Results 1 - 10
of
12
Epipolar Geometry for Central Catadioptric Cameras
, 2002
"... Central catadioptric cameras are cameras which combine lenses and mirrors to capture a very wide field of view with a central projection. In this paper we extend the classical epipolar geometry of perspective cameras to all central catadioptric cameras. Epipolar geometry is formulated as the geometr ..."
Abstract
-
Cited by 85 (5 self)
- Add to MetaCart
Central catadioptric cameras are cameras which combine lenses and mirrors to capture a very wide field of view with a central projection. In this paper we extend the classical epipolar geometry of perspective cameras to all central catadioptric cameras. Epipolar geometry is formulated as the geometry of corresponding rays in a three-dimensional space. Using the model of image formation of central catadioptric cameras, the constraint on corresponding image points is then derived. It is shown that the corresponding points lie on epipolar conics. In addition, the shape of the conics for all types of central catadioptric cameras is classified. Finally, the theory is verified by experiments with real central catadioptric cameras.
Using Symmetry as a Feature in Panoramic Images for Mobile Robot Applications
- In Proc
, 2002
"... We propose to use symmetry as a global feature for mobile robot applications in an indoor environment. Our mobile robot solely uses an omnidirectional vision sensor consisting of a digital colour video camera and a hyperbolic mirror. Thus, robust image feature extraction is required for good perform ..."
Abstract
-
Cited by 8 (2 self)
- Add to MetaCart
(Show Context)
We propose to use symmetry as a global feature for mobile robot applications in an indoor environment. Our mobile robot solely uses an omnidirectional vision sensor consisting of a digital colour video camera and a hyperbolic mirror. Thus, robust image feature extraction is required for good performance in each application. The detection of symmetry is an effective natural vision routine resulting in more global features than edges, corner, etc. Each image can be reduced to certain points of symmetric interest, which can be tracked in all azimuthal directions and used for multiple tasks like range estimation, object classification and probably egomotion. In this paper, we present a qualitative symmetry algorithm, the results of range estimation and object classification experiments using symmetry as a feature in panoramic images. 1
Omnidirectional Depth Computation from a Single Image
, 2005
"... Omnidirectional cameras offer a much wider field of view than the perspective ones and alleviate the problems due to occlusions. However, both types of cameras suffer from the lack of depth perception. A practical method for obtaining depth in computer vision is to project a known structured light ..."
Abstract
-
Cited by 7 (1 self)
- Add to MetaCart
(Show Context)
Omnidirectional cameras offer a much wider field of view than the perspective ones and alleviate the problems due to occlusions. However, both types of cameras suffer from the lack of depth perception. A practical method for obtaining depth in computer vision is to project a known structured light pattern on the scene avoiding the problems and costs involved by stereo vision. This paper is focused on the idea of combining omnidirectional vision and structured light with the aim to provide 3D information about the scene. The resulting sensor is formed by a single catadioptric camera and an omnidirectional light projector. It is also discussed how this sensor can be used in robot navigation applications.
Modelling and accuracy estimation of a new omnidirectional depth computation sensor
, 2006
"... ..."
Accuracy estimation of a new omnidirectional 3D vision sensor
- In Int. Conf. Image Proc
, 2005
"... We present a computer vision system that associates omni-directional vision with structured light with the aim of ob-taining depth information for a 360 degrees field of view.The approach proposed in this article combines an omnidirec-tional camera with a panoramic laser projector. The article shows ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
We present a computer vision system that associates omni-directional vision with structured light with the aim of ob-taining depth information for a 360 degrees field of view.The approach proposed in this article combines an omnidirec-tional camera with a panoramic laser projector. The article shows how the sensor is modelled and its accuracy is proved by means of experimental results. The proposed sensor pro-vides useful information for robot navigation applications, pipe inspection, 3D scene modelling etc. 1.
Capturing Mosaic-Based Panoramic Depth Images with a Single Standard Camera
"... Abstract. In this paper we present a panoramic depth imaging system. The system is mosaic-based which means that we use a single rotating camera and assemble the captured images in a mosaic. Due to a setoff of the camera’s optical center from the rotational center of the system we are able to captur ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract. In this paper we present a panoramic depth imaging system. The system is mosaic-based which means that we use a single rotating camera and assemble the captured images in a mosaic. Due to a setoff of the camera’s optical center from the rotational center of the system we are able to capture the motion parallax effect which enables the stereo reconstruction. The camera is rotating on a circular path with the step defined by an angle equivalent to one column of the captured image. The equation for depth estimation can be easily extracted from system geometry. To find the corresponding points on a stereo pair of panoramic images the epipolar geometry needs to be determined. It can be shown that the epipolar geometry is very simple if we are doing the reconstruction based on a symmetric pair of stereo panoramic images. We get a symmetric pair of stereo panoramic images when we take symmetric columns on the left and on the right side from the captured image center column. Epipolar lines of the symmetrical pair of panoramic images are image rows. We focused mainly on the system analysis. The system performs well in the reconstruction of small indoor spaces.
