Application of Machine and Deep Learning Strategies for the Classification of Heritage Point Clouds

Grilli, Eleonora; Özdemir, E.; Remondino, Fabio

doi:10.5194/isprs-archives-xlii-4-w18-447-2019

Cited by 48 publications

(37 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research group is focusing his efforts even in this direction [73]. In future works, we plan to improve and better integrate the framework with more effective architectures, in order to improve performances and test also different kind of input features [19,74].…”

Section: Discussionmentioning

confidence: 99%

“…At the best of our knowledge, the only recent attempt to use DL for the semantic classification of Point Clouds of DCH is [19]. The method described consists of a workflow composed of feature extraction, feature selection and classification, as proposed in [40], for the subdivision into a high level of detailed architectural elements, using and comparing both ML and DL strategies.…”

Section: Classification and Semantic Segmentation In The Field Of Dchmentioning

confidence: 99%

“…Achieving such result is not trivial, since HBIM is generally based on scan-to-BIM processes that allow to generate a parametric 3D model from Point Cloud [16]; these processes, although very reliable since they are made manually by domain experts, have two drawbacks that are noteworthy: first, it is very time consuming and, secondly, it wastes an uncountable amount of data, given that a 3D scanning (both TLS or Close Range Photogrammetry based), contains much more information than the ones required for describing a parametric object. The literature demonstrates that, up to now, traditional methods applied to DCH field still make extensive use of manual operations to capture the real estate from Point Clouds [17][18][19][20]. Lately, towards this end, a very promising research field is the development of Deep Learning (DL) frameworks for Point Cloud such as Point-Net/Pointnet++ [21,22] open up more powerful and efficient ways to handle 3D data [23].…”

mentioning

confidence: 99%

“…In fact, even if they revealed to be suitable for handling Point Cloud of regular shapes, DCH goods are characterised by complex geometries, highly variable between them and defined only with a high level of detail. In [19], the authors study the potential offered by DL approaches for the supervised classification of 3D heritage obtaining promising results. However, the work does not cope with the irregular nature of CH data.To address these drawbacks, we propose a DL framework for Point Cloud segmentation, inspired by the work presented in [32].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage

et al. 2020

View full text Add to dashboard Cite

In the Digital Cultural Heritage (DCH) domain, the semantic segmentation of 3D Point Clouds with Deep Learning (DL) techniques can help to recognize historical architectural elements, at an adequate level of detail, and thus speed up the process of modeling of historical buildings for developing BIM models from survey data, referred to as HBIM (Historical Building Information Modeling). In this paper, we propose a DL framework for Point Cloud segmentation, which employs an improved DGCNN (Dynamic Graph Convolutional Neural Network) by adding meaningful features such as normal and colour. The approach has been applied to a newly collected DCH Dataset which is publicy available: ArCH (Architectural Cultural Heritage) Dataset. This dataset comprises 11 labeled points clouds, derived from the union of several single scans or from the integration of the latter with photogrammetric surveys. The involved scenes are both indoor and outdoor, with churches, chapels, cloisters, porticoes and loggias covered by a variety of vaults and beared by many different types of columns. They belong to different historical periods and different styles, in order to make the dataset the least possible uniform and homogeneous (in the repetition of the architectural elements) and the results as general as possible. The experiments yield high accuracy, demonstrating the effectiveness and suitability of the proposed approach.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Classification and Semantic Segmentation In The Field Of Dchmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Various types of machine learning and deep learning techniques are available, as described in [32]. In [35], a comparison on several machine learning and deep learning techniques were performed. The authors in [36] described a deep learning approach to classify outdoor point clouds in the case of heritage sites, while the authors in [37] proposed the use of a multi-scalar approach for classifying multi-resolution TLS data.…”

Section: Machine Learning and Deep Learning Approachesmentioning

confidence: 99%

Virtual Disassembling of Historical Edifices: Experiments and Assessments of an Automatic Approach for Classifying Multi-Scalar Point Clouds into Architectural Elements

Murtiyoso

Grussenmeyer

2020

Sensors

View full text Add to dashboard Cite

3D heritage documentation has seen a surge in the past decade due to developments in reality-based 3D recording techniques. Several methods such as photogrammetry and laser scanning are becoming ubiquitous amongst architects, archaeologists, surveyors, and conservators. The main result of these methods is a 3D representation of the object in the form of point clouds. However, a solely geometric point cloud is often insufficient for further analysis, monitoring, and model predicting of the heritage object. The semantic annotation of point clouds remains an interesting research topic since traditionally it requires manual labeling and therefore a lot of time and resources. This paper proposes an automated pipeline to segment and classify multi-scalar point clouds in the case of heritage object. This is done in order to perform multi-level segmentation from the scale of a historical neighborhood up until that of architectural elements, specifically pillars and beams. The proposed workflow involves an algorithmic approach in the form of a toolbox which includes various functions covering the semantic segmentation of large point clouds into smaller, more manageable and semantically labeled clusters. The first part of the workflow will explain the segmentation and semantic labeling of heritage complexes into individual buildings, while a second part will discuss the use of the same toolbox to segment the resulting buildings further into architectural elements. The toolbox was tested on several historical buildings and showed promising results. The ultimate intention of the project is to help the manual point cloud labeling, especially when confronted with the large training data requirements of machine learning-based algorithms.

show abstract

3D Modelling Approach for Ancient Floor Plans’ Quick Browsing

Swaileh

Jordan

Kotzinos

2022

Document Analysis Systems

View full text Add to dashboard Cite

Although 2D architectural floor plans are a commonly used way to express the design of a building, 3D models provide precious insight into modern building usability and safety. In addition, for a historical monument like the Palace of Versailles, the 3D models of its ancient floor plans help us to reconstruct the evolution of its buildings over the years. Such old floor plans are hand made and thus present some problems in automatic creation of a 3D model due to the drawing style variability. In this paper, we introduce a fully automatic and fast method to compute 3D building models from a set of architectural floor plans of the Palace of Versailles dated to the 17 th and 18 th century. First, we detect and localise walls in an input floor plan image using a statistical image segmentation model based on the U-net convolutional neural network architecture and a binary wall mask image is obtained. Secondly, using the generated wall mask image, the 3D model is built upon the linear edge segments representing the detected wall sides in the mask image. In order to cope with the lack of accurate ground truth information for the 3D models of ancient floor plans, we use a dedicated semi-automatic software to build a set of reference 3D models that describe plans' wall projections from three sides of view. We evaluate the performance of our approach on an input floor plan image by measuring the overlapping between the 3D reference model and our 3D model. Our fast and fully automatic approach performs efficiently and produces quite accurate 3D models with 84.2% of IoU score in average. Furthermore, its performance surpasses the performance of the state of the art approach in the wall detection task.

show abstract

Application of Machine and Deep Learning Strategies for the Classification of Heritage Point Clouds

Cited by 48 publications

References 32 publications

Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage

Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage

Virtual Disassembling of Historical Edifices: Experiments and Assessments of an Automatic Approach for Classifying Multi-Scalar Point Clouds into Architectural Elements

3D Modelling Approach for Ancient Floor Plans’ Quick Browsing

Contact Info

Product

Resources

About