MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122620 A) filed by Malla Reddy (MR) Deemed to be University; Malla Reddy Vishwavidyapeeth; Malla Reddy University; Malla Reddy Engineering College For Women; and Malla Reddy College Of Engineering And Technology, Medchal-Malkajgiri, Telangana, on Dec. 5, 2025, for 'intelligent video analysis system for crowd density estimation.'
Inventor(s) include Dr. S. Mahipal; Dr. S. Marakatham; Dr. M. Narayanan; Dr. Yasaswini Vanapalli; and D. Chandra Sekhar Reddy.
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: "A smart video analytical system is created to approximate the crowd concentration and spatial arrangement with the help of computer vision and deep learning. Complete automation of image segmentation, object detection and spatial mapping are incorporated in the system to give real-time estimates of population gathering in the surveillance places like transportation hubs, stadiums and other public assemblies. The model uses adaptive neural networks that acquire the characteristics of the crowd across a variety of environmental and lighting circumstances, which remain stable when using the model in dynamic, high-scale settings. Video streams of fixed and mobile cameras are fed down a multi-stage pipeline which includes frame acquisition, background suppression, and feature detection. The deep learning sub-block identifies the human presence variant by trained convolutional neural network that is trained to take care of occlusion and motion over-lapping. The densities are then calculated as pixel-based feature aggregation followed by the spatial-temporal smoothing of the density to be able to reliably estimate crowd densities. A decision intelligent layer assesses changes of density, issues congestion alert and offers predictive ideas about the trends of crowd movement. It can be combined with surveillance and management platforms to implement automated control measures (e.g. route diversion or capacity optimization) using the framework. The model will run at minimal computational cost but the accuracy of real-time processing remains. Field tests show that it is a solid solution in terms of intelligent crowd management and safety analytics due to high detection accuracy, flexibility, and scalability."
Disclaimer: Curated by HT Syndication.
