Automatic composition of video with dynamic background and composite frames selected based on frame criteria

Patent metadata

Field	Value
Publication number	US-9930271-B2
Application number	US-201615080280-A
Country	US
Kind code	B2
Filing date	Mar 24, 2016
Priority date	Sep 28, 2015
Publication date	Mar 27, 2018
Grant date	Mar 27, 2018

Abstract

A processing device generates composite images from a sequence of images. The composite images may be used as frames of video. A foreground/background segmentation is performed at selected frames to extract a plurality of foreground object images depicting a foreground object at different locations as it moves across a scene. The foreground object images are stored to a foreground object list. The foreground object images in the foreground object list are overlaid onto subsequent video frames that follow the respective frames from which they were extracted, thereby generating a composite video.

First claim

The invention claimed is:

1. A method for generating a composite output video from an input video having a sequence of frames, the method comprising:
receiving a current video frame for processing from the sequence of frames;
determining, by a processing device, whether the current video frame meets first criteria;
responsive to the current video frame meeting the first criteria, performing, by the processing device, a foreground/background segmentation based on a predictive model to extract a foreground object image from the current video frame, the foreground object image comprising a representation of a foreground object depicted in the current video frame with background pixels subtracted, and storing the foreground object image to a foreground object list that stores a plurality of previously extracted foreground object images;
overlaying each of the foreground object images in the foreground object list onto the current video frame to generate a composite video frame;
determining whether the current video frame meets second criteria; and
responsive to the current video frame meeting the second criteria, updating the predictive model.

2. The method of claim 1 , further comprising:
training the predictive model based on a plurality of training video frames, the predictive model to predict whether a pixel in a given video frame belongs to a background model or the foreground object.

3. The method of claim 1 , wherein determining whether the current video frame meets the first criteria comprises:
determining if a frame number of the current video frame is a multiple of a predefined integer Y.

4. The method of claim 1 , wherein determining whether the current video frame meets second criteria comprises:
determining if a frame number of the current video frame is a multiple of a predefined integer X.

5. The method of claim 1 , wherein performing the foreground/background segmentation comprises:
obtaining a preliminary foreground object image;
applying a filter to reduce noise in the preliminary foreground object image to generate a filtered image;
detecting a filled convex hull region in the preliminary foreground object image;
adding extra pixels from the filtered image to the preliminary foreground object image to generate a temporary image;
discarding pixels in the temporary image outside the filled convex hull region to generate a noisy convex hull image; and
closing gaps in foreground regions of the noisy convex hull image to generate the foreground object image.

6. The method of claim 1 , wherein the predictive model comprises an adaptive Gaussian Mixture Model.

7. A non-transitory computer-readable storage medium storing instructions for generating a composite output video from an input video having a sequence of frames, the instructions when executed by a processor causing the processor to perform steps comprising:
receiving a current video frame for processing from the sequence of frames;
determining whether the current video frame meets first criteria;
responsive to the current video frame meeting the first criteria, performing a foreground/background segmentation based on a predictive model to extract a foreground object image from the current video frame, the foreground object image comprising a representation of a foreground object depicted in the current video frame with background pixels subtracted, and storing the foreground object image to a foreground object list that stores a plurality of previously extracted foreground object images;
overlaying each of the foreground object images in the foreground object list onto the current video frame to generate a composite video frame;
determining whether the current video frame meets second criteria; and
responsive to the current video frame meeting the second criteria, updating the predictive model.

8. The non-transitory computer-readable storage medium of claim 7 , wherein the instructions when executed further cause the processor to perform steps including:
training the predictive model based on a plurality of training video frames, the predictive model to predict whether a pixel in a given video frame belongs to a background model or the foreground object.

9. The non-transitory computer-readable storage medium of claim 7 , wherein determining whether the current video frame meets the first criteria comprises:
determining if a frame number of the current video frame is a multiple of a predefined integer Y.

10. The non-transitory computer-readable storage medium of claim 7 , wherein determining whether the current video frame meets second criteria comprises:
determining if a frame number of the current video frame is a multiple of a predefined integer X.

11. The non-transitory computer-readable storage medium of claim 7 , wherein performing the foreground/background segmentation comprises:
obtaining a preliminary foreground object image;
applying a filter to reduce noise in the preliminary foreground object image to generate a filtered image;
detecting a filled convex hull region in the preliminary foreground object image;
adding extra pixels from the filtered image to the preliminary foreground object image to generate a temporary image;
discarding pixels in the temporary image outside the filled convex hull region to generate a noisy convex hull image; and
closing gaps in foreground regions of the noisy convex hull image to generate the foreground object image.

12. The non-transitory computer-readable storage medium of claim 7 , wherein the predictive model comprises an adaptive Gaussian Mixture Model.

13. A system comprising:
one or more processors; and
a non-transitory computer-readable storage medium storing instructions for generating a composite output video from an input video having a sequence of frames, the instructions when executed by the one or more processors causing the one or more processors to perform steps comprising:
receiving a current video frame for processing from the sequence of frames;
determining whether the current video frame meets first criteria;
responsive to the current video frame meeting the first criteria, performing a foreground/background segmentation based on a predictive model to extract a foreground object image from the current video frame, the foreground object image comprising a representation of a foreground object depicted in the current video frame with background pixels subtracted, and storing the foreground object image to a foreground object list that stores a plurality of previously extracted foreground object images;
overlaying each of the foreground object images in the foreground object list onto the current video frame to generate a composite video frame;
determining whether the current video frame meets second criteria; and
responsive to the current video frame meeting the second criteria, updating the predictive model.

14. The system of claim 13 , wherein the instructions when executed further cause the one or more processors to perform steps including:
training the predictive model based on a plurality of training video frames, the predictive model to predict whether a pixel in a given video frame belongs to a background model or the foreground object.

15. The system of claim 13 , wherein determining whether the current video frame meets the first criteria comprises:
determining if a frame number of the current video frame is a multiple of a predefined integer Y.

16. The system of claim 13 , wherein determining whether the current video frame meets second criteria comprises:
determining if a frame number of the current

Assignees

• Gopro Inc

Inventors

• Adsumilli Balineedu Chowdary
• Lustig Ryan

Classifications

• G06T7/11

  Region-based segmentation · CPC title

• G06T7/143

  involving probabilistic approaches, e.g. Markov random field [MRF] modelling · CPC title

• G06T7/194

  involving foreground-background segmentation · CPC title

• G06T2207/10021

  Stereoscopic video; Stereoscopic image sequence · CPC title

• G06T7/254

  involving subtraction of images · CPC title