Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196838,
        author = {Ch Roshika and K Mamatha and Vijayalaxmi and Sk Tehazeeb and M Sandhya and Vijayalaxmi},
        title = {Urban Atlas: Satellite Imagery for Urban Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {5414-5418},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196838},
        abstract = {India’s growth has been rapid, and we have seen a rapid shift in land use. Different taxonomies, such as houses, buildings, forests, roads, and public places, have changed a lot. Because of this rapid expansion, it is very important for us to find a good map structure and to watch and study these changes. So we came up with an idea to understand how rapidly growing cities are spreading and making better places. Our project UrbanAtlas, which is a smart system that can automatically recognise different taxonomies in a picture and make better decisions for our future. To differentiate them, we have used the YOLOv6 Segmentation model, which will separate the labels accurately based on 2 properties: threshold and overshadow. We have trained our model using LoveDa dataset, which has more than 45k pictures and contains both rural and urban pictures. We prepared our data, converted it into the appropriate format for building and testing the model, and then used Streamlit as a web platform to present the model’s results. When tested, we can see some key metrics like precision, recall, validation percentage, and f1-score. this metrics help us determine how much our trained data set has learned.},
        keywords = {Key Terms: Urban growth, Semantic segmenta- tion, YOLOv6 segmentation, Threshold and overshadow proper- ties, Deep learning, Automated monitoring},
        month = {April},
        }