A Deep Learning Model for YOLOv9-based Human Abnormal Activity Detection: Violence and Non-Violence Classification
Abnormal activity detection is crucial for video surveillance and security systems, aiming to identify behaviors that deviate from normal patterns and may indicate threats or incidents such as theft, vandalism, accidents, and aggression. Timely recognition of these activities enhances public safety...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Iran University of Science and Technology
2024-11-01
|
| Series: | Iranian Journal of Electrical and Electronic Engineering |
| Subjects: | |
| Online Access: | http://ijeee.iust.ac.ir/article-1-3433-en.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841551017347383296 |
|---|---|
| author | 𝐒𝐢𝐫𝐚𝐣𝐮𝐬 𝐒𝐚𝐥𝐞𝐡𝐢𝐧 Shakila Rahman 𝐌𝐨𝐡𝐚𝐦𝐦𝐚𝐝 𝐍𝐮𝐫 𝐀𝐡𝐦𝐚𝐝 𝐀𝐬𝐢𝐟 𝐌𝐨𝐡𝐚𝐦𝐦𝐚𝐝 𝐁𝐢𝐧 𝐇𝐚𝐫𝐮𝐧 JIA UDDIN |
| author_facet | 𝐒𝐢𝐫𝐚𝐣𝐮𝐬 𝐒𝐚𝐥𝐞𝐡𝐢𝐧 Shakila Rahman 𝐌𝐨𝐡𝐚𝐦𝐦𝐚𝐝 𝐍𝐮𝐫 𝐀𝐡𝐦𝐚𝐝 𝐀𝐬𝐢𝐟 𝐌𝐨𝐡𝐚𝐦𝐦𝐚𝐝 𝐁𝐢𝐧 𝐇𝐚𝐫𝐮𝐧 JIA UDDIN |
| author_sort | 𝐒𝐢𝐫𝐚𝐣𝐮𝐬 𝐒𝐚𝐥𝐞𝐡𝐢𝐧 |
| collection | DOAJ |
| description | Abnormal activity detection is crucial for video surveillance and security systems, aiming to identify behaviors that deviate from normal patterns and may indicate threats or incidents such as theft, vandalism, accidents, and aggression. Timely recognition of these activities enhances public safety across various environments, including transportation hubs, public spaces, workplaces, and homes. In this study, we focus on detecting violent and non-violent activities of humans using a YOLOv9-based deep learning model considering the above issues. A diverse dataset has been built of 9,341 images from various platforms, and then the dataset has been pre-processed, i.e., augmentation, resizing, and annotating. After pre-processing, the proposed model has been trained which demonstrated strong performance, achieving an F1 score of 95% during training for 150 epochs. It was also trained for 200 epochs, but early stopping was applied at 148 epochs as there was no significant improvement in the results. Finally, the results of the YOLOv9-based model have been analyzed with other baseline models (YOLOv5, YOLOv7, YOLOv8, and YOLOv10) and it performed better compared with others. |
| format | Article |
| id | doaj-art-be850f6491a946b19a5a3da3fe5979db |
| institution | Kabale University |
| issn | 1735-2827 2383-3890 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Iran University of Science and Technology |
| record_format | Article |
| series | Iranian Journal of Electrical and Electronic Engineering |
| spelling | doaj-art-be850f6491a946b19a5a3da3fe5979db2025-01-09T18:47:15ZengIran University of Science and TechnologyIranian Journal of Electrical and Electronic Engineering1735-28272383-38902024-11-01204102114A Deep Learning Model for YOLOv9-based Human Abnormal Activity Detection: Violence and Non-Violence Classification𝐒𝐢𝐫𝐚𝐣𝐮𝐬 𝐒𝐚𝐥𝐞𝐡𝐢𝐧0Shakila Rahman1𝐌𝐨𝐡𝐚𝐦𝐦𝐚𝐝 𝐍𝐮𝐫2𝐀𝐡𝐦𝐚𝐝 𝐀𝐬𝐢𝐟3𝐌𝐨𝐡𝐚𝐦𝐦𝐚𝐝 𝐁𝐢𝐧 𝐇𝐚𝐫𝐮𝐧4JIA UDDIN5 American International University, Bangladesh American International University, Bangladesh American International University, Bangladesh American International University, Bangladesh American International University, Bangladesh Woosong University Abnormal activity detection is crucial for video surveillance and security systems, aiming to identify behaviors that deviate from normal patterns and may indicate threats or incidents such as theft, vandalism, accidents, and aggression. Timely recognition of these activities enhances public safety across various environments, including transportation hubs, public spaces, workplaces, and homes. In this study, we focus on detecting violent and non-violent activities of humans using a YOLOv9-based deep learning model considering the above issues. A diverse dataset has been built of 9,341 images from various platforms, and then the dataset has been pre-processed, i.e., augmentation, resizing, and annotating. After pre-processing, the proposed model has been trained which demonstrated strong performance, achieving an F1 score of 95% during training for 150 epochs. It was also trained for 200 epochs, but early stopping was applied at 148 epochs as there was no significant improvement in the results. Finally, the results of the YOLOv9-based model have been analyzed with other baseline models (YOLOv5, YOLOv7, YOLOv8, and YOLOv10) and it performed better compared with others.http://ijeee.iust.ac.ir/article-1-3433-en.pdfabnormal activity detectiondeep learningyolov9-based modelreal-time object detection |
| spellingShingle | 𝐒𝐢𝐫𝐚𝐣𝐮𝐬 𝐒𝐚𝐥𝐞𝐡𝐢𝐧 Shakila Rahman 𝐌𝐨𝐡𝐚𝐦𝐦𝐚𝐝 𝐍𝐮𝐫 𝐀𝐡𝐦𝐚𝐝 𝐀𝐬𝐢𝐟 𝐌𝐨𝐡𝐚𝐦𝐦𝐚𝐝 𝐁𝐢𝐧 𝐇𝐚𝐫𝐮𝐧 JIA UDDIN A Deep Learning Model for YOLOv9-based Human Abnormal Activity Detection: Violence and Non-Violence Classification Iranian Journal of Electrical and Electronic Engineering abnormal activity detection deep learning yolov9-based model real-time object detection |
| title | A Deep Learning Model for YOLOv9-based Human Abnormal Activity Detection: Violence and Non-Violence Classification |
| title_full | A Deep Learning Model for YOLOv9-based Human Abnormal Activity Detection: Violence and Non-Violence Classification |
| title_fullStr | A Deep Learning Model for YOLOv9-based Human Abnormal Activity Detection: Violence and Non-Violence Classification |
| title_full_unstemmed | A Deep Learning Model for YOLOv9-based Human Abnormal Activity Detection: Violence and Non-Violence Classification |
| title_short | A Deep Learning Model for YOLOv9-based Human Abnormal Activity Detection: Violence and Non-Violence Classification |
| title_sort | deep learning model for yolov9 based human abnormal activity detection violence and non violence classification |
| topic | abnormal activity detection deep learning yolov9-based model real-time object detection |
| url | http://ijeee.iust.ac.ir/article-1-3433-en.pdf |
| work_keys_str_mv | AT sirajussalehin adeeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification AT shakilarahman adeeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification AT mohammadnur adeeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification AT ahmadasif adeeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification AT mohammadbinharun adeeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification AT jiauddin adeeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification AT sirajussalehin deeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification AT shakilarahman deeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification AT mohammadnur deeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification AT ahmadasif deeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification AT mohammadbinharun deeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification AT jiauddin deeplearningmodelforyolov9basedhumanabnormalactivitydetectionviolenceandnonviolenceclassification |