IMPACT: Integrated Multimodal Pipeline for Rapid Accident Causality Tracking (Student Abstract)

Authors

  • Vashu Chauhan IIIT Delhi, India
  • Avinash Anand IIIT Delhi, India Nvidia AI Center, SiT, Singapore
  • Manisha Luthra Technical University of Darmstadt, Germany
  • Uelison Jean Lopes dos Santos Technical University of Darmstadt, Germany
  • Carsten Binnig Technical University of Darmstadt, Germany
  • Rajiv Ratn Shah IIIT Delhi, India

DOI:

https://doi.org/10.1609/aaai.v40i48.42198

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 real-time 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.
AAAI-26 / IAAI-26 / EAAI-26 Proceedings Cover

Downloads

Published

2026-03-14

How to Cite

Chauhan, V., Anand, A., Luthra, M., Jean Lopes dos Santos, U., Binnig, C., & Shah, R. R. (2026). IMPACT: Integrated Multimodal Pipeline for Rapid Accident Causality Tracking (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41159–41161. https://doi.org/10.1609/aaai.v40i48.42198

Issue

Vol. 40 No. 48: EAAI-26 AI for Education, Model AI Assignments, AAAI-26 Emerging Trends, Doctoral Consortium, Student Abstracts, Undergraduate Consortium and Demonstrations

Section

AAAI Student Abstract and Poster Program