Jetson TX2 Processors & Capabilities

Hello,
I am new with NVIDIA embedded systems and i need a little help. I am part of an industrial robotics team at my University and we want to use Jetson TX2 for our SBC. If we use the Jetson must we use parallel programing or we can program as usual ?

At our prototype we used haar cascades for object recognition, as far as i know this method does not need parallel programming. So can we use this method at Jetson ?

Also it will be great if someone can explain or send a link so i can learn about which processors can do what tasks.

Thanks everybody for their time.

Hi,

TX2 is an ARM system. You can write an application as usual as well as it can be executed on an ARM system.
But it’s still recommended you to implement your feature with CUDA which can maximize the GPU power on TX2.

A common interface to do haar cascades is openCV.
You can get the OpenCV installed with this script:
https://github.com/AastaNV/JEP/blob/master/script/install_opencv3.4.0_TX2.sh

Another popular way to do object recognition is DNN.
Here is a corresponding tutorial for your reference:
https://github.com/dusty-nv/jetson-inference/blob/master/docs/imagenet-console-2.md

Thanks.