AI Research Topic/Action Recognition

[Activity Recognition] 쓰러짐(Fall Down)행동 인식 관련 데이터 세트

꾸준희 2019. 8. 5. 10:13



Fall Down 관련 논문


UP-Fall Detection Dataset: A Multimodal Approach


UP-Fall Detection Dataset: A Multimodal Approach

Falls, especially in elderly persons, are an important health problem worldwide. Reliable fall detection systems can mitigate negative consequences of falls. Among the important challenges and issues reported in literature is the difficulty of fair compari


Vision-Based Fall Detection with Convolutional Neural Networks


[PDF] Vision-Based Fall Detection with Convolutional Neural Networks - Semantic Scholar

One of the biggest challenges in modern societies is the improvement of healthy aging and the support to older persons in their daily activities. In particular, given its social and economic impact, the automatic detection of falls has attracted considerab





Fall Down Datasets






1. Multiple Cameras Fall Dataset


Multiple cameras fall dataset

관련 논문 

Hung, Dao Huu, and Hideo Saito. "Fall detection with two cameras based on occupied area." Proc. of 18th Japan-Korea Joint Workshop on Frontier in Computer Vision. 2012.






2. Fall Detection Dataset


Fall detection Dataset - Le2i - Laboratoire Electronique, Informatique et Image

Accueil du site > Structuration Scientifique > Electronique > Architecture des Systèmes Electroniques de vision > Outils de prototypage rapide pour Smart Camera > Fall detection Dataset Fall detection Dataset par Antoine Trapet - 27 février 2013 Automatic

Coffee Room 1, 2

Home 1, 2

Lecture Room 

Office 1, 2




3. UR Fall Dataset


UR Fall Detection Dataset

This dataset contains 70 (30 falls + 40 activities of daily living) sequences. Fall events are recorded with 2 Microsoft Kinect cameras and corresponding accelerometric data. ADL events are recorded with only one device (camera 0) and accelerometer. Sensor

1. Daily Living Sequence

2. Fall Sequence 





4. MultiMultiple Pose Human Body Database (LSP/MPII-MPHB)


(링크 수정됨, 2021/01/11)


LSP + MPII 에서 추출한 Lying Dataset 







5. CAVIAR Test Case Scenarios


CAVIAR Test Case Scenarios

CAVIAR Test Case Scenarios Video clips created July 11, 2003 and January 20, 2004 Introduction For the CAVIAR project a number of video clips were recorded acting out the different scenarios of interest. These include people walking alone, meeting with oth

Rest_FallOnFloor 데이터 포함 







6. UMAFall: Fall Detection Dataset (Universidad de Malaga)


이 데이터세트는 일련의 미리 결정된 ADL(Activities of Daily Life)과 Fall(쓰러짐) 행동을 담았으며,

19명에 의해 생성되었다. 관련 논문은 다음과 같다. 


Santoyo-Ramón, José Antonio, Eduardo Casilari, and José Manuel Cano-García. 

"Analysis of a smartphone-based architecture with multiple mobility sensors for fall detection with supervised learning." 

Sensors 18.4 (2018): 1155.

Casilari, Eduardo, Jose A. Santoyo-Ramón, and Jose M. Cano-García. "UMAFall: A Multisensor Dataset for the Research on Automatic Fall Detection." 

Procedia Computer Science 110 (2017): 32-39.


UMAFall: Fall Detection Dataset (Universidad de Malaga)

The files contain the mobility traces generated by a group of 19 experimental subjects that emulated a set of predetermined ADL (Activities of Daily Life) and falls. The traces are aimed at evaluating fall detection algorithms.Several video clips describin




7. Fall Data Set (RGB + Depth)


RGB 영상 뿐만 아니라 Depth 영상까지도 포함한 쓰러짐 데이터 세트이다. 

kinect 센서는 2.4m 높이에서 고정되어 촬영되었으며, 데이터 세트에는 총 21,499 장의 이미지로 이루어진다. 

22,636장 중에서 16,796장을 train, 3,299장을 val 로 사용할 수 있고, 2,543장을 test set 으로 사용할 수 있다.

데이터 세트의 이미지는 8개의 서로 다른 화각으로 구성된 다른 방에서 촬영되었다. 


Fall detection Dataset

Fall detection Dataset Fall detection Dataset Overview: The datasets that are used for the simulation purpose are raw RGB and Depth images of size 320x240 recorded from a single uncalibrated Kinect sensor after resizing from 640x480. The Kinect sensor is

1 2 3 4 5 6