[Joseph DeGol]

ChromaTag: A Colored Marker and Fast Detection Algorithm

Joseph DeGol, Timothy Bretl, Derek Hoiem

2017 IEEE International Conference on Computer Vision (ICCV '17)






Current fiducial marker detection algorithms rely on marker IDs for false positive rejection. Time is wasted on potential detections that will eventually be rejected as false positives. We introduce ChromaTag, a fiducial marker and detection algorithm designed to use opponent colors to limit and quickly reject initial false detections and gray scale for precise localization. Through experiments, we show that ChromaTag is significantly faster than current fiducial markers while achieving similar or better detection accuracy. We also show how tag size and viewing direction effect detection accuracy. 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.


ChromaTags are based on the tag families created by Olson et. al. for AprilTag. An example AprilTag from the 16H5 family is shown below in (1). The grid spaces are white or black to embed a binary code (2). For ChromaTag, we reassign the 4 inner squares to two shades of red and the outer grid squares to two shades of green (3). This results in a ChromaTag (4).

1. Example 16H5 AprilTag

2. Code Grid

3. Assign Colors

4. Example 16H5 ChromaTag

For this paper, we used the 16H5 family to create ChromaTags. These tags can be downloaded below. The tags are 800x800 pixels in size. Note that the color of the downloaded tags look different than those on this website. This is because the colors of the tags were optimized for printing with a generic home printer. When printed, the colors should look like those shown in the paper.

Download ChromaTag 16H5


Source code coming soon ... !

  author    = {Joseph DeGol and Timothy Bretl and Derek Hoiem},
  title     = {ChromaTag: A Colored Marker and Fast Detection Algorithm},
  booktitle = {ICCV},
  year      = {2017}

Last Updated: 8/10/17