Mobile Light Detection And Ranging Data Research Articles

Designing and Building an Intelligent Pavement Management System for Urban Road Networks

Pavement maintenance plays a significant role in megacities. Managing complaints and scheduling road reviews are the two maintenance concerns under the intelligent pavement management system (PMS) plan. In contrast, if the damages are not treated immediately, they will increase over time. By leveraging accurate data from sensors, smart PMS will improve management capability, support sustainability, and drive economic growth in the road network. This research aimed to elaborate on the different modules of an intelligent city pavement network to advance to a sustainable city. First, a 3D mobile light detection and ranging (LiDAR) sensor, accompanied by a camera, was applied as the data collection tool. Although 3D mobile LiDAR data have gained popularity, they lack precise detection of pavement distresses, including cracks. As a result, utilizing RGB imaging may help to detect distresses properly. Two approaches were integrated alongside conducting the data analysis in this paper: (1) ArcGIS pro, developed by Esri Inc., which includes noise removal, digital elevation model (DEM) generation, and pavement and building footprint extraction; (2) the Mechanistic-Empirical Pavement Design Guide (AASHTOWare PMED), which was used to assess site specifications such as traffic, weather, subbase, and current pavement conditions in an effort to design the most appropriate pavement for each road section. For the 3D visualization module, CityEngine (a software from Esri) was used to provide the 3D city model. After implementing the research methodology, we drew the following conclusions: (1) using the AASHTOWare PMED method to make decisions about road maintenance and rehabilitation(M&R) actions can significantly speed up the decision-making process, essentially saving time and money and shortening the project’s duration; and (2) if the road conditions are similar, the smart geographical information system (GIS)-based PMS can make consistent decisions about road M&R strategies, i.e., the interference from human factors is less significant.

Automatic Registration for Panoramic Images and Mobile LiDAR Data Based on Phase Hybrid Geometry Index Features

The registration of panoramic images and mobile light detection and ranging (LiDAR) data is quite challenging because different imaging mechanisms and viewing angle differences generate significant geometric and radiation distortions between the two multimodal data sources. To address this problem, we propose a registration method for panoramic images and mobile LiDAR data based on the hybrid geometric structure index feature of phase. We use the initial GPS/IMU to transform the mobile LiDAR data into an intensity map and align the two images to complete registration. Firstly, a novel feature descriptor called a hybrid geometric structure index of phase (HGIFP) is built to capture the structural information of the images. Then, a set of corresponding feature points is obtained from the two images using the constructed feature descriptor combined with a robust false-match elimination algorithm. The average pixel distance of the corresponding feature points is used as the error function. Finally, in order to complete the accurate registration of the mobile LiDAR data and panoramic images and improve computational efficiency, we propose the assumption of local motion invariance of 3D–2D corresponding feature points and minimize the error function through multiple reprojections to achieve the best registration parameters. The experimental results show that the method in this paper can complete the registration of panoramic images and the mobile LiDAR data under a rotation error within 12° and a translation error within 2 m. After registration, the average error of rotation is about 0.15°, and the average error of translation is about 1.27 cm. Moreover, it achieves a registration accuracy of less than 3 pixels in all cases, which outperforms the current five state-of-the-art methods, demonstrating its superior registration performance.

Ground-based/UAV-LiDAR data fusion for quantitative structure modeling and tree parameter retrieval in subtropical planted forest

