No description available.

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.

As datasets grow, the need for automated methods to ensure dataset quality arises. This report presents an experiment conducted on the MSCOCO train2017 dataset to identify image outliers using a force-directed graph built from a co-occurrence context, focusing on the mean average precision and average precision. The experiment involved placing anomaly scores on images using Euclidean distance and k-means clustering, creating subsets where a percentage of images withthe highest anomaly scores were removed. You Only Look Once version 8 models were trained on each subset, and the results showed a promising increase in performance compared to randomlyr emoving images. However, the increase was relatively small, and further research is needed. Interms of future work, other methods of identifying outliers, other datasets, and investigating the uses of contextual information in other areas are discussed.

In recent years, eye-tracking technology has gained considerable attention, facilitating analysis of gaze behavior and human visual attention. However, eye-tracking analysis often requires manual annotation on the objects being gazed upon, making quantitative data analysis a difficult and time-consuming process. This thesis explores the area of object detection and object tracking applied on scene camera footage from mobile eye-tracking glasses. We have evaluated the performance of state-of-the-art object detectors and trackers, resulting in an automated pipeline specialized at detecting and tracking objects in scene videos. Motion blur constitutes a significant challenge in moving cameras, complicating tasks such as object detection and tracking. To address this, we explored two approaches. The first involved retraining object detection models on datasets with augmented motion-blurred images, while the second one involved preprocessing the video frames with deblurring techniques. The findings of our research contributes with insights into efficient approaches to optimally detect and track objects in scene camera footage from eye-tracking glasses. Out of the technologies we tested, we found that motion deblurring using DeblurGAN-v2, along with a DINO object detector combined with the StrongSORT tracker, achieved the highest accuracies. Furthermore, we present an annotated dataset consisting of frames from recordings with eye-tracking glasses, that can be utilized for evaluating object detection and tracking performance.

In this dissertation, image feature extraction quality is enhanced through the introduction of two feature learning techniques and, subsequently, feature-level fusion strategies are presented that improve classification performance. Two image/signal processing techniques are defined for pre-conditioning image data such that the discriminatory information is highlighted for improved feature extraction. The first approach, improved Evolution-COnstructed features, employs a modified genetic algorithm to learn a series of image transforms, specific to a given feature descriptor, for enhanced feature extraction. The second method, Genetic prOgramming Optimal Feature Descriptor (GOOFeD), is a genetic programming-based approach to learning the transformations of the data for feature extraction. GOOFeD offers a very rich and expressive solution space due to is ability to represent highly complex compositions of image transforms through binary, unary, and/or the combination of the two, operators. Regardless of the two techniques employed, the goal of each is to learn a composition of image transforms from training data to present a given feature descriptor with the best opportunity to extract its information for the application at hand. Next, feature-level fusion via multiple kernel learning (MKL) is utilized to better combine the features extracted and, ultimately, improve classification accuracy performance. MKL is advanced through the introduction of six new indices for kernel weight assignment. Five of the indices are measured directly from the kernel matrix proximity values, making them highly efficient to compute. The calculation of the sixth index is performed explicitly on distributions in the reproducing kernel Hilbert space. The proposed techniques are applied to an automatic buried explosive hazard detection application and significant results are achieved.

Machine learning models are becoming popular in the industry since the technology has developed to solve numerous problems, such as classification [1], detection [2], and segmentation [3]. These algorithms require training with a large dataset which includes correct class labels to perform well on unseen data. One way to get access to large sets of annotated data is to use data from simulation engines. However this data is often not as complex and rich as real data, and for images, for examples, there can be a need to make these look more photorealistic. One approach to do this is denoted Domain adaptation. In collaboration with SAAB Aeronautics, which funds this research, this study aims to explore available domain adaptation frameworks, implement a framework and use it to make a transformation from simulation to real- life. A state-of-the-art framework CyCADA was re-implemented from scratch using Python and TensorFlow as a Deep Learning package. The CyCADA implementation was successfully verified by reproducing the digit adaptation result demonstrated in the original paper, making domain adaptations between MNIST, USPS, and SVHN. CyCADA was used to domain adapt landscape images from simulation to real-life. Domain-adapted images were used to train an object detector to evaluate whether CyCADA allows a detector to perform more accurately in real-life data. Statistical measurements, unfortunately, showed that domain-adapted images became less photorealistic with CyCADA, 88.68 FID on domain-adapted images compared to 80.43 FID on simulations, and object detection performed better on real-life data without CyCADA, 0.131 mAP with a detector trained on domain-adapted images compared to 0.681 mAP with simulations. Since CyCADA produced effective domain adaptation results between digits, there remains a possibility to try multiple hyperparameter settings and neural network architecture to produce effective results with landscape images. / Denna studie genomfördes i ett samarbete med SAAB Aeronautics och handlar om att utveckla en Domain Adaptation-modul som förbättrar prestandan av ett nätverk för objektdetektering. När ett objektdetekteringsnätverk är tränat med data från en domän så är det inte givet att samma nätverk presterar bra på en annan domän. Till exempel, ritningar och fotografier av frukter. Forskare löser problemet genom att samla data från varje domän och träna flera maskininlärningsalgoritmer, vilket är en lösning som kräver tid och energi. Detta problem kallas för domänskiftesproblem. Ett hett ämne inom djupinlärning handlar om att lösa just detta problem med domänskift och det finns en rad algoritmer som faller i kategorin Domain Adaptation. Denna studie utvecklar CyCADA som metod att evaluera en toppmodern Domain Adaptation-algoritm. Återimplementering av CyCADA blev lyckad, eftersom flera resultat var återskapade från den originala artikeln. CyCADA producerade effektiva domänskiften på bilder av siffror. CyCADA användes med landskapsbilder från en simulator för att öka verklighetsförankringen på bilderna. Domänskiftade landskapsbilder blev suddiga med CyCADA. FID värdet av domänskiftade bilder, ett utvärderingsmått som evaluerar fotorealism av bilder, blev lägre i jämförelse med endast simulerade bilder. Objektdetekteringsnätverket presterade bättre utan användning av CyCADA. Givet att CyCADA presterade bra i att transformera bilder av siffror från en domän till en annan finns det hopp om att ramverket kan prestera bra med landskapsbilder med fler försök i att ställa in hyperparameterar.

Idag är det vanligt att det sker filmning av evenemang utan att man använder sig av en professionell videofotograf. Det kan vara knatteligans fotbollsmatch, konferensmöten, undervisning eller YouTube-klipp. För att slippa ha en kameraman kan man använda sig av något som kallas för objektföljningskameror. Det är en kamera som kan följa ett objekts position över tid utan att en kameraman styr kameran. I detta examensarbete beskrivs hur objektföljning fungerar, samt görs en jämförelse mellan objektföljningskameror med datorseende och en kameraman. För att kunna jämföra de mot varandra har en prototyp byggts. Prototypen består av en Raspberry Pi 4B med MOSSE som är en objektföljningsalgoritm och SSD300 som är en detekteringsalgoritm inom datorseende. Styrningen består av en gimbal som består av tre borstlösa motorer som styr kameran med en regulator. Resultatet blev en prototyp som klarar av att följa en person som promenerar i maximalt 100 pixlar per sekund eller 1 meter per sekund i helbild, med en maxdistans på 11,4 meter utomhus. Medan en kameraman klarar av att följa en person i 300–800 pixlar per sekund eller 3 meter per sekund. Prototypen är inte lika bra som en ka-meraman men kan användas för att följa en person som undervisar och går långsamt. Under förutsättningen att prototypen är robust vilket inte är fallet. För att få bättre resultat behövs starkare processor och bättre algoritmer än som använts med prototypen. Då ett stort problem var att uppdateringshastigheten var låg för detekteringsalgoritmen. / Today, it is common for events to be filmed without the use of a professional video photographer. It can be the little league football game, conference meetings, teaching or YouTube clips. To film without a cameraman, you can use something called object tracking cameras. It is a camera that can follow an object's position without a cameraman.This thesis describes how object tracking works as well as comparison between ob-ject tracking cameras with computer vision and a cameraman. In order to compare them against each other, a prototype has been developed. The prototype consists of a Raspberry Pi 4B with MOSSE which is an object tracking algorithm and SSD300 which is a detection algorithm in computer vision. The steering consists of a gimbal consisting of three brushless motors that control the camera with a regulator. The result was a prototype capable of following a person walking at a maximum speed 100 pixels per second or 1 meter per second in full screen, with a maximum distance of 11.4 meters outdoors. While a cameraman managed to follow a person at 300-800 pixels per second or 3 meters per second. The prototype is not as good as a cameraman but can be used to follow a person who teaches and walks slowly. Under basis that the prototype is robust, which is not the case. To get better results, stronger processor and better algorithms are needed than used with the prototype. That’s because a big problem was that the refresh rate was low for the detection algorithm.

<p>Climate change is recognized as one of the most significant challenge of the 21st century. Anthropogenic activities have led to a substantial increase in greenhouse gases (GHGs) since the Industrial Revolution, with the energy sector being one the biggest contributors globally. The energy sector is now facing unique challenges not only due to decarbonization goals but also due to increased risks of climate extremes under climate change. </p><p>This dissertation focuses on leveraging machine learning, specifically utilizing unstructured data such as images, to address many of the unprecedented challenges faced by the energy systems. The dissertation begins (Chapter 1) by providing an overview of the risks posed by climate change to modern energy systems. It then explains how machine learning applications can help with addressing these risks. By harnessing the power of machine learning and unstructured data, this research aims to contribute to the development of more resilient and sustainable energy systems, as described briefly below. </p><p>Accurate forecasting of generation is essential for mitigating the risks associated with the increased penetration of intermittent and non-dispatchable variable renewable energy (VRE). In Chapters 2 and 3, deep learning techniques are proposed to predict solar irradiance, a crucial factor in solar energy generation, in order to address the uncertainty inherent in solar energy. Specifically, Chapter 2 introduces a cost-efficient fully exogenous solar irradiance forecasting model that effectively incorporates atmospheric cloud dynamics using satellite imagery. Building upon the work of Chapter 2, Chapter 3 extends the model to a fully probabilistic framework that not only forecasts the future point value of irradiance but also quantifies the uncertainty of the prediction. This is particularly important in the context of energy systems, as it relates to high-risk decision making.</p><p>While the energy system is a major contributor to GHG emissions, it is also vulnerable to climate change risks. Given the essential role of energy systems infrastructure in modern society, ensuring reliable and sustainable operations is of utmost importance. However, our understanding of reliability analysis in electricity transmission networks is limited due to the lack of access to large-scale transmission network topology datasets. Previous research has mostly relied on proxy or synthetic datasets. Chapter 4 addresses this research gap by proposing a novel deep learning-based object detection method that utilizes satellite images to construct a comprehensive large-scale transmission network dataset.</p>

<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>

Multitask Learning (MTL) was conceived as an approach to improve thegeneralization ability of machine learning models. When applied to neu-ral networks, multitask models take advantage of sharing resources forreducing the total inference time, memory footprint and model size. Wepropose MTL as a way to speed up deep learning models for applicationsin which multiple tasks need to be solved simultaneously, which is par-ticularly useful in embedded, real-time systems such as the ones foundin autonomous cars or UAVs.In order to study this approach, we apply MTL to a Computer Vi-sion problem in which both Object Detection and Semantic Segmenta-tion tasks are solved based on the Single Shot Multibox Detector andFully Convolutional Networks with skip connections respectively, usinga ResNet-50 as the base network. We train multitask models for twodifferent datasets, Pascal VOC, which is used to validate the decisionsmade, and a combination of datasets with aerial view images capturedfrom UAVs.Finally, we analyse the challenges that appear during the process of train-ing multitask networks and try to overcome them. However, these hinderthe capacity of our multitask models to reach the performance of the bestsingle-task models trained without the limitations imposed by applyingMTL. Nevertheless, multitask networks benefit from sharing resourcesand are 1.6x faster, lighter and use less memory compared to deployingthe single-task models in parallel, which turns essential when runningthem on a Jetson TX1 SoC as the parallel approach does not fit intomemory. We conclude that MTL has the potential to give superior per-formance as far as the object detection and semantic segmentation tasksare concerned in exchange of a more complex training process that re-quires overcoming challenges not present in the training of single-taskmodels.