Solved

Porting from OpenCV (Pioneer 10 - Brobot)

Forum|Forum|10 months ago
June 26, 2025
4 replies
103 views

llrds
Ensign

Hi All,

I’ve got a PoC running using OpenCV+M1 Mac while I wait for my Metis hardware. In preparation for the kit arrival, I want to plan the porting process and get ahead on refracturing so I can compare the performance. I plan to use inferenceStream with Python to keep it really simple.

Any experience here going from OpenCV to Voyager? Is it a drop in replacement or are they used in parallel?

If there is a better development environment than OpenCV i’d be glad to hear it - my application is taking shape so I want to make sure I do not stray to far down the wrong path!

Best answer by Spanner

Ah great stuff! Good idea getting a jump on things 👍

This is probably all stuff you already know, but just to clarify one or two points that might help. Voyager isn’t so much a drop-in replacement for OpenCV, as it is a full AI pipeline framework with its own architecture.

However, you can use OpenCV alongside Voyager, especially for tasks and additional processing outside the main AI pipeline. So you’ll probably need to re-implement the logic, but your efforts won’t be wasted! You’re in a good spot 😀

+3

Spanner
Axelera Team
Answer
Forum|Forum|10 months ago
June 26, 2025

Ah great stuff! Good idea getting a jump on things 👍

This is probably all stuff you already know, but just to clarify one or two points that might help. Voyager isn’t so much a drop-in replacement for OpenCV, as it is a full AI pipeline framework with its own architecture.

However, you can use OpenCV alongside Voyager, especially for tasks and additional processing outside the main AI pipeline. So you’ll probably need to re-implement the logic, but your efforts won’t be wasted! You’re in a good spot 😀

Like

llrds
Author
Ensign
Forum|Forum|10 months ago
June 27, 2025

Thanks for getting back to me, when I actually get started on the SDK i’m sure the pipelines will be a huge revelation of simplicity!

Like

+1

saadtiwana
Ensign
Forum|Forum|10 months ago
July 9, 2025

Hi @Spanner Is there any simple example that shows how to use a detection model from the model zoo in C or Python along with opencv for obtaining image and displaying the results? In the examples I have seen so far, it’s all implemented as pipelines which do the part of getting the images from usb camera/file and displaying them by themselves.

However, for me, I want my application to have control of sending the image for inference (detection) and then using the results as needed by the application. I understand it’s not as efficient/speedy as the pipelines implementation but my application requires it (I think!).

Or, can I run the model inference as a gstreamer pipeline and then feed the images into it, and get the results out to the opencv application?

Like

+1

saadtiwana
Ensign
Forum|Forum|10 months ago
July 9, 2025

@Spanner Just say your comment about creating a launchpad idea on another post, so I do that now.

Like

Sign up

Log in, or create an Axelera AI account

Login to the community

Log in, or create an Axelera AI account

Scanning file for viruses.

This file cannot be downloaded