[I know, this section just echos the same stuff as on the résumé. I plan to expand later.] Worked with PhDs, staff and university interns researching disruptive technologies. Barco Labs deliverables are research papers, patents and demos. Any research that might become a viable product in 2 to 5 years is then passed off to one of the product divisions. (Due to the trade secret nature of this research some details cannot be revealed.) Accomplishments:
I didn't really get into machine learning (ML) or computer vision until I joined Barco Labs in 2017. The team I work with specializes in ML research and to get up to speed on the concepts and terminology, I did the IEEE Workshop on Machine Learning and TensorFlow right after joining the team though I was already familiar with some concepts in ML like convolution, gradient decent, back-propagation and the problem of local minima from my experiences with adaptive noise cancelling (at NOSC), force-directed graph layout (at Yahoo! Research Labs and the Burke Institute) and simulated annealing (at ForceField). I have a basic understanding of TensorFlow but I am far from being able to program effectively with it.
I was actually invited to join the ML team to support the work of the real ML experts with all the skills I had acquired over the years in video processing, GUIs, 3-D visualization, framework design, messaging protocols, full stack engineering and so forth. And, I was also known for my ability to learn and apply new technologies. Some of my early ML support work was creating labelled and unlabelled image data sets to train and evaluate ML and computer vision accuracy and performance.
I am now more directly involved in ML research evaluating preexisting ML algorithms and statistical AI techniques in OpenCV such as image stabilization, homography estimation, augmented reality, auto-exposure algorithms, text detection and OCR to see how these algorithms can be applied to the research I am currently doing.
Experiences using this skill are shown below: