How to use template matching for car detection?

I want to detect car from an input image. the brand of car is not an issue. I want to use template matching method for detection. I want to use binary edge detected image of car as template and any road image for input image. How can i start? Do i have to create a train data set with more then one template for detecting any car? How can i do that?

Answer 1

[sandeep]

Try normalized cross correlation to do template matching. Follow this link http://www.mathworks.com/help/images/examples/registering-an-image-using-normalized-cross-correlation.html