Hi,
I am trying to understand what does and doesn't work on the Pico Ultra.
The SDK I am using is here: https://github.com/LuckfoxTECH/luckfox-pico.git
What does not work
1. Enabling OpenCV in the buildroot build. - It appears this version of openCV is not compatible with the board. I cannot find any examples that use this version and produce usable results. Luckfox recommends using the lightweight version, OpenCV-Mobile -which is available [here](https://github.com/nihui/opencv-mobile).
2. The rknn_toolkit_lite2 toolkit which comes as part of the RKNN-toolkit available at: https://github.com/airockchip/rknn-toolkit2 is not suitable for the Pico Ultra. I think this means we cannot run python code on the Pico Ultra board itself that can talk with the NPU, but this is not clear in the documentation. In fact the documentation states: RKNN-Toolkit-Lite2 provides Python programming interfaces for Rockchip NPU platform to help users deploy RKNN models and accelerate the implementation of AI applications.And under that it says: Support Platform, and then lists RV1103/RV1106. Luckfox do not maintain this and it currently is not suitable for the Pico Ultra.
What does work
1. There are a series of examples that are available here: https://github.com/LuckfoxTECH/luckfox_ ... pi_example. These appear to work and use a statically compiled libraries, including a library for openCV which works. It would be nice to be able to recompile these libraries and add some more OpenCV modules if possible. Based on feedback from Luckfox this should be possible. The source code is available https://github.com/nihui/opencv-mobile.
2. There is the RKNN-toolkit available https://github.com/airockchip/rknn-toolkit2/. This is a software development kit for users to perform model conversion, inference and performance evaluation on PC and Rockchip NPU platforms. There is a directory RKNN/rknn-toolkit2/rknpu2/examples which has a number of interesting examples, but it seems most of these are not suitable for the Pico Ultra. There is a subdirectory called RV1106_RV1103 which has two examples: rknn_mobilenet_demo and rknn_yolov5_demo. These work on the Ultra, but do not use OpenCV or show how to interface with the camera. They take static images and use the NPU to infer object detection. Again Luckfox do not maintain this, but the examples I mentioned do work on the Ultra.
3. There are some good examples https://wiki.luckfox.com/zh/Luckfox-Pic ... cv-mobile/, including a basic example that shows how to capture a still image from the camera via OpenCV Mobile.
What is not clear
1. There are a number of code samples in the SDK at: luckflox-pico/media/samples/example which appear to be Rockchip camera test utilities of various sorts. These are all low level and do not use OpenCV, but do give examples of capturing video frames from /dev/video(n). Unfortunately, these is no documentation with these samples. I don't know if they are relevant for the Pico Ultra. They should work, but there is no documentation.
2. I am not aware of any other examples, but would be happy to add to this post if people have found other sources. I would also be grateful for any corrections.
Clarifying what does and doesn't work on the LuckFox Pico Ultra
-
Last edited by RogerTheFox on 2025-06-30 19:47, edited 2 times in total.
Hello, regarding your questions, here are our replies:
1 We have not verified whether OpenCV in Buildroot works properly on the Luckfox Pico. For related porting efforts, we suggest referring to discussions by other users in the forums. On resource-constrained platforms like the RV1103/RV1106, we generally recommend using the lightweight version, OpenCV-Mobile.
2 The rknn-toolkit2-lite only provides a Python package for aarch64 and does not include an arm32 version suitable for RV1103/RV1106. At present, we have not found any examples of using rknn-toolkit2-lite on the RV1103/RV1106 platform. Therefore, I assume that the term "Supported Platform" likely refers to platforms supported by rknn-toolkit2, rather than those compatible with rknn-toolkit2-lite.
Please note that we do not participate in the development or maintenance of rknn-toolkit2 or rknn-toolkit2-lite.For more information, please raise an issue in the corresponding GitHub repository.
3 The https://github.com/LuckfoxTECH/luckfox_ ... pi_example project uses OpenCV-Mobile. For usage details, please refer to https://github.com/nihui/opencv-mobile.
4 Same as point 2 — we are not involved in the development or maintenance of rknn-toolkit2, and therefore cannot provide support for related issues.
5 The Luckfox Pico Ultra is a development board based on the RV1106. The examples in luckflox-pico/media/samples/example also support the Luckfox Pico Ultra.
1 We have not verified whether OpenCV in Buildroot works properly on the Luckfox Pico. For related porting efforts, we suggest referring to discussions by other users in the forums. On resource-constrained platforms like the RV1103/RV1106, we generally recommend using the lightweight version, OpenCV-Mobile.
2 The rknn-toolkit2-lite only provides a Python package for aarch64 and does not include an arm32 version suitable for RV1103/RV1106. At present, we have not found any examples of using rknn-toolkit2-lite on the RV1103/RV1106 platform. Therefore, I assume that the term "Supported Platform" likely refers to platforms supported by rknn-toolkit2, rather than those compatible with rknn-toolkit2-lite.
Please note that we do not participate in the development or maintenance of rknn-toolkit2 or rknn-toolkit2-lite.For more information, please raise an issue in the corresponding GitHub repository.
3 The https://github.com/LuckfoxTECH/luckfox_ ... pi_example project uses OpenCV-Mobile. For usage details, please refer to https://github.com/nihui/opencv-mobile.
4 Same as point 2 — we are not involved in the development or maintenance of rknn-toolkit2, and therefore cannot provide support for related issues.
5 The Luckfox Pico Ultra is a development board based on the RV1106. The examples in luckflox-pico/media/samples/example also support the Luckfox Pico Ultra.