NYC Congestion Pricing: A Vision-Based Analysis

Changes in traffic patterns for the congestion pricing, as obtained through computer vision-based analysis. — Using a computer vision framework applied to a network of 910 NYC traffic cameras, we analyze traffic patterns using year-to-year data from November 14 to January 4 (before and after) to look at the effects of the pricing. The visualization above depicts relative traffic volume changes at key intersections throughout Manhattan and New York, with circle diameter representing magnitude of change and color indicating direction (green for reduction, red for increase).

Change in Peak Observed Car Count per Frame (%)

Metric

Day Type

Launch Interactive Visualization

Interactive Map

Real Time Map

Click on the button to open the interactive visualization in a new tab.

Abstract

We examine the impact of New York City’s congestion pricing program through automated analysis of traffic camera data. Our computer vision pipeline processes footage from over 900 cameras distributed throughout Manhattan, comparing traffic patterns using year-to-year data from November 14 to January 4. By excluding anomalous periods such as holidays, we establish baseline traffic patterns and identify systematic changes in vehicle density across the monitored region. This ongoing research project will provide regular updates to track long-term evolution of urban mobility patterns in response to the pricing policy.

Current Limitations

Our approach has some important limitations:

The computer vision system includes stationary vehicles in traffic density calculations, which may affect measurements in areas with high street parking density
The current implementation analyzes aggregate traffic flow without distinguishing between individual lanes or travel directions
Camera-based instantaneous vehicle counts serve as a proxy measure and may not directly correlate with actual transit times or congestion levels

Research Team

Columbia University

Acknowledgement

This project was partly supported by compute resources at the PAWR COSMOS testbed at Columbia University.

This work began while the first author was a member of the Department of Electrical Engineering (AIDL Lab) at Columbia University, and is currently maintained by the first author at the NSF Center for Smart Streetscapes.

References

If you use this dataset or code in your research, please kindly cite the following works:

@misc{turkcan2026visionbasedanalysiscongestionpricing,
      title={A Vision-Based Analysis of Congestion Pricing in New York City},
      author={Mehmet Kerem Turkcan and Jhonatan Tavori and Javad Ghaderi and Gil Zussman and Zoran Kostic and Andrew Smyth},
      year={2026},
      eprint={2602.03015},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2602.03015},
}