Computer vision-based model for detecting turning lane features on Florida's public roadways

TL;DR

This paper presents a computer vision model that detects turning lane features from aerial images of Florida's roads, offering a safer, more efficient alternative to traditional data collection methods with promising accuracy.

Contribution

The study introduces an AI-based approach for extracting roadway features from aerial imagery, improving safety and efficiency over land-based data collection methods.

Findings

Achieved 80.4% average accuracy in feature detection.

Demonstrated feasibility of integrating extracted data with traffic and crash data.

Provided a scalable method for roadway feature mapping using aerial images.

Abstract

Efficient and current roadway geometry data collection is critical to transportation agencies in road planning, maintenance, design, and rehabilitation. Data collection methods are divided into land-based and aerial-based. Land-based methods for extensive highway networks are tedious, costly, pose safety risks. Therefore, there is the need for efficient, safe, and economical data acquisition methodologies. The rise of computer vision and object detection technologies have made automated extraction of roadway geometry features feasible. This study detects roadway features on Florida's public roads from high-resolution aerial images using AI. The developed model achieved an average accuracy of 80.4 percent when compared with ground truth data. The extracted roadway geometry data can be integrated with crash and traffic data to provide valuable insights to policymakers and roadway users.