Automating Infrastructure Surveying: A Framework for Geometric Measurements and Compliance Assessment Using Point Cloud Data

TL;DR

The paper tackles labor-intensive infrastructure surveying by proposing a hybrid AI-geometric framework that couples machine-learning-based asset detection and segmentation with precise geometric analysis and rule-based refinement. It demonstrates the approach on ADA curb ramp compliance, leveraging a large annotated ramp dataset and a SAM-based segmentation pipeline, supplemented by a novel Score-Based Line Fitting (SBLF) for robust geometric references. Experimental results show strong ramp-detection (mAP around 0.87) and segmentation (mean Dice ~0.86) performance, with automated measurements generally aligning with manual field data within tolerances and offering significant reductions in manual effort. The work also releases the dataset and open-source code, paving the way for scalable, consistent automated infrastructure surveys and broader applications beyond ADA ramps.

Abstract

Automation can play a prominent role in improving efficiency, accuracy, and scalability in infrastructure surveying and assessing construction and compliance standards. This paper presents a framework for automation of geometric measurements and compliance assessment using point cloud data. The proposed approach integrates deep learning-based detection and segmentation, in conjunction with geometric and signal processing techniques, to automate surveying tasks. As a proof of concept, we apply this framework to automatically evaluate the compliance of curb ramps with the Americans with Disabilities Act (ADA), demonstrating the utility of point cloud data in survey automation. The method leverages a newly collected, large annotated dataset of curb ramps, made publicly available as part of this work, to facilitate robust model training and evaluation. Experimental results, including comparison with manual field measurements of several ramps, validate the accuracy and reliability of the proposed method, highlighting its potential to significantly reduce manual effort and improve consistency in infrastructure assessment. Beyond ADA compliance, the proposed framework lays the groundwork for broader applications in infrastructure surveying and automated construction evaluation, promoting wider adoption of point cloud data in these domains. The annotated database, manual ramp survey data, and developed algorithms are publicly available on the project's GitHub page: https://github.com/Soltanilara/SurveyAutomation.

Figures (15)

• Figure 1: A prototypical ramp representing ramp types A, D, and E CEM5773ADE. Center ramp (1), warning surface (2), left flare (3), right flare (4), landing (5), and gutter (6) are denoted on the figure. Assessing ADA compliance requires multiple measurements across each ramp component, making the manual process labor-intensive, time-consuming, and costly.
• Figure 2: Flowchart of the proposed infrastructure asset compliance assessment automation method based on point cloud data.
• Figure 3: An example ramp point cloud (top) and its manual segment annotations (bottom). Due to the ambiguity in the landing area for visual annotation, this segment (orange) is annotated with expansion going away from the ramp as long as the visually flat sidewalk area would allow. This is to ensure the annotation incorporates the correct landing area.
• Figure 4: Top: partial street-level point cloud with segmentation masks (shown in red) projected onto the ground plane. Example overlapping patches are outlined in orange and green. Bottom: corresponding patches where 2D segmentation masks have been converted into tight bounding box annotations (shown in red).
• Figure 5: Left: 2D image with detected ADA ramps highlighted with predicted 2D bounding boxes and confidence scores. Right: corresponding 3D crops of the original point cloud, reconstructed from the 2D predictions using stored transformation metadata.