MU Camera

Function introduction

MU Vision Sensor is an intelligent vision sensor that can recognize many kinds of objects with a deep-learning algorithm inside. For example, it can detect color blocks, balls, the human body, and cards. Its detect result can be transmitted through UART or I2C interface. MU is compact, has low power consumption, processes all algorithms locally, and can be widely used in intelligent toys, AI+STEAM lessons, creators, and other products or fields.

Software setup

Currently only supports the product Bittle, software version 2.0, please select "Camera" for the mode.

• You can use the Firmware Uploader within the Petoi Desktop App to finish the configuration.

• You can also use Arduino IDE for the most freedom to upload and modify the codes.

1. First, download and install the MU camera library into your Arduino IDE.

2. Use the latest OpenCat code to finish the setup.

If you have already uploaded the latest OpenCat code to make Bittle walk, you only need to uncomment the #define CAMERA at the beginning of OpenCat.ino then upload the code.

If you are not sure, you need to finish the upload process for the standard mode to ensure everything is configured correctly, then upload the code in the camera mode.

Hardware setup

After uploading the firmware, switching the dial switches on the MU Vision Sensor and connecting to the NyBoard with wire as shown in the following picture:

Note: The position of the left and right switches (left: down and up; right: down and down) must be dialed to the position shown in the figure.

Fix the end connected to the camera to the robot's head (included in Bittle's mouth).

If the camera code is uploaded correctly, Bittle maintains a squat position basically, you can see success messages printed on the serial monitor of Arduino IDE. When the MU Vision Sensor recognizes a target, the two LEDs will turn blue, and Bittle's head can follow the target and swing left and right. The demo code will auto-switch the target between a yellow tennis ball and a human body if it fails to find any object.

If the MU Vision Sensor has not been able to identify the target object, please press the reset button on the camera, then press the reset button on the main board.

For more details, please refer to the Technical Support Document.

The demo video is as follows: