|
Dear Colleague,
Recently, I spent three days at the Consumer Electronics Show.
It was time very well spent. Many of the vision-based concepts and
products I saw there were flat-out amazing: autonomous drones and
automobiles, depth-sensing smartphones and tablets, deep-learning based
object recognition, augmented and virtual reality, and countless other examples
of embedded vision’s proliferation. I shot numerous demo videos while I
was there, and I look forward to sharing them with you on the website
in the near future. For now, check out Marco
Jacobs’ (videantis) show report.
Speaking of new website content (and of deep learning), I
recently conducted a great interview with the three primary developers
of the popular open-source Caffe convolutional neural network
framework. A transcript
of the interview is now published; I commend it to your attention.
And if you feel inspired to further your deep-learning understanding
after reading it, as I strongly suspect you will be, I encourage you to
attend next
month’s live Caffe tutorial organized by the Alliance and BDTI,
and taught by those same three individuals. Register by this Friday and
you can take advantage of the Early Bird discount; for more
information, see the event
page.
And speaking of early-registration promotions, I’ll also
encourage you to consider registering for the Embedded Vision Summit
while the 15%-off Early Bird discount
rates remain in effect (via promo code 03EVI). The Embedded Vision Summit,
an educational forum for product creators interested in incorporating
visual intelligence into electronic systems and software, takes place
May 2-4 at the Santa Clara (California) Convention Center. Among other
features is the dedicated Deep Learning day on May 2, complete with
workshops, presentations and demos. Don’t forget, too, about the Vision
Tank start-up competition, whose finalists will strive to out-do each
other live on stage at the Summit. (Note to start-ups with innovative
vision-based products: Vision
Tank entries are due by March 1, so don’t delay!)
Finally, while you’re on the Alliance website, make sure to
also check out the other great recently published content there. Thanks
as always for your support of the Embedded Vision Alliance, and for
your interest in and contributions to embedded vision technologies,
products and applications. If you have an idea as to how the Alliance
can better serve your needs, please contact me.
Brian Dipert
Editor-In-Chief, Embedded Vision Alliance
|
|
“Taming the Beast: Performance and Energy Optimization Across
Embedded Feature Detection and Tracking,” a Presentation from Cadence
Chris Rowen, Fellow at Cadence, presents
the “Taming the Beast: Performance and Energy Optimization Across
Embedded Feature Detection and Tracking” tutorial at the May 2014
Embedded Vision Summit. This presentation looks at a cross-section of
advanced feature detectors, and considers the algorithm, bit precision,
arithmetic primitives and implementation optimizations that yield high
pixel processing rates, high result quality and low energy. Rowen also
examines how these optimization methods apply to kernels used in
tracking applications, including fast connected component labeling.
From this Rowen derives general principles on the priority and likely
impact of different optimization types.
Getting Started With GPU-Accelerated Computer Vision Using
OpenCV and CUDA
OpenCV is a free library for research and
commercial purposes that includes hundreds of optimized computer vision
and image processing algorithms. NVIDIA and Itseez have optimized many
OpenCV functions using CUDA on desktop machines equipped with NVIDIA
GPUs. These functions are 5 to 100 times faster in wall-clock time
compared to their CPU counterparts. Anatoly Baksheev, OpenCV GPU Module
Team Leader at Itseez, demonstrates how to obtain and build OpenCV, its
GPU module, and the sample programs. You’ll then learn how to use the
OpenCV GPU module to create your own high-performance computer vision
applications. Finally, you’ll learn how to start using CUDA to create
your own custom GPU computer vision functions and integrate them with
OpenCV GPU functions to add novel capabilities.
More Videos
|
|
New Competition Aims to Spur Energy-efficient Computer
Vision Innovation
Powerful vision processors have existed
for some time now, as exemplified by supercomputers and the
longstanding academic research on computer vision. What’s recently
changed are the “low-cost” and “energy-efficient” aspects of vision
processing, along with evolutionary (and sometimes revolutionary)
accuracy and other improvements in the algorithms running on the
processors. Well-known image classification competitions like the
yearly ImageNet Large Scale Visual Recognition Challenge (ILSVRC) focus
only on accuracy; the speed, cost and power consumption of the
solutions tested isn’t factored into the results. In light of the
growing importance of cost-effective, energy-efficient real-time vision
solutions, professors Yung-Hsiang Lu of Purdue University and Alex Berg
of the University of North Carolina have created the Low Power Image
Recognition Competition (LPIRC). More
Intuition in a Box?
“Since reading Malcolm Gladwell’s Blink a
decade ago,” says Alliance founder Jeff Bier, “I’ve been intrigued by
how the mind works, particularly how judgements and decisions are made.
I’ve been inspired to take an armchair tour of research on this topic,
and have encountered fascinating insights from the likes of David
Eagleman and Daniel Kahneman. Reading the work of these talented
researchers and writers has led me to the inescapable conclusion that
most of our judgements and decision-making take place in our
subconscious minds. I consider myself a hyper-rational engineering
type, so the idea that my subconscious is calling the shots, based not
on deliberation and calculation but rather on intuition, was initially
uncomfortable. Lately, though, I’ve come to appreciate the value of
intuition; the way it can alert me to a dangerous situation before I
comprehend the nature of the danger, for example, or warn me that
someone’s being untruthful before I’m able to identify the actual lie.
And that has started me wondering: What if our devices, systems and
applications could gain this type of intuitive insight?” More
More Articles
|
