Pedestrian Accessible Infrastructure Inventory: Assessing Zero-Shot Segmentation on Multi-Mode Geospatial Data for All Pedestrian Types

TL;DR

This paper presents a SAM-based workflow for zero-shot segmentation of pedestrian infrastructure using multi-source geospatial data, enhancing accessibility mapping for diverse pedestrian needs.

Contribution

It introduces a novel approach combining LiDAR and satellite data with SAM for scalable pedestrian infrastructure segmentation, including street furniture.

Findings

LiDAR-derived street view images improve segmentation accuracy

Satellite imagery paired with LiDAR enhances data representation for SAM

The method benefits accessibility mapping for disabled pedestrians

Abstract

In this paper, a Segment Anything Model (SAM)-based pedestrian infrastructure segmentation workflow is designed and optimized, which is capable of efficiently processing multi-sourced geospatial data including LiDAR data and satellite imagery data. We used an expanded definition of pedestrian infrastructure inventory which goes beyond the traditional transportation elements to include street furniture objects that are important for accessibility but are often omitted from the traditional definition. Our contributions lie in producing the necessary knowledge to answer the following two questions. First, which data representation can facilitate zero-shot segmentation of infrastructure objects with SAM? Second, how well does the SAM-based method perform on segmenting pedestrian infrastructure objects? Our findings indicate that street view images generated from mobile LiDAR point cloud data, when paired along with satellite imagery data, can work efficiently with SAM to create a scalable pedestrian infrastructure inventory approach with immediate benefits to GIS professionals, city managers, transportation owners, and walkers, especially those with travel-limiting disabilities, such as individuals who are blind, have low vision, or experience mobility disabilities.