There is a lot happening this week at CES. The awards are already rolling in and the Consumer Electronics Association (CEA) had its 2012 Design and Engineering Awards Honorees displayed Sunday night at a CES press event. One of the honorees, in the Software & Mobile Apps category, was Picitup for its computer vision (CV) based driving safety app, iOnRoad. We know these folks pretty well and we were psyched when they downloaded the FastCV™ SDK, quickly incorporated it into iOnRoad and significantly upped the performance.
So congratulations to all the hard-working folks at Picitup from Qualcomm!
What’s FastCV and why does it matter? Before FastCV, there were no mobile-optimized computer vision functions available to developers. With FastCV, some pretty remarkable things are possible. Picitup’s head of software, Ram Dayan, told us, “We had never seen such a jump in performance as with FastCV. It usually takes weeks of work to get the kind of performance improvement we saw within a couple days of integrating FastCV.”
What was that improvement? Well, for image conversion, it was a whopping 30%. Overall performance improvement, according to Ram, was 10-15% for the entire algorithm.
Designed for efficiency on all ARM-based processors, FastCV offers the most widely used, computationally intensive vision processing APIs, with hardware acceleration and better performance on mobile devices. FastCV is designed for developers interested in creating sophisticated CV apps, as well as CV middleware developers looking to build the frameworks necessary for everyday developers to include computer vision functionality in their apps. The FastCV SDK is available for download.
I hope those of you who decided to brave CES this year have a great show. If you run across the Picitup guys, add your congratulations to ours. They did some really impressive work, really quickly and we are glad the CEA recognized their efforts.