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

RGB-D and SLAM scene reconfiguration method based on FAST and FREAK feature matching algorithm

A scene reconstruction and feature matching technology, applied in the field of RGB-D and SLAM scene reconstruction, can solve the problem that the relative transformation matrix does not meet the theoretical constraints of the unit matrix, and achieve the effect of reducing the number of splicing and reducing the accumulation of errors

Active Publication Date: 2017-02-08
HARBIN ENG UNIV
View PDF1 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the relative transformation matrix obtained by image frame registration usually does not satisfy the theoretical constraints of the identity matrix

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
  • RGB-D and SLAM scene reconfiguration method based on FAST and FREAK feature matching algorithm
  • RGB-D and SLAM scene reconfiguration method based on FAST and FREAK feature matching algorithm
  • RGB-D and SLAM scene reconfiguration method based on FAST and FREAK feature matching algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with the accompanying drawings.

[0032] Traditional RGB-D SLAM uses feature matching algorithms such as SIFT, SURF, and ORB. In terms of real-time performance, algorithms such as SIFT and SURF are not ideal. ORB and FREAK algorithms are proposed for running on mobile devices, so real-time In terms of robustness, the comprehensive performance of SIFT is good, the performance of SURF is poor when the illumination changes, and the performance is relatively stable under other conditions, the comprehensive performance of ORB algorithm is average, and the performance of FREAK algorithm is relatively good in various environments. good stability. Considering both real-time and robustness of the method, a RGB-D SLAM scene reconstruction method based on FAST and FREAK feature matching algorithms is proposed.

[0033] (1) First, calibrate the Kinect device. The present invention adopts the calibration function...

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 present invention belongs to the computer graphics field, and concretely relates to a RGB-D and SLAM scene reconfiguration method based on the FAST and FREAK feature matching algorithm. The method comprises: performing calibration of the Kinect; performing FAST feature point extraction of a color image, employing the FREAK feature descriptors to perform image matching, employing the RANSAC algorithm of the feature points to reject the exterior points, and retaining the internal points. The RGB-D and SLAM scene reconfiguration method based on the FAST and FREAK feature matching algorithm screens the key frames and performs cloud point jointing of the key frames so as to greatly reduce the joint number of times of the cloud points. The RGB-D and SLAM scene reconfiguration method based on the FAST and FREAK feature matching algorithm employs the loop detection algorithm based on the graph optimization to construct a posture graph and perform global optimization so as to greatly reduce the error accumulation.

Description

technical field [0001] The invention belongs to the field of computer graphics, in particular to a RGB-D and SLAM scene reconstruction method based on FAST and FREAK feature matching algorithms. Background technique [0002] 3D reconstruction technology involves computer graphics, sensing technology, machine vision, reverse engineering, virtual reality, robot navigation and other fields. Its purpose is to display the spatial shape and position of object models or indoor scenes more realistically and objectively. Therefore, the Technology is currently a hot topic of research by many scholars at home and abroad. [0003] The visual computing theory proposed by Marr divides vision into three stages. The first stage, the primary stage of 3D reconstruction, starts with the acquisition of simple 2D image information, including basic geometric shapes or feature elements such as depth images, edge maps, and color texture images. The position and shape information of the object sur...

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): G06T17/00G06T7/80G06T7/33
CPCG06T17/00G06T2200/04G06T2200/32G06T2207/10021G06T2207/10024G06T2207/10028G06T2207/20221
Inventor 叶秀芬邢会明张建国王璘黄乐李鹏贾同超
Owner HARBIN ENG 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