In modern manufacturing environments, it is essential to be able to react autonomously and dynamically to unpredictable events in an automated manner in order to schedule production in a cost-effective manner. One of the prerequisites for the development of this technology is the progressive integration of cyberphysical systems into industrial sectors. Data generated by the industry constitutes the basis for operative and strategic decision-making in this context. Collecting these data in real time, transforming it if necessary, and analyzing it in order to ensure time-critical decision-making is a major challenge. This paper presents a novel approach that simplifies dynamic scheduling through efficient action selection. YoloRL, the method presented in this paper, which is based on reinforcement learning, which allows for a reduction in the complexity of the training process in a substantial way. For the purpose of identifying promising action sequences, YoloRL does not take into consideration all of the state information of an episode; it only takes into account the initial state. As a result, training complexity is significantly reduced while at the same time robust and adaptive control can be achieved. This study improves the manufacturing system’s performance by minimizing the overall completion time (for any given order). Experimental results indicate that the proposed method results in a faster generalization of the domain knowledge and provides for a powerful policy that is both efficient and reliable in dynamic environments. With YoloRL, overall completion time is reduced by a moderate but quantifiable amount compared with the traditional approach. In accordance with our experimental results, the proposed methodology has the ability to accelerate and stabilize the training process. Thus, a reliable and generalizable policy network is established, which can nevertheless respond dynamically to unforeseen events and changing environmental conditions due to its adaptability. The policy ...

Convolutional Neural Network (CNN) has been established as a powerful toolto automate various computer vision tasks without requiring any aprioriknowledge. Printed Circuit Board (PCB) manufacturers want to improve theirproduct quality by employing vision based automatic optical inspection (AOI)systems at PCB assembly manufacturing. An AOI system employs classiccomputer vision and image processing techniques to detect variousmanufacturing faults in a PCB assembly. Recently, CNN has been usedsuccessfully at various stages of automatic optical inspection. However, nonehas used 2D image of PCB assembly directly as input to a CNN. Currently, allavailable systems are specific to a PCB assembly and require a lot ofpreprocessing steps or a complex illumination system to improve theaccuracy. This master thesis attempts to design an effective soldering faultdetection system using CNN applied on image of a PCB assembly, withRaspberry Pi PCB assembly as the case in point.Soldering faults detection is considered as equivalent of object detectionprocess. YOLO (short for: “You Only Look Once”) is state-of-the-art fast objectdetection CNN. Although, it is designed for object detection in images frompublicly available datasets, we are using YOLO as a benchmark to define theperformance metrics for the proposed CNN. Besides accuracy, theeffectiveness of a trained CNN also depends on memory requirements andinference time. Accuracy of a CNN increases by adding a convolutional layer atthe expense of increased memory requirement and inference time. Theprediction layer of proposed CNN is inspired by the YOLO algorithm while thefeature extraction layer is customized to our application and is a combinationof classical CNN components with residual connection, inception module andbottleneck layer.Experimental results show that state-of-the-art object detection algorithmsare not efficient when used on a new and different dataset for object detection.Our proposed CNN detection algorithm predicts more accurately than YOLOalgorithm with an increase in average precision of 3.0%, is less complexrequiring 50% lesser number of parameters, and infers in half the time takenby YOLO. The experimental results also show that CNN can be an effectivemean of performing AOI (given there is plenty of dataset available for trainingthe CNN). / Convolutional Neural Network (CNN) har etablerats som ett kraftfullt verktygför att automatisera olika datorvisionsuppgifter utan att kräva någon apriorikunskap. Printed Circuit Board (PCB) tillverkare vill förbättra sinproduktkvalitet genom att använda visionbaserade automatiska optiskainspektionssystem (AOI) vid PCB-monteringstillverkning. Ett AOI-systemanvänder klassiska datorvisions- och bildbehandlingstekniker för att upptäckaolika tillverkningsfel i en PCB-enhet. Nyligen har CNN använts framgångsrikti olika stadier av automatisk optisk inspektion. Ingen har dock använt 2D-bildav PCB-enheten direkt som inmatning till ett CNN. För närvarande är allatillgängliga system specifika för en PCB-enhet och kräver mångaförbehandlingssteg eller ett komplext belysningssystem för att förbättranoggrannheten. Detta examensarbete försöker konstruera ett effektivtlödningsfelsdetekteringssystem med hjälp av CNN applicerat på bild av enPCB-enhet, med Raspberry Pi PCB-enhet som fallet.Detektering av lödningsfel anses vara ekvivalent medobjektdetekteringsprocessen. YOLO (förkortning: “Du ser bara en gång”) ärdet senaste snabba objektdetekteringen CNN. Även om det är utformat förobjektdetektering i bilder från offentligt tillgängliga datasätt, använder viYOLO som ett riktmärke för att definiera prestandametriken för detföreslagna CNN. Förutom noggrannhet beror effektiviteten hos en tränadCNN också på minneskrav och slutningstid. En CNNs noggrannhet ökargenom att lägga till ett invändigt lager på bekostnad av ökat minnesbehov ochinferingstid. Förutsägelseskiktet för föreslaget CNN är inspirerat av YOLOalgoritmenmedan funktionsekstraktionsskiktet anpassas efter vår applikationoch är en kombination av klassiska CNN-komponenter med restanslutning,startmodul och flaskhalsskikt.Experimentella resultat visar att modernaste objektdetekteringsalgoritmerinte är effektiva när de används i ett nytt och annorlunda datasätt förobjektdetektering. Vår föreslagna CNN-detekteringsalgoritm förutsäger merexakt än YOLO-algoritmen med en ökning av den genomsnittliga precisionenpå 3,0%, är mindre komplicerad som kräver 50% mindre antal parametraroch lägger ut under halva tiden som YOLO tar. De experimentella resultatenvisar också att CNN kan vara ett effektivt medel för att utföra AOI (med tankepå att det finns gott om datamängder tillgängliga för utbildning av CNN)

This project aims to develop an automated image pre-processing chain to extract valuable information from appliance labels before recycling. The primary goal is to improve optical character recognition accuracy by addressing noise issues using reinforcement learning and an evolutionary algorithm. Python was selected as the primary programming language for this project due to its extensive support for machine learning and computer vision libraries. Different techniques are implemented to enhance text extraction from labels. Binary Robust Invariant Scalable Keypoints (BRISK) are used to straighten labels and separate the label from the background. You Only Look Once version 8x (YOLOv8x) is then used for extracting the regions containing the text of interest. The reinforcement learning model and genetic algorithm dataset are created using BRISK with YOLOv8x. The results showed that pre-processing images in the dataset, provided through BRISK and YOLOv8x, does not affect text extraction accuracy, as suggested by reinforcement learning and evolutionary algorithms. / Detta projekt syftar till att utveckla en automatiserad bildförbehandlingskedja för att extrahera värdefull information från apparatmärken före återvinning. Det primära målet är att förbättra noggrannheten för optisk teckenigenkänning genom att hantera brusproblem med hjälp av förstärkningsinlärning och en evolutionär algoritm. Python valdes som det primära programmeringsspråket för detta projekt på grund av dess omfattande stöd för maskininlärnings- och datorseendebibliotek. Olika tekniker implementeras för att förbättra textutvinningen från etiketterna. Binary Robust Invariant Scalable Keypoints (BRISK) används för att räta ut etiketter och separera etiketten från bakgrunden. You Only Look Once version 8x (YOLOv8x) används sedan för att extrahera områden som innehåller den önskade texten. Datasetet för förstärkningsinlärningsmodellen och den genetiska algoritmen skapas genom att använda BRISK med YOLOv8x. Resultaten visade att förbehandlingen av bilder i datasetet, som tillhandahålls genom BRISK och YOLOv8x, inte påverkar noggrannheten för textutvinning, som föreslagits av förstärkningsinlärning och evolutionära algoritmer.

Hydropower plants create blockages in fish migration routes. Fish ladders can serve as alternative routes but are complex to install and follow up to help adapt and develop them further. In this study, computer vision tools are considered in this regard. More specifically, object detection is applied to images collected in a hydropower plant fish ladder to localise and classify wild, farmed and unknown fish labelled according to the presence, absence or uncertainty of an adipose fin. Fish migration patterns are not deterministic, making it a challenge to collect representative and balanced data to train a model that is resilient to changing conditions. In this study, two data imbalances are addressed by modifying a YOLOv3 baseline model: foreground-foreground class imbalance is targeted using hard and soft resampling and positional imbalance using translation augmentation. YOLOv3 is a convolutional neural network predicting bounding box coordinates, class probabilities and confidence scores simultaneously. It divides images into grids and makes predictions based on grid cell locations and anchor box offsets. Performance is estimated across 10 random data splits and different bounding box overlap thresholds, using (mean) average precision as well as recall, precision and F1 score estimated at optimal validation set confidence thresholds. The Wilcoxon signed-ranks test is used for determining statistical significance. In experiments, the best performance was observed on wild and farmed fish, with F1 scores reaching 94.8 and 89.0 percent respectively. The inconsistent appearance of unknown fish appears harder to generalise to, with a corresponding F1 score of 65.7 percent. Soft sampling but especially translation augmentation contributed to enhanced performance and reduced variance, implying that the baseline model is particularly sensitive to positional imbalance. Spatial dependencies introduced by YOLOv3’s grid cell strategy likely produce local bias or overfitting. An experimental evaluation highlight the importance of not relying on a single data split when evaluating performance on a moderately large or custom dataset. A key challenge observed in experiments is the choice of a suitable confidence threshold, influencing the dynamics of the results. / Vattenkraftverk blockerar fiskars vandringsvägar. Fisktrappor kan skapa alternativa vägar men är komplexa att installera och följa upp för vidare anpassning och utveckling. I denna studie betraktas datorseende i detta avseende. Mer specifikt appliceras objektdetektering på bilder samlade i en fisktrappa i anslutning till ett vattenkraftverk, med målet att lokalisera och klassificera vilda, odlade och okända fiskar baserat på förekomsten, avsaknaden eller osäkerheten av en fett-fena. Fiskars migrationsmönster är inte deterministiska vilket gör det svårt att samla representativ och balanserad data för att trana en modell som kan hantera förändrade förutsättningar. I denna studie addresseras två obalanser i datan genom modifikation av en YOLOv3 baslinjemodell: klass-obalans genom hård och mjuk återanvändning av data och positionell obalans genom translation av bilder innan träning. YOLOv3 är ett convolutional neural network som simultant förutsäger avgränsnings-lådor, klass-sannolikheter och prediktions-säkerhet. Bilder delas upp i rutnätceller och prediktioner görs baserat på cellers position samt modifikation av fördefinierade avgränsningslådor. Resultat beräknas på 10 slumpmässiga uppdelningar av datan och för olika tröskelvärden för avgränsningslådors överlappning. På detta beräknas (mean) average precision, liksom recall, precision och F1 score med tröskelvärden för prediktions-säkerhet beräknat på valideringsdata. Wilcoxon signed-ranks test används för att avgöra statistisk signifikans. Bäst resultat observeras på vilda och odlade fiskar, med F1 scores som når 94.8 respektive 89.0 procent. Okända fiskars inkonsekventa utseenden verkar svårare att generalisera till, med en motsvarande F1 score på 65.7 procent. Mjuk återanvändning av data men speciellt translation bidrar till förbättrad prestanda och minskad varians, vilket pekar på att baslinjemodellen är särskilt känslig för positionell obalans. Spatiala beroenden skapade av YOLOv3s rutnäts-strategi producerar troligen lokal partiskhet eller överträning. I en experimentell utvärdering understryks vikten av multipel uppdelning av datan vid evaluering på ett måttligt stort eller egenskapat dataset. Att välja tröskelvärdet för prediktions-säkerhet anses utmanande och påverkar resultatens dynamik.

Основная цель выпускной квалификационной работы состоит в разработке системы компьютерного зрения для определения вида фракции щебня. А также определении наиболее эффективного метода для определения фракции щебня, сравнивая задачи компьютерного зрения: обнаружение объектов и классификация. Первая часть исследования посвящена анализу существующий методов и алгоритмов классификации изображений на основе нейронных сетей. Были проанализированы модели, предназначенные для обнаружения объектов и классификации. Для задачи классификации изображений сравнение выполнялось для моделей: Resnet, Efficientnet, Deit, Tinyvit. Для задачи обнаружения объектов: Yolo, Faster R-CNN и SSD. Во второй части исследования была обучена модель обнаружения объектов и обучены модели классификации. После произведено сравнение производительности данных моделей для решаемой задачи – определения фракции щебня. Третья часть выпускной квалификационной работы направлена на разработку системы компьютерного зрения для определения фракции щебня. Для работоспособности системы было развернуто два Docker-контейнера и сервер Uvicorn с работающим приложением FastAPI. / The main objective of the final qualification work is to develop a computer vision system for determining the type of crushed stone fraction. As well as determining the most effective method for determining the crushed stone fraction, comparing the tasks of computer vision: object detection and classification. The first part of the study is devoted to the analysis of existing methods and algorithms for image classification based on neural networks. Models designed for object detection and classification were analyzed. For the task of image classification, the comparison was performed for the following models: Resnet, Efficientnet, Deit, Tinyvit. For the task of object detection: Yolo, Faster R-CNN and SSD. In the second part of the study, an object detection model was trained and classification models were trained. After that, a comparison of the performance of these models for the problem being solved - determining the crushed stone fraction was made. The third part of the final qualification work is aimed at developing a computer vision system for determining the crushed stone fraction. For the system to work, two Docker containers and a Uvicorn server with a running FastAPI application were deployed.

Research in the Arctic is of ever growing importance, and modern technology is used in news ways to map and understand this very complex region and how it is effected by climate change. Here, animals and vegetation are tightly coupled with their environment in a fragile ecosystem, and when the environment undergo rapid changes it risks damaging these ecosystems severely.  Understanding what kind of data that has potential to be used in artificial intelligence, can be of importance as many research stations have data archives from decades of work in the Arctic. In this thesis, a YOLOv4 object detection model has been trained on two classes of images to investigate the performance impacts of disturbances in the training data set. An expanded data set was created by augmenting the initial data to contain various disturbances. A model was successfully trained on the augmented data set and a correlation between worse performance and presence of noise was detected, but changes in saturation and altered colour levels seemed to have less impact than expected. Reducing noise in gathered data is seemingly of greater importance than enhancing images with lacking colour levels. Further investigations with a larger and more thoroughly processed data set is required to gain a clearer picture of the impact of the various disturbances.

The study of this research has a challenge of learning data gathering sensor programming and design of electronic sensor circuit. The cost of autonomous vehicle development is expensive compared to purchasing an economy vehicle such as the Hyundai Elantra. Keeping the development cost down is critical to maintaining a competitive edge on vehicle pricing with newer technologies. Autonomous vehicle sensor integration was designed and then tested for the driving vision data-gathering system that requires the system to gather driving vision data utilizing area scan sensors, Lidar, ultrasonic sensor, and camera on real road scenarios. The project utilized sensors such as cheap cost LIDAR, which is that drone is used for on the road testing; other sensors include myRIO (myRIO Hardware), LabVIEW (LabVIEW software), LIDAR-Lite v3 (Garmin, 2019), Ultrasonic sensor, and Wantai stepper motor (Polifka, 2020). This research helps to reduce the price of usage of autonomous vehicle driving systems in the city. Due to resolution and Lidar detecting distance, the test environment is limited to within city areas. Lidar is the most expensive equipment on autonomous vehicle driving data gathering systems. This study focuses on replacing expensive Lidar, ultrasonic sensor, and camera to drone scale low-cost Lidar to real size vehicle. With this study, economic expense autonomous vehicle driving data acquisition is possible. Lowering the price of autonomous vehicle driving data acquisition increases involving new companies on the autonomous vehicle market. Multiple testing with multiple cars is possible. Since multiple testing at the same time is possible, collecting time reduces.