Light detection and ranging (LiDAR) has contributed immensely to forest mapping and 3D tree modelling. From the perspective of data acquisition, the integration of LiDAR data from different platforms would enrich forest information at the tree and plot levels. This research develops a general framework to integrate ground-based and UAV-LiDAR (ULS) data to better estimate tree parameters based on quantitative structure modelling (QSM). This is accomplished in three sequential steps. First, the ground-based/ULS LiDAR data were co-registered based on the local density peaks of the clustered canopy. Next, redundancy and noise were removed for the ground-based/ULS LiDAR data fusion. Finally, tree modeling and biophysical parameter retrieval were based on QSM. Experiments were performed for Backpack/Handheld/UAV-based multi-platform mobile LiDAR data of a subtropical forest, including poplar and dawn redwood species. Generally, ground-based/ULS LiDAR data fusion outperforms ground-based LiDAR with respect to tree parameter estimation compared to field data. The fusion-derived tree height, tree volume, and crown volume significantly improved by up to 9.01%, 5.28%, and 18.61%, respectively, in terms of r RMSE. By contrast, the diameter at breast height (DBH) is the parameter that has the least benefits from fusion, and r RMSE remains approximately the same, because stems are already well sampled from ground data. Additionally, particularly for dense forests, the fusion-derived tree parameters were improved compared to those derived from ground-based LiDAR. Ground-based LiDAR can potentially be used to estimate tree parameters in low-stand-density forests, whereby the improvement owing to fusion is not significant. • Mitigation of the limitations of tree localization in case of ground-based/ULS LiDAR data co-registration using virtual keypoints. • Fusion of ground-based/ULS LiDAR data based on removal of redundant and noisy points. • Investigation and evaluation of the utility of ground-based/ULS LiDAR data fusion for tree parameter estimation. • Ground-based/ULS LiDAR data fusion improved estimation of tree height, tree volume, and crown volume. • Ground-based/ULS LiDAR data fusion has strong potential in QSM of trees particularly in high-stand-density forest.

Impacts of point cloud density reductions on extracting road geometric features from mobile LiDAR data

The variation in point cloud density is driven by many different factors. This variation is expected to affect the quality of the information extracted from the point clouds, however, the extent to which these variations impact the ability to accurately extract and assess geometric features of highways from point cloud data are unknown. This paper investigates the impacts of point density reduction on the extraction and assessment of four critical geometric features. The density of light detection and ranging (LiDAR) data was first reduced and the different features were extracted at varying levels of point density and on a selection of different highway segments in Alberta, Canada. The information obtained at lower point density was then compared to what was obtained at 100% point density. It was found that clearance assessments and sight distance assessments had low sensitivity to reductions in point density (i.e., reducing the point density to as low as 10% of the original data (30 ppm2 on the pavement surface) yielded results comparable to what was obtained at 100% density (300 ppm2) In contrast, for cross section slope estimation and curve attribute estimation higher sensitivity to point density was observed. These findings are critical for transportation agencies considering the adoption of LiDAR technology to manage elements of their infrastructure and for researchers developing data processing tools and algorithms for the semantic segmentation of transportation features from remotely sensed point clouds.

Safety Assessment of Urban Intersection Sight Distance Using Mobile LiDAR Data

This paper proposes an automated framework that utilizes Light Detection and Ranging (LiDAR) point cloud data to map and detect road obstacles that impact drivers’ field of view at urban intersections. The framework facilitates the simulation of a driver’s field of vision to estimate the blockage percentage as they approach an intersection. Furthermore, a collision analysis is conducted to examine the relationship between poor visibility and safety. The visibility assessment was used to determine the blockage percentage as a function of intersection control type. The safety assessment indicated that intersections with limited available sight distances (ASD) exhibited an increased risk of collisions. The research also conducted a sensitivity analysis to understand the impact of the voxel size on the extraction of intersection obstacles from LiDAR datasets. The findings from this research can be used to assess the intersection without the burden of manual intervention. This would effectively support transportation agencies in identifying hazardous intersections with poor visibility and adopt policies to enhance urban intersections’ operation and safety.

