• A. Divya Krishna Sree
• K. Durga Ganga Rao

Remote sensing (RS) images are valuable data sources to measure and observe detailed structures on the earth’s surface. As the amount of remote sensing images drastically increases, it becomes more challenging to understand and analyze such a huge data set. Hence, the classification of remote sensing image scenes has drawn more attention in academic studies and industrial uses. However, Advanced computer vision, has made significant progress in classifying millions of sample images. In recent years, Deep learning algorithms have been rapidly developed and widely used, Scene classification uses this field as well and has achieved desirable results. In this work, the application of scene classification using different types of deep learning models on UCMerced land use data set and made performance comparisons among various deep learning models like Convolution neural networks (CNN), GoogLeNet, VGG-16, EfficientNet-B0 and CNN model with recurrent Long short term memory (LSTM) network. It is observed that GoogLeNet and VGG-16 show better accuracy for scene classification upon the UCMerced dataset.

Remote sensing scenes, Deep learning, convolution neural networks (CNN), GoogleNet, VGG16, EfficientNet-B0, long short-term memory (LSTM)

"REMOTE SENSING SCENE CLASSIFICATION USING DEEP LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 11, page no.a147-a153, November-2022, Available :http://www.jetir.org/papers/JETIR2211017.pdf

"REMOTE SENSING SCENE CLASSIFICATION USING DEEP LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 11, page no. ppa147-a153, November-2022, Available at : http://www.jetir.org/papers/JETIR2211017.pdf