TST Fall detection dataset v1
- Citation Author(s):
- Submitted by:
- Susanna Spinsante
- Last updated:
- Tue, 09/17/2019 - 11:12
- Data Format:
The dataset contains depth frames collected using Microsoft Kinect v1 in top-view configuration and can be used for fall detection.
Instructions – Four young actors simulated actions and falls. The dataset is constituted by 20 tests organized as follows: Tests from 1 to 10 contain data of two or more people walking in the monitored area. Tests from 11 to 20 contain data of a person simulating falls.This code can be used to read depth data with MATLAB:
If you use the dataset, please cite the following paper:
S. Gasparrini, E. Cippitelli, S. Spinsante, E. Gambi, “A Depth-Based Fall Detection System Using a Kinect® Sensor,” Sensors 2014, 14(2), 2756-2775; doi:10.3390/s140202756.
- Group A (test 1-10) Test_1_10.zip (151.47 MB)
- Group B (test 11-20) Test_11_20.zip (160.57 MB)
- Matlab code LoadDepthFrame.zip (17.71 kB)