O presente trabalho propõe uma metodologia para a elaboração de modelos digitais de elevação e ortofotos, em média e pequena escala, de maneira automática, utilizando correlação de imagens digitais, a partir de fotografias aéreas métricas. Aborda conceitos básicos de Fotogrametria e correlação de imagens digitais, e lança o conceito da janela epipolar como ferramenta auxiliar na busca e correlação. Estas janelas permitem obter a máxima correlação simultânea entre duas ou mais imagens, como também a varredura em qualquer direção. Isso torna bastante robusto o método de elaboração dos produtos propostos. Esta metodologia foi implementada em um caso prático onde se utilizou uma cobertura aerofotogramétrica em escala 1:25.000. Os produtos foram validados, a partir de elementos de referência retirados de outra cobertura em escala 1:5.000. As precisões atenderam os requisitos do PEC Classe A para a escala 1:2.500 em planimetia, e intervalos de curvas de nível de 5 metros de eqüidistância, em altimetria. / This work presents a methodology for the production of digital elevation model and orthophotos on medium and small scales, with an automatic manner, using the concepts of digital image correlation. It presents basic fundamentals of photogrammetry and digital image correlation, and launches the concept of epipolar window like an auxiliary search and correlation tool. These windows allow the simultaneous multiple image correlation, in different direction scanning. This makes quite robust the production method of the proposed products. This methodology was implemented in a practical case, where 1:25.000 scale photogrammetric images were used. The products were validated using a 1:5.000 scale coverage as reference. The accuracy and precision achieved are into the Brazilian Cartography Standards as \"Classe A\" for the 1:2.500 scale, in planimmetry, and 5 meter contour lines interval in altimetry.

This thesis focuses on the analysis of all data sources available for landscape memory interpretation. Amongst those data sources are Lidar, Landsat and orthophoto pictures. According to the analytical outcome the most convenient data source seems to be the Lidar data. Based on their analysis and interpretation an information source for complex land consolidation was elaborated in the form of the forest park proposal.

O presente trabalho propõe uma metodologia para a elaboração de modelos digitais de elevação e ortofotos, em média e pequena escala, de maneira automática, utilizando correlação de imagens digitais, a partir de fotografias aéreas métricas. Aborda conceitos básicos de Fotogrametria e correlação de imagens digitais, e lança o conceito da janela epipolar como ferramenta auxiliar na busca e correlação. Estas janelas permitem obter a máxima correlação simultânea entre duas ou mais imagens, como também a varredura em qualquer direção. Isso torna bastante robusto o método de elaboração dos produtos propostos. Esta metodologia foi implementada em um caso prático onde se utilizou uma cobertura aerofotogramétrica em escala 1:25.000. Os produtos foram validados, a partir de elementos de referência retirados de outra cobertura em escala 1:5.000. As precisões atenderam os requisitos do PEC Classe A para a escala 1:2.500 em planimetia, e intervalos de curvas de nível de 5 metros de eqüidistância, em altimetria. / This work presents a methodology for the production of digital elevation model and orthophotos on medium and small scales, with an automatic manner, using the concepts of digital image correlation. It presents basic fundamentals of photogrammetry and digital image correlation, and launches the concept of epipolar window like an auxiliary search and correlation tool. These windows allow the simultaneous multiple image correlation, in different direction scanning. This makes quite robust the production method of the proposed products. This methodology was implemented in a practical case, where 1:25.000 scale photogrammetric images were used. The products were validated using a 1:5.000 scale coverage as reference. The accuracy and precision achieved are into the Brazilian Cartography Standards as \"Classe A\" for the 1:2.500 scale, in planimmetry, and 5 meter contour lines interval in altimetry.

Att arbeta med flygfoton som är ämnade att bli ortofoton kan innebära en hel del manuellt arbete. Ett ortofoto skapas av flertalet flygfoton som bearbetats av ett bildbehandlingsprogram. Varje ortofoto skapas av ett jobb i ett sådant program. Input till ett jobb är alla bilder som ska vara en del av ortofotot. Detta är inget problem om man bara har foton från en flygning. Har man däremot mängder av flygfoton, från olika områden och tidpunkter måste dessa sorteras så att alla olika jobb senare kan genomföras. Arbetet med att sortera bilder sker idag helt manuellt och behöver inte nödvändigtvis bli rätt alla gånger, speciellt inte om någon annan än den som flugit drönaren ska sortera bilderna. Detta arbete fokuserar på att lösa de manuella stegen i förhanteringen av flygfoton ämnade att bli ortofoton. En sorteringsalgoritm tas fram och en applikation som sorterar bilderna med hjälp av denna algoritm implementeras.

Det har under lång tid odlats frukt i Sverige. Fruktodlingen var länge knuten till herrgårdar och slott. Sedan slutet av 1800-talet började fruktodlingar anläggas i områdena runt Vånga, Kivik och Båstad i Skåne. Det växer fram en ny typ av näring som är mer industriellt präglad än den tidigare herrgårds- och slottsodlingen. Syftet med studien är att undersöka industrifruktodlingsarealens utveckling mellan åren 1926 och 2014 i socknarna Västra Karup vid Båstad och Södra Mellby vid Kivik. Socknarna valdes som undersökningsområden för att de ligger i två fruktodlingsdistrikt i Skåne. Metoden som används är digitalisering av fruktodlingarna i kartmaterialet och beräkning av arealen i GIS-programmet ArcMap.   Fruktodlingsarealen ökade i båda socknarna under första hälften av undersökningsperioden och minskade under den andra. I Västra Karup är arealen minst i slutet av undersökningsperioden och i Södra Mellby i början, arealen var störst i båda socknarna i mitten av perioden. Ökningen beror bland annat på avskärmningen från världsmarknaden under andra världskriget samt ett importstopp på utländsk frukt och minskningen på tullar och ett borttaget importstopp.

The development in photogrammetry has created possibilities for new methods in aerial images acquisition. Remotely-controlled imaging from an unmanned helium zeppelin is a new and relatively unexplored acquisition. The purpose with this degree project is to evaluate the accuracy of this kind of low-height photographing system, a task given from the consultant company WSP, in Sweden. Landbadet in Uddevalla municipality was chosen as a test field for the zeppelin. Seventeen images distributed over three strips were acquired from the flying height of 80 m. The ground control points for the purpose of block adjustment and control points for the purpose of accuracy evaluation were measured with Network RTK. Block adjustment were performed in the software Photomodeler Scanner. Afterwards the control points could be measured photogrammetrically and compared with the reference measurement. The evaluation of the photogrammetric point accuracy was based on the differences between the photogrammetric and the GPS-measured coordinates of the control points in plane and height. The RMS-value of the differences was 0,040 m in plane and 0,056 m in height for the whole block. The difference in the point accuracy was partially affected by the base-height ratio and by the number of images used to determine the point`s coordinates. The conclusion in general is that the system has the possibility to be used for rationalizing the mapping work compared to measurements done with conventional aerial images acquisition methods. However a satisfactorily result is dependent on a well working video link, good base-height ratio and calm wind conditions.

There are a number of studies that deal with detection of road network from image Remote Sensing data. However, little work has been done on algorithms for horizontal road signs detection from Remote Sensing data. On the other hand there are many papers that deal with horizontal road signs detection in the field of Computer vision. Theoretical part of master thesis sumarizes the methods that are used to detect objects from both, Remote Sensing and Computer vision data. In the practical part an algorithm of automatic Zebra-crossing detection based on Aerial Images and vector road layer is designed. Zebra-crossings are detected using matching of image with set of predefined patterns. Obtained set of potential objects is then filtred using geometric and relational criteria. At the end of this thesis, the proposed algorithm is validated and the results are discussed with literature. Key words: Zebra-crossing, Horizontal road signs, Image matching, Aerial images

This thesis deals with the application of unmanned aerial vehicles (UAV) in photogrammetric purposes useful in geodesy. The UAV that was used for imaging is described in the first part, also there are introduced two programs which were used for data processing. A system of mission planning and data collecting is shown on the ortofoto creating as an example. The second part of this thesis deals with testing of the accuracy through terrestrially independently measured points. The main aim of the work is to demonstrate the high potential of UAV devices for geodesy purposes.

