Fall Detection Based on Body Part Tracking Using a Depth Camera

The elderly population is increasing rapidly all over the world. One major risk for elderly people is fall accidents, especially for those living alone. In this paper, we propose a robust fall detection approach by analyzing the tracked key joints of the human body using a single depth camera. Compared to the rivals that rely on the RGB inputs, the proposed scheme is independent of illumination of the lights and can work even in a dark room. In our scheme, a pose-invariant randomized decision tree algorithm is proposed for the key joint extraction, which requires low computational cost during the training and test. Then, the support vector machine classifier is employed to determine whether a fall motion occurs, whose input is the 3-D trajectory of the head joint. The experimental results demonstrate that the proposed fall detection method is more accurate and robust compared with the state-of-the-art methods.

Authors

• Zhen-Peng Bian
• Junhui Hou Department of Computer Science, City University of Hong Kong
• Lap-Pui Chau
• Nadia Magnenat-Thalmann

Keywords

• Joints
• Equations
• Cameras
• Trajectory
• Head
• Training
• Three-dimensional displays
• Body Parts
• Depth Camera
• Body Part Tracking
• Support Vector Machine
• Support Vector Machine Classifier
• Random Decision Tree
• Fall Accidents
• Computational Complexity
• Image Pixels
• Search Algorithm
• Depth Images
• Shannon Entropy
• Inertial Measurement Unit
• Motion Analysis
• Leaf Node
• Joint Position
• Human Motion
• Previous Frame
• Human Joint
• Body Orientation
• Test Pixel
• Fall Events
• Joint Trajectories
• Color Preference
• Node Splitting
• Vision-based Methods
• Geometric Surface
• Depth Values
• Computer vision
• fall detection
• head tracking
• monocular
• video surveillance
• 3-D
• Accidental Falls
• Adult
• Female
• Humans
• Image Processing, Computer-Assisted
• Male
• Monitoring, Ambulatory
• Reproducibility of Results
• Video Recording
• Young Adult