Anomaly detection is a general theory of detecting unusual patterns or events in data. This master thesis investigates the subject of anomaly detection in two different applications. The first application is product inspection using a camera and the second application is surveillance using a 2D laser scanner. The first part of the thesis presents a system for automatic visual defect inspection. The system is based on aligning the images of the product to a common template and doing pixel-wise comparisons. The system is trained using only images of products that are defined as normal, i.e. non-defective products. The visual properties of the inspected products are modelled using three different methods. The performance of the system and the different methods have been evaluated on four different datasets. The second part of the thesis presents a surveillance system based on a single laser range scanner. The system is able to detect certain anomalous events based on the time, position and velocities of individual objects in the scene. The practical usefulness of the system is made plausible by a qualitative evaluation using unlabelled data.

The usage of a robotic simulator hasprovidedthe advantages of the efficientdevelopment and testing of robotics applications, saving time and resources and making easier publics demonstrations. This thesis project consists on the simulation of a wheel loader at an industrial environment inthe cycle of material handling. For the development of the Project have been used the Robot Operating System (ROS) and Gazebo frameworks which allows to reproduce the 3D map of the work site as well as the robotic wheel loaderand simulate it in a realistic way. The developed softwarealsoprovidesthemechanism to drive the wheel loader throughthereproduced terrain, to controlthe movement of the different articulated joints of the robot, to recompile information of the environmentthroughdifferent sensors (Laser, Odometry, GPS, IMU, etc) and to provide of a waypoint routes to the robot. Furthermore the simulator will be able to reproduce and integrate an asphalt plant modelto the scenario. Allowing an interaction with the wheel loader, this will transport gravel from the piles of the terrain to the pocket of the asphalt plant.

There are situations where you would like to know the size of an object but do not have a ruler nearby. However, it is likely that you are carrying a smartphone that has an integrated digital camera, so imagine if you could snap a photo of the object to get a size estimation. Different methods for finding the dimensions of a cuboid from a photography are evaluated in this project. A simple Android application implementing these methods has also been created. To be able to perform measurements of objects in images we need to know how the scene is reproduced by the camera. This depends on the traits of the camera, called the intrinsic parameters. These parameters are unknown unless a camera calibration is performed, which is a non-trivial task. Because of this eight smartphone cameras, of different models, were calibrated in search of similarities that could give ground for generalisations. To be able to determine the size of the cuboid the scale needs to be known, which is why a reference object is used. In this project a credit card is used as reference, which is placed on top of the cuboid. The four corners of the reference as well as four corners of the cuboid are used to determine the dimensions of the cuboid. Two methods, one dependent and one independent of the intrinsic parameters, are used to find the width and length, i.e. the sizes of the two dimensions that share a plane with the reference. These results are then used in another two methods to find the height of the cuboid. Errors were purposely introduced to the corners to investigate the performance of the different methods. The results show that the different methods perform very well and are all equally suitable for this type of problem. They also show that having correct reference corners is more important than having correct object corners as the results were highly dependent on the accuracy of the reference corners. Another conclusion is that the camera calibration is not necessary because different approximations of the intrinsic parameters can be used instead. / Det finns tillfällen då man undrar över storleken på ett föremål, men inte har något mätinstrument i närheten. Det är dock troligt att du har en smartphone på dig. Smartphones har oftast en integrerad digitalkamera, så tänk om du kunde ta ett foto på föremålet och få en storleksuppskattning. I det här projektet har olika metoder för att beräkna dimensionerna på ett rätblock utvärderats. En enkel Android-applikation som implementerar dessa metoder har också skapats. För att kunna göra mätningar på föremål i bilder måste vi veta hur vyn återskapas av kameran. Detta beror på kamerans egenskaper vilka kallas kameraparametrarna. Dessa parametrar kan man få fram genom att göra en kamerakalibrering, vilket inte är en trivial uppgift. Därför har åtta smartphonekameror, från olika tillverkare, kalibrerats för att se om det finns likheter mellan kamerorna som kan befoga vissa generaliseringar. För att kunna räkna ut storleken på rätblocket måste skalan vara känd och därför används ett referensobjekt. I detta projekt har ett kreditkort använts som referensobjekt. Referensen placeras ovanpå rätblocket och sedan används fyra av referensens hörn samt fyra av rätblockets hörn i beräkningarna. Två metoder, en beroende och en oberoende av kameraparametrarna, har använts för att beräkna längden och bredden, alltså längden på de två sidor som ligger i samma plan som referensobjektet. Detta resultat används sedan i ytterligare två olika metoder för att beräkna höjden på rätblocket. För att undersöka hur de olika metoderna klarade av fel manipulerades hörnen. Resultaten visar att de olika metoderna fungerar bra och är alla lika lämpliga för att lösa den här uppgiften. De visar också på att det är viktigare att referensobjektets hörn är korrekta än rätblockets hörn eftersom referensobjektets hörn hade större inverkan på resultaten. En slutsats som också kan dras är att kameraparametrarna kan approximeras och att kamerakalibrering därför inte nödvändigtvis behöver utföras.

Fog and haze can have a dramatic impact on vision systems for land and sea vehicles. The impact of such conditions on infrared images is not as severe as for standard images. By fusing images from two cameras, one ordinary and one near-infrared camera, a complete dehazing system with colour preservation can be achieved. Applying several different algorithms to an image set and evaluating the results, the most suitable image fusion algoritm has been identified. Using an FPGA, a programmable integrated circuit, a crucial part of the algorithm has been implemented. It is capable of producing processed images 30 times faster than a laptop computer. This implementation lays the foundation of a real-time dehazing system and provides a significant part of the full solution. The results show that such a system can be accomplished with an FPGA.

AASS, or the Center for Applied Autonomous Sensor Systems, is a research environment at Örebro University. This report will touch the development of a robot intended for elderly care in a project called "Project Sputnik". The robot is essentially a manually controlled communication robot that is driven by a pilot from a computer. The robot’s purpose is to provide the option of virtual visits between elders and healthcare professionals or family and friends. The requirements for the robot are numerous and the project itself is far too extensive for one student to complete in a 15 credit course. Therefore, the project was limited to the physical design only. During the pilot-study a large amount of research was done to gain a better understanding of the touched subjects and to prepare for the future development of the project. The project followed the design methodology to gradually develop a conceptual sketch. The concept should form a basis that AASS can continue the development on, and is therefore deliberately crude not to limit AASS in the continued work of Project Sputnik. / AASS, eller Centrum för tillämpade autonoma sensorsystem är en forskningsmiljö på Örebro Universitet. Den här rapporten kommer röra utvecklandet av en robot ämnad åt äldreomsorgen i ett projekt vid namn "Project Sputnik". Roboten är huvudsakligen en kommunikationsrobot som styrs manuellt av en pilot från en hemdator och ska ge en upplevelse av virtuell närvaro. Kraven för roboten är många och projektet i sig är för omfattande för en student att utföra i en kurs på 15 högskolepoäng. Därför begränsades projektet till enbart den fysiska designen. Under förstudien gjordes en stor mängd research för att få en bättre förståelse för berörda områden och förbereda inför kommande processer i projektet. Projektet följde designmetodiken för att gradvis bygga fram en konceptskiss. Konceptskissen ska utgöra en grund som AASS kan utveckla, och är därför medvetet grov för att inte begränsa AASS i det fortsatta arbetet i Project Sputnik.

The purpose of this bachelor thesis was to evaluate and propose a solution for how the material handling of steel rods produced by a metal cutting machine could be automated. The intention of the automation was to meet an increasing demand and to ensure that the quality requirements set are met. These quality requirements are defined by a removal of the small steel edge which occurs on the rod after the cutting process, as well as making sure that the rods meet the specified length tolerances. Initially, a data collection and status analysis of the process was carried out, where problem areas were identified and a requirements specification was formulated. Based on these findings, several solution proposals were generated. The proposed solutions were evaluated and used as a basis on which further development of automation solutions were conducted. During this development, a software simulation environment was used to simulate and evaluate the resulting concepts. Included with these concepts were drawings of necessary constructed equipment, simulation models and cost estimates. The work resulted in two concepts based on the use of industrial robotics. The concept that was considered most suitable for the task is based on an implementation of an ABB IRB 1600 industrial robot with a magnetic gripping tool, a stand-alone station for removing remaining steel edges from the rod, and a measuring arrangement to make sure that the tolerance requirements are met. / Detta examensarbete utfördes med syftet att undersöka om och hur materialhanteringen vid en kallsåg för stålstänger kunde automatiseras. Detta för att hantera en ökad efterfråga och säkerställa att de kvalitetskrav som ställs blir uppfyllda. Kvalitetskrav avser här att kvarvarande grader som uppstår på stängerna vid kapning ska vara borttagna och att stängerna ska uppfylla specificerade längdtoleranser. I arbetet genomfördes inledningsvis en datainsamling och nulägesanalys av processen där problemområden identifierades och en kravspecifikation formulerades. Utifrån dessa genererades sedan flera lösningsförslag. De framställda lösningsförslagen utvärderades och utgjorde sedan en grund för vidareutveckling av automationslösningar. Under vidareutvecklingen användes en robot simuleringsmjukvara för att simulera och utvärdera koncept. Till dessa koncept framställdes tillhörande konstruktioner, simuleringsmodeller och kostnadsuppskattningar. Arbetet resulterade i två koncept för automation baserade på ett användande av industrirobotar. Det koncept som bedömdes som mest lämpat för uppgiften bygger på en implementering av en ABB IRB 1600 industrirobot med ett magnetiskt gripverktyg, en fristående station för avgradning av stänger samt en mätanordning för att kontrollera att toleranskrav uppfylls.

In this thesis, three well known self-supervised methods have been implemented and trained on road scene images. The three so called pretext tasks RotNet, MoCov2, and DeepCluster were used to train a neural network self-supervised. The self-supervised trained networks where then evaluated on different amount of labeled data on two downstream tasks, object detection and semantic segmentation. The performance of the self-supervised methods are compared to networks trained from scratch on the respective downstream task. The results show that it is possible to achieve a performance increase using self-supervision on a dataset containing road scene images only. When only a small amount of labeled data is available, the performance increase can be substantial, e.g., a mIoU from 33 to 39 when training semantic segmentation on 1750 images with a RotNet pre-trained backbone compared to training from scratch. However, it seems that when a large amount of labeled images are available (>70000 images), the self-supervised pretraining does not increase the performance as much or at all.

Generative Adversarial Networks (GANs) have attracted much attention because of their ability to learn high-dimensional, realistic data distributions. In the field of medical imaging, they can be used to augment the often small image sets available. In this way, for example, the training of image classification or segmentation models can be improved to support clinical decision making. GANs can be distinguished according to their input. While Noise-to-Image GANs synthesize new images from a random noise vector, Image-To-Image GANs translate a given image into another domain. In this study, it is investigated if the performance of a Noise-To-Image GAN, defined by its generated output quality and diversity, can be improved by using elements of a previously trained Image-To-Image GAN within its training. The data used consists of paired T1- and T2-weighted MR brain images. With the objective of generating additional T1-weighted images, a hybrid model (Hybrid GAN) is implemented that combines elements of a Deep Convolutional GAN (DCGAN) as a Noise-To-Image GAN and a Pix2Pix as an Image-To-Image GAN. Thereby, starting from the dependency of an input image, the model is gradually converted into a Noise-to-Image GAN. Performance is evaluated by the use of an independent classifier that estimates the divergence between the generative output distribution and the real data distribution. When comparing the Hybrid GAN performance with the DCGAN baseline, no improvement, neither in the quality nor in the diversity of the generated images, could be observed. Consequently, it could not be shown that the performance of a Noise-To-Image GAN is improved by using elements of a previously trained Image-To-Image GAN within its training.

Superpixel segmentation is a preprocessing step for computer vision applications, where an image is split into segments referred to as superpixels. Then running the main algorithm on these superpixels reduces the number of data points processed in comparison to running the algorithm on pixels directly, while still keeping much of the same information. In this thesis, the possibility to run superpixel segmentation on an FPGA is researched. This has resulted in the development of a modified version of the algorithm SLIC, Simple Linear Iterative Clustering. An FPGA implementation of this algorithm has then been built in VHDL, it is designed as a pipeline, unrolling the iterations of SLIC. The designed algorithm shows a lot of potential and runs on real hardware, but more work is required to make the implementation more robust, and remove some visual artefacts.

The aim of this work was to determine whether line-type features(straight lines found in geometry considered interesting by auser) could be identified in spatial map data of indoorenvironments produced by the Microsoft Hololens augmented realityheadset. Five different data sets were used in this work onwhich the feature detection was performed, these data sets wereprovided as sample data representing the spatial map of fivedifferent rooms scanned using the Hololens headset which areavailable as part of the Hololens emulator. Related work onfeature detection in point clouds and 3D meshes were investigatedto try and find a suitable method to achieve line-type featuredetection. The chosen detection method used LSQ-plane fitting andrelevant cutoff variables to achieve this, which was inspired byrelated work on the subject of feature identification and meshsimplification. The method was evaluated using user-placedvalidation features and the distance between them and the detectedfeatures, defined using the midpoint diistance metric was used asa measure of quality for the detected measures. The resultingfeatures were not accurate enough to reliably or consistentlymatch the validation features inserted in the data and furtherimprovements to the detection method would be necessary to achievethis. A local feature-edge detection using the SOD & ESODoperators was considered and tested but was found to not besuitable for the spatial data provided by the Hololens emulator.The results shows that finding these features using the provideddata is possible, and the methods to produce them numerous. Thechoice of mehtod is however dependent on the ultimate applicationof these features, taking into account requirements for accuracyand performance.