Hi Guys,

I'm new to C and OpenCV, my postgraduate project requires me to find different body parts in an image, like legs, hands and torso and head. And then determine if the person is lying on the ground or standing upright.

Please help if you have some ideas.

Thanx

Recommended Answers

All 3 Replies

OpenCV's HAAR-detection is what you need.
Be aware that the learning-time will be enormous, specially for objects that 'look alike' like an arm or a leg...

There's a face-detection demo-program in the tuts from OpenCV, you might want to take a look at that.

Niek

i have tried to train haar-detection, but it doesnt seem to work. Do all the positive images need to be of the same size before the training process?

i have tried to train haar-detection, but it doesnt seem to work. Do all the positive images need to be of the same size before the training process?

I think so actually. But it's a long time ago that I used HAAR. The most important thing is that the negative images NEVER show the object that you want to detect.

For good OpenCV info and advice, I'd recommend you join this yahoo! group. Most problems I encountered when I used OpenCV were already solved there.

Be a part of the DaniWeb community

We're a friendly, industry-focused community of developers, IT pros, digital marketers, and technology enthusiasts meeting, networking, learning, and sharing knowledge.