In this project, we implement a system for retrieving instances of objects from point clouds using feature based matching techniques. The target dataset of point clouds consists of approximately 80 full scans of office rooms over a period of one month. The raw clouds are reprocessed to remove regions which are unlikely to contain objects. Using locations determined by one of several possible interest point selection methods, one of a number of descriptors is extracted from the processed clouds. Descriptors from a target cloud are compared to those from a query object using a nearest neighbour approach. The nearest neighbours of each descriptor in the query cloud are used to vote for the position of the object in a 3D grid overlaid on the room cloud. We apply clustering in the voting space and rank the clusters according to the number of votes they contain. The centroid of each of the clusters is used to extract a region from the target cloud which, in the ideal case, corresponds to the query object. We perform an experimental evaluation of the system using various parameter settings in order to investigate factors affecting the usability of the system, and the efficacy of the system in retrieving correct objects. In the best case, we retrieve approximately 50% of the matching objects in the dataset. In the worst case, we retrieve only 10%. We find that the best approach is to use a uniform sampling over the room clouds, and to use a descriptor which factors in both colour and shape information to describe points.

Personal variations severely limit the performance of appearance-based gaze tracking. Adapting to these variations using standard neural network model adaptation methods is difficult. The problems range from overfitting, due to small amounts of training data, to underfitting, due to restrictive model architectures. In this thesis, these problems are tackled by introducing the SPatial Adaptive GaZe Estimator (\spaze{}). By modeling personal variations as a low-dimensional latent parameter space, \spaze{} provides just enough adaptability to capture the range of personal variations without being prone to overfitting. Calibrating \spaze{} for a new person reduces to solving a small optimization problem. \spaze{} achieves an error of \ang{2.70} with \num{9} calibration samples on MPIIGaze, improving on the state-of-the-art by \SI{14}{\percent}. In the introductory chapters the history, methods and applications of eye tracking are reviewed, with focus on video-based eye tracking and the use of personal calibration in these methods. Emphasis is placed on methods using neural networks and the strengths and weaknesses of how these methods implement personal calibration. / <p>QC 20210528</p>

No description available.

No description available.

In industrial processes, products are often visually inspected for defects inorder to verify their quality. Many automated visual inspection algorithms exist, and in many cases humans still perform the inspections. Advances in machine learning have showed that deep learning methods lie at the forefront of reliability and accuracy in such inspection tasks. In order to detect defects, most deep learning methods need large amounts of training data to learn from. This makes demonstrating such methods to a new customer problematic, since such data often does not exist beforehand, and has to be gathered specifically for the task. The aim of this thesis is to develop a method to perform such demonstrations. With access to only a small dataset, the method should be able to analyse an image and return a map of binary values, signifying which pixels in the original image belong to a defect and which do not. A method was developed that divides an image into overlapping patches, and analyses each patch individually for defects, using a deep learning method. Three different deep learning methods for classifying the patches were evaluated; a convolutional neural network, a transfer learning model based on the VGG19 network, and an autoencoder. The three methods were first compared in a simple binary classification task, without the patching method. They were then tested together with the patching method on two sets of images. The transfer learning model was able to identify every defect across both tests, having been trained using only four training images, proving that defect detection with deep learning can be done successfully even when there is not much training data available.

Motoriserad trafik är i ständig utveckling samtidigt som nya innovationer inom trafiken gör anspråk på det befintliga vägnätet. Något som studeras noggrant är hur den autonoma fordonsflottan ska kunna integreras in i samhället i samband med att den manuellt manövrerade fordonsflottan avvecklas. Nya möjligheter skapas vid ny teknik och effekten av autonom teknik visar på en förändrad markanvändning jämfört med vad samhället har idag, koncentrerat på centrala delar av städer. Högre precision, mindre säkerhetsrisker och ett effektivare rörelsemönster kan i helhet ge möjligheter till ett mindre behov av ytor avsedda för motoriserade fordon. Examensarbetet syftar på att studera hur markanvändningen i städer påverkas av en eventuell autonom fordonsflotta. En fördjupning sker i nya behov och strukturer som kan komma att uppstå av att en ny teknik integreras i samhället. Slutligen sker det en analys angående vilken automatiseringsgrad som krävs för att nya strukturer och resultat ska uppstå. Studien baseras på en kvalitativ metod där insamlade fakta sker på två sätt. En litteraturstudie som står i grund för majoriteten av den vetenskapliga fakta i studien samt en intervjustudie för att understryka och stärka den information som tagits in. Litteraturstudien genomfördes genom att studera vetenskapliga artiklar och rapporter tagna från hemsidor som Researchgate, Google Scholar och Universitetsbiblioteket LTU. Intervjustudien gjordes i samband med litteraturstudien och efter. Frågeformuläret indelas i 4 olika huvuddelar och antalet frågor under varje huvuddel varierar mellan 2 och 4 med totalt 14 frågor. Huvuddelarna är autonoma fordon in i samhället, autonoma fordons påverkan på mark, autonoma fordons fördelar och nackdelar samt autonoma fordon och parkering. Som avslutande del i studien sker det analyser och slutsatser av den framtagna fakta för att vidare se om forskningen är rimlig. Under senare år har tanken om autonoma fordon i samhället blivit annorlunda och forskningen har förändrats betydligt med ett större fokus på vad som händer härnäst och inte vad som kan ske om autonoma fordon blir verklighet i större skala. Idag sker det mycket forskning kring infrastrukturen och hur den kan integreras med en eventuell autonom fordonsflotta istället för effekterna av en eventuell implementering i större skala i samhället. Trots detta finns det forskning som visar på att yta avsedd för motoriserade fordon frigörs vid en framtida implementering. Mycket pekar speciellt på att parkeringsyta kommer förändras och ge upphov till nya möjligheter för människan, där utformningen av sociala ytor ämnade för människan är att tillgå. Automatiseringsgrader påverkar även hur nya strukturer behöver utformas. SAE-skalan används vid forskning om autonoma fordon och denna studie kommer fokusera på nivå 3 och högre eftersom vägnätet idag präglas av autonoma fordon på nivå 3 och lägre. Större skalor i samället med nivå 3 och högre kan ge upphov till nya resultat och strukturer där fokus ligger på förändringar i vägnätet samt ytor avsedda för just motoriserad trafik. Det lägger grunden till att studien valt denna fokusnivå, mest intressant för framtiden.

Digital image analysis is the field of extracting relevant information from digital images. Recent developments in imaging techniques have made 3-dimensional volume images more common. This has created a need to extend existing 2D image analysis tools to handle images of higher dimensions. Such extensions are usually not straightforward. In many cases, the theoretical and computational complexity of a problem increases dramatically when an extra dimension is added. A fundamental problem in image analysis is image segmentation, i.e., identifying and separating relevant objects and structures in an image. Accurate segmentation is often required for further processing and analysis of the image can be applied. Despite years of active research, general image segmentation is still seen as an unsolved problem. This mainly due to the fact that it is hard to identify objects from image data only. Often, some high-level knowledge about the objects in the image is needed. This high-level knowledge may be provided in different ways. For fully automatic segmentation, the high-level knowledge must be incorporated in the segmentation algorithm itself. In interactive applications, a human user may provide high-level knowledge by guiding the segmentation process in various ways. The aim of the work presented here is to develop segmentation and analysistools for volume images. To limit the scope, the focus has been on two specic capplications of volume image analysis: analysis of volume images of fibrousmaterials and interactive segmentation of medical images. The respective image analysis challenges of these two applications will be discussed. While the work has been focused on these two applications, many of the results presented here are applicable to other image analysis problems.

This thesis introduces a GPU-accelerated algorithm for path planning under kinodynamic constraints, focusing on navigation of flying vehicles within a high-resolution cost map. The algorithm operates by creating dynamically feasible initial paths, and a non-reversible parallel tempering Markov chain Monte Carlo scheme to optimize the paths while adhering to the nonholonomic kinodynamical constraints. The algorithm efficiently generates high quality dynamically feasible paths. An analysis demonstrates the algorithm's robustness, stability and scalability. The approach used for this algorithm is versatile, allowing for straightforward adaptation to different dynamic conditions and cost maps. The algorithm's applicability also extends to various path planning problems, signifying the potential advantages of GPU-accelerated algorithms in the domain of path planning.

MDU, in collaboration with several other universities, plans to join the World Robotic Sailing Championship (WRSC), where in certain sub-challenges some object detection is necessary. Such as for detecting objects such as boats, buoys, and possibly other items. Utilizing a camera system could significantly aid in these tasks, and in this research, an omnidirectional camera is proposed. This is a camera that offers a wide field of view of 360 degrees and could provide comprehensive information about the boat’s surroundings. However, these images use a spherical camera model, which projects the image on a sphere and, when saved to a 2D format, becomes very distorted. To be able to use state-of-the-art vision algorithms for object detection and tracking, this research proposes to project these images to other formats. As such, four systems using object detection and tracking are made that uses different image representation projected from the spherical images. One system uses spherical images and is used as a baseline, while the three remaining systems use some form of projection. The first is cubemap projection, which projects the spherical image to a cube and unfolds this image on a 2D plane. The two other image representations used perspective projections, which are when the spherical image is projected to small sub-images. The two image representations that used perspective projections had 4 and 8 perspective images. None of the systems ultimately performed very well but did have some advantages and disadvantages.

No description available.