Exploração da Point Cloud Library aplicada à percepção em sistemas autónomos

A navegação e a interpretação do meio envolvente por veículos autónomos em ambientes não estruturados continua a ser um grande desafio na actualidade. Sebastian Thrun, descreve em [Thr02], que o problema do mapeamento em sistemas robóticos é o da aquisição de um modelo espacial do meio envolvente do robô. Neste contexto, a integração de sistemas sensoriais em plataformas robóticas, que permitam a construção de mapas do mundo que as rodeia é de extrema importância. A informação recolhida desses dados pode ser interpretada, tendo aplicabilidade em tarefas de localização, navegação e manipulação de objectos. Até à bem pouco tempo, a generalidade dos sistemas robóticos que realizavam tarefas de mapeamento ou Simultaneous Localization And Mapping (SLAM), utilizavam dispositivos do tipo laser rangefinders e câmaras stereo. Estes equipamentos, para além de serem dispendiosos, fornecem apenas informação bidimensional, recolhidas através de cortes transversais 2D, no caso dos rangefinders. O paradigma deste tipo de tecnologia mudou consideravelmente, com o lançamento no mercado de câmaras RGB-D, como a desenvolvida pela PrimeSense TM e o subsequente lançamento da Kinect, pela Microsoft R para a Xbox 360 no final de 2010. A qualidade do sensor de profundidade, dada a natureza de baixo custo e a sua capacidade de aquisição de dados em tempo real, é incontornável, fazendo com que o sensor se tornasse instantaneamente popular entre pesquisadores e entusiastas. Este avanço tecnológico deu origem a várias ferramentas de desenvolvimento e interacção humana com este tipo de sensor, como por exemplo a Point Cloud Library [RC11] (PCL). Esta ferramenta tem como objectivo fornecer suporte para todos os blocos de construção comuns que uma aplicação 3D necessita, dando especial ênfase ao processamento de nuvens de pontos de n dimensões adquiridas a partir de câmaras RGB-D, bem como scanners laser, câmaras Time-of-Flight ou câmaras stereo. Neste contexto, é realizada nesta dissertação, a avaliação e comparação de alguns dos módulos e métodos constituintes da biblioteca PCL, para a resolução de problemas inerentes à construção e interpretação de mapas, em ambientes indoor não estruturados, utilizando os dados provenientes da Kinect. A partir desta avaliação, é proposta uma arquitectura de sistema que sistematiza o registo de nuvens de pontos, correspondentes a vistas parciais do mundo, num modelo global consistente. Os resultados da avaliação realizada à biblioteca PCL atestam a sua viabilidade, para a resolução dos problemas propostos. Prova da sua viabilidade, são os resultados práticos obtidos, da implementação da arquitectura de sistema proposta, que apresenta resultados de desempenho interessantes, como também boas perspectivas de integração deste tipo de conceitos e tecnologia em plataformas robóticas desenvolvidas no âmbito de projectos do Laboratório de Sistemas Autónomos (LSA).

Geometric 3D point cloud compression

The use of 3D data in mobile robotics applications provides valuable information about the robot’s environment but usually the huge amount of 3D information is unmanageable by the robot storage and computing capabilities. A data compression is necessary to store and manage this information but preserving as much information as possible. In this paper, we propose a 3D lossy compression system based on plane extraction which represent the points of each scene plane as a Delaunay triangulation and a set of points/area information. The compression system can be customized to achieve different data compression or accuracy ratios. It also supports a color segmentation stage to preserve original scene color information and provides a realistic scene reconstruction. The design of the method provides a fast scene reconstruction useful for further visualization or processing tasks.

Logarithmically proportional objective function for planar surfaces recognition in 3D point cloud

3D laser scanning is becoming a standard technology to generate building models of a facility's as-is condition. Since most constructions are constructed upon planar surfaces, recognition of them paves the way for automation of generating building models. This paper introduces a new logarithmically proportional objective function that can be used in both heuristic and metaheuristic (MH) algorithms to discover planar surfaces in a point cloud without exploiting any prior knowledge about those surfaces. It can also adopt itself to the structural density of a scanned construction. In this paper, a metaheuristic method, genetic algorithm (GA), is used to test this introduced objective function on a synthetic point cloud. The results obtained show the proposed method is capable to find all plane configurations of planar surfaces (with a wide variety of sizes) in the point cloud with a minor distance to the actual configurations. © 2014 IEEE.

People semantic description and re-identification from point cloud geometry

The automatic extraction of biometric descriptors of anonymous people is a challenging scenario in camera networks. This task is typically accomplished making use of visual information. Calibrated RGBD sensors make possible the extraction of point cloud information. We present a novel approach for people semantic description and re-identification using the individual point cloud information. The proposal combines the use of simple geometric features with point cloud features based on surface normals.

Crete fault scarp point cloud data

This paper assesses the along strike variation of active bedrock fault scarps using long range terrestrial laser scanning (t-LiDAR) data in order to determine the distribution behaviour of scarp height and the subsequently calculate long term throw-rates. Five faults on Cretewhich display spectacular limestone fault scarps have been studied using high resolution digital elevation model (HRDEM) data. We scanned several hundred square metres of the fault system including the footwall, fault scarp and hanging wall of the investigated fault segment. The vertical displacement and the dip of the scarp were extracted every metre along the strike of the detected fault segment based on the processed HRDEM. The scarp variability was analysed by using statistical and morphological methods. The analysis was done in a geographical information system (GIS) environment. Results show a normal distribution for the scanned fault scarp's vertical displacement. Based on these facts, the mean value of height was chosen to define the authentic vertical displacement. Consequently the scarp can be divided into above, below and within the range of mean (within one standard deviation) and quantify the modifications of vertical displacement. Therefore, the fault segment can be subdivided into areas which are influenced by external modification like erosion and sedimentation processes. Moreover, to describe and measure the variability of vertical displacement along strike the fault, the semi-variance was calculated with the variogram method. This method is used to determine how much influence the external processes have had on the vertical displacement. By combining of morphological and statistical results, the fault can be subdivided into areas with high external influences and areas with authentic fault scarps, which have little or no external influences. This subdivision is necessary for long term throw-rate calculations, because without this differentiation the calculated rates would be misleading and the activity of a fault would be incorrectly assessed with significant implications for seismic hazard assessment since fault slip rate data govern the earthquake recurrence. Furthermore, by using this workflow areas with minimal external influences can be determined, not only for throw-rate calculations, but also for determining samples sites for absolute dating techniques such as cosmogenic nuclide dating. The main outcomes of this study include: i) there is no direct correlation between the fault's mean vertical displacement and dip (R² less than 0.31); ii) without subdividing the scanned scarp into areas with differing amounts of external influences, the along strike variability of vertical displacement is ±35%; iii) when the scanned scarp is subdivided the variation of the vertical displacement of the authentic scarp (exposed by earthquakes only) is in a range of ±6% (the varies depending on the fault from 7 to 12%); iv) the calculation of the long term throw-rate (since 13 ka) for four scarps in Crete using the authentic vertical displacement is 0.35 ± 0.04 mm/yr at Kastelli 1, 0.31 ± 0.01 mm/yr at Kastelli 2, 0.85 ± 0.06 mm/yr at the Asomatos fault (Sellia) and 0.55 ± 0.05 mm/yr at the Lastros fault.

AGV Safety Areas Obstacle Detection and Interaction with Point Cloud Derived Map

This thesis project aims to the development of an algorithm for the obstacle detection and the interaction between the safety areas of an Automated Guided Vehicles (AGV) and a Point Cloud derived map inside the context of a CAD software. The first part of the project focuses on the implementation of an algorithm for the clipping of general polygons, with which has been possible to: construct the safety areas polygon, derive the sweep of this areas along the navigation path performing a union and detect the intersections with line or polygon representing the obstacles. The second part is about the construction of a map in terms of geometric entities (lines and polygons) starting from a point cloud given by the 3D scan of the environment. The point cloud is processed using: filters, clustering algorithms and concave/convex hull derived algorithms in order to extract line and polygon entities representing obstacles. Finally, the last part aims to use the a priori knowledge of possible obstacle detections on a given segment, to predict the behavior of the AGV and use this prediction to optimize the choice of the vehicle's assigned velocity in that segment, minimizing the travel time.

From point cloud to HBIM: an integrated workflow for 3D reconstruction of heritage building with model accuracy evaluation

Modern society is now facing significant difficulties in attempting to preserve its architectural heritage. Numerous challenges arise consequently when it comes to documentation, preservation and restoration. Fortunately, new perspectives on architectural heritage are emerging owing to the rapid development of digitalization. Therefore, this presents new challenges for architects, restorers and specialists. Additionally, this has changed the way they approach the study of existing heritage, changing from conventional 2D drawings in response to the increasing requirement for 3D representations. Recently, Building Information Modelling for historic buildings (HBIM) has escalated as an emerging trend to interconnect geometrical and informational data. Currently, the latest 3D geomatics techniques based on 3D laser scanners with enhanced photogrammetry along with the continuous improvement in the BIM industry allow for an enhanced 3D digital reconstruction of historical and existing buildings. This research study aimed to develop an integrated workflow for the 3D digital reconstruction of heritage buildings starting from a point cloud. The Pieve of San Michele in Acerboli’s Church in Santarcangelo Di Romagna (6th century) served as the test bed. The point cloud was utilized as an essential referential to model the BIM geometry using Autodesk Revit® 2022. To validate the accuracy of the model, Deviation Analysis Method was employed using CloudCompare software to determine the degree of deviation between the HBIM model and the point cloud. The acquired findings showed a very promising outcome in the average distance between the HBIM model and the point cloud. The conducted approach in this study demonstrated the viability of producing a precise BIM geometry from point clouds.

Domain adaptation per classificazione di point cloud mediante pseudo-annotazioni

La classificazione di dati geometrici 3D come point cloud è un tema emergente nell'ambito della visione artificiale in quanto trova applicazione in molteplici contesti di guida autonoma, robotica e realtà aumentata. Sebbene nel mercato siano presenti una grande quantità di sensori in grado di ottenere scansioni reali, la loro annotazione costituisce un collo di bottiglia per la generazione di dataset. Per sopperire al problema si ricorre spesso alla domain adaptation sfruttando dati sintetici annotati. Questo elaborato si pone come obiettivo l'analisi e l'implementazione di metodi di domain adaptation per classificazione di point cloud mediante pseudo-labels. In particolare, sono stati condotti esperimenti all'interno del framework RefRec valutando la possibilità di sostituire nuove architetture di deep learning al modello preesistente. Tra queste, Transformer con mascheramento dell'input ha raggiunto risultati superiori allo stato dell'arte nell'adattamento da dati sintetici a reali (ModelNet->ScanNet) esaminato in questa tesi.

Deciduous tree reconstruction algorithm based on cylinder fitting from mobile terrestrial laser scanned point clouds

Vector reconstruction of objects from an unstructured point cloud obtained with a LiDAR-based system (light detection and ranging) is one of the most promising methods to build three dimensional models of orchards. The cylinder fitting method for woody structure reconstruction of leafless trees from point clouds obtained with a mobile terrestrial laser scanner (MTLS) has been analysed. The advantage of this method is that it performs reconstruction in a single step. The most time consuming part of the algorithm is generation of the cylinder direction, which must be recalculated at the inclusion of each point in the cylinder. The tree skeleton is obtained at the same time as the cluster of cylinders is formed. The method does not guarantee a unique convergence and the reconstruction parameter values must be carefully chosen. A balanced processing of clusters has also been defined which has proven to be very efficient in terms of processing time by following the hierarchy of branches, predecessors and successors. The algorithm was applied to simulated MTLS of virtual orchard models and to MTLS data of real orchards. The constraints applied in the method have been reviewed to ensure better convergence and simpler use of parameters. The results obtained show a correct reconstruction of the woody structure of the trees and the algorithm runs in linear logarithmic time

A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.