The diploma thesis deals with the creation of a 3D model using laser scanning by unmanned aircraft (UAV). In the first part the author describes the history, legislation, the possibility of using unmanned aircraft and their dividing. The next section describes the process of creating a 3D model from data collection, using a drone to the actual modeling in Revit and subsequent use of the 3D model.

The aim of this thesis is to design an automated scanning system for components for the purpose of inspecting their dimensions and tolerances. The theoretical introduction provides the reader with basic information on the topic of 3D scanning. The work also includes the design of own scanning system. The greatest attention is paid to the design of a program using the PCL library. The aim of the program is automatic processing of data from a 3D scanner and evaluation of the required dimensions of the scanned component. The final part of the work is devoted to testing the proposed solution.

In the last fifteen years, the use of smartphones has exploded and almost everyone in the Nordic countries owns a smartphone that they use for everyday matters. With the rise of popularity in the usage of smartphones and not least their technical development, the number of applications to use them continues to increase. One area that smartphones can be used for is virtual reality (VR) and as this area has become more popular, the technology behind VR has become more and more sophisticated. Nowadays many smartphones are equipped with multiple cameras and LiDAR sensors that can be used by the device to create a virtual model of the physical environment. In this project, different methods were evaluated to use this virtual model to estimate the size of physical packages to add functionality to the PostNord consumer app for measuring packages when purchasing postage.

The importance of single-tree-based information for forest management and related industries in countries like Sweden, which is covered in approximately 65% by forest, is the motivation for developing algorithms for tree detection and species identification in this study. Most of the previous studies in this field are carried out based on aerial and spectral images and less attention has been paid on detecting trees and identifying their species using laser points and clustering methods. In the first part of this study, two main approaches of clustering (hierarchical and K-means) are compared qualitatively in detecting 3-D ALS points that pertain to individual tree clusters. Further tests are performed on test sites using the supervised k-means algorithm in which the initial clustering points are defined as seed points. These points, which represent the top point of each tree are detected from the cross section analysis of the test area. Comparing those three methods (hierarchical, ordinary K-means and supervised K-means), the supervised K-means approach shows the best result for clustering single tree points. An average accuracy of 90% is achieved in detecting trees. Comparing the result of the thesis algorithms with results from the DPM software, developed by the Visimind Company for analysing LiDAR data, shows more than 85% match in detecting trees. Identification of trees is the second issue of this thesis work. For this analysis, 118 trees are extracted as reference trees with three species of spruce, pine and birch, which are the dominating species in Swedish forests. Totally six methods, including best fitted 3-D shapes (cone, sphere and cylinder) based on least squares method, point density, hull ratio and slope changes of tree outer surface are developed for identifying those species. The methods are applied on all extracted reference trees individually. For aggregating the results of all those methods, a fuzzy logic system is used because of its good reputation in combining fuzzy sets with no distinct boundaries. The best-obtained model from the fuzzy system provides 73%, 87% and 71% accuracies in identifying the birch, spruce and pine trees, respectively. The overall obtained accuracy in species categorization of trees is 77%, and this percentage is increased dealing with only coniferous and deciduous types classification. Classifying spruce and pine as coniferous versus birch as deciduous species, yielded to 84% accuracy.

