Arducam KingKong – A Raspberry Pi CM4-based Edge AI camera with global shutter sensor, Myriad X AI accelerator

ArduCam KingKong is a Smart Edge AI camera based on the Raspberry Pi CM4 and system-on-module based on Intel Myriad X AI accelerator that follows the Raspberry Pi 5-powered Arducam PiINSIGHT camera introduced at the beginning of the year. The new product launch aims to provide a complete Raspberry Pi-based camera rather than an accessory for the Raspberry Pi 4/5.

Smart cameras built around the Raspberry Pi CM4 are not new as we previously covered the EDATEC ED-AIC2020 IP67-rated industrial AI Edge camera and the StereoPi v2 stereoscopic camera used to create 3D video and 3D depth maps. The ArduCam KingKong adds another option suitable for computer vision applications with an AR0234 global shutter module, PoE support, and a CNC metal enclosure.

ArduCam KingKong specifications:

• SoM – Raspberry Pi Compute Module 4 (CM4) by default CM4104000 Wireless 4GB RAM Lite (0GB eMMC).
• AI accelerator – Luxonis OAK SOM BW1099 based on Intel Myriad X 4 TOPS vision processing unit
• Image Sensor
  • 2.3 MP ON Semiconductor AR0234 global shutter color CMOS sensor as found in e-con Systems e-CAM20_CURB and See3CAM_24CUG camera modules
  • Optical Size – 1/2.6″
  • Pixel Size – 3 µm x 3 µm
  • Sensor Active area – 1920(H)×1200(V)
  • Output Format – RAW10/YUV/NV12/RGB
  • Video Modes – 4056×3040 @ 30fps, 3840×2160 @ 30fps, 1920×1080 @ 60fps
• Lens
  • Manual focus
  • Focal Length – 3.6mm
  • F.NO – F2.8
  • Field of View(FOV) – 120°(D)×90°(H)×75°(V)
  • Lens Mount – M12 (S-Mount)
  • Distortion – -0.33%
  • IR Sensitivity – Integral IR-cut Filter, visible light only
• Storage – MicroSD card
• Video Output – HDMI port up to 4Kp60
• Networking – Gigabit Ethernet RJ45 port, WiFi 5 and Bluetooth 5 with external antenna
• USB – 1x USB 2.0 Type-A port
• Expansion – M12 connector for some GPIOs
• Misc – External Trigger support
• Power Supply
  • 5V/1A via USB
  • PoE via Ethernet port
• Dimensions – 90 × 45 × 73 mm (CNC enclosure excluding antenna and camera module); four mounting points
• Temperature Range – -20°C to 50°C

The camera runs Raspberry Pi OS and has basically the same capabilities as the Arducam PiNSIGHT add-on leveraging DepthAI to run various computer vision algorithms on the OAK-SOM module such as face recognition, fatigue detection, object recognition, object tracking, anomaly detection, edge detection, and pose estimation, and so on. The Arducam KingKong is also said to come with pre-installed software such as OpenCV, TensorFlow, a Web UI, RTSP Streaming, and support for typical industrial applications. More details, instructions, and tutorials should eventually be made available on the documentation website.

Arducam has started taking pre-orders for the KingKong Edge AI camera for $399.99 with shipping scheduled for the end of the month (March 2024). The price may seem a little high, but the Raspberry Pi CM4-based EDATEC Edge AI camera goes for around $300 without an AI accelerator, so that’s about the price range for this type of hardware.

Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress