RasterNet: Modeling Free-Flow Speed using LiDAR and Overhead Imagery
This addresses the challenge of modeling free-flow speed for transportation engineering applications where traditional geometric data is unavailable, though it is incremental as it builds on existing neural network and data fusion techniques.
The authors tackled the problem of estimating free-flow speed for roads without explicit geometric features by proposing RasterNet, a neural network that fuses overhead imagery and LiDAR data, achieving state-of-the-art results on a benchmark dataset.
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.