Publication
IMPACT: Integrated Multimodal Pipeline for Rapid Accident Causality Tracking (Student Abstract)
Vashu Chauhan; Avinash Anand; Manisha Luthra; Uélison Santos; Carsten Binnig; Rajiv Ratn Shah
In: Sven Koenig; Chad Jenkins; Matthew E. Taylor (Hrsg.). Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2026, Singapore, January 20-27, 2026. AAAI Conference on Artificial Intelligence (AAAI), Pages 41159-41161, AAAI Press, 2026.
Abstract
Traffic accidents pose a significant societal challenge, with
many fatalities being avoidable through timely emergency
response. We introduce IMPACT (Integrated Multimodal
Pipeline for Rapid Accident Causality Tracking), a scalable
AI framework designed for autonomous, rapid traffic incident
analysis using existing urban CCTV infrastructure. IMPACT
combines a low-latency CPU-based vision module for realtime
key-frame filtering (24 FPS) with the causal reasoning
capabilities of MLLMs, reducing costly MLLM calls by over
92% compared to naive sparse sampling. We further present
TRACE10K, a dataset featuring three-tier textual annotations
that describe accident dynamics at the frame-sequence
level.
