IP67-rated CM4 AI camera uses Raspberry Pi Compute Module 4 for computer vision applications

EDATEC ED-AIC2020 is an IP67-rated, Raspberry Pi CM4-based industrial AI camera equipped with a fixed or liquid lens and LED illumination that leverages the Raspberry Pi Compute Module 4 to run computer vision applications using OpenCV, Python, And Qt.

We’ve previously written about Raspberry Pi Compute Module-based smart cameras such as the Q-Wave Systems EagleEye camera (CM3+) working with OpenCV and LabVIEW NI Vision and the StereoPi v2 (CM4) with stereo vision. But the EDATEC ED-AIC2000 is the first ready-to-deploy Raspberry Pi CM4 AI camera we’ve covered so far.

EDATEC “CM4 AI camera” (ED-AIC2020) specifications:

SoM – Raspberry Pi Compute Module 4 up to 8GB RAM, up to 32GB eMMC flash
Camera
- 2.0MP global shutter or 5.0MP rolling shutter
- Acquisition rate – Up to 70 FPS
- Aiming point – Red cross laser
- Built-in LED illumination (optional)
- Scanning field
  - Electronic liquid lens
  - Fixed focal length lens
Networking
- Gigabit Ethernet M12 port
- Communication protocols – Ethernet/IP, PROFINET, Modbus TCP, TCP/IP, MC (MELSEC)
Expansion – M12 connector with 4x optical isolated GPIO and RS232
Misc – Power, Failure, Good Read, and Network LEDs
Power Supply – 10 to 30V DC up to 1.5A @ 24V DC (36W) via M12 connector (shared with expansion port)
Dimensions – 75 x 54 x 50mm (Industrial blue aluminum shell)
Weight – 150 grams
Temperature Range – Storage: -40°C to 70°C
Humidity – 5% to 90% relative humidity, non-condensing
IP Rating – IP65 and IP67
Shock Resistance – EN 60068-227, 30 g, 11ms, 3 impacts per axial direction
Vibration Resistance – EN 60068-26, 14 mm @ 2 to 10 Hz, 1.5mm @ 13 to 55 Hz; 2 g @ 70 to 500 Hz; 2 hours per shaft.

EDATEC provides a camera SDK with OpenCV 4.5.4, Python 3.7, and Qt pre-installed, and lists support for YOLO V5 and V8, third-party Machine Vision Libraries like Halcon, AVS and more. But the company’s CM4 AI camera appears to be especially suited to barcode/QR code and OCR applications with EDATEC highlighting support for one-dimensional codes (Code 39, Code 93, Code 128, I 2 of 5, UPC/EAN), two-dimensional codes (Data Matrix, DotCode, MaxiCode, PDF417, Micro PDF417, QR Code, Micro QR), and optical character recognition capabilities with OCR-A, OCR-B, MICR, and trained OCR.

Samples of the EDATEC ED-AIC2020 CM4 AI camera can be purchased on Aliexpress for $238 and up plus pricy shipping ($77 to the US) because only DHL and FedEx shipping options are available.

There are three somewhat confusing options:

No Accessories – $238 for the CM4 AI camera only.
Accessories – $55 for the accessories only, i.e. M12 cables and mounting attachments.
Accessories included – $293 for the CM4 AI camera and accessories.

We’re not told which Raspberry Pi CM4 module is included in the camera sold on Aliexpress. More details may also be found on the product page.

Jean-Luc Aufranc (CNXSoft)

Jean-Luc started CNX Software in 2010 as a part-time endeavor, before quitting his job as a software engineering manager, and starting to write daily news, and reviews full time later in 2011.