Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

J. P. Fleischer, Tanchanok Sirikanchittavon, Chonlachart Jeenprasom, Nooshin Yousefzadeh, Sanjay Ranka, Mohammed Hadi

TL;DR

This work addresses measuring braking behavior from conventional traffic cameras without camera calibration by aligning camera views to satellite orthoimagery through a robust ground-plane homography estimated with MAGSAC++. The open-source RoadPairer pipeline converts YOLO11l detections into a rectified top-down coordinate system, enabling detailed trajectory and braking metrics that are stored in a ClickHouse database. Real-world results from two Key West intersections reveal pronounced temporal peaks in braking and spatial patterns tied to upstream deceleration, demonstrating the approach's potential to support connected-vehicle safety, proactive traffic management, and data-driven roadway design. The study advances scalable, GIS-based, calibration-free traffic analysis, with implications for safety analytics, outage planning, and infrastructure design.

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.

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

TL;DR

This work addresses measuring braking behavior from conventional traffic cameras without camera calibration by aligning camera views to satellite orthoimagery through a robust ground-plane homography estimated with MAGSAC++. The open-source RoadPairer pipeline converts YOLO11l detections into a rectified top-down coordinate system, enabling detailed trajectory and braking metrics that are stored in a ClickHouse database. Real-world results from two Key West intersections reveal pronounced temporal peaks in braking and spatial patterns tied to upstream deceleration, demonstrating the approach's potential to support connected-vehicle safety, proactive traffic management, and data-driven roadway design. The study advances scalable, GIS-based, calibration-free traffic analysis, with implications for safety analytics, outage planning, and infrastructure design.

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.
Paper Structure (12 sections, 3 equations, 10 figures, 2 tables)

This paper contains 12 sections, 3 equations, 10 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Case Study Site Specifications
  3. System Architecture
  4. System Overview
  5. Hardware
  6. Software
  7. RoadPairer: Traffic Camera-to-Satellite Correspondence
  8. Object Detection and Tracking
  9. Braking Metrics Analysis
  10. Experimental Results
  11. Related Works
  12. Conclusions

Figures (10)

  • Figure 1: Satellite image of the Overseas Hwy. and Roosevelt Blvd. intersection from Monroe County.
  • Figure 3: A screenshot of the RoadPairer GUI mapping points between a native traffic camera image and a satellite image.
  • Figure 4: A screenshot of the Tracks Viewer interface.
  • Figure 5: Average hourly braking event counts by severity (mild, moderate, severe) over 2 days of traffic footage at Overseas Hwy / Roosevelt Blvd.
  • Figure 6: Average hourly braking event counts by severity (mild, moderate, severe) over 2 days of traffic footage at White Street / Truman Avenue.
  • ...and 5 more figures