METHOD, APPARATUS AND TERMINAL FOR DETECTING IMAGE STABILITY

• US 20140321747A1
• Filed: 05/19/2014
• Published: 10/30/2014
• Est. Priority Date: 04/28/2013
• Status: Active Grant

• Current Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Original Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Inventors: Liu, Xiao, Liu, Hailong, Chen, Bo, Ding, Jian
• Granted Patent: US 9,317,770 B2
• Time in Patent Office: Days
• US Class Current: 382/173
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 7/00 Image analysis
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern
• CPC Class Codes: H04N 23/6811 based on the image signal

Abstract

An apparatus and terminal perform a method for detecting image stability in image processing. The method includes: acquiring N consecutive image frames, wherein N is an integer equal to 2 or larger; performing in each of the N consecutive image frames, the following: detecting corner points in the image frame, dividing the image frame into multiple areas, and recording distribution of the corner points in each of the multiple areas of the image frame in order to obtain a description vector of the image frame; calculating a number of areas according to the description vector of the image frame over the N consecutive image frames, wherein an existing state of the corner points has changed; determining whether the N consecutive image frames are stable, based on the number of areas which the existing state of the corner points has changed over the N consecutive image frames.

Claims

1. A method for detecting image stability, comprising:

acquiring N consecutive image frames, wherein N is an integer equal to 2 or larger;

performing in each of the N consecutive image frames, the following;

detecting corner points in the image frame,

dividing the image frame into multiple areas, and

recording distribution of the corner points in each of the multiple areas of the image frame in order to obtain a description vector of the image frame;

calculating a number of areas according to the description vector of the image frame over the N consecutive image frames, wherein an existing state of the corner points has changed;

determining whether the N consecutive image frames are stable, based on the number of areas which the existing state of the corner points has changed over the N consecutive image frames.

2. The method according to claim 1, wherein the dividing of the image frame into multiple areas, and the recording of the distribution of the corner points in each of the multiple areas to obtain the description vector of the image frame, comprises:

dividing the image frame to obtain M areas, recording each of the M areas whether a corner point exists in;

obtaining the description vector of the image based on a length of M, wherein the description vector indicates the existing state of the corner points in the M areas, wherein M represents an integer greater than 1.

3. The method according to claim 1, wherein the calculating of the number of areas according to the description vector of the image frame, comprises:

comparing every two consecutive adjacent image frames at a time, description vectors of the two consecutive adjacent image frames over the N consecutive image frames; and

counting the number of areas in which the existing state of the corner points has changed based on comparing the every two consecutive adjacent image frames over the N consecutive image frames.

4. The method according to claim 1, wherein the determining whether the N consecutive image frames are stable, based on the number of areas which the existing state of the corner points has changed over the N consecutive image frames, comprises:

comparing if the number of areas in which the existing state of the corner points has changed over the N consecutive image frames has exceeded a preset threshold;

determining the N consecutive image frames as being stable, if the number of areas is less than the preset threshold;

determining the N consecutive image frames as being unstable, if the number of areas is greater than or equals to the preset threshold.

5. The method according to claim 2, wherein the recording of each of the M areas whether a corner point exists in for obtaining the description vector of the image based on obtaining the length of M, comprises:

for each area in the M areas, if corner points are existed in, recording as “

1”

, if no corner points are existed in, recording as “

0”

, wherein the recorded “

1”

s are utilized to obtain the description vector of each image in order to obtain the length of M;

calculating to obtain the number of areas in which the existing state of corner points in each corresponding image frame has changed in the N consecutive image frames, according to the description vector of each image frame according to the following formula;

6. An apparatus for detecting image stability, comprising at least a processor operating in conjunction with a memory and a plurality of modules, wherein the plurality of modules comprise:

an acquisition module, configured to acquire N consecutive image frames, wherein N represents an integer equal to 2 or larger;

wherein in each of the N consecutive image frames, the following functions are performed by;

a processing module, which performs the function of detecting corner points in the image frame, dividing the image frame into multiple areas and recording distribution of the corner points in each of the multiple areas of the image frame in order to obtain a description vector of the image frame;

a computation module, which performs the function of calculating a number of areas according to the description vector of the image frame over the N consecutive image frames, wherein an existing state of the corner points has changed;

a determining module, which performs the function of determining whether the N consecutive image frames are stable, based on the number of areas which the existing state of the corner points has changed over the N consecutive image frames.

7. The apparatus according to claim 6, wherein the processing module comprises:

a processing unit configured to detect the corner points of each of the N consecutive image frames and divide each image frame to obtain M areas, record whether the corner points exist in each of the M areas to obtain the description vector of the image frame with a length of M, wherein the length of M represents the existing state of the corner points in the M areas, wherein M represents an integer greater than 1.

8. The apparatus according to claim 6, wherein the computation module comprises:

a computation unit configured to compare the description vectors of every two consecutive adjacent image frames over the N consecutive image frames, and count the number of areas in which the existing state has changed within the every two consecutive adjacent image frames to obtain the number of areas in which the existing state has changed over the N consecutive image frames.

9. The apparatus according to claim 6, wherein the determining module comprises:

a comparison unit, configured to compare the number of areas in which the existing state of the corner points has changed in the N consecutive image frames to a preset threshold;

a determining unit configured to determine that if the number of areas is less than the preset threshold, determine the N consecutive image frames as being stable;

if the number of areas is more than or equal to the preset threshold, determine the N consecutive image frames as being unstable.

