Military Based Object Detection in Satellite Imagery by Optimising YOLOv8

Singh, S and Ratna, GN (2024) Military Based Object Detection in Satellite Imagery by Optimising YOLOv8. In: 2024 IEEE Space, Aerospace and Defence Conference, SPACE 2024, 22 July 2024 through 23 July 2024, Bangalore, pp. 165-168.

PDF IEEE_Spa_Aer_and_Def_Con_SPACE_2024.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Identifying objects from satellite images can be challenging because of their varying visible qualities, hampering their value in some scenarios such as urban planning or responses to emergencies. The ability to detect vehicles and other elements in satellite imagery can give vital information on latest military developments of adversaries, especially when planning for military operations. This study addresses the detection of military objects with more accuracy by studying YOLOv8 with optimized YOLOv8 architecture improving real-time object detection capabilities. © 2024 IEEE.

Item Type:	Conference Paper
Publication:	2024 IEEE Space, Aerospace and Defence Conference, SPACE 2024
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to the publishers.
Keywords:	Military mapping; Military photography; Military satellites; Object detection; Object tracking; Urban planning, Class-specific variation; Dataset augmentation; Map50; Military object detection; Military objects; Objects detection; Satellite object detection; Xview dataset; YOLOv8, Satellite imagery
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	16 Oct 2024 11:21
Last Modified:	16 Oct 2024 11:21
URI:	http://eprints.iisc.ac.in/id/eprint/86563

Actions (login required)

View Item