CN103473544A - Robust human body feature rapid extraction method - Google Patents

Robust human body feature rapid extraction method Download PDF

Info

Publication number
CN103473544A
CN103473544A CN2013101596012A CN201310159601A CN103473544A CN 103473544 A CN103473544 A CN 103473544A CN 2013101596012 A CN2013101596012 A CN 2013101596012A CN 201310159601 A CN201310159601 A CN 201310159601A CN 103473544 A CN103473544 A CN 103473544A
Authority
CN
China
Prior art keywords
gradient
passage
human body
image
extracting method
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN2013101596012A
Other languages
Chinese (zh)
Inventor
刘亚洲
张艳
孙权森
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Science and Technology
Original Assignee
Nanjing University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing University of Science and Technology filed Critical Nanjing University of Science and Technology
Priority to CN2013101596012A priority Critical patent/CN103473544A/en
Publication of CN103473544A publication Critical patent/CN103473544A/en
Pending legal-status Critical Current

Links

Images

Abstract

The invention discloses a robust human body feature rapid extraction method. The method comprises a step of inputting an original image and calculating an image gradient to obtain a gradient image; a step of quantifying a step size according to the direction, performing directional division on the gradient image to obtain channels in different directions; a step of quantifying a step size according to the space and performing space division on each channel; a step of rotating each channel in a certain angle to obtain a channel; a step of using an integrogram to rapidly calculate a feature describer for every channel; a step of cascading the feature describers of all channels to form a group of feature describers; and a step of, according to different step size adjusting parameters, repeating the above steps until a preset number of groups of feature describers having different descriptive abilities are generated. The robust human body feature rapid extraction method prevents the introduction of noises, and significantly improves the efficiency of human body feature extraction.

Description

A kind of characteristics of human body's rapid extracting method of robust
Technical field
The present invention relates to computer vision and area of pattern recognition, more particularly, relate to a kind of characteristics of human body's method for expressing of isotropic multiple hierachical description.
Background technology
Human detection refers to position and the big or small process of determining all human bodies in defeated people's image or video sequence.As a gordian technique in the visual analysis of human motion, because its widespread use demand in intelligent monitoring and vehicle-mounted supplementary security system and obtained the attention of more and more researchers and research institution.Effectively feature extracting method can significantly promote the robustness reduce false alarm of human body detector.Therefore, how extracting effective feature is described and becomes the key factor that affects the human detection performance somatic data.
According to the difference of characteristic type, can be divided into feature and the feature based on gradient and the method based on multi-feature fusion of intensity-based.The difference existed for human appearance, much results of study show, the human body expression way based on gradient has better robustness than the expression way of intensity-based for variations such as illumination.And relatively recent a lot of results of study show, the method based on the gradient statistical information has better robustness for translation and the rotation at edge.For example: Lowe has proposed the constant descriptor of famous yardstick (Scale-Invariant Feature Transform, SIFT) and has carried out object detection; Mikolajczyk etc. have proposed position-direction histogram feature; Wu etc. have set forth the thought of the multi-level expression way based on the statistic abstraction degree.
Because human body has more degree of freedom, characteristic quantity is larger, although the method for the statistical nature based on gradient can obtain performance preferably, computation complexity is relatively high, often because computing velocity is crossed, is difficult to reach slowly requirement of real-time.In addition, if the yardstick of selected characteristic area is different with shape in characteristic extraction procedure, some tiny structures may be exaggerated by normalized mode, thereby introduce noise.
Summary of the invention
The object of the invention is to, in above-mentioned Human Detection, somatic data is difficult to carry out registration and the lower problem of counting yield, has proposed a kind of characteristics of human body's rapid extracting method of robust.
The technical solution that realizes the object of the invention is: a kind of characteristics of human body's rapid extracting method of robust, and the method comprises the following steps:
1) input original image, the computed image gradient obtains gradient image;
2) according to the direction quantization step
Figure 864607DEST_PATH_IMAGE002
, the gradient image travel direction is divided, obtain the different passage of direction
Figure 858233DEST_PATH_IMAGE004
;
3) according to the space quantization step-length , to each passage carry out spatial division;
4) for each passage
Figure 80770DEST_PATH_IMAGE004
, with
Figure 415936DEST_PATH_IMAGE008
the angle rotation, obtain passage
Figure 207175DEST_PATH_IMAGE010
.
5) for each passage
Figure 285989DEST_PATH_IMAGE010
, adopt integrogram to calculate fast its Feature Descriptor;
6) Feature Descriptor of all passages is connected in series, forms a stack features descriptor.
7) regulate parameter according to different step-lengths
Figure 846283DEST_PATH_IMAGE002
with
Figure 352351DEST_PATH_IMAGE006
, repeating step 2) ~ step 6), until generate the Feature Descriptor with different descriptive powers of preset group number.
In said method, in described step 1), original image can be gray level image or coloured image, if coloured image is converted to gray level image;
In said method, described step 2) comprise following concrete steps:
21) the compute gradient angle is the tangential angle of each pixel of gradient image;
22) adopt the direction quantization step
Figure 132351DEST_PATH_IMAGE002
the gradient angle is quantized, gradient image is divided into to the passage of different directions
Figure 2013101596012100002DEST_PATH_IMAGE012A
, the angle of each passage
Figure 77173DEST_PATH_IMAGE014
, the number of passage
Figure 429657DEST_PATH_IMAGE016
= ;
23) for , after retaining those and quantizing, the gradient angle is pixel, other pixel sets to 0;
In said method, described step 22) in
Figure 919172DEST_PATH_IMAGE002
be directly proportional to the rotation robustness of Gradient Features, be inversely proportional to orientation determination.
In said method, in described step 3), space is divided and is referred to, for
Figure 2013101596012100002DEST_PATH_IMAGE012AAA
, utilize one group of tangential angle to be
Figure 454059DEST_PATH_IMAGE020
spacing be
Figure 364246DEST_PATH_IMAGE006
parallel lines be divided into a plurality of divisions;
In said method, in described step 3)
Figure 289476DEST_PATH_IMAGE006
be directly proportional to the translation robustness of Gradient Features, be inversely proportional to location positioning.
In said method, in described step 4) for passage
Figure 576101DEST_PATH_IMAGE004
on the point
Figure 903177DEST_PATH_IMAGE022
, be mapped to passage
Figure 751310DEST_PATH_IMAGE010
on point be .
Figure 988573DEST_PATH_IMAGE022
with
Figure 170156DEST_PATH_IMAGE024
relation as follows:
Figure 687725DEST_PATH_IMAGE010
: postrotational passage input picture:
Figure 215975DEST_PATH_IMAGE026
（1）
Wherein,
Figure 252064DEST_PATH_IMAGE028
a little
Figure 442000DEST_PATH_IMAGE022
the gradient intensity at place.
Figure 829119DEST_PATH_IMAGE030
:
Figure 933341DEST_PATH_IMAGE010
marking image:
（2）
Figure 948887DEST_PATH_IMAGE034
:
Figure 620040DEST_PATH_IMAGE010
's
Figure 793532DEST_PATH_IMAGE036
the coordinate position document image:
Figure 866531DEST_PATH_IMAGE038
（3）
Figure 834487DEST_PATH_IMAGE040
:
Figure 930619DEST_PATH_IMAGE010
's
Figure 940425DEST_PATH_IMAGE042
the coordinate position document image:
（4）
Figure 272366DEST_PATH_IMAGE046
:
Figure 855794DEST_PATH_IMAGE048
position Square Graphs picture:
（5）
Figure 153101DEST_PATH_IMAGE052
:
Figure 462859DEST_PATH_IMAGE042
position Square Graphs picture:
Figure 595900DEST_PATH_IMAGE054
(6)
In said method, described step 5) comprises following concrete steps:
51) at each passage in, generate a rectangular characteristic window;
52), in characteristic window, calculate the gradient intensity of each division;
53) select to there is the division of greatest gradient intensity and calculate its Feature Descriptor;
In said method, described step 51) characteristic window can be random the generation, also can generate regularly according to a fixed step size.
In said method, described step 52) middle gradient intensity employing integrogram calculating of dividing.
Will
Figure 52869DEST_PATH_IMAGE010
brief note is
Figure 533529DEST_PATH_IMAGE056
, establish passage
Figure 825970DEST_PATH_IMAGE056
Figure 745384DEST_PATH_IMAGE022
the integrogram at place is designated as
Figure 439671DEST_PATH_IMAGE058
, establish and be divided into arbitrarily rectangle
Figure 153549DEST_PATH_IMAGE060
, wherein (
Figure 198865DEST_PATH_IMAGE062
) mean the point in the rectangle upper left corner,
Figure 656391DEST_PATH_IMAGE064
mean the wide and high of rectangle, divide
Figure 205184DEST_PATH_IMAGE066
gradient intensity adopt following formula to calculate:
Figure 293226DEST_PATH_IMAGE068
(7)
In said method, described step 53) in for passage
Figure 112322DEST_PATH_IMAGE010
, the division that has greatest gradient intensity in characteristic window is denoted as
Figure 45643DEST_PATH_IMAGE070
, its Feature Descriptor is the heterogeneous vector of one 7 dimension , meaning and the account form of each component of this vector are as follows:
A) be
Figure DEST_PATH_IMAGE076A
index value, this index value is normalized to
Figure 649166DEST_PATH_IMAGE078
, wherein
Figure 651757DEST_PATH_IMAGE080
it is the gradient intensity of dividing arbitrarily;
B)
Figure 175142DEST_PATH_IMAGE082
it is the gradient intensity of each division
Figure 903189DEST_PATH_IMAGE080
in maximal value, it is normalized to
Figure 144815DEST_PATH_IMAGE084
;
C)
Figure 747834DEST_PATH_IMAGE086
be the standard deviation of the gradient intensity of all divisions, calculate with following formula: , wherein ;
D)
Figure 252131DEST_PATH_IMAGE092
with
Figure 596524DEST_PATH_IMAGE094
be the average of the position of interior all non-zero pixels points, by following formula, calculate:
Figure 720601DEST_PATH_IMAGE096
,
Figure 226668DEST_PATH_IMAGE098
, wherein,
Figure 505203DEST_PATH_IMAGE100
the center of representation feature window,
Figure 387708DEST_PATH_IMAGE102
representation feature window wide and high, " ", " " and "
Figure 917413DEST_PATH_IMAGE108
" be
Figure 665926DEST_PATH_IMAGE030
,
Figure 872916DEST_PATH_IMAGE034
with
Figure 986366DEST_PATH_IMAGE040
write a Chinese character in simplified form,
Figure 475378DEST_PATH_IMAGE110
,
Figure 699686DEST_PATH_IMAGE112
with
Figure 89079DEST_PATH_IMAGE114
employing formula (7) is calculated.
E)
Figure 373430DEST_PATH_IMAGE116
with
Figure 582694DEST_PATH_IMAGE118
be
Figure DEST_PATH_IMAGE076AAA
the position distribution of interior all non-zero pixels points, along the standard deviation of gradient and normal orientation, is calculated by following formula:
Figure 673010DEST_PATH_IMAGE120
,
Figure 854593DEST_PATH_IMAGE122
, wherein, "
Figure 873627DEST_PATH_IMAGE124
" and "
Figure 773449DEST_PATH_IMAGE126
" be
Figure 401877DEST_PATH_IMAGE128
with
Figure 437966DEST_PATH_IMAGE052
write a Chinese character in simplified form,
Figure 126436DEST_PATH_IMAGE130
with
Figure 247976DEST_PATH_IMAGE132
employing formula (7) is calculated.
In said method, in described step 6), the form of Feature Descriptor is
Figure 617778DEST_PATH_IMAGE134
.
The present invention compared with prior art, its remarkable advantage: characteristics of human body's rapid extracting method of a kind of robust that the present invention proposes, because the yardstick of the division of all direction passages in characteristic extraction procedure is equal, tiny structure in little division can not be exaggerated by normalized mode, thereby has avoided the introducing noise.In addition, isotropic feature, because all divisions in characteristic window are all the rectangles of vertical direction, can be used the integrogram fast method to calculate, and has improved significantly the efficiency that the characteristics of human body extracts.
The accompanying drawing explanation
Fig. 1 feature extraction process flow diagram of the present invention.
Fig. 2 is transformed into original image the process of gradient image.
The process that Fig. 3 divides the gradient image travel direction.
The process of Fig. 4 spatial division quick calculated characteristics.
Embodiment
Integrated operation flow process of the present invention is as shown in Fig. 1.Below in conjunction with accompanying drawing, body embodiment of the present invention is described in further detail.
step 1:the input original image, the computed image gradient obtains gradient image.
Data source of the present invention is gray level image or coloured image.If coloured image can first convert gray level image to, then carry out subsequent treatment.
For input picture , as shown in figure 21, a tlv triple for each pixel on image
Figure 633324DEST_PATH_IMAGE138
mean, here with
Figure 713855DEST_PATH_IMAGE042
the position that means pixel,
Figure 786853DEST_PATH_IMAGE140
the gray-scale value that means pixel, used wave filter
Figure 754809DEST_PATH_IMAGE142
to image
Figure 850941DEST_PATH_IMAGE136
compute gradient, produce gradient image 22.
step 2:according to the direction quantization step
Figure 624862DEST_PATH_IMAGE002
, the gradient image travel direction is divided, obtain the passage of different directions.
The set direction quantization step
Figure 755629DEST_PATH_IMAGE002
for
Figure 956803DEST_PATH_IMAGE144
, to the gradient angle
Figure 274652DEST_PATH_IMAGE146
quantized, gradient image is divided into to the passage that several directions are different, here, the number of passage is designated as
Figure 353729DEST_PATH_IMAGE016
, =
Figure 648761DEST_PATH_IMAGE018
=9, the angle of each passage is designated as
Figure 516223DEST_PATH_IMAGE020
,
Figure 569629DEST_PATH_IMAGE148
, angle is
Figure 471726DEST_PATH_IMAGE020
passage is designated as
Figure 952386DEST_PATH_IMAGE004
.For
Figure 572723DEST_PATH_IMAGE004
, only have the rear gradient angle of those quantifications to be
Figure 790340DEST_PATH_IMAGE020
pixel be retained, other pixel is set to 0.As shown in Figure 3,31,32,33 ... 39 mean that respectively angle is
Figure 750206DEST_PATH_IMAGE144
,
Figure DEST_PATH_IMAGE150
,
Figure DEST_PATH_IMAGE152
......
Figure DEST_PATH_IMAGE154
passage.
Known according to the direction division methods, parameter
Figure DEST_PATH_IMAGE156
control the orientation determination of Gradient Features: when
Figure 526401DEST_PATH_IMAGE156
when value is larger, the orientation determination of the feature of reservation is less, and the rotation robustness is larger; Otherwise the orientation determination of the feature retained is larger, the rotation robustness is less.
step 3:according to the space quantization step-length , gradient image is carried out to spatial division.
For each passage
Figure 276848DEST_PATH_IMAGE004
, utilize tangential direction to be , spacing is one group of parallel lines be divided into a plurality of divisions.Take Figure 33 passage as example, and spatial division as shown in figure 41.
Known according to space-division method, parameter
Figure 305350DEST_PATH_IMAGE006
control the location positioning of Gradient Features: when
Figure 504250DEST_PATH_IMAGE006
when value is larger, the location positioning of the Gradient Features of reservation is less, and the translation robustness is larger; Otherwise the location positioning of the Gradient Features retained is larger, the translation robustness is less.
step 4:for each passage
Figure 173129DEST_PATH_IMAGE004
, with
Figure 228809DEST_PATH_IMAGE008
the angle rotation, postrotational passage is called as
Figure 983139DEST_PATH_IMAGE010
.
At passage the place two field picture on point
Figure 135214DEST_PATH_IMAGE022
, be mapped to passage point on the image of place frame is . with
Figure 584333DEST_PATH_IMAGE024
relation as follows:
: postrotational passage
Figure 648421DEST_PATH_IMAGE020
input picture:
Figure 556596DEST_PATH_IMAGE026
（1）
Wherein,
Figure 788994DEST_PATH_IMAGE028
a little
Figure 622958DEST_PATH_IMAGE022
the gradient intensity at place.