Automated Assessment of Passing Sight Distance on Rural Highways using Mobile LiDAR Data

Providing sufficient Available Sight Distance (ASD) that meets the minimum design requirements is crucial for highway safety. Previous work on sight distance assessment focused on Stopping Sight Distance (SSD) with little attention given to Passing Sight Distance (PSD). Insufficient PSD could lead to severe collisions such as head-on and sideswipe crashes. To address this gap, this paper introduces an automated method for PSD assessment on two-lane highways using mobile Light Detection and Ranging (LiDAR) data. The procedure involved extracting centerline lane marking, defining passing-allowed and passing-prohibited regions, computing the ASD, and comparing the existing centerline marking pattern (i.e., passing and no-passing zones) to a proposed lane marking that is based on the ASD for passing maneuvers. Regions that meet the design standards, substandard zones, and non-optimal design regions were all defined. A reallocation of PSD zones was conducted based on the ASD including modifying the existing lane marking pattern, which resulted in increasing the total length of passing zones by up to 20%, providing more, but safer, passing opportunities. A high-level safety assessment of historical collisions showed clusters of crashes along regions where passing is currently allowed at locations where the ASD is less than standard requirements. The proposed framework represents a tool by which transportation agencies could assess PSD, upgrade the design of existing highways, and investigate the consequences of PSD limitations to ensure compliance with standards during highway service life.

Efficient segment-based ground filtering and adaptive road detection from mobile light detection and ranging (LiDAR) data

ABSTRACT Mobile light detection and ranging (LiDAR) has been widely applied to support a variety of tasks because it captures detailed three-dimensional data of a scene with high accuracy with reduced costs and time compared with many other techniques. Given the large volume of data within a mobile LiDAR point cloud, automation of processing and analysis is critical to improve the efficiency of the entire workflow, particularly for common tasks of ground filtering (separating points representing the ground from non-ground objects) and road detection (identifying and extracting the road surface). This paper proposes a novel and highly efficient method of segment-based ground filtering and adaptive road detection from mobile LiDAR data. The proposed method includes four principal steps: (1) preprocessing of the mobile LiDAR point cloud with data merging and splitting, (2) an improved Mo-norvana trajectory reconstruction and segmentation, (3) segment-based ground filtering via a segment analysis followed by a scanline analysis, and (4) road detection including an adaptive rasterization and vehicle access analysis. The proposed method is demonstrated to be robust, effective, and efficient by testing on representative datasets collected with different speeds in a rural/highway and an urban/suburban scene. The performance of our method is further evaluated quantitatively through a model-based accuracy assessment by comparison to a model generated from manually extracted ground points where the F 1 score and Root Mean Square Error of the elevation model are 98.14% and 0.0027 m, and 99.16% and 0.0004 m for the rural and suburban datasets, respectively.

Extraction of Road Lane Markings from Mobile LiDAR Data

This study presents a method for automatic extraction of road lane markings from mobile light detection and ranging (LiDAR) data. Road lanes and traffic signs on the road surface provide safe driving for drivers and aid traffic flow movement along the highway and street. Mobile LiDAR systems acquire massive datasets very quickly in a short time. To simplify the data structure and feature extraction, it is essential for traffic management personnel to apply the right methods. Road lanes must be visible and are a major factor in road safety for drivers. In this study, a methodology is devised and implemented for the extraction of features such as dashed lines, continuous lanes, and direction arrows on the pavement from point clouds. Point cloud data was collected from the Riegl VMX-450 mobile LiDAR system. The alpha shape algorithm is implemented on a point cloud and compared with the widespread use of edge detection techniques applied for intensity-based raster images. The proposed methodology directly extracts three-dimensional and two-dimensional road features to control the quality of road markings and spatial positions with the obtained marking boundaries. State-of-the-art results are obtained and compared with manually digitized reference markings. The standard deviations were evaluated and acquired for intensity image-based and direct point cloud-based extractions, at 1.2 cm and 1.7 cm, respectively.

