3-D Road Boundary Extraction From Mobile Laser Scanning Data via Supervoxels and Graph Cuts

Zai, Dawei; Li, Jonathan; Guo, Yulan; Cheng, Ming; Lin, Yangbin; Luo, Haipeng; Wang, Cheng

doi:10.1109/tits.2017.2701403

Cited by 88 publications

(71 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the sliding-beam method to segment the road, the curb-detection method is finally applied. Zai [21] proposes super voxels that are used to obtain candidate points; then, the trajectory data is used to classify left and right candidate points. Guojun et al [22] present a robust method for curb detection and tracking in a structured environment.…”

Section: Introductionmentioning

confidence: 99%

Automated Road Curb Break Lines Extraction from Mobile LiDAR Point Clouds

Gézero

Antunes

2019

IJGI

View full text Add to dashboard Cite

In last decades, Mobile Light Detection And Ranging (LiDAR) systems were revealed to be an efficient and reliable method to collect dense and precise point clouds. The challenge now faced by researchers is the automatic object extraction from those point clouds, such as the curb break lines, which are essential to road rehabilitation projects and autonomous driving. Throughout this work, an efficient method to extract road curb break lines from mobile LiDAR point clouds is presented. The proposed method was based on the system working principles instead of an algorithmic application over the cloud as a mass of points. The point cloud was decomposed in the original sensor scan profiles. Then, a GPS epoch versus trajectory distance was used to eliminate most non-ground points. Finally, through a vertical monotone chain decomposition, candidate point arrays were created and the curb break lines are formed. The proposed method was shown to be able to avoid the occlusion effect caused by undergrowth. The method allows for distinguishing between right and left curbs and works on curved curbs. Both top and bottom tridimensional break lines were extracted. When compared with a reference manual method, in the tested dataset, the proposed method allowed for a decrease in the curb break lines extraction time from 25 min to less than 30 s. The extraction method provided completeness and correctness rates above 95% and 97%, respectively, and a quality value higher than 93%.Typically, when obtained using photogrammetric methods or a field survey, the break line designs are time consuming.Mobile Light Detection And Ranging (LiDAR) is a widely disseminated technology that allows for gathering dense and precise point clouds. Initially installed on aerial platforms, the static and mobile terrestrial systems rapidly emerged, becoming a crucial source of georeferenced data. However, LiDAR is a non-selective technique, i.e., the georeferenced point clouds represent the sensor's surrounding physical reality at an acquisition moment, indiscriminately, with no classification of terrain, vegetation, buildings, or any other object within the system range. The automatic classification and object extraction from those point clouds became a noteworthy challenge for researchers.Since the initial LiDAR systems, numerous techniques for automatic break lines extraction have been presented. Brugelmann [6] shortly describes some methods for break lines extraction from airborne point clouds, testing an approach proposed by Forstner [7]. In that approach, all pixels with a significant noise homogeneity measure are denoted as potential edge pixels. The quadratic variation, used as a homogeneity measure, indicates the extent of the curvature. Although the resulting lines have a lower quality when compared with the photogrammetrically measured break lines, the author showed that automatic break line extraction from airborne laser data is feasible.Other approach based on two intersecting planes as fitted functions can extract some 3D lines, but they nee...

show abstract

Section: Introductionmentioning

confidence: 99%

Automated Road Curb Break Lines Extraction from Mobile LiDAR Point Clouds

Gézero

Antunes

2019

IJGI

View full text Add to dashboard Cite

show abstract

“…Without removing the points during the partition procedure, other methods divide the data into sections or tiles, such that each section can be processed separately to reduce the computation complexity (e.g., Chen, et al [6], Holgado-Barco, et al [8], Wu, et al [10], Soilán, et al [16], Jung, et al [17], Teo and Chiu [19], Pu, et al [23]). Furthermore, depending on the desired analysis, the refinement of the data partition can be achieved by merging multiple profiles to generate a series of overlapping tiles (e.g., Zai, et al [11], Wang, et al [20]), or by dividing a profile based on some other constraints, such as the slope of the roadway (e.g., Wang, et al [9]).…”

Section: Introductionmentioning

confidence: 99%

An Efficient Framework for Mobile Lidar Trajectory Reconstruction and Mo-norvana Segmentation

Che

Olsen

2019

Remote Sensing

View full text Add to dashboard Cite

Mobile laser scanning (MLS, or mobile lidar) is a 3-D data acquisition technique that has been widely used in a variety of applications in recent years due to its high accuracy and efficiency. However, given the large data volume and complexity of the point clouds, processing MLS data can be still challenging with respect to effectiveness, efficiency, and versatility. This paper proposes an efficient MLS data processing framework for general purposes consisting of three main steps: trajectory reconstruction, scan pattern grid generation, and Mo-norvana (Mobile Normal Variation Analysis) segmentation. We present a novel approach to reconstructing the scanner trajectory, which can then be used to structure the point cloud data into a scan pattern grid. By exploiting the scan pattern grid, point cloud segmentation can be performed using Mo-norvana, which is developed based on our previous work for processing Terrestrial Laser Scanning (TLS) data, normal variation analysis (Norvana). In this work, with an unorganized MLS point cloud as input, the proposed framework can complete various tasks that may be desired in many applications including trajectory reconstruction, data structuring, data visualization, edge detection, feature extraction, normal estimation, and segmentation. The performance of the proposed procedures are experimentally evaluated both qualitatively and quantitatively using multiple MLS datasets via the results of trajectory reconstruction, visualization, and segmentation. The efficiency of the proposed method is demonstrated to be able to handle a large dataset stably with a fast computation speed (about 1 million pts/sec. with 8 threads) by taking advantage of parallel programming.

show abstract

“…The correctness and completeness of extracted road markings have great impacts on the performance of driving line generation. Various studies were carried out in the past years (Zai et al, 2018, Soilán et al, 2017. Nevertheless, the prior knowledge about LiDAR-derived control point selection makes the accurate driving line generation very challenging (Cabo et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Automated Extraction of Driving Lines from Mobile Laser Scanning Point Clouds

et al. 2019

Adv. Cartogr. GIScience Int. Cartogr. Assoc.

Self Cite

View full text Add to dashboard Cite

<p><strong>Abstract.</strong> This paper presents a novel approach to automated generation of driving lines from mobile laser scanning (MLS) point cloud data. The proposed method consists of three steps: road surface segmentation, road marking extraction and classification, and driving line generation. The voxel-based upward-growing algorithm was firstly used to extract ground points from the raw MLS point clouds followed by segmentation of road surface using a region-growing algorithm. Then, the statistical outlier removal filter was applied to separate and refine the road marking points followed by extracting and classifying the lane markings based on the geometric features of different road markings using empirical hierarchical decision trees. Finally, land node structures were constructed followed by generation of driving lines using a curve-fitting algorithm. The proposed method was tested on both circular road sections and irregular intersections. The smoothing spline curve fitting model was tested on the circular road sections, while the Catmull-Rom spline with five control points was used to generate the driving lines at road intersections. The overall performance of the proposed algorithms is promising with 96.0% recall, 100.0% precision, and 98.0% F1-score for the lane marking extraction specifically. Most significantly, the validation results demonstrate that the driving lines can be effectively generated within 20&thinsp;cm-level localization accuracy at an average of 3.5% miscoding using MLS point clouds, which meets the requirement of localization accuracy of fully autonomous driving functions. The results demonstrate the proposed methods can successfully generate road driving lines in the test datasets to support the development of high-definition maps.</p>

show abstract

3-D Road Boundary Extraction From Mobile Laser Scanning Data via Supervoxels and Graph Cuts

Cited by 88 publications

References 40 publications

Automated Road Curb Break Lines Extraction from Mobile LiDAR Point Clouds

Automated Road Curb Break Lines Extraction from Mobile LiDAR Point Clouds

An Efficient Framework for Mobile Lidar Trajectory Reconstruction and Mo-norvana Segmentation

Automated Extraction of Driving Lines from Mobile Laser Scanning Point Clouds

Contact Info

Product

Resources

About