Gravity: AI Vision Gesture and Posture Sensor

SKU: SEN0670

The Gravity: AI Vision Posture and Gesture Sensor is revolutionizing smart home control and interactive art with its ability to recognize and learn human postures and gestures without coding. Designed for robot interactions, this sensor supports three recognition modes—gesture and skeleton—and offers one-click learning for personalized interactions. Its low power consumption allows battery-powered and long-term use. With compatibility for micro:bit, Arduino, and ESP32, and support for MakeCode and Arduino IDE, it lowers the barrier for creators. The sensor processes data locally, ensuring privacy and fast response. Ideal for hobbyists, it addresses challenges like high entry barriers and complex model training, making personalized body interaction projects easy to implement.

  • Docs
  • Tech Specs
  • 1. Getting Started

    Covers AI posture and gesture sensor SEN0670 getting started, from custom gesture recognition, custom posture recognition, fixed gesture mode to PC host software tutorial. Guides through hardware connection, CH343 driver, keypoints data and similarity threshold settings, linking to Docs → Tutorials → Projects → SKU → Category.

    2. Example Code for Arduino - Custom Gesture Recognition

    The tutorial demonstrates how Arduino can use AI pose and gesture sensor SEN0670 and ESP32 controller DFR0654 for custom gesture recognition. Covering I2C/UART wiring, library installation, and example code to confidently detect learning gestures and unknown gestures, and output keypoint coordinates

    3. Example Code for Arduino - Custom Posture Recognition

    Step‑by‑step guide to Arduino custom posture recognition with AI posture and gesture sensor SEN0670 and FireBeetle 2 ESP32‑E: hardware list, I2C/UART wiring, Arduino IDE setup, DFRobot_HumanPose library, and example code to classify learned vs unknown postures.

    4. Example Code for Arduino - Fixed gesture recognitionNew

    Covers Arduino fixed gesture recognition using AI posture and gesture sensor SEN0670 with ESP32. Guides from hardware wiring (I2C/UART) → Arduino IDE + DFRobot_HumanPose library → set fixed gesture model → read gesture ID, name, confidence.

    5. Example Code for Arduino - Detecting Gesture with ID=1

    FireBeetle 2 ESP32-E enables gesture detection with the AI Vision Posture Sensor. Setup includes hardware, Arduino IDE, and library guide. Follow the I2C wiring and use provided sample code for detecting learned gestures and controlling the onboard LED.

    6. Example Code for Arduino - Get Learned Gesture ListNew

    Step-by-step guide to wire the AI posture and gesture sensor SEN0670 to FireBeetle 2 ESP32-E, install DFRobot_HumanPose in Arduino IDE, and run example code to print the learned gesture list via I2C.

    7. Example Code for Arduino - Sleep and Wake-up

    This tutorial on Firebeetle 2 ESP32-E covers implementing timed sleep and wake-up using a gesture sensor. It includes hardware setup, Arduino IDE software installation, and step-by-step code execution for seamless project integration.

    8. Example Code for Arduino - Setting the UART Baud RateNew

    Explain how to use Arduino UART baud rate example to configure AI posture and gesture sensor over ESP32 hardware serial, including UART wiring, IDE setup, and sample code.

    9. Example Code for AT commandNew

    This article compiles AT command example codes and UART AT communication, covering AT+INVOKE inference calls, model switching AT+MODEL, TSCORE/TIOU/TSIMILARITY threshold configuration, and gesture/posture learning instructions.

    ReferenceNew

    Docs → Tutorials → Projects → Arduino vision sensor API、human pose detection、hand keypoints、gesture recognition guide

    Specification

    Power Parameters

    Parameter Specification
    Supply Voltage 3.3V–5V
    Logic Level 3.3V
    Operating Current Typical [email protected]
    Sleep Current Typical 37μ[email protected] (low-power mode required)
    Wake-up Method WAKEUP pin

    Interface Parameters

    Parameter Specification
    Communication I2C / UART
    Connector PH2.0-4P / 2.54mm pin header
    Debug/Config Port USB Type-C receptacle
    I2C Address 0x3A
    UART Default Baud Rate 921600 bps
    UART Protocol Modbus RTU

    Recognition Parameters

    Parameter Specification
    Hand Keypoints 21 keypoints
    Human Skeleton Keypoints 17 keypoints
    Fixed Gesture Types 13 fixed gestures
    Custom Gesture Capacity Up to 8, deletable and re-learnable
    Custom Posture Capacity Up to 8, deletable and re-learnable
    Gesture Recognition Range 0.1–1m under adequate lighting (0.5m recommended)
    Posture Recognition Range 2–4m under adequate lighting (2m recommended)
    Gesture Recognition Frame Rate ~5 FPS
    Skeleton Recognition Frame Rate ~10 FPS
    Hand Recognition Single-hand only; custom gestures limited to one hand at a time, even with multiple hands present
    Posture Recognition Multi-person supported; custom postures limited to one person at a time, even with multiple people present
    Recognition Type Static actions only; dynamic actions not supported
    Camera Resolution 640 × 480 (VGA)
    Camera Field of View (FOV) 89° diagonal (DFOV)
    Camera Effective Focal Length (EFL) 3.01mm

    Physical Dimensions

    Parameter Specification
    PCB Size 37mm × 37mm
    Mounting Hole Spacing 30mm
    Mounting Hole Diameter 3.2mm

    Pinout

    SEN0670-Pinout

    No. Name Function Description
    VCC Power Supply Positive (3.3~5.5V)
    GND Power Ground
    C/R I2C Clock Line SCL / UART Receive Pin RXD (3.3V Logic Level)
    D/T I2C Data Line SDA / UART Transmit Pin TXD (3.3V Logic Level)
    WAKEUP Pull high to wake up the sensor, pull low to enter low-power mode. Used to control the operating state on demand and reduce power consumption.
    USB Type-C Interface 1. Connect to the configuration software to view the sensor's recognition image and recognition data.
    2. Connect to the configuration software to set up custom learned gestures and poses.
    I2C/UART Communication Mode Selection Switch Factory default is I2C communication mode with slave address 0x3A. The sensor must be re-powered on after switching the communication mode.

    Was this article helpful?

    TOP