Data extraction and processing methods to aid the study of driving behaviors at intersections in naturalistic driving

TL;DR

This paper presents automated methods for extracting and analyzing driver behavior at intersections from naturalistic driving data, including head pose, scene objects, and vehicle maneuvers, to facilitate large-scale behavioral studies.

Contribution

The study introduces novel AI-based tools for processing in-car videos and sensor data to accurately identify intersection features and driver behaviors in naturalistic driving environments.

Findings

Automated detection of intersection signage and maneuvers achieved 100% and 94% accuracy.

Median error in vehicle entry detection was 1.1 meters and 0.2 seconds.

Processed data from 190 intersections across different regions and vehicle types.

Abstract

Naturalistic driving studies use devices in participants' own vehicles to record daily driving over many months. Due to diverse and extensive amounts of data recorded, automated processing is necessary. This report describes methods to extract and characterize driver head scans at intersections from data collected from an in-car recording system that logged vehicle speed, GPS location, scene videos, and cabin videos. Custom tools were developed to mark the intersections, synchronize location and video data, and clip the cabin and scene videos for +/-100 meters from the intersection location. A custom-developed head pose detection AI model for wide angle head turns was run on the cabin videos to estimate the driver head pose, from which head scans >20 deg were computed in the horizontal direction. The scene videos were processed using a YOLO object detection model to detect traffic lights, stop signs, pedestrians, and other vehicles on the road. Turning maneuvers were independently detected using vehicle self-motion patterns. Stop lines on the road surface were detected using changing intensity patterns over time as the vehicle moved. The information obtained from processing the scene videos, along with the speed data was used in a rule-based algorithm to infer the intersection type, maneuver, and bounds. We processed 190 intersections from 3 vehicles driven in cities and suburban areas from Massachusetts and California. The automated video processing algorithm correctly detected intersection signage and maneuvers in 100% and 94% of instances, respectively. The median [IQR] error in detecting vehicle entry into the intersection was 1.1[0.4-4.9] meters and 0.2[0.1-0.54] seconds. The median overlap between ground truth and estimated intersection bounds was 0.88[0.82-0.93].