scholarly journals METRIC EVALUATION PIPELINE FOR 3D MODELING OF URBAN SCENES

2017 ◽  
Vol XLII-1/W1 ◽  
pp. 239-246 ◽  
Author(s):  
M. Bosch ◽  
A. Leichtman ◽  
D. Chilcott ◽  
H. Goldberg ◽  
M. Brown
Keyword(s):  
Open Source ◽  
Satellite Imagery ◽  
3D Modeling ◽  
Ground Truth ◽  
3D Models ◽  
Airborne Lidar ◽  
Perceptual Quality ◽  
Urban Scenes ◽  
Sensing Applications ◽  
3D Point Clouds

Publicly available benchmark data and metric evaluation approaches have been instrumental in enabling research to advance state of the art methods for remote sensing applications in urban 3D modeling. Most publicly available benchmark datasets have consisted of high resolution airborne imagery and lidar suitable for 3D modeling on a relatively modest scale. To enable research in larger scale 3D mapping, we have recently released a public benchmark dataset with multi-view commercial satellite imagery and metrics to compare 3D point clouds with lidar ground truth. We now define a more complete metric evaluation pipeline developed as publicly available open source software to assess semantically labeled 3D models of complex urban scenes derived from multi-view commercial satellite imagery. Evaluation metrics in our pipeline include horizontal and vertical accuracy and completeness, volumetric completeness and correctness, perceptual quality, and model simplicity. Sources of ground truth include airborne lidar and overhead imagery, and we demonstrate a semi-automated process for producing accurate ground truth shape files to characterize building footprints. We validate our current metric evaluation pipeline using 3D models produced using open source multi-view stereo methods. Data and software is made publicly available to enable further research and planned benchmarking activities.

scholarly journals GENERATION OF GROUND TRUTH DATASETS FOR THE ANALYSIS OF 3D POINT CLOUDS IN URBAN SCENES ACQUIRED VIA DIFFERENT SENSORS

2018 ◽  
Vol XLII-3 ◽  
pp. 2009-2015 ◽  
Author(s):  
Y. Xu ◽  
Z. Sun ◽  
R. Boerner ◽  
T. Koch ◽  
L. Hoegner ◽  
...  
Keyword(s):  
Point Cloud ◽  
Spatial Information ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Urban Scenes ◽  
3D Space ◽  
3D Point Clouds ◽  
Testing Site ◽  
Voxel Grid

In this work, we report a novel way of generating ground truth dataset for analyzing point cloud from different sensors and the validation of algorithms. Instead of directly labeling large amount of 3D points requiring time consuming manual work, a multi-resolution 3D voxel grid for the testing site is generated. Then, with the help of a set of basic labeled points from the reference dataset, we can generate a 3D labeled space of the entire testing site with different resolutions. Specifically, an octree-based voxel structure is applied to voxelize the annotated reference point cloud, by which all the points are organized by 3D grids of multi-resolutions. When automatically annotating the new testing point clouds, a voting based approach is adopted to the labeled points within multiple resolution voxels, in order to assign a semantic label to the 3D space represented by the voxel. Lastly, robust line- and plane-based fast registration methods are developed for aligning point clouds obtained via various sensors. Benefiting from the labeled 3D spatial information, we can easily create new annotated 3D point clouds of different sensors of the same scene directly by considering the corresponding labels of 3D space the points located, which would be convenient for the validation and evaluation of algorithms related to point cloud interpretation and semantic segmentation.

scholarly journals Mapping Large-Scale Plateau Forest in Sanjiangyuan Using High-Resolution Satellite Imagery and Few-Shot Learning

2022 ◽  
Vol 14 (2) ◽  
pp. 388
Author(s):  
Zhihao Wei ◽  
Kebin Jia ◽  
Xiaowei Jia ◽  
Pengyu Liu ◽  
Ying Ma ◽  
...  
Keyword(s):  
High Resolution ◽  
Satellite Imagery ◽  
Large Scale ◽  
Ground Truth ◽  
Fine Tuning ◽  
Forest Monitoring ◽  
Learning Method ◽  
Ground Truth Data ◽  
Sensing Applications ◽  
High Resolution Satellite Imagery

