Rapid indoor scene understanding method

An indoor scene and scene technology, applied in the field of indoor three-dimensional scene understanding

Pending Publication Date: 2021-10-22
HANGZHOU DIANZI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Applicable to the field of interior decoration construction

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
  • Rapid indoor scene understanding method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0030] Such as figure 1 As shown, a fast indoor scene understanding method includes the following steps:

[0031] Step 1: Use the RGB-D sensor to obtain the overall 3D scanning data of the room;

[0032] Step 2: Detect the scene plane, and assign semantic information (wall, ground) to the plane;

[0033] Detecting planes from point clouds is actually a common problem in computer vision and robotics. Indoor scenes usually consist of a variable number of planes; RANSAC is run continuously to detect all planes in the scene until no more planes are found. Since the planes in the scene will include small planes such as tables, it is first necessary to obtain the plane parameters of all the detected planes, and then merge the normal ...

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 rapid indoor scene understanding method. The method includes: firstly, using an RGB-D sensor to obtain indoor overall 3D scanning data; detecting a scene plane, giving semantic information to the plane, removing the scene plane, and only leaving objects; performing semantic segmentation on the object, and applying a planar semantic tag; and finally, understanding the scene by using a tree diagram. According to the method, the layout layout is removed, so that more concise object representation can be obtained, and subsequent object segmentation and recognition are facilitated.

Description

technical field [0001] The present invention belongs to the field of computer vision, and mainly relates to the understanding of indoor three-dimensional scenes. A relatively lightweight framework is used to understand the scene relatively quickly, and the layout information of the scene is applied to object recognition and classification, and the whole scene depends on the tree Graphics are used to represent the overall structure. [0002] technical background [0003] Three-dimensional reconstruction refers to the establishment of mathematical models suitable for computer representation and processing of three-dimensional objects. In recent years, the widespread use of consumer-grade RGB-D sensors such as Microsoft Kinect, Intel RealSense, and Google Tango has enabled significant progress in RGB-D reconstruction. The reconstruction accuracy has been greatly improved compared to before. Therefore, 3D scene understanding based on the reconstruction effect has become the nex...

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): G06K9/00G06K9/62G06T7/10
CPCG06T7/10G06T2207/10012G06F18/241
Inventor 吕坤颜成钢路统宇孙垚棋张继勇李宗鹏
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap