Video metadata correction apparatus and method

• US 7,801,927 B2
• Filed: 03/28/2006
• Issued: 09/21/2010
• Est. Priority Date: 12/05/2005
• Status: Expired due to Fees

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Kaneko, Soutaro, Morimatsu, Eishi, Mizutani, Masami
• Primary Examiner(s): Trujillo; James
• Assistant Examiner(s): Singh; Amresh
• Application Number:
  US11/390,379
• Publication Number:
  US 20070130175A1
• Time in Patent Office: 1,638 Days
• Field of Search: 707/100, 707/1
• US Class Current: 707/803
• 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: H04N 21/42202 environmental sensors, e.g. for detecting temperature, luminosity, pressure, earthquakes
• CPC Class Codes: H04N 21/84 Generation or processing of descriptive data, e.g. content descriptors systems specially adapted for using meta-information in broadcast systems H04H60/73
• CPC Class Codes: H04N 5/772 the recording apparatus and the television camera being placed in the same enclosure
• CPC Class Codes: H04N 5/781 on disks or drums
• CPC Class Codes: H04N 5/85 on discs or drums
• CPC Class Codes: H04N 5/907 using static stores, e.g. storage tubes or semiconductor memories H04N5/91 takes precedence
• CPC Class Codes: H04N 5/91 Television signal processing therefor
• CPC Class Codes: H04N 9/8205 involving the multiplexing of an additional signal and the colour video signal

Abstract

This invention is to provide a technique for properly correcting video metadata related to and synchronized with the video. This video metadata correction apparatus includes: a section identification unit that identifies a section including incorrect video metadata based on information concerning video metadata in a first video metadata storage for storing the information concerning the video metadata as sensor information synchronized with video and a first video feature value, which correlates with the information concerning the video metadata and is extracted from the video; and a corrector that corrects the video metadata in the identified section based on the first video feature value or a second video feature value, which correlates with the information concerning the video metadata and is extracted from the video. In this manner, only an incorrectly measured part can be corrected in an effective manner.

Claims

1. A video metadata correction apparatus, comprising:

a first video metadata storage to store azimuth angles as sensor information synchronized with video;

a section identification unit to identify a section including incorrect azimuth angle based on azimuth angle difference calculated from said azimuth angles stored in said first video metadata storage and a horizontal distance extracted from said video, wherein said horizontal distance is a feature value corresponding to change of said video with respect to time and follows change of said azimuth angle difference with respect to time while said azimuth angles are correctly measured; and

a corrector to correct said azimuth angle in the identified section based on said horizontal distance or a second video feature value, which correlates with information concerning said azimuth angle and is extracted from said video, and store the corrected azimuth angle into a second video metadata storage.

2. The video metadata correction apparatus as set forth in claim 1,

wherein

said section identification unit comprises a unit to extract a candidate section including said incorrect azimuth angle based on said change of said azimuth angle difference with respect to time.

3. The video metadata correction apparatus as set forth in claim 1, wherein said section identification unit comprises a unit to judge whether or not a coefficient minimizing a function including a residual between said azimuth angle difference in a specific section and a product of said coefficient and said horizontal distance in said specific section is within a predetermined range.

4. The video metadata correction apparatus as set forth in claim 1, wherein said corrector comprises a unit to calculate a correction amount of said azimuth angle so as to be proportional to a change amount of said horizontal distance or the second video feature value.

5. The video metadata correction apparatus as set forth in claim 1, wherein said corrector comprises a unit to calculate a correction amount of said azimuth angle so as to smoothly change said azimuth angle according to a change amount of said horizontal distance or said second video feature value.

6. The video metadata correction apparatus as set forth in claim 1, wherein said corrector comprises a unit to calculate a correction amount of said azimuth angle so as to be proportional to a change amount of said horizontal distance or said second video feature value and continuously connect the identified section and its preceding and following sections or a correction section and its preceding and following sections, said correction section including the identified section and at least its preceding or following subsection.

7. A video metadata recording apparatus, comprising:

said video metadata correction apparatus as set forth in claim 1;

a video data storage that stores data of said video;

a camera that shoots said data of said video to store said data into said video data storage;

a sensor that obtains said sensor information and stores said sensor information into said first video metadata storage.

8. A terminal apparatus, comprising:

said video metadata correction apparatus as set forth in claim 1;

a video data storage that stores data of said video;

a map database that stores data of map elements at each position;

a unit that reads out video stored in said video data storage and said azimuth angle that is stored in said second video metadata storage and is synchronized with said video, searches said map database by said azimuth angle to read out data of a corresponding map element, and displays said data of said corresponding map element on a display device.

9. A video metadata correction method, comprising:

identifying a section including incorrect azimuth angle based on azimuth angle difference calculated from said azimuth angles stored in a first video metadata storage and a first horizontal distance extracted from a video, wherein said first video metadata storage stores said azimuth angles as sensor information synchronized with said video, and said horizontal distance is a feature value corresponding to change of said video with respect to time and follows change of said azimuth angle difference with respect to time while said azimuth angles are correctly measured;

correcting said azimuth angle in the identified section based on said horizontal distance or a second video feature value, which correlates with information concerning said azimuth angle and is extracted from said video; and

storing the corrected azimuth angle into a second video metadata storage.

10. A computer-readable storage medium storing a video metadata correction program, said video metadata correction program causing a computer to execute a process comprising:

identifying a section including incorrect azimuth angle based on azimuth angle difference calculated from said azimuth angles stored in a first video metadata storage and a first horizontal distance extracted from a video, wherein said first video metadata storage stores said azimuth angles as sensor information synchronized with said video, and said horizontal distance is a feature value corresponding to change of said video with respect to time and follows change of said azimuth angle difference with respect to time while said azimuth angles are correctly measured;

correcting said azimuth angle in the identified section based on said horizontal distance or a second video feature value, which correlates with information concerning said azimuth angle and is extracted from said video; and

storing the corrected azimuth angle into a second video metadata storage.