Advanced search

Showing result 1 - 5 of 6 swedish dissertations matching the above criteria.

  2. 1. A new kernel method for object recognition:spin glass-Markov random fields

    Author : Barbara Caputo; Stefan Arnborg; Kalle Åström; KTH; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Datalogi; Datalogi; Computer science; Datalogi;

    Abstract : Recognizing objects through vision is an important part of our lives: we recognize people when we talk to them, we recognize our cup on the breakfast table, our car in a parking lot, and so on. While this task is performed with great accuracy and apparently little effort by humans, it is still unclear how this performance is achieved. READ MORE

  4. 2. Global Pose Estimation from Aerial Images : Registration with Elevation Models

    Author : Bertil Grelsson; Michael Felsberg; Per-Erik Forssén; Kalle Åström; Linköpings universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES;

    Abstract : Over the last decade, the use of unmanned aerial vehicles (UAVs) has increased drastically. Originally, the use of these aircraft was mainly military, but today many civil applications have emerged. READ MORE

  5. 3. Ground Object Recognition using Laser Radar Data : Geometric Fitting, Performance Analysis, and Applications

    Author : Christna Grönwall; Fredrik Gustafsson; Kalle Åström; Linköpings universitet; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Laser radar; object detection; object recognition; performance; least squares; ICP; Cramér-Rao; Signal processing; Signalbehandling;

    Abstract : This thesis concerns detection and recognition of ground object using data from laser radar systems. Typical ground objects are vehicles and land mines. For these objects, the orientation and articulation are unknown. The objects are placed in natural or urban areas where the background is unstructured and complex. READ MORE

  6. 4. Approximative Uncertainty in Neural Network Predictions

    Author : Magnus Malmström; Fredrik Gustafsson; Daniel Axehill; Isaac Skog; Kalle Åström; Linköpings universitet; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY;

    Abstract : Suppose data-driven black-box models, e.g., neural networks, should be used as components in safety-critical systems such as autonomous vehicles. In that case, knowing how uncertain they are in their predictions is crucial. READ MORE

  7. 5. Drill Failure Detection based on Sound using Artificial Intelligence

    Author : Thanh Tran; Jan Thim; Sebastian Bader; Kalle Åström; Mittuniversitetet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Convolutional neural network; machine failure detection; Mel-spectrogram; long short-term memory; sound signal processing;

    Abstract : In industry, it is crucial to be able to detect damage or abnormal behavior in machines. A machine's downtime can be minimized by detecting and repairing faulty components of the machine as early as possible. It is, however, economically inefficient and labor-intensive to detect machine fault sounds manual. READ MORE