Media handling system

• US 7,739,598 B2
• Filed: 11/28/2003
• Issued: 06/15/2010
• Est. Priority Date: 11/29/2002
• Status: Expired due to Fees

• Current Assignee: Sony United Kingdom Limited (Sony Group Corp.)
• Original Assignee: Sony United Kingdom Limited (Sony Group Corp.)
• Inventors: David, Morgan William Amos, Porter, Robert Mark Stefan
• Primary Examiner(s): ENGLAND, SARA M
• Application Number:
  US10/536,814
• Publication Number:
  US 20060044446A1
• Time in Patent Office: 2,391 Days
• Field of Search: 715/720, 715/721, 715/723, 382/118, 348/207.99
• US Class Current: 715/723
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence
• CPC Class Codes: G11B 27/34 Indicating arrangements indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D
• CPC Class Codes: H04N 21/23418 involving operations for analysing video streams, e.g. detecting features or characteristics television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/854 Content authoring

Abstract

A media handling system in which candidate video sequences are displayed on a display screen in schematic form for selection by a user comprises means for detecting human faces in the candidate video sequences; a display screen for displaying representations of the candidate video sequences for selection by a user, each representation including one or more images representing human faces derived from the respective video sequences; and a user control for defining a set of one or more of the video sequences.

Claims

1. A media handling system in which candidate video sequences are displayed on a display screen in schematic form for selection by a user, the system comprising:

user control means for defining a set of one or more of the video sequences;

detecting means for detecting human faces in the candidate video sequences, for detecting a probability of a human face being present in each field or frame of the video sequences, and for weighting at least some of the detected probability levels depending on the size of the detected face, each one of the weighted probability levels corresponds with a respective face size stored in a look-up table; and

a display screen configured to display at least one representation of the candidate video sequences for selection by the user, each representation of the candidate video sequence including one or more images representing human faces derived from the respective video sequences and having the highest weighted probability levels amongst the respective video sequences, wherein

the detector means weights the probability levels based on the correspondence between each one of the weighted probability levels and the respective face sizes as defined by the look-up table, such that detected faces closer in size to a preferred representation size are presented to the user for selection thereof as the displayed representation of the candidate video sequence.

2. A system according to claim 1, wherein the set of one or more of the video sequences is an ordered edited set forming an output media product.

3. A system according to claim 2, further comprising:

means for displaying, on the display screen, a further ordered representation of a group of at least a subset of the video sequences forming the output media product, the ordered representation including one or more images representing human faces derived from the respective video sequences in the group.

4. A system according to claim 3, wherein the ordered representation is a timeline representation, providing an ordered representation of the group of video sequences forming the output media product along a generally rectilinear path on the display screen.

5. A system according to claim 3, wherein the ordered representation may be scaled so as to vary the proportion of the video sequences forming the output media product which are currently displayed in the ordered representation.

6. A system according to claim 1, wherein the detecting means applies the weighting over a subset of the fields or frames of a video sequence.

7. A system according to claim 6, wherein the detecting means applies the weighting over an initial subset of the fields or frames of a video sequence.

8. A system according to claim 1, wherein each candidate video sequence is a sequence over which a face has been detected.

9. A system according to claim 8, wherein selection of a displayed representation by the user control causes the display of the corresponding video sequence.

10. A system according to claim 1, wherein the candidate video sequences are selected from a video sequence captured by a surveillance camera.

11. A system according to claim 1, wherein the user control means indicates that faces detected in two or more of the candidate video sequences represent a same person'"'"'s face.

12. A method of media handling in which candidate video sequences are displayed on a display screen in schematic form for selection by a user, the method comprising:

detecting human faces in the candidate video sequences;

detecting a probability of a human face being present in each field or frame of the video sequences;

weighting at least some of the detected probability levels depending on the size of the detected face, each one of the weighted probability levels corresponds with a respective face size stored in a look-up table;

displaying on a display screen at least one representation of the candidate video sequences for selection by the user, each representation of the candidate video sequences including one or more images representing human faces derived from the respective video sequences and having the highest weighted probability levels amongst the respective video sequences;

defining a set of one or more of the video sequences; and

weighting the probability levels based on the correspondence between each one of the weighted probability levels and the respective face sizes as defined by the look-up table, such that detected faces closer in size to a preferred representation size are presented to the user for selection thereof as the displayed representation of the of the candidate video sequences.

13. A computer readable storage medium encoded with a computer readable program configured to cause an information processing apparatus to execute the method according to claim 12.

14. A media handling system in which candidate video sequences are displayed on a display screen in schematic form for selection by a user, the system comprising:

a user control configured to define a set of one or more of the video sequences;

a detector configured to detect human faces in the candidate video sequences, to detect a probability of a human face being present in each field or frame of the video sequences, and to weight at least some of the detected probability levels depending on the size of the detected face, each one of the weighted probability levels corresponds with a respective face size stored in a look-up; and

a display screen configured to display at least one representation of the candidate video sequences for selection by the user, each representation of the candidate video sequence including one or more images representing human faces derived from the respective video sequences and having the highest weighted probability levels amongst the respective video sequences, wherein

the detector weights the probability levels based on the correspondence between each one of the weighted probability levels and the respective face sizes as defined by the look-up table, such that detected faces closer in size to a preferred representation size are presented to the user for selection thereof as the displayed representation of the of the candidate video sequences.