Intellectual Property India Publishes Patent Application for 'System And Method For Real-Time Object Detection And Tracking In Maritime Surveillance Using Deep Learning' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122947 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'system and method for real-time object detection and tracking in maritime surveillance using deep learning.'

Inventor(s) include Gursimran Singh Bains.

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 real-time object detection and tracking in maritime surveillance. The system includes a data processing module configured to merge Ship Detection and Segmentation (SDS) and Unmanned Aerial Vehicle Detection and Tracking (UAVDT) datasets with Common Objects in Context (COCO) format standardization and apply augmentation techniques. The system further includes an object detection module comprising a Faster Region-based Convolutional Neural Network (Faster R-CNN) architecture with a ResNet-50 Feature Pyramid Network (FPN) backbone pre-trained on COCO dataset weights and fine-tuned on merged training data. The system also includes a tracking module implementing a Simple Online and Realtime Tracking (SORT) algorithm with Kalman filtering and Hungarian algorithm for data association, and a video processing module configured to capture and preprocess video frames from maritime surveillance sources."

Disclaimer: Curated by HT Syndication.