Learning Traffic Anomalies from Generative Models on Real-Time Observations
This work addresses traffic management challenges for urban planners by providing an incremental improvement in anomaly detection using existing methods on new data.
The paper tackled traffic anomaly detection using a Spatiotemporal Generative Adversarial Network (STGAN) on real-time data from 42 cameras in Gothenburg, Sweden, achieving high precision and low false positive rates in identifying issues like camera interruptions and weather effects.
Accurate detection of traffic anomalies is crucial for effective urban traffic management and congestion mitigation. We use the Spatiotemporal Generative Adversarial Network (STGAN) framework combining Graph Neural Networks and Long Short-Term Memory networks to capture complex spatial and temporal dependencies in traffic data. We apply STGAN to real-time, minute-by-minute observations from 42 traffic cameras across Gothenburg, Sweden, collected over several months in 2020. The images are processed to compute a flow metric representing vehicle density, which serves as input for the model. Training is conducted on data from April to November 2020, and validation is performed on a separate dataset from November 14 to 23, 2020. Our results demonstrate that the model effectively detects traffic anomalies with high precision and low false positive rates. The detected anomalies include camera signal interruptions, visual artifacts, and extreme weather conditions affecting traffic flow.