Recent developments in the field of object detection have highlighted a significant variation in quality between visual datasets. As a result, there is a need for a standardized approach of validating visual dataset features and their performance contribution. With a focus on vehicle detection, this thesis aims to develop an evaluation method utilized for comparing visual datasets. This method was utilized to determine the dataset that contributed to the detection model with the greatest ability to detect vehicles. The visual datasets compared in this research were BDD100K, KITTI and Udacity, each one being trained on individual models. Applying the developed evaluation method, a strong indication of BDD100K's performance superiority was determined. Further analysis and feature extraction of dataset size, label distribution and average labels per image was conducted. In addition, real-world experimental conduction was performed in order to validate the developed evaluation method. It could be determined that all features and experimental results pointed to BDD100K's superiority over the other datasets, validating the developed evaluation method. Furthermore, the TensorFlow Object Detection API's ability to improve performance gain from a visual dataset was studied. Through the use of augmentations, it was concluded that the TensorFlow Object Detection API serves as a great tool to increase performance gain for visual datasets. / Inom fältet av objektdetektering har ny utveckling demonstrerat stor kvalitetsvariation mellan visuella dataset. Till följd av detta finns det ett behov av standardiserade valideringsmetoder för att jämföra visuella dataset och deras prestationsförmåga. Detta examensarbete har, med ett fokus på fordonsigenkänning, som syfte att utveckla en pålitlig valideringsmetod som kan användas för att jämföra visuella dataset. Denna valideringsmetod användes därefter för att fastställa det dataset som bidrog till systemet med bäst förmåga att detektera fordon. De dataset som användes i denna studien var BDD100K, KITTI och Udacity, som tränades på individuella igenkänningsmodeller. Genom att applicera denna valideringsmetod, fastställdes det att BDD100K var det dataset som bidrog till systemet med bäst presterande igenkänningsförmåga. En analys av dataset storlek, etikettdistribution och genomsnittliga antalet etiketter per bild var även genomförd. Tillsammans med ett experiment som genomfördes för att testa modellerna i verkliga sammanhang, kunde det avgöras att valideringsmetoden stämde överens med de fastställda resultaten. Slutligen studerades TensorFlow Object Detection APIs förmåga att förbättra prestandan som erhålls av ett visuellt dataset. Genom användning av ett modifierat dataset, kunde det fastställas att TensorFlow Object Detection API är ett lämpligt modifieringsverktyg som kan användas för att öka prestandan av ett visuellt dataset.

Logosol AB i Härnösand, Sverige är en sågverkstillverkare som bland annat utvecklar bandsågar och kedjesågverk. Målet med detta examensarbete är att effektivisera kedjesågning i längsgåendesågning genom att justera skärtänderna på sågkedjor. För att åstadkomma detta undersöktes mätningar på sågsnitt där mått togs på hastighet och effekt. Mätningarna utfördes på träslaget gran i två olika tjocklekar där befintliga original sågkedjan jämfördes med modifierade sågkedjor. Utifrån detta identifierades några faktorer som påverkar hastigheten positivt. Faktorerna är att det går fortare att såga på längden med större avstånd mellan skärtänderna på en sågkedja. En betydande ökning av hastigheten vid sågning kan observeras där större avstånd mellan skärtänder visar sig ge bättre resultat vid längsgåendesågning av tjockare stockar. Hastigheten ökar betydligt mer i modifierade sågkedjor jämfört med effektökningen vilket i sin tur ger en minskad energiförbrukning också. Det finns ingen synlig skillnad på snittytans utseende mellan original sågkedjan och modifierade sågkedjor. De lämnar inga ränder efter sig, skapar inga rester från virket på kanten utan går rakt och fint genom hela sågsnittet. / Logosol AB in Härnösand, Sweden is a sawmill manufacturer that develops, among other things, band saws and chainsaw mills. The aim of this thesis project is to enhance the efficiency of chainsaw milling in longitudinal sawing by adjusting the cutting teeth on the saw chains. To accomplish this, measurements were conducted on saw cuts, capturing data on speed and power. The measurements were performed on spruce wood of two different thicknesses, comparing the existing original saw chain with modified saw chains. Based on this, several factors that positively affect speed were identified. It was found that sawing longitudinally is faster with larger distances between the cutting teeth on a saw chain. A significant increase in speed during sawing can be observed where larger distances between the cutting teeth yield better results in longitudinal sawing of thicker logs. The speed increases significantly more in modified saw chains compared to the increase in power, resulting in reduced energy consumption as well. There is no visible difference in the appearance of the cut surface between the original saw chain and modified saw chains. They leave no marks, create no residue from the wood on the edge, but rather cut straight and smoothly through the entire saw cut.

