Fall Detection with Event-Based Data: A Case Study

Xueyi Wang*, Nicoletta Risi, Estefanía Talavera, Elisabetta Chicca, Dimka Karastoyanova, George Azzopardi

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Downloads (Pure)


Fall detection systems are relevant in our aging society aiming to support efforts towards reducing the impact of accidental falls. However, current solutions lack the ability to combine low-power consumption, privacy protection, low latency response, and low payload. In this work, we address this gap through a comparative analysis of the trade-off between effectiveness and energy consumption by comparing a Recurrent Spiking Neural Network (RSNN) with a Long Short-Term Memory (LSTM) and a Convolutional Neural Network (CNN). By leveraging two pre-existing RGB datasets and an event-camera simulator, we generated event data by converting intensity frames into event streams. Thus, we could harness the salient features of event-based data and analyze their benefits when combined with RSNNs and LSTMs. The compared approaches are evaluated on two data sets collected from a single subject; one from a camera attached to the neck (N-data) and the other one attached to the waist (W-data). Each data set contains 469 video samples, of which 213 are four types of fall examples, and the rest are nine types of non-fall daily activities. Compared to the CNN, which operates on the high-resolution RGB frames, the RSNN requires 200 × less trainable parameters. However, the CNN outperforms the RSNN by 23.7 and 17.1% points for W- and N-data, respectively. Compared to the LSTM, which operates on event-based input, the RSNN requires 5 × less trainable parameters and 2000 × less MAC operations while exhibiting a 1.9 and 8.7% points decrease in accuracy for W- and N-data, respectively. Overall, our results show that the event-based data preserves enough information to detect falls. Our work paves the way to the realization of high-energy efficient fall detection systems.

Original languageEnglish
Title of host publicationComputer Analysis of Images and Patterns
Subtitle of host publication20th International Conference, CAIP 2023, Limassol, Cyprus, September 25–28, 2023, Proceedings, Part II
EditorsNicolas Tsapatsoulis, Efthyvoulos Kyriacou, Andreas Lanitis, Zenonas Theodosiou, Marios Pattichis, Constantinos Pattichis, Christos Kyrkou, Andreas Panayides
Place of PublicationCham
Number of pages10
ISBN (Electronic)978-3-031-44240-7
ISBN (Print)978-3-031-44239-1
Publication statusPublished - 2023
Event20th International Conference on Computer Analysis of Images and Patterns, CAIP 2023 - Limassol, Cyprus
Duration: 25 Sept 202328 Sept 2023
Conference number: 20

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference20th International Conference on Computer Analysis of Images and Patterns, CAIP 2023
Abbreviated titleCAIP 2023


  • CNN
  • Deep Learning (DL)
  • Event-based
  • Fall detection
  • LSTM
  • RSNN
  • Wearable cameras
  • n/a OA procedure


Dive into the research topics of 'Fall Detection with Event-Based Data: A Case Study'. Together they form a unique fingerprint.

Cite this