Intellectual Property India Publishes Patent Application for 'High Resolution Building Footprint Maps For Disaster Management And Urban Planning Using Machine Learning' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122084 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'high resolution building footprint maps for disaster management and urban planning using machine learning.'

Inventor(s) include Dr. Jabanjalin Hilda J; Dr. Surendar M; Mr. A Anirudh Bharadwaj; and Mr. Sayan Mitra.

The application for the patent was published on Jan. 2, under issue no. 01/2026.

According to the abstract released by the Intellectual Property India: "The present disclosure provides a system for generating high-resolution building footprint maps from satellite imagery. The system includes a satellite imagery input module (FIG. 1) configured to receive satellite images, a YOLOv8-based detection module configured to identify and localize buildings within the satellite imagery using bounding box coordinates, a YOLOv8-based segmentation module configured to generate pixel-level segmentation masks for buildings and land cover types, and an output processing module configured to generate building footprint maps from detection results and segmentation results. The YOLOv8-based detection module includes a custom neural network architecture having a backbone network with convolutional layers and a detection head configured to output the bounding box coordinates and confidence scores for detected buildings. The system processes input images simultaneously through the detection module and segmentation module to generate combined outputs for disaster management and urban planning applications."

Disclaimer: Curated by HT Syndication.