Paper Title
Satellite Based Aircraft Detection Levering Inceptionv3, Transfer Learning and Functional API

Abstract
The challenge of enhancing aircraft detection fast and accurately in pictures from the air is tackled in this paper. Our suggested approach is to utilise the InceptionV3 architecture along with functional API and transfer learning to develop an alternative approach that addresses the drawbacks of the existing technique, which combines VGG-16 with a Bidirectional LSTM network. With the assistance of InceptionV3, which is popular for its efficacy and productivity in performing image recognition tasks, we hope to substantially boost the speed of computation as well as detection accuracy. Our proposed approach exhibits improved accuracy through extensive experimentation and evaluation using standard metrics, providing a promising alternative for improving aircraft detection in surveillance aircraft applications and with this model we secured a high accuracy of 96%. Keywords - Satellite-based aircraft detection , InceptionV3, Transfer learning , Functional API, VGG-16 Architecture Bidirectional LSTM , Aerial-Surveillance, Accuracy, Speed.