Deep Learning Enhanced Road Traffic Analysis: Scalable Vehicle Detection and Velocity Estimation Using PlanetScope Imagery

TL;DR

This paper introduces a scalable satellite-based method using deep learning to detect vehicles and estimate their speeds from PlanetScope imagery, enabling broad and frequent traffic monitoring despite some accuracy limitations.

Contribution

The paper presents a novel Keypoint R-CNN approach for vehicle detection and speed estimation from satellite imagery, addressing challenges of low frame rates and small vehicle detection.

Findings

Achieved a Mean Average Precision of 0.53 in vehicle detection.

Estimated vehicle speeds with an average error of 3.4 m/s.

Demonstrated potential for global daily traffic monitoring.

Abstract

This paper presents a method for detecting and estimating vehicle speeds using PlanetScope SuperDove satellite imagery, offering a scalable solution for global vehicle traffic monitoring. Conventional methods such as stationary sensors and mobile systems like UAVs are limited in coverage and constrained by high costs and legal restrictions. Satellite-based approaches provide broad spatial coverage but face challenges, including high costs, low frame rates, and difficulty detecting small vehicles in high-resolution imagery. We propose a Keypoint R-CNN model to track vehicle trajectories across RGB bands, leveraging band timing differences to estimate speed. Validation is performed using drone footage and GPS data covering highways in Germany and Poland. Our model achieved a Mean Average Precision of 0.53 and velocity estimation errors of approximately 3.4 m/s compared to GPS data. Results from drone comparison reveal underestimations, with average speeds of 112.85 km/h for satellite data versus 131.83 km/h from drone footage. While challenges remain with high-speed accuracy, this approach demonstrates the potential for scalable, daily traffic monitoring across vast areas, providing valuable insights into global traffic dynamics.