Omnidirectional sensing for human interaction

Yagi, Yasushi; Yachida, Masahiko

doi:10.1109/omnvis.2002.1044505

Cited by 23 publications

(30 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This section aims at describing the most commonly used technologies in computer vision and related areas, without any claim of being exhaustive. More information, including historical overviews, can be found in the following references, which include textbooks, articles, and webpages [50,51,54,71,103,220,227,294,326,335,528,541].…”

Section: Technologiesmentioning

confidence: 99%

See 1 more Smart Citation

Camera Models and Fundamental Concepts Used in Geometric Computer Vision

Sturm

2010

FNT in Computer Graphics and Vision

157

122

View full text Add to dashboard Cite

A printed and bound version is available at a special discount price of US35 from Now Publishers. This can be obtained by entering the promotional code CGV006023 on https://www.nowpublishers.com/bookorder.aspx?doi=0600000023&product=CGVInternational audienceThis survey is mainly motivated by the increased availability and use of panoramic image acquisition devices, in computer vision and various of its applications. Different technologies and different computational models thereof exist and algorithms and theoretical studies for geometric computer vision ("structure-from-motion") are often re-developed without highlighting common underlying principles. One of the goals of this survey is to give an overview of image acquisition methods used in computer vision and especially, of the vast number of camera models that have been proposed and investigated over the years, where we try to point out similarities between different models. Results on epipolar and multi-view geometry for different camera models are reviewed as well as various calibration and self-calibration approaches, with an emphasis on non-perspective cameras. We finally describe what we consider are fundamental building blocks for geometric computer vision or structure-from-motion: epipolar geometry, pose and motion estimation, 3D scene modeling, and bundle adjustment. The main goal here is to highlight the main principles of these, which are independent of specific camera models

show abstract

Section: Technologiesmentioning

confidence: 99%

“…However, the issue of how to compensate for the camera displacement during rotations of the mirror, due to the airplane's motion, was not fully discussed. Other systems that use rotating mirrors or prisms are referenced by Yagi [541], see also Section 2.3.4.…”

Section: Other Technologiesmentioning

confidence: 99%

Camera Models and Fundamental Concepts Used in Geometric Computer Vision

Sturm

2010

FNT in Computer Graphics and Vision

157

122

View full text Add to dashboard Cite

show abstract

“…To deal with this ambiguity problem, additional constraints are usually required for motion models so as to disambiguate a true global motion direction [19], [39], [40]. Although this problem can be overcome by using the wide field of view camera such as omnidirectional camera or the multiple cameras, how to obtain the precise omnidirectional images itself is another problem having attracted a lot of interests [41]. Another problem is that motion pattern is easily distorted, since image motion is not only produced by the global motion of the vehicle on which camera is mounted, but also by unexpected camera motion due to bumping and shaking of the vehicle [17].…”

Section: Copyright C 2010 the Institute Of Electronics Information Amentioning

confidence: 99%

An Ego-Motion Detection System Employing Directional-Edge-Based Motion Field Representations

Hao¹,

Shibata²

2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper, a motion field representation algorithm based on directional edge information has been developed. This work is aiming at building an ego-motion detection system using dedicated VLSI chips developed for real time motion field generation at low powers [1], [2]. Directional edge maps are utilized instead of original gray-scale images to represent local features of an image and to detect the local motion component in a moving image sequence. Motion detection by edge histogram matching has drastically reduced the computational cost of block matching, while achieving a robust performance of the ego-motion detection system under dynamic illumination variation. Two kinds of feature vectors, the global motion vector and the component distribution vectors, are generated from a motion field at two different scales and perspectives. They are jointly utilized in the hierarchical classification scheme employing multiple-clue matching. As a result, the problems of motion ambiguity as well as motion field distortion caused by camera shaking during video capture have been resolved. The performance of the ego-motion detection system was evaluated under various circumstances, and the effectiveness of this work has been verified.

