Computer vision and imaging technologies
I joined General Electric in 1997. Prior to this I received my doctorate from Oxford University. Over the years I have developed computer vision algorithms for a number of application spaces including: Fingerprint matching algorithms for the FBI, face reconstruction algorithms that can take a skull found at a crime scene and reconstruct its face, optical metrology methods for measuring the shapes of manufactured parts, person detection methods from surveillance video, crowd segmentation methods from surveillance video and behavior recognition methods from surveillance video. My current interest is in the topic of intelligent video – I try to answer questions like where are the people, what are they doing and what are their intentions.
In this blog I will be reporting on efforts from the Imaging Technology labs. This includes not just the exciting world of computer vision, but also a whole suite of imaging modality technologies such as CT, MR and Ultra Sound to name but a few. Over the weeks and months to come, we will delve into the science that GE is pursuing for the purposes of sensing and understanding the world around us. A lot of topics in healthcare will be explored, particularly as it relates to expanding access to imaging technologies in the developing world. There will also be a healthy dose of computer vision topics ranging from computer aided manufacturing to real-time analysis of sports video.
I’m intrigued by the last computer vision topic you mentioned, of “real-time analysis of sports video”… What can be learned and what is it good for?