scholarly journals TOPOLOGY-AWARE 3D MODELLING OF INDOOR SPACES FROM POINT CLOUDS

2021 ◽  
Vol XLIII-B4-2021 ◽  
pp. 267-274
Author(s):  
H. Zavar ◽  
H. Arefi ◽  
S. Malihi ◽  
M. Maboudi
Keyword(s):  
3D Model ◽  
Ground Truth ◽  
Point Clouds ◽  
Data Set ◽  
Adjacency Graph ◽  
Practical Applications ◽  
Benchmark Data ◽  
Data Driven Approach ◽  
Active Research ◽  
Indoor Spaces

Abstract. In this paper we introduce a topology-aware data-driven approach for 3D reconstruction of indoor spaces, which is an active research topic with several practical applications. After separating floor and ceiling, segmentation is followed by computing the α-shapes of the segment. The adjacency graph of all α-shapes is used to find the intersecting planes. By employing a B-rep approach, an initial 3D model is computed. Afterwards, adjacency graph of the intersected planes which constitute the initial model is analyzed in order to refine the 3D model. This leads to a water-tight and topologically correct 3D model. The performance of our proposed approach is qualitatively and quantitatively evaluated on an ISPRS benchmark data set. On this dataset, we achieved 77% completeness, 53% correctness and 1.7–5 cm accuracy with comparison of the final 3D model to the ground truth.

scholarly journals Terrestrial Laser Scanning and Ground Truth Data for Characterizing Downed Dead Wood

2020 ◽  
Author(s):  
Tuomas Yrttimaa ◽  
Ninni Saarinen ◽  
Ville Luoma ◽  
Topi Tanhuanpää ◽  
Ville Kankare ◽  
...  
Keyword(s):  
Boreal Forests ◽  
Laser Scanning ◽  
Dead Wood ◽  
Terrestrial Laser Scanning ◽  
Ground Truth ◽  
Point Clouds ◽  
Data Set ◽  
Ground Truth Data ◽  
Standing Trees ◽  
Downed Dead Wood

The feasibility of terrestrial laser scanning (TLS) in characterizing standing trees has been frequently investigated, while less effort has been put in quantifying downed dead wood using TLS. To advance dead wood characterization using TLS, we collected TLS point clouds and downed dead wood information from 20 sample plots (32 m x 32 m in size) located in southern Finland. This data set can be used in developing new algorithms for downed dead wood detection and characterization as well as for understanding spatial patterns of downed dead wood in boreal forests.

Land Map Image Dataset: Ground-Truth And Classification Using Visual And Textural Features

2014 ◽  
Vol 19 (4) ◽  
pp. 37-55 ◽  
Author(s):  
Sayan Mandal ◽  
Samit Biswas ◽  
Amit Kumar Das ◽  
Bhabatosh Chanda
Keyword(s):  
Ground Truth ◽  
Document Image ◽  
Geographical Information ◽  
Data Sets ◽  
Data Set ◽  
Handwritten Documents ◽  
Form Processing ◽  
Public Data ◽  
Active Research ◽  
The Right

Abstract Research on document image analysis is actively pursued in the last few decades and services like OCR, vectorization of drawings/graphics and various types of form processing are very common. Handwritten documents, old historical documents and documents captured through camera are now being the subjects of active research. However, another very important type of paper document, namely the map document image processing research suffers due to the inherent complexities of the map document and also for nonavailability of benchmark public data-sets. This paper presents a new data-set, namely, the Land Map Image Database (LMIDb) that consists of a variety of land maps images (446 images at present and growing; scanned at 200/300 dpi in TIF format) and the corresponding ground-truth. Using semiautomatic tools non-text part of the images are deleted and the text-only ground-truth is also kept in the database. This paper also presents a classification strategy for map images using which the maps in the database are automatically classified into Political (Po), Physical (Ph), Resource (R) and Topographic (T) maps. The automatic classification of maps help indexing of the images in LMIDb for archival and easy retrieval of the right maps to get the appropriate geographical information. Classification accuracy is also tested on the proposed data-set and the result is encouraging.

ON COMPUTING THE FUZZIFIER IN ↓FLVQ: A DATA DRIVEN APPROACH

2002 ◽  
Vol 12 (02) ◽  
pp. 149-157 ◽  
Author(s):  
L. B. ROMDHANE ◽  
B. AYEB ◽  
S. WANG
Keyword(s):  
Fuzzy Clustering ◽  
Research Area ◽  
Book Design ◽  
Data Set ◽  
Practical Applications ◽  
Probabilistic Clustering ◽  
Data Driven Approach ◽  
Optimal Setting ◽  
Important Research Area

Clustering is an important research area that has practical applications in many fields. Fuzzy clustering has shown advantages over crisp and probabilistic clustering, especially when there are significant overlaps between clusters. Most analytic fuzzy clustering approaches are derived from Bezdek's fuzzy c-means algorithm. One major factor that influences the determination of appropriate clusters in these approaches is an exponent parameter, called the fuzzifier. To our knowledge, no theoretical reason leading to an optimal setting of this parameter is available. This paper presents the development of an heuristic scheme for determining the fuzzifier. This scheme creates close interactions between the fuzzifier and the data set to be clustered. Experimental results in clustering IRIS data and in code book design required for image compression reveal a good performance of our proposal.

scholarly journals Voxel-Based 3D Object Reconstruction from Single 2D Image Using Variational Autoencoders

Mathematics ◽  
2021 ◽  
Vol 9 (18) ◽  
pp. 2288
Author(s):  
Rohan Tahir ◽  
Allah Bux Sargano ◽  
Zulfiqar Habib
Keyword(s):  
3D Reconstruction ◽  
3D Model ◽  
3D Models ◽  
Object Reconstruction ◽  
Data Set ◽  
3D Object ◽  
Practical Applications ◽  
3D Object Reconstruction ◽  
First Time ◽  
Memory Efficient

In recent years, learning-based approaches for 3D reconstruction have gained much popularity due to their encouraging results. However, unlike 2D images, 3D cannot be represented in its canonical form to make it computationally lean and memory-efficient. Moreover, the generation of a 3D model directly from a single 2D image is even more challenging due to the limited details available from the image for 3D reconstruction. Existing learning-based techniques still lack the desired resolution, efficiency, and smoothness of the 3D models required for many practical applications. In this paper, we propose voxel-based 3D object reconstruction (V3DOR) from a single 2D image for better accuracy, one using autoencoders (AE) and another using variational autoencoders (VAE). The encoder part of both models is used to learn suitable compressed latent representation from a single 2D image, and a decoder generates a corresponding 3D model. Our contribution is twofold. First, to the best of the authors’ knowledge, it is the first time that variational autoencoders (VAE) have been employed for the 3D reconstruction problem. Second, the proposed models extract a discriminative set of features and generate a smoother and high-resolution 3D model. To evaluate the efficacy of the proposed method, experiments have been conducted on a benchmark ShapeNet data set. The results confirm that the proposed method outperforms state-of-the-art methods.

scholarly journals SEMANTIC CHANGE DETECTION OF RIVER GROUND POINTS IN AIRBORNE LIDAR BATHYMETRY DATA USING VOXEL OCCUPANCIES

2019 ◽  
Vol IV-2/W7 ◽  
pp. 9-15
Author(s):  
R. Boerner ◽  
L. Hoegner ◽  
U. Stilla
Keyword(s):  
Water Surface ◽  
Semantic Information ◽  
Reference Data ◽  
Ground Truth ◽  
Point Clouds ◽  
Airborne Lidar ◽  
Semantic Change ◽  
Data Set ◽  
Airborne Lidar Bathymetry ◽  
Semantic Reference

<p><strong>Abstract.</strong> This paper proposes a method to get semantic information of changes in bathymetric point clouds. This method aims for assigning labels to river ground points which determine if either the point can be compared with a reference DEM, if there are no data in the reference or if there are no water points inside the new Data of wet areas of the reference data. This labels can be further used to specify areas where differences of DEMS can be calculated, the comparable areas. The Areas where no reference data is found specify areas where the reference DEM will have a higher variance due to interpolation which should be considered in the comparison. The areas where no water in the new data was found specify areas there no refraction correction in the new data can be done and which should be considered with a higher variance of the ground points or there the water surface should be tried to reconstruct. The proposed approach uses semantic reference data to specify water areas in the new scan. An occupancy analysis is used to specify if voxels of the new data exist in the reference or not. In case of occupancy, the labels of the reference are assigned to the new data and in case of no occupancy, the label of changed data is assigned. A histogram based method is used to separate ground and water points in wet areas and a second occupancy analysis is used to specify the semantic changes in wet areas. The proposed method is evaluated on a proposed data set of the Mangfall area where the ground truth is manually labelled.</p>

scholarly journals 3D MODEL FOR INDOOR SPACES USING DEPTH SENSOR

2019 ◽  
Vol XLII-4/W16 ◽  
pp. 471-479
Author(s):  
N. F. Mukhtar ◽  
S. Azri ◽  
U. Ujang ◽  
M. G. Cuétara ◽  
G. M. Retortillo ◽  
...  
Keyword(s):  
Data Processing ◽  
Data Acquisition ◽  
High Speed ◽  
3D Model ◽  
High Mobility ◽  
Point Clouds ◽  
Sensor Data ◽  
Depth Sensor ◽  
3D Point Clouds ◽  
Indoor Spaces

Abstract. In recent years, 3D model for indoor spaces have become highly demanded in the development of technology. Many approaches to 3D visualisation and modelling especially for indoor environment was developed such as laser scanner, photogrammetry, computer vision, image and many more. However, most of the technique relies on the experience of the operator to get the best result. Besides that, the equipment is quite expensive and time-consuming in terms of processing. This paper focuses on the data acquisition and visualisation of a 3D model for an indoor space by using a depth sensor. In this study, EyesMap3D Pro by Ecapture is used to collect 3D data of the indoor spaces. The EyesMap3D Pro depth sensor is able to generate 3D point clouds in high speed and high mobility due to the portability and light weight of the device. However, more attention must be paid on data acquisition, data processing, visualizing, and evaluation of the depth sensor data. Hence, this paper will discuss the data processing from extracting features from 3D point clouds to 3D indoor models. Afterwards, the evaluation on the 3D models is made to ensure the suitability in indoor model and indoor mapping application. In this study, the 3D model was exported to 3D GIS-ready format for displaying and storing more information of the indoor spaces.

scholarly journals IMPROVING AUTOMATIC RECONSTRUCTION OF INTERIOR WALLS FROM POINT CLOUD DATA

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 849-855
Author(s):  
E. Maset ◽  
L. Magri ◽  
A. Fusiello
Keyword(s):  
Point Cloud ◽  
Model Fitting ◽  
Point Clouds ◽  
Research Topic ◽  
Point Cloud Data ◽  
Cloud Data ◽  
Practical Applications ◽  
Main Building ◽  
Active Research ◽  
Interior Walls

<p><strong>Abstract.</strong> In this paper we deal with the automatic reconstruction of interior walls from point clouds, an active research topic with several practical applications. We propose an improved version of the method presented in (Magri and Fusiello, 2018), where the overall structure of the environment is extracted by fitting lines to the main building features, using Min-hashed J-Linkage as a multi-model fitting technique. Our variation has the merit of producing more accurate results, both in terms of wall reconstruction and room segmentation, and greatly reducing the need for user-defined thresholds.</p>

scholarly journals A SYNTHETIC 3D SCENE FOR THE VALIDATION OF PHOTOGRAMMETRIC ALGORITHMS

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 1221-1228
Author(s):  
D. Frommholz
Keyword(s):  
Optical Sensors ◽  
Measurement Errors ◽  
Ground Truth ◽  
Point Clouds ◽  
Visual Assessment ◽  
Double Precision ◽  
Data Set ◽  
Global Matching ◽  
3D Scene ◽  
Programming Knowledge

<p><strong>Abstract.</strong> This paper describes the construction and composition of a synthetic test world for the validation of photogrammetric algorithms. Since its 3D objects are entirely generated by software, the geometric accuracy of the scene does not suffer from measurement errors which existing real-world ground truth is inherently afflicted with. The resulting data set covers an area of 13188 by 6144 length units and exposes positional residuals as small as the machine epsilon of the double-precision floating point numbers used exclusively for the coordinates. It is colored with high-resolution textures to accommodate the simulation of virtual flight campaigns with large optical sensors and laser scanners in both aerial and close-range scenarios. To specifically support the derivation of image samples and point clouds, the synthetic scene gets stored in the human-readable Alias/Wavefront OBJ and POV-Ray data formats. While conventional rasterization remains possible, using the open-source ray tracer as a render tool facilitates the creation of ideal pinhole bitmaps, consistent digital surface models (DSMs), true ortho-mosaics (TOMs) and orientation metadata without programming knowledge. To demonstrate the application of the constructed 3D scene, example validation recipes are discussed in detail for a state-of-the-art implementation of semi-global matching and a perspective-correct multi-source texture mapper. For the latter, beyond the visual assessment, a statistical evaluation of the achieved texture quality is given.</p>

The COBRA fixed-wing georeferenced imagery dataset

2015 ◽  
Vol 3 (2/3) ◽  
pp. 62-71 ◽  
Author(s):  
Sajad Saeedi ◽  
Carl Thibault ◽  
Michael Trentini ◽  
Howard Li
Keyword(s):  
Ground Truth ◽  
Target Localization ◽  
Data Sets ◽  
Data Set ◽  
Content Type ◽  
Robot Operating System ◽  
Benchmark Data ◽  
Localization And Mapping ◽  
Aerial Vehicle ◽  
Sensor Configuration

Purpose – The purpose of this paper is to present a localization and mapping data set acquired by a fixed-wing unmanned aerial vehicle (UAV). The data set was collected for educational and research purposes: to save time in dealing with hardware and to compare the results with a benchmark data set. The data were collected in standard Robot Operating System (ROS) format. The environment, fixed-wing, and sensor configuration are explained in detail. GPS coordinates of the fixed-wing are also available as ground truth. The data set is available for download (www.ece.unb.ca/COBRA/open_source.htm). Design/methodology/approach – The data were collected in standard ROS format. The environment, fixed-wing, and sensor configuration are explained in detail. Findings – The data set can be used for target localization and mapping. The data were collected to assist algorithm developments and help researchers to compare their results. Robotic data sets are specifically important when they are related to unmanned systems such as fixed-wing aircraft. Originality/value – The Robotics Data Set Repository (RADISH) by A. Howard and N. Roy hosts 41 well-known data sets with different sensors; however, there is no fixed-wing data set in RADISH. This work presents two data sets collected by a fixed-wing aircraft using ROS standards. The data sets can be used for target localization and SLAM.

scholarly journals LEARNED COMPACT LOCAL FEATURE DESCRIPTOR FOR TLS-BASED GEODETIC MONITORING OF NATURAL OUTDOOR SCENES

2018 ◽  
Vol IV-2 ◽  
pp. 113-120 ◽  
Author(s):  
Z. Gojcic ◽  
C. Zhou ◽  
A. Wieser
Keyword(s):  
Laser Scanning ◽  
Point Clouds ◽  
Feature Descriptor ◽  
Data Set ◽  
Benchmark Data ◽  
Displacement Vectors ◽  
Unseen Data ◽  
Outdoor Scenes ◽  
Low Dimension ◽  
Feature Based

The advantages of terrestrial laser scanning (TLS) for geodetic monitoring of man-made and natural objects are not yet fully exploited. Herein we address one of the open challenges by proposing feature-based methods for identification of corresponding points in point clouds of two or more epochs. We propose a learned compact feature descriptor tailored for point clouds of natural outdoor scenes obtained using TLS. We evaluate our method both on a benchmark data set and on a specially acquired outdoor dataset resembling a simplified monitoring scenario where we successfully estimate 3D displacement vectors of a rock that has been displaced between the scans. We show that the proposed descriptor has the capacity to generalize to unseen data and achieves state-of-the-art performance while being time efficient at the matching step due the low dimension.

Sign in / Sign up

Export Citation Format

Share Document