GENERATING CONTENT DATA FOR A VIDEO FILE

• US 20150050008A1
• Filed: 11/03/2014
• Published: 02/19/2015
• Est. Priority Date: 05/23/2011
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.), Sony Mobile Communications AB (Sony Group Corp.)
• Inventors: Johansson, Fredrik, Hff, Olle
• Granted Patent: US 9,396,759 B2
• Time in Patent Office: Days
• US Class Current: 386/241
• CPC Class Codes: G06F 16/70 of video data
• CPC Class Codes: G06F 16/784 the detected or recognised objects being people
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G11B 27/10 Indexing; Addressing; Timing or synchronising; Measuring tape travel

Abstract

A method for generating content data for a video file (200) is provided. The video file (200) comprises a video sequence and the content data (201) for characterizing the video sequence. According to the method, at least one face containing image (204, 205, 207, 209, 212) is determined by scanning at least a part of the video sequence for face containing images. Each face containing image contains at least one representation of a face. Based on the determined face containing image a picture containing the face is generated and assigned to the content data (201) of the video file (200).

Claims

1. A method for generating content data for a video file, the video file comprising a video sequence and the content data for characterizing the video sequence, wherein the method comprises the steps:

determining at least one face containing image by scanning at least a part of the video sequence for face containing images, each face containing image containing at least one representation of a face;

generating at least one picture containing the face based on the determined at least one face containing image; and

assigning the at least one picture to the content data of the video file,

wherein the step of generating at least one picture comprises;

determining for each face containing image a percentage area covered by the representation of the face, the percentage area indicating a relative amount of area of the image covered by the representation of the face as compared to an entire area of the image; and

generating the at least one picture based on the determined at least one face containing image and on the corresponding percentage area.

2. The method according to claim 1, wherein the steps of generating and assigning the at least one picture comprise:

selecting a subset of face containing images from the at least one face containing image,

generating a picture sequence based on the subset of face containing images, and

assigning the picture sequence to the content data of the video file.

3. The method according to claim 1, wherein the method further comprises the step of:

cropping the at least one picture by removing an area of the picture which does not contain the representation of the face.

5. The method according to claim 1, wherein the method further comprises the step of:

reducing a resolution of each picture to a resolution which is lower than a resolution of the corresponding face containing image.

6. The method according to claim 1, wherein the method further comprises:

displaying the at least one picture as a thumbnail of an icon on a display for a user.

9. The method according to claim 1, wherein the step of generating the at least one picture comprises:

selecting one face containing image of the at least one face containing image, and

selecting a video subsequence of a predetermined length from the video sequence as the at least one picture, the video subsequence containing the selected face containing image.

10. The method according to claim 1, wherein the video sequence comprises a plurality of sequential image frames, and wherein the step of determining at least one face containing image comprises:

determining at least one face containing image by scanning at least a subset of the plurality of sequential image frames for face containing image frames.

11. The method according to claim 10, wherein the subset of the plurality of sequential image frames comprises every n-th image frame of the plurality of sequential image frames.

12. The method according to claim 10, wherein the subset of the plurality of sequential image frames comprises image frames of the plurality of sequential image frames within a predetermined time interval of the video sequence only.

4. (canceled)

7. A method for generating content data for a video file, the video file comprising a video sequence and the content data for characterizing the video sequence, wherein the method comprises the steps:

determining at least one face containing image by scanning at least a part of the video sequence for face containing images, each face containing image containing at least one representation of a face;

generating at least one picture containing the face based on the determined at least one face containing image; and

assigning the at least one picture to the content data of the video file,

wherein the step of generating at least one picture comprises;

generating one picture based on a face containing image which represents the largest number of faces.

8. A method for generating content data for a video file, the video file comprising a video sequence and the content data for characterizing the video sequence;

wherein the method comprises the steps;

determining at least one face containing image by scanning at least a part of the video sequence for face containing images, each face containing image containing at least one representation of a face;

generating at least one picture containing the face based on the determined at least one face containing image; and

assigning the at least one picture to the content data of the video file,

wherein the step of generating at least one picture comprises;

generating one picture based on a first determined face containing image in the video sequence.

13. A device comprising:

a video access unit adapted to access a video file, the video file comprising a video sequence and content data for characterizing the video sequence;

a face detection unit coupled to the video access unit, the face detection unit being configured to determine at least one face containing image by scanning at least a part of the video sequence for face containing images, each face containing image containing at least one representation of a face; and

a processing unit coupled to the face detection unit, the processing unit being configured to generate at least one picture containing the face based on the determined at least one face containing image, and to assign the at least one picture to the content data of the video file,

wherein the processing unit is configured to determine for each face containing image a percentage area covered by the representation of the face, the percentage area indicating a relative amount of area of the image covered by the representation of the face as compared to an entire area of the image, and generate the at least one picture based on the determined at least one face containing image and on the corresponding percentage area.

15. The device according to claim 13, wherein the device comprises at least one device of a group consisting of a mobile phone, a personal digital assistant, and a mobile video player.

14. (canceled)

16. A device comprising:

a video access unit adapted to access a video file, the video file comprising a video sequence and content data for characterizing the video sequence;

a face detection unit coupled to the video access unit, the face detection unit being configured to determine at least one face containing image by scanning at least a part of the video sequence for face containing images, each face containing image containing at least one representation of a face; and

a processing unit coupled to the face detection unit, the processing unit being configured to generate at least one picture containing the face based on the determined at least one face containing image, and to assign the at least one picture to the content data of the video file,

wherein the at least one picture is generated based on a face containing image which represents tile largest number of faces.

17. A device comprising:

a video access unit adapted to access a video file, the video file comprising a video sequence and content data for characterizing the video sequence;

a face detection unit coupled to the video access unit, the face detection unit being configured to determine at least one face containing image by scanning at least a part of the video sequence for face containing images, each face containing image containing at least one representation of a face; and

a processing unit coupled to the face detection unit, the processing unit being configured to generate at least one picture containing the face based on the determined at least one face containing image, and to assign the at least one picture to the content data of the video file,

wherein the at least one picture is generated based on a first determined face containing image in the video sequence.