Smart Fortune God - Grove Shield for Seeed Studio XIAO - dumpling—li - CodeCraft Hub
Scene: Smart Home. Edge AI application on CodeCraft Hub for Smart Home use cases.
Devices / BOM: Grove Shield for Seeed Studio XIAO, Grove Vision AI V2, Seeed Studio XIAO ESP32S3, Grove - VART Crossover Cable 4Pin 20cm (5pcs), MP3 Module V4.0, UART Interface, mini MP3 Player/Walkman, powered by WT2605X, 2mm plywood or acrylic, R型膨胀铆钉, M3*60双通六角隔离柱
Smart Home application on CodeCraft Hub. This AI God of Wealth installation uses facial recognition to deliver personalized voice interactions. How it works: It plays exclusive VIP blessings when identifying the owner, offers humorous greetings for visitors, and remains completely silent when no one is detected in the frame.
Documentation
This project is an AI God of Wealth (Caishen) interactive installation powered by visual camera and facial recognition technology. The system detects individuals in the frame in real time through the camera and delivers tailored voice feedback based on the recognition results.
Interactive Features
Owner Recognition: When the system recognizes the owner, the God of Wealth plays an exclusive blessing, such as, "VIP client of the God of Wealth detected! Prioritizing today's delivery of good luck!" This creates a personalized, humorous, and engagingly ritualistic interactive experience.
Visitor Recognition: When the system recognizes unrecognized individuals, the God of Wealth plays a playful visitor welcome message, such as, "Welcome! Quotas for getting rich are limited, please line up first." This significantly enhances the fun and interactive appeal.
Standby Mode: When no one is detected in the camera's view, the system remains completely silent and provides no response.
Design Concept and Applications
This project seamlessly integrates facial recognition, voice broadcasting, and traditional God of Wealth cultural elements, empowering a classic cultural figure with smart interactive capabilities.
Compared to standard "detect and play" devices, this system reacts dynamically according to different identities. This highlights the practical value of facial recognition while making the installation much more unique and entertaining. It is highly suitable for a variety of scenarios, including homes, retail shops, exhibition halls, festive events, and tech project showcases.
Deploy steps
- Burn the model
This is an image classification vision model trained using the Vision AI V2, with three categories: me, other people, and no one.
If you want to customize your own visual recognition model, you need to retrain it.
Deploy an AI model to your device (in-app tool on CodeCraft Hub).
- Hardware Connection
Insert the XIAO ESP32-S3 into the Grove Shield: Ensure the USB port aligns with the shield's orientation and press the pins firmly into place.
Connect the XIAO ESP32-S3 to your computer via a USB Type-C cable. Note: The Type-C cable must be a data cable, not a charging-only cable.
Connect the Vision AI V2 module (visual input) to the XIAO-ESP32's SDA/SCL pins.
GND → XIAO GND
VCC → XIAO 3.3V
SDA → XIAO D4
SCL → XIAO D5
Insert a FAT32‑formatted memory card, connect a speaker, then connect to the XIAO board's serial port. TX and RX are crossed (not side-by-side)!!!!
GND → XIAO GND
VCC → XIAO 3.3V
RX → XIAO D6
TX → XIAO D7
- Firmware Flashing
This application supports the XIAO ESP32‑S3 . Select the corresponding firmware based on your board.
Click the "Flash Firmware" button below, follow the prompts to select the appropriate serial port, and connect the device.
If the device is not recognized, double‑click the Reset button on the XIAO to enter Download Mode, then try again.
Flash firmware to your device (in-app tool on CodeCraft Hub).
- Powering On and Usage
After flashing is complete, press the reset button on the XIAO‑ESP32‑S3. The system will enter "Standby Sensing" mode.
Use the Vision AI V2 to train an image classification model. You can define three image categories:
You (the target person)
Other people (non-target individuals)
Environment (no one present – simply take photos facing an empty room)
Prepare a FAT32-formatted memory card. Save two audio recordings to the root directory as 0001.mp3 and 0002.mp3 (or 0001.wav and 0002.wav).
When the target subject faces the camera, the speaker plays 0001 (.mp3/.wav). The audio message is: "VIP client of the God of Wealth detected! Prioritizing today's delivery of good luck!"
When other individuals face the camera, the speaker plays 0002 (.mp3/.wav). The audio message is: "Quotas for getting rich are limited, but here is a blessing for you first."
If no one appears in the frame, the speaker remains silent.
点击链接，查看（抖音）作品视频：https://v.douyin.com/a4bxairnIwg/
- Future Expandable Directions
Voice Content Randomization: Prepare multiple humorous voice lines for each identity category. The system will randomly select and play one upon recognition to avoid monotony. For example, visitor messages could randomly play "Quotas for getting rich are limited, please line up first" or "The God of Wealth suggests you don't spend recklessly today."
Action Control Upgrades: Integrate servos, motors, or lighting modules to enable the God of Wealth to nod, wave, light up, or shake a gold ingot (yuanbao) upon detecting a person. This achieves a fully interactive experience where the installation can "talk, move, and glow."
Emoji / Screen Animation Linkage: If the installation is equipped with a screen, it can synchronously display God of Wealth expressions, gold coin animations, red envelope (hongbao) animations, or funny subtitles while playing audio, significantly enhancing the visual impact of the interaction.
AI-Generated Blessings: Future iterations can integrate Large Language Models (LLMs) to allow the God of Wealth to dynamically generate blessings based on the time of day, holidays, user identity, or status. For instance, it could say, "A prosperous start to your wealth today!"…
- File
0001.mp3
0002.mp3