, making the construction of grid maps more precise and accurate. It is a method for constructing raster maps using multiple sensors. Background technique [0002] In recent years, with the development of artificial intelligence, mobile robots and autonomous vehicles have attracted more and more attention, and one of the main problems that needs to be solved is map construction. Grid map is the most common type of map in unmanned navigation, so how to construct a fast and accurate grid map has become a very important issue in mobile robots and unmanned vehicles. The mainstream method at this stage roughly uses three kinds of sensors, binocular camera, depth camera and radar. Due to their own characteristics, the three sensors have inevitable shortcomings. The binocular ca...

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 Patents(China)
IPC IPC(8): G01C21/00G01C21/20G01C21/32
CPCG01C21/005G01C21/20G01C21/32
Inventor 仲维李豪杰陈圣伦王智慧罗钟铉刘日升樊鑫
Owner DALIAN UNIV OF TECH