AUTOMATIC EXTRACTION AND RECOGNITION OF ROAD MARKINGS BASED ON VEHICLE LASER POINT CLOUD

Abstract. At present, automatic driving technology has become one of the development direction of the future intelligent transportation system. The high high-precision map, which is an important supplement of the on on-board sensors under the condition of shielding or the restriction of observation distance, provides a priori information for high high-precision positioning and path planning of the automatic driving with the level of L3 and above. The position and semantic information of the road markings, such as the absolute coordinates of th e solid line and the bro ken line, are the basic components of the high high-precision map. At present, point cloud data are still one of the most important data source of the high high-precision map. So, how to get road markings information from original point clouds automatically deserve study. In this paper, point cloud is sliced by the mileage of the road, then each slice is projected onto respective vertical section section. Random Sample Consensus (RANSAC) algorithm is applied to establish road surface buffer area . Finally, moving window filtering is used to extract road surface point cloud from road surface buffer area area. On this basis, the road surface point cloud image is transformed into raster image with a certain resolution by using the method of inverse distance weighted interpolation , and the grid image is converted into binary image by using the method of adaptive threshold segmentation based on the integral graph. Then the method of the Euclidean clustering is used to extract the road markings point cloud from the binary image. Characteristic attribute detection is applied to recognize solid line marking from all clusters. Deep learning network framework pointnet++ is applied to recognize remain road markings including guideline, broken line, straight arrow, and right turn arrow.

Download Full-text

Automatic Road Marking Extraction and Vectorization from Vehicle-Borne Laser Scanning Data

Remote Sensing ◽

10.3390/rs13132612 ◽

2021 ◽

Vol 13 (13) ◽

pp. 2612

Author(s):

Lianbi Yao ◽

Changcai Qin ◽

Qichao Chen ◽

Hangbin Wu

Keyword(s):

High Precision ◽

Point Cloud ◽

Point Clouds ◽

Adaptive Threshold ◽

Point Cloud Data ◽

Threshold Segmentation ◽

Cloud Data ◽

The Road ◽

Automatic Driving ◽

Road Marking

Automatic driving technology is becoming one of the main areas of development for future intelligent transportation systems. The high-precision map, which is an important supplement of the on-board sensors during shielding or limited observation distance, provides a priori information for high-precision positioning and path planning in automatic driving. The position and semantic information of the road markings, such as absolute coordinates of the solid lines and dashed lines, are the basic components of the high-precision map. In this paper, we study the automatic extraction and vectorization of road markings. Firstly, scan lines are extracted from the vehicle-borne laser point cloud data, and the pavement is extracted from scan lines according to the geometric mutation at the road boundary. On this basis, the pavement point clouds are transformed into raster images with a certain resolution by using the method of inverse distance weighted interpolation. An adaptive threshold segmentation algorithm is used to convert raster images into binary images. Followed by the adaptive threshold segmentation is the Euclidean clustering method, which is used to extract road markings point clouds from the binary image. Solid lines are detected by feature attribute filtering. All of the solid lines and guidelines in the sample data are correctly identified. The deep learning network framework PointNet++ is used for semantic recognition of the remaining road markings, including dashed lines, guidelines and arrows. Finally, the vectorization of the identified solid lines and dashed lines is carried out based on a line segmentation self-growth algorithm. The vectorization of the identified guidelines is carried out according to an alpha shape algorithm. Point cloud data from four experimental areas are used for road marking extraction and identification. The F-scores of the identification of dashed lines, guidelines, straight arrows and right turn arrows are 0.97, 0.66, 0.84 and 1, respectively.

