DF Robot AI 3D Vision Sensor

The DF Robot AI 3D Vision Sensor is a fully self-contained binocular AI recognition module designed for secure, contactless identity authentication. It integrates an AI main processor with dual 2-megapixel cameras—one color and one infrared—enabling reliable recognition in complete darkness as well as outdoor environments with non-direct sunlight. All AI processing is performed locally on the module using embedded deep neural network algorithms, eliminating any computation requirements on the host system and enabling true plug-and-play integration.



Running a fast-boot Linux operating system, the sensor supports advanced binocular 3D liveness detection to effectively prevent spoofing using photos or videos. It combines face recognition, palm vein recognition, palm print recognition, and QR code decoding into a single compact module, making it ideal for multi-factor identity verification systems. Recognition results are output via UART, while real-time color video can be streamed over USB using UVC for local display or remote transmission. With dual power modes, ultra-low standby consumption, and high recognition accuracy, this sensor is well suited for upgrading both new and existing products that require secure, offline biometric authentication.

Quick Spec

• SoC: Arm CPU @ 900 MHz, NPU @ 0.5 TOPS, RISC-V @ 600 MHz
• DDR2: 64 MB
• Flash: 32 MB
• Cameras: Dual 1/5″ CMOS, 2 MP, dual MIPI interfaces
• Lens: FOV 83° diagonal; optimal focus 60 cm
• LED: IR @ 850 nm, RGB @ 650 nm (90° illumination)
• USB: UVC video transmission (expandable to UAC); MJPEG output (H.264 / YUY2 expandable)
• Communication: UART @ 115200 baud
• Supply voltage: 5–12 V
• Operating current: 320–330 mA @ 8 V
• Standby current: 120–130 mA (auto-detection mode)
• Shutdown current: 0 µA (non-auto-detection mode)
• Operating temperature: −20 °C to +60 °C
• Storage temperature: −30 °C to +70 °C
• Humidity: 10–93 % RH (non-condensing)
• Audio I/O: Expandable (speaker / microphone)
• Boot time: 900 ms–2.5 s (varies with stored user count)
• User capacity: 1,000 faces; 1,000 palm veins
• Algorithms: Binocular liveness detection, deep-learning face recognition, palm vein recognition, QR code recognition
• Liveness metrics: FAR ≤ 1 %, FRR ≤ 1 %
• Face recognition: Pass rate 98.85 %, FAR 0.001 %, recognition angle ± 20° pitch / yaw, supports multi-angle enrollment
• Detection range: Face 30–120 cm; Palm vein / QR code 15 cm
• Dimensions: 57.8 × 20 × 10.12 mm

Dimensions

Product Video

Board Layout

• Motherboard: The algorithm motherboard uses an AI main chip and a Linux quick-start operating system. It has transplanted face recognition, palm print and vein, and QR code algorithms, and developed application firmware, which mainly realizes the functions of registration and recognition, and outputs recognition results.
• Dual cameras: Includes color and infrared cameras, using a 2-megapixel CMOS chip with an 850 lens and a 650 lens.
• Infrared light & white light: (White light can be used. When white light is not used, black and white images are displayed in the dark) The function of infrared light is to provide real-time fill light for infrared camera. The function of white light is to automatically start fill light when the environment is not bright enough to ensure the clarity of infrared and color images.
• Foam: Used to isolate the fill light and COMS to prevent light from entering COMS and causing image glare.
• Built-in algorithm:
• Binocular face liveness detection algorithm
• Deep learning face recognition algorithm
• QR code recognition algorithm

Wiring Diagram

Resources

• Product Page
• Product Wiki
• Development Manual
• GUI

Shipping List

• 1 x DF Robot AI 3D Vision Sensor
• 1 x 1.25mm 4-pin to Dupont female connector cable
• 1 x USB data cable