Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Precise visual identification of aircraft by manufac- turer is an important aspect in ground-based air traffic control and defense surveillance, where in many situations visual confirmation is necessary due to incomplete, corrupted, or missing ADS-B data. This work proposes a deep learning-driven vision pipeline that combines object detection and fine-grained image classification for identifying aircraft in both images and videos based on manufacturer and model variant. A new multi-class dataset, flmanufacturers, was established for commercial and defense aircraft types, including Airbus, Boeing, ATR, among others. Such images were then subjected to systematic preprocessing, normalization, and augmentation to improve the generalization of the model for changing lighting conditions and angles of view. The proposed system combines a YOLOv8 model with fast and accurate aircraft detection and a fine-tuned ResNet18 classifier that recognizes aircraft manufacturers. Training was done on GPU- enabled systems for faster convergence and real-time inference. It obtained a training accuracy of 65% with 20–25 FPS during video inference, hence making it feasible in the real world. These are modularly designed, so scaling to more aircraft categories or fusing with flight metadata for multimodal recognition is possible.
Keywords:
Transfer learning, aircraft identification, ResNet-18, YOLOv8, video inspection, ATC validation.
Cite Article:
"Precise Aircraft Recognition", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 11, page no.b707-b712, November-2025, Available :http://www.ijrti.org/papers/IJRTI2511177.pdf
Downloads:
000205
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator