scholarly journals Deep Localization of Static Scans in Mobile Mapping Point Clouds

2021 ◽  
Vol 13 (2) ◽  
pp. 219
Author(s):  
Yufu Zang ◽  
Fancong Meng ◽  
Roderik Lindenbergh ◽  
Linh Truong-Hong ◽  
Bijun Li
Keyword(s):  
Neural Network ◽  
Laser Scanning ◽  
Large Scale ◽  
Reference Data ◽  
Point Clouds ◽  
Autonomous Driving ◽  
Place Recognition ◽  
Global Features ◽  
Mobile Mapping ◽  
Mapping Point

Mobile laser scanning (MLS) systems are often used to efficiently acquire reference data covering a large-scale scene. The terrestrial laser scanner (TLS) can easily collect high point density data of local scene. Localization of static TLS scans in mobile mapping point clouds can afford detailed geographic information for many specific tasks especially in autonomous driving and robotics. However, large-scale MLS reference data often have a huge amount of data and many similar scene data; significant differences may exist between MLS and TLS data. To overcome these challenges, this paper presents a novel deep neural network-based localization method in urban environment, divided by place recognition and pose refinement. Firstly, simple, reliable primitives, cylinder-like features were extracted to describe the global features of a local urban scene. Then, a probabilistic framework is applied to estimate a similarity between TLS and MLS data, under a stable decision-making strategy. Based on the results of a place recognition, we design a patch-based convolution neural network (CNN) (point-based CNN is used as kernel) for pose refinement. The input data unit is the batch consisting of several patches. One patch goes through three main blocks: feature extraction block (FEB), the patch correspondence search block and the pose estimation block. Finally, a global refinement was proposed to tune the predicted transformation parameters to realize localization. The research aim is to find the most similar scene of MLS reference data compared with the local TLS scan, and accurately estimate the transformation matrix between them. To evaluate the performance, comprehensive experiments were carried out. The experiments demonstrate that the proposed method has good performance in terms of efficiency, i.e., the runtime of processing a million points is 5 s, robustness, i.e., the success rate of place recognition is 100% in the experiments, accuracy, i.e., the mean rotation and translation error is (0.24 deg, 0.88 m) and (0.03 deg, 0.06 m) on TU Delft campus and Shanghai urban datasets, respectively, and outperformed some commonly used methods (e.g., iterative closest point (ICP), coherent point drift (CPD), random sample consensus (RANSAC)-based method).

scholarly journals THE IQMULUS URBAN SHOWCASE: AUTOMATIC TREE CLASSIFICATION AND IDENTIFICATION IN HUGE MOBILE MAPPING POINT CLOUDS

2016 ◽  
Vol XLI-B3 ◽  
pp. 301-307
Author(s):  
J. Böhm ◽  
M. Bredif ◽  
T. Gierlinger ◽  
M. Krämer ◽  
R. Lindenberg ◽  
...  
Keyword(s):  
Spatial Data ◽  
Laser Scanning ◽  
Point Clouds ◽  
Urban Trees ◽  
Automatic Identification ◽  
Mobile Mapping ◽  
3D Data ◽  
Hadoop Distributed File System ◽  
Individual Trees ◽  
Mapping Point

Current 3D data capturing as implemented on for example airborne or mobile laser scanning systems is able to efficiently sample the surface of a city by billions of unselective points during one working day. What is still difficult is to extract and visualize meaningful information hidden in these point clouds with the same efficiency. This is where the FP7 IQmulus project enters the scene. IQmulus is an interactive facility for processing and visualizing big spatial data. In this study the potential of IQmulus is demonstrated on a laser mobile mapping point cloud of 1 billion points sampling ~ 10 km of street environment in Toulouse, France. After the data is uploaded to the IQmulus Hadoop Distributed File System, a workflow is defined by the user consisting of retiling the data followed by a PCA driven local dimensionality analysis, which runs efficiently on the IQmulus cloud facility using a Spark implementation. Points scattering in 3 directions are clustered in the tree class, and are separated next into individual trees. Five hours of processing at the 12 node computing cluster results in the automatic identification of 4000+ urban trees. Visualization of the results in the IQmulus fat client helps users to appreciate the results, and developers to identify remaining flaws in the processing workflow.

scholarly journals ACCURACY ASSESSMENT OF MOBILE MAPPING POINT CLOUDS USING THE EXISTING ENVIRONMENT AS TERRESTRIAL REFERENCE

2016 ◽  
Vol XLI-B1 ◽  
pp. 601-608 ◽  
Author(s):  
S. Hofmann ◽  
C. Brenner
Keyword(s):  
Point Cloud ◽  
Reference Data ◽  
Geodetic Network ◽  
Point Clouds ◽  
Test Field ◽  
Mobile Mapping ◽  
Total Station ◽  
Processed Products ◽  
Mapping Point

Mobile mapping data is widely used in various applications, what makes it especially important for data users to get a statistically verified quality statement on the geometric accuracy of the acquired point clouds or its processed products. The accuracy of point clouds can be divided into an absolute and a relative quality, where the absolute quality describes the position of the point cloud in a world coordinate system such as WGS84 or UTM, whereas the relative accuracy describes the accuracy within the point cloud itself. Furthermore, the quality of processed products such as segmented features depends on the global accuracy of the point cloud but mainly on the quality of the processing steps. Several data sources with different characteristics and quality can be thought of as potential reference data, such as cadastral maps, orthophoto, artificial control objects or terrestrial surveys using a total station. In this work a test field in a selected residential area was acquired as reference data in a terrestrial survey using a total station. In order to reach high accuracy the stationing of the total station was based on a newly made geodetic network with a local accuracy of less than 3 mm. The global position of the network was determined using a long time GNSS survey reaching an accuracy of 8 mm. Based on this geodetic network a 3D test field with facades and street profiles was measured with a total station, each point with a two-dimensional position and altitude. In addition, the surface of poles of street lights, traffic signs and trees was acquired using the scanning mode of the total station. <br><br> Comparing this reference data to the acquired mobile mapping point clouds of several measurement campaigns a detailed quality statement on the accuracy of the point cloud data is made. Additionally, the advantages and disadvantages of the described reference data source concerning availability, cost, accuracy and applicability are discussed.

scholarly journals ACCURACY ASSESSMENT OF MOBILE MAPPING POINT CLOUDS USING THE EXISTING ENVIRONMENT AS TERRESTRIAL REFERENCE

2016 ◽  
Vol XLI-B1 ◽  
pp. 601-608
Author(s):  
S. Hofmann ◽  
C. Brenner
Keyword(s):  
Point Cloud ◽  
Reference Data ◽  
Geodetic Network ◽  
Point Clouds ◽  
Test Field ◽  
Mobile Mapping ◽  
Total Station ◽  
Processed Products ◽  
Mapping Point

Mobile mapping data is widely used in various applications, what makes it especially important for data users to get a statistically verified quality statement on the geometric accuracy of the acquired point clouds or its processed products. The accuracy of point clouds can be divided into an absolute and a relative quality, where the absolute quality describes the position of the point cloud in a world coordinate system such as WGS84 or UTM, whereas the relative accuracy describes the accuracy within the point cloud itself. Furthermore, the quality of processed products such as segmented features depends on the global accuracy of the point cloud but mainly on the quality of the processing steps. Several data sources with different characteristics and quality can be thought of as potential reference data, such as cadastral maps, orthophoto, artificial control objects or terrestrial surveys using a total station. In this work a test field in a selected residential area was acquired as reference data in a terrestrial survey using a total station. In order to reach high accuracy the stationing of the total station was based on a newly made geodetic network with a local accuracy of less than 3 mm. The global position of the network was determined using a long time GNSS survey reaching an accuracy of 8 mm. Based on this geodetic network a 3D test field with facades and street profiles was measured with a total station, each point with a two-dimensional position and altitude. In addition, the surface of poles of street lights, traffic signs and trees was acquired using the scanning mode of the total station. <br><br> Comparing this reference data to the acquired mobile mapping point clouds of several measurement campaigns a detailed quality statement on the accuracy of the point cloud data is made. Additionally, the advantages and disadvantages of the described reference data source concerning availability, cost, accuracy and applicability are discussed.

scholarly journals Go Wider: An Efficient Neural Network for Point Cloud Analysis via Group Convolutions

2020 ◽  
Vol 10 (7) ◽  
pp. 2391
Author(s):  
Can Chen ◽  
Luca Zanotti Fragonara ◽  
Antonios Tsourdos
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Point Cloud ◽  
Large Scale ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Autonomous Driving ◽  
Fine Grained ◽  
Point Cloud Analysis ◽  
Cloud Analysis

In order to achieve a better performance for point cloud analysis, many researchers apply deep neural networks using stacked Multi-Layer-Perceptron (MLP) convolutions over an irregular point cloud. However, applying these dense MLP convolutions over a large amount of points (e.g., autonomous driving application) leads to limitations due to the computation and memory capabilities. To achieve higher performances but decrease the computational complexity, we propose a deep-wide neural network, named ShufflePointNet, which can exploit fine-grained local features, but also reduce redundancies using group convolution and channel shuffle operation. Unlike conventional operations that directly apply MLPs on the high-dimensional features of a point cloud, our model goes “wider” by splitting features into groups with smaller depth in advance, having the respective MLP computations applied only to a single group, which can significantly reduce complexity and computation. At the same time, we allow communication between groups by shuffling the feature channel to capture fine-grained features. We further discuss the multi-branch method for wider neural networks being also beneficial to feature extraction for point clouds. We present extensive experiments for shape classification tasks on a ModelNet40 dataset and semantic segmentation task on large scale datasets ShapeNet part, S3DIS and KITTI. Finally, we carry out an ablation study and compare our model to other state-of-the-art algorithms to show its efficiency in terms of complexity and accuracy.

scholarly journals IMPROVING GPS TRAJECTORIES USING 3D CITY MODELS AND KINEMATIC POINT CLOUDS

2019 ◽  
Vol IV-4/W9 ◽  
pp. 35-42 ◽  
Author(s):  
Y. Dehbi ◽  
L. Lucks ◽  
J. Behmann ◽  
L. Klingbeil ◽  
L. Plümer
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Point Clouds ◽  
Autonomous Driving ◽  
Urban Environments ◽  
Support Vector ◽  
Mobile Mapping ◽  
General Applicability ◽  
Data Set ◽  
Building Models

Abstract. Accurate and robust positioning of vehicles in urban environments is of high importance for many applications (e.g. autonomous driving or mobile mapping). In the case of mobile mapping systems, a simultaneous mapping of the environment using laser scanning and an accurate positioning using GNSS is targeted. This requirement is often not guaranteed in shadowed cities where GNSS signals are usually disturbed, weak or even unavailable. Both, the generated point clouds and the derived trajectory are consequently imprecise. We propose a novel approach which incorporates prior knowledge, i.e. 3D building model of the environment, and improves the point cloud and the trajectory. The key idea is to benefit from the complementarity of both GNSS and 3D building models. The point cloud is matched to the city model using a point-to-plane ICP. An informed sampling of appropriate matching points is enabled by a pre-classification step. Support vector machines (SVMs) are used to discriminate between facade and remaining points. Local inconsistencies are tackled by a segment-wise partitioning of the point cloud where an interpolation guarantees a seamless transition between the segments. The full processing chain is implemented from the detection of facades in the point clouds, the matching between them and the building models and the update of the trajectory estimate. The general applicability of the implemented method is demonstrated on an inner city data set recorded with a mobile mapping system.

scholarly journals THE IQMULUS URBAN SHOWCASE: AUTOMATIC TREE CLASSIFICATION AND IDENTIFICATION IN HUGE MOBILE MAPPING POINT CLOUDS

2016 ◽  
Vol XLI-B3 ◽  
pp. 301-307 ◽  
Author(s):  
J. Böhm ◽  
M. Bredif ◽  
T. Gierlinger ◽  
M. Krämer ◽  
R. Lindenberg ◽  
...  
Keyword(s):  
Spatial Data ◽  
Laser Scanning ◽  
Point Clouds ◽  
Urban Trees ◽  
Automatic Identification ◽  
Mobile Mapping ◽  
3D Data ◽  
Hadoop Distributed File System ◽  
Individual Trees ◽  
Mapping Point

Current 3D data capturing as implemented on for example airborne or mobile laser scanning systems is able to efficiently sample the surface of a city by billions of unselective points during one working day. What is still difficult is to extract and visualize meaningful information hidden in these point clouds with the same efficiency. This is where the FP7 IQmulus project enters the scene. IQmulus is an interactive facility for processing and visualizing big spatial data. In this study the potential of IQmulus is demonstrated on a laser mobile mapping point cloud of 1 billion points sampling ~ 10 km of street environment in Toulouse, France. After the data is uploaded to the IQmulus Hadoop Distributed File System, a workflow is defined by the user consisting of retiling the data followed by a PCA driven local dimensionality analysis, which runs efficiently on the IQmulus cloud facility using a Spark implementation. Points scattering in 3 directions are clustered in the tree class, and are separated next into individual trees. Five hours of processing at the 12 node computing cluster results in the automatic identification of 4000+ urban trees. Visualization of the results in the IQmulus fat client helps users to appreciate the results, and developers to identify remaining flaws in the processing workflow.

