I am looking for activity recognition data sets that are captures through sensors (i.e. accelerometer, gyroscope etc) or using a smartphone. Most of the publicly available data sets contain data from normal activities of daily living (e.g. walking, running, cycling etc), however I am interested in data sets that shall also contain data from unusual/abnormal activities such as fall or stroke apart from normal activities. Currently I am using DLR Human Activity Recognition data set, and looking for some other similar data sets. I would appreciate if you would please direct me to any such data you are aware of.
I have a relative work concerning activity recognition ADL datasets. I would be quite happy if it could help you even a bit. You can find it here:
https://www.researchgate.net/publication/249656578_DemCare_action_dataset_for_evaluating_dementia_patients_in_a_home-based_environment
Conference Paper DemCare action dataset for evaluating dementia patients in a...
Not yet. But currently we are working on acquiring an official permit.
You can also check our project web site :
http://www.demcare.eu
CMU kitchen dataset provides a lot of different sensor data + anomalous data: http://kitchen.cs.cmu.edu/
visit the following link to get information about publicly available datasets for action recognition. In addition, fall detection and monitoring datasets are also given.
https://naveenideas.blogspot.in/2017/02/datasets-action-recognition.html
- Badges
- Science topic