Reliable Automatic Calibration of a Marker-Based Position Tracking System

Claus, D.; Fitzgibbon, Andrew

doi:10.1109/acvmot.2005.101

Cited by 41 publications

(21 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [11] and [16] dedicated "data rings" are added to the fiducial design. A set of four circles located at the corner of a square is adopted by [4]: in this case an identification pattern is placed at the centroid of the four dots in order to distinguish between different targets. This ability to recognize the viewed markers is very important .…”

Section: Introductionmentioning

confidence: 99%

RUNE-Tag: A high accuracy fiducial marker with strong occlusion resilience

et al. 2011

View full text Add to dashboard Cite

Over the last decades fiducial markers have provided widely adopted tools to add reliable model-based features into an otherwise general scene. Given their central role in many computer vision tasks, countless different solutions have been proposed in the literature. Some designs are focused on the accuracy of the recovered camera pose with respect to the tag; some other concentrate on reaching high detection speed or on recognizing a large number of distinct markers in the scene. In such a crowded area both the researcher and the practitioner are licensed to wonder if there is any need to introduce yet another approach. Nevertheless, with this paper, we would like to present a general purpose fiducial marker system that can be deemed to add some valuable features to the pack. Specifically, by exploiting the projective properties of a circular set of sizeable dots, we propose a detection algorithm that is highly accurate. Further, applying a dot pattern scheme derived from errorcorrecting codes, allows for robustness with respect to very large occlusions. In addition, the design of the marker itself is flexible enough to accommodate different requirements in terms of pose accuracy and number of patterns. The overall performance of the marker system is evaluated in an extensive experimental section, where a comparison with a wellknown baseline technique is presented.

show abstract

Section: Introductionmentioning

confidence: 99%

RUNE-Tag: A high accuracy fiducial marker with strong occlusion resilience

et al. 2011

View full text Add to dashboard Cite

show abstract

“…In [2] the concentric circle approach is enhanced by adding colors and multiple scales, while In [9] and [13] dedicated "data rings" are added to the marker design. A set of four circles located at the corner of a square is adopted by [3]: in this case an identification pattern is placed at the centroid of the four dots in order to distinguish between different targets. This ability to recognize the viewed markers is very important for complex scenes where more than a single fiducial is required, furthermore, the availability of a coding schema allows for an additional validation step and lowers the number of false positives.…”

Section: Introductionmentioning

confidence: 99%

Image-Space Marker Detection and Recognition Using Projective Invariants

Bergamasco

Albarelli

Torsello

2011

2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission

View full text Add to dashboard Cite

Visual marker systems have become an ubiquitous tool to supply a reference frame onto otherwise general scenes. Throughout the last decades, a wide range of different approaches have emerged, each one endowed with different strengths and limitations. Some techniques adopt tags that are optimized to reach a high accuracy in the recovered camera pose, others are based on designs that aim to maximizing the detection speed or minimizing the effect of occlusion on the detection process. Most of them, however, employ a two step procedure where an initial homography estimation is used to translate the marker from the image plane to an orthonormal world where it is validated and recognized. With this paper, we present a general purpose fiducial marker system that allows to perform both steps directly in image-space. Specifically, by exploiting projective invariants such as collinearity and cross-ratios, we introduce a detection and recognition algorithm that is fast, accurate and moderately robust to occlusion. The overall performance of the system is evaluated in an extensive experimental section, where a comparison with a well-known baseline technique is presented. I. . IntroductionA visual marker is an artificial object consistent with a known model that is placed into a scene in order to supply a reference frame. Currently, such artifacts are unavoidable whenever a high level of precision and repeatability in image-based measurement is required, as in the case of accurate camera pose estimation, 3D structure-frommotion or, more in general, any flavor of vision-driven dimensional assessment task. While in some scenarios approaches based on naturally occurring features have been shown to obtain satisfactory results, they still suffer from a couple of shortcomings that severely hinder their broader use. Specifically, the lack of a well known model limits their usefulness in pose estimation and, even when such a model can be inferred (for instance by using bundle adjustment) its accuracy heavily depends on the correctness of localization and matching steps. Moreover, the availability and distinctiveness of natural features is not guaranteed at all. Indeed the smooth surfaces found in most man-made objects can easily lead to scenes that are very poor in features. Finally, photometric inconsistencies due to reflective or translucent materials jeopardizes the repeatability of the detected points. For this reasons, it is not surprising that artificial fiducial tags continue to be widely used and are still an active research topic. Markers are generally designed to be easily detected and recognized in images produced by a pinhole-modeled camera. In this sense they make heavy use of the projective invariance properties of geometrical entities such as lines, planes and conics. One of the earliest property used is probably the invariance of ellipses with respect to projective transformation, specifically, ellipses, and in particular circles, appear as (different) ellipses under any projective transformation. This allows...

show abstract

“…Pattern recognition is performed by identifying the four vertices of square regions contained on a video image, which is then converted to a binary image (black and white). The symbol inside the vertices is compared to templates input by the user or developer [Claus and Fitzgibbon 2005]. Whenever the information contained in the extracted square is similar to any of the registered markers, the system identifies the marker and determines its relative pose to the camera.…”

Section: Tracking and Identification Of Fiducial Markersmentioning

confidence: 99%

“…Meanwhile, each monitor displays a different fiducial marker. Computer vision techniques are used to calculate the angle between the monitors by comparing how the markers appear in the video captured by the webcam [Claus and Fitzgibbon 2005]. Such angles are then saved and used in the game to define the position and orientation of three virtual cameras, one for each monitor, which are finally used to render the game view to a player (details in Section 4.4.…”

Section: Overviewmentioning

confidence: 99%

Desktop-CAVE for First Person Shooter Games

Roman

Maciel

Nedel

2010

2010 Brazilian Symposium on Games and Digital Entertainment

View full text Add to dashboard Cite

Games are everywhere and, with the sharp improvement of graphics in the later years, a new challenge is to create better interfaces to amplify the sensorial experience of game players. In this context, the present work proposes a desktop based CAVE system using three video monitors with dynamic angles between them. Our hypothesis is that such a system provide an improvement in the players' peripheral vision for 3D first person shooter games. This would even benefit the player performance. In our implementation we used augmented reality and computer vision techniques to calibrate the monitors. Graphics libraries (ARToolkit e OpenGL) have been used to detect and calibrate monitors within the same 3D space and calculate the angles between them. The open source game AssaultCube has been modified to support three monitors and different camera angles. The game have shown to be entertaining and has been used as a use case for user tests. Tests have shown that the desktop CAVE system allows for performance improvement as the players make significatively less look-around movements with the mouse while keeping the average number of kills and deaths favorable in relation to a conventional one monitor setup.

show abstract

Reliable Automatic Calibration of a Marker-Based Position Tracking System

Cited by 41 publications

References 11 publications

RUNE-Tag: A high accuracy fiducial marker with strong occlusion resilience

RUNE-Tag: A high accuracy fiducial marker with strong occlusion resilience

Image-Space Marker Detection and Recognition Using Projective Invariants

Desktop-CAVE for First Person Shooter Games

Contact Info

Product

Resources

About