FULL-AUTOMATIC DETECTION METHOD AND SYSTEM FOR STATIC CHARACTERISTIC INFORMATION IN DYNAMIC IMAGE

• US 20150186731A1
• Filed: 04/21/2014
• Published: 07/02/2015
• Est. Priority Date: 12/31/2013
• Status: Active Grant

• Current Assignee: Montage LZ Semiconductor (shanghai) Co., ltd., Montage Lz Technologies (Chengdu) Co.Ltd.
• Original Assignee: Montage Technology Company Limited
• Inventors: SUN, Binxuan, CHEN, Cheng-Tie, HUANG, Xiaodong, WU, Ke
• Granted Patent: US 9,323,990 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 2201/09 Recognition of logos

Abstract

According to a method in the present invention, first whether an inter-frame difference for each pixel in predetermined first region and second region in the dynamic image exceeds a predetermined threshold is judged to determine whether the pixel is a static information point, and when, in the second region, pixels in regions not overlapping with the first region are determined as non-static information points, judgment on the inter-frame difference and the predetermined threshold is stopped; and then static characteristic information in the dynamic image is determined based on the static information points in the first region. Preferably, the inter-frame difference for each pixel in the first region may be re-judged based on an adjusted predetermined threshold, to further determine the static characteristic information in the dynamic image, so that static opaque static characteristic information or static characteristic information with arbitrary degrees of transparency in the dynamic image can be detected.

Claims

1. A full-automatic detection method for static characteristic information in a dynamic image, wherein the full-automatic detection method for static characteristic information in a dynamic image at least comprises:

(1) judging whether an pixel is a static information pixel or not by comparing the inter-frame difference with a predetermined threshold in a predetermined first region and second region;

the judging process is stopped when the pixels in the non overlap region of the first and second region is judged as non-static information points; and

(2) determining static characteristic information in the dynamic image based on the static information points in the first region.

2. The full-automatic detection method for static characteristic information in a dynamic image as in claim 1, wherein

when the static information points in the first region are determined as belonging to the static characteristic information in the dynamic image, the steps (1) and (2) are repeated based on an adjusted predetermined threshold.

3. The full-automatic detection method for static characteristic information in a dynamic image as in claim 1, further comprising:

detecting background information points in the static information points based on a horizontal frequency,

wherein the step (2) is proceeded as follows;

determining the static characteristic information in the dynamic image based on static information points in the first region which are not background information points.

4. The full-automatic detection method for static characteristic information in a dynamic image as in claim 1, further comprising:

synthesizing the static characteristic information obtained after multiple times of determination operations to obtain ultimate static characteristic information.

5. The full-automatic detection method for static characteristic information in a dynamic image as in claim 1, wherein the first region is contained within the second region.

6. The full-automatic detection method for static characteristic information in a dynamic image as in claim 1, wherein the first region and the second region overlap partially or do not overlap at all.

13. The full-automatic detection method for static characteristic information in a dynamic image as in claim 2, further comprising:

detecting background information points in the static information points based on a horizontal frequency,

wherein the step (2) is proceeded as follows;

determining the static characteristic information in the dynamic image based on static information points in the first region which are not background information points.

14. The full-automatic detection method for static characteristic information in a dynamic image as in claim 2, further comprising:

synthesizing the static characteristic information obtained after multiple times of determination operations to obtain ultimate static characteristic information.

7. A full-automatic detection system for static characteristic information in a dynamic image, wherein the full-automatic detection system for static characteristic information in a dynamic image at least comprises:

a judgment module, for judging whether an inter-frame difference for each pixel in a predetermined first region and second region in the dynamic image exceeds a predetermined threshold to determine whether the pixel is a static information point, and stopping the judgment operation between the inter-frame difference and the predetermined threshold when all the pixels in a specific region within the second region and not overlapping with the first region are determined as non-static information points; and

a determination module, for determining static characteristic information in the dynamic image based on the static information points in the first region.

8. The full-automatic detection system for static characteristic information in a dynamic image as in claim 7, wherein

when the static information points in the first region are determined as belonging to the static characteristic information in the dynamic image, the judgment module and the determination module repetitively perform respective operations based on an adjusted predetermined threshold.

9. The full-automatic detection system for static characteristic information in a dynamic image as in claim 7, further comprising:

a detection module, for detecting background information points in the static information points based on a horizontal frequency;

wherein the determination module is further used for;

determining the static characteristic information in the dynamic image based on static information points in the first region which are not background information points.

10. The full-automatic detection system for static characteristic information in a dynamic image as in claim 7, further comprising:

a synthesis module, for synthesizing the static characteristic information obtained after multiple times of determination operations to obtain ultimate static characteristic information.

11. The full-automatic detection system for static characteristic information in a dynamic image as in claim 7, wherein the first region is contained within the second region.

12. The full-automatic detection system for static characteristic information in a dynamic image as in claim 7, wherein the first region and the second region overlap partially or do not overlap at all.

15. The full-automatic detection system for static characteristic information in a dynamic image as in claim 8, further comprising:

a detection module, for detecting background information points in the static information points based on a horizontal frequency;

wherein the determination module is further used for;

determining the static characteristic information in the dynamic image based on static information points in the first region which are not background information points.

16. The full-automatic detection system for static characteristic information in a dynamic image as in claim 8, further comprising:

a synthesis module, for synthesizing the static characteristic information obtained after multiple times of determination operations to obtain ultimate static characteristic information.