Developing the greenest battery cell and establishing a European supply of batteries is the main goal for Northvolt. To achieve this, the recycling of batteries is a key enabler towards closing the loop and enabling the future of energy.When it comes to the recycling of electric vehicle battery packs, dismantling is one of of the main process steps.Given the size, weight and high voltage of the battery packs, automatic disassembly using robots is the preferred solution. The work presented in this thesis aims to develop and integrate a vision system able to identify and verify the battery pack dismantling process. To achieve this, two cameras were placed in the robot cell and the object detectors You Only Look Once (YOLO) and template matching were implemented, tested and compared. The results show that YOLO is the best object detector out of the ones implemented. The integration of the vision system with the robot controller was also tested and showed that with the results from the vision system, the robot controller can make informed decisions regarding the disassembly.

I detta arbete genomförs utvecklingen av ett realtids objektdetekteringssystem för iOS. För detta ändamål används YOLO, en ett-stegs objektdetekterare och ett s.k. ihoplänkat neuralt nätverk vilket åstadkommer betydligt bättre prestanda än övriga realtidsdetek- terare i termer av hastighet och precision. En dörrdetekterare baserad på YOLO tränas och implementeras i en systemutvecklingsprocess. Maskininlärningsprocessen sammanfat- tas och praxis för att undvika överträning eller “overfitting” samt för att öka precision och hastighet diskuteras och appliceras. Vidare genomförs en rad experiment vilka pekar på att dataaugmentation och inkludering av negativ data i ett dataset medför ökad precision. Hyperparameteroptimisering och kunskapsöverföring pekas även ut som medel för att öka en objektdetekringsmodells prestanda. Författaren lyckas öka modellens mAP, ett sätt att mäta precision för objektdetekterare, från 63.76% till 86.73% utifrån de erfarenheter som dras av experimenten. En modells tendens för överträning utforskas även med resultat som pekar på att träning med över 300 epoker rimligen orsakar en övertränad modell. / This paper features the creation of a real time object detection system for mobile iOS using YOLO, a state-of-the-art one stage object detector and convoluted neural network far surpassing other real time object detectors in speed and accuracy. In this process an object detecting model is trained to detect doors. The machine learning process is outlined and practices to combat overfitting and increasing accuracy and speed are discussed. A series of experiments are conducted, the results of which suggests that data augmentation, including negative data in a dataset, hyperparameter optimisation and transfer learning are viable techniques in improving the performance of an object detection model. The author is able to increase mAP, a measurement of accuracy for object detectors, from 63.76% to 86.73% based on the results of experiments. The tendency for overfitting is also explored and results suggest that training beyond 300 epochs is likely to produce an overfitted model.

This thesis investigates the impact of image enhancement techniques on object detection for carsin real-world traffic scenarios. The study focuses on upscaling and light correction treatments andtheir effects on detecting cars in challenging conditions. Initially, a YOLOv8x model is trained on clear static car images. The model is then evaluated on a test dataset captured in real-world driving with images from a front-mounted camera on a car, incorporating various lighting conditions and challenges. The images are then enhanced with said treatments and then evaluated again. The results in this experiment with its specific context show that upscaling seems to decreasemAP performance while lighting correction slightly improves accuracy. Additional training on acomplex image dataset outperforms all other approaches, highlighting the importance of diverse and realistic training data. These findings contribute to advancing computer vision research for object detection models.