Measuring Braking Behavior Using Vehicle Tracking and Camera-to-Satellite Homography Rectification

TL;DR

This paper introduces an open-source system that uses vehicle tracking and homography rectification to analyze traffic camera footage, accurately measuring vehicle behavior and braking events for improved traffic safety analysis.

Contribution

The paper presents a novel, calibration-free method for rectifying traffic camera views to satellite imagery, enabling precise vehicle behavior analysis without extensive camera calibration.

Findings

Peak braking activity at the high-volume intersection was around 57.5 events/hour at 4 PM.

Most braking events started 30-45 meters upstream of the stop bar.

Severe braking was concentrated in lanes with higher interaction and merging.

Abstract

This paper presents an open-source software application for analyzing traffic camera footage, focusing on vehicle behavior and braking events at signalized urban highways. The core innovation is a robust ground-plane homography estimation that links fixed traffic camera views to satellite orthoimagery. This process rectifies the camera's oblique perspective, ensuring that pixel distances accurately represent real-world distances. This enables the acquisition of features such as vehicle trajectory, speed, deceleration, and braking severity without the need for camera calibration. The pipeline employs the MAGSAC++ estimator to build the homography, converting YOLO11 object detections into a rectified top-down coordinate system. All detection and trajectory data are stored in a ClickHouse database for subsequent analysis. A real-world case study at two signalized intersections in Key West, Florida, showcased the system's capabilities. Across two days of daytime footage, braking activity at the higher-volume intersection peaked around 4 PM at approximately 57.5 events per hour, while the second intersection peaked around 10 AM at roughly 15.5 events per hour. The spatial analysis revealed that most braking events initiated upstream, with mild and moderate braking mostly occurring 30 to 45+ meters away from the stop bar and severe braking distributed throughout, but particularly concentrated in lanes with higher interaction and merging activity. The findings highlight the significant potential of this centralized safety information system to support connected vehicles, facilitating proactive traffic management, crash mitigation, and data-driven roadway design and safety analysis.