Sökning: "Geometric Vision"

Visar resultat 1 - 5 av 42 avhandlingar innehållade orden Geometric Vision.

1. 1. Computational Methods for Computer Vision : Minimal Solvers and Convex Relaxations

   Författare :Viktor Larsson; Mathematical Imaging Group; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Computer Vision; Geometric Vision; minimal solvers; Convex relaxation; Pose estimation;

   Sammanfattning : Robust fitting of geometric models is a core problem in computer vision. The most common approach is to use a hypothesize-and-test framework, such as RANSAC. In these frameworks the model is estimated from as few measurements as possible, which minimizes the risk of selecting corrupted measurements. LÄS MER

3. 2. Polynomial Solvers for Geometric Problems - Applications in Computer Vision and Sensor Networks

   Författare :Yubin Kuang; Matematik LTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; polynomial solver; geometric problems; computer vision; sensor networks; symmetry;

   Sammanfattning : Given images of a scene taken by a moving camera or recordings of a moving smart phone playing a song by a microphone array, how hard is it to reconstruct the scene structure or the moving trajectory of the phone? In this thesis, we study and solve several fundamental geometric problems in order to provide solutions to these problems. The key underlying technique for solving such geometric problems is solving systems of polynomial equations. LÄS MER

4. 3. Higher-Order Regularization in Computer Vision

   Författare :Johannes Ulén; Matematik LTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Computer Vision; Regularization; Segmentation; Dense Stereo;

   Sammanfattning : At the core of many computer vision models lies the minimization of an objective function consisting of a sum of functions with few arguments. The order of the objective function is defined as the highest number of arguments of any summand. LÄS MER

5. 4. Low Rank Matrix Factorization and Relative Pose Problems in Computer Vision

   Författare :Fangyuan Jiang; Matematik LTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Geometric Computer Vision; Low-rank Matrix Factorization; Relative Pose;

   Sammanfattning : This thesis is focused on geometric computer vision problems. The first part of the thesis aims at solving one fundamental problem, namely low-rank matrix factorization. We provide several novel insights into the problem. In brief, we characterize, generate, parametrize and solve the minimal problems associated with low-rank matrix factorization. LÄS MER

7. 5. Geometric Computer Vision for Rolling-shutter and Push-broom Sensors

   Författare :Erik Ringaby; Per-Erik Forssén; Anders Heyden; Linköpings universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; rolling shutter cmos video rectification stabilisation push-broom kinect;

   Sammanfattning : Almost all cell-phones and camcorders sold today are equipped with a CMOS (Complementary Metal Oxide Semiconductor) image sensor and there is also a general trend to incorporate CMOS sensors in other types of cameras. The sensor has many advantages over the more conventional CCD (Charge-Coupled Device) sensor such as lower power consumption, cheaper manufacturing and the potential for on-chip processing. LÄS MER