# Run a computer vision model on a Himax microcontroller

## In this learning path

- [Introduction](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/yolo-on-himax/)
- [Overview](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/yolo-on-himax/overview/)
- [Set up the environment](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/yolo-on-himax/dev-env/)
- [Build the firmware](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/yolo-on-himax/build-firmware/)
- [Flash firmware onto the microcontroller](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/yolo-on-himax/flash-and-run/)
- [Run additional models in the web toolkit](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/yolo-on-himax/web-toolkit/)
- [Next Steps](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/yolo-on-himax/_next-steps/)

## About this Learning Path

| Skill level:      | Introductory       |
|-------------------|--------------------|
| Reading time:     | 1 hr 30 min        |
| Last updated:     | 13 Aug 2026        |

### Authors:
- Chaodong Gong
- Alex Su
- Kieran Hejmadi, Arm [[GitHub](https://github.com/kieranhejmadi01)] [[LinkedIn](https://linkedin.com/in/kieran-hejmadi-88920815b)]

### Arm IP:
- [Cortex-M](https://support.arm.com/?tab=compute-ip&Product%20Type=Microcontrollers)
- [Ethos-U](https://support.arm.com/?tab=compute-ip&Product%20Type=Neural%20Processing%20Units)

### Tags:
- [ML](https://learn.arm.com/tag/ml)
- [Linux](https://learn.arm.com/tag/linux)
- [macOS](https://learn.arm.com/tag/macos)
- [Himax SDK](https://learn.arm.com/tag/himax-sdk)
- [Python](https://learn.arm.com/tag/python)
- [Hugging Face](https://learn.arm.com/tag/hugging-face)

### Who is this for?
This is an introductory topic for developers who would like to learn about how to run a computer vision application on an embedded device from Himax.

### What will you learn?
Upon completion of this Learning Path, you will be able to:
- Run a You-Only-Look-Once (YOLO) object detection model on a Himax WiseEye2 module.
- Build the Himax Software Development Kit (SDK) and generate a firmware image file.
- Update firmware on the Himax WiseEye2.
- Connect to and use Grove Vision AI module.

### Prerequisites
Before starting, you will need the following:
- A [Seeed Grove Vision AI Module V2](https://www.seeedstudio.com/Grove-Vision-AI-Module-V2-p-5851.html) development board.
- An [OV5647-62 Camera Module](https://www.seeedstudio.com/OV5647-69-1-FOV-Camera-module-for-Raspberry-Pi-3B-4B-p-5484.html).
- A Flexible Printed Circuit (FPC) cable.
- A USB-C cable.
- An x86 Linux machine, or a Mac running macOS.

### Summary
You’ll build and deploy a YOLO computer-vision example on a Himax WiseEye2 microcontroller with the Grove Vision AI Module V2. First, you’ll prepare the host, clone the example repository, and build firmware. Then, you’ll connect the camera, select an application in the makefile, flash the device, and verify its live feed on Cortex-M55 and Ethos-U55 hardware.

### Frequently Asked Questions
<details><summary>How do I clone the correct Himax examples and make sure submodules are included?</summary>
Run `git clone --recursive https://github.com/HimaxWiseEyePlus/Seeed_Grove_Vision_AI_Module_V2.git`, then change into the new directory. The `--recursive` option pulls the required third-party subrepositories.
</details>

<details><summary>Where do I change the application type and which option should I pick for YOLO object detection?</summary>
Go to `Seeed_Grove_Vision_AI_Module_V2/EPII_CM55M_APP_S` and open the makefile. Set `APP_TYPE` to a value from the provided table. For object detection, use `tflm_yolov8_od`. Then, pass the corresponding model argument with the `--model` option when flashing.
</details>

<details><summary>How do I install the Xmodem dependency before flashing?</summary>
From the repository root, run `pip install -r xmodem/requirements.txt`. This installs an Xmodem file transfer utility used by the flashing scripts.
</details>

<details><summary>How should I connect the camera module to the Grove Vision AI V2?</summary>
Insert the flexible printed circuit (FPC) cable into the module’s connector and lift the dark grey latch, then secure the cable. Connect the board to the host with a USB-C cable.
</details>

<details><summary>What result should I expect after flashing, and how do I know the model is running?</summary>
You should be able to view a live camera feed with the computer vision application active. If you selected the YOLO option, expect object detection to appear in the feed.
</details>