Download Full-text

Mobile Laser Scanning Data for the Evaluation of Pavement Surface Distress

Remote Sensing ◽

10.3390/rs12060942 ◽

2020 ◽

Vol 12 (6) ◽

pp. 942 ◽

Cited By ~ 3

Author(s):

Maria Rosaria De Blasiis ◽

Alessandro Di Benedetto ◽

Margherita Fiani

Keyword(s):

Point Cloud ◽

Laser Scanning ◽

Road Traffic ◽

Single Point ◽

Three Dimensional ◽

Point Clouds ◽

Road Surface ◽

Important Indicator ◽

The Road ◽

Laser Systems

The surface conditions of road pavements, including the occurrence and severity of distresses present on the surface, are an important indicator of pavement performance. Periodic monitoring and condition assessment is an essential requirement for the safety of vehicles moving on that road and the wellbeing of people. The traditional characterization of the different types of distress often involves complex activities, sometimes inefficient and risky, as they interfere with road traffic. The mobile laser systems (MLS) are now widely used to acquire detailed information about the road surface in terms of a three-dimensional point cloud. Despite its increasing use, there are still no standards for the acquisition and processing of the data collected. The aim of our work was to develop a procedure for processing the data acquired by MLS, in order to identify the localized degradations that mostly affect safety. We have studied the data flow and implemented several processing algorithms to identify and quantify a few types of distresses, namely potholes and swells/shoves, starting from very dense point clouds. We have implemented data processing in four steps: (i) editing of the point cloud to extract only the points belonging to the road surface, (ii) determination of the road roughness as deviation in height of every single point of the cloud with respect to the modeled road surface, (iii) segmentation of the distress (iv) computation of the main geometric parameters of the distress in order to classify it by severity levels. The results obtained by the proposed methodology are promising. The procedures implemented have made it possible to correctly segmented and identify the types of distress to be analyzed, in accordance with the on-site inspections. The tests carried out have shown that the choice of the values of some parameters to give as input to the software is not trivial: the choice of some of them is based on considerations related to the nature of the data, for others, it derives from the distress to be segmented. Due to the different possible configurations of the various distresses it is better to choose these parameters according to the boundary conditions and not to impose default values. The test involved a 100-m long urban road segment, the surface of which was measured with an MLS installed on a vehicle that traveled the road at 10 km/h.

Download Full-text

Pole-like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road Scenes

Remote Sensing ◽

10.3390/rs13214382 ◽

2021 ◽

Vol 13 (21) ◽

pp. 4382

Author(s):

Ziyang Wang ◽

Lin Yang ◽

Yehua Sheng ◽

Mi Shen

Keyword(s):

High Precision ◽

Point Cloud ◽

Smart Cities ◽

Regional Growth ◽

Large Data ◽

Point Clouds ◽

Global Scale ◽

Structural Constraints ◽

Cloud Data ◽

The Road

Real-time acquisition and intelligent classification of pole-like street-object point clouds are of great significance in the construction of smart cities. Efficient point cloud processing technology in road scenes can accelerate the development of intelligent transportation and promote the development of high-precision maps. However, available algorithms have the problems of incomplete extraction and the low recognition accuracy of pole-like objects. In this paper, we propose a segmentation method of pole-like objects under geometric structural constraints. As for classification, we fused the classification results at different scales with each other. First, the point cloud data excluding ground point clouds were divided into voxels, and the rod-shaped parts of the pole-like objects were extracted according to the vertical continuity. Second, the regional growth based on the voxel was carried out based on the rod part to retain the non-rod part of the pole-like objects. A one-way double coding strategy was adopted to preserve the details. For spatial overlapping entities, we used multi-rule supervoxels to divide them. Finally, the random forest model was used to classify the pole-like objects based on local- and global-scale features and to fuse the double classification results under the different scales in order to obtain the final result. Experiments showed that the proposed method can effectively extract the pole-like objects of the point clouds in the road scenes, indicating that the method can achieve high-precision classification and identification in the lightweight data. Our method can also bring processing inspiration for large data.

Download Full-text

3D lidar point-cloud projection operator and transfer machine learning for effective road surface features detection and segmentation

The Visual Computer ◽

10.1007/s00371-021-02103-8 ◽

2021 ◽

Author(s):

Heyang Thomas Li ◽

Zachary Todd ◽

Nikolas Bielski ◽

Felix Carroll

Keyword(s):

Road Safety ◽

Point Cloud ◽

Point Clouds ◽

Road Surface ◽

Image Space ◽

Affine Transformations ◽

The Road ◽

Road Surfaces ◽

Computational Resources ◽

3D Lidar

AbstractThe classification and extraction of road markings and lanes are of critical importance to infrastructure assessment, planning and road safety. We present a pipeline for the accurate segmentation and extraction of rural road surface objects in 3D lidar point-cloud, as well as a method to extract geometric parameters belonging to tar seal. To decrease the computational resources needed, the point-clouds were aggregated into a 2D image space before being transformed using affine transformations. The Mask R-CNN algorithm is then applied to the transformed image space to localize, segment and classify the road objects. The segmentation results for road surfaces and markings can then be used for geometric parameter estimation such as road widths estimation, while the segmentation results show that the efficacy of the existing Mask R-CNN to segment needle-type objects is improved by our proposed transformations.

