Indoor scene understanding method based on 2D-3D semantic data set

A technology for indoor scenes and data sets, applied in the field of scene understanding, can solve the problems of ignoring the semantic information of image content and differences in image understanding

Inactive Publication Date: 2017-05-24
SHENZHEN WEITESHI TECH
View PDF0 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, low-level visual features only represent visual information, ignoring the semantic information contained in the image content, which is different from human understanding of images.

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
  • Indoor scene understanding method based on 2D-3D semantic data set
  • Indoor scene understanding method based on 2D-3D semantic data set
  • Indoor scene understanding method based on 2D-3D semantic data set

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0028] figure 1 It is a system flowchart of an indoor scene understanding method based on a two-dimensional-three-dimensional semantic data set of the present invention. It mainly includes data collection and organization, training and testing splits.

[0029] Data collection and collation, using a camera to collect data, which combines 3 structured light sensors, rotates at each scanning position, and captures 18 kinds of RGB and depth images 360°; output scanning area, original color depth image (RGB-D) 3D texture mesh reconstructed with camera metadata; use these data as a basis to generate additional RGB-D data, and generate a point cloud by sampling the mesh; semantically annotat...

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 indoor scene understanding method based on a 2D-3D semantic data set. The indoor scene understanding method comprises the main content of collection, arrangement, training and test division of data and comprises the following steps: firstly capturing an image, outputting a scanning region, an original color depth image (RGB-D) and a 3D texture grid, sampling the grid to generate point clouds, carrying out semantic annotation on the data, projecting each point label to a 3D grid and an image field, and representing certain regions with concentrated data to parts with similar buildings in aspects of appearances and architectural features, so as to define standard training and test division. According to the semantic data set disclosed by the invention, cross-modal study models and non-supervision methods can be developed and united by virtue of rules existing in large-scale indoor spaces; powerful prompts are provided for the detection of semanteme, layout, shields, shapes and modes; and the indoor scene understanding method is not limited by scale, diversity and number.

Description

technical field [0001] The invention relates to the field of scene understanding, in particular to an indoor scene understanding method based on a two-dimensional-three-dimensional semantic data set. Background technique [0002] The recognition and understanding of indoor scenes is one of the key technologies of intelligent information processing. Related research results have been successfully applied in different fields, such as target tracking, pedestrian detection and face detection and recognition in the field of security protection, Internet information Image content retrieval in the field, target search, scene understanding, obstacle detection in the field of intelligent robots, rescue in smart homes and dangerous environments, etc., make people's work and life more convenient. Therefore, the recognition and understanding of indoor scenes is of great importance. Theoretical research significance and engineering application value. [0003] Traditional image resource ...

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): G06K9/00G06T11/00G06T15/04G06T17/30
CPCG06T11/003G06T15/04G06T17/30G06V20/36
Inventor 夏春秋
Owner SHENZHEN WEITESHI TECH
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