Download PDFOpen PDF in browser

Fall Detection from Thermal Camera Using Convolutional LSTM Autoencoder

EasyChair Preprint 824

4 pagesDate: March 12, 2019

Abstract

Human falls occur very rarely; this makes it difficult to employ supervised classification techniques. Moreover, the sensing modality used must preserve the identity of those being monitored. In this paper, we investigate the use of thermal camera for fall detection, since it effectively masks the identity of those being monitored. We formulate the fall detection problem as an anomaly detection problem and aim to use autoencoders to identify falls. We also present a new anomaly scoring method to combine the reconstruction score of a frame across different video sequences. Our experiments suggests that Convolutional LSTM autoencoders perform better than convolutional and deep autoencoders in detecting unseen falls.

Keyphrases: anomaly detection, computer vision, deep learning, fall detection, machine learning, unseen fall

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:824,
  author    = {Jacob Nogas and Shehroz Khan and Alex Mihailidis},
  title     = {Fall Detection from Thermal Camera Using Convolutional LSTM Autoencoder},
  doi       = {10.29007/xt7r},
  howpublished = {EasyChair Preprint 824},
  year      = {EasyChair, 2019}}
Download PDFOpen PDF in browser