-3

I and my partner decided to implement a traffic light recognition program as a student project.

But we are absolute beginners with computer vision and have no idea how to start with this. (What only we know is to use OpenCV)

Should we firstly learn image recognition or just start with object tracking?

Our ideal production is to recognize traffic light in a video but not just an image.

  • Welcome to Stack Overflow. Please consider [taking the tour](https://stackoverflow.com/tour). Users are much more likely to help if you (1) show some [research effort](https://meta.stackoverflow.com/questions/261592/how-much-research-effort-is-expected-of-stack-overflow-users) on your own, and (2) learn [how to ask](https://stackoverflow.com/help/how-to-ask) questions around here. Please provide a [minimal, complete, and verifiable example](https://stackoverflow.com/help/mcve) to your _specific_ problem. Your question is way too broad to be answered here. – HansHirse Mar 12 '19 at 12:56

1 Answers1

0

In my opinion, you should take a serious course about computer vision before going deeper.

The video is just a sequence of picture. So you could use opencv to read each image then process them.

For you current project, a simple object detection using hog feature should be more than enough.

There's tutorial at http://www.hackevolve.com/create-your-own-object-detector/ . It's very easy to understand and source code is also available, so you can move quick.

Good luck.

Vu Gia Truong
  • 1,022
  • 6
  • 14