Defense Assets Classification Using Deep Learning

Author(s)	Ms. Sukanya Chikmath, Dr. Rashmi CR, Prof. Dr. Shantala CP
Country	India
Abstract	Detecting military assets from images is challenging because of lighting variations, occlusion, and complex object appearances. This work applies the YOLOv8 model for automated military asset detection using the Kaggle Military Assets Dataset containing 26,315 images across twelve classes. Following image pre-processing and augmentation, the trained model produced a precision of 62.44%, recall of 50.01%, F1-score of 55.54%, and mAP@0.5 value of 50.50% during testing. The results show that YOLOv8 can support real-time defense surveillance, while improvements are still required to reduce missed detections.
Keywords	Military Asset Detection, YOLOv8 model, Deep Learning Technique, Object Detection System, Defense Surveillance, Computer Vision.
Field	Engineering
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-26

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research