Change search
Refine search result
1 - 10 of 10
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • apa.csl
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Barkman, Richard Dan William
    Karlstad University, Faculty of Health, Science and Technology (starting 2013).
    Object Tracking Achieved by Implementing Predictive Methods with Static Object Detectors Trained on the Single Shot Detector Inception V2 Network2019Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    In this work, the possibility of realising object tracking by implementing predictive methods with static object detectors is explored. The static object detectors are obtained as models trained on a machine learning algorithm, or in other words, a deep neural network. Specifically, it is the single shot detector inception v2 network that will be used to train such models. Predictive methods will be incorporated to the end of improving the obtained models’ precision, i.e. their performance with respect to accuracy. Namely, Lagrangian mechanics will be employed to derived equations of motion for three different scenarios in which the object is to be tracked. These equations of motion will be implemented as predictive methods by discretising and combining them with four different iterative formulae.

    In ch. 1, the fundamentals of supervised machine learning, neural networks, convolutional neural networks as well as the workings of the single shot detector algorithm, approaches to hyperparameter optimisation and other relevant theory is established. This includes derivations of the relevant equations of motion and the iterative formulae with which they were implemented. In ch. 2, the experimental set-up that was utilised during data collection, and the manner by which the acquired data was used to produce training, validation and test datasets is described. This is followed by a description of how the approach of random search was used to train 64 models on 300×300 datasets, and 32 models on 512×512 datasets. Consecutively, these models are evaluated based on their performance with respect to camera-to-object distance and object velocity. In ch. 3, the trained models were verified to possess multi-scale detection capabilities, as is characteristic of models trained on the single shot detector network. While the former is found to be true irrespective of the resolution-setting of the dataset that the model has been trained on, it is found that the performance with respect to varying object velocity is significantly more consistent for the lower resolution models as they operate at a higher detection rate.

    Ch. 3 continues with that the implemented predictive methods are evaluated. This is done by comparing the resulting deviations when they are let to predict the missing data points from a collected detection pattern, with varying sampling percentages. It is found that the best predictive methods are those that make use of the least amount of previous data points. This followed from that the data upon which evaluations were made contained an unreasonable amount of noise, considering that the iterative formulae implemented do not take noise into account. Moreover, the lower resolution models were found to benefit more than those trained on the higher resolution datasets because of the higher detection frequency they can employ.

    In ch. 4, it is argued that the concept of combining predictive methods with static object detectors to the end of obtaining an object tracker is promising. Moreover, the models obtained on the single shot detector network are concluded to be good candidates for such applications. However, the predictive methods studied in this thesis should be replaced with some method that can account for noise, or be extended to be able to account for it. A profound finding is that the single shot detector inception v2 models trained on a low-resolution dataset were found to outperform those trained on a high-resolution dataset in certain regards due to the higher detection rate possible on lower resolution frames. Namely, in performance with respect to object velocity and in that predictive methods performed better on the low-resolution models.

    Download full text (pdf)
    fulltext
  • 2.
    Greenberg, Daniel
    Karlstad University, Faculty of Health, Science and Technology (starting 2013).
    GPU-Based Path Optimization Algorithm in High-Resolution Cost Map with Kinodynamic Constraints: Using Non-Reversible Parallel Tempering2023Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    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.

    Download full text (pdf)
    fulltext
    Download full text (pdf)
    Arkivfil
  • 3.
    Hellner, Simon
    et al.
    Karlstad University, Faculty of Health, Science and Technology (starting 2013), Department of Mathematics and Computer Science (from 2013).
    Syvertsson, Henrik
    Karlstad University, Faculty of Health, Science and Technology (starting 2013), Department of Mathematics and Computer Science (from 2013).
    Neurala nätverk försjälvkörande fordon: Utforskande av olika tillvägagångssätt2021Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Artificial Neural Networks (ANN) have a broad area of application and are growing increasingly relevant, not least in the field of autonomous vehicles. Meta algorithms are used to train networks, which can control a vehicle using several kinds of input data. In this project we have looked at two meta algorithms: genetic algorithm (GA), and gradient descent with backpropagation (GD & BP). We have looked at two types of input to the ANN: distance sensors and line detection. We explain the theory behind the methods we have tried to implement. We did not succeed in using GD & BP to train ANNs to control vehicles, but we describe our attemps. We did however succeeded in using GA to train ANNs using a combination of distance sensors and line detection as input. In summary we managed to train ANNs to control vehicles using two methods of input, and we encountered interesting problems along the way.

    Download full text (pdf)
    fulltext
  • 4.
    Jakobsson, Kenny
    Karlstad University, Faculty of Arts and Social Sciences (starting 2013).
    Är framtiden här?: En undersökning kring AI-konstens relation till kreativitet2023Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    The purpose of the thesis is to investigate and draw attention to current discussions around the use of artificial intelligence to produce images, as well as to examine different ways to perceive the relationship between artificial intelligence and creativity. The thesis’ theoretical framework consists of an account on the historical understanding of the concepts regarding creativity and art, as well as the theories that have dominated the Western world in terms of understanding the internal processes of creativity and art. Six articles published by various newspapers regarding AI-generative art have been examined by use of a modified Toulmin method. The result shows that the authors behind the articles regard AI-generative art to be considered as art and the process to be creative. Their view seems to indicate that the relationship between creativity and artificial intelligence may have several societal and ethical implications that need to be addressed in the future.

    Download full text (pdf)
    fulltext
    Download full text (pdf)
    fulltext
  • 5.
    Khajo, Gabriel
    Karlstad University, Faculty of Health, Science and Technology (starting 2013).
    Region Proposal Based Object Detectors Integrated With an Extended Kalman Filter for a Robust Detect-Tracking Algorithm2019Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    In this thesis we present a detect-tracking algorithm (see figure 3.1) that combines the detection robustness of static region proposal based object detectors, like the faster region convolutional neural network (R-CNN) and the region-based fully convolutional networks (R-FCN) model, with the tracking prediction strength of extended Kalman filters, by using, what we have called, a translating and non-rigid user input region of interest (RoI-) mapping. This so-called RoI-mapping maps a region, which includes the object that one is interested in tracking, to a featureless three-channeled image. The detection part of our proposed algorithm is then performed on the image that includes only the RoI features (see figure 3.2). After the detection step, our model re-maps the RoI features to the original frame, and translates the RoI to the center of the prediction. If no prediction occurs, our proposed model integrates a temporal dependence through a Kalman filter as a predictor; this filter is continuously corrected when detections do occur.

    To train the region proposal based object detectors that we integrate into our detect-tracking model, we used TensorFlow®’s object detection api, with a random search hyperparameter tuning, where we fine-tuned, all models from TensorFlow® slim base network classification checkpoints. The trained region proposal based object detectors used the inception V2 base network for the faster R-CNN model and the R-FCN model, while the inception V3 base network only was applied to the faster R-CNN model. This was made to compare the two base networks and their corresponding affects on the detection models. In addition to the deep learning part of this thesis, for the implementation part of our detect-tracking model, like for the extended Kalman filter, we used Python and OpenCV® . The results show that, with a stationary camera reference frame, our proposed detect-tracking algorithm, combined with region proposal based object detectors on images of size 414 × 740 × 3, can detect and track a small object in real-time, like a tennis ball, moving along a horizontal trajectory with an average velocity v ≈ 50 km/h at a distance d = 25 m, with a combined detect-tracking frequency of about 13 to 14 Hz. The largest measured state error between the actual state and the predicted state from the Kalman filter, at the aforementioned horizontal velocity, have been measured to be a maximum of 10-15 pixels, see table 5.1, but in certain frames where many detections occur this error has been shown to be much smaller (3-5 pixels). Additionally, our combined detect-tracking model has also been shown to be able to handle obstacles and two learnable features that overlap, thanks to the integrated extended Kalman filter. Lastly, our detect-tracking model also was applied on a set of infra-red images, where the goal was to detect and track a moving truck moving along a semi-horizontal path. Our results show that a faster R-CNN inception V2 model was able to extract features from a sequence of infra-red frames, and that our proposed RoI-mapping method worked relatively well at detecting only one truck in a short test-sequence (see figure 5.22).

    Download full text (pdf)
    fulltext
  • 6.
    Larsson, Robin
    Karlstad University, Faculty of Health, Science and Technology (starting 2013), Department of Engineering and Physics (from 2013).
    A GPU Implementation of Kinodynamic Path Planning in Large Continuous Costmap Environments: Using Dijkstra's Algorithm and Simulated Annealing2023Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Path planning that takes kinodynamic constraints into account is a crucial part of critical missions where autonomous vehicles must function independently without communication from an operator as this ensures that the vehicle will be able to follow the planned path. In this thesis, an algorithm is presented that can plan kinodynamically feasible paths through large scale continuous costmap environments for different constraints on the maximum allowed acceleration and jerk along the path. The algorithm begins by taking a small stochastic sample of the costmap, with a higher probability to keep more information from the cheaper, interesting areas of the map. This random sample is turned into a graph to which Dijkstra's algorithm is applied in order to obtain an initial guess of a path. Simulated annealing is then used to first smooth this initial guess to obey the kinodynamic constraints and then optimize the path with respect to cost while keeping the kinodynamics below the set limits. The majority of the simulated annealing iterations utilize a GPU to significantly reduce the computational time needed.

    The performance of the algorithm was evaluated by studying the paths generated from a large number of different start and end points in a complex continuous costmap with a high resolution of 2551×2216 pixels. To evaluate the robustness of the algorithm a large number of paths were generated, both with the same and with different start and end points, and the paths were inspected both visually, and the spread of the cost of the different paths was studied. 

    It was concluded that the algorithm is able to generate paths of high quality for different limits on the allowed acceleration and jerk as well as achieving a low spread in cost when generating multiple paths between the same pair of points. The utilization of a GPU to improve computational performance proved successful as the GPU executed between 2.4 and 2.8 times more simulated annealing iterations in a given time compared to the CPU. This result hopefully inspires future work to utilize GPUs to improve computational performance, even in problems that traditionally are solved using sequential algorithms.

    Download full text (pdf)
    fulltext
    Download full text (pdf)
    Arkivfil
  • 7.
    Lokkin, Caj
    et al.
    Karlstad University, Faculty of Health, Science and Technology (starting 2013), Department of Mathematics and Computer Science (from 2013).
    Bragd, Sebastian
    Karlstad University, Faculty of Health, Science and Technology (starting 2013), Department of Mathematics and Computer Science (from 2013).
    Öppen källkodslösning för datorseende: Skapande av testmiljö och utvärdering av OpenCV2021Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Computer vision is a subject in computer science that have evolved over many years and the functionality is more accessible then ever.

    Among other things, it can be used for non-contact measurement to locate, verify, and detect defects of objects.

    The question is if it is possible to create an open source solution for computer vision equivalent to a closed source solution. In other words, can a company using a closed source commercial program instead use a free open source code library and produce equivalent results? 

    In this report we describe the design of a prototype that uses the open source library for computer vision, OpenCV. 

    In order to evaluate our prototype, we let it identify block in a tower on image in a series of test cases. 

    We compare the results from the prototype with the results obtained with a commercial solution, created with the program ''Vision Builder for Automated Inspection''. 

    Results from the cases tested show that OpenCV seems to have performance and functionality equivalent to the commercial solution but has some limitations. 

    As OpenCV's focus is on programmatic development of computer vision solutions, the result is dependent on the user's skills in programming and program design. 

    Based on the tests that we have performed, we believe that OpenCV can replace a licensed commerical program, but the license cost may come to be replaced by other development costs.

