Privacy-preserving video fall detection via chaotic compressed sensing and GAN-based feature enhancement

Jixin LIU, Ru MENG, Ning SUN, Guang HAN, Sam KWONG

Research output: Journal PublicationsJournal Article (refereed)peer-review

1 Citation (Scopus)


Currently, falling is the primary cause of injury and death of the elderly due to accidents, which seriously threatens the health and life of the elderly. Considering the phenomenon of video privacy disclosure in recent years, this paper proposes a computer vision fall detection method to meet the needs of video privacy protection. The innovation here lies in compressed sensing (CS) visual privacy protection and GAN-based feature enhancement. There are three main steps: 1) the video frame visual privacy protection with chaotic pseudo-random CS mechanism, 2) the foreground extraction with improved low rank sparse decomposition theory, 3) the temporal and spatial feature enhancement and fall detection with improved-ACGAN architecture. The experimental results on three open fall datasets show that the method can not only effectively detect the fall behavior in video, but also has high accuracy. At the same time, the overall operation speed of the algorithm increases with the increase of the number of compression layers.
Original languageEnglish
JournalIEEE Multimedia
Issue number4
Publication statusPublished - 10 May 2022
Externally publishedYes


  • Chaotic pseudorandom mechanism
  • Computer vision
  • Fall detection
  • Feature enhancement
  • Feature extraction
  • Foreground extraction
  • Older adults
  • Privacy
  • Sparse matrices
  • Video fall detection
  • Visual privacy protection
  • Visualization


Dive into the research topics of 'Privacy-preserving video fall detection via chaotic compressed sensing and GAN-based feature enhancement'. Together they form a unique fingerprint.

Cite this