Research on Children's Fall Detection by Characteristic Operator
| Autor: | HuaiJun Wang, Facun Zhang, Lijun Cui |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Computer science
business.industry Value (computer science) 020206 networking & telecommunications Pattern recognition 02 engineering and technology Machine learning computer.software_genre Svm classifier Operator (computer programming) Character (mathematics) Feature (computer vision) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Fall detection Artificial intelligence Abnormality Representation (mathematics) business computer |
| Zdroj: | Proceedings of the International Conference on Advances in Image Processing. |
| DOI: | 10.1145/3133264.3133268 |
| Popis: | Aiming at the problem of abnormal behavior detection in kindergarten video surveillance, adetection algorithm based on feature operator is proposed. By analyzing and researching the behavior of young child in the video, the description method of the specific behavior of the children is defined, and two feature operators are defined as the representation of the behavioral character in the video. These features are used as the input of the SVM classifier, which trains the inputs and establishes the abnormal behavior detection model. The algorithm in this paper has a certain practical value and a good performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|