Content generation, extraction and distribution of image region segments from video images

• US 7,313,278 B2
• Filed: 03/08/2002
• Issued: 12/25/2007
• Est. Priority Date: 03/16/2001
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Masumitsu, Ken, Echigo, Tomio, Murao, Takaaki, Teraguchi, Masayoshi
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): KIM, CHONG R
• Application Number:
  US10/094,896
• Publication Number:
  US 20020159637A1
• Time in Patent Office: 2,118 Days
• Field of Search: None
• US Class Current: 382/190
• CPC Class Codes: G06F 16/9577 Optimising the visualization of content, e.g. distillation of HTML documents
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 20/40 in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44

Abstract

The present invention provides methods for extracting an image region segment from a video image, a system for extracting an image region segment, a program for extracting an image region segment, a method for distributing an extracted video image, and a method for generating content. Motion compensation data is calculated using sequential video images captured by a video camera, and the sequential video images are employed to prepare an estimation of the video camera operation. Based on the estimated camera operation, the center position (xc, yc) of an area that is aimed at in a video image is estimated under predetermined conditions (rules), an image feature is designated in the vicinity of the center position of the target area, and an image segment is specified that includes this image feature.

Claims

1. An image region segment extraction method comprising extracting an image segment from a video image,

extracting only said target area being one of an area aimed at by a cameraman and an essential portion of the video image, and either enlarging an image sequence of said target area, or increasing a resolution only of the target area while high compression scalable coding is performed for other portions of said video image,

the step of extracting comprising the steps of:

calculating motion data for a video image based on two sequential frames of video images obtained by a video camera;

using said sequential video images to estimate the camera operations required of said video camera;

referring to said camera operations performed under predetermined conditions to estimate the location of the center of a target area in a video image that has been obtained;

designating image features in the vicinity of said center position of said target area;

designating an image segment in which said image features are included;

extracting said target area being one of;

an area aimed at by a cameraman and an essential portion of the video image, and

either enlarging an image sequence of said target area, or increasing a resolution only of the target area while performing high compression scalable coding for other portions of said video image,

wherein said video image is selected from a format taken from a group of formats including;

an MPEG format, a CGM format, an EPS format, a GIF format, a JPEG format, a PICT format, a PNG format, a PS format, a TIF format or a BMP format;

wherein said step of calculating said camera operations includes the step of;

making an estimation of the robustness of a predetermined parameter of said camera operations, so as to perform a robust estimation process for the camera operation to enable determination of camera operations, such as panning, tilting and zooming;

further comprising a steps of;

obtaining an average movement for said predetermined parameter for two sequential frames;

wherein, at said step of estimating said center position of said target area, a rule is employed concerning front-space video in said camera operations;

at least one of;

trimming said image segment and generating a trimmed image, and performing scalable coding to obtain a high resolution for said image segment.

2. The image region segment extraction method according to claim 1, further comprising the step of:

generating content, including trimmed images or scalable coded images, the step of generating content comprising the steps of;

generating one of trimmed images or scalable coded images;

arranging said trimmed images or scalable coded images in an order occupied by video images before trimming to constitute a continuous content time series; and

storing said content in a storage media.

3. The image region segment extraction method according to claim 2, further comprising the step of employing an article of manufacture comprising a computer usable medium having computer readable program code means embodied therein for causing generation of content, the computer readable program code means in said article of manufacture comprising computer readable program code means for causing a computer to effect the steps of calculating;

using;

referring;

designating image features;

designating an image segment;

trimming or performing; and

generating content.

4. The image region segment extraction method according to claim 1, further comprising the step of employing an article of manufacture comprising a computer usable medium having computer readable program code means embodied therein for causing extraction of an image segment from the video image, the computer readable program code means in said article of manufacture comprising computer readable program code means for causing a computer to effect the steps of calculating;

using;

referring;

designating image features; and

designating an image segment.