Search

Point cloud registration plays a crucial role in many applications, from robotics and autonomous navigation to medical imaging and 3D scene reconstruction. While the Iterative Closest Point (ICP) algorithm is a well-known shape registration choice, its efficiency and accuracy can be affected by the vast search space for point correspondences. k-means clustering emerges as a promising solution for partitioning the search space into smaller clusters to reduce the computational complexity and increase the performance of the matching. However, the number and size of these clusters and how they affect the registration remains a critical and yet not fully explored factor. This paper delves into the relationship between the number of k-means clusters and point cloud registration accuracy. To determine the effect of the number of k-means clusters on registration accuracy and efficiency and to understand any emerging pattern, k-meansICP is developed to use the k-means algorithm to cluster the correspondence search space. Two sets of 3D molecular shapes with differing complexities are matched using initial rotation angles 15, 30, and 60 degrees with 2 to 10 k-means clusters. The results are then compared with the original ICP algorithm.

Point cloud registration is an extensively studied field in computer vision, featuring a variety of existing methods, all aimed at achieving the common objective of determining a transformation that aligns two point clouds. Methods like the Iterative Closet Point (ICP) and Fast Global Registration (FGR) have shown to work well for many years, but recent work has explored different learning-based approaches, showing promising results. This work compares the performance of two learning-based methods GeoTransformer and RegFormer against three baseline methods ICP point-to-point, ICP point-to-plane, and FGR. The comparison was conducted on data provided by the Swedish Defence Research Agency (FOI), where the data was captured with a photon-counting LiDAR sensor. Findings suggest that while ICP point-to-point and ICP point-to-plane exhibit solid performance, the GeoTransformer demonstrates the potential for superior outcomes. Additionally, the RegFormer and FGR perform worse than the ICP variants and the GeoTransformer.

Point Cloud Registration with data measured from a photon-counting LIDAR sensor from a large distance (500 m - 1.5 km) is an expanding field. Data measuredfrom far is sparse and have low detail, which can make the registration processdifficult, and registering this type of data is fairly unexplored. In recent years,machine learning for point cloud registration has been explored with promisingresults. This work compares the performance of the point cloud registration algorithm Iterative Closest Point with state-of-the-art algorithms, with data froma photon-counting LIDAR sensor. The data was provided by the Swedish Defense Research Agency (FOI). The chosen state-of-the-art algorithms were thenon-learning-based Fast Global Registration and learning-based D3Feat and SpinNet. The results indicated that all state-of-the-art algorithms achieve a substantial increase in performance compared to the Iterative Closest Point method. Allthe state-of-the-art algorithms utilize their calculated features to obtain bettercorrespondence points and therefore, can achieve higher performance in pointcloud registration. D3Feat performed point cloud registration with the highestaccuracy of all the state-of-the-art algorithms and ICP.

Carbon fiber and fiberglass composite panels are commonly used in the aerospace and automotive industries. During the manufacturing process, composite panels undergo surface treatment processes such as priming and coating. For coating layers to adhere strongly to the surface, the part surface must be free of any contamination such as grease. Detection and removal of contamination is an important step in the manufacturing of composite panels, particularly in the aerospace industry. This thesis develops a novel vision-based framework to enable fully automated inspection and robotic abrasion of free-form composite panels. The first aim of the thesis is to automatically locate arbitrarily placed composite panels within the robot workplace. The proposed method employs iterative closest point (ICP) registration technique for locating the part in the robot cell. An additional module based on vision-based error correction is developed in the thesis for improving the accuracy of part localization. The proposed part localization technique eliminates the need for manual calibration of part placement in each robot cycle. The ASTM-F22 water-break test is widely used for detecting hydrophobic contamination on a surface. As the second aim in this thesis, vision-based algorithms are developed to allow for the automated detection (inspection) of hydrophobic contamination during the water-break test. The developed vision-based algorithms can successfully detect the layer of hydrophobic contamination on the free-form panel. The third aim of this thesis is to automatically generate robotic abrasion tool paths to remove detected contamination. In the proposed framework, the panel surface is divided into multiple grids. The point clouds of each grid are first used to reconstruct continuous parametric B-spline surfaces. B-spline surfaces are then used to make an abrasion tool path for each grid. The developed vision-based inspection algorithm determines which grids contain contamination a

Point cloud registration is a technique to align two sets of points with manifold applications across a range of industries. However, due to a lack of adequate sensing technology, this technique has seldom found applications in the automotive sector up to now. With the advent of solid-state Light Detection and Ranging (LiDAR) sensors that are easily integrable in series production vehicles as means to sense the surrounding environment, this technique can be functional to automate their operations. Maneuvering a vehicle in the proximity of a reference object is one such operation, which can only be performed by accurately estimating its position and orientation relative to the vehicle itself. This project deals with the design and the implementation of an algorithm to accurately locate an aircraft parked on an airfield apron in real time. This is achieved by registering the point cloud model of the plane to the measurement point cloud of the scene produced by the LiDAR sensors on board the vehicle. To this end, the Iterative Closest Point (ICP) algorithm is a well-established approach to register two sets of points without prior knowledge of the correspondences between pairs of points, which, however, is notoriously sensitive towards outliers and computationally expensive with large point clouds. In this work, different variants are presented that improve on the standard ICP algorithm, in terms of accuracy and runtime performance, by leveraging different data structures to index the reference model and outlier rejection strategies. The results show that the implemented algorithms can produce estimates of centimeter precision in milliseconds based only on partial observations of the aircraft, outperforming another established solution tested., Punktmolnregistrering är en teknik för att anpassa två uppsättningar punkter med mångfaldiga applikationer inom en rad branscher. På grund av bristen på adekvat sensorsteknik har denna teknik hittills sällan används inom automotivesektorn. Med tillkomsten av solid-state LiDAR -sensorer som enkelt kan integreras i serieproduktionsfordon för att kunna känna av den omgivningen, kan denna teknik automatisera verksamheten. Att manövrera ett fordon i närheten av ett referensobjekt är en sådan operation, som bara kan utföras genom att exakt uppskatta dess position och orientering i förhållande till själva fordonet. Detta projekt handlar om design och implementering av en algoritm för att exakt lokalisera ett flygplan parkerat på ett flygfält i realtid. Detta uppnås genom att registrera planetens molnmodell till mätpunktsmolnet på scenen som produceras av LiDAR -sensorerna ombord på fordonet. För detta ändamålet är Iterative Closest Point (ICP) -algoritmen ett väletablerat tillvägagångssätt för att registrera två uppsättningar punkter utan föregående kännedom om överensstämmelserna mellan parpar, vilket dock är notoriskt känsligt för avvikelser och beräknat dyrt med stora punktmoln. I detta arbete presenteras olika varianter som förbättrar standard ICP - algoritmen, när det gäller noggrannhet och runtime performance, genom att utnyttja olika datastrukturer för att indexera referensmodellen och outlier -avvisningsstrategier. Resultaten visar att de implementerade algoritmerna kan producera uppskattningar av centimeters precision i millisekunder baserat endast på partiella observationer av flygplanet, vilket överträffar en annan etablerad lösning som testats.

Práce je zaměřena na vytvoření aplikace pro lokalizaci předmětů pro Bin Picking. Teoretická část je zaměřena na popis lokalizačních algoritmů, Bin pickingu a systému Intel Realsense. V praktické části je hlavním cílem vytvořit aplikaci, která je schopná určit polohu předmětu v prostoru pomocí 3D kamery. Součástí je i implementace algoritmů a jejich vyhodnocení., The work is focused on making an application for object localization in order to use in Bin Picking. In the theoretical part is described algorithms for object localization, Bin Picking and Intel Realsense Systems. The main goal in the practical part is to make an application that is able to determine the position of an object in space using a 3D camera. It also includes implementation of the algorithms and their evaluation., Fakulta elektrotechniky a informatiky, Práce se věnuje vytvoření postupu pro lokalizaci blízkých složitých předmětů a otestování všech jeho kroků. Jako zdroj dat byla použita kamera Intel RealSenze ZR300. Co se týká obsahové stránky diplomové práce, diplomant splnil všechny body zadání, vypíchnout je třeba zejména rešeršní část práce, kterou je možno použít jako komplexní úvod do problematiky tohoto bouřlivě se rozvíjejícího se oboru. Diplomová práce splnila zadání., Dokončená práce s úspěšnou obhajobou

Point clouds are commontly used in many areas of technical practice. Nowadays, the common applications are in area of autonomous cars and 3D terrain or object modelling. During the scanning process, the scanning device or object is moving. So, the problem of precise point cloud registration arises. In this article, we describe Iterative Closest Point (ICP) algorithm that is suitable for fine registration. We introduce some of the improvements that leads to higher precision, speed computation and efficiency.

Point clouds are commontly used in many areas of technical practice. Nowadays, the common applications are in area of autonomous cars and 3D terrain or object modelling. During the scanning process, the scanning device or object is moving. So, the problem of precise point cloud registration arises. In this article, we describe Iterative Closest Point (ICP) algorithm that is suitable for fine registration. We introduce some of the improvements that leads to higher precision, speed computation and efficiency.

Point clouds are commontly used in many areas of technical practice. Nowadays, the common applications are in area of autonomous cars and 3D terrain or object modelling. During the scanning process, the scanning device or object is moving. So, the problem of precise point cloud registration arises. In this article, we describe Iterative Closest Point (ICP) algorithm that is suitable for fine registration. We introduce some of the improvements that leads to higher precision, speed computation and efficiency.

Die Kartierung und Lokalisierung eines mobilen Roboters in seiner Umgebung ist eine wichtige Voraussetzung für dessen Autonomie. In dieser Arbeit wird der Einsatz eines 3D-Laserscanners zur Erfüllung dieser Aufgaben untersucht. Durch die optimierte Anordnung eines rotierenden 2D-Laserscanners werden hochauflösende Bereiche vorgegeben. Zudem wird mit Hilfe von ICP die Kartierung und Lokalisierung im Stillstand durchgeführt. Bei der Betrachtung zur Verbesserung der Bewegungsschätzung wird auch eine Möglichkeit zur Lokalisierung während der Bewegung mit 3D-Scans vorgestellt. Die vorgestellten Algorithmen werden durch Experimente mit realer Hardware evaluiert.

This dissertation describes the development of an integrated locomotion interface for building self-contained, portable, and immersive virtual environment (VE) systems. Such VE systems do not rely on any infrastructure support and can be used in indoor/outdoor open spaces. The natural walking motions of the user are utilized as a means of signal generation to drive the locomotion interface, which provides the user with a higher sense of presence. This work investigates the use of two types of measurement systems, the inertial/magnetic measurement units and the ranging measurement systems, to develop a locomotion interface for portable VE systems. Algorithms were developed for each of the two systems to provide the necessary functionalities of the desired locomotion interface. Fusing measurements from a head-mounted and a foot-mounted inertial/magnetic sensor, a locomotion interface was developed for allowing the use of natural walking motions to navigate through virtual environments. To prevent collisions with physical environment boundaries such as walls, a ranging measurement system was used to detect the presence of obstacles. An improved Iterative Closest Point (ICP) algorithm was developed for map-building of the physical environment and for estimating the user s orientation and position within the map. A redirected-walking mechanism was utilized for redirecting the user s walking direction away from boundaries in the physical environment. The two types of measurement systems were integrated to constitute a novel locomotion interface for portable VE systems, and its effectiveness was experimentally tested and demonstrated.

With a growing threat from space debris, it has become more important for space agencies to have a means of reducing the probability of escalating the dangers posed by it. For this purpose, servicer satellites need to be built. These satellites need to be able to interfere with “dead” satellites and deorbit defunct satellites. In order to be able to navigate around these types of objects, it is necessary for the servicer satellite to be able to determine its position around the object and the relative motion between the debris and the servicer. This thesis describes an algorithm that determines the trajectory of the servicer satellite based on a 3D reconstruction of a model of the target object. It takes 3D point clouds from a sensor and transform these point clouds into a 3D model that can be used by the servicer to navigate and determine its position around the target object. The approach uses a simulation of a LIDAR instrument to obtain the data which is then used as input for the algorithm to reconstruct the path of the servicer satellite. This thesis was done at Airbus Defense and Space as it is currently activley trying to develop the capability to interfere with space objects. The resulting algorithm can perform a 3D reconstruction of a target object in real-time if appropriate parameters are being used and it can also determine the position of the servicer around this model. Moreover, it can also reconstruct the trajectory for the observer around its target., Engineering, Space, Aerospace Engineering

The Iterative Closest Point algorithm (ICP) is commonly used in engineering applications to solve the rigid registration problem of partially overlapped point sets which are pre-aligned with a coarse estimate of their relative positions. This iterative algorithm is applied in many areas such as the medicine for volumetric reconstruction of tomography data, in robotics to reconstruct surfaces or scenes using range sensor information, in industrial systems for quality control of manufactured objects or even in biology to study the structure and folding of proteins. One of the algorithm’s main problems is its high computational complexity (quadratic in the number of points with the non-optimized original variant) in a context where high density point sets, acquired by high resolution scanners, are processed. Many variants have been proposed in the literature whose goal is the performance improvement either by reducing the number of points or the required iterations or even enhancing the complexity of the most expensive phase: the closest neighbor search. In spite of decreasing its complexity, some of the variants tend to have a negative impact on the final registration precision or the convergence domain thus limiting the possible application scenarios. The goal of this work is the improvement of the algorithm’s computational cost so that a wider range of computationally demanding problems from among the ones described before can be addressed. For that purpose, an experimental and mathematical convergence analysis and validation of point-to-point distance metrics has been performed taking into account those distances with lower computational cost than the Euclidean one, which is used as the de facto standard for the algorithm’s implementations in the literature. In that analysis, the functioning of the algorithm in diverse topological spaces, characterized by different metrics, has been studied to check the convergence, efficacy and cost of the method in order to deter

Proposed in this work is a method for real-time 3D human pose tracking using depth video with the ability to learn and utilize functional environmental features from the scene. Learning environmental features is done by pose classifications of the tracked trajectory for recovering pose-to-surface interaction points, resulting in surfaces represented by floating planes, either bounded or unbounded. In the tracking method surfaces can be utilized for inferring likely poses for interaction with the surfaces, as well as be utilized as hard physical constraints for reducing freedom of interpretation in the tracker.The method employed for tracking is a top-down approach, with the only significant learning criterion being a library of prefabricated body poses in this implementation inhabited by 15 variants distributed into three categories.The method used for inferring likely poses of interaction with the environment is created explicitly for use in this work, and includes a nearness measure along with a 1NN classification using the tracked state and the defined pose library.The method used for pose classifications for learning surfaces is a 1NN approach using the tracked state and the defined pose library to gather interaction points, to which an orthogonal least squares plane fitting method is applied.For evaluation of the method a dataset consisting of two sequences was created, with synchronized depth- and motion capture data, containing challenging poses. Additionally two other data sources were included, also having synchronized depth- and motion capture data.The results suggest an achievable benefit in tracking robustness from knowing the environment, as well as an achievable method for learning specific parts of this environment during tracking. However, not every type of environmental features could be feasibly detected and used.

This thesis describes all the necessary parts needed to build a complete system for autonomous indoor mapping in 3D. The robotic platform used is a two-wheeled Segway, operating in a planar environment. This, together with wheel odometers, an Inertial Measurement Unit (IMU), two Microsoft Kinects and a laptop comprise the backbone of the system, which can be divided into three parts: The localization and mapping part, which fundamentally is a SLAM (simultaneous localization and mapping) algorithm implemented using the registration technique Iterative Closest Point (ICP). Along with the map being in 3D, it also designed to handle the mapping of dynamic scenes, something absent from the standard SLAM design. The planning used by the system is twofold. First, the path planning - finding a path from the current position to a destination - and second, the target planning - determining where to go next given the current state of the map and the robot. The third part of the system is the control and collision systems, which while they have not received much focus, are very necessary for a fully autonomous system. Contributions made by this thesis include: The 3D map framework Octomap is extended to handle the mapping of dynamic scenes; A new method for target planning, based on image processing is presented; A calibration procedure for the robot is derived that gives a full six degree of freedom pose for each Kinect. Results show that our calibration procedure produces an accurate pose for each Kinect, which is crucial for a functioning system. The dynamic mapping is shown to outperform the standard occupancy grid in fundamental situations that arise when mapping dynamic scenes. Additionally, the results indicate that the target planning algorithm provides a fast and easy way to plan new target destinations. Finally, the entire system’s autonomous mapping capabilities are evaluated together, producing promising results. However, it also highlights some problems that limit, Detta exjobb beskriver delarna som krävs för att för bygga ett komplett system som autonomt kartlägger inomhusmiljöer i tre dimensioner. Robotplattformen är en Segway, som är kapabel att röra sig i ett plan. Segwayn, tillsammans med en tröghetssensor, två Microsoft Kinects och en bärbar dator utgör grunden till systemet, som kan delas i tre delar: En lokaliserings- och karteringsdel, som i grunden är en SLAM-algoritm (simultan lokalisering och kartläggning) baserad på registreringsmetoden Iterative Closest Point (ICP). Kartan som byggs upp är i tre dimensioner och ska dessutom hantera kartläggningen av dynamiska miljöer, något som orginalforumleringen av SLAM problemet inte klarar av. En automatisk planeringsdel, som består av två delar. Dels ruttplanering som går ut på att hitta en väg från sin nuvarande position till det valda målet och dels målplanering som innebär att välja ett mål att åka till givet den nuvarande kartan och robotens nuvarande position. Systemets tredje del är regler- och kollisionssystemen. Dessa system har inte varit i fokus i detta arbete, men de är ändå högst nödvändiga för att ett autonomt system skall fungera. Detta examensarbete bidrar med följande: Octomap, ett ramverk för kartläggningen i 3D, har utökats för att hantera kartläggningen av dynamiska miljöer; En ny metod för målplanering, baserad på bildbehandling läggs fram; En kalibreringsprocedur för roboten är framtagen som ger den fullständiga posen i förhållande till roboten för varje Kinect. Resultaten visar att vår kalibreringsprocedur ger en nogrann pose for för varje Kinect, vilket är avgörande för att systemet ska fungera. Metoden för kartläggningen av dynamiska miljöer visas prestera bra i grundläggande situationer som uppstår vid kartläggning av dynamiska miljöer. Vidare visas att målplaneringsalgoritmen ger ett snabbt och enkelt sätt att planera mål att åka till. Slutligen utvärderas hela systemets autonoma kartläggningsförmåga, som ger lovande resultat. Dock lyfter resultat

Fine registration of point clouds plays an important role in data analysis in Terrestrial Laser Scanning (TLS). This work proposes a block-to-point fine registration approach to correct the errors of point clouds from TLS and of geodetic networks observed using total stations. Based on a reference coordinate system, the block-to-point estimation is performed to obtain representative points. Then, fine registration with a six-parameter transformation is performed with the help of an Iterative Closest Point (ICP) method. For comparisons, fine registration with a seven-parameter transformation is introduced by applying a Singular Value Decomposition (SVD) algorithm. The proposed method not only corrects the registration errors between a geodetic network and the scans, but also considers the errors among the scans. The proposed method was tested on real TLS data of a dam surface, and the results showed that distance discrepancies of estimated representative points between scans were reduced by approximately 60%.

This research examines the application of using a scanning Light Detection and Ranging(LiDAR) to perform Automated Aerial Refueling(AAR). Speci cally this thesis presents two algorithms to determine the relative position between the tanker and receiver aircraft. These two algorithms require a model of the tanker aircraft and the relative attitude between the aircraft. The rst algorithm ts the measurements to the model of the aircraft using a modi ed Iterative Closest Point (ICP) algorithm. The second algorithm uses the model to predict LiDAR scans and compare them to actual measurements while perturbing the estimated location of the tanker. Each algorithm was tested with simulated LiDAR data before real data became available from test ights. The data collected from this test ight was used to determine the accuracy of the two algorithms with real LiDAR data. After correcting for modeling errors the accuracy of each algorithm is about a Mean Radial Spherical Error of 40cm., The original document contains color images.

Now a days where technological advancements are growing at a rapid pace, it has become a common norm for all the manufacturing companies to be abreast with these advancements for being competitive in market. This thesis deals with development of one such common norm for one of the products (Roof rack component) for company Thule. The main aim of the thesis is to curtail the products lead time to market and this was achieved by using an artificial intelligence technique i.e., Case-based reasoning (CBR). Roof rack component which is mounted on car roof is mainly constituted by two parts foot pad and bracket, this thesis main interest was concerned with only brackets and its geometry. This thesis is based on contemplating the already implemented concepts in this context, designer requirements and exploring better solutions. The methods of implementation adopted here was using CBR concept which is based on indexing , retrieve, adapt, review, retain and employing these concepts in form of an algorithm. The concept for developing the algorithm was based on Iterative closest point (ICP) approach which emphasise on assigning lower weight to pairs with greater point to point distance. The results portrayed are with respect to geometry and also with respect to application interface developed, which both together provides us a better solution.

Matching and fusion of 3D point clouds, such as close range laser scans, is important for creating an integrated 3D model data infrastructure. The Iterative Closest Point algorithm for alignment of point clouds is one of the most commonly used algorithms for matching of rigid bodies. Evidently, scans are acquired from different positions and might present different data characterization and accuracies, forcing complex data-handling issues. The growing demand for near real-time applications also introduces new computational requirements and constraints into such processes. This research proposes a methodology to solving the computational and processing complexities in the ICP algorithm by introducing specific performance enhancements to enable more efficient analysis and processing. An Octree data structure together with the caching of localized Delaunay triangulation-based surface meshes is implemented to increase computation efficiency and handling of data. Parallelization of the ICP process is carried out by using the Single Instruction, Multiple Data processing scheme – based on the Divide and Conquer multi-branched paradigm – enabling multiple processing elements to be performed on the same operation on multiple data independently and simultaneously. When compared to the traditional non-parallel list processing the Octree-based SIMD strategy showed a sharp increase in computation performance and efficiency, together with a reliable and accurate alignment of large 3D point clouds, contributing to a qualitative and efficient application.

Quality descriptions are parts of the key tasks of geodetic data processing. Systematic errors should be detected and avoided in order to insure the high quality standards required by structural monitoring. In this study, the iterative closest point (ICP) method was invested to detect systematic errors in two overlapping data sets. There are three steps to process the systematic errors: firstly, one of the data sets was transformed to a reference system by the introduction of the Gauss–Helmert (GH) model. Secondly, quadratic form estimation and segmentation methods are proposed to guarantee the overlapping data sets. Thirdly, the ICP method was employed for a finer registration and detecting the systematic errors. A case study was casted in which a dam surface in Germany was scanned by terrestrial laser scanning (TLS) technology. The results indicated that with the conjugation of ICP algorithm the accuracy of the data sets was improved approximately by 1.6 mm.

