Graphtracker: A topology projection invariant optical tracker

Smit, F. A.; Rhijn, Arjen van; Liere, Robert van

doi:10.1016/j.cag.2006.09.004

Cited by 8 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In practice however further filtering must be performed since interfering lights can have a similar size as the target’s IR-LED blobs. Based on approaches [ 54 , 57 , 58 , 59 ], a 2D Model Fitting within the set of remaining blob candidates is performed. Therefore, the

-Invariants of the blob candidates as well as their collinear properties are computed and compared to the pre-calculated target model.…”

Section: Methodsmentioning

confidence: 99%

Robust 3D Position Estimation in Wide and Unconstrained Indoor Environments

Mossel

2015

Sensors

View full text Add to dashboard Cite

In this paper, a system for 3D position estimation in wide, unconstrained indoor environments is presented that employs infrared optical outside-in tracking of rigid-body targets with a stereo camera rig. To overcome limitations of state-of-the-art optical tracking systems, a pipeline for robust target identification and 3D point reconstruction has been investigated that enables camera calibration and tracking in environments with poor illumination, static and moving ambient light sources, occlusions and harsh conditions, such as fog. For evaluation, the system has been successfully applied in three different wide and unconstrained indoor environments, (1) user tracking for virtual and augmented reality applications, (2) handheld target tracking for tunneling and (3) machine guidance for mining. The results of each use case are discussed to embed the presented approach into a larger technological and application context. The experimental results demonstrate the system’s capabilities to track targets up to 100 m. Comparing the proposed approach to prior art in optical tracking in terms of range coverage and accuracy, it significantly extends the available tracking range, while only requiring two cameras and providing a relative 3D point accuracy with sub-centimeter deviation up to 30 m and low-centimeter deviation up to 100 m.

show abstract

-Invariants of the blob candidates as well as their collinear properties are computed and compared to the pre-calculated target model.…”

Section: Methodsmentioning

confidence: 99%

Robust 3D Position Estimation in Wide and Unconstrained Indoor Environments

Mossel

2015

Sensors

View full text Add to dashboard Cite

show abstract

“…By combining the approaches [41,39,37,30], we perform a two-dimensional Model Fitting within the set of re- maining blob candidates. Thereby, we exploit the permutation and perspective invariant properties of our target.…”

Section: Interference-filter Pipelinementioning

confidence: 99%

Vision-Based Long-Range 3D Tracking, applied to Underground Surveying Tasks

Mossel

Gerstweiler

Vonach

et al. 2014

Journal of Applied Geodesy

View full text Add to dashboard Cite

To address the need of highly automated positioning systems in underground construction, we present a long-range 3D tracking system based on infrared optical markers. It provides continuous 3D position estimation of static or kinematic targets with low latency over a tracking volume of m x m x m (width x height x depth). Over the entire volume, relative 3D point accuracy with a maximal deviation ≤ mm is ensured with possible target rotations of yaw, pitch = − • and roll = − • . No preliminary sighting of target(s) is necessary since the system automatically locks onto a target without user intervention and autonomously starts tracking as soon as a target is within the view of the system. The proposed system needs a minimal hardware setup, consisting of two machine vision cameras and a standard workstation for data processing. This allows for quick installation with minimal disturbance of construction work. The data processing pipeline ensures camera calibration and tracking during on-going underground activities. Tests in real underground scenarios prove the system's capabilities to act as 3D position measurement platform for multiple underground tasks that require long range, low latency and high accuracy. Those tasks include simultaneously tracking of personnel, machines or robots.

show abstract

“…In the case of the proposed algorithm, we have used two techniques employed in pattern recognition, here applied in the implementation of marker pattern matching in an optical tracking system. These two techniques on which the algorithm is based are the theory about projective invariant properties described in [3], [8], [10] and the "divide and conquer" strategy exemplified by the use of a quadtree to segment an image where the leaves will be the image coordinates of the markers, which are spread over the image.…”

Section: Related Workmentioning

confidence: 99%

A Novel Optical Tracking Algorithm for Point-Based Projective Invariant Marker Patterns

Loaiza

Raposo

Gattass

Advances in Visual Computing

View full text Add to dashboard Cite

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.

show abstract

Graphtracker: A topology projection invariant optical tracker

Abstract: In this paper, we describe a new optical tracking algorithm for pose estimation of interaction devices in virtual

Cited by 8 publications

References 19 publications

Robust 3D Position Estimation in Wide and Unconstrained Indoor Environments

Robust 3D Position Estimation in Wide and Unconstrained Indoor Environments

Vision-Based Long-Range 3D Tracking, applied to Underground Surveying Tasks

A Novel Optical Tracking Algorithm for Point-Based Projective Invariant Marker Patterns

Contact Info

Product

Resources

About