Background: Self-driving cars, also known as automated cars are a form of vehicle that can move without a driver or human involvement to control it. They employ numerous pieces of equipment to forecast the car’s navigation, and the car’s path is determined depending on the output of these devices. There are numerous methods available to anticipate the path of self-driving cars. Pedestrian detection is critical for autonomous cars to avoid fatalities and accidents caused by self-driving cars. Objectives: In this research, we focus on the algorithms in machine learning and deep learning to detect pedestrians on the roads. Also, to calculate the most accurate algorithm that can be used in pedestrian detection in automated cars by performing a literature review to select the algorithms. Methods: The methodologies we use are literature review and experimentation, literature review can help us to find efficient algorithms for pedestrian detection in terms of accuracy, computational complexity, etc. After performing the literature review we selected the most efficient algorithms for evaluation and comparison. The second methodology includes experimentation as it evaluates these algorithms under different conditions and scenarios. Through experimentation, we can monitor the different factors that affect the algorithms. Experimentation makes it possible for us to evaluate the algorithms using various metrics such as accuracy and loss which are mainly used to provide a quantitative measure of performance. Results: Based on the literature study, we focused on pedestrian detection deep learning models such as CNN, SSD, and RPN for this thesis project. After evaluating and comparing the algorithms using performance metrics, the outcomes of the experiments demonstrated that RPN was the highest and best-performing algorithm with 95.63% accuracy & loss of 0.0068 followed by SSD with 95.29% accuracy & loss of 0.0142 and CNN with 70.84% accuracy & loss of 0.0622. Conclusions: Among the three deep learning models evaluated for pedestrian identification, the CNN, RPN, and SSD, RPN is the most efficient model with the best performance based on the metrics assessed.

Falls are a major cause of morbidity and mortality in neurological disorders. Technical means of detecting falls are of high interest as they enable rapid notification of caregivers and emergency services. Such approaches must reliably differentiate between normal daily activities and fall events. A promising technique might be based on the classification of movements based on accelerometer signals by machine-learning algorithms, but the generalizability of classifiers trained on laboratory data to real-world datasets is a common issue. Here, three machine-learning algorithms including Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Random Forest (RF) were trained to detect fall events. We used a dataset containing intentional falls (SisFall) to train the classifier and validated the approach on a different dataset which included real-world accidental fall events of elderly people (FARSEEING). The results suggested that the linear SVM was the most suitable classifier in this cross-dataset validation approach and reliably distinguished a fall event from normal everyday activity at an accuracy of 93% and similarly high sensitivity and specificity. Thus, classifiers based on linear SVM might be useful for automatic fall detection in real-world applications.

Background: Cyberbullying involves the use of digital technologies to harass, humiliate, or threaten individuals or groups. This form of bullying can occur on various platforms such as social media, messaging apps, gaming platforms, and mobile phones. With the outbreak of covid-19, there was a drastic increase in utilization of social media. And this upsurge was coupled with cyberbullying, making it a pressing issue that needs to be addressed. Sentiment analysis involves identifying and categorizing emotions and opinions expressed in text data using natural language processing and machine learning techniques. SVM is a machine learning algorithm that has been widely used for sentiment analysis due to its accuracy and efficiency. Objectives: The main objective of this study is to use SVM for sentiment analysis of cyberbullying tweets and evaluate its performance. The study aimed to determine the feasibility of using SVM for sentiment analysis and to assess its accuracy in detecting cyberbullying. Methods: The quantitative research method is used in this thesis, and data is analyzed using statistical analysis. The data set is from Kaggle and includes data about cyberbullying tweets. The collected data is preprocessed and used to train and test an SVM model. The created model will be evaluated on the test set using evaluation accuracy, precision, recall, and F1 score to determine the performance of the SVM model developed to detect cyberbullying. Results: The results showed that SVM is a suitable technique for sentiment analysis of cyberbullying tweets. The model had an accuracy of 82.3% in detecting cyberbullying, with a precision of 0.82, recall of 0.82, and F1-score of 0.83. Conclusions: The study demonstrates the feasibility of using SVM for sentimental analysis of cyberbullying tweets. The high accuracy of the SVM model suggests that it can be used to build automated systems for detecting cyberbullying. The findings highlight the importance of developing tools to detect and address cyberbullying in the online world. The use of sentimental analysis and SVM has the potential to make a significant contribution to the fight against cyberbullying.

The usage of convolutional neural networks (CNNs) has revolutionized the field of computer vision. Though the algorithms used in image recognition have improved significantly in the past decade, they are still limited by the availability of training data. This paper aims to gain a better understanding of how limitations in the training data might affect the performance of the system. A robustness study was conducted. The study utilizes three different image datasets; pre-training CNN models on the ImageNet or CIFAR-10 datasets, and then training on the MAdWeather dataset, whose main characteristic is containing images with differing levels of obscurity in front of the objects in the images. The MAdWeather dataset is used in order to test how accurately a model can identify images that differ from its training dataset. The study shows that CNNs performance on one condition does not translate well to other conditions. / Bildklassificering med hjälp av datorer har revolutionerats genom introduktionen av CNNs. Och även om algoritmerna har förbättrats avsevärt, så är de fortsatt begränsade av tillgänglighet av data. Syftet med detta projekt är att få en bättre förståelse för hur begränsningar i träningsdata kan påverka prestandan för en modell. En studie genomförs för att avgöra hur robust en modell är mot att förutsättningarna, under vilka bilderna tas, förändras. Studien använder sig av tre olika dataset: ImageNet och CIFAR-10, för förträning av modellerna, samt MAdWeather för vidare träning. MAdWeather är speciellt framtaget med bilder där objekten är till olika grad grumlade. MAdWeather datasetet används vidare för att avgöra hur bra en modell är på att klassificera bilder som tagits fram under omständigheter som avviker från träningsdatan. Studien visar att CNNs prestanda på en viss omständighet, inte kan generaliseras till andra omständigheter. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

Object detection is a prominent area of research within computer vision. While object detection based on infrared videos holds great practical significance, the majority of mainstream methods are primarily designed for visible datasets. This thesis investigates the enhancement of object detection accuracy on infrared datasets by leveraging temporal and spatial information. The Memory Enhanced Global-Local Aggregation (MEGA) framework is chosen as a baseline due to its capability to incorporate both forms of information. Based on the initial visualization result from the infrared dataset, CAMEL, the noisy characteristic of the infrared dataset is further explored. Through comprehensive experiments, the impact of temporal and spatial information is examined, revealing that spatial information holds a detrimental effect, while temporal information could be used to improve model performance. Moreover, an innovative Dual Frame Average Aggregation (DFAA) framework is introduced to address challenges related to object overlapping and appearance changes. This framework processes two global frames in parallel and in an organized manner, showing an improvement from the original configuration. / Objektdetektion är ett framträdande forskningsområde inom datorseende. Även om objektdetektering baserad på infraröda videor har stor praktisk betydelse, är majoriteten av vanliga metoder i första hand utformade för synliga datauppsättningar. Denna avhandling undersöker förbättringen av objektdetektionsnoggrannhet på infraröda datauppsättningar genom att utnyttja tids- och rumslig information. Memory Enhanced Global-Local Aggregation (MEGA)-ramverket väljs som baslinje på grund av dess förmåga att införliva båda formerna av information. Baserat på det initiala visualiseringsresultatet från den infraröda datamängden, CAMEL, utforskas den brusiga karaktäristiken för den infraröda datamängden ytterligare. Genom omfattande experiment undersöks effekten av tids- och rumslig information, vilket avslöjar att den rumsliga informationen har en skadlig effekt, medan tidsinformation kan användas för att förbättra modellens prestanda. Dessutom introduceras en innovativ Dual Frame Average Aggregation (DFAA) ramverk för att hantera utmaningar relaterade till objektöverlappning och utseendeförändringar. Detta ramverk bearbetar två globala ramar parallellt och på ett organiserat sätt, vilket visar en förbättring från den ursprungliga konfigurationen.

No description available.

With the rapid development of computers andmodels for machine learning, image recognition has, in recentyears, become widespread in various areas. In this report, imagerecognition is discussed in relation to biometric identificationusing fingerprint images. The aim is to investigate how well abiometric identification model can be trained with an extendeddataset, which resulted from rotating and shifting the images inthe original dataset consisting of very few images. Furthermore,it is investigated how the accuracy of this single-stage modeldiffers from the accuracy of a model with two-stage identification.We chose Random Forest (RF) as the machine learning modeland Scikit default values for the hyperparameters. We furtherincluded five-fold cross-validation in the training process. Theperformance of the trained machine learning model is evaluatedwith testing accuracy and confusion matrices. It was shown thatthe method for extending the dataset was successful. A greaternumber of images gave a greater accuracy in the predictions.Two-stage identification gave approximately the same accuracyas the single-stage method, but both methods would need tobe tested on datasets with images from a greater number ofindividuals before any final conclusions can be drawn. / Tack vare den snabba utvecklingen av datoreroch modeller för maskininlärning har bildigenkänning desenaste åren fått stor spridning i samhället. I denna rapportbehandlas bildigenkänning i relation till biometrisk identifieringi form av fingeravtrycksavläsning. Målet är att undersöka hurväl en modell för biometrisk identifiering kan tränas och testaspå ett dataset med ursprungligen mycket få bilder, om datasettetförst expanderas genom att flertalet kopior av originalbildernaskapas och sedan roteras och förskjuts i olika riktningar.Vidare undersöks hur noggrannheten för denna enstegsmodellskiljer sig jämfört med identifiering i två steg. Vi valdeRandom Forest (RF) som maskininlärningsmodell och Scikitsstandardinställningar för hyperparametrarna. Vidare inkluderadesfemfaldig korsvalidering i träningsprocessen. Prestandanhos den tränade maskininlärningsmodellen bedömdes med hjälpav testnoggrannhet och confusion matriser. Det visades sig attmetoden för att expandera datasettet var framgångsrik. Ettstörre antal bilder gav större noggrannhet i förutsägelserna.Tvåstegsidentifiering gav ungefärligen samma noggrannhet somenstegsidentifiering, men metoderna skulle behöva testas på datamängder med bilder från ett större antal individer innannågra slutgiltiga slutsatser kan dras. / Kandidatexjobb i elektroteknik 2021, KTH, Stockholm

<p dir="ltr">Agricultural applications often require human experts with domain knowledge to ensure compliance and improve productivity, which can be costly and inefficient. To tackle this problem, automated video systems can be implemented for agricultural tasks thanks to the ubiquity of cameras. In this thesis, we focus on designing and implementing video analytics systems for real applications in agriculture by combining both traditional image processing and recent advancements in computer vision. Existing research and available methods have been heavily focused on obtaining the best performance on large-scale benchmarking datasets, while neglecting the applications to real-world problems. Our goal is to bridge the gap between state-of-art methods and real agricultural applications. More specifically, we design video systems for the two tasks of monitoring turkey behavior for turkey welfare and handwashing action recognition for improved food safety. For monitoring turkeys, we implement a turkey detector, a turkey tracker, and a turkey head tracker by combining object detection and multi-object tracking. Furthermore, we detect turkey activities by incorporating motion information. For recognizing handwashing activities, we combine a hand extraction method for focusing on the hand regions with a neural network to build a hand image classifier. In addition, we apply a two-stream network with RGB and hand streams to further improve performance and robustness.</p><p dir="ltr">Besides designing a robust hand classifier, we explore how dataset attributes and distribution shifts can impact system performance. In particular, distribution shifts caused by changes in hand poses and shadow can cause a classifier’s performance to degrade sharply or breakdown beyond a certain point. To better explore the impact of hand poses and shadow and to mitigate the induced breakdown points, we generate synthetic data with desired variations to introduce controlled distribution shift. Experimental results show that the breakdown points are heavily impacted by pose and shadow conditions. In addition, we demonstrate mitigation strategies to significant performance degradation by using selective additional training data and adding synthetic shadow to images. By incorporating domain knowledge and understanding the applications, we can effectively design video analytics systems and apply advanced techniques in agricultural scenarios.</p>

The thesis focuses on modern methods of traffic sign detection and traffic lights detection directly in traffic and with use of back analysis. The main subject is convolutional neural networks (CNN). The solution is using convolutional neural networks of YOLO type. The main goal of this thesis is to achieve the greatest possible optimization of speed and accuracy of models. Examines suitable datasets. A number of datasets are used for training and testing. These are composed of real and synthetic data sets. For training and testing, the data were preprocessed using the Yolo mark tool. The training of the model was carried out at a computer center belonging to the virtual organization MetaCentrum VO. Due to the quantifiable evaluation of the detector quality, a program was created statistically and graphically showing its success with use of ROC curve and evaluation protocol COCO. In this thesis I created a model that achieved a success average rate of up to 81 %. The thesis shows the best choice of threshold across versions, sizes and IoU. Extension for mobile phones in TensorFlow Lite and Flutter have also been created.

An extensive multi-channel seismic dataset acquired between 1970 and 1990 by Oljeprospektering AB (OPAB) has recently been made available by the Geological Survey of Sweden (SGU). This thesis summarizes four papers, which utilize this largely unpublished dataset to improve our understanding of the geology and CO2 storage capacity of the Baltic and Hanö Bay basins in southern Sweden. A range of new processing workflows were developed, which typically provide an improvement in the final stacked seismic image, when compared to the result obtained with the original processing. A method was developed to convert scanned images of seismic sections into SEGY files, which allows large amounts of the OPAB dataset to be imported and interpreted using modern software. A new method for joint imaging of multiples and primaries was developed, which is shown to provide an improvement in signal to noise for some of the seismic lines within the OPAB dataset. For the first time, five interpreted regional seismic profiles detailing the entire sedimentary sequence within these basins, are presented. Depth structure maps detailing the Outer Hanö Bay area and the deeper parts of the Baltic Basin were also generated. Although the overall structure and stratigraphy of the basins inferred from the reprocessed OPAB dataset are consistent with previous studies, some new observations have been made, which improve the understanding of the tectonic history of these basins and provide insight into how the depositional environments have changed throughout time. The effective CO2 storage potential within structural and stratigraphic traps is assessed for the Cambrian Viklau, När and Faludden sandstone reservoirs. A probabilistic methodology is utilized, which allows a robust assessment of the storage capacity as well as the associated uncertainty. The most favourable storage option in the Swedish sector of the Baltic Basin is assessed to be the Faludden stratigraphic trap, which is estimated to have a mid case (P50) storage capacity of 3390 Mt in the deeper part of the basin, where CO2 can be stored in a supercritical phase.