100 Days Of ML Code — Day 039

100 Days Of ML Code — Day 039

Recap From Day 038

In day 038, we got started with video features. We learned that “Tracking objects based on color is one of the quickest and easiest methods for tracking an object from one image frame to the next. The speed of this technique makes it very attractive for near-realtime applications but due to its simplicity many issues exist that can cause the tracking to fail.”

Today, we will continue from where we left off in day 038.

Video Features Continued

Fiducials

“Fiducial is an object placed in the field of view of an imaging system which appears in the image produced, for use as a point of reference or a measure. It may be either something placed into or on the imaging subject, or a mark or set of marks in the reticle of an optical instrument.”

In computer vision, a fiducial marker is a known object which can be easily identified. If we want really accurate object tracking, an alternative is to use fiducials, symbols that are designed specifically to be easily tracked by a camera system.

[Source](https://cdn.hashnode.com/res/hashnode/image/upload/v1632827168479/wXpMGigw0.png)Source

The image above shows a set of fiducials from the reacTIVission project. reacTIVision is an open source, cross-platform computer vision framework for the fast and robust tracking of fiducial markers attached onto physical objects, as well as for multi-touch finger tracking. It was mainly designed as a toolkit for the rapid development of table-based tangible user interfaces (TUI) and multi-touch interactive surfaces.

If we download one of their software libraries and incorporate it into our project, it’s quite easy to get information about which of the shapes in the image above is present in front of a camera, where they are, and how they’re rotated. If we don’t mind sticking one of the funny-looking shapes from the image above onto something, we can track it pretty accurately.

It’s good to know that you’re still here. We’ve come to the end of day 039. I hope you found this informative. Thank you for taking time out of your schedule and allowing me to be your guide on this journey. And until next time, remain legendary.

Reference

*https://www.kadenze.com/courses/machine-learning-for-musicians-and-artists-v/sessions/sensors-and-features-generating-useful-inputs-for-machine-learning*

*http://reactivision.sourceforge.net/*

*https://en.wikipedia.org/wiki/Fiducial_marker*