Extraction of Street Pole-Like Objects Based on Plane Filtering From Mobile LiDAR Data

Pole-like objects provide important street infra- structure for road inventory and road mapping. In this article, we proposed a novel pole-like object extraction algorithm based on plane filtering from mobile Light Detection and Ranging (LiDAR) data. The proposed approach is composed of two parts. In the first part, a novel octree-based split scheme was proposed to fit initial planes from off-ground points. The results of the plane fitting contribute to the extraction of pole-like objects. In the second part, we proposed a novel method of pole-like object extraction by plane filtering based on local geometric feature restriction and isolation detection. The proposed approach is a new solution for detecting pole-like objects from mobile LiDAR data. The innovation in this article is that we assumed that each of the pole-like objects can be represented by a plane. Thus, the essence of extracting pole-like objects will be converted to plane selecting problem. The proposed method has been tested on three data sets captured from different scenes. The average completeness, correctness, and quality of our approach can reach up to 87.66%, 88.81%, and 79.03%, which is superior to state-of-the-art approaches. The experimental results indicate that our approach can extract pole-like objects robustly and efficiently.

A framework for automatic classification of mobile LiDAR data using multiple regions and 3D CNN architecture

ABSTRACT This paper proposes a framework for automatic classification of mobile laser scanner (MLS) point cloud using multi-faceted multi-object convolutional neural network (MMCN). The proposed method takes a full three-dimensional (3D) point cloud as input and outputs a class label for each point. Unlike other existing classification methods for MLS data, the proposed method is not dependent on any parameter or its tuning. The proposed MMCN uses multiple objects of a sample, defined by different sizes of the sample, in addition to the different facets obtained by rotating about the various axes, thus adding more information during the training and testing stages. The proposed framework uses manually extracted samples for training the MMCN. Automatically extracted multiple regions based on the various radii of spherical neighbourhoods around MLS points are passed through the trained MMCN for determining their probabilities of belonging to different classes. The class probabilities of different sized regions are then used as a feature vector to train a support vector machine (SVM), and the final decision for the class of a point is based on the SVM output. The proposed framework has been trained for five classes, viz., Ground, House, Pole, Tree, and Car and has been tested on Oakland and Paris-Lille 3D MLS datasets. The total accuracy and kappa coefficient (κ) reach up to 96.5% and 93.8%, respectively, for the framework. The MMCN together with the SVM is able to achieve parameter-free classification of MLS data, thereby eliminating the need for manual parameter tuning as in the existing methods. Therefore, besides the use for classification of MLS data for mapping purpose, the approach is also suitable for classification of light detection and ranging (LiDAR) data resulting from autonomous vehicle sensors. The accuracy of this work can be further improved by incorporating more and varied training samples and deeper convolutional neural network (CNN) with better hardware resources.

Pole-Like Street Furniture Segmentation and Classification in Mobile LiDAR Data by Integrating Multiple Shape-Descriptor Constraints

Nowadays, mobile laser scanning is widely used for understanding urban scenes, especially for extraction and recognition of pole-like street furniture, such as lampposts, traffic lights and traffic signs. However, the start-of-art methods may generate low segmentation accuracy in the overlapping scenes, and the object classification accuracy can be highly influenced by the large discrepancy in instance number of different objects in the same scene. To address these issues, we present a complete paradigm for pole-like street furniture segmentation and classification using mobile LiDAR (light detection and ranging) point cloud. First, we propose a 3D density-based segmentation algorithm which considers two different conditions including isolated furniture and connected furniture in overlapping scenes. After that, a vertical region grow algorithm is employed for component splitting and a new shape distribution estimation method is proposed to obtain more accurate global shape descriptors. For object classification, an integrated shape constraint based on the splitting result of pole-like street furniture (SplitISC) is introduced and integrated into a retrieval procedure. Two test datasets are used to verify the performance and effectiveness of the proposed method. The experimental results demonstrate that the proposed method can achieve better classification results from both sites than the existing shape distribution method.

