scholarly journals ROAD SEGMENTATION ON LOW RESOLUTION LIDAR POINT CLOUDS FOR AUTONOMOUS VEHICLES

2020 ◽  
Vol V-2-2020 ◽  
pp. 335-342
Author(s):  
L. Gigli ◽  
B. R. Kiran ◽  
T. Paul ◽  
A. Serna ◽  
N. Vemuri ◽  
...  
Keyword(s):  
Autonomous Vehicles ◽  
Point Cloud ◽  
Negative Impact ◽  
Point Clouds ◽  
Autonomous Driving ◽  
Normal Vector ◽  
Low Resolution ◽  
Subsequent Transformation ◽  
Dense Point ◽  
Road Segmentation

Abstract. Point cloud datasets for perception tasks in the context of autonomous driving often rely on high resolution 64-layer Light Detection and Ranging (LIDAR) scanners. They are expensive to deploy on real-world autonomous driving sensor architectures which usually employ 16/32 layer LIDARs. We evaluate the effect of subsampling image based representations of dense point clouds on the accuracy of the road segmentation task. In our experiments the low resolution 16/32 layer LIDAR point clouds are simulated by subsampling the original 64 layer data, for subsequent transformation in to a feature map in the Bird-Eye-View(BEV) and Spherical-View (SV) representations of the point cloud. We introduce the usage of the local normal vector with the LIDAR’s spherical coordinates as an input channel to existing LoDNN architectures. We demonstrate that this local normal feature in conjunction with classical features not only improves performance for binary road segmentation on full resolution point clouds, but it also reduces the negative impact on the accuracy when subsampling dense point clouds as compared to the usage of classical features alone. We assess our method with several experiments on two datasets: KITTI Road-segmentation benchmark and the recently released Semantic KITTI dataset.

scholarly journals LIDAR Point Cloud Registration for Sensing and Reconstruction of Unstructured Terrain

2018 ◽  
Vol 8 (11) ◽  
pp. 2318 ◽  
Author(s):  
Qingyuan Zhu ◽  
Jinjin Wu ◽  
Huosheng Hu ◽  
Chunsheng Xiao ◽  
Wei Chen
Keyword(s):  
Autonomous Vehicles ◽  
Point Cloud ◽  
Laser Scanning ◽  
Point Clouds ◽  
Normal Vector ◽  
Registration Method ◽  
High Noise ◽  
Key Points ◽  
Scanning Lidar ◽  
Multisensor Data

When 3D laser scanning (LIDAR) is used for navigation of autonomous vehicles operated on unstructured terrain, it is necessary to register the acquired point cloud and accurately perform point cloud reconstruction of the terrain in time. This paper proposes a novel registration method to deal with uneven-density and high-noise of unstructured terrain point clouds. It has two steps of operation, namely initial registration and accurate registration. Multisensor data is firstly used for initial registration. An improved Iterative Closest Point (ICP) algorithm is then deployed for accurate registration. This algorithm extracts key points and builds feature descriptors based on the neighborhood normal vector, point cloud density and curvature. An adaptive threshold is introduced to accelerate iterative convergence. Experimental results are given to show that our two-step registration method can effectively solve the uneven-density and high-noise problem in registration of unstructured terrain point clouds, thereby improving the accuracy of terrain point cloud reconstruction.

scholarly journals Ground-distance segmentation of 3D LiDAR point cloud toward autonomous driving

2020 ◽  
Vol 9 ◽  
Author(s):  
Jian Wu ◽  
Qingxiong Yang
Keyword(s):  
Point Cloud ◽  
Large Scale ◽  
Ground Plane ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Autonomous Driving ◽  
Urban Environments ◽  
Cloud Data ◽  
Dense Point ◽  
3D Lidar

In this paper, we study the semantic segmentation of 3D LiDAR point cloud data in urban environments for autonomous driving, and a method utilizing the surface information of the ground plane was proposed. In practice, the resolution of a LiDAR sensor installed in a self-driving vehicle is relatively low and thus the acquired point cloud is indeed quite sparse. While recent work on dense point cloud segmentation has achieved promising results, the performance is relatively low when directly applied to sparse point clouds. This paper is focusing on semantic segmentation of the sparse point clouds obtained from 32-channel LiDAR sensor with deep neural networks. The main contribution is the integration of the ground information which is used to group ground points far away from each other. Qualitative and quantitative experiments on two large-scale point cloud datasets show that the proposed method outperforms the current state-of-the-art.

scholarly journals Cost Effective Mobile Mapping System for Color Point Cloud Reconstruction

