- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Automated Method of Extracting Urban Roads Based on Region Growing from Mobile Laser Scanning Data
摘要： With the rapid development of three-dimensional point cloud acquisition from mobile laser scanning systems, the extraction of urban roads has become a major research focus. Although it has great potential for digital image processing, the extraction of roads using the region growing approach is still in its infancy. We propose an automated method of urban road extraction based on region growing. First, an initial seed is chosen under constraints relating to the Gaussian curvature, height and number of neighboring points, which ensures that the initial seed is located on a road. Then, the growing condition is determined by the angle threshold of the tangent plane of the seed point. Then, new seeds are selected based on the identi?ed road points and their curvature. The method also includes a strategy for dealing with multiple discontinuous roads in a dataset. The result shows that the method can not only achieve high accuracy in urban road extraction but is also stable and robust.
关键词： road extraction,tangent plane,point cloud,region growing,mobile laser scanning
更新于2025-09-11 14:15:04
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - UAV-BASED INTEGRATED MULTISENSOR PAYLOAD FOR HIGH RESOLUTION IMAGING
摘要： This paper describes the development of a multisensor UAV-based imaging platform. A sensor package consisting of a LiDAR, imaging spectrometer, and RGB camera were integrated with an inertial navigation system. This package is currently being flown on a hexacopter. A number of data acquisition missions have been conducted with this platform, including the imaging of a small active rotational mass movement, a wetland estuary, and several vineyards.
关键词： SfM point cloud,UAV,imaging spectrometer,LiDAR,INS
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Discriminative Learning of Point Cloud Feature Descriptors Based on Siamese Network
摘要： It is challenging to direct extract the feature descriptors of the object in the point cloud, although deep learning has been widely used with the classification and detection in the point cloud, those methods hidden feature presentation in the network. Since the point cloud scanned by the Laser Scanner usually have different point density, unordered and even the different occlusion, which go beyond the reach of hand-crafted descriptors, e.g. FPH, FPFH, VFH, ROPS. In this paper, we aim to direct extract the feature descriptors of the point cloud object through the raw point cloud. Inspired by the recent success of the Siamese networks[6], PointNet[7] and PointNet++[8], we propose a novel network to direct extract the feature descriptors of the whole point cloud object. We train our network with the Euclidean distance as the loss function which reflects feature descriptors similarity. The experiment object datasets were acquired by Mobile Laser Scanning (MLS) system which contains 6 categories. Experiment result shows that our network has a robust generalization, which can well direct extract the feature descriptors of the whole point cloud object.
关键词： Point cloud,mobile laser scanning,feature description,siamese network
更新于2025-09-10 09:29:36
-
[IEEE 2018 IEEE 22nd International Conference on Intelligent Engineering Systems (INES) - Las Palmas de Gran Canaria, Spain (2018.6.21-2018.6.23)] 2018 IEEE 22nd International Conference on Intelligent Engineering Systems (INES) - High Resolution 3D Thermal Imaging Using FLIR DUO R Sensor
摘要： With the spread of photogrammetry processes, photo-based 2D/3D reconstruction became general, in research as well as in the industry. Source images are taken using either a hand-held camera or an automated camera fixed to the carrier, a UAV, then they are matched during post-processing. The price of digital microbolometer-based high-resolution (1 megapixel) thermal cameras is currently very high, but these, compared to RGB cameras (16-20 megapixel), are still considered to have very low-resolution, in this way employing photogrammetry in this present case is not feasible. In the article, a novel method developed by us is introduced which by using a low thermal resolution camera (FLIR DUO R), based on which a 3D thermal image can be produced with the help of a camera capable of dual imaging (RGB and Thermal). The work is illustrated using measurements, and post-production was conducted using the MATLAB software. The process is adequate for producing 3D thermal images taken using UAV devices.
