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

Indoor fall detection method and device for old people based on FPGA and deep learning

A deep learning and detection method technology, applied in the field of data processing, can solve the problems of lack of privacy protection, low accuracy and efficiency, complex detection technology, etc., and achieve health protection, high accuracy, and enhanced real-time and privacy Effect

Inactive Publication Date: 2021-09-17
深圳思悦创新有限公司 +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] To this end, the present invention provides an indoor fall detection method and device for the elderly based on FPGA and deep learning, which can realize the detection and early warning of the fall state of the elderly, and solve the problems of complex traditional detection technology, low accuracy and efficiency, and lack of privacy protection.

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 fall detection method and device for old people based on FPGA and deep learning
  • Indoor fall detection method and device for old people based on FPGA and deep learning
  • Indoor fall detection method and device for old people based on FPGA and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] See figure 1 with figure 2 Provide an indoor fell detection method based on FPGA and deep learning, including the following steps:

[0070] S1, get the gesture image data under the preset gesture, and labeled the position of the body frame in the posture picture;

[0071] S2, construct the deep learning network model of the body frame, using the labeling posture picture to carry out the deep learning network model training, to obtain the deep learning network model of training for the old people's indoor falling inspection;

[0072] S3, load the deep learning network model of the training to the FPGA platform; use the FPGA platform to identify the video stream image to be detected;

[0073] S4, when the FPGA platform determines that a frame of picture in the video stream picture is falling, the output warning signal is output to voice alert and alarm.

[0074] In this embodiment, in step S1, the gesture image data under the preset gesture includes MSCOCO, MPII, LSP, and FLI...

Embodiment 2

[0116] See image 3 The present invention also provides an indoor falling detection device based on FPGA and depth learning, including:

[0117] Image acquisition module 1 is used to get the gesture image data in the preset gesture;

[0118] The human body frame identification module 2 is used to identify the position of the human body frame in the posture picture;

[0119] Model Training Module 3, is used to construct a deep learning network model of the body frame, and use the labeling posture to perform the training of the depth learning network model to obtain a deep learning network model of training for the old people's indoor falling.

[0120] Fall detection module 4, for the completion of training the learning network model is loaded into the depth of the FPGA platform; video stream by using the image recognition FPGA platform to be detected;

[0121] Early Warning Module 5, is used to determine a voice reminder and alarm when the FPGA platform determines that a frame pictu...

Embodiment 3

[0146] Embodiment 3 of the present invention provides a computer readable storage medium that stores a program code for an old people within an old man's indoor fall detection method based on FPGA and deep learning, the program code including an Example. 1 or any of its possible implementation of an indoor falling detection method based on FPGA and depth learning.

[0147] The computer readable storage medium can be any available medium that the computer can access or a data storage device such as a server, data center, such as one or more available media. The available medium may be a magnetic medium, (eg, a floppy disk, a hard disk, a tape, a photoreaterial (eg, a DVD), or a semiconductor medium (e.g., SolidStatedisk, SSD), and the like.

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 fall detection method and device for old people based on FPGA and deep learning. The method comprises the steps: obtaining posture picture data of a human body in a preset posture, and marking the position of a human body frame in a posture picture; constructing a deep learning network model of the human body frame, and training the deep learning network model by using the labeled posture picture to obtain the trained deep learning network model for indoor fall detection of the old; loading the trained deep learning network model into an FPGA platform to identify a video stream picture to be detected; when it is judged that the human body state of a certain frame of picture in the video streaming pictures is falling down, outputting an early warning signal for voice reminding and alarming. According to the method, the characteristics of high speed, big data processing capability, hardware programming design and the like of the FPGA are fully utilized, and a deep learning algorithm is implanted into the FPGA, so that the real-time performance and privacy of human body tumble detection are enhanced; in addition, the human body frame coordinates are automatically extracted by adopting the deep learning neural network model, and the accuracy is high.

Description

Technical field [0001] The present invention relates to the field of data processing, and more particularly to an indoor falling detection method and apparatus based on FPGA and depth learning. Background technique [0002] According to the seventh national population census data, my country's 60-year-old and over the population reached 18.7%, which accounted for 18.7% of my country's population, of which 13.5% of the population of 65 and over, my country has entered a deep aging society. For the elderly, the action is inconvenient to cause falls that is harmful. The Ministry of Health announced the "Elderly Falling Intervention Technical Guide" pointed out that "falling is the first cause of death in the age of 65 years old." If the old man falls, it will not be able to worsen the results. How can I detect that the elderly fall, and will be able to timely alarm and notify the ambulance person when falling in the old man. It has great market value. [0003] In traditional techniq...

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
CPCG06N3/08G06N3/045
Inventor 李卫东刘平涛张招罗博文
Owner 深圳思悦创新有限公司
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