FAQ | Help

It is currently not possible to create your own function blocks for use in the editor.

The C++ development environment IDS NXT Vision App Creator offers much more possibilities for the design of vision apps.

Yes, this is possible for IDS NXT cameras of the rio/rome series, but they have to be converted into a suitable format. Neural networks on an IDS NXT camera are hardware accelerated by the AI-Core - thus they must be available in a special format. Neural networks trained with IDS lighthouse are already available in the correct format and can be loaded directly onto the camera. If you already train with Keras (with TensorFlow Backend), the conversion of network architectures such as MobileNet is possible with little effort. IDS provides special tools on request. If you need more detailed information or assistance with the conversion, please contact IDS Sales.

Yes, it is possible to use multiple uEye cameras at the same time. The exact number of cameras that can be used simultaneously depends on various factors, including the performance of your computer, the available interfaces (USB, GigE, etc.) and the software used for image processing.

Here are some general points to consider:

1. Computer performance: If you connect several cameras, you may need a powerful computer that is able to handle image processing and data transfer for all cameras simultaneously.
2. Interfaces: The number of cameras you can connect depends on the number and type of interfaces available on your computer. For example, you can connect multiple USB cameras with USB expansion cards. For multiple GigE cameras, you can use Gigabit Ethernet expansion cards and possibly switches. You can also find interface cards in our product portfolio.
3. Software: The software you use for image processing should be able to control multiple cameras simultaneously and process the image data efficiently. Many image processing libraries and software packages offer support for operating multiple cameras.
4. Synchronization: If precise synchronization between the cameras is required, you should ensure that your cameras and the software used support this function.

In our IDS Vision Channel video "How-to multi-camera system", we explain key points to consider when developing a multi-camera system. This includes aspects such as the right interfaces, the different camera families, the right hardware setup and the software.

Yes, this is possible for IDS NXT cameras of the rio/rome series, but they have to be converted into a suitable format. Neural networks on an IDS NXT camera are hardware accelerated by the AI-Core - thus they must be available in a special format. Neural networks trained with IDS lighthouse are already available in the correct format and can be loaded directly onto the camera. If you already train with Keras (with TensorFlow Backend), the conversion of network architectures such as MobileNet is possible with little effort. IDS provides special tools on request. If you need more detailed information or assistance with the conversion, please contact IDS Sales.

Yes. IDS peak is based entirely on GenICam as the communication channel to our uEye+ cameras. But in addition to GenTL producers for GigE Vision® and USB3 Vision®, the SDK includes a special "uEye transport layer", which allows uEye cameras (matchcode "UI-") to be used on the GenICam base and to benefit from the many advantages of the new SDK.

Please note that in addition to IDS peak, the latest version of the IDS Software Suite (4.95 or higher) must be installed. For more information and to operate uEye cameras in IDS peak applications, please refer to the IDS peak manual.

To run neural networks in IDS NXT cameras, an application workflow is needed. A so-called vision app determines how and when images are captured and fed to the AI-based image analysis. The further processing and communication of the results is also determined by the vision app.

For classification and detection there are vision apps available. You only need to configure these with your self-trained networks.

In the cloud-based AI Vision Studio, you can also build your own individual workflows as vision apps for your networks using the block-based editor or the use case assistant. You can also evaluate these with test data before loading and executing the network and app on the camera with the IDS NXT cockpit.

Watch our tutorial video for app creation.

uEye+ industrial cameras are fully vision standard compliant and can be operated via the GigE Vision® and USB3 Vision® protocol standards. This means they work in any GenICam-compliant application without additional IDS software.

Our uEye camera models with USB2, USB3 and GigE interfaces (matchcode "UI-") do not have standard compliant vision firmware and therefore require IDS driver software to operate in a machine vision application. Our new IDS peak camera SDK includes a special "uEye transport layer", which enables the uEye product line to be used via GenICam and to profit from the many advantages of the new SDK.