Monitoring the extent of plateau forests has drawn much attention from governments given the fact that the plateau forests play a key role in global carbon circulation. Despite the recent advances in the remote-sensing applications of satellite imagery over large regions, accurate mapping of plateau forest remains challenging due to limited ground truth information and high uncertainties in their spatial distribution. In this paper, we aim to generate a better segmentation map for plateau forests using high-resolution satellite imagery with limited ground-truth data. We present the first 2 m spatial resolution large-scale plateau forest dataset of Sanjiangyuan National Nature Reserve, including 38,708 plateau forest imagery samples and 1187 handmade accurate plateau forest ground truth masks. We then propose an few-shot learning method for mapping plateau forests. The proposed method is conducted in two stages, including unsupervised feature extraction by leveraging domain knowledge, and model fine-tuning using limited ground truth data. The proposed few-shot learning method reached an F1-score of 84.23%, and outperformed the state-of-the-art object segmentation methods. The result proves the proposed few-shot learning model could help large-scale plateau forest monitoring. The dataset proposed in this paper will soon be available online for the public.

scholarly journals CityJSON Building Generation from Airborne LiDAR 3D Point Clouds

2020 ◽  
Vol 9 (9) ◽  
pp. 521
Author(s):  
Gilles-Antoine Nys ◽  
Florent Poux ◽  
Roland Billen
Keyword(s):  
Smart Cities ◽  
Contextual Information ◽  
Compliance Rate ◽  
Point Clouds ◽  
3D Models ◽  
Automatic Generation ◽  
Airborne Lidar ◽  
Generation Process ◽  
3D Point Clouds ◽  
Unique Source

The relevant insights provided by 3D City models greatly improve Smart Cities and their management policies. In the urban built environment, buildings frequently represent the most studied and modeled features. CityJSON format proposes a lightweight and developer-friendly alternative to CityGML. This paper proposes an improvement to the usability of 3D models providing an automatic generation method in CityJSON, to ensure compactness, expressivity, and interoperability. In addition to a compliance rate in excess of 92% for geometry and topology, the generated model allows the handling of contextual information, such as metadata and refined levels of details (LoD), in a built-in manner. By breaking down the building-generation process, it creates consistent building objects from the unique source of Light Detection and Ranging (LiDAR) point clouds.

scholarly journals 3D Modeling from Multi-views Images for Cultural Heritage in Wat-Pho, Thailand

2015 ◽  
Vol XL-5/W7 ◽  
pp. 403-407 ◽  
Author(s):  
N. Soontranon ◽  
P. Srestasathiern ◽  
S. Lawawirojwong
Keyword(s):  
3D Modeling ◽  
Laser Scanner ◽  
Point Clouds ◽  
3D Models ◽  
Public Access ◽  
3D Point Clouds ◽  
Surface Simplification ◽  
Triangulated Surfaces ◽  
Initial Work ◽  
Printed Materials

In Thailand, there are several types of (tangible) cultural heritages. This work focuses on 3D modeling of the heritage objects from multi-views images. The images are acquired by using a DSLR camera which costs around $1,500 (camera and lens). Comparing with a 3D laser scanner, the camera is cheaper and lighter than the 3D scanner. Hence, the camera is available for public users and convenient for accessing narrow areas. The acquired images consist of various sculptures and architectures in Wat-Pho which is a Buddhist temple located behind the Grand Palace (Bangkok, Thailand). Wat-Pho is known as temple of the reclining Buddha and the birthplace of traditional Thai massage. To compute the 3D models, a diagram is separated into following steps; <i>Data acquisition</i>, <i>Image matching</i>, <i>Image calibration and orientation</i>, <i>Dense matching</i> and <i>Point cloud processing</i>. For the initial work, small heritages less than 3 meters height are considered for the experimental results. A set of multi-views images of an interested object is used as input data for 3D modeling. In our experiments, 3D models are obtained from MICMAC (open source) software developed by IGN, France. The output of 3D models will be represented by using standard formats of 3D point clouds and triangulated surfaces such as .ply, .off, .obj, etc. To compute for the efficient 3D models, post-processing techniques are required for the final results e.g. noise reduction, surface simplification and reconstruction. The reconstructed 3D models can be provided for public access such as website, DVD, printed materials. The high accurate 3D models can also be used as reference data of the heritage objects that must be restored due to deterioration of a lifetime, natural disasters, etc.