Download Full-text

ROAD SURFACE DETECTION FROM MOBILE LIDAR DATA

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-iv-5-95-2018 ◽

2018 ◽

Vol IV-5 ◽

pp. 95-101 ◽

Cited By ~ 1

Author(s):

M. Yadav ◽

B. Lohani ◽

A. K. Singh

Keyword(s):

Point Cloud ◽

Three Dimensional ◽

Test Site ◽

Road Surface ◽

Lidar Data ◽

Rural Roads ◽

The Road ◽

Surface Detection ◽

Rural Road ◽

Data Points

Abstract. The accurate three-dimensional road surface information is highly useful for health assessment and maintenance of roads. It is basic information for further analysis in several applications including road surface settlement, pavement condition assessment and slope collapse. Mobile LiDAR system (MLS) is frequently used now a days to collect detail road surface and its surrounding information in terms three-dimensional (3D) point cloud. Extraction of road surface from volumetric point cloud data is still in infancy stage because of heavy data processing requirement and the complexity in the road environment. The extraction of roads especially rural road, where road-curb is not present is very tedious job especially in Indian roadway settings. Only a few studies are available, and none for Indian roads, in the literature for rural road detection. The limitations of existing studies are in terms of their lower accuracy, very slow speed of data processing and detection of other objects having similar characteristics as the road surface. A fast and accurate method is proposed for LiDAR data points of road surface detection, keeping in mind the essence of road surface extraction especially for Indian rural roads. The Mobile LiDAR data in XYZI format is used as input in the proposed method. First square gridding is performed and ground points are roughly extracted. Then planar surface detection using mathematical framework of principal component analysis (PCA) is performed and further road surface points are detected using similarity in intensity and height difference of road surface pointe in their neighbourhood.A case study was performed on the MLS data points captured along wide-street (two-lane road without curb) of 156m length along rural roadway site in the outskirt of Bengaluru city (South-West of India). The proposed algorithm was implemented on the MLS data of test site and its performance was evaluated it terms of recall, precision and overall accuracy that were 95.27%, 98.85% and 94.23%, respectively. The algorithm was found computationally time efficient. A 7.6 million MLS data points of size 27.1MB from test site were processed in 24 minutes using the available computational resources. The proposed method is found to work even for worst case scenarios, i.e., complex road environments and rural roads, where road boundary is not clear and generally merged with road-side features.

Download Full-text

RAPID INSPECTION OF PAVEMENT MARKINGS USING MOBILE LIDAR POINT CLOUDS

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsarchives-xli-b1-717-2016 ◽

2016 ◽

Vol XLI-B1 ◽

pp. 717-723 ◽

Cited By ~ 1

Author(s):

Haocheng Zhang ◽

Jonathan Li ◽

Ming Cheng ◽

Cheng Wang

Keyword(s):

Decision Tree ◽

Case Studies ◽

Region Growing ◽

Software Tool ◽

Point Clouds ◽

Road Surface ◽

Pavement Markings ◽

The Road ◽

Pavement Marking ◽

Corrected Intensity

This study aims at building a robust semi-automated pavement marking extraction workflow based on the use of mobile LiDAR point clouds. The proposed workflow consists of three components: preprocessing, extraction, and classification. In preprocessing, the mobile LiDAR point clouds are converted into the radiometrically corrected intensity imagery of the road surface. Then the pavement markings are automatically extracted with the intensity using a set of algorithms, including Otsu’s thresholding, neighbor-counting filtering, and region growing. Finally, the extracted pavement markings are classified with the geometric parameters using a manually defined decision tree. Case studies are conducted using the mobile LiDAR dataset acquired in Xiamen (Fujian, China) with different road environments by the RIEGL VMX-450 system. The results demonstrated that the proposed workflow and our software tool can achieve 93% in completeness, 95% in correctness, and 94% in F-score when using Xiamen dataset.

