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

Dynamic environment three-dimensional reconstruction method

A technology of three-dimensional reconstruction and dynamic environment, applied in the field of three-dimensional reconstruction, can solve the problems of system positioning error, affecting reconstruction results, etc., to achieve the effect of less false detection, high detection rate and edge accuracy, and reduced calculation amount

Active Publication Date: 2020-09-25
浙江四点灵机器人股份有限公司
View PDF10 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

And if in the actual 3D reconstruction application scenario, if the objects used for multi-frame matching are in a high dynamic state, and the feature points on these objects also participate in the calculation of 3D poses, then these objects will give the system The positioning of the system will bring serious errors, which will affect the reconstruction results

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
  • Dynamic environment three-dimensional reconstruction method
  • Dynamic environment three-dimensional reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The technical scheme of the present invention will be further described below by specific examples:

[0029] figure 1 It is the judgment logic block diagram of the dynamic area; first use the optical flow method to process the area to be judged, and then use 3D object detection for further processing to determine the area boundary.

[0030] figure 2 It is the overall flow chart of the system; it mainly includes ORB feature extraction of images collected by depth sensors, dynamic point detection, relocation, retrieval of new key frames, mapping of initial key frames, 3D depth filtering to form a semantic library, and loopback detection.

[0031] 1. Calibrate the parameters of the depth sensor used, and collect RGB-D images (including color images and depth images) of the scene;

[0032] 2. Extract ORB feature points from the color image;

[0033] 3. Detect the dynamic objects in the scene every 5 frames. The specific steps include:

[0034] 3.1 First process the col...

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 dynamic environment three-dimensional reconstruction method. The method comprises the following steps: calibrating parameters of an adopted depth sensor; according to the 3Dtarget detection method provided by the invention, compared with a conventional point cloud matching algorithm, the calculated amount is greatly reduced, so that the whole reconstruction process can be realized in real time. According to the dynamic object detection method integrating the traditional optical flow method and the deep learning target detection, compared with the detection rate and the edge accuracy of independent action of the traditional optical flow method and the deep learning target detection method, the detection rate and the edge accuracy are higher, and false detection isless. According to the three-dimensional reconstruction method based on the dynamic detection method, dynamic objects can be removed more quickly and better, and quick and accurate scene reconstruction is carried out.

Description

technical field [0001] The invention relates to the field of three-dimensional reconstruction, in particular to a method for three-dimensional reconstruction of a dynamic environment. Background technique [0002] 3D reconstruction is a very meaningful topic in the field of computer vision. Vision-based 3D reconstruction refers to obtaining data images of scene objects through cameras, analyzing and processing the images, and then deriving 3D information of objects in the real environment by combining computer vision knowledge. How to achieve high-precision, high-speed, The 3D reconstruction of large scenes is the goal pursued by this field. The 3D reconstruction technology has a wide range of applications in various fields of industry and life. Facing more practical needs, dynamic indoor real-time 3D reconstruction technology is widely used in indoor augmented reality games, robot indoor navigation, AR furniture display, and home decoration modeling display. And if in th...

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 Applications(China)
IPC IPC(8): G06T7/50G06T7/90G06T17/00G06K9/32
CPCG06T7/90G06T7/50G06T17/005G06V10/25
Inventor 林斌张梦玥
Owner 浙江四点灵机器人股份有限公司
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