This thesis aims to analyze how object detectors perform under winter weather conditions, specifically in areas with varying degrees of snow cover. The investigation will evaluate the effectiveness of commonly used object detection methods in identifying vehicles in snowy environments, including YOLO v8, Yolo v5, and Faster R-CNN. Additionally, the study explores the method of labeling vehicle objects within a set of image frames for the purpose of high-quality annotations in terms of correctness, details, and consistency. Training data is the cornerstone upon which the development of machine learning is built. Inaccurate or inconsistent annotations can mislead the model, causing it to learn incorrect patterns and features. Data augmentation techniques like rotation, scaling, or color alteration have been applied to enhance some robustness to recognize objects under different alterations. The study aims to contribute to the field of deep learning by providing valuable insights into the challenges of detecting vehicles in snowy conditions and offering suggestions for improving the accuracy and reliability of object detection systems. Furthermore, the investigation will examine edge devices' real-time tracking and detection capabilities when applied to aerial images under these weather conditions. What drives this research is the need to delve deeper into the research gap concerning vehicle detection using drones, especially in adverse weather conditions. It highlights the scarcity of substantial datasets before Mokayed et al. published the Nordic Vehicle Dataset. Using unmanned aerial vehicles(UAVs) or drones to capture real images in different settings and under various snow cover conditions in the Nordic region contributes to expanding the existing dataset, which has previously been restricted to non-snowy weather conditions. In recent years, the leverage of drones to capture real-time data to optimize intelligent transport systems has seen a surge. The potential of drones in providing an aerial perspective efficiently collecting data over large areas to precisely and timely monitor vehicular movement is an area that is imperative to address. To a greater extent, snowy weather conditions can create an environment of limited visibility, significantly complicating data interpretation and object detection. The emphasis is set on edge devices' real-time tracking and detection capabilities, which in this study introduces the integration of edge computing in drone technologies to explore the speed and efficiency of data processing in such systems.

L’extraction d’information dans des documents est une nécessité, particulièrement dans notre ère actuelle où il est commun d’employer un téléphone portable pour photographier des documents ou des factures. On trouve aussi une utilisation répandue de documents PDF qui nécessite de traiter une imposante quantité de documents digitaux. Par leur nature, les données des documents PDF sont complexes à extraire, nécessitant d’être analysés comme des images. Dans cette recherche, on se concentre sur une information particulière à prélever: des tableaux. En effet, les tableaux retrouvés dans les docu- ments représentent une entité significative, car ils contiennent des informations décisives. L’utilisation de modèles neuronaux pour performer des extractions automatiques permet considérablement d’économiser du temps et des efforts. Dans ce mémoire, on définit les métriques, les modèles et les ensembles de données utilisés pour la tâche de détection de tableaux. On se concentre notamment sur l’étude des ensembles de données TableBank et PubLayNet, en soulignant les problèmes d’an- notations présents dans l’ensemble TableBank. On relève que différentes combinaisons d’ensembles d’entraînement avec TableBank et PubLayNet semblent améliorer les perfor- mances du modèle Faster R-CNN, ainsi que des méthodes d’augmentations de données. On compare aussi le modèle de Faster R-CNN avec le modèle CascadeTabNet pour la détection de tableaux où ce premier demeure supérieur. D’autre part, on soulève un enjeu qui est peu discuté dans la tâche de détection d’objets, soit qu’il existe une trop grande quantité de métriques. Cette problématique rend la comparaison de modèles ardue. On génère ainsi les résultats de modèles selon plusieurs métriques afin de démontrer qu’elles conduisent généralement vers différents modèles gagnants, soit le modèle ayant les meilleures performances. On recommande aussi les métriques les plus pertinentes à observer pour la détection de tableaux, c’est-à- dire APmedium/APmedium, Pascal AP85 ou COCO AP85 et la métrique de TableBank. / Extracting information from documents is a necessity, especially in today’s age where it is common to use a cell phone to photograph documents or invoices. There is also the widespread use of PDF documents that requires processing a large amount of digital documents. Due to their nature, the data in PDF documents are complex to retrieve, needing to be analyzed as images. In this research, we focus on a particular information to be extracted: tables. Indeed, the tables found in documents represent a significant entity, as they contain decisive information. The use of neural networks to perform automatic retrieval saves time and effort. In this research, the metrics, models and datasets used for the table detection task are defined. In particular, we focus on the study of the TableBank and PubLayNet datasets, highlighting the problems of annotations present in the TableBank set. We point out that different combinations of training sets using TableBank and PubLayNet appear to improve the performance of the Faster R-CNN model, as well as data augmentation methods. We also compare the Faster R-CNN model with the CascadeTabNet model for table detection where the former remains superior. In addition, we raise an issue that is not often discussed in the object detection task, namely that there are too many metrics. This problem makes model comparison difficult. We therefore generate results from models with several metrics in order to demonstrate the influence of these metrics in defining the best performing model. We also recommend the most relevant metrics to observe for table detection, APmedium/APmedium, Pascal AP85 or COCO AP85 and the TableBank metric.

Supraglacial lakes in the ablation zone of the Greenland Ice Sheet (GrIS) often drain rapidly (in hours to days) by hydraulically-driven fracture (“hydrofracture”) in the summer. Hydrofracture can deliver large meltwater volumes to the ice-bed interface and open-up surface-to-bed connections, thereby routing surface meltwater to the subglacial system, altering basal water pressures and, consequently, the velocity profile of the GrIS. The study of rapidly draining lakes is thus important for developing coupled hydrology and ice-dynamics models, which can help predict the GrIS’s future mass balance. Remote sensing is commonly used to identify the location, timing and magnitude of rapid lake-drainage events for different regions of the GrIS and, with the increased availability of high-quality satellite data, may be able to offer additional insights into the GrIS’s surface hydrology. This study uses new remote-sensing datasets and develops novel analytical techniques to produce improved knowledge of rapidly draining lake behaviour in west Greenland over recent years. While many studies use 250 m MODerate-resolution Imaging Spectroradiometer (MODIS) imagery to monitor intra- and inter-annual changes to lakes on the GrIS, no existing research with MODIS calculates changes to individual and total lake volume using a physically-based method. The first aim of this research is to overcome this shortfall by developing a fully-automated lake area and volume tracking method (“the FAST algorithm”). For this, various methods for automatically calculating lake areas and volumes with MODIS are tested, and the best techniques are incorporated into the FAST algorithm. The FAST algorithm is applied to the land-terminating Paakitsoq and marine-terminating Store Glacier regions of west Greenland to investigate the incidence of rapid lake drainage in summer 2014. The validation and application of the FAST algorithm show that lake areas and volumes (using a physically-based method) can be calculated accurately using MODIS, that the new algorithm can identify rapidly draining lakes reliably, and that it therefore has the potential to be used widely across the GrIS to generate novel insights into rapidly draining lakes. The controls on rapid lake drainage remain unclear, making it difficult to incorporate lake drainage into models of GrIS hydrology. The second aspect of this study therefore investigates whether various hydrological, morphological, glaciological and surface-mass-balance controls can explain the incidence of rapid lake drainage on the GrIS. These potential controlling factors are examined within an Exploratory Data Analysis statistical technique to elicit statistical similarities and differences between the rapidly and non-rapidly draining lake types. The results show that the lake types are statistically indistinguishable for almost all factors, except lake area. It is impossible, therefore, to elicit an empirically-supported, deterministic method for predicting hydrofracture in models of GrIS hydrology. A frequent problem in remote sensing is the need to trade-off high spatial resolution for low temporal resolution, or vice versa. The final element of this thesis overcomes this problem in the context of monitoring lakes on the GrIS by adapting the FAST algorithm (to become “the FASTER algorithm”) to use with a combined Landsat 8 and Sentinel-2 satellite dataset. The FASTER algorithm is applied to a large, predominantly land-terminating region of west Greenland in summers 2016 and 2017 to track changes to lakes, identify rapidly draining lakes, and ascertain the extra quantity of information that can be generated by using the two satellites simultaneously rather than individually. The FASTER algorithm can monitor changes to lakes at both high spatial (10 to 30 m) and temporal (~3 days) resolution, overcoming the limitation of low spatial or temporal resolution associated with previous remote sensing of lakes on the GrIS. The combined dataset identifies many additional rapid lake-drainage events than would be possible with Landsat 8 or Sentinel-2 alone, due to their low temporal resolutions, or with MODIS, due to its inferior spatial resolution.

