Automated Extraction of Urban Road Facilities Using Mobile Laser Scanning Data

Abstract

This paper proposes a novel, automated algorithm for rapidly extracting urban road facilities, including street light poles, traffic signposts, and bus stations, for transportation-related applications. A detailed description and implementation of the proposed algorithm is provided using mobile laser scanning data collected by a state-of-the-art RIEGL VMX-450 system. First, to reduce the quantity of data to be handled, a fast voxel-based upward growing method is developed to remove ground points. Then, off-ground points are clustered and segmented into individual objects via Euclidean distance clustering and voxel-based normalized cut segmentation, respectively. Finally, a 3-D object matching framework, benefiting from a locally affine-invariant geometric constraint, is developed to achieve the extraction of 3-D objects. Quantitative evaluations show that the proposed algorithm attains an average completeness, correctness, quality, and F 1 -measure of 0.949, 0.971, 0.922, and 0.960, respectively, in extracting 3-D light poles, traffic signposts, and bus stations. Comparative studies demonstrate the efficiency and feasibility of the proposed algorithm for automated and rapid extraction of urban road facilities.Index Terms-Bus station, light pole, mobile laser scanning (MLS), road feature inventory, traffic safety, traffic signpost.

Revue des descripteurs tridimensionnels (3D) pour la catégorisation des nuages de points acquis avec un système LiDAR de télémétrie mobile

“…Dans Yu et al (2015), une nouvelle méthode est proposée pour la reconnaissance de mobilier urbain (c-à-d., panneau de signalisation, lampadaire, arrêt de bus) dans des nuages de points acquis avec des STM. La démarche implique le descripteur FPFH ainsi qu'une fonction de coût d'appariement entre les segments de points extraits du nuage et des objets de référence.…”

An Enhanced Algorithm for Concurrent Recognition of Rail Tracks and Power Cables from Terrestrial and Airborne LiDAR Point Clouds

“…Jochem et al [10] and Wu et al [11] extract buildings from LiDAR data of urban environments. Yu et al [12] identify road features from mobile terrestrial LiDAR datasets. Hullo et al [13] create as-built model of industrial sites from terrestrial LiDAR data.…”

Semantic Labelling of Ultra Dense MLS Point Clouds in Urban Road Corridors Based on Fusing CRF With Shape Priors

“…The results are appealing for a wide range of applications such as facility mapping, environment assessment and road inventory. While digital imaging sensors are frequently adopted to characterize the urban landscape and land use types, mobile laser scanners (MLS) are increasingly used to directly acquire dense 3D geo-data about urban facility along the road corridor (Babahajiani et al, 2016;Yu et al, 2015). MLS is generally used for small-scale area applications, such as road inventory in individual sections, and provide accurate and dense 3D data of the object surfaces.…”

“…Former studies are frequently focused on individual object classes such as buildings, vegetation, or street lights/traffic signs (Steinsick et al, 2017;Yu et al, 2015). Weinmann et al (2015) used Conditional Random Fields (CRF) for point-by-point classification of several objects in urban ALS or MLS data.…”