Gravity: Offline Edge AI Gesture & Face Detection Sensor – 5 Gestures, 10 Faces, 3m (Arduino/ RPi/ ESP32)
- Delivery nationwide via The Courier Guy — R150 flat, free over R2,000
- Free collection from our Milnerton (Cape Town) warehouse
- Secure checkout — PayFast card payment or EFT
- Questions? WhatsApp us on +27 65 900 8570
Description
The Gravity: Offline Edge AI Gesture & Face Detection Sensor delivers real-time computer vision processing directly on-device without requiring internet connectivity or cloud servers. Equipped with an onboard AI processor and camera, it recognises five distinct hand gestures and tracks up to ten human faces at distances up to three metres. It is well suited for makers, educators, and engineers creating touchless interfaces, presence-aware appliances, and interactive robotics using Arduino, ESP32, or Raspberry Pi.
Onboard private edge AI computing
All vision and recognition algorithms run locally on the integrated processor, ensuring full data privacy with no cloud storage or transmission. The module operates at a low current draw of 100mA, making it well suited for energy-conscious standalone projects.
Five-gesture contactless recognition
The sensor identifies five predefined hand gestures at distances between 0.5 and 3 metres, including thumbs-up, OK, open palm, V sign, and call me. Each detected gesture provides immediate visual feedback via an integrated multi-colour RGB LED and can trigger a low-level interrupt signal.
Multi-person presence and coordinate tracking
The sensor detects human presence by identifying the head-and-shoulders area, tracking and counting up to ten individuals simultaneously. It outputs real-time head count, confidence scores from 0 to 100, and X/Y position coordinates on a 0 to 640 scale for tracking applications.
Optimised wide-angle detection range
With an 85-degree diagonal field of view and a 3-metre detection range, the module maintains reliable coverage across desktop setups and wider room environments. An onboard status LED illuminates whenever a human face is present in the frame.
Dual communication and platform compatibility
The board supports both I2C and UART Modbus communication and operates across 3.3V to 5V power supplies. It connects smoothly to microcontrollers such as Arduino, ESP32, and Raspberry Pi, and is compatible with visual programming environments like Mind+ and MakeCode.
Downloads & documentation
Specifications
| Supply Voltage | 3.3V - 5V |
| Level Voltage | 3.3V |
| Operating Current | 100mA |
| Communication Interface | PH2.0-4P / 2.54mm pin header |
| Communication Methods | I2C / UART |
| Default I2C Address | 0x72 |
| Default UART Baud Rate | 9600 |
| UART Protocol | Modbus |
| Interrupt Interface | 2.54mm pin header hole (Low level output on gesture recognition) |
| Gesture Recognition Types | 5, Good (Thumbs-up) / OK (OK gesture) / Stop (Open palm) / Victory (V sign) / Call me (Call me gesture) |
| Recognition Distance (Gesture/Face) | 0.5 - 3 meters |
| Facial Recognition Range | Area above the human shoulders |
| Maximum Recognizable Faces | 10 |
| Recognition Score Range | 0 - 100 |
| Facial Position Coordinate Range | 0 - 640 |
| Gesture Indicator Light | RGB LED - Blue for Good (Thumbs-up), Green for OK (OK gesture), Red for Stop (Open palm), Yellow for Victory (V sign), Purple for Call me (Call me gesture) |
| Facial Indicator Light | Single LED (lit for presence, unlit for no presence) |
| PCB Dimensions | 42mm * 32mm |
| Mounting Hole Spacing | 25mm * 35mm |
| Mounting Hole Diameter | 3.1mm |
In the box
| Gravity: AI Gesture & Face Detection Sensor ×1 | 1 |
| Gravity-4P I2C/UART Sensor Cable ×1 | 1 |
Reviews
No reviews yet — be the first to review this product.
From the same brand
Gravity: 4Pin I2C/UART Sensor Cable (10PCS)
Gravity: Analog CH4 Gas Sensor (MQ4) For Arduino
Gravity: Analog Gas Sensor (MQ2)
3xAAA Battery Holder
You might like
KY-008 650nm Laser Transmitter Module, 5V
Nano I/O Expansion Board for Arduino Nano V2.X and V3.X
1.3-Inch 128x64 Blue SPI OLED Display Module (SH1106)