The app-based concept of the cameras enables the integration of additional communication protocols. The OPC UA Server Vision App is an example of such an add-on.

Via the Vision App Creator, users can create their very own communication channels. The technical article "EyeBot - Vision Guided Robot" describes this use case.

The video "Integration of IDS NXT in manufacturing automation" explains the possibilities for IDS NXT cameras to communicate with their environment.

The ANNs cannot be used with random cameras. IDS lighthouse was specially developed to train neural networks for image processing tasks that can be used with IDS cameras and software. IDS NXT cameras of the rio/rome series are equipped with an AI core developed by IDS, which performs the inference in a hardware-accelerated manner. IDS malibu models work with a special AI accelerator from Ambarella. IDS lighthouse provides the networks for the respective platform in the appropriate format.

Yes, most uEye+ cameras with GigE Vision or USB3 Vision interface support both hardware and software triggers for image acquisition.

• In hardware trigger mode, an I/O signal is used as a trigger for image acquisition. When the camera receives a trigger signal on the line, a single image is captured and transmitted.
• In software trigger mode, a software command is used as the trigger for image capture. The software command is executed by an application software on a host PC and thus transmitted to the camera. When the camera receives the software command, a single image is captured and transmitted.

HW Trigger vs. SW Trigger

The advantage of the software trigger method is that no additional hardware is required, which makes it simple and cost-effective. However, due to the way operating systems work, there can be unpredictable delays between the moment the software command is given and the actual start of image capture. These delays cannot be predicted exactly. Therefore, the software trigger is not ideal for applications that require very precise response times of 10 milliseconds or less. In such cases, a hardware trigger should be used, which enables more reliable and precise control.

User manual:

• Software Trigger
• Hardware Trigger
• Trigger settings in the IDS peak Cockpit

Tech tip: Triggering according to the Lego principle

The trigger capabilities of uEye+ cameras are even more versatile thanks to GenICam and the SFNC. The separation of trigger signals (software) from trigger-capable device inputs (hardware) makes the possible uses of "triggers" even more varied. This means that the triggering of an image acquisition is no longer restricted to one external source. Counters, timers, generated PWM signals or a software event are also possible "signallers". In this tech tip, we show the various possibilities with examples.

The easiest way to make a complaint, return or replace a faulty IDS product is via our RMA process.

The camera parameter "Throughput limit for the device connection" (DeviceLinkThroughputLimit) can be used for this purpose, which defines the maximum data rate (in bytes per second) that a camera can transmit via its interface. This allows the data rate and therefore the necessary performance of the PC system to be reduced or optimized.

Use cases:

• This can be helpful, for example, to optimally use "lower-performance" systems such as a Paspberry Pi.
• With the uEye cameras of the X series, which have no memory, this parameter can be helpful in ensuring stable operation.
• Controlling the maximum data throughput of each camera is also an advantage in multi-camera applications.

Further information:

• "DeviceLinkThroughputLimit" can be found and set in the nodetree of the uEye cameras.
• User manual chapter: Device Link Throughput Limit
• Vision Channel video "How-to multi-camera system"
• Tech tips: "Bandwidth under control" and "clock comparison"

The easiest way to order an inspection, cleaning, repair, etc. is to use the "Repair order" form.

Connect to your camera with the IDS NXT cockpit. Then you can load and activate your trained neural network from the AI vision studio with a vision app.

If you have also created a vision app in IDS lighthouse, the procedure is quite similar. In IDS NXT cockpit, use the Vision App Manager to load, configure or delete apps.

Multiple vision apps may be executed simultaneously.

However, only one vision app can be active that uses the AI accelerator of an IDS NXT camera to execute CNNs. If you want to execute several AI-based analysis steps in sequence, this is also possible in a single app. With the block-based editor in IDS lighthouse, you can easily build such sequences together.

The general costs for a repair can be found in the form for a possible repair order.

