Remote Sensing Aircraft Classification Harnessing Deep Learning Advancements

Remote sensing imagery is challenging to analyze due to its diverse sources, object image variability and contextual backgrounds. In current era, Aviation Industry is continuously progressing from specific domain of aircraft classification to improving in its safety measures, maintenance procedures and diverse flight operations by utilizing the potential of satellite imagery and Deep Learning methods. This paper highlights and explores the potential of Transfer Learning with state-of-the-art Deep Learning architectures on publicly available Multi Type Aircraft Remote Sensing Imagery datasets. In the same context, our experiments and training mechanism on the state-of-the-art models, like Vision Transformers, ResNet50v2, EfficientNetB0 and InceptionNetV3 outperforms earlier methods on the benchmark remote sensing military aircraft dataset. Our experiments on mentioned Deep learning models yielded, 95%, 93.4%, 92% and 80% classification accuracy due to advance architecture design and fine tuning techniques by allowing them to capture more intricate features and patterns of multifaceted military platforms. This research will provide a valuable resource in the aviation industry in the perspective of aircraft recognition domain by utilizing the power of advance Deep Learning methods to handle the complexity and diversity of remote sensing imagery.