Abstract :

The Rapid Growth Of High-resolution Satellite Imaging And Artificial Intelligence Has Enabled Automated Monitoring Of Large Geographical Areas For Aircraft Detection And Surveillance. This Paper Presents An Intelligent System For Detecting And Counting Military Aircraft From Satellite Imagery Using Advanced Deeplearning Techniques. The Proposed Framework Employs The YOLOv8 Object Detection Model To Identify Aircraft Based On Their Visual Characteristics, Spatial Patterns, And Appearance In Complex Remotesensing Scenes. The System Performs Image Preprocessing To Improve Input Quality And Applies Object Detection To Localize Aircraft Using Bounding Boxes And Confidence Scores. Detected Aircraft Are Automatically Counted To Provide An Efficient Estimation Of Aircraft Presence Within The Analyzed Imagery. A Flask-based Application Provides Secure User Authentication, Image Upload, And Real-time Video-based Detection Functionalities Through An Interactive Interface. The Framework Is Designed To Handle Variations In Aircraft Scale, Orientation, Background Complexity, And Image Conditions. In Addition To Detection And Counting, The System Supports Continuous Monitoring And Provides Visual Outputs That Assist Users In Interpreting Detection Results. The Proposed Approach Aims To Reduce Manual Inspection Effort While Improving The Speed, Consistency, And Scalability Of Aircraft Monitoring From Satellite Imagery. The Framework Can Support Applications In Aerial Surveillance, Strategic Monitoring, Border Observation, And Defense-related Image Analysis. Overall, The Proposed System Provides An Intelligent Computer-vision Solution For Automated Aircraft Detection, Localization, And Counting Using Modern Deep-learning Techniques.

Published:

21-9-2026

Issue:

Vol. 26 No. 9 (2026)

Page Nos:

291 - 296

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite