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

2026-01-24

AI Summary

This work proposes an end-to-end system to accurately extract vehicle braking events and real-world trajectories from traffic surveillance videos without requiring explicit camera calibration. By robustly estimating the homography between fixed traffic cameras and satellite orthophotos using MAGSAC++, the system maps object detections from YOLOv11 into a rectified bird’s-eye-view coordinate frame, enabling precise pixel-to-meter conversion. Trajectories and braking events are efficiently stored using ClickHouse for scalable analysis. Validation at two signalized intersections in Key West, Florida, demonstrates the system’s capability to reliably identify spatially and temporally diverse braking events, with peak-hour frequencies of 57.5 and 15.5 events per hour, respectively. These results provide high-fidelity data to support intelligent traffic management and road safety design.

Technology Category

• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Application Domains: Transportation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• braking behavior
• vehicle tracking
• homography rectification
• traffic safety analysis
• camera-to-satellite alignment

Innovation

• homography rectification
• camera-to-satellite alignment
• braking behavior analysis
• MAGSAC++
• YOLO11