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

A scene recognition method and apparatus based on indoor opportunity signal enhancement

A scene recognition and signal enhancement technology, applied in the field of indoor scene recognition, can solve the problem of low recognition accuracy

Active Publication Date: 2019-01-29
WUHAN UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a scene recognition method and device based on indoor opportunity signal enhancement to solve or at least partially solve the technical problem of low recognition accuracy in the scene recognition method in the prior art

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
  • A scene recognition method and apparatus based on indoor opportunity signal enhancement
  • A scene recognition method and apparatus based on indoor opportunity signal enhancement
  • A scene recognition method and apparatus based on indoor opportunity signal enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] This embodiment provides a scene recognition method based on indoor opportunity signal enhancement, please refer to figure 1 , The method includes:

[0069] First, perform step S1: for the preset application scenario, collect a typical scene image set.

[0070] Specifically, the preset application scene can be selected according to actual research or application requirements, and the typical scene image set can be collected using existing methods.

[0071] Then step S2 is performed: combining the scene base map corresponding to the scene to be studied, the positioning information and image information of the mobile device are collected on the main road of the scene to be studied, where the positioning information and the image information correspond to the positioning points.

[0072] Specifically, a scene base map refers to an indoor base map of an application scene, and a scene base map contains multiple scenes. Indoor opportunity signals are radio signals collected by radio...

Embodiment 2

[0138] This embodiment provides a scene recognition device based on indoor opportunity signal enhancement, please refer to Figure 5 , The device includes:

[0139] The scene image collection module 501 is configured to collect a typical scene image collection for preset application scenarios;

[0140] The positioning information and image information collection module 502 is used to combine the scene base map corresponding to the scene to be studied to collect the positioning information and image information of the mobile device on the main road of the scene to be studied, where the positioning information includes a positioning point;

[0141] The transfer learning module 503 is used to input the scene image set into the preset feature fusion neural network, and fine-tune the convolutional neural network module of the preset feature fusion neural network to obtain the convolutional neural network model that is migrated to the scene to be studied, Among them, the preset feature fus...

Embodiment 3

[0173] Based on the same inventive concept, this application also provides a computer-readable storage medium 600, please refer to Image 6 , A computer program 611 is stored thereon, and when the program is executed, the method in the first embodiment is realized.

[0174] Since the computer-readable storage medium introduced in the third embodiment of the present invention is the computer-readable storage medium used in the implementation of the indoor opportunity signal enhancement-based scene recognition method in the first embodiment of the present invention, it is based on the introduction in the first embodiment of the present invention Those skilled in the art can understand the specific structure and deformation of the computer-readable storage medium, so it will not be repeated here. All computer-readable storage media used in the method of the first embodiment of the present invention belong to the scope of the present invention.

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 provides a scene recognition method and device based on indoor opportunity signal enhancement. By using a convolution neural network trained by transfer learning to obtain the scene-level image features of indoor localization points, and describing the positioning characteristics of the positioning point through the positioning information of the positioning point and the scene bottom map and the positioning error and then using the location feature to expand and enhance the image features, and using the depth learning method to fuse the image features and the location features to predict the scene recognition, a technical effect of achieving higher accuracy of scene recognition is realized.

Description

Technical field [0001] The present invention relates to the technical field of indoor scene recognition, in particular to a scene recognition method and device based on enhancement of indoor opportunity signals. Background technique [0002] The problem of scene recognition is a very challenging topic in the field of computer vision, which is applied in various fields such as autonomous driving and robotics. [0003] Existing scene recognition methods usually use image feature analysis to identify and classify. For example, traditional image processing and pattern recognition related research are used to classify and mark scene images, but they require a lot of manual operations and the algorithms are more complex. There are also some using deep learning methods on large-scale data sets. However, for indoor environments, the scenes include complex decorations and layouts. Therefore, using deep learning to solve indoor scene recognition still has the problem of low recognition accur...

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): G06K9/00G06K9/62G06N3/04
CPCG06V20/41G06N3/045G06F18/2411G06F18/253
Inventor 呙维吴然陈艳华朱欣焰
Owner WUHAN 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

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