You are currently browsing the tag archive for the ‘signal processing’ tag.

Strange things occur when things are suddenly switched on or off. It happens in signal processing all the time. The sudden application or removal of a signal sends shockwaves of infinite frequency through the system. Similarly, abrupt behavioral transitions during winter months can generate reverberations in our lives. More »


“Humans are fallible, and they often operate with half-formed intentions, based on incomplete information.”

– Steve Young, “Cognitive User Interfaces”, IEEE Signal Processing Magazine, May 2010

Taken out of context like this, it’s quite a poetic statement. The entire article is a pretty awesome read on how the user interfaces of the future will have to compensate for our own fallibility.

I uploaded two movies from my Kalman filtering project to my school section. In it, I use the matched filter to detect a moving ball and the Kalman filter to track and predict its movement. No code yet, probably within the next few days.

I don’t know how it happened, but from 12:30 onward was devoted entirely to the Kalman Filter and variants thereof. Be it the Extended Kalman Filter, Gaussian-Hermite Kalman Filter, spherical-simplex Kalman Filter, or just the plain ol’ Kalman Filter, this day overflowed with the stuff. This could be a good thing, I suppose, because I’m starting to understand them — for radars. The problem, however, is that I have to take my unique snowflake of a problem and apply a Kalman filter to it. Well, all I know is that it’s not getting done tonight because I’m going to bed.

While working full time I’m studying for my Master’s Degree in Electrical Engineering.  Work pays for classes so it’s a great deal, but man is it tiring.  The latest struggle is Kalman Filters.

Let’s start from the beginning.  I’m taking an advanced course in digital signal processing.  It’s been one of my favorite classes in this program — no midterms or finals, just a student created project.  So we go through the class learning different prediction techniques, working up towards the Kalman Filter and the Extended Kalman Filter, which aren’t impossible to understand.  But now that I have to apply one…well, we’ll see.


RSS Scrobbles

  • An error has occurred; the feed is probably down. Try again later.