Figure 573597DEST_PATH_IMAGE030
:
Figure 518419DEST_PATH_IMAGE010
marking image:
Figure 870903DEST_PATH_IMAGE032
（2）
Figure 875768DEST_PATH_IMAGE034
:
Figure 313702DEST_PATH_IMAGE010
's the coordinate position document image:
Figure 770671DEST_PATH_IMAGE038
（3）
Figure 884120DEST_PATH_IMAGE040
:
Figure 871668DEST_PATH_IMAGE010
's
Figure 95976DEST_PATH_IMAGE042
the coordinate position document image:
（4）
Figure 504140DEST_PATH_IMAGE046
:
Figure 978984DEST_PATH_IMAGE048
position Square Graphs picture:
Figure 6983DEST_PATH_IMAGE050
（5）
:
Figure 207600DEST_PATH_IMAGE042
position Square Graphs picture:
Figure 841843DEST_PATH_IMAGE054
（6）
Take Figure 41 as example, image is rotated counterclockwise
Figure DEST_PATH_IMAGE158
, obtain Figure 42.
step 5:for each passage
Figure 470271DEST_PATH_IMAGE010
, adopt integrogram to calculate fast its Feature Descriptor.
step 51:for each passage
Figure 834256DEST_PATH_IMAGE010
, generate a rectangular characteristic window, as shown in figure 42.
Characteristic window can be random the generation, also can generate regularly according to a fixed step size.If picture traverse and highly being respectively
Figure DEST_PATH_IMAGE160
, the characteristic window of generation is
Figure DEST_PATH_IMAGE162
, wherein (
Figure DEST_PATH_IMAGE164
) mean the point in the window upper left corner,
Figure 522726DEST_PATH_IMAGE102
the representation feature window is wide and high respectively, and characteristic window satisfies condition: .
step 52:adopt integrogram calculated characteristics window
Figure 208048DEST_PATH_IMAGE162
the gradient intensity of interior all divisions.
Will brief note is
Figure 796341DEST_PATH_IMAGE056
, establish passage
Figure 264548DEST_PATH_IMAGE022
the integrogram at place is designated as
Figure 172462DEST_PATH_IMAGE058
, divide and be designated as rectangular area arbitrarily
Figure 245460DEST_PATH_IMAGE060
, divide
Figure 213416DEST_PATH_IMAGE066
gradient intensity adopt following formula to calculate:
Figure 873329DEST_PATH_IMAGE068
(7)
step 53:selection has the division of greatest gradient intensity, calculates its Feature Descriptor.
Selection has the division of greatest gradient intensity, as shown in figure 43, is denoted by
Figure 584934DEST_PATH_IMAGE070
,
Figure 512438DEST_PATH_IMAGE070
feature Descriptor be one 7 the dimension heterogeneous vector
Figure 651296DEST_PATH_IMAGE072
, meaning and the account form of each component of this vector are as follows:
A)
Figure 297041DEST_PATH_IMAGE074
be
Figure DEST_PATH_IMAGE076AAAA
index value, this index value is normalized to
Figure 874652DEST_PATH_IMAGE078
, wherein
Figure 158128DEST_PATH_IMAGE080
it is the gradient intensity of dividing arbitrarily;
B)
Figure 467887DEST_PATH_IMAGE082
it is the gradient intensity of each division
Figure 600928DEST_PATH_IMAGE080
in maximal value, it is normalized to
Figure 654335DEST_PATH_IMAGE084
;
C)
Figure 556432DEST_PATH_IMAGE086
be the standard deviation of the gradient intensity of all divisions, calculate with following formula:
Figure 37092DEST_PATH_IMAGE088
, wherein
Figure 595112DEST_PATH_IMAGE090
;
D) with
Figure 943234DEST_PATH_IMAGE094
be
Figure DEST_PATH_IMAGE076AAAAA
the average of the position of interior all non-zero pixels points, by following formula, calculate: ,
Figure 254491DEST_PATH_IMAGE098
, wherein,
Figure 712017DEST_PATH_IMAGE100
the center of representation feature window,
Figure 526390DEST_PATH_IMAGE102
the representation feature window is wide and high respectively, "
Figure 411169DEST_PATH_IMAGE104
", "
Figure 678202DEST_PATH_IMAGE106
" and "
Figure 877102DEST_PATH_IMAGE108
" be
Figure 109763DEST_PATH_IMAGE030
,
Figure 103127DEST_PATH_IMAGE034
with
Figure 919773DEST_PATH_IMAGE040
write a Chinese character in simplified form,
Figure 656785DEST_PATH_IMAGE110
,
Figure 242487DEST_PATH_IMAGE112
with employing formula (7) is calculated.
E)
Figure 913957DEST_PATH_IMAGE116
with
Figure 251397DEST_PATH_IMAGE118
be the position distribution of interior all non-zero pixels points, along the standard deviation of gradient and normal orientation, is calculated by following formula:
Figure 458650DEST_PATH_IMAGE120
,
Figure 856133DEST_PATH_IMAGE122
, wherein, "
Figure 585055DEST_PATH_IMAGE124
" and "
Figure 663869DEST_PATH_IMAGE126
" be
Figure 224163DEST_PATH_IMAGE128
with
Figure 995810DEST_PATH_IMAGE052
write a Chinese character in simplified form,
Figure 8766DEST_PATH_IMAGE130
with
Figure 891271DEST_PATH_IMAGE132
employing formula (7) is calculated.
step 6:the Feature Descriptor of all direction passages is joined together, form final descriptor, be expressed as
Figure 807537DEST_PATH_IMAGE134
.
step 7:change respectively the direction quantization step according to different step-lengths
Figure 750085DEST_PATH_IMAGE002
with the space quantization step-length
Figure 188020DEST_PATH_IMAGE006
, repeating step 2 ~ step 6, until generate the Feature Descriptor with different descriptive powers of preset group number.

