Stick and Machete Detection in Crisis-Affected Areas using Yolov8
Keywords:
Object Detection, YOLOv8, Crisis-Affected Regions, Cameroon Security, SurveillanceSynopsis
This is a Chapter in:
Book:
Intelligent and Sustainable Solutions
Print ISBN 978-1-6692-0012-3
Online ISBN 978-1-6692-0011-6
Series:
Chronicle of Computing
Chapter Abstract [Under Revision]:
Enhancing security measures in the crisis-affected regions of Cameroon, which have faced prolonged unrest over the years, is critically important. Detecting potentially threatening objects like sticks and machetes within dense crowds can significantly improve surveillance and safety amidst ongoing challenges. These regions require advanced security solutions to address persistent threats faced by the local population. This study develops a detection model based on the You Only Look Once (YOLOv8) architecture to accurately identify and segment sticks and machetes in these crisis-affected areas. By assembling a diverse dataset that captures various scenarios, orientations, and lighting conditions, the model learns to recognize the distinctive features of these objects. Data augmentation techniques further enhance the model’s adaptability to new circumstances, ensuring reliable performance in real-world applications. Through rigorous training, the YOLOv8 model achieved a mean Average Precision (mAP) of 0.604 for stick detection and 0.618 for machete detection, marking a promising start for this type of detection. Fine-tuning the model on a region-specific dataset was pivotal for improving its accuracy and effectiveness in identifying these objects within crowds. This research highlights the potential impact of leveraging the YOLOv8 model for object detection in regions plagued by persistent crises. By enhancing security measures through advanced technology, this study aims to contribute to ongoing efforts to safeguard communities and restore stability in these troubled areas.
About this Paper
Cite this paper as:
Nkamgam L., Essimbi Zobo B., Mbous Ikong J., Onanena Guelan R., Videme Bossou O.(2025) Stick and Machete Detection in Crisis-Affected Areas using Yolov8. In: Tiako P.F. (ed) Intelligent and Sustainable Solutions. Chronicle of Computing. OkIP. CAIF25#10. https://doi.org/10.55432/978-1-6692-0011-6_7
Presented at:
The 2025 OkIP International Conference on Artificial Intelligence Frontiers (CAIF) in Oklahoma City, Oklahoma, USA, and Online, on April 2, 2025
Contact:
Laurent Nkamgam
nkamgans@gmail.com
References
[Under Revision]:
Yan, W; Kehua, Z.; Ling, W; Lintong, W. Improved YOLOv8 Algorithm for Rail Surface Defect Detection, in IEEE Access, vol. 12, pp. 44984- 44997, 2024.
Lou, H.; Duan, X.; Guo, J.; Liu, H.; Gu, J.; Bi, L.; Chen, H. DCYOLOv8: Small-Size Object Detection Algorithm Based on Camera Sensor. Electronics 2023, 12, 2323.
Shaoqing, R; Kaiming, H; Ross, G; Jian, S. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 06, pp.1137-1149, 2017.
Roberto, O.; Siham, T.; Francisco, H. Automatic handgun detection alarm in videos using deep learning, Neurocomputing, Volume 275, 2018, Pages 66-72, ISSN 0925 2312, https://doi.org/10.1016/j.neucom.2017.05.012.
Zhou, X.; Gong, W.; Wen, F.; Fengtong, D. Application of deep learning in object detection. 2017 IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS), 631-634.
Alaqil, R.; Alhumaidi, B.; Alotaibi, R.; Alsuhaibani, J.; Alnasser, R.; Benhidour, H. (2020). Automatic Gun Detection from Images Using Faster R-CNN. 10.1109/SMART-TECH49988.2020.00045.
Suryam, S.; Swapnil N. A System for Vehicle Detection using Machine Learning. International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064.
Chandan, G.; Jain, A.; Jain, Ha.; Mohana. Real Time Object Detection and Tracking Using Deep Learning and OpenCV. Proceedings of the International Conference on Inventive Research in Computing Applications.1305-1308. 10.1109.
Raghunandan, A.; Mohana, R, P.; Ravish, H, V. Object Detection Algorithms for Video Surveillance Applications. 2018 International Conference on Communication and Signal Processing (ICCSP), 0563-0568.
Rodrigo, F.; Neto, A. Firearm Detection using Convolutional Neural Networks. DOI: 10.5220/0007397707070714 In Proceedings of the 11th International Conference on Agents and Artificial Intelligence (ICAART 2019),707-714.
Mohana.; Ravish, A. Object Detection and Tracking using Deep Learning and Artificial Intelligence for Video Surveillance Applications. International Journal of Advanced Computer Science and Applications, Vol. 10, No. 12, 2019.
Suxia, Cui.; Yu, Z.; Yonghui, W.; Lujun, Z. Fish DetectionUsing Deep Learning. Applied Computational Intelligence and Soft Computing. Volume 2020, Article ID 3738108, 13 pages https://doi.org/10.1155/2020/3738108.
Jeberson, R.; Senduru, S. Object Detection in Live Streaming Video Using Deep Learning Approach. IOP Conference Series: Materials Science and Engineering, 1020.
Priyal, J.; Hitiksha, p.; Nivedita, R. Real-Time Object Detection using TensorFlow. International Research Journal of Engineering and Technology (IRJET). Volume: 07 Issue: 08I Aug 2020
Narejo, S.; Pandey, B.; Esenarro, V.; Rodriguez, C.; Anjum, M. Weapon Detection Using YOLO V3 for Smart Surveillance System. Mathematical Problems in Engineering. 2021. 1-9. 10.1155/2021/9975700.
Jamilu, S.; Majeed, H. Weapon Detection for Smart Surveillance System using YOLOV6. Global Journal of Research in Humanities and Cultural Studies ISSN: 2583-2670 (Online) Volume 02— Issue 05 — Sept.-Oct. 2022
Liyao, L. Improved YOLOv8 Detection Algorithm in X-ray Contraband. Advances in Artificial Intelligence and Machine Learning. 2023:3(3):72.
Armstrong, A.; Bin, W.; Ulas, B.; Yaw, A. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada, 2023,pp.5350-5358, Doi: 10.1109/CVPRW59228.2023.00564.
Motwani, N.; Soumya, S. Human Activities Detection using Deep Learning Technique- YOLOv8. ITM Web of Conferences. 56. 10.1051/itmconf/ 20235603003.
Nkamgan,N,L,S. Stick-Detection-Segmentation Dataset.Roboflow Universe.Information on https://universe.roboflow.com/nkamgan/stick_detection_segmentation.
Nkamgan,N,L,S. Machete-detection-segmentation Dataset.Roboflow Universe.Information on https://universe.roboflow.com/nkamgan/machete_detection_segmentation.
