Intelligent Traffic Monitoring with Hybrid AI

TL;DR

This paper introduces HANS, a neuro-symbolic architecture leveraging knowledge graphs for multi-modal context understanding in intelligent traffic monitoring, addressing data complexity and reasoning challenges.

Contribution

The paper presents HANS, a novel neuro-symbolic framework that integrates knowledge graphs with reasoning methods for improved traffic monitoring.

Findings

HANS effectively handles multi-modal traffic data.

HANS enhances reasoning capabilities in traffic monitoring.

The approach demonstrates adaptability across various traffic scenarios.

Abstract

Challenges in Intelligent Traffic Monitoring (ITMo) are exacerbated by the large quantity and modalities of data and the need for the utilization of state-of-the-art (SOTA) reasoners. We formulate the problem of ITMo and introduce HANS, a neuro-symbolic architecture for multi-modal context understanding, and its application to ITMo. HANS utilizes knowledge graph technology to serve as a backbone for SOTA reasoning in the traffic domain. Through case studies, we show how HANS addresses the challenges associated with traffic monitoring while being able to integrate with a wide range of reasoning methods