# AI Camera KOI 2 Info

<figure><img src="/files/hLVJH069FRdhWh0yvzGw" alt=""><figcaption></figcaption></figure>

Kittenbot has released KOI 2 AI Camera in 2024 as the new version of the KOI, KOI is designed to be more user-friendly and more stable to suit education needs.

Various functions and features of the KOI 2 have been optimized and improved, making it more suitable for STEM Education Curriculum.

AI Camera KOI 2 is an offline Artificial Intelligence Module developed by Kittenbot. It is aimed to provide an easy to use platform for students and enthusiasts.KOI is an integrated module combining <mark style="color:orange;">AI chip, camera, microphone, speaker, IPS display and Wifi chip</mark> into 1 convenient module.

AI Camera KOI 2 has a lot of abilities, including Visual Recognition, Face Detection and Recognition, Object Classification, Speech Recognition and Text to Speech. With its built in Wifi chipset, you can even <mark style="color:orange;">connect your KOI to the cloud</mark> for IoT AI Projects!

KOI’s functions can let you experience and learn Artificial Intelligence in a systematic way!

· **Intended Audience:**

STEM Education in Primary or Secondary Schools / STEM Enthusiasts / Advanced MakeCode or Kittenblock users

<div><figure><img src="/files/enuRiRJ2BZiAT5eD9efr" alt=""><figcaption></figcaption></figure> <figure><img src="/files/DnH3MQsCuwtnuhwsmpbh" alt=""><figcaption></figcaption></figure> <figure><img src="/files/PGWG7fMU6hzqxCdOUj5p" alt=""><figcaption></figcaption></figure></div>

### <mark style="color:orange;">KOI 2 Major Upgrades</mark>

1. Image Classifier
   * Model <mark style="color:orange;">Training</mark>: Loosened the Sample Limit of 40, number of samples increased(Upper Limit still undergoing testing, as of now 150 samples can be stored)
   * Image Classification: <mark style="color:orange;">Similarity value</mark> can also be obtained alongside the class
   * Model Storage: No SD card is needed, models and files can be directly stored on board
2. Face Detection
   * Mask Detection: Built-in model allows KOI to detect whether a person is wearing a mask
   * Facial Attributes: Built-in model allows KOI to detect attributes such as gender, and glasses
3. <mark style="color:orange;">**Built-in Tracking Models**</mark>
   * Built-in models allow for object tracking
     * Numbers(PDF provided), Road Signs(PDF Included), Color Balls
4. <mark style="color:orange;">**Built-in Object Tracking Model**</mark>**&#x20;for 20 common items**
5. Improved <mark style="color:orange;">Line Tracing</mark>
   * Faster and more accurate

### KOI 2 Features Upgrade Demo Video

{% embed url="<https://youtu.be/Pw0zEsgpX-0>" %}

### KOI & KOI 2 Comparisons

<figure><img src="/files/6SmIAWpD1756mWlRxEmH" alt=""><figcaption></figcaption></figure>

### KOI 2產品參數

<figure><img src="/files/dHa8JCPnaE8KzZTpb0cR" alt=""><figcaption></figcaption></figure>

· Chipset: K210

· Supports: Microbit, Futureboard, Arduino and any MCU with serial capabilities

· Display: 1.3 inch 240x240 IPS

· Camera: 640x480 RGB

· Audio: Mono Speaker, 48kb/s sample rate / Mono Microphone, 8kbit/s sample rate

· SD Card Slot: Maximum 16GB

· Wifi: ESP32 Wifi

· Data Out: UART / USB

· Buttons: 2 Programmable Buttons

· Required Voltage: 5V

· Programming Platforms:

1. Kittenblock
2. Makecode
3. Micropython
4. [ObjectBlocks](https://www.objectblocks.cc/)

### KOI & KOI 2 Differences

1. Colour

&#x20;        KOI 1: Light Blue ; KOI2: Orange

2. Power Connector

&#x20;        KOI: micro USB  ; KOI 2 : Type C。

<figure><img src="/files/RqFmZLxaO6AxWA27KGxg" alt=""><figcaption></figcaption></figure>

a


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://sharinghub-eng.kittenbot.hk/airelated/ai-camera-koi-2/ai-camera-koi-2-info.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.