Intellectual Property India Publishes Patent Application for 'Lightweight Deep Learning Models For Urban Change Detection' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122934 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'lightweight deep learning models for urban change detection.'

Inventor(s) include Dr. Annapurna Jonnalagadda; and Thikkireddy Srikara Rao.

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 urban change detection including an image processing module configured to receive first and second temporal images of an urban area captured at different time periods and preprocess them by resizing to standardized dimensions and normalizing pixel values to 0-1 range, a feature extraction module including lightweight deep learning architecture selected from Vanilla CNN, U-Net, U-Net with ResNet backbone, Siamese Network with ResNet backbone, VGG with ResNet backbone, and Swin Transformer, configured to extract spatial features from the preprocessed temporal images, a change detection module configured to compute differences between extracted spatial features to identify areas of urban change, and an output module configured to generate a binary segmentation mask highlighting detected urban changes."

Disclaimer: Curated by HT Syndication.