Conference Paper

Innovative geometric pose reconstruction for marker-based single camera tracking.

DOI: 10.1145/1128923.1128962 Conference: Proceedings VRCIA 2006 ACM International Conference on Virtual Reality Continuum and its Applications, Chinese University of Hong Kong, Hong Kong, China, June 14-17, 2006
Source: DBLP


Mobile augmented reality applications are in need of tracking systems which can be wearable and do not cause a high processing load, while still offering reasonable performance, robustness and accuracy. The motivation to develop yet another tracking algorithm is two-fold. Most of the existing approaches use classical optimization techniques such as the Gauss-Newton method. However, since those algorithms were developed to address general optimization problems, they do not fully exploit the structure of the pose estimation problem with its geometric constraint targets. Also, mixed reality applications demand that pose estimation be not only accurate but also robust and computationally efficient. Hence there is a need for algorithms that are as accurate as classical algorithms, yet are also globally convergent and fast enough for real-time applications. In this paper we introduce a new iterative geometric method for pose estimation from four co-planar points and we present the current status of PTrack, an infrared marker-based single camera tracking system benefiting from this approach. Our novel pose estimation algorithm identifies possible labels composed of retro-reflective markers in a 2D post-processing using a divide-and-conquer strategy to segment the camera's image space and attempts an iterative geometric D reconstruction of position and orientation in camera space. Tracking results are made available to applications through OpenTracker [OpenTracker 2006] framework. To analyse tracking accuracy and precision, we built a generic test-bed and compared PTrack to ARToolKit [Kato and Billinghurst 1999; Kato et al. 2000], one of the most wide-spread low-cost tracking solutions. Results show that our tracking system achieves competitive accuracy levels better than ARToolKit and close to commercial systems, while being highly stable and affordable.

Download full-text


Available from: Joaquim Armando Jorge, Aug 24, 2015
27 Reads
  • Source
    • "Santos et. al. proposes accuracy evaluation of a new infrared based marker in which the experimental conditions with real data are very close to the conditions in which we use our simulator [12](camera marker distance around 80 cm). However, the experiments are realized with inaccurate hand made materials which explain their final low tracking accuracy (6 mm). "
    [Show abstract] [Hide abstract]
    ABSTRACT: In recent years, many simulation softwares and augmented reality applications have been developed using optical tracking system as a mode of interface. For some of them, and more specifically in the area of medical applications, a high accuracy and stability is required. A commercial stereoscopic tracking system is then of-ten integrated with the software to ensure the accuracy. However, the price of such system makes it very expensive for an individual user. Indeed, the manufacturer must ensure an excellent calibration between both camera. Using a single camera to perform tracking would be more cost effective and would allow the user to calibrate the system on his own. However, it is well known that single cam-era tracking is very sensitive and provides usually poor performance for object pose estimation. In this paper, we investigate the influ-ence of the number of point embedded in an optical marker on the tracking accuracy using a single camera. Firstly, we show how we can increase the number of tracked points by extracting more fea-tures from the central part of a typical marker used in the literature. Secondly, we evaluate on synthetic data the accuracy enhancement in the estimation of the marker pose when the number of point are increased. Then, we show in two of our applications that a larger number of point can provide an accuracy that is equivalent to the one provided by a stereoscopic system with fewer points. Finally, we show that our approach can be easily used with the open source ARToolkit+ library, and we provide experimental results on real data to measure the pose stability improvement in comparison with common approaches.
  • Source
    • "Several vision-based tracking systems are based on planar targets. [11][12][13][14]. "
    20th International Congress of Graphic Engeeniering, Valencia, 4-6 June; 01/2008
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we describe a novel algorithm to group, label, identify and perform optical tracking of marker sets, which are grouped into two specific configurations, and whose projective invariant properties will allow obtaining a unique identification for each predefined marker pattern. These configurations are formed by 4 collinear and 5 coplanar markers. This unique identification is used to correctly recognize various and different marker patterns inside the same tracking area, in real time. The algorithm only needs image coordinates of markers to perform the identification of marker patterns. For grouping the dispersed markers that appear in the image, the algorithm uses a "divide and conquer" strategy to segment the image and give some neighborhood reference among markers.
    Advances in Visual Computing, Third International Symposium, ISVC 2007, Lake Tahoe, NV, USA, November 26-28, 2007, Proceedings, Part I; 01/2007
Show more