Imago Technologies GmbH “VisionAI” is a programmable Smart AI camera that combines a quad-core Cortex-A53 processor @ 1.8 GHz together with Google Edge TPU, and designed for embedded image processing applications in the fields of AI, Deep Learning, and Machine Learning.
The smart camera supports TensorFlow Lite and AutoML Vision Edge frameworks, and is suited for tasks such as pattern recognition, classification, anomaly or defect detection in inspection applications, code reading, and other machine vision applications.
Imago VisionAI (VisionSensor PV3 AI) camera specifications:
- SoC – Unnamed quad-core Arm Cortex-A53 processor @ 1.8 GHz (likely NXP i.MX 8M Mini)
- AI Accelerator – Google Edge TPU with up to 4 TOPS of AI processing power
- System Memory – 2 GB DDR4 RAM
- Storage – MicroSD card up to 32GB
- Connectivity – Gigabit Ethernet M12 connector
- 1/1.8” 5MP mono or color CMOS sensor with 2560 × 1936 pixels resolution, up to 65 fps frame rate, 2.8 μm pixel size, partial scan support
- C-mount lens mount with optional lens protection tube
- LED strobe synchronized with shutter
- I/Os – 8-pin M12 connector with 2x Inputs, 4x Outputs, 24V
- Misc –
- Power Supply – 24 VDC / (21….28 V)
- Dimensions – 50 x 50 x 40.1 mm without tube. 4x M3 mounting holes
- Weight – 198 grams with cables
- Temperature Range – +5°C … +40°C
The VisionAI camera runs a Debian-based Linux OS, and is programmable to meet the application needs through a Linux SDK with a VisionBox Interface C++ Library, an FG camera library, and support for TensorFlow Lite or AutoML Vision Edge. Imago also provides example programs and a video training course. The Linux distribution is most like the same Debian-based Mendel Linux distribution developed by Google for Coral boards and also supporting TensorFlow Lite and AutoML Vision Edge.
The kit also comes with two 50cm M12 cables for Ethernet and I/Os. M12 connectors are typically used to waterproof the system, but the company did not provide an IP rating for the camera. But there must be some level of dust and/or waterproofness, as the camera is said to be suitable for the food and pharmaceutical sectors, besides electronics and logistics industries.
Imago Technologies did not provide availability nor pricing information. More details, including 3D files and SDK documentation, can be found on the product page.
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.