Avancerad sökning

Hittade 5 avhandlingar som matchar ovanstående sökkriterier.

1. 1. Local visual feature based localisation and mapping by mobile robots

   Författare :Henrik Andreasson; Achim Lilienthal; Jim Little; Örebro universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; mobile robotics; registration; localisation; SLAM; mapping; omnidirectional vision; 3D vision; appearance based; TECHNOLOGY; TEKNIKVETENSKAP; Computer science; Datavetenskap; Computer and Systems Science; Data- och systemvetenskap;

   Sammanfattning : This thesis addresses the problems of registration, localisation and simultaneous localisation and mapping (SLAM), relying particularly on local visual features extracted from camera images. These fundamental problems in mobile robot navigation are tightly coupled. LÄS MER

3. 2. Improving Multi-Atlas Segmentation Methods for Medical Images

   Författare :Jennifer Alvén; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Supervised learning; semantic segmentation; multi-atlas segmentation; conditional random fields; label fusion; feature-based registration; image registration; random decision forests; convolutional neural networks; medical image segmentation;

   Sammanfattning : Semantic segmentation of organs or tissues, i.e. delineating anatomically or physiologically meaningful boundaries, is an essential task in medical image analysis. One particular class of automatic segmentation algorithms has proved to excel at a diverse set of medical applications, namely multi-atlas segmentation. LÄS MER

4. 3. Combining Shape and Learning for Medical Image Analysis

   Författare :Jennifer Alvén; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; feature-based registration; convolutional neural networks; conditional random fields; medical image segmentation; random decision forests; machine learning; multi-atlas segmentation; medical image registration; shape models;

   Sammanfattning : Automatic methods with the ability to make accurate, fast and robust assessments of medical images are highly requested in medical research and clinical care. Excellent automatic algorithms are characterized by speed, allowing for scalability, and an accuracy comparable to an expert radiologist. LÄS MER

5. 4. Three-dimensional guidance for Endovascular Aortic Repair

   Författare :Giasemi Koutouzi; Göteborgs universitet; []
   Nyckelord :MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; anatomy deformation; CBCT; EVAR; image fusion; image guidance; image registration;

   Sammanfattning : Image fusion (IF) of preoperative computed tomography (CT) with intraoperative cone-beam CT (CBCT) is a potentially powerful tool for guidance during endovascular aortic repair (EVAR). It may improve intraoperative anatomic visualization and reduce doses of radiation and contrast medium. LÄS MER

7. 5. Vision-based Localization and Attitude Estimation Methods in Natural Environments

   Författare :Bertil Grelsson; Michael Felsberg; Per-Erik Forssén; Joni Kämäräinen; Linköpings universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES;

   Sammanfattning : Over the last decade, the usage of unmanned systems such as Unmanned Aerial Vehicles (UAVs), Unmanned Surface Vessels (USVs) and Unmanned Ground Vehicles (UGVs) has increased drastically, and there is still a rapid growth. Today, unmanned systems are being deployed in many daily operations, e.g. LÄS MER