Fall Detection Dataset (2014)

Available

Dataset

Licence : CC BY-NC-SA doi:10.25666/DATAUBFC-2024-04-09

Data creators : Julien Dubois ^[1], Johel Miteran ^[1]

[1] : Imagerie et Vision Artificielle (UR 7535) (Université de Bourgogne)

Description :

In order to evaluate automatic fall detection methods, we build a dataset in realistic videosurveillance setting using a single camera. The frame rate is 25 frames/s and the resolution is 320×240 pixels. The video data illustrates the main difficulties of realistic video sequences that we can find at an elderly home environment, as well as in a simplest office room. Our video sequences contain variable illumination, and typical difficulties like occlusions or cluttered and textured background. The actors performed various normal daily activities and falls. The dataset contains 191 videos that we annotated, for evaluation purpose, with extra information representing the ground-truth of the fall position in the image sequence. Then, each frame of each video is annotated : the localization of the body is manually defined using bounding boxes. This annotation allows to evaluate the classification features independently from the automatic body detection.

Discipline :

computer science, software engineering (engineering science)

Keywords :

computer vision (Traitement du signal), fall detection

General metadata

Data acquisition date : from 1 Sep 2013 ongoing

Data acquisition methods :

Experimental data :
Generally, the few available datasets dedicated to fall detection use the same location for testing and training. Therefore, it does not enable to evaluate the robustness of the method to the location change between traning and testing. In order to evaluate this robustness, we recorded the video of our dataset from different locations, allowing to define several evaluation protocols (« Home », « Coffee room », « Office » and « Lecture room »).

Language : English (eng)

Formats : image/jpeg

Audience : Research

Publications :

Optimised spatio-temporal descriptors for real-time fall detection : comparison of SVM and Adaboost based classification (doi:10.1117/1.JEI.22.4.041106)
Fast prototyping of a SoC-based smart camera:a real-time fall detection case study (doi:10.1007/s11554-014-0456-4)
Robust spatio-temporal descriptors for real-time SVM-based fall detection (doi:10.1109/WSCAR.2014.6916794)

Publisher : dataUBFC - Atelier de la donnée de Bourgogne-Franche-Comté

Additional information :

Data collected as part of the PhD thesis of Imen Charfi "Automatic human fall detection based on spatio-temporal descriptors : definition of the method, evaluation of the performance and real-time implementation", co-supervised by Johel Miteran (ImViA, university of Burgundy), Rached Tourki (university of Monastir), Julien Dubois (ImViA, university of Burgundy).

Data

	1 file
		FallDataset.zip Published : 09/04/2024 11:42 Size : 8.95 GB Continued Description : In order to evaluate our automatic fall detection method, we build a dataset in realistic videosurveillance setting using a single camera.

1 file

FallDataset.zip

Published : 09/04/2024 11:42 Size : 8.95 GB

Continued

Description : In order to evaluate our automatic fall detection method, we build a dataset in realistic videosurveillance setting using a single camera.