MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641043182 A) filed by Cvr College Of Engineering, Hyderabad, Telangana, on April 4, for 'system and method for contactless heart rate monitoring using multi-stage deep feature fusion and adaptive attention-based recurrent neural network.'
Inventor(s) include Jyostna J; and M Santhoshi.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a system for contactless heart rate monitoring from facial video sequences using an optimized deep learning technique. The system consists of a video acquisition unit and a hybrid face detection module integrating transformer-based spatial modelling with real-time object detection with high accuracy of facial localization in varying illumination and motion conditions. A dual path feature extraction mechanism is utilized, in which a three-dimensional residual attention network is utilized to extract spatiotemporal features, and an RGB-DBN network is used to extract colour domain and hierarchical features. The extracted features are combined using a weighted feature fusion module. An ESGO algorithm is used to dynamically find the best fusion weights and hyperparameters to minimize the prediction error. The fused features are then fed to an attention-based LSTM network to predict the heart rate. This invention provides an automated, robust, and scalable solution for remote health care applications."
Disclaimer: Curated by HT Syndication.
