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

Motion estimation method applying depth data distribution constraints

A motion estimation and depth data technology, applied in the field of computer vision, can solve the problems of ICP result offset and large error, and achieve the effect of improving accuracy and stability

Pending Publication Date: 2020-05-01
南通慧识智能科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in actual application scenarios, when the number of texture-rich feature points on close objects is far greater than the number of feature points on distant objects, most of the inliers are distributed on close objects, so the ICP results in the next step will be offset. Larger errors are produced, and an improved technology is urgently needed to solve this problem existing in the prior art

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
  • Motion estimation method applying depth data distribution constraints
  • Motion estimation method applying depth data distribution constraints
  • Motion estimation method applying depth data distribution constraints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0036] The present invention provides a technical solution: a motion estimation method applying depth data distribution constraints, comprising the following steps:

[0037] Step 1: If Figure 1-2As shown, the RGB-D camera collects two frames of images at adjacent times, and extracts the feature points and their descriptors in the images respectively. At present, the most commonly used feature extraction algorithms in visual SLAM mainly include SIFT, SURF and ...

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 motion estimation method applying depth data distribution constraints. The scheme of the invention mainly aims at the requirement of estimating the motion of a robot from twoadjacent image data in a visual SLAM; extracting feature points and feature point descriptors by using a feature extraction algorithm; according to the method, dividing feature points into near points and far points according to distances to eliminate error results by using an RANSAC method, so that a relatively reasonable number of near-distance feature points and far-distance feature points canexist in a final matching result, and the precision and stability of robot pose motion estimation are improved on the basis.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a motion estimation method applying depth data distribution constraints. Background technique [0002] In recent years, the technology for mobile robots to perceive the environment has been continuously developed. Simultaneous Localization and Mapping (SLAM) is the key technology for realizing intelligent robots. When the mobile robot is located in an unknown scene and cannot directly obtain its own position and attitude information through external information, the robot body needs to analyze the real-time data of its own sensors and complete the estimation of its own position and the construction of the environment map. [0003] The SLAM problem can be described as: the robot starts from the initial point in an unknown environment, and realizes self-positioning through the environmental observation information obtained from external sensors and internal odometer data du...

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): G06K9/00G06K9/46G06K9/62G06T7/73B25J19/02
CPCG06T7/73B25J19/023G06V20/10G06V10/462G06F18/22
Inventor 吕岳张晓峰沈季玮
Owner 南通慧识智能科技有限公司