Search

Virtual Reality (VR) technology has become cheaper over time and makes it possible to own. However, interaction techniques in VR need to be natural as possible to be accepted by users. Compared to other computing devices (e.g., mobile and desktop), there is very few human-computer interactions (HCI) paradigms in VR and a lot of HCI issues and problems are yet to be solved. In this paper, we present a VR Welding Kit, a virtual reality welding training simulation developed for mobile smartphones using multiple marker images as an interaction method. The experimental results have revealed with comparison benchmark with high-end VR device, Oculus Quest to see the efficiency of multiple marker interaction with a current VR technology device. System Usability Scales (SUS) also used to see the acceptance between users with this new interaction. This is the first evaluation of combination VR with marker-based tracking method interaction. Simulator Sickness Questionnaire (SSQ) are used to check the cybersickness between participants toward multiple marker interaction. The results on performance shows that mobile VR have a large gap completion compared with Oculus Quest. The SUS score is 73.33, above 68 which is great. SSQ surveys result shows that participant almost feels none in simulation sickness.

Many real world applications for Microsoft HoloLens*-based applications suffer the problem of reliably recognizing and identifying movable objects within an environment. While the HoloLens is perfectly able to discern already known rooms, it still has troubles with reflecting surfaces or identically shaped objects. Using dedicated recognition libraries for each task poses the issue of shared resource access in the rather controlled HoloLens environment-In this poster we present a solution for scenario with hard to track objects and similarly shaped objects for an electrical cabinet assembly task, where the reflective cabinet is tagged with a marker and the prefabricated cables are differentiated by text-based labels.

Evaluation of robotic experiments requires physical robots as well as position sensing systems. Accurate systems detecting sufficiently all necessary degrees of freedom, like the famous Vicon system, are commonly too expensive. Therefore, we target an economical multi-camera based solution by following these three requirements: Using multiple cameras to track even large laboratory areas, applying fiducial marker trackers for pose identification, and fuse tracking hypothesis resulting from multiple cameras via extended Kalman filter (i.e. ROS's robot\_localization). While the registration of a multi-camera system for collaborative tracking remains a challenging issue, the contribution of this paper is as follows: We introduce the framework of Cognitive Interaction Tracking (CITrack). Then, common fiducial marker tracking systems (ARToolKit, AprilTag, ArUco) are compared with respect to their maintainability. Lastly, a graph-based camera registration approach in SE(3), using the fiducial marker tracking in a multi-camera setup, is presented and evaluated.

Marker-based measurement has been used to assess human body positioning, but human marker tracking has yet to make the transition from the laboratory to personal computing devices, such as smartphones. A novel smartphone-based approach could use a fiducial marker system. Fiducial markers are applicable to augmented reality, robotics, and other applications where a camera-object pose is required and tracked. However, few fiducial systems can be implemented on a mobile phone because of the processing requirements for identifying and tracking the tags in realtime. In augmented reality, virtual information is shared with the real world to further enhance a person’s view of the environment; therefore, this illusion is directly associated with good registration of both virtual and real worlds. Measurement applications also require accurate and fast registration so that real objects are in alignment with virtual objects in real-time. Our research reviewed and evaluated various fiducial marker systems by developing an Android mobile application for real-time biomechanical measurement. A test was designed for two nominated fiducial systems to compare their speed and robustness on the mobile phone. AprilTag2 was selected as the best fiducial marker option for this application.

Speeding-up of computational capabilities has greatly augmented the capture accuracy of motion pictures. That technology has been widely applied in the field of entertainment, sports, public welfare, and medical services. Today, motion capture has general versatility for its marker tracking technology. However, it is possible that marker tracking accuracy depends on the measurement. This paper describes assessment of capture accuracy for different configurations of measurements.

Videofluoroscopy (VF) is one of the most commonly used tools to assess oropharyngeal dysphagia as well as to visualize musculoskeletal structures of humans and animals engaged in various behaviors, including feeding. Despite its importance in clinical and scientific use, processing VF data has historically been extremely tedious because it is performed using manual frame-by-frame methods. With recent technological advances, the frame rate for scientific use has been increasing along with the use of high speed data capture systems. In the current study, we used non-human primates as a model animal to study human feeding behaviors to capture tongue movement based on markers implanted into the tongue. Here, we introduce a semi-automatic marker tracking algorithm that yields high tracking accuracy (> 90%) and dramatic speed improvements (faster than real time labeling). Furthermore, we quantify the sources of tracking errors and the tracking performance as a function of marker speeds. Our results indicate that there is more room for methodological improvements both in detection and prediction of marker positions. Moreover, correspondingly faster frame rates will be required to capture faster kinematic behaviors such as those of mice, which are extensively used to study both control and pathological conditions.

Augmented Reality (AR) is a great partner of Edutainment in motivating students and enriching a class. Students can check out additional digital information of physical items such as books, samples, exhibits or even sites. The information looks just like existing in the reality. In addition to a show of multimedia content, we opine that if the virtual objects augmented to the reality can act and react like real objects, the learning experience can be greatly promoted. We developed an AR system in that the virtual objects can interact with each others. We implemented several applications using the system to demonstrate the use of interactive AR in edutainment. We also attempted to resolve the limitation of image angle coming with vision-based AR by building a multi-marker mechanism using a cube structure with surface area approximation. We also discussed some challenges and issues that researchers or developers should take note of in pursuing AR development.

In this paper, we present an AR framework that allows natural hand and tangible AR interaction for physically-based interaction and environment awareness to support face-to-face collaboration using Microsoft Kinect. Our framework comprises of six major components: (1) marker tracking (2) depth acquisition (3) image processing (4) physics simulation (5) communication and (6) rendering. The resulting augmented environment supports occlusion, shadows, and physically-based interaction of real and virtual objects. We propose three methods of natural hand representations including mesh-based, direct sphere substitution and variational optical flow. A tabletop racing game and AR Sandbox applications are created based on this framework, showing the application possibilities. Refereed/Peer-reviewed

This paper describes the concept of a dynamic blocks platform, called ARBlocks, based on projective augmented reality and tangible user interfaces aiming educational activities. In it, the information is displayed by projectors, that exhibit the content only on the blocks using a projector calibration technique and the blocks are tracked through a frame marker. Despite the platform is still under development, some results regarding the frame marker tracking and the projection was achieved.

In this study, we investigated the mechanical properties of porcine aortic sinus using a three-dimensional marker measuring technique called the direct linear transformation (DLT) method. By recording pressure-inflation tests of five porcine aortic roots with the use of two cameras simultaneously, we were able to obtain stress and strain responses of aortic sinus upon applied luminal pressures and compare them with previously published planar biaxial results of the same tissue. We found that the roots were stiffer in the circumferential direction for the middle region of the non-coronary sinus for all specimens. The magnitude of stress at 30% strain was higher than that observed using planar biaxial testing.

We present an overview on the history of tracking for mobile phone Augmented Reality. We present popular approaches using marker tracking, natural feature tracking or offloading to nearby servers. We then outline likely future work.

Typical tasks of learning groups and knowledge workers include working both with printed and digital documents. We present a pen-based and tangible interaction concept for the linking and tagging of documents in a mixed physical and digital environment. The interaction with printed and electronic documents is unified. We therefore use digital pens, which equally capture physical handwriting on real paper and act as an input device on a specific screen prototype. Links and tags can have variable scopes ranging from small document passages to a collection of several documents. Physical folders along with camera-based marker tracking provide for the tangible definition of document collections. Tags are intuitively defined on a paper tag menu card. We present two visualizations of links and tags (a document-centered viewer and a hyperstructure-centered graph view). These are closely coupled with the physical environment.

Marker tracking has revolutionized augmented reality about a decade ago. However, this revolution came at the expense of visual clutter. In this paper, we propose several new marker techniques, which are less obtrusive than the usual black and white squares. Furthermore, we report methods that allow tracking beyond the visibility of these markers further improving robustness. All presented techniques are implemented in a single tracking library, are highly efficient in their memory and CPU usage and run at interactive frame rates on mobile phones.

In this paper, we propose a new tracking system based on invisible markers using the image watermarking technique for augmented reality. Markers are invisibly embedded into image or video contents and then it is extracted from the scene image acquired by a general camera. Our method has the advantages of the marker-based methods and the marker-less methods at the same time without additional hardware.

This paper presents an active vision based space-positioning robot (AVBSPR) for surgical navigation applications. The development of the proposed navigation robot consists of a five-axis SCROBOT-ER VII Robot, a stereoscopic based eye-in-hand image capture module and a set of infrared (IR) based surgical marker emitters. To increase the navigation space and to determine the best image capture orientation, a fuzzy inference engine is constructed to dynamically track the moving surgical markers. On the other hand, the stereoscopic image coordinates are used to calculate the 3D space coordinates of the surgical markers for surgical navigation applications. Finally, a prototype system had been implemented, and several experimental tests had been done. The experimental results showed that the robot tracks the surgical markers well, and the positioning error is around 5 mm within 2000 mm distance operating ranges.

We introduce a novel tracking system based on invisible markers which are created/drawn with an IR fluorescent pen. The tracking system consists of one scene camera, one IR camera, and one half mirror. The two cameras are positioned in each side of half mirror so that their optical centers coincide with each other. We track the invisible markers using the IR camera and visualize AR in the view of the scene camera. Thus, it works as a robust marker-less tracking system. Experimental results are given to demonstrate the viability of the proposed system.

Optical tracking with fiducial markers is commonly used in Augmented Reality (AR) systems. AR systems that rely on the ARToolKit [Marker Tracking and HMD Calibration for a Video-based Augmented Reality Conferencing System] are prominent examples. The information obtained by the tracking subsystem are widely used in AR, e.g. in order to calculate how virtual objects should be located and oriented. The results of extensive accuracy experiments with single markers are reported and made operational by the definition of an accuracy function. The results show a specific distribution of tracking accuracy dependent on distance as well as angle between camera and marker. This insight is applicable for designing the set-up of AR applications in general that rely on optical tracking.

We have developed ARLINER an observation system to register virtual property lines on a TV monitor at an unmanned dam construction site. The system tracks markers set at regular intervals on the baseline of the site in the input image, calculates the camera parameters from the positions of the detected markers, and registers the property lines in association with the camera motion. We describe the conditions of application at the construction, marker tracking, the registration algorithm for property lines, and practical operation using the system at a dam construction site.