• N.Bharanikumar
• P. Dhanalakshmi

Presently, the domain of unmanned aerial vehicles (UAVs) has gained significant interest in several application areas owing to its characteristics of inexpensive, versatile, and autonomous. Robust remote sensing scene classification process find useful in several UAV based surveillance systems like forest fire detection, which facilitating object detection, tracking process and drastically improves the result of visual surveillance. The recently developed deep learning (DL) models can be employed for automated remote sensing scene classification. This paper presents an effective Quasi Oppositional based Artificial Fish Swarm Optimization Algorithm with MobileNet(QAFSOMN) model for aerial image classification. The presented QAFSOMN model uses MobileNet based feature extraction technique, which is further optimized by the QAFSO algorithm to optimally select the hyperparameters. In addition, two classification models such as gradient boosting tree (GBT) and random forest (RF) are used to determine the different classes of remote sensing images. The utilization of the QAFSO algorithm paves a way of achieving higher detection performance compared to the existing methods.The detailed experimental validation process on remote sensing imagery dataset pointed out that the QAFSOMN-GBT and QAFSOMN-RF models have obtained a maximum accuracy of 0.9871 and 0.9784.

Deep learning, Machine learning, Hyperparameter tuning, Remote sensing classification, Feature extraction

"Quasi Oppositional based Artificial Fish Swarm Optimization Algorithm with Mobile Net for Remote Sensing Image Scene Classification", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 6, page no.e501-e520, June-2022, Available :http://www.jetir.org/papers/JETIR2206459.pdf

"Quasi Oppositional based Artificial Fish Swarm Optimization Algorithm with Mobile Net for Remote Sensing Image Scene Classification", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 6, page no. ppe501-e520, June-2022, Available at : http://www.jetir.org/papers/JETIR2206459.pdf