Multiperspective panoramic depth imaging
"... In this chapter we present a stereo panoramic depth imaging system, which builds depth panoramas from multiperspective panoramas while using only one standard camera. The basic system is mosaic-based, which means that we use a single standard rotating camera and assemble the captured images in a mul ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
In this chapter we present a stereo panoramic depth imaging system, which builds depth panoramas from multiperspective panoramas while using only one standard camera. The basic system is mosaic-based, which means that we use a single standard rotating camera and assemble the captured images in a multiperspective panoramic image. Due to a setoff of the camera’s optical center from the rotational center of the system, we are able to capture the motion parallax effect, which enables the stereo reconstruction. The system has been comprehensively analysed. The analyses include the study of influence of different system parameters on the reconstruction accuracy, constraining the search space on the epipolar line, meaning of error in estimation of corresponding point, definition of the maximal reliable depth value, contribution of the vertical reconstruction and influence of using different cameras. They are substantiated with a number of experiments, including experiments addressing the baseline, the repeatability of results in different rooms, by using different cameras, influence of lens distortion presence on the reconstruction accuracy and evaluation of different models for estimation of system parameters. The analyses and the experiments revealed a number of interesting properties of the system. According to the basic system accuracy we definitely can use the system for autonomous robot localization and navigation tasks.
A computer vision sensor for panoramic depth perception
- Proc. of the 2nd Iberian Conf. on Pattern Recognition and Image Analysis
, 2005
"... Abstract. A practical way for obtaining depth in computer vision is the use of structured light systems. For panoramic depth reconstruction several images are needed which most likely implies the construction of a sensor with mobile elements. Moreover, misalignments can appear for non-static scenes. ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract. A practical way for obtaining depth in computer vision is the use of structured light systems. For panoramic depth reconstruction several images are needed which most likely implies the construction of a sensor with mobile elements. Moreover, misalignments can appear for non-static scenes. Omnidirectional cameras offer a much wider field of view than the perspective ones, capture a panoramic image at every moment and alleviate the problems due to occlusions. This paper is focused on the idea of combining omnidirectional vision and structured light with the aim to obtain panoramic depth information. The resulting sensor is formed by a single catadioptric camera and an omnidirectional light projector. 1
Non-central Cameras for 3D Reconstruction
, 2001
"... This thesis proposal deals with a 3D reconstruction from noncentral cameras. An introduction to the 3D reconstruction in general is given, together with the definition of non-central cameras and their comparison with central cameras. State-of-the-art in the field of the non-central cameras is pr ..."
Abstract
- Add to MetaCart
(Show Context)
This thesis proposal deals with a 3D reconstruction from noncentral cameras. An introduction to the 3D reconstruction in general is given, together with the definition of non-central cameras and their comparison with central cameras. State-of-the-art in the field of the non-central cameras is presented. Our previous contribution in this area is described and thesis goals are formulated.
Robot Assisted Sewer Inspection
, 2002
"... This report is the result of a student exchange project between Delft University of Technology (TU Delft) and the Czech Technical University in Prague (CVUT). Due to existing good contacts between the computer science departments of these two universities I was able to spend eight weeks in Pragu ..."
Abstract
- Add to MetaCart
This report is the result of a student exchange project between Delft University of Technology (TU Delft) and the Czech Technical University in Prague (CVUT). Due to existing good contacts between the computer science departments of these two universities I was able to spend eight weeks in Prague at the Department of Cybernetics . There, I was located at a research unit specialized in computer vision, image processing and pattern recognition, called Center for Machine Perception (CMP). I participated in an ongoing project that targets on Inspecting Sewerage systems and Image Analysis by Computer (ISAAC). During my stay I was able to see a lot of new and interesting technologies in which the computer vision lab specializes. The project I worked on was quite interesting and challenging and I was able to extend my knowledge in a lot of areas. Besides spending time at the university I got to see a lot of beautiful historical buildings, landscapes and a lot of interesting aspects of the Czech culture. I would like to thank prof. Vaclav Hlavac, drs. dr. Leon Rothkrantz, ir. Vladimir Smutney and my colleagues at the lab for the opportunity and help offered. I would also like to thank the CVUT and TU Delft for financial support offered for travel expenses and accommodation. One unexpected aspect of the last week of my stay was a mayor flooding that struck the Czech Republic. The water of the river Vltava, running through the center of Prague, rose an incredible 8 meters and caused a lot of damage and grief. As a result bridges and public transport were closed down and I was unable to reach university during that time. As a side effect the final stage of gathering results was not properly conducted as will get clear in chapter seven. I would like to express my feelings...
