IncidentNet: Traffic Incident Detection, Localization and Severity Estimation with Sparse Sensing

TL;DR

IncidentNet is a deep learning model that detects, localizes, and estimates the severity of traffic incidents using sparse sensor data, achieving high accuracy in urban environments with limited sensor coverage.

Contribution

This paper introduces IncidentNet, a novel deep learning approach for traffic incident detection and analysis using sparse microscopic traffic data, along with a synthetic dataset generation methodology.

Findings

Detection rate of 98% for traffic incidents

False alarm rate below 7%

Average detection time of 197 seconds

Abstract

Prior art in traffic incident detection relies on high sensor coverage and is primarily based on decision-tree and random forest models that have limited representation capacity and, as a result, cannot detect incidents with high accuracy. This paper presents IncidentNet - a novel approach for classifying, localizing, and estimating the severity of traffic incidents using deep learning models trained on data captured from sparsely placed sensors in urban environments. Our model works on microscopic traffic data that can be collected using cameras installed at traffic intersections. Due to the unavailability of datasets that provide microscopic traffic details and traffic incident details simultaneously, we also present a methodology to generate a synthetic microscopic traffic dataset that matches given macroscopic traffic data. IncidentNet achieves a traffic incident detection rate of 98%, with false alarm rates of less than 7% in 197 seconds on average in urban environments with cameras on less than 20% of the traffic intersections.