This paper presents a method for measuring the in-bucket payload volume on a dragline excavator for the purpose of estimating the material's bulk density in real-time. Knowledge of the payload's bulk density can provide feedback to mine planning and scheduling to improve blasting and therefore provide a more uniform bulk density across the excavation site. This allows a single optimal bucket size to be used for maximum overburden removal per dig and in turn reduce costs and emissions in dragline operation and maintenance. The proposed solution uses a range bearing laser to locate and scan full buckets between the lift and dump stages of the dragline cycle. The bucket is segmented from the scene using cluster analysis, and the pose of the bucket is calculated using the Iterative Closest Point (ICP) algorithm. Payload points are identified using a known model and subsequently converted into a height grid for volume estimation. Results from both scaled and full scale implementations show that this method can achieve an accuracy of above 95%.

This paper presents a new edge-based technique for image alignment, combining Fourier Descriptors (FD) and the Iterative Closest Point (ICP) computation into an accurate and robust processing pipeline. Once edges are identified in the reference and target images, Fourier Descriptors are used to simultaneously determine edge correspondence and estimate the transformation parameters. Subsequently, an ICP computation is applied to further improve the alignment results. Using Fourier Descriptors in combination with a reliable distance matrix, corresponding edge pairs can be reliably detected for all identified edges. (C) 2008 Published by Elsevier B.V.

Registration, the process of transforming different sets of data into a common coordinate system, is often required to allow the comparison or integration of the data sets. Techniques such as the widely used Iterative Closest Point (ICP) algorithm have limited effectiveness on data sets that require significant transformation or that have large degrees of inconsistencies. This paper describes a biologically inspired algorithm for data registration that is based on two theories of human perception. The use of macro level registration based on these theories combined with micro level registration using the ICP algorithm provides enhanced registration of these challenging data sets. The new algorithm was tested extensively on simulated sensor images in several scenarios key to successful application to autonomous ground navigation. The excellent performance of the biologically inspired algorithm in these cases makes it a promising candidate for this field., Presented at the Performance Metrics for Intelligent Systems Workshop held in Gaithersburg, MD on 21-23 Aug 2006. Published in the Proceedings of the Performance Metrics for Intelligent Systems Workshop, p197-204, 2006. The original document contains color images.

Diplomová práce je zaměřena na problematiku detekce a sledování polohy hlavy v obraze jako jednu s možností jak zlepšit možnosti interakce mezi počítačem a člověkem. Hlavním přínosem diplomové práce je využití inovativních hardwarových a softwarových technologií jakými jsou Microsoft Kinect, Point Cloud Library a CImg Library. Na úvod je představeno shrnutí předchozích prací na podobné téma. Následuje charakteristika a popis databáze, která byla vytvořena pro účely diplomové práce. Vyvinutý systém pro detekci a sledování polohy hlavy je založený na akvizici 3D obrazových dat a registračním algoritmu Iterative Closest Point. V závěru diplomové práce je nabídnuto hodnocení vzniklého systému a jsou navrženy možnosti jeho budoucího zlepšení., This thesis is focused on head pose estimation as a possibility to bridge a gap between human and computers. The main contribution of the thesis is usage of a novel hardware and software technology such as Kinect, Point Cloud Library and CImg Library. In the beginning of the thesis overview of prior works in a field of head pose estimation is provided. Own database was created in order to test and evaluate developed algorithm. The head pose estimation and tracking system is based on 3D image data acquisition and Iterative Closest Point registration algorithm. In the end of thesis performance and limitation of the system are described and further improvement is proposed.

Cílem této práce je najít vhodnou metodu pro určení pózy dvou vzájemně pootočených objektů, pokusit se ji implementovat nejprve v jazyce C++ bez použití externích knihoven a následně v jazyce Kuka Robot Language (KRL). V úvodu jsou probrány dva možné způsoby řešení: iterative closest point algoritmus (ICP) a Kabschův algoritmus. Z nich je následně jeden vybrán a je navrhnuta strukturu programu, který bude implementován. Následně se otestuje s jakou přesností tato implementace vybraného algoritmu funguje a jaká skýtá úskalí. Poté je krátce popsán jazyk KRL a je uveden postup migrace algoritmu z C++ a problémy, které se v průběhu vyskytly., The goal of this paper is to find a good method to determine the pose of two, mutually rotated, objects and to try and implement it first in C++ without the usage of any external libraries and then in Kuka Robot Language (KRL). First we are going to look at two different approaches to solving this problem: The Iterative Closest Point algorithm (ICP) and the Kabsch Algorithm. From them one is going to be chosen and a program will be build around it. Following its implementation, the algorithm’s precision is going to be tested. Finally KRL will be briefly introduced and the various problems involving transition of the algorithm from C++ to KRL will be talked about.

Tato práce se zabývá vytvářením 3D map vnitřního prostředí pomocí senzoru Microsoft Kinect. V první části je uveden popis senzoru Microsoft Kinect, metody získávání a zpracování hloubkových dat a jejich následné skládání pomocí různých algoritmů. V druhé části práce je ukázáno použití algoritmu pro skládání prostorových map a výsledné 3D mapy vnitřního prostředí., This work is focused on creating 3D maps of indoor enviroment using Microsoft Kinect sensor. The first part shows the description of Microsoft Kinect sensor, the methods for acquisition and processing of depth data and their registration using different algorithms. The second part shows application of algorithms for map registration and final 3D maps of indoor enviroment.