关键词： FLIR,photogrammetry,large scale point cloud,MATLAB,object reconstruction,3D thermal imaging
更新于2025-09-10 09:29:36
-
Surface Light Field Compression using a Point Cloud Codec
摘要： Light ?eld (LF) representations aim to provide photo-realistic, free-viewpoint viewing experiences. However, the most popular LF representations are images from multiple views. Multi-view image-based representations generally need to restrict the range or degrees of freedom of the viewing experience to what can be interpolated in the image domain, essentially because they lack explicit geometry information. We present a new surface light ?eld (SLF) representation based on explicit geometry, and a method for SLF compression. First, we map the multi-view images of a scene onto a 3D geometric point cloud. The color of each point in the point cloud is a function of viewing direction known as a view map. We represent each view map ef?ciently in a B-Spline wavelet basis. This representation is capable of modeling diverse surface materials and complex lighting conditions in a highly scalable and adaptive manner. The coef?cients of the B-Spline wavelet representation are then compressed spatially. To increase the spatial correlation and thus improve compression ef?ciency, we introduce a smoothing term to make the coef?cients more similar across 3D space. We compress the coef?cients spatially using existing point cloud compression (PCC) methods. On the decoder side, the scene is rendered ef?ciently from any viewing direction by reconstructing the view map at each point. In contrast to multi-view image-based LF approaches, our method supports photo-realistic rendering of real-world scenes from arbitrary viewpoints, i.e., with an unlimited six degrees of freedom (6DOF). In terms of rate and distortion, experimental results show that our method achieves superior performance with lighter decoder complexity compared with a reference image-plus-geometry compression (IGC) scheme, indicating its potential in practical virtual and augmented reality applications.
关键词： point cloud compression,free-viewpoint,full 6DoF,augmented reality,Surface light ?eld,virtual reality
更新于2025-09-10 09:29:36
-
Efficient and robust lane marking extraction from mobile lidar point clouds
摘要： Surveys of roadways with Mobile Laser Scanning (MLS) are now being conducted on a regular basis by many transportation agencies to provide detailed geometric information to support a wide range of applications, including asset management. Most MLS systems provide intensity (return signal strength) data as a point attribute in georeferenced point clouds, which may be used to estimate retro-reflectivity of pavement markings for effective maintenance. Nevertheless, the extraction of pavement markings from mobile lidar data remains an open challenge, due to variable noise, degree of wear on the markings, and road conditions. This paper addresses these challenges, presenting a novel approach for efficient, reliable extraction of lane markings, including those that have been significantly worn. First, using the MLS trajectory information, the lidar data is discretized into smaller sections, and then transformed to the local coordinate system, such that the road surface is near-horizontal for reliable extraction on roads with significant grade. Subsequently, the road surface is extracted using the constrained Random Sampling and Consensus (RANSAC) algorithm and then rasterized into a 2D intensity image to apply image processing techniques, namely: image segmentation to separate the lane markings from the road pavement, and a morphological opening operation to remove small objects. However, the extracted lane markings are prone to over-segmentation, due to occlusions or worn portions caused by moving vehicles. To rectify this, topologically-similar lane markings are associated with each other by computing line parameters (i.e., orientation and distance from the origin), which enables the gaps to be filled among the associated lanes. Finally, the remaining incorrect lane markings are detected and removed through a noise filtering phase using Dip test statistics. Examples of the effectiveness and application of the methodology are shown for a variety of sites with stripes of variable condition to highlight the robustness of the approach. Using optimized parameter values, the algorithm achieved F1 scores of 89–97% when tested on a variety of datasets encompassing a wide range of road scene types.
关键词： Point cloud,Mobile laser scanning,Lane marking extraction
更新于2025-09-10 09:29:36
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - R-Covnet: Recurrent Neural Convolution Network for 3D Object Recognition
摘要： Point cloud is a very precise digital format for recording objects in space. Point clouds have received increasing attention lately, due to the higher amount of information it provides compared to images. In this paper, we propose a new deep learning architecture called R-CovNet, designed for 3D object recognition. Unlike previous architectures that usually sample or convert point cloud into three-dimensional grids before processing, R-CovNet does not require any preprocessing. Our main goal is to provide a permutation invariant architecture especially designed for point clouds data of any size. Experiments with well-known benchmarks show that R-CovNet can achieve an accuracy of 92.7%, thus outperforming all the volumetric methods.
