Method of generating a framed video system

Patent metadata

Field	Value
Publication number	US-9904979-B2
Application number	US-201514825963-A
Country	US
Kind code	B2
Filing date	Aug 13, 2015
Priority date	Aug 19, 2014
Publication date	Feb 27, 2018
Grant date	Feb 27, 2018

Abstract

A method to frame a video stream is provided. A video stream is captured, then motion of the camera, object presence in the video stream, and position of the object are detected. A framed video stream is generated using a framing in dependence on the motion of the camera and the position of the object. A system for framing a video stream is also provided, wherein the system comprises a camera and a processing unit, and the processing unit comprises at least one processor and at least on memory including computer program instructions to execute a method to frame a video stream.

First claim

What is claimed is:

1. A method of framing a video stream, the method comprising:
capturing a video stream having frames using a camera, an object being present in the video stream during at least part of the frames;
detecting a motion of the camera;
detecting the presence of the object in the video stream;
determining a position of the object within at least one frame in which the object is present; and
generating a framed video stream using a framing in dependence on the motion of the camera and also in dependence on the position of the object, a relative degree of dependence on the motion of the camera and dependence on the position of the object being dependent on a relative weighting factor, the relative weighting factor depending on a detection score assigned to the object by the detecting the presence of the object.

2. The method according to claim 1 , wherein the dependence is determined by the presence of the object such that:
the framing is in dependence on the motion of the camera when the object is not present in the video stream; and
the framing is in dependence on the position of the object when the object is present in the video stream.

3. The method according to claim 2 , wherein the framing is simultaneously dependent on the motion of the camera and on the position of the object when the object is present in the video stream.

4. The method according to claim 1 , further comprising applying spatial filtering or temporal filtering to determining the relative weighting factor.

5. The method according to claim 1 , further comprising applying spatial or temporal filtering to the motion of the camera or to the position of the object.

6. The method according to claim 1 , wherein the framing comprises scaling the video stream for obtaining a size of the object in the framed video stream substantially equal to a predetermined size with respect to a size of frames of the framed video stream.

7. The method according to claim 1 , wherein the generating the framed video stream comprises positioning the object in a position offset from a centre of frames of the framed video stream, the offset depending on an orientation of the object.

8. The method according to claim 1 , wherein a set of frames of the captured video stream have a first resolution, and wherein the generation of the framed video stream comprises cropping the set of frames of the captured video stream, such that frames of the framed video stream have a second resolution lower than the first resolution.

9. The method according to claim 1 , wherein the object is a person.

10. A system for framing a video stream, the system comprising a camera and a processing unit;
wherein the processing unit comprises:
at least one processor; and
at least one memory including computer program instructions, the at least one memory and the computer program instructions being configured to, with the at least one processor, cause the apparatus to:
capture a video stream having frames using the camera, an object being present in the video stream during at least part of the frames;
detect a motion of the camera;
detect the presence of the object in the video stream;
determine a position of the object within at least one frame in which the object is present; and
generate a framed video stream using a framing in dependence on the motion of the camera and also in dependence on the position of the object, a relative degree of dependence on the motion of the camera and dependence on the position of the object being dependent on a relative weighting factor, the relative weighting factor depending on a detection score assigned to the object by the detecting the presence of the object.

11. The system according to claim 10 , wherein the camera and the processing unit are integrated in a single apparatus.

12. The method according to claim 1 , further comprising applying spatial filtering and temporal filtering to determining the relative weighting factor.

13. The method according to claim 1 , further comprising applying spatial filtering and temporal filtering to the motion of the camera or to the position of the object.

14. The method according to claim 1 , further comprising applying spatial filtering and temporal filtering to the motion of the camera and to the position of the object.

Assignees

• Apical Ltd
• Apical Ltd

Inventors

• Tusch Michael
• Romanenko Ilya

Classifications

• H04N23/6811 Primary

  based on the image signal · CPC title

• H04N23/683

  performed by a processor, e.g. controlling the readout of an image memory · CPC title

• H04N23/68

  for stable pick-up of the scene, e.g. compensating for camera body vibrations · CPC title

• G06T3/40 Primary

  Scaling of whole images or parts thereof, e.g. expanding or contracting · CPC title