Fall Detection Using Depth Maps Acquired by a Depth Sensing Camera
(2016) MAMM01 20152Ergonomics and Aerosol Technology
- Abstract
- In a time when the population and life expectancy increase, the demands on health care change. The biggest cost in Swedish health care today is related to accidents regarding falls of old people. This Master's thesis presents a solution to fall detection and logging of data from falls. Falls themselves are hard to stop, but there are several factors behind falls that can be changed in order to prevent them.
In this Master's thesis the development of a fall detection system and it's results are presented. The system is based on a Microsoft Kinect and a Raspberry Pi 2, these components are standard, of-the-shelf products with a total price less than 2000 SEK, which is significantly less than the price of the hardware used in the majority... (More) - In a time when the population and life expectancy increase, the demands on health care change. The biggest cost in Swedish health care today is related to accidents regarding falls of old people. This Master's thesis presents a solution to fall detection and logging of data from falls. Falls themselves are hard to stop, but there are several factors behind falls that can be changed in order to prevent them.
In this Master's thesis the development of a fall detection system and it's results are presented. The system is based on a Microsoft Kinect and a Raspberry Pi 2, these components are standard, of-the-shelf products with a total price less than 2000 SEK, which is significantly less than the price of the hardware used in the majority of other projects in this field. Using consumer components opens up the possibility for others to further develop the system in the future. The developed solution uses thresholds based on acceleration and height to identify falls. These parameters have been used alone in earlier studies, by using the unique technique of combining them gives more accurate results.
The development of the system was divided in to two phases. In the first phase a data collection was carried out, 200 falls and activities performed by a total of 5 test subjects were logged and the data analyzed. The results were used when developing the final fall detection software. In the second phase, 75 falls and activities where performed by two test subjects in order to test the accuracy of the software. Combining acceleration with height proved to be a good solution, detecting falls with a sensitivity of 92 percent and a specificity of 96 percent. (Less) - Abstract (Swedish)
- I en tid där befolkningen ökar och medellivslängden blir äldre förändras villkoren för vården. Den största kostnaden inom svensk vård idag är relaterade till äldre människor och fallskador. I den här uppsatsen presenteras en framtagen lösning som detekterar fall och sparar information om vad som händer under ett fall. Ett fall i sig självt är väldigt svårt att stoppa, men det finns faktorer runt människorna som faller som kan ändras så att risken för fall minskar.
Den här uppsatsen tar upp utvecklandet av ett falldetektionssystem och dess testresultat. Systemet är baserat på en Microsoft Kinect och en Raspberry Pi 2, standardkomponenter med ett totalpris på under 2000 kr. Det är signifikant lägre än priset på de komponenter som används... (More) - I en tid där befolkningen ökar och medellivslängden blir äldre förändras villkoren för vården. Den största kostnaden inom svensk vård idag är relaterade till äldre människor och fallskador. I den här uppsatsen presenteras en framtagen lösning som detekterar fall och sparar information om vad som händer under ett fall. Ett fall i sig självt är väldigt svårt att stoppa, men det finns faktorer runt människorna som faller som kan ändras så att risken för fall minskar.
Den här uppsatsen tar upp utvecklandet av ett falldetektionssystem och dess testresultat. Systemet är baserat på en Microsoft Kinect och en Raspberry Pi 2, standardkomponenter med ett totalpris på under 2000 kr. Det är signifikant lägre än priset på de komponenter som används i majoriteten av andra projekt inom samma område. Användandet av standardkomponenter gör systemet lätt att utveckla vidare av andra i framtiden. Den framtagna lösningen använder tröskelvärden baserade på acceleration och höjd för att identifiera fall. Dessa parametrar har använts enskilt i tidigare studier, genom att använda den unika tekniken där de kombineras fås mer exakta resultat.
Utvecklingen av systemet utfördes i två faser. I den första fasen gjordes en datainsamling. Totalt utfördes 200 fall och vardagsaktiviteter av fem testpersoner, datan från fallen loggades och analyserades. Resultatet från datainsamlingen användes som grund för att utveckla det slutgiltiga falldetektions-programet. I den andra fasen utfördes 75 fall och vardagsaktiviteter av två testpersoner för att bestämma systemets noggrannhet. Kombinationen av acceleration och höjd visade sig vara en bra lösning, fall detekterades med en sensitivitet på 92 procent och en specificitet på 96 procent. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/8885192
- author
- Knorn, Jonathan LU and Lindholm, Fredrik LU
- supervisor
- organization
- course
- MAMM01 20152
- year
- 2016
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- Fall detection, Smart Home, Home Care, Raspberry Pi, Kinect, Falldetektion, Smarta hem, Hemsjukvård
- language
- English
- id
- 8885192
- date added to LUP
- 2016-06-30 10:26:03
- date last changed
- 2016-06-30 10:26:03
@misc{8885192,
abstract = {{In a time when the population and life expectancy increase, the demands on health care change. The biggest cost in Swedish health care today is related to accidents regarding falls of old people. This Master's thesis presents a solution to fall detection and logging of data from falls. Falls themselves are hard to stop, but there are several factors behind falls that can be changed in order to prevent them.
In this Master's thesis the development of a fall detection system and it's results are presented. The system is based on a Microsoft Kinect and a Raspberry Pi 2, these components are standard, of-the-shelf products with a total price less than 2000 SEK, which is significantly less than the price of the hardware used in the majority of other projects in this field. Using consumer components opens up the possibility for others to further develop the system in the future. The developed solution uses thresholds based on acceleration and height to identify falls. These parameters have been used alone in earlier studies, by using the unique technique of combining them gives more accurate results.
The development of the system was divided in to two phases. In the first phase a data collection was carried out, 200 falls and activities performed by a total of 5 test subjects were logged and the data analyzed. The results were used when developing the final fall detection software. In the second phase, 75 falls and activities where performed by two test subjects in order to test the accuracy of the software. Combining acceleration with height proved to be a good solution, detecting falls with a sensitivity of 92 percent and a specificity of 96 percent.}},
author = {{Knorn, Jonathan and Lindholm, Fredrik}},
language = {{eng}},
note = {{Student Paper}},
title = {{Fall Detection Using Depth Maps Acquired by a Depth Sensing Camera}},
year = {{2016}},
}