> For the complete documentation index, see [llms.txt](https://sharinghub-eng.kittenbot.hk/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sharinghub-eng.kittenbot.hk/airelated/ai-camera-koi-2/ai-camera-koi-2-info.md).

# 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