Efficient fall activity recognition by combining shape and motion features
| Autor: | Mohammed Rziza, Rachid Oulad Haj Thami, Abderrazak Iazzi |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Aspect ratio
Computer science Feature vector ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Optical flow 02 engineering and technology motion features Ellipse lcsh:QA75.5-76.95 Artificial Intelligence Minimum bounding box Histogram 0202 electrical engineering electronic engineering information engineering Projection (set theory) ComputingMethodologies_COMPUTERGRAPHICS elderly people Orientation (computer vision) business.industry shape features 020207 software engineering Pattern recognition Computer Graphics and Computer-Aided Design fall detection classification 020201 artificial intelligence & image processing lcsh:Electronic computers. Computer science Computer Vision and Pattern Recognition Artificial intelligence business |
| Zdroj: | Computational Visual Media, Vol 6, Iss 3, Pp 247-263 (2020) |
| ISSN: | 2096-0662 2096-0433 |
| DOI: | 10.1007/s41095-020-0183-7 |
| Popis: | This paper presents a vision-based system for recognizing when elderly adults fall. A fall is characterized by shape deformation and high motion. We represent shape variation using three features, the aspect ratio of the bounding box, the orientation of an ellipse representing the body, and the aspect ratio of the projection histogram. For motion variation, we extract several features from three blocks corresponding to the head, center of the body, and feet using optical flow. For each block, we compute the speed and the direction of motion. Each activity is represented by a feature vector constructed from variations in shape and motion features for a set of frames. A support vector machine is used to classify fall and non-fall activities. Experiments on three different datasets show the effectiveness of our proposed method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink