MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202611059500 A) filed by Chandigarh University on May 09, 2026, for Adaptive Multimodal Real-Time Human Detection And Rescue Mapping System For Enclosed Disaster Environments.
Inventors include Ujjwal Mishra; Dr. Preeti Khera; and Aashutosh Kumar Choudhary.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: The present invention discloses an adaptive, AI-powered, edge-deployable system for real-time human detection and rescue mapping in enclosed disaster environments such as fires, gas leaks, or structural collapses. The system integrates multiple sensing modalities visual, thermal, ultrasonic, and beamformed acoustic whose data are fused through a Bayesian dynamic confidence weighting model that adaptively adjusts sensor importance based on environmental conditions. The system segments indoor spaces into micro-zones and computes a Rescue Priority Index (RPI) for each zone, guiding first responders toward critical rescue areas. Operating entirely on edge hardware, the system maintains low-latency, offline functionality while autonomously recalibrating to variations in smoke, temperature, and noise. It further detects non-verbal acoustic cues like breathing or coughing and automatically manages sensor failover and reintegration, ensuring continuous, environment-resilient operation for life-saving missions.
Disclaimer: Curated by HT Syndication.