This thesis has been written on behalf of Västerås stad with the purpose to test and evaluate methods for automatic classification of land use from orthophotos. Today, only manual classification of land use based on orthophotos is used, which is a time-consuming task. Västerås stad therefore want to find a method to use in the future that is more efficient and provides equal quality. The land use classes used today, and which will also be used for the automatic classification, are: ●      Green area ●      Asphalt ●      Gravel ●      Sand ●      Other hard surfaces ●      Building In the project, two different methods for automatic classification were tested: classification algorithms and deep learning. Deep learning was used to train a model to classify land use from orthophotos according to the previously mentioned classes. The same set of training samples was used for all classification algorithms and for the training of the deep learning model. Accuracy calculations were performed for all classifications. The trained deep learning model achieved an accuracy of 0.843284. The classification algorithms tested were Support Vector Machine, Random Trees, K-Nearest Neighbor, and Maximum Likelihood. These were tested with different sets of input data. The results showed that Support Vector Machine with a normalized Digital Surface Model (nDSM) and Normalized Difference Vegetation Index (NDVI) as supplementary input data to the orthophoto provided the highest accuracy, with an overall accuracy of 0.852886, which is also better than the result from the deep learning model. After the best result was identified, it was generalized to remove small, misclassified segments. After generalization, the overall accuracy increased to 0.882682. The classes gravel and other hard surfaces stood out with particularly low accuracy in all classifications. When comparing the manually performed classification with the automatically created classifications, clear interruptions in the road network are noticeable. This has been identified as being due to trees and vegetation obscuring the ground beneath. This is a problem that seems difficult to solve with current automatic classification methods. / Detta examensarbete har genomförts på uppdrag av Västerås stad med syftet att testa och utvärdera metoder för automatisk klassificering av markanvändning från ortofoton. Idag används endast manuell klassificering av ortofoton, vilket är ett tidskrävande arbete. Västerås stad önskar därför hitta en metod att använda i framtiden som är effektivare men som ger en motsvarande kvalitet. Klasserna som används idag och som ska användas även för den automatiska klassificeringen är: ●      Grönyta ●      Asfalt ●      Grus ●      Sand ●      Övriga hårda ytor ●      Byggnad  I projektet testades två olika metoder för automatisk klassificering: klassificeringsalgoritmer och djupinlärning. Djupinlärning har använts till att träna upp en modell till att klassificera markanvändning från ortofoton enligt de tidigare nämnda klasserna. För alla klassificeringsalgoritmer samt för träningen av djupinlärningsmodellen har samma uppsättning träningsprov använts. Noggrannhetsberäkningar har gjorts för samtliga klassificeringar. Den egentränade djupinlärningsmodellen gav en noggrannhet på 0,843284.  Klassificeringsalgoritmerna som testades var Support Vector Machine, Random Trees, K-Nearest Neighbor och Maximum Likelihood. Dessa har testats med olika uppsättningar av indata. Resultatet visade att Support Vector Machine med en normaliserad digital ytmodell (nDSM) och normaliserat vegetationsindex (NDVI) som kompletterande indata till ortofotot gav den högsta noggrannheten med en övergripande noggrannhet på 0,852886, vilket även är bättre än resultatet från djupinlärningsmodellen. Efter att det bästa resultatet identifierats generaliserades det för att få bort små felklassificerade segment. Efter generaliseringen steg den övergripande noggrannheten till 0,882682.   Klasserna grus och övriga hårda ytor stack ut med särskilt låg noggrannhet i samtliga klassificeringar. Vid jämförelse mellan den klassificering som gjorts manuellt och de klassificeringar som skapats automatiskt märks tydliga avbrott i vägnätet. Detta har identifierats bero på att träd och växtlighet skymmer marken under. Detta är ett problem som tycks svårt att lösa med nuvarande automatiska klassificeringsmetoder.

The main aim of this dissertation is to suggest an application of unmanned aircrafts and to compare them with the currently used methods. In the introductory part the dissertation deals with the history and development of unmanned aircrafts. Further, it presents a theory essential to understand a principle of operation of the proposed methods and its analysis of the currently used methods and procedures. In the final part the dissertation explains a proposal of use of unmanned aircrafts in the industry and compares them with the methods currently used.