Self-learning AI Camera

TURCK Intelligent Vision (TIV) brings artificial intelligence directly to the line – robust, flexible, and fast

With its new AI camera TIV, TURCK promises a paradigm shift in industrial image processing: instead of complex programming, all you need to do is train the intelligent camera with a few sample images. TIV (TURCK Intelligent Vision) learns patterns and differences independently and reliably recognizes good and bad parts or different classes. The training and execution of the neural networks takes place directly on the camera, supported by a powerful 12-megapixel global shutter sensor (Sony Pregius S, 4th generation) and an NVIDIA Jetson Nano GPU with 4 GB RAM. Image processing runs in real time on the device.

With four pre-installed AI apps – Difference Check, Classifier, Detector, and Code Scan – the TIV12MG-Q110N covers key industrial image processing tasks: from completeness checks and classification to object detection and 1D/2D code recognition. The camera recognizes and evaluates test areas separately, delivering coordinates, confidence scores, and IO/NIO signals directly to PLCs or IT systems. Thanks to the C-mount connection, standard lenses can be used flexibly; an optional protective tube brings the system up to IP67 protection class. The entire control system, lighting technology, sensors, and power supply are decentralized and robust – ideal for use directly on the line.

Operation is intuitive via the web browser. Integration into the TURCK Automation Suite (TAS) facilitates device management and integration into digital maintenance and monitoring processes. M12 connections for power, network, trigger, and I/O allow the camera to be flexibly integrated into existing systems. On-premise operation, transferable data sets, and neural networks enable scalable rollouts without additional edge hardware or licensing costs.