Windows & .NET Watch: Prototyping with Processing



Email    print   
July 15, 2009 —  (Page 1 of 3)
Recently, I had a client who was interested in “augmented reality” applications. The phrase is used to describe applications that overlay computer-generated imagery on a heads-up display or, at least, a live video feed. This type of thing is old hat at ACM SIGGraph but still pretty radical for a consumer website marketing campaign.

Perhaps one day I’ll have one of those clients that says, “Take your time and let us know what you discover. We’re writing this development effort off as high-risk, high-payback research and development.” They’ll pay in pixie dust and give me rides on their flying horses. Until then, like most post-collegiate developers, I have to be careful about embarking on “interesting” programming projects.

In the case of augmented reality, success depends on recognizing targets within video frames. The targets take up relatively few pixels and have lower contrast and far more noise than in a reference photo. Even a plain vanilla video display eats up a significant amount of local resources, and in addition to finding the targets, you presumably have to, you know, do something with the information, such as reconstruct the spatial location of the targets, project that onto some model, and composite that into the output. And then you have to do it all over again in the next several dozen milliseconds.

If you are interested in video processing, you should probably begin with OpenCV and, if possible, combine it with Intel’s Integrated Performance Primitive libraries. Unfortunately, for various reasons this was inappropriate for my client’s application. Strangely, this actually lowered my risk profile for the project; had I the advantages of object-recognizing libraries and SIMD instructions, I definitely would have faced the risk of not properly taking advantage of them!

Instead, I had a straightforward brick wall to get through: Could I reliably do target detection in a video frame? Further, I knew that the client would not fund the development of a sophisticated object-detection algorithm (no Viola-Jones boosted rejection cascades for me!). If I couldn’t achieve the detection goals with a relatively simple algorithm, I would have too little traction on the problem to commit to a schedule for the whole project.



Related Search Term(s): Processing

Pages 1 2 3 


Share this link: http://sdt.bz/33614
 
Most Read Latest News Blog Resources

Add comment


Name*
Email*  
Country     


  • Comment
Loading




close
NEXT ARTICLE
Watch out multicore: GPUs are right behind
As multicore CPUs hit limitations, general-purpose GPUs are stepping up to make heterogeneous computing possible Read More...
 
 
 
 
News on Monday
more>>
SharePoint Tech Report
more>>


   

 
 

Download Current Issue
FEBRUARY 2012 PDF ISSUE

Need Back Issues?
DOWNLOAD HERE

Want to subscribe?


 
blogs tab
Agility, mom, and apple pie
If we're to evaluate the state-of-the-art in software development, we should start with the values espoused in the Agile Manifesto.
02/07/2012 11:57 AM EST

RIM woos developers with free tablet
How do you get more apps ported to the BlackBerry PlayBook? By giving every developer a free tablet, of course!
02/04/2012 01:57 PM EST

GitHire: Use Headhunters to Find Your Perfect Programmer
Are you a hiring manager tired of scouring the job boards? Check out this new service that will find 5 people interested in your jobs.
02/03/2012 12:17 PM EST

Facebook claims hacker cred
Facebook's SEC S-1 filing form includes a short essay on the Hacker Way by Mark Zuckerberg himself.
02/02/2012 08:26 AM EST

Ryan Dahl steps down
Ryan Dahl, creator of Node.js, steps back from his position as gatekeeper for the project.
02/01/2012 04:58 PM EST

Bloomberg opens its API
Bloomberg's APIs could lead to a future standard for accessing market data.
02/01/2012 04:41 PM EST

 
Events calendar tab
2/13/2012 to 2/16/2012
Santa Clara
TechWeb

2/26/2012 to 2/29/2012
San Francisco
BZ Media

2/27/2012 to 3/2/2012
San Francisco
RSA

3/4/2012 to 3/7/2012
Las Vegas
IBM Tivoli

3/5/2012 to 3/9/2012
San Francisco
TechWeb