This module is to learn about basic image filtering. It was developed to allow students to instantly observe the effects of different filters and their parameters on live video. The module implements a variety of filters using OpenCV. Each filter exposes some paremeters (e.g., kernel size) that can be set interactively to understand their effects onto the filter behavior.
How to use this module
- On JeVois-Pro, select the effect and set its parameters in the Parameters tab of the GUI. You can also drag the cyan handles left and right on screen to change which portion of the image is shown as original vs processed.
- On JeVois-A33, either try it with JeVois Inventor using YUYV 640x240 @ 30 fps. Note that each time you select a new
effect, this will affect the set of parameters that are available for that effect, but currently JeVois Inventor has no way of being notified of that change. So just click to another tab (e.g., the Info tab), and then back to the Parameters tab each time you change the effect. This will refresh the parameter list.
- Or, open a video viewer on your host computer and select YUYV 640x240 @ 30 fps (see JeVois-A33 Quickstart user guide)
- Open a serial communication to JeVois (see Command-line interface user guide)
help and observe the available parameter called
- Start by setting the
effect parameter to a given effect type. For example:
setpar effect Median or
setpar effect Morpho (commands are case-sensitive).
help to see what additional parameters are available for each effect. For example, for Median, you can adjust the kernel size (parameter
ksize). For Morpho, you can select the type of morphological operation (parameter
op), structuring element shape (parameter
kshape) and size (parameter
setpar effect Morpho
setpar op Open
setpar ksize 7 7
With JeVois v1.5 and above, you may want to use
help2 instead of
help, which is a shorter and more compact help message that shows parameters and commands of the running machine vision module only (and no general parameters related to the JeVois core).