Fall detection for multiple pedestrians using depth image processing technique

• Published in: Computer methods and programs in biomedicine Vol. 114; no. 2; pp. 172 - 182
• Main Authors: Yang, Shih-Wei, Lin, Shir-Kuan
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ireland Ltd 01.04.2014; Elsevier
• Subjects: Accidental Falls - statistics & numerical data; Applied sciences; Artificial intelligence; Computer science; control theory; systems; Depth image analysis; Exact sciences and technology; Fall detection; Humans; Illumination compensation; Image Processing, Computer-Assisted - methods; Imaging, Three-Dimensional - methods; Internal Medicine; Multiple pedestrian detection; Other; Pattern recognition. Digital image processing. Computational geometry; Posture; Walking; Depth image analysis; Fall detection; Multiple pedestrian detection; Illumination compensation; Occlusion; Light source; Computer vision; Image processing; Color; Pedestrian; Silhouette; Multiple image; Light sources; Tilt angle; Walking; Image analysis; Luminance; Experimental result; Indoor installation; Surveillance; Illumination; Fall; Occultation
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2014.02.001

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.