Tools
Tools
Kundeti, Lakshmi Narasimha (2024) Redefining Public Safety: A Comparative Analysis of RTDETR and YOLOv8 – Unveiling The Future of Real-Time Handgun Detection. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (4MB) | Preview |
Abstract
This study raises a very fundamental challenge: the improvement of public safety by integrating advanced handgun detection systems. It concerns a comparative analysis between two leading technologies in object detection techniques, which are RT-DETR and YOLOv8. The research targets proving which model has better performance when considering accuracy, robustness, and adaptability concerning real-time handgun detection in public spaces.
Models implemented using RT-DETR and YOLOv8 were tuned on a comprehensive dataset of 15,579 handgun images with heavy data augmentation applied. Results are measured in terms of mAP, precision, and recall for different classes. This was achieved through rigorous tuning of hyperparameters by running the experiment several times to squeeze out better performance from the model.
The summary of key results shows that RT-DETR performed very marginally better when it came to peak performance on all metrics: mAP50-95, 0.728; precision, 0.940; recall, 0.883; while YOLOv8 had an mAP50-95 of 0.7073, precision of 0.9010, and recall of 0.8560. However, YOLOv8 proved to be steadier and more robust among different hyperparameter settings, hence it gives better adaptability to diverge operational conditions.
This comparative analysis thus illustrates the contribution of effective and reliable AI-driven security solutions and further provides insights to enhance academic research as well as practical applications of public safety and surveillance systems.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Chikkankod, Arjun UNSPECIFIED |
| Subjects: | H Social Sciences > HV Social pathology. Social and public welfare > Criminology > Crimes and Offences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence > Computer vision Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence > Computer vision |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 20 Aug 2025 09:47 |
| Last Modified: | 20 Aug 2025 09:47 |
| URI: | https://norma.ncirl.ie/id/eprint/8583 |
Actions (login required)
 |
View Item |