Preregistration Classification of Mobile LIDAR Data Using Spatial Correlations

We explore a novel paradigm for light detection and ranging (LIDAR) point classification in mobile laser scanning (MLS). In contrast to the traditional scheme of performing classification for a 3-D point cloud after registration, our algorithm operates on the raw data stream classifying the points on-the-fly before registration. Hence, we call it preregistration classification (PRC). Specifically, this technique is based on spatial correlations, i.e., local range measurements supporting each other. The proposed method is general since exact scanner pose information is not required, nor is any radiometric calibration needed. Also, we show that the method can be applied in different environments by adjusting two control parameters, without the results being overly sensitive to this adjustment. As results, we present classification of points from an urban environment where noise, ground, buildings, and vegetation are distinguished from each other, and points from the forest where tree stems and ground are classified from the other points. As computations are efficient and done with a minimal cache, the proposed methods enable new on-chip deployable algorithmic solutions. Broader benefits from the spatial correlations and the computational efficiency of the PRC scheme are likely to be gained in several online and offline applications. These range from single robotic platform operations including simultaneous localization and mapping (SLAM) algorithms to wall-clock time savings in geoinformation industry. Finally, PRC is especially attractive for continuous-beam and solid-state LIDARs that are prone to output noisy data.

Semiautomatic Construction of 2-D Façade Footprints From Mobile LiDAR Data

Although mobile light detection and ranging (LiDAR) technology has excellent potential in mapping street scenes, there is little research in constructing facade footprints from unorganized, uneven, and incomplete mobile LiDAR point clouds. In fact, facade footprint vectorization from mobile LiDAR data still involves a lot of manual work, especially in complex street scenes with various types of buildings. In this paper, we present a new and effective framework for extracting 2-D facade footprints from mobile LiDAR point clouds. The proposed framework consists of three steps: 1) line segment extraction from projected point clouds based on a hypotheses and selection strategy; 2) completion of missing parts between adjacent walls using line intersections; and 3) delineation of footprints through finding the least cost path in the graph of the line segments. We compare our method with several existing ones and discuss its robustness against data missing and noise such as nonwall structures and vegetation. Our proposed method is also tested in two large-scale data sets, a residential data set, and an urban data set. The coverage ratio, i.e., the percentage of outer wall points covered by the generated outlines in the residential data set is 93.4% and 91.7% in the urban data set is achieved. The mean distance between points of ground truth and constructed footprints for the residential data set and urban data set is 0.019 and 0.028 m, respectively. The experimental results demonstrate that the proposed framework is effective in modeling various facade footprints from mobile LiDAR point clouds.

Automated traffic sign and light pole detection in mobile LiDAR scanning data

Detection of traffic signs and light poles using light detection and ranging (LiDAR) data has demonstrated a valid contribution to road safety improvements. In this study, the authors propose a fast and reliable method, which can identify various traffic signs and light poles in mobile LiDAR data. Specifically, they first use the surface reconstruction algorithm to extract the normal vectors of the points as one of the characteristic features and apply k-means on the characteristic features of the points to automatically segment the data into road or non-road points. They then employ sliding cuboids to search for high-elevated objects that are located near the borders and on top of the road points. They further employ the random sample consensus algorithm to remove outliers and keep the points that fall on the perpendicular planes to the road trajectory. Finally, they introduce a modified seeded region growing algorithm to remove noisy points and incorporate the shape information to reject the false objects. A set of extensive experiments have been carried out on the datasets that are captured by Utah Department of Transportation from I-15 highway. The results demonstrate the robustness of the proposed method in detecting almost all traffic signs and light poles.

Automatic extraction of pavement markings on streets from point cloud data of mobile LiDAR

Pavement markings provide an important foundation as they help to keep roads users safe. Accurate and comprehensive information about pavement markings assists the road regulators and is useful in developing driverless technology. Mobile light detection and ranging (LiDAR) systems offer new opportunities to collect and process accurate pavement markings’ information. Mobile LiDAR systems can directly obtain the three-dimensional (3D) coordinates of an object, thus defining spatial data and the intensity of (3D) objects in a fast and efficient way. The RGB attribute information of data points can be obtained based on the panoramic camera in the system. In this paper, we present a novel method process to automatically extract pavement markings using multiple attribute information of the laser scanning point cloud from the mobile LiDAR data. This method process utilizes a differential grayscale of RGB color, laser pulse reflection intensity, and the differential intensity to identify and extract pavement markings. We utilized point cloud density to remove the noise and used morphological operations to eliminate the errors. In the application, we tested our method process on different sections of roads in Beijing, China, and Buffalo, NY, USA. The results indicated that both correctness (p) and completeness (r) were higher than 90%. The method process of this research can be applied to extract pavement markings from huge point cloud data produced by mobile LiDAR.