scholarly journals UAV LINEAR PHOTOGRAMMETRY

2015 ◽  
Vol XL-3/W3 ◽  
pp. 327-333 ◽  
Author(s):  
V. Tournadre ◽  
M. Pierrot-Deseilligny ◽  
P. H. Faure
Keyword(s):  
Open Source ◽  
Ground Truth ◽  
3D Models ◽  
Bundle Adjustment ◽  
Acquisition Process ◽  
Calibration Models ◽  
All Solutions ◽  
Oblique Images ◽  
Free Open Source ◽  
Terrestrial Photogrammetry

The photogrammetric treatment of images acquired on a linear axis is a problematic case. Such tricky configurations often leads to bended 3D models, described as a bowl effect, which requires ground measurements to be fixed. This article presents different solutions to overcome that problem. All solutions have been implemented into the free open-source photogrammetric suite MicMac. The article presents the lasts evolutions of MicMac's bundle adjustment core, as well as some extended calibration models and how they fit for the camera evaluated. The acquisition process is optimized by presenting how oblique images can improve the accuracy of the orientations, while the 3D models accuracies are assessed by producing a millimeter accurate ground truth from terrestrial photogrammetry.

From Spherical Photogrammetry to 3D Modeling

2016 ◽  
pp. 96-115
Author(s):  
Wissam Wahbeh
Keyword(s):  
3D Modeling ◽  
Survey Methods ◽  
Texture Mapping ◽  
3D Models ◽  
Image Stitching ◽  
Urban Scenes ◽  
Survey System ◽  
Architectural Structures ◽  
Mapping Techniques ◽  
Stitching Techniques

The introduced research is about 3D modeling technique that can be considered as an assembly point of photography, topography, photogrammetry, and computer graphics. The chapter present survey methods based on spherical panoramas produced by image stitching techniques, which are proved efficient in order to obtain a high metric quality. It is an interactive survey system to generating 3D models of architectural structures and urban scenes. Photogrammetric fundamentals are applied using two different approaches to obtain the 3D model: the first one is by using texture-mapping techniques in the way of creating the virtual models; while the second is by using parametric visual programing process.

scholarly journals 3D CITYGML BUILDING MODELLING FROM LIDAR POINT CLOUD DATA

2018 ◽  
Vol XLII-5 ◽  
pp. 175-180 ◽  
Author(s):  
P. Jayaraj ◽  
A. M. Ramiya
Keyword(s):  
Open Source ◽  
Point Cloud ◽  
Smart Cities ◽  
Open Data ◽  
3D Models ◽  
Airborne Lidar ◽  
Model Framework ◽  
Cloud Data ◽  
Building Models ◽  
Virtual City

<p><strong>Abstract.</strong> With recent government initiatives for smart cities, 3D virtual city models are in demand for managing and monitoring the urban infrastructure. 3D building models forms an important component of 3D virtual city model. LiDAR remote sensing has revolutionized the way the third dimension can be precisely mapped and proved to be an important source of data for 3D models. The model thus generated should be in an open data format to be used across various applications. CityGML is an open data model framework that enables storage and exchange of 3D models which can be used for diversified applications. The main objective of this research is to develop a methodological workflow to create 3D building models in CityGML standard from airborne LiDAR point cloud. Initially building points were isolated from the airborne LiDAR data using point cloud processing algorithms. 3D building models with levels of detail (LoD1 and LoD2) were generated from the building points in CityGML standard using commercial (ArcGISPro) well as open source packages (3dfier, Citygml4j). Results prove that the models developed using open source packages are comparable to that provided by commercial packages.</p>

scholarly journals CNN-Based Individual Tree Species Classification Using High-Resolution Satellite Imagery and Airborne LiDAR Data

Forests ◽  
2021 ◽  
Vol 12 (12) ◽  
pp. 1697
Author(s):  
Hui Li ◽  
Baoxin Hu ◽  
Qian Li ◽  
Linhai Jing
Keyword(s):  
High Resolution ◽  
Satellite Imagery ◽  
Tree Species ◽  
Airborne Lidar ◽  
Support Vector ◽  
Lidar Data ◽  
Individual Tree ◽  
Sensing Applications ◽  
High Resolution Satellite Imagery ◽  
Airborne Lidar Data