10. The apparatus according to claim 7, wherein:

the processing unit performs the function of;

detecting the corner points of each image frame in the N consecutive image frames and dividing each image frame to obtain M areas, for each area in the M areas, recording as 1 if the corner point exists, recording as 0 if the corner point does not exist, in order to obtain the description vector of each image frame with a length of M, wherein the length of M represents the existing state of the corner points in M areas, wherein M is an integer greater than 1;

a computation module performs the function of;

calculating to obtain the number of areas in which the existing state of corner points has changed over the N consecutive image frames according to the description vector of each image frame according to the following formula;

11. A terminal for detecting image stability, comprises at least a processor operating in conjunction with a memory and a plurality of modules, wherein the plurality of modules comprise:

an acquisition module, which performs the function of acquiring N consecutive image frames, wherein N represents an integer equal to 2 or larger;

wherein in each of the N consecutive image frames, the following functions are performed by;

a processing module, which performs the function of detecting corner points in the image frame, dividing the image frame into multiple areas and recording distribution of the corner points in each of the multiple areas of the image frame in order to obtain a description vector of the image frame;

a computation module, which performs the function of calculating a number of areas according to the description vector of the image frame over the N consecutive image frames, wherein an existing state of the corner points has changed;

a determining module, which performs the function of determining whether the N consecutive image frames are stable, based on the number of areas which the existing state of the corner points has changed over the N consecutive image frames.

12. The terminal according to claim 11, wherein the processing module comprises:

a processing unit, which performs the function of detecting the corner points of each of the N consecutive image frames and dividing each image frame to obtain M areas, recording whether the corner points exist in each of the M areas to obtain the description vector of the image frame with a length of M, wherein the length of M represents the existing state of the corner points in the M areas, wherein M is an integer greater than 1.

13. The terminal according to claim 11, wherein the Computation module comprises:

a computation unit, which performs the function of comparing the description vectors of every two consecutive adjacent image frames over the N consecutive image frames, and counting the number of areas in which the existing state has changed within the every two consecutive adjacent image frames to obtain the number of areas in which the existing state has changed over the N consecutive image frames.

14. The terminal according to claim 11, wherein the determining module comprises:

a comparison unit, which performs the function of comparing the number of areas in which the existing state of the corner points has changed in the N consecutive image frames to a preset threshold;

a determining unit, which determines that If the number of areas is less than the preset threshold, the N consecutive image frames will be determined as being stable;

If the number of areas is more than or equal to the preset threshold, the N consecutive image frames will be determined as being unstable.

15. The terminal according to claim 12, wherein:

the processing unit performs the function of;

detecting the corner points of each image frame in the N consecutive image frames and dividing each image frame to obtain M areas, for each area in M areas, it will be recorded as 1 if the corner point exists, it will be recorded as 0 if the corner point does not exist, in order to obtain the description vector of each image frame with a length of M, wherein the length of M represents the existing state of the corner points in M areas, wherein M is an integer greater than 1;

a computation module performs the function of;

calculating to obtain the number of areas in which the existing state of corner points has changed over the N consecutive image frames according to the description vector of each image frame according to the following formula;

16. A non-transitory computer-readable storage medium having stored thereon, a computer program having at least one code section being executable by a machine for causing the machine to perform steps in detecting image stability, comprising:

acquiring N consecutive image frames, wherein N is an integer equal to 2 or larger;

performing in each of the N consecutive image frames, the following;

detecting corner points in the image frame,

dividing the image frame into multiple areas, and

recording distribution of the corner points in each of the multiple areas of the image frame in order to obtain a description vector of the image frame;

calculating a number of areas according to the description vector of the image frame over the N consecutive image frames, wherein an existing state of the corner points has changed;

determining whether the N consecutive image frames are stable, based on the number of areas which the existing state of the corner points has changed over the N consecutive image frames.

17. The non-transitory computer-readable storage medium according to claim 16, wherein the dividing of the image frame into multiple areas, and the recording of the distribution of the corner points in each of the multiple areas to obtain the description vector of the image frame, comprising:

dividing the image frame to obtain M areas, recording each of the M areas whether a corner point exists in;

obtaining the description vector of the image based on a length of M, wherein the description vector indicates the existing state of the corner points in the M areas, wherein M is an integer greater than 1.

18. The non-transitory computer-readable storage medium according to claim 16, wherein the calculating of the number of areas according to the description vector of the image frame, comprising:

comparing every two consecutive adjacent image frames at a time, description vectors of the two consecutive adjacent image frames over the N consecutive image frames; and

counting the number of areas in which the existing state of the corner points has changed based on comparing the every two consecutive adjacent image frames over the N consecutive image frames.

19. The non-transitory computer-readable storage medium according to claim 16, wherein the determining whether the N consecutive image frames are stable, based on the number of areas which the existing state of the corner points has changed over the N consecutive image frames, comprising:

comparing if the number of areas in which the existing state of the corner points has changed over the N consecutive image frames has exceeded a preset threshold;

if the number of areas is less than the preset threshold, the N consecutive image frames will be determined as being stable;

if the number of areas is greater than or equals to the preset threshold, the N consecutive image frames will be determined as being unstable.

20. The non-transitory computer-readable storage medium according to claim 17, wherein the recording of each of the M areas whether a corner point exists in for obtaining the description vector of the image based on obtaining the length of M, comprises:

for each area in the M areas, if corner points are existed in, recording as “

1”

, if no corner points are existed in, recording as “

0”

, wherein the recorded “

1”

s are utilized to obtain the description vector of each image in order to obtain the length of M;

calculating to obtain the number of areas in which the existing state of corner points in each corresponding image frame has changed in the N consecutive image frames, according to the description vector of each image frame according to the following formula;