IDS peak 2.10.0 / uEye+ firmware 3.34

IDS Peak comfortSDK, genericSDK, IPL, and AFL developer manuals are external documents. Please contact us if you need them.

1.Open IDS peak Cockpit.

2.Open a camera.

3.Configure camera parameters such as frame rate, exposure time, etc.

4.Click on in the camera window to open the "Inference" dialog.

5.Click on behind "File" to open the file selection dialog.

6.Select a network for classification (*.pcla) or object detection (*.pdet).

7.Click on "Add".

8.An additional display for the loaded network is shown in the dialog.

9.You can generally set whether the labels should be displayed and with which font size they are displayed in the camera window.

10.After loading, the network is automatically enabled for image analysis.
Use the "Enable" switch to disable the AI-based image analysis for a network.

11.Under image preprocessing, you see the time in milliseconds that is required for image processing before the AI-supported image analysis. This is, for example, conversion to the required pixel format, scaling, etc.

12.Under inference time, you see the processing time of the neural network in milliseconds.

13.Use the confidence threshold to define from which confidence score on a result is displayed.

Below the confidence threshold, the results are displayed. Additionally, the objects found are highlighted with boxes in the camera image and the corresponding results are displayed.

Fig. 302: Object detection in IDS peak Cockpit