scholarly journals SEMANTIC LABELLING OF ROAD FURNITURE IN MOBILE LASER SCANNING DATA

2017 ◽  
Vol XLII-2/W7 ◽  
pp. 247-254 ◽  
Author(s):  
F. Li ◽  
S. Oude Elberink ◽  
G. Vosselman
Keyword(s):  
Laser Scanning ◽  
Large Scale ◽  
Point Clouds ◽  
Autonomous Driving ◽  
Urban Environments ◽  
3D Point Clouds ◽  
Promising Solution ◽  
Novel Method ◽  
Detailed Interpretation ◽  
Semantic Labelling

Road furniture semantic labelling is vital for large scale mapping and autonomous driving systems. Much research has been investigated on road furniture interpretation in both 2D images and 3D point clouds. Precise interpretation of road furniture in mobile laser scanning data still remains unexplored. In this paper, a novel method is proposed to interpret road furniture based on their logical relations and functionalities. Our work represents the most detailed interpretation of road furniture in mobile laser scanning data. 93.3&amp;thinsp;% of poles are correctly extracted and all of them are correctly recognised. 94.3&amp;thinsp;% of street light heads are detected and 76.9&amp;thinsp;% of them are correctly identified. Despite errors arising from the recognition of other components, our framework provides a promising solution to automatically map road furniture at a detailed level in urban environments.

scholarly journals Segmentation and Multi-Scale Convolutional Neural Network-Based Classification of Airborne Laser Scanner Data

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3347 ◽  
Author(s):  
Zhishuang Yang ◽  
Bo Tan ◽  
Huikun Pei ◽  
Wanshou Jiang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Laser Scanning ◽  
Laser Scanner ◽  
Region Growing ◽  
Point Clouds ◽  
Classification Method ◽  
Multi Scale ◽  
Airborne Laser

The classification of point clouds is a basic task in airborne laser scanning (ALS) point cloud processing. It is quite a challenge when facing complex observed scenes and irregular point distributions. In order to reduce the computational burden of the point-based classification method and improve the classification accuracy, we present a segmentation and multi-scale convolutional neural network-based classification method. Firstly, a three-step region-growing segmentation method was proposed to reduce both under-segmentation and over-segmentation. Then, a feature image generation method was used to transform the 3D neighborhood features of a point into a 2D image. Finally, feature images were treated as the input of a multi-scale convolutional neural network for training and testing tasks. In order to obtain performance comparisons with existing approaches, we evaluated our framework using the International Society for Photogrammetry and Remote Sensing Working Groups II/4 (ISPRS WG II/4) 3D labeling benchmark tests. The experiment result, which achieved 84.9% overall accuracy and 69.2% of average F1 scores, has a satisfactory performance over all participating approaches analyzed.

scholarly journals Automated Visual Recognizability Evaluation of Traffic Sign Based on 3D LiDAR Point Clouds

2019 ◽  
Vol 11 (12) ◽  
pp. 1453 ◽  
Author(s):  
Shanxin Zhang ◽  
Cheng Wang ◽  
Lili Lin ◽  
Chenglu Wen ◽  
Chenhui Yang ◽  
...  
Keyword(s):  
Traffic Safety ◽  
Laser Scanning ◽  
Large Scale ◽  
Evaluation Method ◽  
Evaluation Model ◽  
Point Clouds ◽  
Traffic Sign ◽  
Traffic Signs ◽  
3D Point Clouds ◽  
Traffic Environment

Maintaining the high visual recognizability of traffic signs for traffic safety is a key matter for road network management. Mobile Laser Scanning (MLS) systems provide efficient way of 3D measurement over large-scale traffic environment. This paper presents a quantitative visual recognizability evaluation method for traffic signs in large-scale traffic environment based on traffic recognition theory and MLS 3D point clouds. We first propose the Visibility Evaluation Model (VEM) to quantitatively describe the visibility of traffic sign from any given viewpoint, then we proposed the concept of visual recognizability field and Traffic Sign Visual Recognizability Evaluation Model (TSVREM) to measure the visual recognizability of a traffic sign. Finally, we present an automatic TSVREM calculation algorithm for MLS 3D point clouds. Experimental results on real MLS 3D point clouds show that the proposed method is feasible and efficient.

Sign in / Sign up

Export Citation Format

Share Document