Företaget Team Exact levererar mätningstekniska tjänster, där den främsta verksamheten är riktad mot byggnads- och markindustrin. Företaget använder UAS och levererar tjänster till kunder med ortofoto och DEM som kan användas till kartläggning, volymberäkningar och planering. Team Exact använder konsultföretagets SkyMap’s webbaserade plattform i fotogrammetrisk bearbetning av UAV genererade flygbilder. DEM behöver uppnå HMK-standardnivå 3 för att användas som underlag till bygghandlingar. För att uppnå HMK-standardnivå 3 så krävs det en lägesosäkerhet på 0,02–0,05 m/ 0,03–0,07 m (plan/höjd). Team Exact uppnår god lägesosäkerhet i plan men har varierande resultat i höjdåtergivningen. Studien har således en målsättning att hitta metoder för att säkerställa höjden inom ett studieområde med varierande topografi, terräng och markytor. Faktorer som ska undersökas är markstödspunkter, RTK-data, flygstråk, kamerainställningar och tänkvärda åtgärder i skiftande topografi samt att se tendenser hur höjdåtergivningen varierar på olika markytor.  Ett stomnät etablerades över studieområdet med tre fastställda koordinatsatta stompunkter, punkterna var inmätta med statisk NRTK mätning under 1 minut. Nätet jämnades ut med totalstation och därefter blev kontrollpunkter, profiler, ytor och markstödspunkter inmätta. Studien utredde lägesosäkerheten med 0, 5, 9 och 12 markstödspunkter. Den UAV som användes i studien är försedd med en RTK-modul och förväntades därav tillhandahålla positioneringsdata som var av värde att utreda. Markstödspunkternas utplacering planerades med fyra konstanta i studieområdets yttrehörn och en femte konstant på studieområdets högsta höjd. Resterande punkter placerades ut i en jämnfördelning över områdets toppar och dalar.  Flygmetoderna som utvärderades var förankrade i tidigare studier. Gemensamma inställningar över samtliga metoder var studieområdets avgränsning, en flyghöjd på 40 m samt flyghastigheten på 3 m/s. Resterande var flytande parametrar som var av värde att utreda. Studien justerade parametrarna gällande flygstråk, övertäckning, kameravinkel och kamerainställningar. Totalt blev det tre flygmetoder där de fyra olika markstödskombinationerna undersöktes vilket gav 12 processer att utvärdera. Utvärderingen utfördes mot 77 kontrollpunkter där RMSE-värde för höjd och plan undersöktes. Kontrollpunkterna var jämnt fördelade över ytan och marktyperna. En ytterligare analys utfördes med volymberäkningar mellan referens terrängmodeller och de genererade terrängmodellerna.  Flygmetod 3 gav bästa resultat där fotogrammetriinställningen Double Grid användes och överlappningen var 80/60 % samt att kameran tiltades till -70°. Sensorkänsligheten var inställd på ISO100, bländaren ett öppningsvärde f/5 och slutartiden var inställd på 1/500s. Studiens resultat visar att flygmetod 3 som blockutjämnats med 12 markstödspunkter genererade bästa resultat på en lägesosäkerhet i plan på 0,015 m samt 0,035 m i höjd. / The company Team Exact delivers measurement technical services, and the main business is aimed at the construction and land industry. The company uses UAS and offers services to customers and delivers products such as orthophotos and DEMs that can be used for mapping, volume calculations and planning. Team Exact uses the consulting company SkyMap’s web-based platform for photogrammetric processing of UAV-generated aerial images. DEM needs to achieve good positional uncertainty, to achieve HMK standard level 3, it is required that the basis for construction documents has a positional uncertainty of 0.02–0.05 m / 0.03–0.07 m (level / height). Team Exact achieves good positional uncertainty in horizontal coordinates but has varying results in height reproduction. The study thus aims to find methods to ensure the height within a study area with varying topography, terrain and ground surfaces. Factors to be investigated are ground control points, RTK data, flight paths, camera settings and conceivable measures in varying topography, as well as seeing trends in how the height representation differs on different ground surfaces. A coordinate network was established over the study area with three established coordinate reference points, the points were measured with static NRTK measurement 1 minute. The network was levelled with the total station and then control points, profiles, surfaces, and ground control points were measured. The study investigated the location uncertainty with 0, 5, 9 and 12 ground control points. The UAV used in the study is equipped with an RTK module and was therefore expected to provide positioning data that was worth investigating. The placement of the ground support points was planned with four constants in the outer corner of the study area and a fifth constant at the highest level of the study area. The remaining points were placed in an even distribution over the area’s peaks and valleys. The evaluated flight methods were rooted in previous studies. Common settings across all methods were the study area delimitation, 40 m flight altitude and the flight speed of 3 m/s. Remaining were floating parameters that were of value to investigate. The study adjusted the parameters regarding flight path, coverage, camera angle and camera settings. In total, there were three flight methods where the four different ground support combinations were examined, which gave 12 processes to evaluate. The evaluation was performed against 77 control points where the RMSE value for height and plane was examined. The control points were evenly distributed over the surface and soil types. A further analysis was performed with volume calculations between the reference terrain models and the generated terrain models. Flight method 3 gave the best results where the photogrammetry setting Double Grid was used and the overlap was 80/60 % and the camera was tilted to -70 °. The sensor sensitivity was set to ISO100, the shutter had an aperture value of f/5 and the shutter speed was set to 1/500s. The results of the study indicate that flight method 3, which was levelled with 12 ground support points, generated the best results on a positional uncertainty in horizontal coordinates of 0,015 m and 0,035 m in height.

No description available.

Inspections of bridges are today performed ocularly by an inspector at arm’s lengths distance to evaluate damages and to assess its current condition. Ocular inspections often require specialized equipment to aid the inspector to reach all parts of the bridge. The current state of practice for bridge inspection is therefore considered to be time-consuming, costly, and a safety hazard for the inspector. The purpose of this thesis has been to develop a method for automated modeling of bridges from point cloud data. Point clouds that have been created through photogrammetry from a collection of images acquired with an Unmanned Aerial Vehicle (UAV). This thesis has been an attempt to contribute to the long-term goal of making bridge inspections more efficient by using UAV technology. Several methods for the identification of structural components in point clouds have been evaluated. Based on this, a method has been developed to identify planar surfaces using the model-fitting method Random Sample Consensus (RANSAC). The developed method consists of a set of algorithms written in the programming language Python. The method utilizes intersection points between planes as well as the k-Nearest-Neighbor (k-NN) concept to identify the vertices of the structural elements. The method has been tested both for simulated point cloud data as well as for real bridges, where the images were acquired with a UAV. The results from the simulated point clouds showed that the vertices were modeled with a mean deviation of 0.13− 0.34 mm compared to the true vertex coordinates. For a point cloud of a rectangular column, the algorithms identified all relevant surfaces and were able to reconstruct it with a deviation of less than 2 % for the width and length. The method was also tested on two point clouds of real bridges. The algorithms were able to identify many of the relevant surfaces, but the complexity of the geometries resulted in inadequately reconstructed models. / Besiktning av broar utförs i dagsläget okulärt av en inspektör som på en armlängds avstånd bedömer skadetillståndet. Okulär besiktning kräver därmed ofta speciell utrustning för att inspektören ska kunna nå samtliga delar av bron. Detta resulterar i att det nuvarande tillvägagångssättet för brobesiktning beaktas som tidkrävande, kostsamt samt riskfyllt för inspektören. Syftet med denna uppsats var att utveckla en metod för att modellera broar på ett automatiserat sätt utifrån punktmolnsdata. Punktmolnen skapades genom fotogrammetri, utifrån en samling bilder tagna med en drönare. Uppsatsen har varit en insats för att bidra till det långsiktiga målet att effektivisera brobesiktning genom drönarteknik. Flera metoder för att identifiera konstruktionselement i punktmoln har undersökts. Baserat på detta har en metod utvecklats som identifierar plana ytor med regressionsmetoden Random Sample Consensus (RANSAC). Den utvecklade metoden består av en samling algoritmer skrivna i programmeringsspråket Python. Metoden grundar sig i att beräkna skärningspunkter mellan plan samt använder konceptet k-Nearest-Neighbor (k-NN) för att identifiera konstruktionselementens hörnpunkter. Metoden har testats på både simulerade punktmolnsdata och på punktmoln av fysiska broar, där bildinsamling har skett med hjälp av en drönare. Resultatet från de simulerade punktmolnen visade att hörnpunkterna kunde identifieras med en medelavvikelse på 0,13 − 0,34 mm jämfört med de faktiska hörnpunkterna. För ett punktmoln av en rektangulär pelare lyckades algoritmerna identifiera alla relevanta ytor och skapa en rekonstruerad modell med en avvikelse på mindre än 2 % med avseende på dess bredd och längd. Metoden testades även på två punktmoln av riktiga broar. Algoritmerna lyckades identifiera många av de relevanta ytorna, men geometriernas komplexitet resulterade i bristfälligt rekonstruerade modeller.