Claims (12)

1. characteristics of human body's rapid extracting method of a robust is characterized in that step is as follows:
1) input original image, the computed image gradient obtains gradient image;
2) according to the direction quantization step
Figure 853588DEST_PATH_IMAGE002
, the gradient image travel direction is divided, obtain the different passage of direction ;
3) according to the space quantization step-length
Figure 488149DEST_PATH_IMAGE006
, to each passage
Figure 883358DEST_PATH_IMAGE004
carry out spatial division;
4) for each passage
Figure 635414DEST_PATH_IMAGE004
, with
Figure 457876DEST_PATH_IMAGE008
the angle rotation, obtain passage
Figure 662592DEST_PATH_IMAGE010
;
5) for each passage
Figure 861493DEST_PATH_IMAGE010
, adopt integrogram to calculate fast its Feature Descriptor;
6) Feature Descriptor of all passages is connected in series, forms a stack features descriptor;
7) regulate parameter according to different step-lengths
Figure 969519DEST_PATH_IMAGE002
with
Figure 962883DEST_PATH_IMAGE006
, repeating step 2) ~ step 6), until generate the Feature Descriptor with different descriptive powers of preset group number.
2. characteristics of human body's rapid extracting method of robust according to claim 1, it is characterized in that: in described step 1), original image is gray level image or coloured image, if coloured image is converted to gray level image.
3. characteristics of human body's rapid extracting method of robust according to claim 1, is characterized in that described step 2) comprise following concrete steps:
21) the compute gradient angle is the tangential angle of each pixel of gradient image;
22) adopt the direction quantization step
Figure 654896DEST_PATH_IMAGE002
the gradient angle is quantized, gradient image is divided into to the passage of different directions
Figure DEST_PATH_IMAGE012A
, the angle of each passage
Figure 267274DEST_PATH_IMAGE014
, the number of passage =
Figure 656721DEST_PATH_IMAGE018
,
Figure DEST_PATH_IMAGE020A
=1,2
Figure DEST_PATH_IMAGE022A
;
23) for , after retaining those and quantizing, the gradient angle is pixel, other pixel sets to 0.
4. according to characteristics of human body's rapid extracting method of claim 1 or 3 described robust, it is characterized in that: described step 22)
Figure 986520DEST_PATH_IMAGE002
be directly proportional to the rotation robustness of Gradient Features, be inversely proportional to orientation determination.
5. characteristics of human body's rapid extracting method of robust according to claim 1 is characterized in that: in described step 3), space is divided and is referred to, for
Figure DEST_PATH_IMAGE012AAA
, utilize one group of tangential angle to be spacing be parallel lines be divided into a plurality of divisions.
6. characteristics of human body's rapid extracting method of robust according to claim 1, is characterized in that: in described step 3)
Figure 8593DEST_PATH_IMAGE006
be directly proportional to the translation robustness of Gradient Features, be inversely proportional to location positioning.
7. characteristics of human body's rapid extracting method of robust according to claim 1 is characterized in that: in described step 4) for passage
Figure 25090DEST_PATH_IMAGE004
on the point
Figure 523068DEST_PATH_IMAGE026
, be mapped to passage
Figure 730933DEST_PATH_IMAGE010
on point be
Figure 681572DEST_PATH_IMAGE028
, with
Figure 854244DEST_PATH_IMAGE028
relation as follows:
Figure 734475DEST_PATH_IMAGE010
: postrotational passage
Figure 110093DEST_PATH_IMAGE024
input picture:
Figure 530710DEST_PATH_IMAGE030
（1）
Wherein, a little
Figure 544158DEST_PATH_IMAGE026
the gradient intensity at place;
Figure 469389DEST_PATH_IMAGE034
:
Figure 631380DEST_PATH_IMAGE010
marking image:
Figure 692877DEST_PATH_IMAGE036
（2）
Figure 914911DEST_PATH_IMAGE038
:
Figure 265121DEST_PATH_IMAGE010
's
Figure 293120DEST_PATH_IMAGE040
the coordinate position document image:
Figure 474702DEST_PATH_IMAGE042
（3）
Figure 100593DEST_PATH_IMAGE044
: 's
Figure 504210DEST_PATH_IMAGE046
the coordinate position document image:
Figure 805878DEST_PATH_IMAGE048
（4）
Figure 104136DEST_PATH_IMAGE050
:
Figure 491255DEST_PATH_IMAGE052
position Square Graphs picture:
Figure 798739DEST_PATH_IMAGE054
（5）
:
Figure 925537DEST_PATH_IMAGE046
position Square Graphs picture:
(6)。
