Bookmark and Share


The Embedded Vision Academy is a free online training facility for embedded vision product developers. This program provides educational and other resources to help engineers integrate visual intelligence―the ability of electronic systems to see and understand their environments―into next-generation embedded and consumer devices.

The goal of the Academy is to make it possible for engineers worldwide to gain the skills needed for embedded vision product and application development. Course material in the Embedded Vision Academy spans a wide range of vision-related subjects, from basic vision algorithms to image pre-processing, image sensor interfaces, and software development techniques and tools such as OpenCV. Courses will incorporate training videos, interviews, demonstrations, downloadable code, and other developer resources―all oriented towards developing embedded vision products.

The Embedded Vision Alliance™ plans to continuously expand the curriculum of the Embedded Vision Academy, so engineers will be able to return to the site on an ongoing basis for new courses and resources. The listing below showcases the most recently published Embedded Vision Academy content. Reference the links on the right side of this page to access the full suite of embedded vision content, sorted by technology, application, function, viewer experience level, provider, and type.

Song Han of Stanford delivers a presentation at the March 2016 Embedded Vision Alliance Member Meeting.

Marcus Hammond of Kespry delivers a presentation at the March 2016 Embedded Vision Alliance Member Meeting.

This chapter describes some initial (as well as the simplest and most intuitive) implementations of convolution algorithms.

This Tractica white paper covers the market for computer vision and deep learning technologies, providing real world use cases.

Wenyi Zhao of DAQRI delivers a presentation at the March 2016 Embedded Vision Alliance Member Meeting.

Convolution operations are important in image processing, particularly in filtering. GPU compute can improve performance significantly.

OpenVX enables embedded vision application software developers to efficiently harness the processing resources available in SoCs and systems

Yangqing Jia, Research Scientist at Facebook, delivers a presentation at the Alliance's February 2016 tutorial on deep learning using Caffe.

This article discusses the optimization motivation, vectorization techniques and resultant performance of the FFT on ARM Mali GPUs.

This article extends the mixed-radix FFT OpenCL implementation to two dimensions and explains optimizations for Mobile ARM Mali GPUs.