MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541123164 A) filed by B V Raju Institute Of Technology, Narsapur, Telangana, on Dec. 6, 2025, for 'intelligent remote sensing classification model integrating vgg16, ensemble classifiers, and lstm for multi-spectral analysis.'
Inventor(s) include Mastan Mohammed Meera Durga; Kenchali Shivaji Rao; Rowthu Neelima; Indumathi V; Nagaram Ramesh; Sriharsha Vikruthi; and J. Manikandan.
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: "This paper proposes an improvised model to classify Remotely Sensed Satellite images by extracting image features using Visual Geometry Group 16 which are then fine-tuned by Support Vector Machine (SVM), Random Forest (RF) and Extreme Gradient Boosting(GB) algorithms and are provided as an input to Long Short-Term Memory classifier. Implementing this approach gives us the lever- age of computing more than 30,000 images by using this algorithm at a faster rate using a lower specification CPU and GPU. Unlike any traditional approach of extracting the features using Visual Geometry Group 16 and then classifying the images based on the features, our proposed approach includes stacking up the features along with the predicted features using the three classifiers. Advantage of the proposed model when compared to the traditional and other referred proposed models, the accuracy has been increased by 4.66%. By just not limiting our model to the terminal-based application a Graphic User Interface was also designed to accept an image from the user and classify it into one of the ten classes of our EuroSAT dataset capabilities."
Disclaimer: Curated by HT Syndication.
