MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202631069598 A) filed by National Institute Of Technology Rourkela Nit Rourkela on June 03, 2026, for Deep Learning Technique Based Automated Neurodegenerative Disorder Detection System Using Human Gait Analysis.
Inventors include Ari, Dr. Samit; Jharbade, Mr. Piyush; and Junaid, Mr. Mohammad Iman.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: The present invention relates to a computer-implemented system (100) for automated detection of neurodegenerative disorders based on human gait analysis. The system (100) comprises at least one RGB camera configured to capture real-time video of a subject’s walking sequence within an indoor environment, a processing module coupled with a memory storing executable instructions, a preprocessing module configured to decompose captured video into frames, and generate binary silhouette representation frames of the subject, a windowing and aggregation module configured to construct sequences of silhouette frames representing at least one gait cycle and generate a GEI from the aggregated frames, a MMCNN configured to receive at least two silhouette frames as separate input modalities, extract spatial and temporal gait features through parallel convolutional streams, fuse extracted features by using a feature refinement module, and classify the gait pattern into one or more neurodegenerative disorder classes by using a SoftMax classifier.
Disclaimer: Curated by HT Syndication.