关键词： Point Cloud,RNN,3D Object Recognition
更新于2025-09-10 09:29:36
-
Community-scale multi-level post-hurricane damage assessment of residential buildings using multi-temporal airborne LiDAR data
摘要： Building damage assessment is a critical task following major hurricane events. Use of remotely sensed data to support building damage assessment is a logical choice considering the di?culty of gaining ground access to the impacted areas immediately after hurricane events. However, a remote sensing based damage assessment approach is often only capable of detecting severely damaged buildings. In this study, an airborne LiDAR based approach is proposed to assess multi-level hurricane damage at the community scale. In the proposed approach, building clusters are ?rst extracted using a density-based algorithm. A novel cluster matching algorithm is proposed to robustly match post-event and pre-event building clusters. Multiple features including roof area and volume, roof orientation, and roof shape are computed as building damage indicators. A hierarchical determination process is then employed to identify the extent of damage to each building object. The results of this study suggest that our proposed approach is capable of 1) recognizing building objects, 2) extracting damage features, and 3) characterizing the extent of damage to individual building properties.
关键词： Hurricane damage assessment,Point cloud processing,Geometric computing,Airborne LiDAR,Data clustering
更新于2025-09-10 09:29:36
-
Integration of point cloud data and hyperspectral imaging as a data gathering methodology for refurbishment projects using building information modelling (BIM)
摘要： Purpose – Building information modelling (BIM) is a digital representation of the physical and functional characteristics of a building. Its use offers a range of bene?ts in terms of achieving the ef?cient design, construction, operation and maintenance of buildings. Applying BIM at the outset of a new build project should be relatively easy. However, it is often problematic to apply BIM techniques to an existing building, for example, as part of a refurbishment project or as a tool supporting the facilities management strategy, because of inadequacies in the previous management of the dataset that characterises the facility in question. These inadequacies may include information on as built geometry and materials of construction. By the application of automated retrospective data gathering for use in BIM, such problems should be largely overcome and signi?cant bene?ts in terms of ef?ciency gains and cost savings should be achieved. Design/methodology/approach – Laser scanning can be used to collect geometrical and spatial information in the form of a 3D point cloud, and this technique is already used. However, as a point cloud representation does not contain any semantic information or geometrical context, such point cloud data must refer to external sources of data, such as building speci?cation and construction materials, to be in used in BIM. Findings – Hyperspectral imaging techniques can be applied to provide both spectral and spatial information of scenes as a set of high-resolution images. Integrating of a 3D point cloud into hyperspectral images would enable accurate identi?cation and classi?cation of surface materials and would also convert the 3D representation to BIM. Originality/value – This integrated approach has been applied in other areas, for example, in crop management. The transfer of this approach to facilities management and construction would improve the ef?ciency and automation of the data transition from building pathology to BIM. In this study, the technological feasibility and advantages of the integration of laser scanning and hyperspectral imaging (the latter not having previously been used in the construction context in its own right) is discussed, and an example of the use of a new integration technique is presented, applied for the ?rst time in the context of buildings.
关键词： Laser scanning,Information modelling,Refurbishment,BIM,Point cloud,Hyperspectral imaging
更新于2025-09-10 09:29:36
-
Framework for automated registration of UAV and UGV point clouds using local features in images
摘要： Automatically registering 3D point clouds generated by unmanned aerial and ground vehicles (UAVs and UGVs) is challenging, as data is acquired at different locations with different sensors, consequently resulting in different spatial scales and occlusions. To address these problems, this study proposes a framework for the automated registration of UAV and UGV point clouds using 2D local feature points in the images taken from UAVs and UGVs. This study first conducted field experiments by varying the angles of the UAV camera to identify the optimal angle with which to detect sufficient points matching with the images taken by the UGV. As a result, this study identified that a combination of UAV images taken at 30° and 90° is appropriate for generating a sufficient number of matching points and attaining a reasonable level of precision. The UAV and UGV point clouds were initially scaled and registered with a transformation matrix computed from the 3D points corresponding to the 2D feature matching points. The initially aligned point clouds were subsequently adjusted by the Iterative Closest Point (ICP) algorithm, resulting in the root mean square error (RMSE) of 0.112 m. This promising result indicates that full automation of spatial data collection and registration from a scattered environment (e.g., construction or disaster sites) by UAVs and UGVs is feasible without human intervention.
关键词： UGV,UAV,Registration,Point cloud,Drone,Mobile robot,Automation
更新于2025-09-10 09:29:36