Aufgrund des Mißerfolges der Mars Observer Mission 1992 und allgemeiner sinkender Raumfahrtetats, entwickelte NASA 1995 die „Faster Better Cheaper“ (FBC) Philosophie. Diese sah vor, daß planetare Missionen innerhalb eines kurzen Zeitraumes und mit begrenzten Budgets geplant, gebaut, getestet und gestartet werden sollten. Dabei sollten neue Technologien und neue Betriebsmethoden zum Einsatz kommen. Mögliche Fehlschläge durch unerprobte Instrumente oder Prozesse wurden dabei nicht ausgeschlossen. Der Mißerfolg der Mars-Missionen im Jahr 1999 und weiterer Projekte zwangen jedoch zu einem Umdenken der „Faster Better Cheaper“ Philosophie. Eine Vielzahl von Abhandlungen und Untersuchungen wurden daraufhin veröffentlicht, die Fehler der FBC Philosophie aufzeigten, ohne dabei jedoch auf mögliche Verbesserungen einzugehen. Das Ziel dieser Arbeit besteht in der Ermittlung effektiver Maßnahmen, so daß Ressourcen während des Lebenszyklus eines Projektes optimal eingesetzt werden können. Aus der Analyse der fehlgeschlagenen Missionen und einer Erläuterung der Funktionen verschiedener planetarer Missionskonzepte, werden mögliche Maßnahmen zur Verringerung der Kosten ermittelt. Die Effektivität dieser Maßnahmen wird anhand eines Bewertungskataloges im Rahmen einer Simulation zu verschiedenen Zeitpunkten einer Mission bestimmt. Es wird dabei eine Handlungshilfe erstellt, mit der ein Projektmanager die Verteilung von Ressourcen optimieren kann. Die Systemtechnik bietet hierzu eine Vielzahl von Analyse- und Simulationsmethoden, mit der die hier gemachten Angaben bewertet und überprüft werden können. / Due to the failure of the Mars Observer Mission in 1992 and decreasing budgets, NASA developed a new philosophy for the development, design and operations called „Faster Better Cheaper“ (FBC). New technologies and new management methods were deployed to reduce lift cycle costs. Possible mission failures were expected. After the losses of the Mars Missions in 1999 and other missions, NASA was forced to rethink its FBC approach. Numerous papers have been published in the meantime which identified the mistakes of the missions and of FBC, but none have identified potential improvements. The objective of this paper is the development of potential measurements for the design of the operations of unmanned space missions that should be applied during its life cycles. A new tool in form of an EXCEL spreadsheet will be developed based on historical missions, which can be used a program manager who can allocate resources in optimal way. Systems Engineering Techniques will be used in various ways to identify problems and to measure potential improvements.

Konceptet automatiserad igenkänning och avläsning av registreringsskyltarhar utvecklats mycket de senaste åren och användningen av Artificiellaneurala nätverk har introducerats i liten skala med lovande resultat. Viundersökte möjligheten att använda detta i ett automatiserat system förgarageportar och implementerade en prototyp för testning. Den traditionellaprocessen för att läsa av en skylt kräver flera steg, i vissa fall upp till fem.Dessa steg ger alla en felmarginal som aggregerat kan leda till över 30% riskför ett misslyckat resultat. I denna uppsats adresseras detta problem och medhjälp av att använda oss utav Artificiella neurala nätverk utvecklades enkortare process med endast två steg för att läsa en skylt, (1) lokaliseraregistreringsskylten (2) läsa karaktärerna på registreringsskylten. Dettaminskar antalet steg till hälften av den traditionella processen samt minskarrisken för fel med 13%. Vi gjorde en Litteraturstudie för att identifiera detlämpligaste neurala nätverket för uppgiften att lokalisera registreringsskyltarmed vår miljös begränsningar samt möjligheter i åtanke. Detta ledde tillanvändandet av Faster R-CNN, en algoritm som använder ett antal artificiellaneurala nätverk. Vi har använt metoden Design och Creation för att skapa enproof of concept prototyp som använder vårt föreslagna tillvägagångssätt föratt bevisa att det är möjligt att implementera detta i en verklig miljö. / The concept of automated recognition and reading of license plates haveevolved a lot the last years and the use of Artificial neural networks have beenintroduced in a small scale with promising results. We looked into thepossibility of using this in an automated garage port system and weimplemented a prototype for testing. The traditional process for reading alicense plate requires multiple steps, sometimes up to five. These steps all givea margin of error which aggregated sometimes leads to over 30% risk forfailure. In this paper we addressed this issue and with the help of a Artificialneural network. We developed a process with only two steps for the entireprocess of reading a license plate, (1) localize license plate (2) read thecharacters on the plate. This reduced the number of steps to half of theprevious number and also reduced the risk for errors with 13%. We performeda Literature Review to find the best suited algorithm for the task oflocalization of the license plate in our specific environment. We found FasterR-CNN, a algorithm which uses multiple artificial neural networks. We usedthe method Design and Creation to implement a proof of concept prototypeusing our approach which proved that this is possible to do in a realenvironment.

