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

Online binocular vision ranging method based on RLT2 secondary allocation algorithm

A secondary allocation and binocular vision technology, applied in the field of drones, can solve problems such as poor matching accuracy, insufficient real-time performance, and high solution complexity, and achieve the effects of improving robustness, overcoming texture interference, and increasing computing speed

Inactive Publication Date: 2020-12-01
GUANGDONG UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of image matching in the binocular ranging algorithm on the unmanned aerial vehicle platform with high complexity, poor matching accuracy, and insufficient real-time performance on the embedded platform, to construct a secondary allocation problem to optimize image matching, The quadratic term is linearized by RLT2 (two-level reconstruction linearization technique), and the (mixed) integer programming model equivalent to the original problem is obtained. By solving the linear relaxation of the (mixed) integer programming model, an accurate Matching solution, reducing computational complexity, improving matching accuracy, while ensuring real-time requirements

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
  • Online binocular vision ranging method based on RLT2 secondary allocation algorithm
  • Online binocular vision ranging method based on RLT2 secondary allocation algorithm
  • Online binocular vision ranging method based on RLT2 secondary allocation algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described below in conjunction with specific embodiment:

[0041] This embodiment adopts the binocular vision system based on the unmanned aerial vehicle platform to carry out such as figure 1 The shown online binocular vision ranging method based on the RLT2 secondary allocation algorithm, the specific process is as follows:

[0042] S1. First, edge detection is performed on the left and right images to extract image features:

[0043]UAV ranging platform is built by binocular camera, the optical centers of the two cameras are parallel to the front, and the left and right cameras capture two images respectively, the left camera captures the left image, and the right camera captures the right view, and the image size is M×N pixels. Use the gradient operator to detect the edge of the image and extract the image features. Image edge detection can greatly reduce the amount of data, remove irrelevant information, and retain important...

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 an online binocular vision ranging method based on an RLT2 secondary allocation algorithm, which estimates parallax matching of left and right images through a QAP (quadratic allocation problem optimization) technology, and improves the response speed by utilizing an RTL2 (secondary reconstruction linearization technology). The binocular ranging method comprises the steps of firstly, performing edge detection on left and right images to extract image features; constructing a secondary allocation optimization problem by utilizing the image feature information; obtaininga solution of a secondary allocation optimization problem by utilizing the RTL2 technology to obtain disparity maps of the left image and the right image; and finally, utilizing the target parallax ofthe left and right images to measure the distance of the front scene. The method improves the image matching precision and speed through the linear optimization technology, improves the ranging precision and speed, is small in calculation amount, and is suitable for parallel acceleration calculation.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicles, specifically an online binocular vision ranging method based on the RLT2 secondary allocation algorithm. Background technique [0002] UAVs have broad application prospects in fields such as wilderness search and rescue, environmental detection, agriculture, forestry and plant protection, power energy inspection, fire disaster relief, land surveying and mapping, and parcel delivery. Improve the autonomous flight capabilities of UAVs in complex environments, quickly and efficiently Automatic obstacle avoidance is of great significance to broaden the application field of UAVs and improve the efficiency of UAVs. The current UAV obstacle avoidance schemes mainly include obstacle avoidance schemes based on ultrasonic sensors, obstacle avoidance schemes based on laser sensors, and visual sensor obstacle avoidance schemes. Ultrasonic sensors have narrow sensing range, poor spatial resol...

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): G01C11/34G06T7/55G06T7/13G06F17/10
CPCG01C11/34G06F17/10G06T7/13G06T7/55
Inventor 徐胜苏成悦陈元电
Owner GUANGDONG UNIV OF TECH