• Mahadeva Prasad H M
• Vivek Gautam
• Tariq Anjum
• Pulkit Yadav
• Syed Nawaz

Terrain classification plays a crucial role in various applications ranging from environmental monitoring to urban planning. In this study, we propose a terrain classification framework utilizing the UNET architecture, a convolutional neural network (CNN) commonly employed for image segmentation tasks. The proposed framework involves preprocessing the input data by resizing it into a standardized format of 256x256 pixels to ensure consistency and facilitate efficient processing. Subsequently, the UNET model is trained on the preprocessed data to learn discriminative features representative of different terrain types. The trained model is capable of classifying terrain into seven distinct classes: water, hill, forest, grassland, desert, mountain, and tundra. Experimental results demonstrate the effectiveness of the proposed approach in accurately categorizing diverse terrain types, showcasing its potential for applications such as land cover mapping, environmental assessment, and natural resource management. The UNET-based terrain classification framework offers a robust and scalable solution for analyzing and understanding Earth's complex landscapes, contributing to informed decision-making and sustainable development initiatives.

Terrain classification, UNET architecture, Convolutional neural networks (CNN), Deep learning, Image segmentation, Remote sensing, Geospatial analysis, Environmental monitoring, Land cover mapping, Natural resource management

"CNN BASED TERRAIN RECOGNITION TERRAIN CLASSIFICATION USING U-NET", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.385-390, May-2024, Available :http://www.jetir.org/papers/JETIRGG06061.pdf

"CNN BASED TERRAIN RECOGNITION TERRAIN CLASSIFICATION USING U-NET", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. pp385-390, May-2024, Available at : http://www.jetir.org/papers/JETIRGG06061.pdf