Computer vision is a field that includes methods for acquiring, processing, analyzing, and understanding images and, in general, high-dimensional data from the real world in order to produce numerical or symbolic information, e.g., in the forms of decisions. I’ll break down the installation of OpenCV on Ubuntu (although there’s support for Windows, Mac, iOS and Android) on x86, x86_64 and ARM based devices. I built an automated script that does all the heavy lifting of installing and compiling FFMPEG (x264, fdk-aac, libvpx, libopus) and OpenCV from source. This will get you the latest and greatest OpenCV with Java and Python bindings. Then I’ll move into Java examples for motion and people detection. Finally I’ll cover a new project I’m working on called Java Video Processor that uses a plugin based architecture and lose coupling to provide a complete Computer Vision solution. I’ll try to stay away from the rocket science of computer vision and focus how you can get started without a PhD.
Steven Goldsmith is a Senior level professional with extensive experience in architecture, development, testing, continuous build processes, declarative and meta programming. I have worked for insurance, real estate, finance and technology companies. I’m currently focusing on large scale middleware built with open standards. I have led/managed development teams as well as being in the trenches. I enjoy the total life cycle challenge of R&D, networking, deploying servers, database design, developing code and post production support. I have over 34 years of experience in the Computer Science field with 27 years of that being an IT professional.