Yes, even without any hardware and without any special knowledge about AI, image processing or application programming. All you need is access to our cloud-based AI Vision Studio IDS lighthouse, which you can also use for one month without any restrictions and free of charge.

Our Vision Channel webinar "How to evaluate AI Vision without camera" demonstrates exactly this use case with examples. By following this procedure, you can evaluate your own task independently and see from the results whether the investment in AI Vision hardware is profitable for you.

Maybe the camera firmware is not compatible with the version you built your vision app against in AI Vision Studio. Updating the camera firmware might help. To the latest camera firmware

You can both check the firmware and update it right away via the IDS NXT cockpit.

If you still have problems with it, our support team will be happy to help you.

In case of an incorrect delivery/order, please contact us using our support & returns form. We will then resolve the case as quickly as possible.

In case of an incorrect delivery/order, please contact us using our support & returns form. We will then resolve the case as quickly as possible.

uEye+ represents our industrial cameras, which are accessible via the GigE Vision® and USB3 Vision® protocol standards and are therefore compatible with any GenICam-compliant application. uEye+ is our camera standard. This means that all new camera models and all new sensors are developed exclusively for uEye+. uEye+ cameras can be recognised by their model name. The match codes start with "U3-" for cameras with USB3 interface and "GV-" for cameras connected via Gigabit Ethernet.

We continue to carry many of our proven uEye camera models with USB2, USB3 and GigE interfaces in our portfolio whose match code starts with "UI-". They do not provide a vision standard compliant firmware and therefore require an IDS driver software to operate in a machine vision application. They can still be operated and retrofitted in existing applications.

But for new applications we definitely recommend the new uEye+ cameras and the use of the new modern software environment IDS peak. However, with the GenICam-compliant uEye Transport Layer from the IDS peak SDK, you can also use your existing uEye cameras in new applications with IDS peak and even combine them with new uEye+ cameras.

If you have any further questions about uEye/uEye+, please contact our sales team.

The use case assistant creates simple vision workflows that you can use to test and run your classification, detection, and anomaly networks in an already basic way.

To realise your own individual workflow, you can further develop the assistant app in the block-based editor or completely start there from scratch according to your wishes.

Alternatively, it is also worth taking a look at our online marketplace visionpier. There you will find turnkey solutions, also for IDS NXT.

You can use the vision apps created in IDS lighthouse on any number of IDS NXT cameras without additional runtime license costs or technical restrictions.

The only costs include the all-in user license of the AI Vision Studio and the cameras.

A hot pixel is a pixel of the image sensor that is constantly "on" due to an error and therefore always provides a bright signal, regardless of the actual amount of light that falls on the sensor. This can lead to image errors, especially with long exposures or at high sensor temperatures.

IDS cameras offer adaptive hot pixel correction, which can correct the pixel values of the hot pixels during the runtime of the application. The method is "adaptive" because the corrected pixel values are continuously adjusted to the surrounding pixels in terms of direction and intensity.

Some important points about adaptive hot pixel correction:

    Adaptive hot pixel correction is executed on the host PC.
    Adaptive hot pixel correction can only be used with RAW pixel formats.
    Image pre-processing carried out in the camera influences the hot pixel correction working in the host PC.
    Any subsequent image processing steps on the host PC, e.g. debayering, colour correction, etc., have no impact on the hot pixel correction.

Info sources:

• IDS peak manual: Correcting hot pixels
• IDS peak manual: Host features

Inference means "to conclude". In the context of artificial intelligence, inference refers to the ability to apply "knowledge" acquired through deep learning to new data. An inference camera is thus able to evaluate or categorize newly acquired image content through a pre-trained neural network independently of a PC.

Model-specific information for a specific camera model can be found in the IDS peak manual in section B: Operating uEye+ cameras → Model-specific information

The latest manual for ...

    Cameras with the model name UI- → IDS Software Suite
    Cameras with the model names U3-/GV- → IDS peak & uEye+ firmware