Skip to main content
Associate II
May 21, 2025
Solved

Deploying OpenCV for Object Tracking on STM32N6570-DK (MB1854B)

  • May 21, 2025
  • 4 replies
  • 897 views

Hello Everyone,

I’m still getting up to speed with the STM32N6 series, so apologies if my question seems off, but I’d really appreciate your help!

I’m working on implementing object tracking using the STM32N6570-DK board with the MB1854B camera. I'm wondering if it’s possible to deploy OpenCV on this platform to support the tracking logic.

If anyone has experience with this or knows of any courses, guides, or resources that could help me deploy OpenCV (or similar tracking frameworks) to the board, I’d be incredibly grateful.

Also, if you have relevant experience and are open to offering support or consultancy, I’m more than happy to discuss compensation. Please feel free to reach out!

Thanks in advance for your time and help!

Best answer by Julian E.

Hello @HarisHer 

For OpenCV, we do not have a ready-to-use package or build, only some limited functions ported:

- As of today, the only N6 optimized image-processing function we have is resize (bilinear and nearest).

The MVE vectorized code can be found in the n6-ai-hand-land package (available at https://www.st.com/en/development-tools/stm32n6-ai.html) and located under: n6-ai-hand-land/Lib/ipl.

- Other image-processing functions are provided in IPL Image processing library (non-vectorized): https://github.com/STMicroelectronics/stm32-mw-ipl

- Alternatively, Arm started the development of an CMSIS-CV library implementing vectorized algorithms for computer vision on Cortex-M with MVE: https://github.com/ARM-software/CMSIS-CV. The library includes cannysobel filters for edge detection.

 

Have a good day,

Julian

4 replies

Julian E.
Julian E.Best answer
Technical Moderator
May 22, 2025

Hello @HarisHer 

For OpenCV, we do not have a ready-to-use package or build, only some limited functions ported:

- As of today, the only N6 optimized image-processing function we have is resize (bilinear and nearest).

The MVE vectorized code can be found in the n6-ai-hand-land package (available at https://www.st.com/en/development-tools/stm32n6-ai.html) and located under: n6-ai-hand-land/Lib/ipl.

- Other image-processing functions are provided in IPL Image processing library (non-vectorized): https://github.com/STMicroelectronics/stm32-mw-ipl

- Alternatively, Arm started the development of an CMSIS-CV library implementing vectorized algorithms for computer vision on Cortex-M with MVE: https://github.com/ARM-software/CMSIS-CV. The library includes cannysobel filters for edge detection.

 

Have a good day,

Julian

​In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.
HarisHerAuthor
Associate II
May 22, 2025

Hi Julian,

Thanks for your response,however I am getting 404 on CMSIS-CV provject any ide why?

Julian E.
Technical Moderator
May 23, 2025

Hello @HarisHer ,

 

Sorry, I was given the wrong link. Here it is: 

https://github.com/ARM-software/CMSIS-CV

 

Have a good day,

Julian

​In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.
Associate II
July 21, 2025

Hey there!  Following a similar quest, and found your post @HarisHer .  How’s this going for you?  Any tips to share?

TZiel.1
Associate II
March 17, 2026

Wondering how this is going for you as well. Trying to get an image processing pipeline running on the platform doesn't seem well supported..