Image detection method and device

Patent metadata

Field	Value
Publication number	US-9361702-B2
Application number	US-201214127555-A
Country	US
Kind code	B2
Filing date	Jun 27, 2012
Priority date	Jun 28, 2011
Publication date	Jun 7, 2016
Grant date	Jun 7, 2016

Abstract

A method and device for detecting images are used to improve a detection rate and accuracy rate of the image moving target detection, so that moving targets also can be accurately detected in a scenario with complicated illumination changes. The method for detecting the images includes: collecting an image, performing moving target detection on the image by using a preset mixed space-time background model, and determining a target image; wherein, the mixed space-time background model is obtained in advance by modeling according to a grayscale change trend of the image.

First claim

What is claimed is:

1. A method for detecting images, comprising:
modeling to obtain a mixed space-time background model according to a grayscale change trend of an image; and
collecting the image, performing moving target detection on the image by using the mixed space-time background model to determine a moving target image;
wherein said modeling to obtain a mixed space-time background model according to a grayscale change trend of an image comprises:
determining a predicted pixel value based on exponential smoothing and illumination changes;
integrating the predicted pixel value and a Center Symmetric Local Binary Pattern (CSLBP) operator to obtain a Space Time-Center Symmetric-Local Binary Pattern (ST-CSLBP) operator;
calculating histograms corresponding to all pixels based on the ST-CSLBP operator; and
constructing a mixed space-time background model of the histograms corresponding to all the pixels based on the ST-CSLBP operator;
wherein the predicted pixel value is determined by using the following formula:

z
t

=

m
t

+

1
-
β

β

⁢

r

t
-
1

r
t

=

β
⁡

(

x
t

-

x

t
-
1

)

+

(

1
-
β

)

⁢

r

t
-
1

m
t

=

β
⁢

⁢

x
t

+

(

1
-
β

)

⁢

m

t
-
1

;

wherein z t represents a predicted pixel value of a pixel at time t, m t represents an estimated state value of the pixel at time t, β represents a smoothing factor, r t−1 represents a grayscale change trend of the pixel at time t−1, r t represents a grayscale change trend of the pixel at time t, x t represents an observed pixel value of the pixel at time t, and x t−1 represents an observed pixel value of the pixel at time t−1.

2. The method according to claim 1 , wherein the predicted pixel value and the CSLBP operator are integrated to obtain the ST-CSLBP operator by using the following formula:

ST
-

CSLBP

P
,
R

=

∑

p
=
0

P
/
2

-
1

⁢

{

s
⁡

(

g
p

,

g

p
+

P
/
2

)

⁢

2
p

+

s
⁡

(

g
zp

,

g

z
⁡

(

p
+

P
/
2

)

)

⁢

2

p
+

P
/

Assignees

• Fu Qiang
• Li Bo
• Zhang Zhenwei
• Chen Qimei
• He Jun
• Jiang Dengbiao
• Zte Corp

Inventors

• Fu Qiang
• Li Bo
• Zhang Zhenwei
• Chen Qimei
• He Jun
• Jiang Dengbiao

Classifications

• G06T2207/30232

  Surveillance · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• G06T2207/30196

  Human being; Person · CPC title

• G06T2207/30241

  Trajectory · CPC title

• G06T7/20 Primary

  Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51) · CPC title