Indoor tumble detection method and system based on scene recognition

A technology of scene recognition and detection method, which is applied in the field of deep learning and computer vision, can solve the problems of high cost, lack of monitoring data utilization, old people wearing or wearing related equipment affecting normal life, etc. The method is simple, avoids invalid calculations, and improves The effect of accuracy

Pending Publication Date: 2021-12-03
CHINA THREE GORGES UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For wearable devices, it is easy for the elderly to forget to wear them or wearing related devices will affect their normal life, and the cost of using this method is relatively high
[0003] At this stage, many families will install cameras at home, but the function of this kind of camera is only simple monitoring, and the monitoring data is not used

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 tumble detection method and system based on scene recognition
  • Indoor tumble detection method and system based on scene recognition
  • Indoor tumble detection method and system based on scene recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] like figure 1 As shown, the indoor fall detection method based on scene recognition shown in Embodiment 1 of the present application includes the following steps:

[0056] S1. Collect video image data of the monitoring area.

[0057] In the first embodiment, video surveillance equipment is used to collect video images of daily activities in an indoor environment.

[0058]S2. Based on the video image data of the monitoring area, the scene category is judged. In the first embodiment, the scene category includes unmanned scenes, single-person scenes and multi-person scenes, so as to eliminate the interference of multi-person situations and detect the falling behavior of single-person scenes. It is simple, the experimental results are more accurate, and the logic of fall monitoring is more reasonable; in the case of many people, the actual use of intelligent fall monitoring is not great. In the first embodiment, the target detection algorithm is used to calculate the numb...

Embodiment 2

[0115] like image 3 As shown, it is a schematic structural diagram of an indoor fall detection system based on scene recognition in Embodiment 2 of the present application, including an image acquisition unit, a scene classification unit, a multimodal processing unit, and a fall judgment unit connected in sequence.

[0116] Wherein, the image collection unit is used for collecting video image data of the monitoring area.

[0117] The scene classification unit is used to judge the scene category of the video image data in the monitoring area. The scene categories include unmanned scenes, single-person scenes and multi-person scenes. The scene classification unit is also used to mark single-person pictures and ignore unmanned scenes and multi-person scenes. Scenes;

[0118] The multi-modal processing unit is used to intercept the video clips containing the single-person picture from the video image data of the monitoring area according to the single-person picture to generate ...

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 system based on scene recognition. The method comprises the following steps: collecting video image data of a monitoring area; judging a scene category and cutting a single-person picture; intercepting single-person video data, and carrying out multi-modal processing; according to the multi-modal data and a preset tumble detection network, tumble judgment is carried out; the system comprises an image acquisition unit, a scene classification unit, a multi-mode processing unit and a tumble judgment unit, the image acquisition unit is used for acquiring video image data of a monitoring area; the scene classification unit is used for scene category judgment and single-person picture marking, the multi-modal processing unit is used for multi-modal processing to generate multi-modal data, and the tumble judgment unit is used for tumble judgment. The invention is simple, invalid calculation under a large number of unmanned scenes and multi-person scenes is avoided, and the tumble detection accuracy is improved by using multi-modal data.

Description

technical field [0001] The application belongs to the technical field of deep learning and computer vision, and in particular relates to an indoor fall detection method and system based on scene recognition. Background technique [0002] Falls are the main cause of injury and death for the elderly. Due to the decline in physical fitness or various diseases, the probability of injury increases sharply if the elderly do not get help in time after a fall. The traditional fall detection method is to wear a wearable device, and judge whether a fall occurs by acquiring corresponding behavioral characteristics. For wearable devices, it is easy for the elderly to forget to wear them or wear related devices to affect their normal life, and the cost of using this method is relatively high. [0003] At this stage, many families will install cameras at home, but the function of this kind of cameras is only simple monitoring, and the monitoring data is not used. A large amount of video...

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): G06K9/00G06K9/34G06T7/269G08B21/04
CPCG06T7/269G08B21/043G08B21/0476
Inventor 刘军清严兵康维
Owner CHINA THREE GORGES UNIV
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