thank you sir for guiding me. It will be helpful in my project. I will be glad if you can do the same after I start working more on open CV. Thanks again, great work.
Yesterday, Jeff pointed me to an application Eric has worked in, a dice counter using a dual-core processor from Analog Devices, I'd like to ask, was the two cores feature of the processor a key to the project? Also, if possible, did you use OpenCV for that application?
Early next year we are hopnig to publish a white paper describing the process of developing this demo. It will appear on the Embedded Vision Alliance web site. For today I'll just point out that the ADI chip actually has three cores: two Blackfin CPU/DSP cores and one "PVP" coprocessor for vision tasks.
Yesterday, Jeff pointed me to an application Eric has worked in, a dice counter using a dual-core processor from Analog Devices, I'd like to ask, was the two cores feature of the processor a key to the project? Also, if possible, did you use OpenCV for that application?
Thanks, everyone for attending this class series. I hope you found it wortwhile. For additional (free) embedded vision educational resources, including discussion forums, please visit the Embedded Vision Alliance at www.Embedded-Vision.com.
ok, Qt creator has other parts like linguist and designer, so I want to work in that with using of camera , so which of them should I use or you cant tell more about Qt?
Kind of levels the "multi-core" playing field, brings back an element of "portable". Haven't really played with it enough to judge it, but thought I'd mention it as YOU are much more likely to find good use for it.
Yesterday, Jeff pointed me to an application Eric has worked in, a dice counter using a dual-core processor from Analog Devices, I'd like to ask, was the two cores feature of the processor a key to the project? Also, if possible, did you use OpenCV for that application?
As far as I know, OpenCV is not officially supported by NI in LabView, but there are third-party tutorials and I believe even one third-party software package for this purpose.
@Eric: I remember your using the term "haar" features (as in "haarcascade") in the lecture, but didn't see it on the slides. Is it an acronym, and if so, what for?
I'd also like to recommend the discussion forums on the Embedded Vision Alliance website for ongoing questions such as the ones that have been asked this week:
http://www.embedded-vision.com/forums
Jeff, Eric and I all regularly monitor it, as do other BDTI engineers and (more generally) the site visitor/user community at large
Hope you're feeling better by next week... Now anybody giving transportation-funding grants?? Orlando-to-Boston not TOO bad, but more than I can swing...
Yeah, GPS, accelerometer, etc -- but if you HAVE a camera in operation, you could do a "compare delta" to make sure everything is approximately sane.
flared0one, might be easier to use GPS. accelerometer, etc to asertain velocity ;-) But ADAS (advanced driver assistance systems) use cameras for lots of purposes...including reading speed limit signs as you pass by them and telling you if you're going too fast ;-)
So if I was using a video camera in a car, I could actually do something VERY similar to how a laser mouse works -- [A] find the CURRENT visual features, compare to the LAST set of features, determine how things moved, add any NEW "best features to use", then loop back to [A]... if you have a calibrated imager, you could conceivably track your changing location, determine your velocity, etc -- just like a car-sized mouse... LOL.
If I remember from my Robotic Vision course, the detection algorithm was referred to as an "Expert" system, and each of the "A, B, C, D" feature types were referred to as individual "experts". And if you started with a wide range of random "features", you could figure out over time (while generating that "cascade", approximately) which features didn't matter, which ones to keep and use.
Ah, good clarification -- glad it IS working for you. Thought you were groaning that the update seemed to break stuff.
flared0one, what I meant is that Chrome is working fine for me, even with the latest Flash plugin installed, whereas it seems that Firefox and Safari folks need to downgrade to an older Flash version in order to have audio success
Face detection/recogition is a challenging problem to solve ;-) Android 4.x includes built-in face recognition support for homescreen unlock purposes, and Google claims that it works even with glasses on, but my personal testing results have been hit-and-miss
Oddly, Chrome (at least my copy, on Mac OS X) seems to have the latest Adobe Flash plugin version pre-installed. So it doesn't seem to specifically be the Flash plugin, per se, versus an odd browser-specific interaction
I made the mistake of letting Adobe Flash install an update, not no audio. My IE is not configured, so I guess I'll have to wait to view the archive later....
We haven't tried the Virtualbox virtual machine manager product, but it's open source and free. Formerly a Sun product, now owned by Oracle. I believe, but am not positive, that it will import VMware virtual machines
Sr. Architect, Embedded Industry with a focus on Automotive, Retail, Industrial Manufacturing, and Robotics. Working on multiple vision applications (though new to all of this).
For those of you just joining us, please let us know your job title, the industry you're working in, and the vision applications you're working on or thinking about working on.
If you're having audio issues, please note that some companies block live audio streams. If you don't hear any audio, try refreshing your browser. The show will be archived and available on this page.
Seems like open source is a LITTLE bit more likely to have ongoing conversational access to generic "support" (in most cases its worth much more than what I'm paying for it).
Linux in the machine. Combination of Windows and Linux on our workstations. We use various graphics packages. In general, we have no issues with using open source software.
Hi Everyone. Just want to clrarify one thing: The classroom page says that I am the presenter for today. That is incorrect. Eric will be the presenter today.
Industry: Guided Wave RADAR tank level Gauges for the tank truck industry
Vision apps: only personal interest. will be starting at ground level with an Arduino based frame grabber on breadboard with open source libraries. a simple ciucuit that also overlays MCU generated video back onto the live video.
The streaming audio player will appear on this web page when the show starts at 2pm eastern today. Note however that some companies block live audio streams. If when the show starts you don't hear any audio, try refreshing your browser.
For 3D printing to make the jump from rapid prototyping to manufacturing, engineers will need to find easier ways to move products from their CAD screens to their printers.
Gigabit and PoE are two networking technologies moving ahead in tandem as industrial users power remote Ethernet devices such as IP security cameras at 1,000 Mbps over existing CAT5 cable.
New versions of BASF's Ecovio line are both compostable and designed for either injection molding or thermoforming. These combinations are becoming more common for the single-use bioplastics used in food service and food packaging applications, but are still not widely available.
From Dell / Intel® New Paradigms in Design Work Scott Hamilton, vertical market strategist for Dell Precision workstations, 5/2/2013 5
Early in my career, I worked as a draftsman and remember the days of drawing on vellum with numbered pencils and Mylar with plastic lead. This was a fun experience in the sense that I ...
I've been using workstations for more than 10 years and love finding ways to get more performance from my system. With demanding professional applications that require more power each ...
A lasting memory from my first job as an engineer in an auto assembly plant is standing on hard concrete at six in the morning, vending-machine coffee clutched in hand, listening to ...
For industrial control applications, or even a simple assembly line, that machine can go almost 24/7 without a break. But what happens when the task is a little more complex? That’s where the “smart” machine would come in. The smart machine is one that has some simple (or complex in some cases) processing capability to be able to adapt to changing conditions. Such machines are suited for a host of applications, including automotive, aerospace, defense, medical, computers and electronics, telecommunications, consumer goods, and so on. This radio show will show what’s possible with smart machines, and what tradeoffs need to be made to implement such a solution.
To save this item to your list of favorite Design News content so you can find it later in your Profile page, click the "Save It" button next to the item.
If you found this interesting or useful, please use the links to the services below to share it with other readers. You will need a free account with each service to share an item via that service.
Tweet This
2 