Automated As-Built Model Generation of Subway Tunnels from Mobile LiDAR Data.

This study proposes fully-automated methods for as-built model generation of subway tunnels employing mobile Light Detection and Ranging (LiDAR) data. The employed dataset is acquired by a Velodyne HDL 32E and covers 155 m of a subway tunnel containing six million points. First, the tunnel’s main axis and cross sections are extracted. Next, a preliminary model is created by fitting an ellipse to each extracted cross section. The model is refined by employing residual analysis and Baarda’s data snooping method to eliminate outliers. The final model is then generated by applying least squares adjustment to outlier-free data. The obtained results indicate that the tunnel’s main axis and 1551 cross sections at 0.1 m intervals are successfully extracted. Cross sections have an average semi-major axis of 7.8508 m with a standard deviation of 0.2 mm and semi-minor axis of 7.7509 m with a standard deviation of 0.1 mm. The average normal distance of points from the constructed model (average absolute error) is also 0.012 m. The developed algorithm is applicable to tunnels with any horizontal orientation and degree of curvature since it makes no assumptions, nor does it use any a priori knowledge regarding the tunnel’s curvature and horizontal orientation.

POLE-LIKE OBJECT EXTRACTION FROM MOBILE LIDAR DATA

Abstract. Object detection and recognition from LiDAR (Light Detection And Ranging) data has been a research topic in the fields of photogrammetry and computer vision. Unlike point clouds collected in well-controlled indoor environments, point clouds in urban environments are more complex due to complexity of the real world. For example, trees sometimes close to signs or buildings, which will cause occlusions in the point clouds. Current object detection or reconstruction algorithms will have problems when recognizing objects with severe occlusions caused by trees etc. In this paper, a robust vegetation removal method and a DBSCAN based pole-like object detection method are proposed. Based on observation that major difference between vegetation and other rigid objects is their penetrability with respect to LiDAR, we introduce a local roughness measure to differentiate rigid objects from non-rigid ones (vegetation in this paper). First, a local sphere with a small radius is generated for each input point. Three principal components of the local sphere are then calculated, and a plane is determined. The roughness is obtained through calculating the standard deviation of distances from all inside points to the plane by a weighted summation of the normalized distances. The further the point to the plane, the smaller the weight is. Finally, a graph cuts based method is introduced to classify the input point sets into two groups. The data term is defined by the normalized roughness of the current point, and the smoothness term is defined by the normalized distance between the point and its nearest neighbour point. In terms of pole-like object detection, first, a uniformed 2D grid is generated through projecting all the points to the XY-plane. The seed points of the pole-like objects are obtained by determining the x and y coordinates by the centres of the highest density cells of the grid and the z coordinate by the mean height of the point sets of each object. Finally, a DBSCAN based method is introduced to obtain the rest points of each pole-like object. Experimental results show that the proposed vegetation removal method achieves state-of-the-art results from both mobile LiDAR and airborne LiDAR data. The proposed pole-like object detection approach turns out to be very efficient.

