Method of processing video data, device, computer program product, and data construct

Patent metadata

Field	Value
Publication number	US-10516916-B2
Application number	US-201916441562-A
Country	US
Kind code	B2
Filing date	Jun 14, 2019
Priority date	Dec 11, 2012
Publication date	Dec 24, 2019
Grant date	Dec 24, 2019

Abstract

The invention relates to a method of processing video data, a device (102) and a computer program product for implementing said method, and a data construct including video data processed by said method. The method processes unprocessed video data into processed video data, said unprocessed video data being provided by picking up (112) sequential images of a situation or scene (100), and includes the steps of: applying a motion and gesture recognition technology (114) in real time to said situation or scene; identifying undesirable image contents contained in said unprocessed video data, based on a result of said motion and gesture recognition, said undesirable image contents preferably including inappropriate body expression (128-132) such as obscene gestures or indecent exposures, and providing content information relating to any identified undesirable image contents; and using said content information to produce said processed video data.

First claim

The invention claimed is:

1. A video data processing device comprising:
a processor, a non-transitory computer readable medium communicatively connected to the processor, and at least one sensor device communicatively connected to at least one of the processor and the non-transitory computer readable medium, the at least one sensor device configured to collect information relating to gestures;
the video data processing device configured to identify undesirable image content contained in first video data based on a result of gesture recognition that is based on the information relating to motions and/or gestures obtained via the at least one sensor device, and provide content information relating to any identified undesirable image content, said undesirable image content including inappropriate body expression;
the video data processing device configured to identify one or more indicators in a situation or scene recorded in the first video data that increase the likelihood of undesirable image content to be contained in said first video data in the future based on recognized motions and/or gestures and set an alert state for the at least one sensor device in which a scanning rate for the at least one sensor device is increased and/or a scanning resolution of the at least one sensor device is increased in response to detection of the one or more indicators.

2. The video data processing device of claim 1 , wherein the video data processing device is configured to adapt the at least one sensor in response to identifying the one or more indicators in the situation or scene that increase the likelihood of undesirable image content to be contained in said first video data in the future such that the scanning rate is increased and the scanning resolution is increased at least in an image section in which an obscene gesture or indecent exposure is expected.

3. The video data processing device of claim 2 and wherein the video data processing device is configured to adapt the at least one sensor in response to identifying the one or more indicators in the situation or scene that increase the likelihood of undesirable image content to be contained in said first video data in the future such that a data processing cycle for motion and gesture recognition is accelerated.

4. The video data processing device of claim 1 , wherein the video data processing device is configured to adapt the at least one sensor in response to identifying the one or more indicators in the situation or scene that increase the likelihood of undesirable image content to be contained in said first video data in the future such that a data processing cycle for motion and gesture recognition is accelerated.

5. The video data processing device of claim 1 , wherein the video data processing device is configured to utilize the at least one sensor to scan said situation or scene within a scanning field of the sensor device, identify persons in said scanning field, and decide whether or not at least one of a person in said scanning field is performing an inappropriate body expression based on said recognized motions and/or gestures.

6. The video data processing device of claim 1 , wherein the video data processing device is configured to suppress said identified undesired image contents in processed video data.

7. The video data processing device of claim 1 , wherein said content information comprises area information on image areas including said identified undesired contents.

8. The video data processing device of claim 1 , wherein said video data processing device is configured to include said content information in at least one member of the group consisting of a data region such as a header of each video frame, surplus lines of each video frame, and a data stream apart from a video stream.

9. The video data processing device of claim 1 , wherein said content information comprises at least one member of the group consisting of:
a flag indicating that undesirable image contents are contained in a frame,
an area counter including a number of identified areas in said frame, and
an end-of-areas flag indicating that said area information is finished.

10. The video data processing device of claim 1 , wherein said content information comprises a continue flag indicating that undesirable image contents of a previous frame continue to be present in a presently processed frame.

11. The video data processing device of claim 1 , comprising a camera to record the first video data, wherein the camera is communicatively connected to at least one of the processor and the non-transitory computer readable medium.

12. The video data processing device of claim 11 , wherein the video data processing device is one of a video communication device, a video recording device, and a video playing device.

13. A non-transitory computer readable medium comprising data stored thereon that is executable by a video data processing device, the data stored in the computer readable medium defining a method that is performed by the video data processing device when the video data processing device executes the data, the method comprising:
processing first video data into processed video data, said first video data being provided by picking up sequential images of a situation or scene,
applying a gesture recognition to said situation or scene;
identifying undesirable image content contained in said first video data based on a result of said gesture recognition and providing content information relating to any identified undesirable image content, said undesirable image content including inappropriate body expression;
producing said processed video data using said content information relating to any identified undesirable image content;
identifying one or more indicators in said situation or scene that increase the likelihood of undesirable image contents to be contained in said first video data in the future, based on recognized motions and/or gestures, and providing information on said one or more indicators; and
adapting said gesture recognition by using information on said identified one or more indicators, wherein said adapting includes setting an alert state in which a scanning rate is increased and a scanning resolution is increased at least in an image section in which an obscene gesture or indecent exposure is expected and wherein a data processing cycle for gesture recognition is accelerated.

14. The non-transitory computer readable medium of claim 13 , wherein the method also comprises:
scanning said situation or scene within a scanning field of a sensor device;
identifying persons in said scanning field; and
deciding whether or not at least one of a person in said scanning field is performing an inappropriate body expression, based on said recognized gestures.

15. The non-transitory computer readable medium of claim 13 , wherein the method also comprises:
suppressing said identified undesired content in said processed video data.

16. The non-transitory computer readable medium of claim 15 , wherein said content information comprises area information on image areas including said identified undesired content and wherein said suppressing step includes making said image areas unrecognizable in a frame, based on said area information.

17. A non-transitory computer readable medium comprising data stored thereon that is executable by a video data processing device, the data stored in the computer readable medium defining a method that is performed by the video data processing device when the video data processing device executes the data, the met

Assignees

• Unify Gmbh & Co Kg

Inventors

• Skarakis Konstantinos

Classifications

• H04N21/45455

  applied to a region of the image · CPC title

• H04N21/4542 Primary

  Blocking scenes or portions of the received content, e.g. censoring scenes · CPC title

• H04N21/84

  Generation or processing of descriptive data, e.g. content descriptors {(systems specially adapted for using meta-information in broadcast systems H04H60/73)} · CPC title

• H04N7/15

  Conference systems · CPC title

• G11B27/031

  Electronic editing of digitised analogue information signals, e.g. audio or video signals · CPC title