Category:
Development
Net4Age Ontology Terms:
autonomy
, computer science
, device
, emergency
, housing
, isolation
, safety
, sensor
, technology
, wellbeing
Description:
Research. Detecting falls and getups from bed via 3d depth sensors and radar technology
Overview:
Current emergency systems for elderly contain at least one sensor (button or accelerometer), which has to be worn or pressed in case of emergency. If elderly fall andloose their consciousness, they are not able to press thebutton anymore. Therefore, autonomous systems to detect falls without wearing any devices are needed.
Objectives:
This paperpresents three different non-invasive technologies: the useof audio, 2D sensors (cameras) and introduces a newtechnology for fall detection: the Kinect as 3D depth sen-sor. Our fall detection algorithms using the Kinect are evaluated on 72 video sequences, containing 40 fallsand 32 activities of daily living. The evaluation resultsare compared with State-of-the-Art approaches using 2Dsensors or microphones
Initiatives:
We propose to classify fall detection approaches into thefollowing categories, depending on the technology to beused: (1) wearable sensors (e.g., accelerometers to analyzeacceleration for fall detection [21]), (2) robots (e.g., arobotic dog following elderly and detecting falls [6]), (3)audio-based approaches using microphones, (4) 2D sensorsproviding pictures (cameras), (5) 3D sensors providingdepth information (e.g., Kinect). As we are only dealingwith stationary sensors, only the latter three approacheswill be discussed
Shortcomings:
Hardware dependency on Kinect. Privacy concerns.
Relevance:
4
Relevance Description:
High relevance to healthcare providers for instance, for the improvement of safety and independent living.
Quality:
3
Opinion:
Good approach relevant for the improvement of thequality of care and independent living. Interesting proof of concept.
Recommended:
Yes
Overlap:
Yes
Overlap Detail:
Sources:
https://www.researchgate.net/publication/236902510_Introducing_the_use_of_depth_data_for_fall_detection
Keywords:
fall detection, depth sensor, kinect
Submitted By:
Jennifer Lumetzberger
Email:
kb13575@gmail.com