Fall detection for multiple pedestrians using depth image processing technique

Shih Wei Yang*, Shir-Kuan Lin

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

20 Scopus citations


A fall detection method based on depth image analysis is proposed in this paper. As different from the conventional methods, if the pedestrians are partially overlapped or partially occluded, the proposed method is still able to detect fall events and has the following advantages: (1) single or multiple pedestrian detection; (2) recognition of human and non-human objects; (3) compensation for illumination, which is applicable in scenarios using indoor light sources of different colors; (4) using the central line of a human silhouette to obtain the pedestrian tilt angle; and (5) avoiding misrecognition of a squat or stoop as a fall. According to the experimental results, the precision of the proposed fall detection method is 94.31% and the recall is 85.57%. The proposed method is verified to be robust and specifically suitable for applying in family homes, corridors and other public places.

Original languageEnglish
Pages (from-to)172-182
Number of pages11
JournalComputer Methods and Programs in Biomedicine
Issue number2
StatePublished - 1 Jan 2014


  • Depth image analysis
  • Fall detection
  • Illumination compensation
  • Multiple pedestrian detection

Fingerprint Dive into the research topics of 'Fall detection for multiple pedestrians using depth image processing technique'. Together they form a unique fingerprint.

Cite this