All geek questions in one place

OpenCV vs OpenVX for embedded system

I want to make an image recognition program for rasberry pi. I started working in OpenCV, but just opened OpenVX, a hardware accelerator for OpenCV. Being that speed and efficiency are important for an embedded system, I am curious how to use this new technology. Should I port my code to OpenVX or is it a program that works with my OpenCV program?

+5
source share
3 answers

From the project own site :

OpenVX can be used directly by applications or accelerate linking of a higher level, for example, the popular open source open-source vision library [...]

enter image description here

... which seems completely understandable to me - you can use OpenVX directly or as OpenCV support.

However, it is also clear that OpenVX is currently vapourware - it exists only as a specification and a set of header files (without a real library).

A preliminary release of the specification allows developers and developers to provide feedback before the completion of the specification, which is expected within six months.

, - 19 2013 . , , , .

OpenVX GPU RPi, RPi, - .

+7

2015 . OpenVX vapourware:-) , .

, , OpenVX Raspberry Pi - ( / ). Pi , , "" Broadcom GPU...

+7

OpenVX, OpenVX . ( 2014 )

OpenVX , , , OpenVX Opencv.

:

  • OpenCV:
  • OpenVX: Close focus on basic hardware-accelerated features for mobile vision - but extensible. Uses an external / native camera API.
0
source

Source: https://habr.com/ru/post/1542409/

More articles:


All Articles