IncidentNet: Traffic Incident Detection, Localization and Severity Estimation with Sparse Sensing
This addresses traffic management and safety by improving incident detection with limited infrastructure, though it is incremental as it builds on deep learning methods for a specific domain.
The paper tackles traffic incident detection, localization, and severity estimation using deep learning on sparse sensor data, achieving a 98% detection rate with less than 7% false alarms in 197 seconds on average in urban environments with cameras on under 20% of intersections.
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.