Download Full-text

On the applicability of a scan-based mobile mapping system for monitoring the planarity and subsidence of road surfaces – Pilot study on the A44n motorway in Germany

Journal of Applied Geodesy ◽

10.1515/jag-2019-0016 ◽

2020 ◽

Vol 14 (1) ◽

pp. 39-54 ◽

Cited By ~ 1

Author(s):

Erik Heinz ◽

Christian Eling ◽

Lasse Klingbeil ◽

Heiner Kuhlmann

Keyword(s):

Standard Deviation ◽

Point Clouds ◽

Road Surface ◽

Control Points ◽

Mobile Mapping ◽

The Road ◽

Mapping System ◽

Road Surfaces ◽

Mobile Mapping System ◽

Physical Height

AbstractKinematic laser scanning is widely used for the fast and accurate acquisition of road corridors. In this context, road monitoring is a crucial application, since deficiencies of the road surface due to non-planarity and subsidence put traffic at risk. In recent years, a Mobile Mapping System (MMS) has been developed at the University of Bonn, consisting of a GNSS/IMU unit and a 2D laser scanner. The goal of this paper is to evaluate the accuracy and precision of this MMS, where the height component is of main interest. Following this, the applicability of the MMS for monitoring the planarity and subsidence of road surfaces is analyzed. The test area for this study is a 6 km long section of the A44n motorway in Germany. For the evaluation of the MMS, leveled control points along the motorway as well as point cloud comparisons of repeated passes were used. In order to transform the ellipsoidal heights of the MMS into the physical height system of the control points, undulations were utilized. In this respect, a local tilt correction for the geoid model was determined based on GNSS baselines and leveling, leading to a physical height accuracy of the MMS of < 10 mm (RMS). The related height precision has a standard deviation of about 5 mm. Hence, a potential subsidence of the road surface in the order of a few cm is detectable. In addition, the point clouds were used to analyze the planarity of the road surface. In the course of this, the cross fall of the road was estimated with a standard deviation of < 0.07 %. Yet, no deficiencies of the road surface in the form of significant rut depths or fictive water depths were detected, indicating the proper condition of the A44n motorway. According to our tests, the MMS is appropriate for road monitoring.

Download Full-text

Non-Rigid Vehicle-Borne LiDAR-Assisted Aerotriangulation

Remote Sensing ◽

10.3390/rs11101188 ◽

2019 ◽

Vol 11 (10) ◽

pp. 1188

Author(s):

Li Zheng ◽

Yuhao Li ◽

Meng Sun ◽

Zheng Ji ◽

Manzhu Yu ◽

...

Keyword(s):

Point Cloud ◽

Laser Scanning ◽

Point Clouds ◽

Necessary Condition ◽

Control Points ◽

The Road ◽

Aerial Vehicle ◽

Joint Mapping ◽

Close Range ◽

Uav Images

VLS (Vehicle-borne Laser Scanning) can easily scan the road surface in the close range with high density. UAV (Unmanned Aerial Vehicle) can capture a wider range of ground images. Due to the complementary features of platforms of VLS and UAV, combining the two methods becomes a more effective method of data acquisition. In this paper, a non-rigid method for the aerotriangulation of UAV images assisted by a vehicle-borne light detection and ranging (LiDAR) point cloud is proposed, which greatly reduces the number of control points and improves the automation. We convert the LiDAR point cloud-assisted aerotriangulation into a registration problem between two point clouds, which does not require complicated feature extraction and match between point cloud and images. Compared with the iterative closest point (ICP) algorithm, this method can address the non-rigid image distortion with a more rigorous adjustment model and a higher accuracy of aerotriangulation. The experimental results show that the constraint of the LiDAR point cloud ensures the high accuracy of the aerotriangulation, even in the absence of control points. The root-mean-square error (RMSE) of the checkpoints on the x, y, and z axes are 0.118 m, 0.163 m, and 0.084m, respectively, which verifies the reliability of the proposed method. As a necessary condition for joint mapping, the research based on VLS and UAV images in uncontrolled circumstances will greatly improve the efficiency of joint mapping and reduce its cost.

