VideoFrameCaptureStep is a pipeline step that configures how to extracts a single frame from a video each time inference is called. The video path is hard coded, mainly used for testing/demo purposes.
Location of the video file.
Name of the output key where the image frame will be located. Default name is
Loop the video when it reaches the end. Default is set to
Optional - Number of frames to skip between returned frames. If not set: No frames are skipped. For example:
Value 0: equivalent to no skipping.
Value 1: skip 1 frame between returned frames (i.e., return every 2nd frame).
Value 3: skip 2 frames between returned frames (i.e., return every 3rd frame) and so on.