DFRobot AI Binocular 3D Vision Recognition Sensor

DFRobot AI Binocular 3D Vision Recognition Sensor is a multi-modal recognition module engineered for high-security and versatile identity authentication. This sensor is equipped with two 2-megapixel high-definition cameras. The cameras use color and infrared cameras, which can be recognized normally in dark environments. This sensor core functionality lies in its three-in-one identification capability, integrating robust face recognition, secure palm vein recognition, and universal QR code scanning into a single, compact device. The vision recognition sensor features advanced 3D liveness Detection for anti-spoofing and local storage for up to 1,000 users.

The AI binocular vision recognition sensor starts quickly and supports both power-off and low-power-consumption and constant-power-supply dual modes. This sensor provides a UART protocol that supports third-party integrated docking and realizes audio and video transmission docking of identity recognition functions. Typical applications include smart home systems, smart door locks, self-service retail payment terminals, 3D face/palm vein payment systems, and palm vein authentication systems.

Features

Binocular 3D liveness detection resists spoofing via photos/videos
Neural network-based algorithms: face recognition, palm vein recognition, and QR code decoding

Operates in complete darkness and non-direct sunlight outdoors
Zero host-computation requirement; all AI processing occurs offline on-module

Applications

Smart home systems
Smart door locks
Self-service retail payment terminals

3D face/palm vein payment systems
Palm vein authentication systems

Specifications

Hardware parameters:
- Arm CPU@900MHz, NPU@0.5TOPS, and RISC-V@600MHz SoC
- 64MB DDR2
- 32MB flash
- Dual 1/5" CMOS, 2MP, and dual MIPI interfaces cameras
- Lens: FOV: 83° diagonal; optimal focus: 60cm
- LED: IR@850nm and RGB@650nm (90° illumination)
- USB: UVC video transmission (expandable to UAC) and MJPEG output (H.264/YUY2 expandable)
- UART@115200 baud communication
Power parameters:
- 5V to 12V supply voltage range
- 320mA to 330mA operating current range at 8V
- 120mA to 130mA standby current range (auto-detection mode)
- 0μA shutdown current (non-auto-detection mode)
10–93% RH (non-condensing) humidity
Expandable (speaker/microphone) audio I/O
900ms to 2.5s boot time (varies with stored user count)
1,000 faces and 1,000 palm veins user capacity

Algorithms:
- Binocular liveness detection
- Deep learning face recognition
- Palm vein recognition
- QR code recognition
Liveness metrics:
- False Acceptance Rate (FAR) ≤1%
- False Rejection Rate (FRR) ≤1%
Face recognition:
- 98.85% pass rate
- 0.001% FAR
- ±20° pitch/yaw recognition angle supports multi-angle enrollment
- Detection range:
  - 30cm to 120cm face
  - 15cm palmvein/QR code
57.8mm x 20mm x 10.12mm dimensions