Locating and extracting useful data from images is a task that has been revolutionized in the last decade as computing power has risen to such a level to use deep neural networks with success. A type of neural network that uses the convolutional operation called convolutional neural network (CNN) is suited for image related tasks. Using the convolution operation creates opportunities for the network to learn their own filters, that previously had to be hand engineered. For locating objects in an image the state-of-the-art Faster R-CNN model predicts objects in two parts. Firstly, the region proposal network (RPN) extracts regions from the picture where it is likely to find an object. Secondly, a detector verifies the likelihood of an object being in that region.For this thesis, we review the current literature on artificial neural networks, object detection methods, proposal methods and present our new way of generating proposals. By replacing the RPN with our network, the multiscale proposal network (MPN), we increase the average precision (AP) with 12% and reduce the computation time per image by 10%. / Lokalisering av användbar data från bilder är något som har revolutionerats under det senaste decenniet när datorkraften har ökat till en nivå då man kan använda artificiella neurala nätverk i praktiken. En typ av ett neuralt nätverk som använder faltning passar utmärkt till bilder eftersom det ger möjlighet för nätverket att skapa sina egna filter som tidigare skapades för hand. För lokalisering av objekt i bilder används huvudsakligen Faster R-CNN arkitekturen. Den fungerar i två steg, först skapar RPN boxar som innehåller regioner där nätverket tror det är störst sannolikhet att hitta ett objekt. Sedan är det en detektor som verifierar om boxen är på ett objekt .I denna uppsats går vi igenom den nuvarande litteraturen i artificiella neurala nätverk, objektdektektering, förslags metoder och presenterar ett nytt förslag att generera förslag på regioner. Vi visar att genom att byta ut RPN med vår metod (MPN) ökar vi precisionen med 12% och reducerar tiden med 10%.

No description available.

[pt] Eficiência energética e espectral são características importantes para comunicações militares e internet das coisas (IoT). Nesta tese, métodos e sistemas de quantização de 1-bit com modulação de fase contínua (CPM) são estudados e propostos para resolver as necessidades de sistemas de comunicações modernos com baixo consumo energético. Nesse contexto, o método de superamostragem em relação a duração de um símbolo é promissor, pois a informação está contida ao longo da transição de fase de sinais CPM, que não são estritamente limitados em banda. Consequentemente, a perda de taxa alcançável causada pela quantização de 1-bit pode ser reduzida consideravelmente, até mesmo para esquemas com maior ordem de modulação. Este estudo investiga diferentes abordagens para melhorar o desempenho do modelo de sistema proposto. Um esquema de codificação de canal é projetado com mapeamento de bits adaptado ao problema de quantização grosseira, fazendo uso de um soft-in soft-out (SISO) turbo receiver. Formas de onda CPM com duração de símbolo significamente menor que o inverso da banda do sinal são propostas, nomeadas de faster-than-Nyquist CPM. Um fator maior de superamostragem é aplicado com uma estratégia de seleção de amostras em um modelo de amostragem adaptativa. Finalmente, resultados numéricos confirmam melhor desempenho em taxa de erro de bit, eficiência espectral e taxa alcançável para os métodos propostos, em comparação às técnicas recentemente utilizadas. / [en] Energy and spectral efficiency are appealing features for military communications and internet of things (IoT). On this thesis, systems and schemes with 1-bit quantization and continuous phase modulation (CPM) are studied and proposed to address the needs for modern and power efficient communications. In this context, oversampling with respect to the symbol duration is promising because the information is conveyed in the phase transitions of the CPM signals, which are not strictly bandlimited. With this, the loss in achievable rate caused by the coarse quantization can be greatly reduced, even for higher order modulation schemes. This study investigates different approaches to enhancing the performance of the proposed system model. A channel coding scheme is designed with a tailored bit mapping, by means of employing a soft-in soft-out (SISO) turbo receiver. CPM waveforms with symbol durations significantly shorter than the inverse of the signal bandwidth are proposed, termed faster-than-Nyquist CPM. Higher oversampling is applied with a sample selection strategy for a nonuniform adaptive oversampling model. Finally, numerical results confirm better performance on bit error rate, spectral efficiency and achievable rate for the proposed methods in comparison with state of the art techniques.