IP Library Granted Patent US 7,302,117
Granted Patent B2
US 7,302,117 · App. 11/190,912 · Granted Nov 27, 2007

Method of image feature coding and method of image search

Assignee: Mitsubishi Denki Kabushiki Kaisha
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,302,117
App. No.
11/190,912
Granted
Nov 27, 2007
Kind
B2
Abstract

A feature coding unit extracts and encodes a feature of a video signal so as to generate a feature stream. A feature identifying unit checks a decoded feature obtained as a result of decoding the feature stream against a search key from a user for a match so that a video content requested by the user is retrieved.

Claims (13)

1. An image feature coding method of producing a hierarchical feature stream to facilitate searching of image frames, the feature stream including:

a first tier describing a feature of a video sequence including a plurality of image frames,

a second tier describing a feature of a key frame that is an image frame identified within the video sequence, and

a third tier describing a feature of a rectangular segment that is a predetermined image area within the key frame,

the method comprising the step of:

coding motion features indicating a motion between the rectangular segment with the key frame and a corresponding rectangular segment within another key frame that is different than the key frame in the third tier where the feature of the rectangular segment is being described.

2. An image searching method using a hierarchical feature stream including:

a first tier describing a feature of a video sequence including a plurality of image frames,

a second tier describing a feature of a key frame that is an image frame identified within the video sequence, and

a third tier describing a feature of a rectangular segment that is a predetermined image area within the key frame,

the method comprising the steps of:

decoding a feature stream produced by coding motion features indicating a motion between the rectangular segment within the key frame and a corresponding rectangular segment within another key frame that is different than the key frame in the third tier where the feature of the rectangular segment is being described to obtain decoded features; and

searching a predetermined image frame from the image frames on the basis of the decoded features obtained by the decoding step and an input search condition.

Continuity (4)
Continuation 1041351300 · Apr 15, 2003
Continuation 0971414000 · Nov 17, 2000
Continuation PCTJP990040300 · Jan 29, 1999
Related Publication 20050267879A1 · Dec 1, 2005