Dense Optical Flow Annotations

Annotator to extract dense Optical Flow using Gunnar Farneback’s algorithm.

class dvt.annotate.opticalflow.OpticalFlowAnnotator(**kwargs)

Bases: dvt.abstract.FrameAnnotator

Annotator to extract dense Optical Flow using the opencv Gunnar Farneback’s algorithm.

The annotator will return an image or flow field describing the motion in two subsequent frames.

freq

How often to perform the embedding. For example, setting the frequency to 2 will computer every other frame in the batch.

Type:int

raw

Return optical flow as color image by default, raw returns the raw output as produced by the opencv algorithm.

Type:bool

frames

An optional list of frames to process. This should be a list of integers or a 1D numpy array of integers. If set to something other than None, the freq input is ignored.

Type:array of ints

output_dir

optional location to store the computed images. Only used if raw is set to False.

Type:string

size

What should the size of the output images be? Set to None, the default, to preserve the size as given in the input file. Given as the desired height; the width will be scaled to keep the aspect ratio.

Type:int

name

A description of the aggregator. Used as a key in the output data.

Type:str

annotate(batch)

Annotate the batch of frames with the optical flow annotator.

Parameters:batch (FrameBatch) – A batch of images to annotate. Returns:A list of dictionaries containing the video name, frame, and the optical flow representation. The latter has the same spatial dimensions as the input.

name = 'opticalflow'