show abstract

“…Omnidirectional Vision systems that enable 360° imaging have been widely used in several research fields such as robot navigation, telepresence, close-range Photogrammetry and virtual reality (Kang and Szeliski, 1997;Yagi, 1999;Spacek, 2005;Sturm et al, 2010). Omnidirectional images can be acquired using: camera with fisheye lenses; moving cameras or optical elements; catadioptric systems (camera and mirror); and multiple cameras with divergent views (Sturm et al 2010).…”

Section: Introductionmentioning

confidence: 99%

Experimental Assessment of Techniques for Fisheye Camera Calibration

2015

View full text Add to dashboard Cite

Abstract:Fisheye lens cameras enable to increase the Field of View (FOV), and consequently they have been largely used in several applications like robotics. The use of this type of cameras in closerange Photogrammetry for high accuracy applications, requires rigorous calibration. The main aim of this work is to present the calibration results of a Fuji Finepix S3PRO camera with Samyang 8mm fisheye lens using rigorous mathematical models. Mathematical models based on Perspective, Stereo-graphic, Equi-distant, Orthogonal and Equi-solid-angle projections were implemented and used in the experiments. The fisheye lenses are generally designed following one of the last four models, and Bower-Samyang 8mm lens is based on Stereo-graphic projection. These models were used in combination with symmetric radial, decentering and affinity distortion models. Experiments were performed to verify which set of IOPs (Interior Orientation Parameters) presented better results to describe the camera inner geometry. Collinearity mathematical model, which is based on perspective projection, presented the less accurate results, which was expected because fisheye lenses are not designed following the perspective projection. Stereo-graphic, Equi-distant, Orthogonal and Equi-solid-angle projections presented similar results even considering that Bower-Samyang fisheye lens was built based on Stereo-graphic projection. The experimental results also demonstrated a small correlation between IOPs and EOPs (Exterior Orientation Parameters) for Bower-Samyang lens.Keywords: Photogrammetry; Camera calibration; Digital cameras; Omnidirectional Systems. Resumo:As câmaras com objetiva olho de peixe permitem aumentar o campo de visada da câmara, e consequentemente é amplamente empregada na robótica. O uso desse tipo de câmara em aplicações de alta acurácia na Fotogrametria a curta distância, exige a sua calibração. O objetivo principal é calibrar a câmara Fuji Finepix S3pro com a lente olho de peixe Bower-Samyang 8mm usando modelos matemático rigorosos. Modelos matemáticos baseados nas projeções perspectiva, estereográfica, equidistante, ortogonal e do ângulo equi-sólido foram implementados e usados nos experimentos. As lentes olho de peixe são geralmente fabricadas seguindo um dos quatro últimos modelos, e a lente Bower-Samyang 8 mm é baseada na projeção estereográfica. Os modelos matemáticos foram usados em conjunto com os modelos de distorções radial simétrica, descentrada e de afinidade. Experimentos foram realizados para verificar o conjunto de parâmetros de orientação interior adequado para descrever a geometria interna da câmara. O modelo matemático de colinearidade, baseado na projeção perspectiva, apresentou o resultado menos acurado. As lentes olho de peixe não são fabricadas conforme a projeção perspectiva, o que justifica esse resultado. Os resultados obtidos com as projeções estereográfica, equidistante, ortogonal e do ângulo equi-sólido não apresentam diferenças significativas, embora a lente olho de peixe Bower-Samyang tenha sido constr...

show abstract

Omnidirectional sensing for human interaction

Cited by 23 publications

References 5 publications

Camera Models and Fundamental Concepts Used in Geometric Computer Vision

Camera Models and Fundamental Concepts Used in Geometric Computer Vision

An Ego-Motion Detection System Employing Directional-Edge-Based Motion Field Representations

Experimental Assessment of Techniques for Fisheye Camera Calibration

Contact Info

Product

Resources

About