Slashdot Mirror

← Back to Stories (view on slashdot.org)

Firmware Hack Allows Video Analysis On a Canon Camera

Posted by timothy on from the turn-your-family-green-with-envy dept.

An anonymous reader writes "Researchers from the University of Liege in Belgium have been able to perform real-time video analysis on a regular Canon digicam (video link) without any hardware modification. The results are shown directly on the digicam's screen. They use a hacked version of a popular open-source alternative firmware for Canon cameras: CHDK. This is a proof-of-concept that computer vision algorithms can now be embedded on regular Canon digicams with little effort (CHDK is coded in C). What other popular vision algorithms could be implemented? For what purpose?" You can get some idea about ViBe from this abstract at IEEE; basically, it allows background extraction in moving images.

4 of 115 comments (clear)

  1. CHDK by The+MAZZTer · · Score: 4, Informative

    I use CHDK on my own Canon PowerShot. Good stuff.

    1. Re: CHDK by Anonymous Coward · · Score: 4, Funny

      What's the 'newest' Camera that supports CHDK? Mine got stolen recently and I'd like something to replace it for times I don't want to lug around my SLR.

      I'm interested by that too as I've recently "acquired" a new camera.

  2. Not alternative firmware by marcansoft · · Score: 5, Informative

    It's worth pointing out that CHDK isn't a hacked firmware (that would probably not be legally redistributable), nor is it an alternative firmware (that would be too much work). CHDK is an add-on to the existing firmware, that works by piggibacking on its OS, hooking functions, and spawning off extra processes on the camera's RTOS. This is what makes it so great: you get the original funcionality of the camera plus extra stuff, and you don't have to wait for the developers to add what already came with your camera anyway.

  3. Re:Interesting... by timeOday · · Score: 4, Insightful

    The most computationally demanding onboard processing I've noticed (aside from video encoding, which surely uses a dedicated chip) is recognizing multiple faces in real-time, or tracking a moving object, to maintain focus. Far from the gimmicks you mention, these are very useful functions that just happen to require what amounts to video processing.