Tidigare vid ombyggnation, försäljning och förvaltning av byggnader som var uppförda innan 80-talet utgick fastighetsägarna från enkla handritade pappersritningar. Det är en svår utmaning att hålla ritningen uppdaterad till verkliga förhållanden d.v.s. relationsritning. För ca 25 år sedan (i början på 80-talet) byttes papper och penna ut mot avancerade ritprogram (CAD) för framtagning av ritningar. Idag används CAD i stort sett för all nyprojektering och de senaste åren har utvecklingen gått mot en större användning av 3D-underlag än tidigare 2D-ritningar. Den stora fördelen med att projektera i 3D är att en virtuell modell skapas av hela byggnaden för att få en bättre kontroll av ingående byggdelsobjekt och även att fel kan upptäckas i tidigare skeden än på byggarbetsplatsen. Genom att börja bygga en virtuell byggnad i 3D från första skedet och succesivt fylla den med mer relevant information i hela livscykeln får man en komplett informationsmodell. Ett av kraven som ställs på fastighetsägarna vid ombyggnation och förvaltning är att tillhandahålla korrekt information och uppdaterade ritningar. Det skall vara enkelt för entreprenören att avläsa ritningarna. I rapporten beskrivs en effektiviserad arbetsprocess, metoder, verktyg och användningsområden för framtagning av 3D-modeller. Detta arbete avser att leda fram till en metodbeskrivning som skall användas för erfarenhetsåterföring. Arbetet skall också vara ett underlag som skall användas för att beskriva tillvägagångsättet att modellera från äldre ritningar till 3D-modeller. Metodbeskrivningen kommer att förenkla förståelsen för modellering för både fastighetsägaren och inom företaget, samt höja kvalitén på arbetet med att skapa CAD-modeller från de olika underlag som används för modellering. / The use of hand drawn construction model was the only way of development, rebuilding, sales and real estate management before the 80’s. However, the challenge was to preserve the drawings and maintain its real condition. To make things work faster and easier the development of advanced drawing software (CAD) was introduced which replaced the traditional hand drawn designs. Today, CAD is used broadly for all new constructions with a great success rate. However, with the new advanced technology many engineers and construction companies are heavily using 3D models over 2D drawings. The major advantage of designing in 3D is a virtual model created of the entire building to get a better control of input construction items and the errors can be detected at earlier stages than at the construction sites. By modifying buildings in a virtual model in three dimensions yet at the first stage and gradually fill it with more relevant information throughout the life cycle of buildings to get a complete information model. One of the requirements from the property owners in the redevelopment and management is to provide accurate information and updated drawings. It should be simple for the contractor to read drawings. This report describes a streamlined work processes, methods, tools and applications for the production of 3D models. This work is intended to lead to a methodology and to be used as well as for passing on experience. This report will also be a base to describe the approach to model from older drawings into 3D models. The method description will simplify the understanding of model for both the property owners and for companies who creates 3D models. It will also increase the quality of the work to create CAD models from the different data used for modeling.

Autonomous driving technology is now evolving at an unprecedented speed. HD maps, which are embedded with highly precise and detailed road spatial and object information, play an important role in supporting autonomous vehicles. This thesis presents the development of a semi-automated HD map creation and updating method that is capable of extracting basic road feature information to HD maps by employing raw MLS point cloud data. The proposed HD map creation method consists of four steps: Road edge extraction, road surface extraction, road marking extraction and driving line generation. First, an existing curb-based road edge detection method is applied to extract road edge candidate points according to the elevation difference and slope between points. This thesis develops an edge vectorization algorithm based on the point's distance-to-trajectory. Then, the road surface is extracted by filtering the points inside fitted edges on the XY plane within a range of the ground elevation. In the next step, instead of using intensity to detect road markings used by most studies, this thesis fuses point clouds and images to assign each point with an RGB value to segment marking points. Marking objects are extracted by conditional Euclidean clustering and classified according to a manually defined decision tree. Finally, driving lines are generated based on the vectorized road edge and lane markings. The HD map update method varies depending on which data source is updated for the road segments, including updating images only, updating point clouds only and updating both images and point clouds. The method is evaluated by six point clouds and image datasets collected from different types of roads. The extracted road edges are assessed by both length- and buffer-based assessment methods. The results indicate that the road edge extraction algorithm performs well in all three dimensions. The road surface extraction results confirm the high accuracy of extracted edges. In addition, the quantitative evaluations of road markings demonstrate that the proposed road marking extraction method achieves an average recall, precision, and F1-score of 94.50%, 81.65% and 87.09%.

<p>High-throughput phenotyping has emerged as a powerful approach to expedite crop breeding programs. Modern remote sensing systems, including manned aircraft, unmanned aerial vehicles (UAVs), and terrestrial platforms equipped with multiple sensors, such as RGB cameras, multispectral, hyperspectral, and infrared thermal sensors, as well as light detection and ranging (LiDAR) scanners are now widely used technologies in advancing high throughput phenotyping. These systems can collect high spatial, spectral, and temporal resolution data on various phenotypic traits, such as plant height, canopy cover, and leaf area. Enhancing the capability of utilizing such remote sensing data for automated phenotyping is crucial in advancing crop breeding. This dissertation focuses on developing deep learning and transfer learning methodologies for crop phenotyping using multi-modality remote sensing and environmental data. The techniques address two main areas: multi-temporal/across-field biomass prediction and multi-scale remote sensing data fusion.</p> <p><br></p> <p>Biomass is a plant characteristic that strongly correlates with biofuel production, but is also influenced by genetic and environmental factors. Previous studies have shown that deep learning-based models are effective in predicting end-of-season biomass for a single year and field. This dissertation includes development of transfer learning methodologies for multiyear,</p> <p>across-field biomass prediction. Feature importance analysis was performed to identify and remove redundant features. The proposed model can incorporate high-dimensional genetic marker data, along with other features representing phenotypic information, environmental conditions, or management practices. It can also predict end-of-season biomass using mid-season remote sensing and environmental data to provide early rankings. The framework was evaluated using experimental trials conducted from 2017 to 2021 at the Agronomy Center for Research and Education (ACRE) at Purdue University. The proposed transfer learning techniques effectively selected the most informative training samples in the target domain, resulting in significant improvements in end-of-season yield prediction and ranking. Furthermore, the importance of input remote sensing features was assessed at different growth stages.</p> <p><br></p> <p>Remote sensing technology enables multi-scale, multi-temporal data acquisition. However, to fully exploit the potential of the acquired data, data fusion techniques that leverage the strengths of different sensors and platforms are necessary. In this dissertation, a generative adversarial network (GAN) based multiscale RGB-guided model and domain adaptation framework were developed to enhance the spatial resolution of multispectral images. The model was trained on limited high spatial resolution images from a wheel-based platform and then applied to low spatial resolution images acquired by UAV and airborne platforms.</p> <p>The strategy was tested in two distinct scenarios, sorghum plant breeding, and urban areas, to evaluate its effectiveness.</p>