Indoor home automatic layout algorithm for detecting empty room features based on deep learning

A technology of deep learning and feature detection, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as lack of furniture

Active Publication Date: 2020-05-15
江苏艾佳家居用品有限公司
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the business background of indoor home automatic layout, usually only an empty room floor plan is entered in advance, with only doors, windows and walls on the map, without furniture

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 home automatic layout algorithm for detecting empty room features based on deep learning
  • Indoor home automatic layout algorithm for detecting empty room features based on deep learning
  • Indoor home automatic layout algorithm for detecting empty room features based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The object detection model generally solves the problem of given the existence of objects in the picture, and then requires the model to output the boundary of the object type. The algorithm of the present invention applies the object detection model to non-object detection problems. The detected object does not exist in the input image, and there are only empty rooms in the input image. The experiment found that by detecting the unique model of the door, window and wall, the object detection model can be used to predict the type, size and position of the furniture.

[0036] Step 1, generate an image of an empty room. Based on the OBJ file of the floor plan, a 3-channel empty room picture containing only the picture information of the door, window and wall is generated, and the door, window and wall are represented by different colors.

[0037] Step 2, organize the data labels. Quantify the information such as the type of furniture, the size of the furniture, and the...

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 home automatic layout algorithm for detecting empty room features based on deep learning. According to the algorithm, under the condition that household information is lost, the type, size and position of furniture needing to be arranged in a room are automatically calculated only by depending on the relative position characteristics of doors, windows and walls ofthe empty room. The algorithm is mainly characterized by comprising four points: 1, inputting a picture tensor representing visual features of doors, windows and walls of an empty room; 2, not needing to input furniture information to be laid out additionally; 3, taking an object detection algorithm of deep learning in the image as a door, window and wall feature detection tool; and 4, automatically outputting and inputting furniture types, furniture sizes and furniture positions which should be arranged in empty rooms.

Description

technical field [0001] The invention relates to the application of an object detection model in deep learning in the field of home automatic layout, and is an indoor home automatic layout algorithm for feature detection of empty houses based on deep learning. Background technique [0002] Deep learning, especially the convolutional neural network, is very suitable for building image object detection models. By rationally designing the model structure, the general deep learning object detection model can take advantage of the advantages of the convolutional neural network to automatically learn the visual features of the object and achieve a high accuracy rate. Typical examples are YOLO, RCNN, FAST-RCNN, etc. However, these models are generally used in object detection. When an object is detected, the object exists in the picture. The model locates and recognizes the object by detecting the pixel features of the object. [0003] In the business background of automatic indoo...

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): G06T11/60G06N3/04G06N3/08
CPCG06T11/60G06N3/08G06N3/045
Inventor 陈旋吕成云林善冬
Owner 江苏艾佳家居用品有限公司
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