This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

Video/image processing with OMAP35X EVM

Other Parts Discussed in Thread: OMAP3530

Hi everyone,

I have to implement an algorithm in the OMAP35x EVM board in order to detect vehicules with a camera. I think I will use a camera connected by S-video and I would like to know what is the easiest way to process. it seems to me that S-video is better than composite that's why i would like tp use it.

What is the easiest language C or C++ or another? What library I will use because I know that openCV is a big library for image processing but it is not in my card. I suppose there is an equivalent.

 

thanks!

  • OMAP35x also has a parallel camera port with 8-12 bit parallel data lines. You could configure the device to load the data to ddr where you could implement your algorithm. Any particular reason you are considering only s-video/composite channels?

    Regards, Punya

  • Hi Punya,

    thanks for your help. I have no particular reason to choose only s-video/composite channel it's just I know s-video provides a better quality than composite. I didn't know that there was a parallel camera port on the board and I don't know how to use it? Does it exist camera with a parallel port?

     

    As you know I have to process images from camera iin order to detect a motion automotive or people. This is the purpose of my project in order to watch level crossing. So, to process images I know that I need some specific libraries (like openCV or another) do you know if there are already in the board or if we could implement?

     

     

  • Aurelien,

    OMAP3530 does come with a parallel camera port, alternatively you could also use a USB based camera. You have multiple options to get images to the memory, please refer the omap3530 product specs for additional details.

    Do you have any particular operating system in mind? Please refer to this wiki which is a beginners guide for OpenCV implementation on beagleboard.

    Regards, Punya