While the use of naturally-occurring features is a central focus of machine perception, artificial features (fiducials) play an important role in creating controllable experiments, ground truthing, and in simplifying the development of systems where perception is not the central objective. We describe a new visual fiducial system that uses a 2D bar code style “tag”, allowing full 6 DOF localization of features from a single image. Our system improves upon previous systems, incorporating a fast and robust line detection system, a stronger digital coding system, and greater robustness to occlusion, warping, and lens distortion. While similar in concept to the ARTag system, our method is fully open and the algorithms are documented in detail.

/pdf/apriltag-a-robust-and-flexible-visual-fiducial-system-3i6i7330tw.pdf

AprilTag: A robust and flexible visual fiducial system

Theory and applications of marker-based augmented reality

Due to the perceptual characteristics of the head, vibrotactile Head-mounted Displays are built with low actuator density. Therefore, vibrotactile guidance is mostly assessed by pointing towards objects in the azimuthal plane. When it comes to multisensory interaction in 3D environments, it is also important to convey information about objects in the elevation plane. In this paper, we design and assess a haptic guidance technique for 3D environments. First, we explore the modulation of vibration frequency to indicate the position of objects in the elevation plane. Then, we assessed a vibrotactile HMD made to render the position of objects in a 3D space around the subject by varying both stimulus loci and vibration frequency. Results have shown that frequencies modulated with a quadratic growth function allowed a more accurate, precise, and faster target localization in an active head pointing task. The technique presented high usability and a strong learning effect for a haptic search across different scenarios in an immersive VR setup.

Designing a Vibrotactile Head-Mounted Display for Spatial Awareness in 3D Spaces

Tracking is an important component of augmented reality systems. Tracking means to determine and follow the position and orientation of an object 
with respect to some reference coordinate system over time. As with all physical measurements the estimate is affected by errors. These errors propagate 
through the chain of transformations from the tracking systems to the final 
application, until they appear as alignment errors in the augmented reality 
application. 
This thesis deals with the mathematical tools that are needed to estimate 
the final resulting precision, as well as with visualization concepts for exploring 
and understanding tracking errors. The special case of optical tracking systems 
is further analyzed to provide useful initial estimates of the tracking error. A 
set of examples finally shows the application of the error estimation in real-world setups.

Tracking Errors in Augmented Reality

Three-dimensional computer-aided design (3D CAD) modeling and reviewing is one of the most common engineering project tools. Interaction in these environments is characterized by the need for a high precision level to execute specific tasks. Generally this kind of task uses specific interaction devices with 4 or more degrees of freedom, such as 3D mice. Currently applications involving 3D interaction use interaction devices for object modeling or for the implementation of navigation, selection and manipulation techniques in a virtual environment. A related problem is the need to control naturally non-immersive tasks, such as symbolic input (e.g., text, photos). In addition, the steep learning curve to handle such non-conventional devices is a recurring problem. The addition of sensors and the popularization of smart-phones and tablets, allowed the use of such devices in virtual engineering environments. These devices, differs to other devices by the possibility of including additional information and performing naturally non-immersive tasks.This work presents a 3D interaction tablet-based tool, which allows the aggregation of all major 3D interaction topics, such as navigation, selection, manipulation, system control and symbolic input. To validate the proposed tool, the SimUEP-Ambsim application was chosen, an oil and gas simulator that has the complexity needed and which allows the use of all techniques implemented. Then, the tool was tested in another application, a photo-voltaic solar plant simulator, in order to evaluate the generality of this work concept.

https://webserver2.tecgraf.puc-rio.br/~abraposo/pubs/VRCAI2013/p211-medeiros.pdf

A tablet-based 3D interaction tool for virtual engineering environments

to present a challenge in terms of performance, robustness and accuracy. In particular mobile augmented reality applications are in need of tracking systems which can be wearable and do not cause a high processing load. In this paper we introduce a novel iterative geometric method for pose estimation from four co-planar points and we present the current status of PTrack, a marker-based single camera tracking system benefiting from this approach. The system uses an IDS uEye [1] camera, equipped with infrared flash strobes and infrared pass filter, which acquires grayscale images and sends them to a computer where an image pre-processing algorithm identifies potential projections of retro-reflective markers. Our novel pose estimation algorithm identifies possible labels composed of markers in a 2D post-processing using a divide-and-conquer strategy to segment the camera's image space and attempts an iterative geometric 3D reconstruction of position and orientation in camera space. In the end successfully reconstructed labels are compared to a database for identification. Their 6 DoF data as well as their ID is made available to applications through OpenTracker [2] framework. To assess the performance of our approach we compared PTrack to ARToolKit [3] - which has been adapted to work with the same camera - and final results show that pose estimation is more accurate and precise, in both translation and rotation.

PTrack: Introducing a Novel Iterative Geometric Pose Estimation for a Marker-based Single Camera Tracking System

One of the reasons of how virtual reality applications penetrate industrial production chains slowly is because of significant investment costs to purchase adequate supporting hardware. As a consequence such applications are only available to major companies and fail to benefit the production processes of small and medium enterprises. In this article, we introduce PTrack, a real-time, low-cost, marker-based multiple camera tracking solution for virtual reality providing the accuracy and scalability usually found in much more expensive tracking systems. PTrack is composed of single camera tracking PTrack Units. Each unit is connected to a video camera equipped with infrared strobes and features a novel iterative geometric pose estimation algorithm which does marker-based single camera tracking and is therefore completely autonomous. Multiple PTrack units successively extend the tracking range of the system. For a smooth transition of tracked labels from one camera to another, camera range areas must overlap to form a contiguous tracking space. A PTrack Sensor Fusion Module then computes the pose of a certain label within tracking space and forwards it to interested applications. A universal test setup for optical tracking systems has been built allowing to measure translational and rotational accuracy of PTrack as well as of competing systems.

A real-time low-cost marker-based multiple camera tracking solution for virtual reality applications

Optical motion tracking systems are widely employed in virtual- and mixed reality applications enabling users to directly interact with 3D space. Important efforts have been made to make such technologies available to a larger group of users by significantly reducing their deployment costs. In this poster we introduce the result of a German-Brazilian cooperation: The first commercial low-cost marker-based optical tracking system developed in South-America. Despite using cheaper technologies and being low-cost which usually imply worse performance and accuracy, we developed a system with sufficient accuracy for professional use. There have been significant research efforts to develop cheaper tracking devices to provide interaction capabilities in virutal- and mixed reality. The Augmented Reality Tool Kit (ARToolkit) [1] is a good example of a very popular low-cost academic optical tracker working with any type of webcam. As a non-academic example of affordable tracking systems, Nintendo's latest video game console (Nintendo Wii) comes with the Wiimote interaction device containing a built-in motion tracker that allows for immersive interaction metaphors in home environments. However, most such available low-cost solutions lack in suitability for professional applications due to their usually insufficient accuracy, tracking range or latency time. The starting point of this project was PTrack [2], an academic marker-based single-camera tracker developed at Fraunhofer IGD. PTrack development has shown that an accurate optical tracking system can be built from components that are affordable for a much wider group of users, from the academic AR/VR community to companies’ developers. The performance and accuracy of PTrack were assessed through a comprehensive set of experiments which have proved the suitability of the system for professional applications. One of the main topics raised by PTrack as further research was an extension of the system into a multiple stereo camera configuration, which led to the present work.

BraTrack: a low-cost marker-based optical stereo tracking system

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 3D 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.

Alexandre Buaes

Papers

PTrack: Introducing a Novel Iterative Geometric Pose Estimation for a Marker-based Single Camera Tracking System

A real-time low-cost marker-based multiple camera tracking solution for virtual reality applications

BraTrack: a low-cost marker-based optical stereo tracking system

Innovative geometric pose reconstruction for marker-based single camera tracking