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6536
Author(s):  
Cheng-Wei Peng ◽  
Chen-Chien Hsu ◽  
Wei-Yen Wang
Keyword(s):  
Autonomous Vehicles ◽  
Point Cloud ◽  
Cost Effective ◽  
Point Clouds ◽  
Autonomous Driving ◽  
Fine Tuning ◽  
Measurement Unit ◽  
Practical Implementation ◽  
High Definition ◽  
Mobile Mapping

Survey-grade Lidar brands have commercialized Lidar-based mobile mapping systems (MMSs) for several years now. With this high-end equipment, the high-level accuracy quality of point clouds can be ensured, but unfortunately, their high cost has prevented practical implementation in autonomous driving from being affordable. As an attempt to solve this problem, we present a cost-effective MMS to generate an accurate 3D color point cloud for autonomous vehicles. Among the major processes for color point cloud reconstruction, we first synchronize the timestamps of each sensor. The calibration process between camera and Lidar is developed to obtain the translation and rotation matrices, based on which color attributes can be composed into the corresponding Lidar points. We also employ control points to adjust the point cloud for fine tuning the absolute position. To overcome the limitation of Global Navigation Satellite System/Inertial Measurement Unit (GNSS/IMU) positioning system, we utilize Normal Distribution Transform (NDT) localization to refine the trajectory to solve the multi-scan dispersion issue. Experimental results show that the color point cloud reconstructed by the proposed MMS has a position error in centimeter-level accuracy, meeting the requirement of high definition (HD) maps for autonomous driving usage.

scholarly journals Parallel Point Clouds: Hybrid Point Cloud Generation and 3D Model Enhancement via Virtual–Real Integration

2021 ◽  
Vol 13 (15) ◽  
pp. 2868
Author(s):  
Yonglin Tian ◽  
Xiao Wang ◽  
Yu Shen ◽  
Zhongzheng Guo ◽  
Zilei Wang ◽  
...  
Keyword(s):  
Point Cloud ◽  
Closed Loop ◽  
Real Data ◽  
Point Clouds ◽  
Autonomous Driving ◽  
Training Model ◽  
Labor Cost ◽  
Open Loop ◽  
Training Dataset ◽  
Data Annotation

Three-dimensional information perception from point clouds is of vital importance for improving the ability of machines to understand the world, especially for autonomous driving and unmanned aerial vehicles. Data annotation for point clouds is one of the most challenging and costly tasks. In this paper, we propose a closed-loop and virtual–real interactive point cloud generation and model-upgrading framework called Parallel Point Clouds (PPCs). To our best knowledge, this is the first time that the training model has been changed from an open-loop to a closed-loop mechanism. The feedback from the evaluation results is used to update the training dataset, benefiting from the flexibility of artificial scenes. Under the framework, a point-based LiDAR simulation model is proposed, which greatly simplifies the scanning operation. Besides, a group-based placing method is put forward to integrate hybrid point clouds, via locating candidate positions for virtual objects in real scenes. Taking advantage of the CAD models and mobile LiDAR devices, two hybrid point cloud datasets, i.e., ShapeKITTI and MobilePointClouds, are built for 3D detection tasks. With almost zero labor cost on data annotation for newly added objects, the models (PointPillars) trained with ShapeKITTI and MobilePointClouds achieved 78.6% and 60.0% of the average precision of the model trained with real data on 3D detection, respectively.

Algorithms for Generating Adaptive Projection Patterns for 3-D Shape Measurement

2007 ◽  
Author(s):  
Tao Peng ◽  
Satyandra K. Gupta
Keyword(s):  
Point Cloud ◽  
Measurement Accuracy ◽  
Point Clouds ◽  
Fringe Projection ◽  
Shape Measurement ◽  
Digital Fringe Projection ◽  
Physical Experiments ◽  
Dense Point ◽  
Improved Performance ◽  
Fringe Patterns

Point cloud acquisition using digital fringe projection (PCCDFP) is a non-contact technique for acquiring dense point clouds to represent the 3-D shapes of objects. Most existing PCCDFP systems use projection patterns consisting of straight fringes with fixed fringe pitches. In certain situations, such patterns do not give the best results. In our earlier work, we have shown that in some situations, patterns that use curved fringes with spatial pitch variation can significantly improve the process of constructing point clouds. This paper describes algorithms for automatically generating adaptive projection patterns that use curved fringes with spatial pitch variation to provide improved results for an object being measured. In addition, we also describe the supporting algorithms that are needed for utilizing adaptive projection patterns. Both simulation and physical experiments show that, adaptive patterns are able to achieve improved performance, in terms of measurement accuracy and coverage, than fixed-pitch straight fringe patterns.

scholarly journals PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1573 ◽  
Author(s):  
Haojie Liu ◽  
Kang Liao ◽  
Chunyu Lin ◽  
Yao Zhao ◽  
Meiqin Liu
Keyword(s):  
Point Cloud ◽  
Spatial Information ◽  
Interpolation Method ◽  
Low Frequency ◽  
Point Clouds ◽  
Autonomous Driving ◽  
Sensor Data ◽  
Navigation Systems ◽  
Intermediate Point ◽  
Cascade Structure

LiDAR sensors can provide dependable 3D spatial information at a low frequency (around 10 Hz) and have been widely applied in the field of autonomous driving and unmanned aerial vehicle (UAV). However, the camera with a higher frequency (around 20 Hz) has to be decreased so as to match with LiDAR in a multi-sensor system. In this paper, we propose a novel Pseudo-LiDAR interpolation network (PLIN) to increase the frequency of LiDAR sensor data. PLIN can generate temporally and spatially high-quality point cloud sequences to match the high frequency of cameras. To achieve this goal, we design a coarse interpolation stage guided by consecutive sparse depth maps and motion relationship. We also propose a refined interpolation stage guided by the realistic scene. Using this coarse-to-fine cascade structure, our method can progressively perceive multi-modal information and generate accurate intermediate point clouds. To the best of our knowledge, this is the first deep framework for Pseudo-LiDAR point cloud interpolation, which shows appealing applications in navigation systems equipped with LiDAR and cameras. Experimental results demonstrate that PLIN achieves promising performance on the KITTI dataset, significantly outperforming the traditional interpolation method and the state-of-the-art video interpolation technique.

scholarly journals MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Image

2019 ◽  
Vol 33 ◽  
pp. 8949-8956 ◽  
Author(s):  
Jinglu Wang ◽  
Bo Sun ◽  
Yan Lu
Keyword(s):  
Point Cloud ◽  
Image Plane ◽  
Point Clouds ◽  
Projective Planes ◽  
Network Architectures ◽  
View Point ◽  
Single Image ◽  
Dense Point ◽  
Dependent Point ◽  
3D Surfaces

In this paper, we address the problem of reconstructing an object’s surface from a single image using generative networks. First, we represent a 3D surface with an aggregation of dense point clouds from multiple views. Each point cloud is embedded in a regular 2D grid aligned on an image plane of a viewpoint, making the point cloud convolution-favored and ordered so as to fit into deep network architectures. The point clouds can be easily triangulated by exploiting connectivities of the 2D grids to form mesh-based surfaces. Second, we propose an encoder-decoder network that generates such kind of multiple view-dependent point clouds from a single image by regressing their 3D coordinates and visibilities. We also introduce a novel geometric loss that is able to interpret discrepancy over 3D surfaces as opposed to 2D projective planes, resorting to the surface discretization on the constructed meshes. We demonstrate that the multi-view point regression network outperforms state-of-the-art methods with a significant improvement on challenging datasets.

scholarly journals A comparison of multi-view 3D reconstruction of a rock wall using several cameras and a laser scanner

2014 ◽  
Vol XL-5 ◽  
pp. 573-580 ◽  
Author(s):  
K. Thoeni ◽  
A. Giacomini ◽  
R. Murtagh ◽  
E. Kniest
Keyword(s):  
3D Reconstruction ◽  
Point Cloud ◽  
Laser Scanner ◽  
Ground Truth ◽  
Point Clouds ◽  
Digital Cameras ◽  
Rock Wall ◽  
Geological Features ◽  
Dense Point ◽  
Sharp Edges

This work presents a comparative study between multi-view 3D reconstruction using various digital cameras and a terrestrial laser scanner (TLS). Five different digital cameras were used in order to estimate the limits related to the camera type and to establish the minimum camera requirements to obtain comparable results to the ones of the TLS. The cameras used for this study range from commercial grade to professional grade and included a GoPro Hero 1080 (5 Mp), iPhone 4S (8 Mp), Panasonic Lumix LX5 (9.5 Mp), Panasonic Lumix ZS20 (14.1 Mp) and Canon EOS 7D (18 Mp). The TLS used for this work was a FARO Focus 3D laser scanner with a range accuracy of ±2 mm. The study area is a small rock wall of about 6 m height and 20 m length. The wall is partly smooth with some evident geological features, such as non-persistent joints and sharp edges. Eight control points were placed on the wall and their coordinates were measured by using a total station. These coordinates were then used to georeference all models. A similar number of images was acquired from a distance of between approximately 5 to 10 m, depending on field of view of each camera. The commercial software package PhotoScan was used to process the images, georeference and scale the models, and to generate the dense point clouds. Finally, the open-source package CloudCompare was used to assess the accuracy of the multi-view results. Each point cloud obtained from a specific camera was compared to the point cloud obtained with the TLS. The latter is taken as ground truth. The result is a coloured point cloud for each camera showing the deviation in relation to the TLS data. The main goal of this study is to quantify the quality of the multi-view 3D reconstruction results obtained with various cameras as objectively as possible and to evaluate its applicability to geotechnical problems.

scholarly journals TERRESTRIAL PHOTOGRAMMETRY VS LASER SCANNING FOR RAPID EARTHQUAKE DAMAGE ASSESSMENT

2018 ◽  
Vol XLII-3/W4 ◽  
pp. 527-533 ◽  
Author(s):  
C. Vasilakos ◽  
S. Chatzistamatis ◽  
O. Roussou ◽  
N. Soulakellis
Keyword(s):  
Structure From Motion ◽  
Damage Assessment ◽  
Point Cloud ◽  
Laser Scanning ◽  
Point Clouds ◽  
Earthquake Damage ◽  
Map Building ◽  
Dense Point ◽  
Terrestrial Photogrammetry ◽  
Earthquake Damage Assessment

<p><strong>Abstract.</strong> Building damage assessment caused by earthquakes is essential during the response phase following a catastrophic event. Modern techniques include terrestrial and aerial photogrammetry based on Structure from Motion algorithm and Laser Scanning with the latter to prove its superiority in accuracy assessment due to the high-density point clouds. However, standardized procedures during emergency surveys often could not be followed due to restrictions of outdoor operations because of debris or decrepit buildings, the high human presence of civil protection agencies, expedited deployment of survey team and cost of operations. The aim of this paper is to evaluate whether terrestrial photogrammetry based on a handheld amateur DSLR camera can be used to map building damages, structural deformations and facade production in an accepted accuracy comparing to laser scanning technique. The study area is the Vrisa village, Lesvos, Greece where a Mw&amp;thinsp;6.3 earthquake occurred on June 12th, 2017. A dense point cloud from some digital images created based on Structure from Motion algorithm and compared with a dense point cloud acquired by a laser scanner. The distance measurement and the comparison were conducted with the Multiscale Model to Model Cloud Comparison method. According to the results, the mean of the absolute distances between the two clouds is 0.038&amp;thinsp;m while the 94.9&amp;thinsp;% of the point distances are less than 0.1&amp;thinsp;m. Terrestrial photogrammetry proved to be an accurate methodology for rapid earthquake damage assessment thus its products were used by local authorities for the calculation of the compensation for the property loss.</p>

scholarly journals A REGISTRATION METHOD OF POINT CLOUDS COLLECTED BY MOBILE LIDAR USING SOLELY STANDARD LAS FILES INFORMATION

2017 ◽  
Vol XLII-1/W1 ◽  
pp. 121-128 ◽  
Author(s):  
L. Gézero ◽  
C. Antunes
Keyword(s):  
Point Cloud ◽  
Large Scale ◽  
Auxiliary Information ◽  
Point Clouds ◽  
Registration Method ◽  
Digital Terrain ◽  
Terrain Models ◽  
Dense Point ◽  
Fully Automatic ◽  
Method Point

In the last few years, LiDAR sensors installed in terrestrial vehicles have been revealed as an efficient method to collect very dense 3D georeferenced information. The possibility of creating very dense point clouds representing the surface surrounding the sensor, at a given moment, in a very fast, detailed and easy way, shows the potential of this technology to be used for cartography and digital terrain models production in large scale. However, there are still some limitations associated with the use of this technology. When several acquisitions of the same area with the same device, are made, differences between the clouds can be observed. The range of that differences can go from few centimetres to some several tens of centimetres, mainly in urban and high vegetation areas where the occultation of the GNSS system introduces a degradation of the georeferenced trajectory. Along this article a different method point cloud registration is proposed. In addition to the efficiency and speed of execution, the main advantages of the method are related to the fact that the adjustment is continuously made over the trajectory, based on the GPS time. The process is fully automatic and only information recorded in the standard LAS files is used, without the need for any auxiliary information, in particular regarding the trajectory.

Sign in / Sign up

Export Citation Format

Share Document