8. characteristics of human body's rapid extracting method of robust according to claim 1 is characterized in that described step 5) comprises following concrete steps:
51) at each passage
Figure 645549DEST_PATH_IMAGE010
in, generate a rectangular characteristic window;
52), in characteristic window, calculate the gradient intensity of each division;
53) select to there is the division of greatest gradient intensity and calculate its Feature Descriptor.
9. characteristics of human body's rapid extracting method of robust according to claim 8 is characterized in that: described step 51) characteristic window can be random the generation, also can generate regularly according to a fixed step size.
10. characteristics of human body's rapid extracting method of robust according to claim 8, is characterized in that: the gradient intensity employing integrogram calculating of dividing described step 52);
Will
Figure 656230DEST_PATH_IMAGE010
brief note is
Figure 561869DEST_PATH_IMAGE060
, establish passage
Figure 658001DEST_PATH_IMAGE060
Figure 307288DEST_PATH_IMAGE026
the integrogram at place is designated as
Figure 172476DEST_PATH_IMAGE062
, establish and be divided into arbitrarily rectangle
Figure 747552DEST_PATH_IMAGE064
, wherein (
Figure 330980DEST_PATH_IMAGE066
) mean the point in the rectangle upper left corner,
Figure 518379DEST_PATH_IMAGE068
mean the wide and high of rectangle, divide
Figure 503652DEST_PATH_IMAGE064
gradient intensity adopt following formula to calculate:
Figure 751094DEST_PATH_IMAGE070
(7).
11. characteristics of human body's rapid extracting method of robust according to claim 8 is characterized in that: described step 53) for passage
Figure 821818DEST_PATH_IMAGE010
, the division that has greatest gradient intensity in characteristic window is denoted as
Figure 812908DEST_PATH_IMAGE072
, its Feature Descriptor is the heterogeneous vector of one 7 dimension
Figure 652688DEST_PATH_IMAGE074
, meaning and the account form of each component of this vector are as follows:
A)
Figure 572496DEST_PATH_IMAGE076
be
Figure DEST_PATH_IMAGE078A
index value, this index value is normalized to
Figure 802620DEST_PATH_IMAGE080
, wherein
Figure 659718DEST_PATH_IMAGE082
it is the gradient intensity of dividing arbitrarily;
B)
Figure 291687DEST_PATH_IMAGE084
it is the gradient intensity of each division
Figure 943248DEST_PATH_IMAGE082
in maximal value, it is normalized to
Figure 926248DEST_PATH_IMAGE086
;
C)
Figure 321457DEST_PATH_IMAGE088
be the standard deviation of the gradient intensity of all divisions, calculate with following formula:
Figure 870250DEST_PATH_IMAGE090
, wherein
Figure 394510DEST_PATH_IMAGE092
;
D) with
Figure 798127DEST_PATH_IMAGE096
be the average of the position of interior all non-zero pixels points, by following formula, calculate:
Figure DEST_PATH_IMAGE098
,
Figure DEST_PATH_IMAGE100
, wherein, the center of representation feature window,
Figure DEST_PATH_IMAGE104
representation feature window wide and high, "
Figure DEST_PATH_IMAGE106
", "
Figure DEST_PATH_IMAGE108
" and "
Figure DEST_PATH_IMAGE110
" be
Figure 453623DEST_PATH_IMAGE034
,
Figure 712566DEST_PATH_IMAGE038
with
Figure 404579DEST_PATH_IMAGE044
write a Chinese character in simplified form,
Figure DEST_PATH_IMAGE112
,
Figure DEST_PATH_IMAGE114
with
Figure DEST_PATH_IMAGE116
employing formula (7) is calculated;
E)
Figure DEST_PATH_IMAGE118
with
Figure DEST_PATH_IMAGE120
be the position distribution of interior all non-zero pixels points, along the standard deviation of gradient and normal orientation, is calculated by following formula:
Figure DEST_PATH_IMAGE122
, , wherein, " " and "
Figure DEST_PATH_IMAGE128
" be
Figure DEST_PATH_IMAGE130
with write a Chinese character in simplified form,
Figure DEST_PATH_IMAGE132
with
Figure DEST_PATH_IMAGE134
employing formula (7) is calculated.
12. characteristics of human body's rapid extracting method of robust according to claim 1 is characterized in that: in described step 6), the form of Feature Descriptor is
Figure DEST_PATH_IMAGE136
.
CN2013101596012A 2013-04-28 2013-04-28 Robust human body feature rapid extraction method Pending CN103473544A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2013101596012A CN103473544A (en) 2013-04-28 2013-04-28 Robust human body feature rapid extraction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2013101596012A CN103473544A (en) 2013-04-28 2013-04-28 Robust human body feature rapid extraction method

Publications (1)

Publication Number Publication Date
CN103473544A true CN103473544A (en) 2013-12-25

Family

ID=49798388

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2013101596012A Pending CN103473544A (en) 2013-04-28 2013-04-28 Robust human body feature rapid extraction method

Country Status (1)

Country Link
CN (1) CN103473544A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080304750A1 (en) * 2002-07-16 2008-12-11 Nec Corporation Pattern feature extraction method and device for the same
CN102136066A (en) * 2011-04-29 2011-07-27 电子科技大学 Method for recognizing human motion in video sequence
CN102663449A (en) * 2012-03-12 2012-09-12 西安电子科技大学 Method for tracing human body movement based on maximum geometric flow histogram
CN102663391A (en) * 2012-02-27 2012-09-12 安科智慧城市技术（中国）有限公司 Image multifeature extraction and fusion method and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080304750A1 (en) * 2002-07-16 2008-12-11 Nec Corporation Pattern feature extraction method and device for the same
CN102136066A (en) * 2011-04-29 2011-07-27 电子科技大学 Method for recognizing human motion in video sequence
CN102663391A (en) * 2012-02-27 2012-09-12 安科智慧城市技术（中国）有限公司 Image multifeature extraction and fusion method and system
CN102663449A (en) * 2012-03-12 2012-09-12 西安电子科技大学 Method for tracing human body movement based on maximum geometric flow histogram

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘亚洲: ""基于时空分析和多粒度特征表示的人体检测方法研究"", 《中国博士学位论文全文数据库 信息科技辑（月刊）》 *
陈刚: ""基于多特征的行人检测方法研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Similar Documents

Publication Publication Date Title
CN109918969B (en) Face detection method and device, computer device and computer readable storage medium
Akinlar et al. Edlines: Real-time line segment detection by edge drawing (ed)
CN106960451B (en) Method for increasing number of feature points of image weak texture area
WO2020119661A1 (en) Target detection method and device and pedestrian detection method and system
US9681047B2 (en) Image feature extraction method and system
WO2016082277A1 (en) Video authentication method and apparatus
CN103020993B (en) Visual saliency detection method by fusing dual-channel color contrasts
CN104778476B (en) A kind of image classification method
CN103530619A (en) Gesture recognition method of small quantity of training samples based on RGB-D (red, green, blue and depth) data structure
CN102722891A (en) Method for detecting image significance
IL268215B (en) Method for image processing for content detection
WO2018082308A1 (en) Image processing method and terminal
CN106778768A (en) Image scene classification method based on multi-feature fusion
CN103473537B (en) A kind of target image contour feature method for expressing and device
CN104408445A (en) Automatic real-time human body detecting method
CN103440662A (en) Kinect depth image acquisition method and device
CN105139417A (en) Method for real-time multi-target tracking under video surveillance
CN103646249A (en) Greenhouse intelligent mobile robot vision navigation path identification method
CN103218605A (en) Quick eye locating method based on integral projection and edge detection
US20180144490A1 (en) Method, Apparatus, Storage Medium and Device for Controlled Synthesis of Inhomogeneous Textures
CN106600613B (en) Improvement LBP infrared target detection method based on embedded gpu
CN103093226B (en) A kind of building method of the RATMIC descriptor for characteristics of image process
CN108304833A (en) Face identification method based on MBLBP and DCT-BM2DPCA
CN110570450B (en) Target tracking method based on cascade context-aware framework
CN104050673A (en) Depth map extraction method based on K-means image segmentation

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20131225

RJ01 Rejection of invention patent application after publication