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

A blind person walking assisting method based on deep learning

A deep learning, blind person technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as difficulty in meeting users' precise blind guidance, no real-time alarm function, and difficulty in ensuring user life safety.

Active Publication Date: 2019-06-18
ZHEJIANG UNIV
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the current assistance methods only focus on walking in areas, such as indoors or outdoors, and it is difficult to meet the user's requirements for precise blind guidance throughout the process.
And most of the methods only have static obstacle reminder function, for dynamic dangerous objects such as oncoming vehicles, there is no real-time alarm function, it is difficult to guarantee the safety of users

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 blind person walking assisting method based on deep learning
  • A blind person walking assisting method based on deep learning
  • A blind person walking assisting method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] The present invention will be further described below in conjunction with example and accompanying drawing. The present invention's method for assisting the blind based on deep learning comprises the following steps:

[0076] Step 1: When a blind person is walking, traditional assisted walking methods generally only provide indoor or outdoor guidance. This invention integrates these two modes, collects pictures in real time, and enters the outdoor or indoor guidance mode according to the current situation.

[0077] Step 2: Indoor blind guide mode, including marker recognition and text recognition, such as figure 1 shown. Among them, the marker recognition uses a specific data enhancement method to train the deep convolutional neural network, and then uses the trained network to detect indoor markers.

[0078] The network training process is as follows:

[0079] 1) Data preparation and preprocessing

[0080] First construct the original landmark data set, analyze 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 a blind person walking assisting method based on deep learning. Firstly, a camera is started for real-time data acquisition. The method comprises the following steps: detectingan environmental dangerous object and a traffic signal lamp through a deep convolutional neural network when the vehicle travels outdoors, if the vehicle meets the dangerous object, carrying out Kalman filtering tracking, comparing and calculating an object motion state in a period of time, analyzing a motion trend of the object, and carrying out danger reminding; And if so, performing signal lamp state identification. During indoor advancing, markers in the environment are detected in real time, marker related areas are extracted, and key information such as characters is extracted. The method adopts deep learning to carry out object detection, has the characteristics of high robustness, high accuracy, high speed and the like, and has very high practicability.

Description

technical field [0001] The present invention relates to the field of video detection and analysis technology and blind people's assisted walking, in particular to a blind person's assisted walking method based on deep learning. Background technique [0002] my country is the country with the largest number of blind people. With social development and technological progress, people from all walks of life pay more and more attention to the lives of blind people, and travel activities are an extremely severe challenge in the lives of blind people. General travel activities can be divided into outdoor walking and indoor walking. In outdoor walking, because most cities lack corresponding infrastructure and there is no traffic system for blind people, the travel of blind people is severely restricted; If you are not accompanied by a normal person, you will be in a very dangerous road situation. When walking indoors, since there are basically no blind guide facilities in most ind...

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): G06K9/00G06K9/46G06N3/04G06N3/08
Inventor 周泓杨利娟
Owner ZHEJIANG 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