Treffer: 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 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. [ABSTRACT FROM AUTHOR]

المقال يناقش تطوير نموذج تعلم عميق يعتمد على YOLOv9 لاكتشاف الأنشطة غير الطبيعية للبشر، مع التركيز على تصنيف السلوكيات العنيفة وغير العنيفة. باستخدام مجموعة بيانات مخصصة تتكون من 9,341 صورة، حقق النموذج نتيجة F1 مثيرة للإعجاب بلغت 95%، متفوقًا على الإصدارات السابقة مثل YOLOv5 وYOLOv7 وYOLOv8 من حيث الدقة والكفاءة في الكشف عن الأجسام في الوقت الحقيقي. بينما يظهر نموذج YOLOv9 قدرات قوية في التمييز بين أنواع الأفعال، يشير البحث إلى الحاجة إلى مزيد من التحسين لتقليل معدلات التصنيف الخاطئ. بالإضافة إلى ذلك، يسلط المقال الضوء على مساهمات الباحثين في الجامعة الأمريكية الدولية في بنغلاديش (AIUB) في تطبيقات مختلفة للتعلم العميق والتعلم الآلي، إلى جانب ملفات تعريف للخريجين الجدد وأعضاء هيئة التدريس. [Extracted from the article]

Copyright of Iranian Journal of Electrical & Electronic Engineering is the property of Iran University of Science & Technology and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)