About this document
Wang Et Al 2016 Human Posture Recognition Based On Images Captured by The Kinect Sensor by s8039802 is a document available to read on EtoBox.
This paper presents a hybrid recognition method for human posture recognition using depth images captured by a Kinect sensor, identifying five postures: sitting, standing, stooping, kneeling, and lying. The method employs various image processing techniques, including background subtraction, silhouette contour extraction, and feature vector calculation, achieving a recognition rate over 97%. This approach eliminates the need for wearable sensors, making it suitable for applications in automatic home care sy
- Author
- s8039802
- Language
- EN