POLE-LIKE OBJECT EXTRACTION FROM MOBILE LIDAR DATA

Object detection and recognition from LiDAR (Light Detection And Ranging) data has been a research topic in the fields of photogrammetry and computer vision. Unlike point clouds collected in well-controlled indoor environments, point clouds in urban environments are more complex due to complexity of the real world. For example, trees sometimes close to signs or buildings, which will cause occlusions in the point clouds. Current object detection or reconstruction algorithms will have problems when recognizing objects with severe occlusions caused by trees etc. In this paper, a robust vegetation removal method and a DBSCAN based pole-like object detection method are proposed. Based on observation that major difference between vegetation and other rigid objects is their penetrability with respect to LiDAR, we introduce a local roughness measure to differentiate rigid objects from non-rigid ones (vegetation in this paper). First, a local sphere with a small radius is generated for each input point. Three principal components of the local sphere are then calculated, and a plane is determined. The roughness is obtained through calculating the standard deviation of distances from all inside points to the plane by a weighted summation of the normalized distances. The further the point to the plane, the smaller the weight is. Finally, a graph cuts based method is introduced to classify the input point sets into two groups. The data term is defined by the normalized roughness of the current point, and the smoothness term is defined by the normalized distance between the point and its nearest neighbour point. In terms of pole-like object detection, first, a uniformed 2D grid is generated through projecting all the points to the XY-plane. The seed points of the pole-like objects are obtained by determining the x and y coordinates by the centres of the highest density cells of the grid and the z coordinate by the mean height of the point sets of each object. Finally, a DBSCAN based method is introduced to obtain the rest points of each pole-like object. Experimental results show that the proposed vegetation removal method achieves state-of-the-art results from both mobile LiDAR and airborne LiDAR data. The proposed pole-like object detection approach turns out to be very efficient.

Pole-Like Road Object Detection in Mobile LiDAR Data via Supervoxel and Bag-of-Contextual-Visual-Words Representation

This letter addresses the problem of detecting pole-like road objects (including light poles and traffic signposts) from mobile light detection and ranging (LiDAR) data for transportation-related applications. The method consists of two consecutive stages: training and pole-like object detection. At the training stage, a contextual visual vocabulary is created from the feature regions generated from a training data set by supervoxel segmentation. At the pole-like object detection stage, a bag-of-contextual-visual-words representation is generated for each semantic object segmented from mobile LiDAR data. The experimental results show that the proposed method achieves correctness, omission, and commission of 88.9%, 11.1%, and 2.8%, respectively, in detecting pole-like road objects. Computational complexity analysis demonstrates that our method provides a promising and effective solution to rapid and accurate detection of pole-like objects from large volumes of mobile LiDAR data.

An automated sign retroreflectivity condition evaluation methodology using mobile LIDAR and computer vision

Traffic sign retroreflectivity condition is one of the most critical factors impacting nighttime driving safety. The federal rule on minimum traffic sign retroreflectivity incorporated in the 2009 Manual on Uniform Traffic Control Devices (MUTCD) issued by the Federal Highway Administration (FHWA) is compelling transportation agencies to evaluate how to comply. As the traditional manual methods have become financially and/or practically infeasible, there is an urgent need for an effective and efficient retroreflectivity evaluation method. This paper investigates the possibility and proposes a methodology for automatically evaluating traffic sign retroreflectivity condition using mobile light detection and ranging (LIDAR) and computer vision. The proposed methodology uses (a) the traffic sign detection and color segmentation methods that are introduced for the first time to evaluate the retroreflectivity of different traffic sign colors separately in an automated manner; (b) the proposed theoretical-empirical LIDAR retro-intensity normalization scheme to more reliably model the radiometric responses of traffic sign captured in the mobile LIDAR data; (c) the population-based condition assessment method for the first time to statistically quantify the retroreflectivity condition of traffic signs rather than an four-point average. An experimental test was conducted on 35 Type I Engineer Grade stop signs. The result shows that the proposed methodology can produce a promising outcome with consistent retroreflectivity evaluations based on handheld retroreflectometer measurements; the proposed methodology can, also, better identify traffic signs with non-homogeneous deteriorated retroreflectivity. The reliable retroreflectivity evaluation results make the proposed methodology an appealing alternative for transportation agencies to use to comply with the FHWA’s requirement.