HUSKYLENS 2 + Microscope Camera - AI Cell Identification

auroraAA Jan 28.2026

0 64 Easy

1.1 Project Introduction

This project combines the HUSKYLENS 2 with a microscope camera module and the UNIHIKER K10 to achieve automated detection and real-time feedback for specific targets (e.g., onion epidermal cells), addressing the inefficiencies and inaccuracies of manual observation. The HUSKYLENS 2 captures images via its microscope camera module and performs inference using a self-trained AI model, while the UNIHIKER K10 displays prompt information on the screen based on the detection results. Typical application scenarios include the observation of cell division in middle school biology experiments, the observation of microorganisms in water quality monitoring, as well as the preliminary screening of seed germination rates in the agricultural sector.

1.2 Demo Video

2. Project Implementation Principle

First, use Mind+ V2.0 to train object detection models for different cell categories, then export and install the models on the HUSKYLENS 2. The HUSKYLENS 2 AI camera sensor captures image data through the microscope camera module, and the self-trained models perform inference on the images and output the results. The results are transmitted to the UNIHIKER K10 via the I2C communication protocol. After parsing the data, the UNIHIKER K10 judges whether new cells or abnormal conditions exist and displays the results on the screen. Mind+ is responsible for model training, the HUSKYLENS 2 focuses on image collection and local inference, and the UNIHIKER K10 undertakes data processing and interactive control. The entire workflow forms a closed loop of Model Training → Inference → Computation → Feedback.

3. Hardware and Software Preparation

3.1 Equipment List

Note: Mind+ requires V2.0 or later, HUSKYLENS requires Version 2.

HARDWARE LIST

1 UNIHIKER K10

Link

1 HUSKYLENS 2

Link

1 Microscope Camera Module

Link

1 PH2.0 4Pin Connector Wire

Link

2 USB Cable

Link

3.2 Software Preparation

Download and install the Mind+ installation package(Version 2 or above) from the official website. Double-click to open it after installation.

3.3 Model Training Preparation

If you want to train your own model, follow the instruction below:

3.3.1 Data collection

1. Use HUSKYLENS 2's Camera function: Enter camera → Press Button A to take photos

2. Take enough photos of different cells (multiple angles, ≥50/type, 100 better)

3. Connect HUSKYLENS 2 to PC

4. Find the photo folder on the device

5. Copy images to a folder → Dataset

6. Upload this dataset

3.3.2 Data Annotation and Model Training

Then follow the link below to annotate it, and complete the training:
https://community.dfrobot.com/makelog-318320.html

After training, refer to Section 3.4 to download your model. Alternatively, skip to Section 3.5 to directly use the pre-prepared model for a quick access.

3.4 Model Download Preparation

Click the "Deploy to HuskyLens2" button.

Enter the application name and title settings (only English and numbers are supported temporarily).

Start the conversion. Once the file upload is successful, the automatic cloud conversion will be in progress. Please wait patiently.

Once the model conversion is successful, click "Download to Local Computer" to download a zip file to your local computer.

Note: This hardware only supports object detection currently, and this function requires an internet connection for conversion.

3.5 Model Installation

Use a USB cable to connect your computer and HUSKYLENS 2. Once successfully connected, your computer will detect a drive named HuskyLens.

Copy the generated model ZIP file(in Attachment) to the \storage\installation_package directory on HuskyLens's internal storage.
Note: Do not rename the model ZIP file. Renaming may cause HUSKYLENS 2 to fail recognizing or installing the model.

Then, swipe left and right, click to enter 'Model Installation'.

Select local installation, and the following image will appear once installed.

Observe the HUSKYLENS 2 screen, and you will see a new mode named "cell"—this indicates that we have successfully imported our self-trained model into HUSKYLENS 2.

Finally, select the protocol type for HUSKYLENS 2.
Tap System Settings -> Protocol Type -> select I2C communication mode, then return to the main menu interface.

3.6 Hardware Connection

Make connections by referring to the diagram below.

4. Project Making

Open the programming software Mind+, select "Coding" mode, then click "Upload Mode" to create a new project.

Next, add the required extensions in Mind+, including UNIHIKER K10 and HUSKYLENS 2.
Enter the "Extensions" page, switch to "Board" tab, search for "K10", download and click "UNIHIKER K10".

Load the "HUSKYLENS 2 AI Camera" using the same method.

Click the "Back" button to return to the programming interface.

Click the "Connect Device", choose your device for connecting.

After the device is successfully connected, write the program as follows:

Note: The "Model ID" must match the number displayed on HUSKYLENS 2:

The analysis of the core code is as follows:

The attachment contains the model.zip and program files. You can implement this project by following the steps below:
First, download and install the model.zip into HUSKYLENS 2 according to section 3.5. Then, in Mind+ V2.0, expand the "Project" menu, click "Load Project" to load, and then click "Upload" to run the program.