Deep learning (DL) has shown promising performances in various remote sensing applications as a powerful tool. To explore the great potential of DL in improving the accuracy of individual tree species (ITS) classification, four convolutional neural network models (ResNet-18, ResNet-34, ResNet-50, and DenseNet-40) were employed to classify four tree species using the combined high-resolution satellite imagery and airborne LiDAR data. A total of 1503 samples of four tree species, including maple, pine, locust, and spruce, were used in the experiments. When both WorldView-2 and airborne LiDAR data were used, the overall accuracies (OA) obtained by ResNet-18, ResNet-34, ResNet-50, and DenseNet-40 were 90.9%, 89.1%, 89.1%, and 86.9%, respectively. The OA of ResNet-18 was increased by 4.0% and 1.8% compared with random forest (86.7%) and support vector machine (89.1%), respectively. The experimental results demonstrated that the size of input images impacted on the classification accuracy of ResNet-18. It is suggested that the input size of ResNet models can be determined according to the maximum size of all tree crown sample images. The use of LiDAR intensity image was helpful in improving the accuracies of ITS classification and atmospheric correction is unnecessary when both pansharpened WorldView-2 images and airborne LiDAR data were used.

scholarly journals RobotP: A Benchmark Dataset for 6D Object Pose Estimation

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1299
Author(s):  
Honglin Yuan ◽  
Tim Hoogenkamp ◽  
Remco C. Veltkamp
Keyword(s):  
Pose Estimation ◽  
Ground Truth ◽  
3D Models ◽  
Depth Image ◽  
Great Success ◽  
Estimation Algorithms ◽  
Depth Images ◽  
Object Pose Estimation ◽  
Image Pairs ◽  
Bounding Boxes

Deep learning has achieved great success on robotic vision tasks. However, when compared with other vision-based tasks, it is difficult to collect a representative and sufficiently large training set for six-dimensional (6D) object pose estimation, due to the inherent difficulty of data collection. In this paper, we propose the RobotP dataset consisting of commonly used objects for benchmarking in 6D object pose estimation. To create the dataset, we apply a 3D reconstruction pipeline to produce high-quality depth images, ground truth poses, and 3D models for well-selected objects. Subsequently, based on the generated data, we produce object segmentation masks and two-dimensional (2D) bounding boxes automatically. To further enrich the data, we synthesize a large number of photo-realistic color-and-depth image pairs with ground truth 6D poses. Our dataset is freely distributed to research groups by the Shape Retrieval Challenge benchmark on 6D pose estimation. Based on our benchmark, different learning-based approaches are trained and tested by the unified dataset. The evaluation results indicate that there is considerable room for improvement in 6D object pose estimation, particularly for objects with dark colors, and photo-realistic images are helpful in increasing the performance of pose estimation algorithms.

A Digital Terrain Modeling Method in Urban Areas by the ICESat-2 (Generating precise terrain surface profiles from photon-counting technology)

2021 ◽  
Vol 87 (4) ◽  
pp. 237-248
Author(s):  
Nahed Osama ◽  
Bisheng Yang ◽  
Yue Ma ◽  
Mohamed Freeshah
Keyword(s):  
Urban Areas ◽  
Spatial Clustering ◽  
Photon Counting ◽  
Ground Surface ◽  
Ground Truth ◽  
Surface Model ◽  
Laser Altimeter ◽  
Ground Truth Data ◽  
Urban Scenes ◽  
Terrain Surface

The ICE, Cloud and land Elevation Satellite-2 (ICES at-2) can provide new measurements of the Earth's elevations through photon-counting technology. Most research has focused on extracting the ground and the canopy photons in vegetated areas. Yet the extraction of the ground photons from urban areas, where the vegetation is mixed with artificial constructions, has not been fully investigated. This article proposes a new method to estimate the ground surface elevations in urban areas. The ICES at-2 signal photons were detected by the improved Density-Based Spatial Clustering of Applications with Noise algorithm and the Advanced Topographic Laser Altimeter System algorithm. The Advanced Land Observing Satellite-1 PALSAR –derived digital surface model has been utilized to separate the terrain surface from the ICES at-2 data. A set of ground-truth data was used to evaluate the accuracy of these two methods, and the achieved accuracy was up to 2.7 cm, which makes our method effective and accurate in determining the ground elevation in urban scenes.

Sign in / Sign up

Export Citation Format

Share Document