Please use this identifier to cite or link to this item:
http://elar.urfu.ru/handle/10995/99844
Title: | Recognition of normal and abnormal human actions |
Authors: | Al-Saedi, Hamza Hussein |
Issue Date: | 2021 |
Publisher: | УрФУ |
Citation: | Al-Saedi Hamza Hussein. Recognition of normal and abnormal human actions / Hamza Hussein Al-Saedi. — Текст : электронный // Весенние дни науки : сборник докладов Международной конференции студентов и молодых ученых (Екатеринбург, 22–24 апреля 2021 г.). — Екатеринбург : УрФУ, 2021. — C. 333-335. |
Abstract: | This paper presents an intelligent framework video surveillance system in an academic environment that takes into account the security and emergency aspects. The system proposes an abnormal human activity classification by the detection motion algorithm based on the Gaussian mixture model (GMM) followed by the Fuzzy C-Means (FCM) segmentation algorithm. It combines HARRIS-SIFT algorithms together to extract features, and the Kalman Filter for tracking targets. Finally, the K-Nearest Neighbor (KNN) algorithm used for the classification of the activities that belong to three different datasets tested. The results show the efficiency of the system: the datasets have the accuracy ratio 97%, the detection ratio is %97, and the false alarm ratio is 4%. |
Keywords: | GAUSSIAN MIXTURE MODEL KALMAN FILTER WEIZMANN STANDARD DATASET KTH STANDARD DATASET |
URI: | http://elar.urfu.ru/handle/10995/99844 |
Conference name: | Международная конференция студентов и молодых ученых «Весенние дни науки» |
Conference date: | 22.04.2021-24.04.2021 |
ISBN: | 978-5-91256-519-9 |
Origin: | Весенние дни науки. — Екатеринбург, 2021 |
Appears in Collections: | Конференции, семинары, сборники |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
978-5-91256-519-9_2021_063.pdf | 305,59 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.