Real-Time Action Recognition System for Elderly People Using Stereo Depth Camera
| Autor: | Yuya Akagi, Hiroki Tamura, Sanae Araki, Etsuo Chosa, Thi Thi Zin, Ye Htet, Kazuhiro Kondo |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
Feature vector Feature extraction depth motion history ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION TP1-1185 histogram of oriented gradients depth motion appearance Biochemistry Article Motion (physics) Pattern Recognition Automated UV-disparity maps Analytical Chemistry Motion Computer Systems Humans Computer vision Electrical and Electronic Engineering depth map features Representation (mathematics) Instrumentation Aged action recognition ambient assisted living business.industry Chemical technology Rounding Frame (networking) Atomic and Molecular Physics and Optics Histogram of oriented gradients Action (philosophy) stereo depth camera Artificial intelligence business Algorithms |
| Zdroj: | Sensors Volume 21 Issue 17 Sensors (Basel, Switzerland) Sensors, Vol 21, Iss 5895, p 5895 (2021) |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s21175895 |
| Popis: | Smart technologies are necessary for ambient assisted living (AAL) to help family members, caregivers, and health-care professionals in providing care for elderly people independently. Among these technologies, the current work is proposed as a computer vision-based solution that can monitor the elderly by recognizing actions using a stereo depth camera. In this work, we introduce a system that fuses together feature extraction methods from previous works in a novel combination of action recognition. Using depth frame sequences provided by the depth camera, the system localizes people by extracting different regions of interest (ROI) from UV-disparity maps. As for feature vectors, the spatial-temporal features of two action representation maps (depth motion appearance (DMA) and depth motion history (DMH) with a histogram of oriented gradients (HOG) descriptor) are used in combination with the distance-based features, and fused together with the automatic rounding method for action recognition of continuous long frame sequences. The experimental results are tested using random frame sequences from a dataset that was collected at an elder care center, demonstrating that the proposed system can detect various actions in real-time with reasonable recognition rates, regardless of the length of the image sequences. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|