Download Full-text

POINT CLOUD TRANSFORMATION USING SENSOR CALIBRATION INFORMATION FOR MAP DATA ADJUSTMENT

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xliii-b3-2020-521-2020 ◽

2020 ◽

Vol XLIII-B3-2020 ◽

pp. 521-525

Author(s):

J. Lee ◽

J. Bae ◽

Y. Choi ◽

I. Park ◽

S. Hong ◽

...

Keyword(s):

High Precision ◽

Reference Point ◽

Autonomous Vehicles ◽

Point Cloud ◽

High Performance ◽

Location Information ◽

Delivery Vehicle ◽

The Road ◽

Road Sign ◽

Low Performance

Abstract. In order to operate autonomous vehicles and unmanned delivery vehicle, it is important to accurately acquire location of the device itself. However, since these devices are mainly operated in urban areas, there is a limit in obtaining location information based on GNSS. Therefore, it is necessary to utilize a method of calibrating its own location information by measuring the reference point provided by the existing high-precision map of the region. Point cloud based multi-dimensional high-precision maps are acquired in advance using high-performance LiDAR and GNSS devices for infrastructure such as roads, and provide a reference point for autonomous driving or map updating. Since such high-performance surveying equipment requires high cost, it is difficult to attach to autonomous vehicles or unmanned vehicle for commercialization. Therefore, autonomous vehicles or unmanned delivery vehicle are operated with relatively low performance LiDAR and GNSS, so it is often impossible to accurately measure the reference point, which directly leads to a decrease in the accuracy of the location information of the device. To compensate for this, this study proposes a point interpolation method to extract GCP information from sparse point cloud maps acquired with low performance LiDAR. The proposed method uses calibration parameters between point data and the image data acquired from the device. In general, images provide higher resolution than point clouds, even when using low-end cameras, so that the position of point coordinates relative to a reference point can be measured relatively accurately from the image and projection data of the point cloud. The data acquisition vehicle is an MMS vehicle that provides a panoramic image using four DSLRs and a point cloud with Velodyne VLP 16. The researchers first conducted a reference point survey on features such as road signs. The panorama image including the road sign was transformed into a bird eye’s view, and point projection was performed on the bird eye’s view image. The reference point coordinates, which were not acquired by the point cloud, were obtained from the shape of the road sign in the bird eye’s view image, and the accuracy was compared with the measured data.

Download Full-text

High-Precision Plane Detection Method for Rock-Mass Point Clouds Based on Supervoxel

Sensors ◽

10.3390/s20154209 ◽

2020 ◽

Vol 20 (15) ◽

pp. 4209

Author(s):

Dongbo Yu ◽

Jun Xiao ◽

Ying Wang

Keyword(s):

Rock Mass ◽

High Precision ◽

Point Cloud ◽

Region Growing ◽

Complex Surface ◽

Point Clouds ◽

Recall Rate ◽

Mass Point ◽

Surface Structures ◽

Superior Performance

In respect of rock-mass engineering, the detection of planar structures from the rock-mass point clouds plays a crucial role in the construction of a lightweight numerical model, while the establishment of high-quality models relies on the accurate results of surface analysis. However, the existing techniques are barely capable to segment the rock mass thoroughly, which is attributed to the cluttered and unpredictable surface structures of the rock mass. This paper proposes a high-precision plane detection approach for 3D rock-mass point clouds, which is effective in dealing with the complex surface structures, thus achieving a high level of detail in detection. Firstly, the input point cloud is fast segmented to voxels using spatial grids, while the local coplanarity test and the edge information calculation are performed to extract the major segments of planes. Secondly, to preserve as much detail as possible, supervoxel segmentation instead of traditional region growing is conducted to deal with scattered points. Finally, a patch-based region growing strategy applicable to rock mass is developed, while the completed planes are obtained by merging supervoxel patches. In this paper, an artificial icosahedron point cloud and four rock-mass point clouds are applied to validate the performance of the proposed method. As indicated by the experimental results, the proposed method can make high-precision plane detection achievable for rock-mass point clouds while ensuring high recall rate. Furthermore, the results of both qualitative and quantitative analyses evidence the superior performance of our algorithm.

Download Full-text