RasterNet: Modeling Free-Flow Speed using LiDAR and Overhead Imagery

TL;DR

RasterNet is an automated neural network that estimates free-flow vehicle speeds by integrating overhead imagery and LiDAR data, eliminating the need for explicit geometric features, and demonstrating state-of-the-art accuracy.

Contribution

The paper introduces RasterNet, a novel neural network model that fuses imagery and LiDAR data for free-flow speed estimation without relying on geometric features.

Findings

Achieves state-of-the-art results on a benchmark dataset.

Provides a new dataset combining speeds, imagery, and LiDAR across Kentucky.

Demonstrates effectiveness of multimodal data fusion for transportation modeling.

Abstract

Roadway free-flow speed captures the typical vehicle speed in low traffic conditions. Modeling free-flow speed is an important problem in transportation engineering with applications to a variety of design, operation, planning, and policy decisions of highway systems. Unfortunately, collecting large-scale historical traffic speed data is expensive and time consuming. Traditional approaches for estimating free-flow speed use geometric properties of the underlying road segment, such as grade, curvature, lane width, lateral clearance and access point density, but for many roads such features are unavailable. We propose a fully automated approach, RasterNet, for estimating free-flow speed without the need for explicit geometric features. RasterNet is a neural network that fuses large-scale overhead imagery and aerial LiDAR point clouds using a geospatially consistent raster structure. To support training and evaluation, we introduce a novel dataset combining free-flow speeds of road segments, overhead imagery, and LiDAR point clouds across the state of Kentucky. Our method achieves state-of-the-art results on a benchmark dataset.