Diplomová práce je zaměřena na problematiku detekce a sledování polohy hlavy v obraze jako jednu s možností jak zlepšit možnosti interakce mezi počítačem a člověkem. Hlavním přínosem diplomové práce je využití inovativních hardwarových a softwarových technologií jakými jsou Microsoft Kinect, Point Cloud Library a CImg Library. Na úvod je představeno shrnutí předchozích prací na podobné téma. Následuje charakteristika a popis databáze, která byla vytvořena pro účely diplomové práce. Vyvinutý systém pro detekci a sledování polohy hlavy je založený na akvizici 3D obrazových dat a registračním algoritmu Iterative Closest Point. V závěru diplomové práce je nabídnuto hodnocení vzniklého systému a jsou navrženy možnosti jeho budoucího zlepšení., This thesis is focused on head pose estimation as a possibility to bridge a gap between human and computers. The main contribution of the thesis is usage of a novel hardware and software technology such as Kinect, Point Cloud Library and CImg Library. In the beginning of the thesis overview of prior works in a field of head pose estimation is provided. Own database was created in order to test and evaluate developed algorithm. The head pose estimation and tracking system is based on 3D image data acquisition and Iterative Closest Point registration algorithm. In the end of thesis performance and limitation of the system are described and further improvement is proposed.

Cílem této práce je najít vhodnou metodu pro určení pózy dvou vzájemně pootočených objektů, pokusit se ji implementovat nejprve v jazyce C++ bez použití externích knihoven a následně v jazyce Kuka Robot Language (KRL). V úvodu jsou probrány dva možné způsoby řešení: iterative closest point algoritmus (ICP) a Kabschův algoritmus. Z nich je následně jeden vybrán a je navrhnuta strukturu programu, který bude implementován. Následně se otestuje s jakou přesností tato implementace vybraného algoritmu funguje a jaká skýtá úskalí. Poté je krátce popsán jazyk KRL a je uveden postup migrace algoritmu z C++ a problémy, které se v průběhu vyskytly., The goal of this paper is to find a good method to determine the pose of two, mutually rotated, objects and to try and implement it first in C++ without the usage of any external libraries and then in Kuka Robot Language (KRL). First we are going to look at two different approaches to solving this problem: The Iterative Closest Point algorithm (ICP) and the Kabsch Algorithm. From them one is going to be chosen and a program will be build around it. Following its implementation, the algorithm’s precision is going to be tested. Finally KRL will be briefly introduced and the various problems involving transition of the algorithm from C++ to KRL will be talked about.

Tato práce se zabývá vytvářením 3D map vnitřního prostředí pomocí senzoru Microsoft Kinect. V první části je uveden popis senzoru Microsoft Kinect, metody získávání a zpracování hloubkových dat a jejich následné skládání pomocí různých algoritmů. V druhé části práce je ukázáno použití algoritmu pro skládání prostorových map a výsledné 3D mapy vnitřního prostředí., This work is focused on creating 3D maps of indoor enviroment using Microsoft Kinect sensor. The first part shows the description of Microsoft Kinect sensor, the methods for acquisition and processing of depth data and their registration using different algorithms. The second part shows application of algorithms for map registration and final 3D maps of indoor enviroment.

Cílem této práce je najít vhodnou metodu pro určení pózy dvou vzájemně pootočených objektů, pokusit se ji implementovat nejprve v jazyce C++ bez použití externích knihoven a následně v jazyce Kuka Robot Language (KRL). V úvodu jsou probrány dva možné způsoby řešení: iterative closest point algoritmus (ICP) a Kabschův algoritmus. Z nich je následně jeden vybrán a je navrhnuta strukturu programu, který bude implementován. Následně se otestuje s jakou přesností tato implementace vybraného algoritmu funguje a jaká skýtá úskalí. Poté je krátce popsán jazyk KRL a je uveden postup migrace algoritmu z C++ a problémy, které se v průběhu vyskytly., The goal of this paper is to find a good method to determine the pose of two, mutually rotated, objects and to try and implement it first in C++ without the usage of any external libraries and then in Kuka Robot Language (KRL). First we are going to look at two different approaches to solving this problem: The Iterative Closest Point algorithm (ICP) and the Kabsch Algorithm. From them one is going to be chosen and a program will be build around it. Following its implementation, the algorithm’s precision is going to be tested. Finally KRL will be briefly introduced and the various problems involving transition of the algorithm from C++ to KRL will be talked about.

Cílem této práce je najít vhodnou metodu pro určení pózy dvou vzájemně pootočených objektů, pokusit se ji implementovat nejprve v jazyce C++ bez použití externích knihoven a následně v jazyce Kuka Robot Language (KRL). V úvodu jsou probrány dva možné způsoby řešení: iterative closest point algoritmus (ICP) a Kabschův algoritmus. Z nich je následně jeden vybrán a je navrhnuta strukturu programu, který bude implementován. Následně se otestuje s jakou přesností tato implementace vybraného algoritmu funguje a jaká skýtá úskalí. Poté je krátce popsán jazyk KRL a je uveden postup migrace algoritmu z C++ a problémy, které se v průběhu vyskytly., The goal of this paper is to find a good method to determine the pose of two, mutually rotated, objects and to try and implement it first in C++ without the usage of any external libraries and then in Kuka Robot Language (KRL). First we are going to look at two different approaches to solving this problem: The Iterative Closest Point algorithm (ICP) and the Kabsch Algorithm. From them one is going to be chosen and a program will be build around it. Following its implementation, the algorithm’s precision is going to be tested. Finally KRL will be briefly introduced and the various problems involving transition of the algorithm from C++ to KRL will be talked about.

