Where computer vision needs help from computer science

Опубликовано 7 сентября 2016, 17:32

I'll give my view of the frontier of computer vision and where I feel computer vision needs advances from computer science and machine learning. This will cover where computer vision works well: finding cars and faces, operating in controlled environments, and where it doesn't work well: in the uncontrolled settings of daily life. There will be a quick history object recognition. I'll list a number of computer vision problems, describe their structure, and tell where we need help.