Road and Roadside Feature Extraction Using Imagery and Lidar Data for Transportation Operation

Ural, Serkan; Shan, Jie; Romero, Mario; Tarko, Andrew P.

doi:10.5194/isprsannals-ii-3-w4-239-2015

Cited by 13 publications

(11 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Below are the processes required to define the models from the LiDAR point cloud. Some of these tasks were also found in road feature extraction and road surface modeling literature [25,26].…”

Section: Methodsmentioning

confidence: 99%

Framework for 3D Point Cloud Modelling Aimed at Road Sight Distance Estimations

et al. 2019

View full text Add to dashboard Cite

Existing roads require periodic evaluation in order to ensure safe transportation. Estimations of the available sight distance (ASD) are fundamental to make sure motorists have sufficient visibility to perform basic driving tasks. Mobile LiDAR Systems (MLS) can provide these evaluations with accurate three-dimensional models of the road and surroundings. Similarly, Geographic Information System (GIS) tools have been employed to obtain ASD. Due to the fact that widespread GIS formats used to store digital surface models handle elevation as an attribute of location, the presented methodology has separated the representation of ground and aboveground elements. The road geometry and surrounding ground are stored in digital terrain models (DTM). Correspondingly, abutting vegetation, manmade structures, road assets and other roadside elements are stored in 3D objects and placed on top of the DTM. Both the DTM and 3D objects are accurately obtained from a denoised and classified LiDAR point cloud. Based on the consideration that roadside utilities and most manmade structures are well-defined geometric elements, some visual obstructions are extracted and/or replaced with 3D objects from online warehouses. Different evaluations carried out with this method highlight the tradeoff between the accuracy of the estimations, performance and geometric complexity as well as the benefits of the individual consideration of road assets.

show abstract

Section: Methodsmentioning

confidence: 99%

Framework for 3D Point Cloud Modelling Aimed at Road Sight Distance Estimations

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In 2015, Ural et al (30) investigated roadside feature extraction with orthophotos and lidar data using a semiautomated approach. Initially, the road surface was extracted from an orthorectified image using Support Vector Machine (SVM) classifiers.…”

Section: Literature Reviewmentioning

confidence: 99%

Automated Object Detection, Mapping, and Assessment of Roadside Clear Zones Using Lidar Data

Gouda

Mello

El-Basyouny

2021

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

This paper proposes a fully automated approach to map and assess roadside clearance parameters using mobile Light Detection and Ranging (lidar) data on rural highways. Compared with traditional manual surveying methods, lidar data could provide a more efficient and cost-effective source to extract roadside information. This study proposes a novel voxel-based raycasting approach focused primarily on automating roadside mapping and assessment. First, the scanning vehicle trajectory is extracted. Pavement surface points are then detected, and a method is proposed to extract pavement edge trajectories. Once pavement edges are extracted, guardrails were identified using a conical frustum emitted from the edge trajectory points. Target points and flexion points are then generated and located on the roadside, and a voxel-based raycasting approach is used to search for roadside obstacles and query their locations. Finally, roadside slopes and embankment heights were mapped at specific intervals, and roadside design guidelines and requirements were automatically checked against the mapping results. Noncompliant locations with substandard conditions were automatically queried. The method was tested on four highway segments in Alberta, Canada. The accuracy of the edge detection reached up to 98.5%. Furthermore, the method proved to be accurate in object detection, being able to detect all obstructions on the roadside in each tested segment. The proposed method can help transportation authorities automatically map and inventory roadside clearance parameters. Moreover, the safety performance of existing road infrastructure can be studied using collected information and crash data to support decision making on road maintenance and upgrades.

show abstract

“…The research [33] provides an example of an effective use of video traffic monitoring. Modern techniques allow the use of Bluetooth technology to collect data on traffic parameters [34][35][36] and Lidar technology to collect data on road and its surroundings parameters [37][38][39].…”

Section: Introductionmentioning

confidence: 99%

Measures of Functional Reliability of Two-Lane Highways

Ostrowski

Budzyński

2021

Energies

View full text Add to dashboard Cite

Rural two-lane highways are the most common road type both in Poland and globally. In terms of kilometres, their length is by far greater than that of motorways and expressways. They are roads of one carriageway for each direction, which makes the overtaking of slower vehicles possible only when there is a gap in the stream of traffic moving from the opposite direction. Motorways and express roads are dual carriageways that are expected to support high speed travel mainly over long distances. Express roads have somewhat lower technical parameters and a lower speed limit than motorways. Two-lane highways are used for both short- and long-distance travel. The paper presents selected studies conducted in Poland in 2016–2018 on rural two-lane highways and focuses on the context of the need for their reliability. The research was carried out on selected short and [longer road sections located in various surroundings, grouped in terms of curvature change rate CCR, longitudinal slopes and cross-sections (width of lanes and shoulders). The studies of traffic volumes, travel time and travel speed, as well as traffic density, will be used to analyze traffic performance and identify measures of travel time reliability. The analyzed roads were characterized by good technical parameters and significant variability of traffic volume throughout the day, week and year. Some roads experience congestion, i.e., situations in which traffic volume Q is close to or above respective road capacity C. In order to determine the form of the suitable reliability measures, it will be important to determine the extent to which a road’s geometric and traffic characteristics impact travel speed and time. The paper presents well-known reliability measures for dual carriageways and proposes new measures, along with an evaluation of their usefulness in the assessment of the functioning of two-lane highways.

show abstract

Road and Roadside Feature Extraction Using Imagery and Lidar Data for Transportation Operation

Cited by 13 publications

References 39 publications

Framework for 3D Point Cloud Modelling Aimed at Road Sight Distance Estimations

Framework for 3D Point Cloud Modelling Aimed at Road Sight Distance Estimations

Automated Object Detection, Mapping, and Assessment of Roadside Clear Zones Using Lidar Data

Measures of Functional Reliability of Two-Lane Highways

Contact Info

Product

Resources

About