Method of describing object region data, apparatus for generating object region data, video processing apparatus and video processing method

• US 6,839,465 B2
• Filed: 10/24/2002
• Issued: 01/04/2005
• Est. Priority Date: 01/28/1999
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Yamamoto, Koji, Kaneko, Toshimitsu, Mita, Takeshi, Hori, Osamu
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): Akhavannik, Hussein
• Application Number:
  US10/278,833
• Publication Number:
  US 20030086613A1
• Time in Patent Office: 803 Days
• Field of Search: 382/190, 382/103, 345/475
• US Class Current: 382/190
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56
• CPC Class Codes: G06V 10/471 using approximation functions
• CPC Class Codes: G06V 10/752 Contour matching
• CPC Class Codes: H04N 19/20 using video object coding
• CPC Class Codes: H04N 19/54 using feature points or meshes
• CPC Class Codes: H04N 19/543 using regions
• CPC Class Codes: H04N 19/70 characterised by syntax aspects related to video coding, e.g. related to compression standards

Abstract

A region data describing method for describing, over a plurality of frames, region data about the region of an arbitrary object in a video, the method specifying the object region in the video with at least either of an approximate figure approximating the region or characteristic points of the regions, approximating a trajectory obtained by arranging position data of the representative points or the characteristic point in a direction in which frames proceed with a predetermined function and describing the parameter of the function as region data. Thus, the region of a predetermined object in the video can be described with a small quantity of data. Moreover, creation and handling of data can easily be performed.

Claims

1. A data signal for use in a video decoding apparatus and for describing information of a moving object region in a video sequence, comprising:

time data including a start time and a duration time of the object region in the video sequence;

type data specifying a type of figure, corresponding to the object region, to be a polygon and a number of vertices which are representative points of the figure, the type data being described by an integer; and

figure data specifying a trajectory of at least one of the vertices, including;

time arrangement data including times of points used to determine the trajectory,

key value data representing values of the points used to determine the trajectory, and

function data for indicating the trajectory of the at least one of the vertices using information indicating an order of a function used to determine the trajectory or that no function is defined, the function data being described by another integer.

2. A video data signal of claim 1, wherein:

the figure data specifies a trajectory of at least one of the representative points of at least three successive frames.

3. A video data signal of claim 2, wherein:

the function data is used to indicate the trajectory using a formula;

ƒ

(t)=ƒ

_a+ν

_a(t−

t_a),

where ν

_a=(ƒ

_b−

ƒ

_a)/(t_b−

t_a), when an order of a function used to indicate the trajectory is first order, where t_a represents a time of a first point of the points used to determine the trajectory, t_b represents a time of a second point of the points used to determine the trajectory, ƒ

_a is a coordinate of the first point, ƒ

_b is a coordinate of the second point, and t is a time of a point to be determined.

4. A video data signal of claim 2, wherein the function data further comprises:

parameter data specifying a second order coefficient for the trajectory when an order of a function indicating the trajectory is second order.

5. A video data signal of claim 4, wherein the function data is used to indicate the trajectory using a formula:

ƒ

(t)=ƒ

_a+ν

_a(t−

t_a)+½

a_a(t−

t_a)²,

where ν

_a=(ƒ

_b−

ƒ

_a)/(t_b−

t_a)−

½

a_a (t_b−

t_a) when an order of a function used to indicate the trajectory is second order, where ta represents a time of a first point, t_b represents a time of a second point, ƒ

_a is a coordinate of the first point, ƒ

_b is a coordinate of the second point, and t is a time of a point to be determined.

6. A video data signal of claim 2,

wherein the video data signal comprises hypermedia information.

7. A data signal according to claim 2, wherein:

the representative points are ordered clockwise.

8. A data signal according to claim 7, wherein:

the representative points are continuous.

9. A data signal according to claim 8, wherein:

the representative points are selected from vertices of the figure without omitting any vertices.

10. A data signal according to claim 2, wherein:

the time arrangement data are sorted in increasing order.