By leveraging advanced AI models, teams at the University of Pennsylvania are aiming to bring cutting-edge automation to emergency response.

Meta AI's platform is a resource for artificial intelligence (AI) researchers, machine learning practitioners, and technology enthusiasts. Through articles, research papers, and technical discussions, Meta AI offers insights into AI algorithms, deep learning models, and neural network architectures. Readers can learn about AI applications in various domains, such as computer vision, natural language processing, and reinforcement learning. Additionally, Meta AI provides updates on the latest advancements in AI research, AI ethics, and AI governance to help readers stay informed and engaged in the rapidly evolving field of artificial intelligence.

AI at Meta

The PRONTO team at the University of Pennsylvania is using Meta's SAM 2 and DINO models in a DARPA-funded challenge to automate medical triage in mass casualty incidents. Their multi-robot system combines drones and ground robots with computer vision pipelines to detect and classify injuries without requiring labeled training data. DINO extracts visual features while Grounding DINO uses text prompts to identify wounds and blood. The system estimates heart rate, respiration, body pose, and wound presence, then presents findings to first responders via a mobile interface. Phase 2 of the three-year challenge concluded in October 2024, with Phase 3 set to incorporate Meta's latest model versions.

How DINO and SAM are Helping Modernize Essential Medical Triage Practices