    Download full text (pdf)
    fulltext
  • 8.
    Mørk, Cato
    et al.
    Rikshospitalet University Hospital.
    Salerud, E Göran
    Linköpings universitet.
    Asker, Claes L
    Karlstad University.
    Kvernebo, Knut
    Ulleval University Hospital.
    The prostaglandin E1 analog misoprostol reduces symptoms and microvascular arteriovenous shunting in erythromelalgia-a double-blind, crossover, placebo-compared study.2004In: Journal of Investigative Dermatology, ISSN 0022-202X, E-ISSN 1523-1747, Vol. 122, no 3, p. 587-93Article in journal (Refereed)
    Abstract [en]

    Based on previous experience with parenteral prostanoids, we studied the effect of misoprostol treatment, an orally administered prostaglandin E1 analog, in patients with erythromelalgia. Treatment with placebo was followed by treatment with misoprostol (0.4-0.8 mg per d), both for 6 wk. The patients (n=21) and a study nurse who administered the trial were blinded. The endpoints were change in pain and need for cooling and global assessment of the treatment. Following central body heat provocation, global skin perfusion, capillary morphology, and change in pain were also recorded before and after each treatment period. Results were compared with data from healthy control subjects (n=11) that did not undergo treatment. Clinical safety and tolerability evaluation included physical examinations, clinical laboratory tests, and monitoring of adverse events. All clinical outcome measures were significantly better after treatment with misoprostol (p<0.01) as compared with placebo treatment and after a 3- mo follow-up without treatment. The heat-induced increase in global perfusion after misoprostol treatment was similar to the control group and significantly lower when compared with baseline (p<0.01) and placebo treatment (p<0.05), respectively. This study demonstrates that misoprostol is clinically superior to placebo in patients with erythromelalgia. The results of the perfusion studies may imply that the mechanism of action of the beneficial effect of misoprostol is reduced microvascular arteriovenous shunting in affected skin.

    Download full text (pdf)
    FULLTEXT01
  • 9.
    Nyflött, Åsa
    Karlstad University, Faculty of Technology and Science.
    Development of an Image Processing Tool for Fluorescence Microscopy Analysis of Paper Chemistry2010Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Paper making today is, to some extent, based on empirical knowledge. It is wellknown that fines, pH, charge and ion strength affect the manufacture of paper. One way of extending knowledge of the mechanisms of paper chemistry is to follow the trajectories of fines and additives in the paper suspension to gather information as to the manner in which they react. Four tracking algorithms adapted to the needs of this particular problem were implemented in order to track particles effciently. The tracking algorithms include two variants of the well-known "Lucas-Kanade algorithm" and template matching techniques based on cross-correlation and least squares matching. Although these techniques are similar in principle, the actual tracking can nevertheless differ; the Lucas-Kanade algorithms were found to be more invariant to noise, whereas the cross-correlation and least squares methods are more rapid to execute in Matlab. The tracking methods have been evaluated using a simulator to generate image sequences of synthetic particles moving according to Brownian motion. Tracking has also been evaluated on microscope images of real latex particles where the results have been compared to manual tracking. Tracking of both the simulated particles and the latex particles resulted in similar results when compared to known position and manual tracking, respectively.

    Download full text (pdf)
    FULLTEXT01
  • 10.
    Palm, Magdalena
    Karlstad University, Faculty of Health, Science and Technology (starting 2013), Department of Mathematics and Computer Science.
    Detektering och Identifiering av Vägmärken2017Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    This dissertation describes a project for creating a prototype application for the purpose of simplifying road sign inventory. Instead of manually analyzing a captured image and comparing it to a database of inventory road signs, you can instead launch this application, load the image and get the identification code of that road sign. The idea is that road sign inventory takers will save the time it takes to review all the pictures taken during a day and instead, the system will automatically generate the identification code of that road sign. The basic application is written as a WPF application using the EmguCV framework, which in turn uses the .NET framework. The important aspect of this project is to see if matching road signs can can be done with reasonable computation and within reasonable time, this was made possible with EmguCVs FLANN-algorithm. The project resulted in a functional application in which users can upload circular velocity road signs and the application detects and identifies the road sign via a database of road signs.

    Download full text (pdf)
    fulltext
    Download full text (pdf)
    Arkivfil
1 - 10 of 10
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • apa.csl
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf