IDS NXT Release 3.0: Intelligent cameras can now detect anomalies
Free update makes third deep learning method available for IDS NXT cameras
How can a camera be taught to reliably detect deviations from the norm if they are not or not completely predictable? Rule-based image processing would have to capitulate - with the AI system IDS NXT, on the other hand, such a challenge can be easily solved from now on. In the new IDS NXT 3.0 release, we are making anomaly detection available to all customers as a third AI method, in addition to object detection and classification.
You can even use only "GOOD" training images for training anomaly detection. In addition, relatively little training data is required compared to the other AI methods. This simplifies the development of an AI vision application and is well suited for evaluating the potential of AI-based image processing for projects in a company.
Another highlight of the release is the code reading function in the block-based editor. This enables the IDS NXT cameras to quickly and easily locate, identify and read out different types of code and the required parameters. Attention maps in IDS lighthouse now also provide more transparency in the training process. They illustrate which image areas have an impact on classification results. This allows you to identify and eliminate training errors before the neural network is deployed in the camera.
