# OpenCV on STM32

**URL:** <https://forum.opencv.org/t/opencv-on-stm32/4149>\
**Category:** Uncategorized\
**Tags:** embedded\
**Created:** [July 3, 2021, 10:43am UTC](https://forum.opencv.org/t/opencv-on-stm32/4149 "2021-07-03T10:43:08Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Anton\_Bondarev](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.opencv.org/anton_bondarev/32/2564_2.png) [@Anton\_Bondarev](https://forum.opencv.org/u/Anton_Bondarev)\
**Post date:** [July 3, 2021, 10:43am UTC](https://forum.opencv.org/t/opencv-on-stm32/4149/1 "2021-07-03T10:43:08Z")

</div>

Hi all,  
We, [Embox](https://github.com/embox/embox) team, have run OpenCV on STM32 platforms (MCUs). You can see benchmarking for some apps in the [article](https://www.embedded.com/benchmarking-opencv-on-stm32-mcus/). How do you think is it an interesting direction for OpenCV?

---

<div class="post-metadata">

**Author:** ![crackwitz](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.opencv.org/crackwitz/32/14_2.png) [@crackwitz](https://forum.opencv.org/u/crackwitz)\
**Post date:** [July 6, 2021, 6:48am UTC](https://forum.opencv.org/t/opencv-on-stm32/4149/2 "2021-07-06T06:48:06Z")

</div>

given these numbers, maybe not an “interesting” direction (although interesting work) but the execution times are valuable information to any engineer. I also believe using SIMD/NEON would help a lot. [ST](https://www.st.com/content/st_com/en/ecosystems/stm32-ann.html) [have demoed](https://www.youtube.com/playlist?list=PLnMKNibPkDnG9IC5Nl9vJg1CKMAO1kODW) some simple neural networks running on audio input in realtime and IIRC even some video. I’ve heard of OpenVX, which may assume less than 128 bit SIMD intrinsics.

---

<div class="post-metadata">

**Author:** ![Anton\_Bondarev](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.opencv.org/anton_bondarev/32/2564_2.png) [@Anton\_Bondarev](https://forum.opencv.org/u/Anton_Bondarev)\
**Post date:** [July 6, 2021, 4:22pm UTC](https://forum.opencv.org/t/opencv-on-stm32/4149/3 "2021-07-06T16:22:14Z")

</div>

Yes, I also think that SIMD can improve the performance. We have tried on STM32H7 it decreased time by 25%. It is of course noticeable slower than on big ARMs. However I still think that OpenCV on low power consumption can be great for some tasks. Since OpenCV can be better for them than neural networks.

Thanks for links especially about OpenVX