MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122123 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'hybrid deep learning system for hyperspectral urban landscape change detection.'
Inventor(s) include Dr. Annapurna Jonnalagadda; and Karan Jiwan Mukherjee.
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 hybrid deep learning system for hyperspectral urban landscape change detection. The system includes a three-dimensional convolutional neural network module configured to extract spectral-spatial features from hyperspectral image data by processing volumetric data across spatial and spectral dimensions simultaneously, a vision transformer module configured to capture contextual relationships within the hyperspectral image data using self-attention mechanisms, a feature fusion module configured to combine the spectral-spatial features from the three-dimensional convolutional neural network module with the contextual features from the vision transformer module, and a classification module configured to process the combined features and generate change detection maps indicating areas of urban landscape change. The system processes input hyperspectral cubes through preprocessing operations, extracts features using the dual-branch architecture combining 3D-CNN (1) and Transformer (1) modules, performs feature fusion (1), and generates output change maps through the classification stage (1)."
Disclaimer: Curated by HT Syndication.
