Ask HN: What are the best resources to learn computer vision?

Ideally, I would like to be good enough to get a job at an AI/robotics startup. I already have a CS degree, a decent math background, and am working as an embedded software developer for a large company.

Opencv documentation

I started by getting a webcam or two and trying out various projects: marker tracking (made an optical IR pass filter and tracked an IR LED with two cameras), object segmentation (e.g measure geometry of certain-colored objects).

Measure the speed or count the number of cars passing by your street. Try to implement an OCR for utility meter. There are lot's of applications you can train yourself in, and I guarantee that you will learn a ton from each and every one of them.

Try reading the samples that come with the predominantly used programming library/framework. Works with pretty much everything. I know a thing or two about statistics because I study R examples at night. I know a decent chunk of winapi and windows ipc because of delphi, I know some CV because I studied samples from opencv and tried to solve problems with it, etc.

I learned OpenCV using the O'Reilly book by Bradski and Kaehler (back when it was OpenCV 2). I found it well-structured and it worked for me. They have an updated version for OpenCV 3.

However, I can't tell you if OpenCV is still the framework of choice and/or widely used in the field you want to go into.