An insightful article by Brian Dipert, Editor-in-Chief, Embedded Vision Alliance Here: http://www.embedded-vision.com/industry-analysis/technical-articles/internet-things-see  

https://www.youtube.com/watch?v=kp3ik5f3-2c At 20:00 Dr Shasua talks about Mobileye experiences with CNNs Refers to AlexNETs requirement for 60M parameters and 832M MAC operations Mobileye have developed an architecture to support deep CNNs in software together with additional components like spatial coupling through…

Spectacular videos of embedded vision in action! Provided by the Embedded Vision Alliance http://www.embedded-vision.com/eye-catching-embedded-vision-clips    

From feature descriptors to deep learning: 20 years of computer vision http://quantombone.blogspot.ie/2015/01/from-feature-descriptors-to-deep.html We all know that deep convolutional neural networks have produced some stellar results on object detection and recognition benchmarks in the past two years (2012-2014), so you might…

It’s Time to Relabel the Brain  http://psychsciencenotes.blogspot.ie/2015/01/its-time-to-relabel-brain.html Another day, another study finds that ‘visual’ cortex is activated by something other than information from the eyes: A research team from the Hebrew University of Jerusalem recently demonstrated that the same part…

http://www.movidius.com/our-technology/myriad-2-platform A dedicated vision processing platform Myriad 2 is the industry’s first always-on vision processor. It delivers high-performance computational imaging and visual awareness in severely power-constrained environments. Myriad 2 exhibits a skillful balance between hard-wired and programmable elements. This gives…

Can Machines “See” Using Convolutional Neural Networks? http://www.altera.com/technology/system-design/articles/2015/convolutional-neural-networks.html Convolutional What? “The simplest way to look at CNNs,” explains i-Abra CTO Greg Compton, “is as a way to build a very powerful many-to-one filter.” For instance, you might design a CNN…

Some searching has turned up these public domain datasets http://www.inf.ed.ac.uk/teaching/courses/dme/2014/datasets.html http://www.ee.oulu.fi/~jaska/datasets.html http://mldata.org/repository/data/viewslug/wearable-accelerometers-activity/ http://www-scf.usc.edu/~mizhang/datasets.html In addition we’ve developed an Android app using AppInventor to capture accelerometer and magnetometer data as timeseries in .csv format and gmail it and backend google scripts…

Paper Pdf: http://goo.gl/SdqOl0 Video: https://www.youtube.com/watch?v=KPNwVNQP7jM Source code: https://github.com/plumonito/dtslam