Extendible object-centric tracking for augmented reality

Neumann, Ulrich; Park, J.

doi:10.1109/vrais.1998.658482

Cited by 21 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Today, it is required for making annotation onto newly discovered knowledge from data mining for effectively researches (3), (4) . Taking these into account, we can consider that the annotation function is very useful and important in CVE to promote better understanding.…”

Section: Hybridp2p-based Cvementioning

confidence: 99%

Scientific Visualization in Collaborative Virtual Environment with PDA-Based Control and 3D Annotation

Kukimoto

Nonaka

Ebara

et al. 2005

JSME international journal. Ser. B, Fluids and thermal engineer

View full text Add to dashboard Cite

Scientific collaborative visualization based on visual data mining is an efficient approach for facilitating the intellectual discovery and understanding the visualization data obtained from large-scale ata sets. We think that Collaborative Virtual Environment (CVE) is one of the efficient method to achieve collaborative works by sharing a virtual reality 3D space among users at remote places. In addition, it would be more useful if we could use virtual 3D annotations during collaborative work. In this paper, therefore, we construct a HybridP2P-based CVE in which a wireless handheld PDA is used for making 3D annotations and changing some visualization parameters when necessary.

show abstract

Section: Hybridp2p-based Cvementioning

confidence: 99%

Scientific Visualization in Collaborative Virtual Environment with PDA-Based Control and 3D Annotation

Kukimoto

Nonaka

Ebara

et al. 2005

JSME international journal. Ser. B, Fluids and thermal engineer

View full text Add to dashboard Cite

show abstract

“…They are defined by a 2D screen position p and a type g that encodes characteristics such as colour and shape. Our fiducial design is a coloured circle or triangle [19,25], but other designs such as concentric circles or coded squares are equally valid [9,12,24,34]. We use the three primary and three secondary colours along with the triangle and circle shapes to provide 12 unique fiducial types.…”

Section: Segmentation and Feature Detectionmentioning

confidence: 99%

“…These applications are particularly suited to wearable computers because of the mobility afforded to the user. A more appropriate tracking solution for these highly mobile applications is one that is objectcentric, or in other words, based on viewing the object itself [1,[18][19][20][21][22][23][24][25]. Such tracking is possible with the pose estimation methods developed in the fields of computer vision and photogrammetry [26,27].…”

Section: Introductionmentioning

confidence: 99%

Tracking for augmented reality on wearable computers

Neumann

Park

1998

Virtual Reality

Self Cite

View full text Add to dashboard Cite

Wearable computers afford a degree of mobility that makes tracking for augmented reality difficult. This paper presents a novel object-centric tracking architecture for presenting augmented reality media in spatial relationships to objects, regardless of the objects' positions or motions in the world. The advance this system provides is the ability to sense and integrate new features into its tracking database, thereby extending the tracking region automatically. A "lazy evaluation" of the structure from motior problem uses images obtained from a single calibrated moving camera and applies recursive filtering to identify and estimate the 3D positions of new features. We evaluate the performance of two filters; a classic Extended Kalman Filter (EKF) and a filter based on a RecursivenAverage of Covariances (RAC). Some implementation issues and results are discussed in conclusion.

show abstract

“…Much previous image-based research into methods for aligning video images of real environments and annotation information has relied on the use of artificial markers (fiducials) that identify locations within the actual environment; by detecting the location of such markers within a video sequence the camera position and orientation can be estimated [3][4][5]. However, since such methods require markers to be physically associated with each object that is to be annotated, they struggle to provide coverage for large environments.…”

Section: Introductionmentioning

confidence: 99%

A method and real-time implementation for annotating broadcast video images based on alignment with a set of panoramic images

Kourogi

Kurata

Sakaue

et al. 2006

Electron. Comm. Jpn. Pt. III

View full text Add to dashboard Cite

SUMMARYIn this paper we propose a panorama-based annotation scheme for superimposing annotation information on broadcast video images by using a set of panoramic images, annotation information for each image and the adjacency relations between these images as information sources. The proposed method aligns an input video sequence with a set of panoramic reference images and displays annotation information on those parts of the video image that correspond to locations annotated in these panoramic images. The method first aligns locations on each of the panoramic images with those in the input video sequence and then selects that panoramic image that was taken from the position that is closest to that of the input image and uses this as a reference for annotation. The method uses mean squared error (MSE) of pixel intensities between the two images as a criterion for alignment. Annotation information is then displayed based on the alignment results with the selected panoramic image. In order to display annotation information appropriately when the camera viewpoint moves, we perform alignment of the input image with the panoramic images that are adjacent to the reference image in parallel, and switch over to another panoramic image taking it as the new reference image if this gives better alignment results than the current reference image. By monitoring the progress of such changeovers between images we can estimate the trajectory of the camera and its position. We have implemented the proposed method on a computer system and obtained favorable results regarding its effectiveness and the suitability of the method to realtime processing.

show abstract

Extendible object-centric tracking for augmented reality

Cited by 21 publications

References 32 publications

Scientific Visualization in Collaborative Virtual Environment with PDA-Based Control and 3D Annotation

Scientific Visualization in Collaborative Virtual Environment with PDA-Based Control and 3D Annotation

Tracking for augmented reality on wearable computers

A method and real-time implementation for annotating broadcast video images based on alignment with a set of panoramic images

Contact Info

Product

Resources

About