Diplomová práce je zaměřena na problematiku detekce a sledování polohy hlavy v obraze jako jednu s možností jak zlepšit možnosti interakce mezi počítačem a člověkem. Hlavním přínosem diplomové práce je využití inovativních hardwarových a softwarových technologií jakými jsou Microsoft Kinect, Point Cloud Library a CImg Library. Na úvod je představeno shrnutí předchozích prací na podobné téma. Následuje charakteristika a popis databáze, která byla vytvořena pro účely diplomové práce. Vyvinutý systém pro detekci a sledování polohy hlavy je založený na akvizici 3D obrazových dat a registračním algoritmu Iterative Closest Point. V závěru diplomové práce je nabídnuto hodnocení vzniklého systému a jsou navrženy možnosti jeho budoucího zlepšení., This thesis is focused on head pose estimation as a possibility to bridge a gap between human and computers. The main contribution of the thesis is usage of a novel hardware and software technology such as Kinect, Point Cloud Library and CImg Library. In the beginning of the thesis overview of prior works in a field of head pose estimation is provided. Own database was created in order to test and evaluate developed algorithm. The head pose estimation and tracking system is based on 3D image data acquisition and Iterative Closest Point registration algorithm. In the end of thesis performance and limitation of the system are described and further improvement is proposed.

Cílem této práce je najít vhodnou metodu pro určení pózy dvou vzájemně pootočených objektů, pokusit se ji implementovat nejprve v jazyce C++ bez použití externích knihoven a následně v jazyce Kuka Robot Language (KRL). V úvodu jsou probrány dva možné způsoby řešení: iterative closest point algoritmus (ICP) a Kabschův algoritmus. Z nich je následně jeden vybrán a je navrhnuta strukturu programu, který bude implementován. Následně se otestuje s jakou přesností tato implementace vybraného algoritmu funguje a jaká skýtá úskalí. Poté je krátce popsán jazyk KRL a je uveden postup migrace algoritmu z C++ a problémy, které se v průběhu vyskytly., The goal of this paper is to find a good method to determine the pose of two, mutually rotated, objects and to try and implement it first in C++ without the usage of any external libraries and then in Kuka Robot Language (KRL). First we are going to look at two different approaches to solving this problem: The Iterative Closest Point algorithm (ICP) and the Kabsch Algorithm. From them one is going to be chosen and a program will be build around it. Following its implementation, the algorithm’s precision is going to be tested. Finally KRL will be briefly introduced and the various problems involving transition of the algorithm from C++ to KRL will be talked about.

Diplomová práce je zaměřena na problematiku detekce a sledování polohy hlavy v obraze jako jednu s možností jak zlepšit možnosti interakce mezi počítačem a člověkem. Hlavním přínosem diplomové práce je využití inovativních hardwarových a softwarových technologií jakými jsou Microsoft Kinect, Point Cloud Library a CImg Library. Na úvod je představeno shrnutí předchozích prací na podobné téma. Následuje charakteristika a popis databáze, která byla vytvořena pro účely diplomové práce. Vyvinutý systém pro detekci a sledování polohy hlavy je založený na akvizici 3D obrazových dat a registračním algoritmu Iterative Closest Point. V závěru diplomové práce je nabídnuto hodnocení vzniklého systému a jsou navrženy možnosti jeho budoucího zlepšení., This thesis is focused on head pose estimation as a possibility to bridge a gap between human and computers. The main contribution of the thesis is usage of a novel hardware and software technology such as Kinect, Point Cloud Library and CImg Library. In the beginning of the thesis overview of prior works in a field of head pose estimation is provided. Own database was created in order to test and evaluate developed algorithm. The head pose estimation and tracking system is based on 3D image data acquisition and Iterative Closest Point registration algorithm. In the end of thesis performance and limitation of the system are described and further improvement is proposed.

Tato práce se zabývá vytvářením 3D map vnitřního prostředí pomocí senzoru Microsoft Kinect. V první části je uveden popis senzoru Microsoft Kinect, metody získávání a zpracování hloubkových dat a jejich následné skládání pomocí různých algoritmů. V druhé části práce je ukázáno použití algoritmu pro skládání prostorových map a výsledné 3D mapy vnitřního prostředí., This work is focused on creating 3D maps of indoor enviroment using Microsoft Kinect sensor. The first part shows the description of Microsoft Kinect sensor, the methods for acquisition and processing of depth data and their registration using different algorithms. The second part shows application of algorithms for map registration and final 3D maps of indoor enviroment.

Tato práce se zabývá vytvářením 3D map vnitřního prostředí pomocí senzoru Microsoft Kinect. V první části je uveden popis senzoru Microsoft Kinect, metody získávání a zpracování hloubkových dat a jejich následné skládání pomocí různých algoritmů. V druhé části práce je ukázáno použití algoritmu pro skládání prostorových map a výsledné 3D mapy vnitřního prostředí., This work is focused on creating 3D maps of indoor enviroment using Microsoft Kinect sensor. The first part shows the description of Microsoft Kinect sensor, the methods for acquisition and processing of depth data and their registration using different algorithms. The second part shows application of algorithms for map registration and final 3D maps of indoor enviroment.

Diplomová práce je zaměřena na problematiku detekce a sledování polohy hlavy v obraze jako jednu s možností jak zlepšit možnosti interakce mezi počítačem a člověkem. Hlavním přínosem diplomové práce je využití inovativních hardwarových a softwarových technologií jakými jsou Microsoft Kinect, Point Cloud Library a CImg Library. Na úvod je představeno shrnutí předchozích prací na podobné téma. Následuje charakteristika a popis databáze, která byla vytvořena pro účely diplomové práce. Vyvinutý systém pro detekci a sledování polohy hlavy je založený na akvizici 3D obrazových dat a registračním algoritmu Iterative Closest Point. V závěru diplomové práce je nabídnuto hodnocení vzniklého systému a jsou navrženy možnosti jeho budoucího zlepšení., This thesis is focused on head pose estimation as a possibility to bridge a gap between human and computers. The main contribution of the thesis is usage of a novel hardware and software technology such as Kinect, Point Cloud Library and CImg Library. In the beginning of the thesis overview of prior works in a field of head pose estimation is provided. Own database was created in order to test and evaluate developed algorithm. The head pose estimation and tracking system is based on 3D image data acquisition and Iterative Closest Point registration algorithm. In the end of thesis performance and limitation of the system are described and further improvement is proposed.

Tato práce se zabývá vytvářením 3D map vnitřního prostředí pomocí senzoru Microsoft Kinect. V první části je uveden popis senzoru Microsoft Kinect, metody získávání a zpracování hloubkových dat a jejich následné skládání pomocí různých algoritmů. V druhé části práce je ukázáno použití algoritmu pro skládání prostorových map a výsledné 3D mapy vnitřního prostředí., This work is focused on creating 3D maps of indoor enviroment using Microsoft Kinect sensor. The first part shows the description of Microsoft Kinect sensor, the methods for acquisition and processing of depth data and their registration using different algorithms. The second part shows application of algorithms for map registration and final 3D maps of indoor enviroment.

Cílem této práce je najít vhodnou metodu pro určení pózy dvou vzájemně pootočených objektů, pokusit se ji implementovat nejprve v jazyce C++ bez použití externích knihoven a následně v jazyce Kuka Robot Language (KRL). V úvodu jsou probrány dva možné způsoby řešení: iterative closest point algoritmus (ICP) a Kabschův algoritmus. Z nich je následně jeden vybrán a je navrhnuta strukturu programu, který bude implementován. Následně se otestuje s jakou přesností tato implementace vybraného algoritmu funguje a jaká skýtá úskalí. Poté je krátce popsán jazyk KRL a je uveden postup migrace algoritmu z C++ a problémy, které se v průběhu vyskytly., The goal of this paper is to find a good method to determine the pose of two, mutually rotated, objects and to try and implement it first in C++ without the usage of any external libraries and then in Kuka Robot Language (KRL). First we are going to look at two different approaches to solving this problem: The Iterative Closest Point algorithm (ICP) and the Kabsch Algorithm. From them one is going to be chosen and a program will be build around it. Following its implementation, the algorithm’s precision is going to be tested. Finally KRL will be briefly introduced and the various problems involving transition of the algorithm from C++ to KRL will be talked about.

Diplomová práce je zaměřena na problematiku detekce a sledování polohy hlavy v obraze jako jednu s možností jak zlepšit možnosti interakce mezi počítačem a člověkem. Hlavním přínosem diplomové práce je využití inovativních hardwarových a softwarových technologií jakými jsou Microsoft Kinect, Point Cloud Library a CImg Library. Na úvod je představeno shrnutí předchozích prací na podobné téma. Následuje charakteristika a popis databáze, která byla vytvořena pro účely diplomové práce. Vyvinutý systém pro detekci a sledování polohy hlavy je založený na akvizici 3D obrazových dat a registračním algoritmu Iterative Closest Point. V závěru diplomové práce je nabídnuto hodnocení vzniklého systému a jsou navrženy možnosti jeho budoucího zlepšení., This thesis is focused on head pose estimation as a possibility to bridge a gap between human and computers. The main contribution of the thesis is usage of a novel hardware and software technology such as Kinect, Point Cloud Library and CImg Library. In the beginning of the thesis overview of prior works in a field of head pose estimation is provided. Own database was created in order to test and evaluate developed algorithm. The head pose estimation and tracking system is based on 3D image data acquisition and Iterative Closest Point registration algorithm. In the end of thesis performance and limitation of the system are described and further improvement is proposed.

Image registration is a research field in which images must be compared and aligned independently of the point of view or camera characteristics. In some applications (such as forensic biometrics, satellite photography or outdoor scene identification) classical image registration systems fail due to one of the images compared represents a tiny piece of the other image. For instance, in forensics palmprint recognition, it is usual to find only a small piece of the palmprint, but in the database, the whole palmprint has been enrolled. The main reason for the poor behaviour of classical image registration methods is the gap between the amounts of salient points of both images, which is related to the number of points to be considered as outliers. Usually, the difficulty of finding a good match increases when the image that represents the tiny part of the scene has been drastically rotated. Again, in the case of palmprint forensics, it is difficult to decide a priori the orientation of the found tiny palmprint image. We present a rotation invariant registration method that explicitly considers that the image to be matched is a small piece of a larger image. We have experimentally validated our method in two different scenarios: palmprint identification and outdoor image registration.

Diplomová práce se zabývá rozšířením Fast Point Feature Histogramů o barevnou informaci za účelem vylepšení registrace mračen bodů. Popisuje proces registrace mračen bodů pomocí Iterative Closest Point, jakou roli v ní plní FPFH a diskutuje, jaké barevné prostory jsou vhodné pro registraci mračen bodů. Pro vyhodnocení přínosu zahrnutí barevné informace práce prezentuje implementaci ICP a FPFH algoritmů v Pythonu a navrhuje metodologii evaluace registrace mračen. Závěr práce je věnován diskuzi výsledků experimentů, které demonstrují, že použití barevné informace v registraci mračen snižuje počet iterací potřebných ke konvergenci ICP., This thesis deals with the extension of Fast Point Feature Histogram with color aiming to improve point cloud registration. The thesis describes point cloud registration using Iterative Closest Point, what is the role of FPFH, and explores available color spaces that are suitable to be used for point cloud registration. In order to evaluate whether adding color information helps to achieve better results in point cloud registration a Python implementation of ICP and FPFH is provided together with a methodology to evaluate registration. The thesis concludes with a discussion of experiments demonstrating that the use of color decreases the number of iterations required for the convergence of ICP.