I projektet detekteras och följs granplantor i spatiospektrala bilder för att därefter skapa en hyperspektral datakub för av varje gran. För att detektera granarna prövas fyra metoder: manuell detektion, detektion med segmentering, detektion med SVM och detektion med neuralt nätverk. Minnesanvändning och körningstid jämförs mellan två implementationer, där hyperspektral rekonstruktion görs med olika metoder.

Syftet med studien är att jämföra tre deep learning nätverk med varandra för att ta reda på vilket nätverk som kan producera den högsta uppmätta noggrannheten. Noggrannheten mäts genom att nätverken försöker förutspå antalet personer som vistas i rummet där observation äger rum. Utöver att jämföra de tre djupinlärningsnätverk med varandra, kommer vi även att jämföra dem med en traditionell metoder inom maskininlärning - i syfte för att ta reda på ifall djupinlärningsnätverken presterar bättre än vad traditionella metoder gör. I studien används design and creation. Design and creation är en forskningsmetodologi som lägger stor fokus på att utveckla en IT produkt och använda produkten som dess bidrag till ny kunskap. Metodologin har fem olika faser, vi valde att göra en iterativ process mellan utveckling- och utvärderingfaserna. Observation är den datagenereringsmetod som används i studien för att samla in data. Datagenereringen pågick under tre veckor och under tiden hann 31287 rader data registreras i vår databas. Ett av våra nätverk fick vi en noggrannhet på 78.2%, de andra två nätverken fick en noggrannhet på 45.6% respektive 40.3%. För våra traditionella metoder använde vi ett beslutsträd med två olika formler, de producerade en noggrannhet på 61.3% respektive 57.2%. Resultatet av denna studie visar på att utav de tre djupinlärningsnätverken kan endast en av djupinlärningsnätverken producera en högre noggrannhet än de traditionella maskininlärningsmetoderna. Detta resultatet betyder nödvändigtvis inte att djupinlärningsnätverk i allmänhet kan producera en högre noggrannhet än traditionella maskininlärningsmetoder. Ytterligare arbete som kan göras är följande: ytterligare experiment med datasetet och hyperparameter av djupinlärningsnätverken, samla in mer data och korrekt validera denna data och jämföra fler djupinlärningsnätverk och maskininlärningsmetoder. / The purpose of the study is to compare three deep learning networks with each other to evaluate which network can produce the highest prediction accuracy. Accuracy is measured as the networks try to predict the number of people in the room where observation takes place. In addition to comparing the three deep learning networks with each other, we also compare the networks with a traditional machine learning approach - in order to find out if deep learning methods perform better than traditional methods do. This study uses design and creation. Design and creation is a methodology that places great emphasis on developing an IT product and uses the product as its contribution to new knowledge. The methodology has five different phases; we choose to make an iterative process between the development and evaluation phases. Observation is the data generation method used to collect data. Data generation lasted for three weeks, resulting in 31287 rows of data recorded in our database. One of our deep learning networks produced an accuracy of 78.2% meanwhile, the two other approaches produced an accuracy of 45.6% and 40.3% respectively. For our traditional method decision trees were used, we used two different formulas and they produced an accuracy of 61.3% and 57.2% respectively. The result of this thesis shows that out of the three deep learning networks included in this study, only one deep learning network is able to produce a higher predictive accuracy than the traditional ML approaches. This result does not necessarily mean that deep learning approaches in general, are able to produce a higher predictive accuracy than traditional machine learning approaches. Further work that can be made is the following: further experimentation with the dataset and hyperparameters, gather more data and properly validate this data and compare more and other deep learning and machine learning approaches.

Images are often corrupted by noise which reduces their visual quality and interferes with analysis. Convolutional Neural Networks (CNNs) have become a popular method for denoising images, but their training typically relies on access to thousands of pairs of noisy and clean versions of the same underlying picture. Unsupervised methods lack this requirement and can instead be trained purely using noisy images. This thesis evaluated two different unsupervised denoising algorithms: Noise2Self (N2S) and Parametric Probabilistic Noise2Void (PPN2V), both of which train an internal CNN to denoise images. Four different CNNs were tested in order to investigate how the performance of these algorithms would be affected by different network architectures. The testing used two different datasets: one containing clean images corrupted by synthetic noise, and one containing images damaged by real noise originating from the camera used to capture them. Two of the networks, UNet and a CBAM-augmented UNet resulted in high performance competitive with the strong classical denoisers BM3D and NLM. The other two networks - GRDN and MultiResUNet - on the other hand generally caused poor performance.

When two human beings engage in a conversation, feedback is generally present since it helps in modulating and guiding the conversation for the involved parties. When a robotic agent engages in a conversation with a human, the robot is not capable of understanding the feedback given by the human as other humans would. In this thesis, we model human feedback as a Multivariate Time Series to be classified as positive, negative or neutral. We explore state-of-the-art Deep Learning architectures such as InceptionTime, a Convolutional Neural Network approach, and the Time Series Encoder, a Transformer approach. We demonstrate state-of-the art performance in accuracy, loss and f1-score of such models and improved performance in all metrics when compared to best performing approaches in previous studies such as the Random Forest Classifier. While InceptionTime and the Time Series Encoder reach an accuracy of 85.09% and 84.06% respectively, the Random Forest Classifier stays back with an accuracy of 81.99%. Moreover, InceptionTime reaches an f1-score of 85.07%, the Time Series Encoder of 83.27% and the Random Forest Classifier of 77.61%. In addition to this, we study the data classified by both Deep Learning approaches to outline relevant, redundant and trivial human feedback signals over the whole dataset as well as for the positive, negative and neutral cases. / När två människor konverserar, är feedback (återmatning) en del av samtalet eftersom det hjälper till att styra och leda samtalet för de samtalande parterna. När en robot-agent samtalar med en människa, kan den inte förstå denna feedback på samma sätt som en människa skulle kunna. I den här avhandlingen modelleras människans feedback som en flervariabeltidsserie (Multivariate Time Series) som klassificeras som positiv, negativ eller neutral. Vi utforskar toppmoderna djupinlärningsarkitekturer som InceptionTime, en CNN-metod och Time Series Encoder, som är en Transformer-metod. Vi uppnår hög noggrannhet, F1 och lägre värden på förlustfunktionen jämfört med tidigare högst presterande metoder, som Random Forest-metoder. InceptionTime och Time Series Encoder uppnår en noggrannhet på 85,09% respektive 84,06%, men Random Forest-klassificeraren uppnår endast 81,99%. Dessutom uppnår InceptionTime ett F1 på 85,07%, Time Series Encoder 83,27%, och Random Forest-klassificeraren 77,61. Utöver detta studerar vi data som har klassificerats av båda djupinlärningsmetoderna för att hitta relevanta, redundanta och enklare mänskliga feedback-signaler över hela datamängden, samt för positiva, negativa och neutrala datapunkter.

With more aircraft in the air than ever before, there is a need for automating the surveillance of the airspace. It is widely known that aircraft with different intentions fly in different flight patterns. Support systems for finding different flight patterns are therefore needed. In this thesis, we investigate the possibility of detecting circular flight patterns using deep learning models. The basis for detection is ADS-B data which is continuously transmitted by aircraft containing information related to the aircraft status. Two deep learning models are constructed to solve the binary classification problem of detecting circular flight patterns. The first model is a Long Short-Term Memory (LSTM) model and utilizes techniques such as sliding window and bidirectional LSTM layers to solve the given task. The second model is a Convolutional Neural Network (CNN) and utilizes transfer learning. For the CNN model, the trajectory data is converted into image representations which are fed into a pre-trained model with a custom final dense layer. While ADS-B is openly available, finding specific flight patterns and producing a labeled data set of that pattern is hard and time-consuming. The data set is therefore expanded using other sources of data. Two additional sources of trajectory data are added to the data set; radar and simulated data. Training a model on data of a different distribution than the model is being evaluated on can be problematic and introduces a new source of error known as training-validation mismatch. One of the main goals of this thesis is to be able to quantify the size of this error to decide if using data from other sources is a viable option. The results show that the CNN model outperforms the LSTM model and achieves an accuracy of 98.2%. The results also show that there is a cost, in terms of accuracy, associated with not only training on ADS-B data. For the CNN model that cost was a 1-4% loss in accuracy depending on the training data used. The corresponding cost for the LSTM model was 2-10%.

No description available.

Pest inventory of a field is a way of knowing when the thresholds for pest controlis reached. It is of increasing interest to use machine learning to automate thisprocess, however, many challenges arise with detection of small insects both intraps and on plants.This thesis investigates the prospects of developing an automatic warning system for notifying a user of when certain pests are detected in a trap. For this, sliding window with histogram of oriented gradients based support vector machinewere implemented. Trap detection with neural network models and a check sizefunction were tested for narrowing the detections down to pests of a certain size.The results indicates that with further refinement and more training images thisapproach might hold potential for fungus gnat and rape beetles.Further, this thesis also investigates detection performance of Mask R-CNNand YOLOv5 on different insects in fields for the purpose of automating thedata gathering process. The models showed promise for detection of rape beetles. YOLOv5 also showed promise as a multi-class detector of different insects,where sizes ranged from small rape beetles to larger bumblebees.

<p>Detection of dim point objects plays an important role in many imaging applications such as early warning systems, surveillance, astronomy, and microscopy. In satellite imaging, natural phenomena, such as clouds, can confound object detection methods. We propose an object detection method that uses spatial, spectral, and temporal information to reject detections that are not consistent with a moving object and achieve a high probability of detection with a low false alarm rate. We propose another method for dim object detection using convolutional neural networks (CNN). The method augments a conventional space-based detection processing chain with a lightweight CNN to improve detection performance. For evaluation of the performance of our proposed methods,</p> <p>we used a set of curated satellite images and generated receiver operating characteristics (ROC).</p> <p><br></p> <p>Most satellite images have adequate spatial resolution and signal-to-noise ratio (SNR) for the detection and localization of common large objects, such as buildings. In many applications, the spatial resolution of the imaging system is not enough to localize a point object or two closely-spaced objects (CSOs) that are described by only a few pixels (or less than one pixel). A low signal-to-noise ratio (SNR) increases the difficulty such as when the objects are dim. We describe a method to estimate the objects’ amplitudes and spatial locations with sub-pixel accuracy using non-linear optimization and information from multiple spectral bands. We also propose a machine</p> <p>learning method that minimizes a cost function derived from the maximum likelihood estimation of the observed image to determine an object’s sub-pixel spatial location and amplitude. We derive the Cramer-Rao Lower Bound and compare the proposed estimators’ variance with this bound.</p>

Defects on fiber products have varied appearances and are common in production lines. A reliable system that can classify and identify defects without subjectivity and fatigue can improve a company's quality management. Computer vision systems are crucial for any autonomous system, but accuracy is essential for real-life applications. This study aims to investigate the contribution of computer vision through computer vision and artificial intelligence in detecting defects in formed fiber products. A hand-crafted dataset of four common defects from the production line was created and tested using transfer learning. The system's performance was measured in terms of mean average precision (mAP), precision, and recall, resulting in a performance of 81.8% mAP, 0.84 recall rate, and 0.79 precision rate for the hand-crafted dataset. / Defekter på fiberprodukter har olika framträdanden och är vanliga i produktionslinjer. Ett tillförlitligt system som kan klassificera och identifiera defekter utan subjektivitet och trötthet kan förbättra ett företags kvalitetsledning. Ett datorseende-system är avgörande för alla autonoma system, men noggrannhet är viktigt för tillämpningar i verkliga livet. Denna studie syftar till att undersöka bidraget från datorseende genom datorseende och artificiell intelligens för att upptäcka defekter i formade fiberprodukter. Ett handgjort dataset med fyra vanliga defekter från produktionslinjen skapades och testades med transfer learning. Systemets prestanda mättes i termer av medelvärde av genomsnittlig precision (mAP), precision och återkallelse, vilket resulterade i en prestanda på 81,8% mAP, 0,84 återkallningsfrekvens och 0,79 precision frekvens för det handgjorda datasetet.

No description available.