ChromaTag: A Colored Marker and Fast Detection Algorithm

@article{DeGol2017ChromaTagAC,
  title={ChromaTag: A Colored Marker and Fast Detection Algorithm},
  author={Joseph DeGol and Timothy Bretl and Derek Hoiem},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={1481-1490}
}
Current fiducial marker detection algorithms rely on marker IDs for false positive rejection. [] Key Result Our contribution is significant because fiducial markers are often used in real-time applications (e.g. marker assisted robot navigation) where heavy computation is required by other parts of the system.
Efficient and Robust Circle Grids for Fiducial Detection
TLDR
A new marker coding system design based on 3 × 3 grids of individual circles based on a novel way of composing individual fiducial tags into larger grids that enables the use of larger markers without adapting the detection pipeline, resulting in additional occlusion resistance and error detection.
LiDARTag: A Real-Time Fiducial Tag System for Point Clouds
TLDR
LiDARTag, a novel fiducial tag design and detection algorithm suitable for light detection and ranging (LiDAR) point clouds, is introduced and it is confirmed that the proposed method can reliably provide a tag's pose and unique ID code.
Improved Structure from Motion Using Fiducial Marker Matching
In this paper, we present an incremental structure from motion (SfM) algorithm that significantly outperforms existing algorithms when fiducial markers are present in the scene, and that matches the
ArUcoRSV: Robot Localisation Using Artificial Marker
TLDR
ArUcoRSV applies an automated perspective using marker detection, refining rejected marker and pose estimation, and produces accurate marker detection for robot identification and achieves significant improvements in detection rate with high positional accuracy.
DeepTag: A General Framework for Fiducial Marker Design and Detection
TLDR
A general deep learning based framework, DeepTag, for ducial marker design and detection and an effective procedure to synthesize training data on the y without manual annotations is proposed, which can easily adapt to existing and newly-designed marker families.
TopoTag: A Robust and Scalable Topological Fiducial Marker System
TLDR
Experiments on the dataset and real indoor and outdoor scene tests with a rolling shutter camera both show that TopoTag significantly outperforms previous fiducial marker systems in terms of various metrics, including detection accuracy, vertex jitter, pose jitter and accuracy.
An efficient, dense and long-range marker system for the guidance of the visually impaired
TLDR
The experiments show that the proposed bundle marker-vision algorithm outperforms the alternatives in terms of distance and angle and also that it is very robust to changes in lighting conditions, thus making it a good intelligent system for guiding people with visual impairments in their day to day use of public transportation systems.
DeepFormableTag: end-to-end generation and recognition of deformable fiducial markers
TLDR
This paper presents the captured results of 3D scanning using a 2D array of multiple fiducial markers as structured light patterns as well as motion tracking of human body motion using the authors' deformable markers.
Design and Implementation of a Pose Estimation System Based on Visual Fiducial Features and Multiple Cameras
TLDR
A pose estimation system based on visual fiducial features with multi-cameras is proposed to provide ground truth data for mobile robot indoor localization experiments and the validation result of 6 cm accuracy is achieved.
Fiducial marker-based Metric Initialization for Monocular SLAM
TLDR
The experimental results show that feature-based monocular SLAM can acquire metric scale and the world origin can be coordinated to the marker plane after initialization, and the scale outputs can reach centimeter accuracy with real-time performance in a normal computing unit.
...
...

References

SHOWING 1-10 OF 36 REFERENCES
AprilTag 2: Efficient and robust fiducial detection
  • John Wang, E. Olson
  • Computer Science
    2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2016
TLDR
This work describes AprilTag 2, a completely redesigned tag detector that improves robustness and efficiency compared to the original AprilTag system, and improves performance with higher detection rates, fewer false positives, and lower computational time.
ARTag, a fiducial marker system using digital techniques
  • M. Fiala
  • Computer Science
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
TLDR
This proposed new marker system, ARTag has very low and numerically quantifiable error rates, does not require a grey scale threshold as does other marker systems, and can encode up to 2002 different unique ID's with no need to store patterns.
Comparing ARTag and ARToolkit Plus fiducial marker systems
  • M. Fiala
  • Computer Science
    IEEE International Workshop on Haptic Audio Visual Environments and their Applications
  • 2005
TLDR
This paper compares the two recently developed systems ARTag and ARToolkit Plus on their reliability, detection rates, and immunity to lighting and occlusion.
On the Design and Evaluation of a Precise Scalable Fiducial Marker Framework
TLDR
This paper provides precise and robust full 3D pose estimation of the markers with superior accuracy when compared with many fiducial systems, while color information is used to provide more than \n{65000} distinct markers.
Maximum Detector Response Markers for SIFT and SURF
In this paper, we introduce optimal markers to be used with the SIFT and SURF feature detectors. They can be applied to trigger the detection of feature points at desired locations. Unlike
RUNE-Tag: A high accuracy fiducial marker with strong occlusion resilience
TLDR
This paper proposes a general purpose fiducial marker system that can be deemed to add some valuable features to the pack by exploiting the projective properties of a circular set of sizeable dots and proposes a detection algorithm that is highly accurate.
Reliable Fiducial Detection in Natural Scenes
TLDR
This paper shows why robustness to lighting, scale and foreshortening can be addressed within the machine learning framework with greater reliability than previous, more ad-hoc, fiducial detection schemes.
Fourier tags: Smoothly degradable fiducial markers for use in human-robot interaction
TLDR
The Fourier tag is a synthetic target akin to a bar-code that specifies multi-bit information which can be efficiently and robustly detected in an image.
Pi-Tag: a fast image-space marker design based on projective invariants
TLDR
This paper presents a general purpose fiducial marker system that performs both steps directly in image-space, and introduces a detection and recognition algorithm that is fast, accurate and moderately robust to occlusion.
...
...