CN109767441A - A kind of automatic detection blind element labeling method - Google Patents
A kind of automatic detection blind element labeling method Download PDFInfo
- Publication number
- CN109767441A CN109767441A CN201910035186.7A CN201910035186A CN109767441A CN 109767441 A CN109767441 A CN 109767441A CN 201910035186 A CN201910035186 A CN 201910035186A CN 109767441 A CN109767441 A CN 109767441A
- Authority
- CN
- China
- Prior art keywords
- blind element
- temperature difference
- automatic detection
- point
- labeling 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.)
- Granted
Links
Abstract
The invention discloses a kind of automatic detection blind element labeling methods, which comprises obtains the current frame image and previous frame image of the same position of infrared thermovision system shooting；Calculate the temperature difference in the two field pictures of front and back between pixel judges whether central pixel point is blind element by the average value and minimum estimation central pixel point temperature difference of the calculated field n*n temperature difference；If central pixel point temperature difference is equal to blind element point gray value and deviates default estimated difference, which is blind element；It solves the existing lower technical problem of handmarking's efficiency, realizes the technical effect for carrying out detection label to blind element automatically.
Description
Technical field
The present invention relates to infrared thermovision system blind elements to demarcate field, and in particular, to a kind of automatic detection blind element labeling method.
Background technique
There are a kind of imaging means of the infrared imagery technique as current comparative maturity many visual light imaging technologies not have
Standby feature has irreplaceable role in our industrial production and daily life.But due to device making technics and
The limitation of technology itself, infrared imaging also suffer from certain drawbacks, and there are the lists of some responses " blunt " especially in detector
Member, we are known as blind element, these blind elements can influence image quality to a certain extent,
Blind element, which refers to, responds excessively high and too low detector cells in device, in infrared focal plane device the quantity of blind element and
The influence that it is distributed to device performance is very big, if blind element is excessive, in the infrared imaging system output without any response processing
To occur a large amount of bright spot and dim spot in image, so that the visual effect of output image is very poor.
Infrared thermovision system demarcates blind element when leaving the factory, but might have new blind element in user and generate, at this moment
Blind user's mark is a troublesome thing, so propose the simple and fast method of one kind marks blind element automatically.
Summary of the invention
The present invention provides a kind of automatic detection blind element labeling methods, solve existing handmarking's efficiency compared with low technical
Problem realizes the technical effect for carrying out detection label to blind element automatically.
For achieving the above object, this application provides a kind of automatic detection blind element labeling methods, which comprises
Obtain the current frame image and previous frame image of the same position of infrared thermovision system shooting；
The temperature difference in the two field pictures of front and back between pixel is calculated, being averaged for the calculated field n*n temperature difference is passed through
Value and minimum estimation central pixel point temperature difference, judge whether central pixel point is blind element；
If central pixel point temperature difference be equal to blind element point gray value (blind element point gray value, show as not varying with temperature and
There was only very little variation with temperature) and deviate default estimated difference, then the pixel is blind element.
This method realizes the automatic label of blind element using above method step, is manually marked instead of traditional,
Labeling effciency is detected to improve.
Further, the current frame image In and upper one of the same position of infrared thermovision system shooting is obtained using 3*3 window
Frame image In1；Wherein, w1=In (i+r:j+r), w2=In1 (i+r:j+r), w1 are the 3*3 windows of In, and wn2 is the 3*3 of In1
Window, i are image line coordinates, and j is image column coordinate, r={ -1,0,1 }.
Further, the temperature difference in the two field pictures of front and back between pixel is calculated, specifically:
D (i+r, j+r)=(w1-w2) ^2；Wherein, d (i+r, j+r) is the gray scale difference in the field 3*3.
Further, the gray scale difference mean value avg_d of all non-blind element point d (i+r, j+r) is calculated, and calculates all non-blind elements
Minimum value d_min in point d (i+r, j+r).
Further, d (i, j) is the gray scale difference of the field 3*3 central point, if d (i, j)=d_min, and (d (i, j) * (r*r
+ 1)) * gain < (avg_d)), gain is to take any one integer in (1~3), then d (i, j) is blind element point.
Further, gain=2.
One or more technical solution provided by the present application, has at least the following technical effects or advantages:
Present invention application infrared thermal imaging application product can generate new blind element in use, and this method can be automatic
Flag update blind element point；It solves the existing lower technical problem of handmarking's efficiency, realizes and blind element is detected automatically
The technical effect of label.
Detailed description of the invention
Attached drawing described herein is used to provide to further understand the embodiment of the present invention, constitutes one of the application
Point, do not constitute the restriction to the embodiment of the present invention；
Fig. 1 is the flow diagram of this method.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention is further described in detail.It should be noted that in the case where not conflicting mutually, the application's
Feature in embodiment and embodiment can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used also
Implemented with being different from the other modes being described herein in range using other, therefore, protection scope of the present invention is not by under
The limitation of specific embodiment disclosed in face.
Embodiment
The present invention provides a kind of automatic detection blind element labeling methods, comprising:
Step 1；Using 3*3 window present frame wn=I (i+r:j+r) r={ -1,0,1 }, previous frame same position 3*
3wwn1=I (i+r:j+r) r={ -1,0,1 }；
Step 2:d (i+r, j+r)=(w1-w2) ^2；
Step 3: calculating d (i+r, j+r) non-blind element point and the non-blind element point of sum_d, d (i+r, j+r) minimum value d_
min；
Step 4: if d (i, j)=d_min this point of (d (i, j) * (r*r+1)) * gain < sum_d (gain=2) simultaneously
It is blind element.
Referring to FIG. 1, a kind of automatic detection blind element labeling method, which comprises
Obtain the current frame image and previous frame image of the same position of infrared thermovision system shooting；
The temperature difference in the two field pictures of front and back between pixel is calculated, being averaged for the calculated field n*n temperature difference is passed through
Value and minimum estimation central pixel point temperature difference, judge whether central pixel point is blind element；
If central pixel point temperature difference be equal to blind element point gray value (blind element point gray value, show as not varying with temperature and
There was only very little variation with temperature) and deviate default estimated difference, then the pixel is blind element.
This method realizes the automatic label of blind element using above method step, is manually marked instead of traditional,
Labeling effciency is detected to improve.
Further, the current frame image In and upper one of the same position of infrared thermovision system shooting is obtained using 3*3 window
Frame image In1；Wherein, w1=In (i+r:j+r), w2=In1 (i+r:j+r), w1 are the 3*3 windows of In, and wn2 is the 3*3 of In1
Window, i are image line coordinates, and j is image column coordinate, r={ -1,0,1 }.
Further, the temperature difference in the two field pictures of front and back between pixel is calculated, specifically:
D (i+r, j+r)=(w1-w2) ^2；Wherein, d (i+r, j+r) is the gray scale difference in the field 3*3.
Further, the gray scale difference mean value avg_d of all non-blind element point d (i+r, j+r) is calculated, and calculates all non-blind elements
Minimum value d_min in point d (i+r, j+r).
Further, d (i, j) is the gray scale difference of the field 3*3 central point, if d (i, j)=d_min, and (d (i, j) * (r*r
+ 1)) * gain < (avg_d)), gain is to take any one integer in (1~3), then d (i, j) is blind element point.
Further, gain=2.
This method specifically includes: NUC-- > blind element replacement -- detection of > blind element -- > blind element label.
Using present frame a and previous frame b frame image detection blind element；
Two field pictures all take 3*3 block, judge whether in moving region；
A (i-1:i+1, j-1:j+1)={ a (i-1, j-1), a (i-1, j), a (i-1, j+1)；
a(i,j-1),a(i,j),a(i,j+1)；
a(i+1,j-1),a(i+1,j),a(i+1,j+1)}
B (i-1:i+1, j-1:j+1)={ b (i-1, j-1), b (i-1, j), b (i-1, j+1)；
b(i,j-1),b(i,j),b(i,j+1)；
b(i+1,j-1),b(i+1,j),b(i+1,j+1)}
Tim e- domain detection:
Dif=abs (a (i-1:i+1, j-1:j+1)-b (i-1:i+1, j-1:j+1))；
Dif_s0=sum (dif) (calculate and)；
Dif_min=min (dif) (calculated minimum)；
Mov_f=(dif_s0/9) > thd1 (configurable threshold)；
Blind_f0=abs (a (i, j)-b (i, j))==dif_min；
Blind_f1=abs (a (i, j)-b (i, j)) < thd2 (configurable threshold)；
Spatial filter:
Dmin=min (a (i-1:i+1, j-1:j+1))；
Dmax=min (a (i-1:i+1, j-1:j+1)；
Bind_f2=(Dmax-Dmin) > thd3 (configurable threshold)
Bind_f3=(a (i, j)==Dmin) | (a (i, j)==Dmax)；
Bind_f=blind_f0&blind_f1&Bind_f2&Bind_f3 (Bind_f=1 indicates blind element)
It detects blind element and updates blind element information completion blind element label.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (6)
1. a kind of automatic detection blind element labeling method, which is characterized in that the described method includes:
Obtain the current frame image and previous frame image of the same position of infrared thermovision system shooting；
The temperature difference in the two field pictures of front and back between pixel is calculated, the field n*n temperature difference is obtained, n is number of pixels, is based on n*
The average value and minimum estimation central pixel point temperature difference of the field n temperature difference, judge whether central pixel point is blind element；
If central pixel point temperature difference is equal to blind element point gray value and deviates default estimated difference, which is blind element.
2. automatic detection blind element labeling method according to claim 1, which is characterized in that obtained using 3*3 window infrared
The current frame image In and previous frame image In1 of the same position of thermovision system shooting；Wherein, w1=In (i+r:j+r), w2=
In1 (i+r:j+r), w1 are the 3*3 windows of In, and wn2 is the 3*3 window of In1, and i is image line coordinate, and j is image column coordinate, r
={ -1,0,1 }.
3. automatic detection blind element labeling method according to claim 2, which is characterized in that calculate picture in the two field pictures of front and back
Temperature difference between vegetarian refreshments, specifically:
D (i+r, j+r)=(w1-w2) ^2；Wherein, d (i+r, j+r) is the gray scale difference in the field 3*3.
4. automatic detection blind element labeling method according to claim 3, which is characterized in that calculate all non-blind element point d (i+
R, j+r) gray scale difference mean value avg_d, and calculate the minimum value d_min in all non-blind element point d (i+r, j+r).
5. automatic detection blind element labeling method according to claim 4, which is characterized in that d (i, j) is the field 3*3 center
The gray scale difference of point, if d (i, j)=d_min, and (d (i, j) * (r*r+1)) * gain < (avg_d)), gain is to take (1~3) appoint in
It anticipates an integer, then d (i, j) is blind element point.
6. automatic detection blind element labeling method according to claim 5, which is characterized in that gain=2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910035186.7A CN109767441B (en) | 2019-01-15 | 2019-01-15 | Automatic detection blind pixel marking method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910035186.7A CN109767441B (en) | 2019-01-15 | 2019-01-15 | Automatic detection blind pixel marking method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109767441A true CN109767441A (en) | 2019-05-17 |
| CN109767441B CN109767441B (en) | 2021-11-02 |
Family
ID=66452941
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910035186.7A Active CN109767441B (en) | 2019-01-15 | 2019-01-15 | Automatic detection blind pixel marking method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109767441B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612773A (en) * | 2020-05-22 | 2020-09-01 | 北京富吉瑞光电科技有限公司 | Thermal infrared imager and real-time automatic blind pixel detection processing method |
| WO2021134713A1 (en) * | 2019-12-31 | 2021-07-08 | 深圳市大疆创新科技有限公司 | Infrared image processing method and apparatus |
| CN113252207A (en) * | 2021-07-15 | 2021-08-13 | 广东电网有限责任公司江门供电局 | Electrical equipment metal surface temperature difference detection method and system |
| CN113781580A (en) * | 2021-09-10 | 2021-12-10 | 北京安酷智芯科技有限公司 | Method and device for quickly identifying blind pixels, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980283A (en) * | 2010-10-21 | 2011-02-23 | 电子科技大学 | Method for dynamically compensating blind pixel |
| US20140270568A1 (en) * | 2013-03-14 | 2014-09-18 | Drs Rsta, Inc. | Method and system for noise reduction in video systems |
| US20160234489A1 (en) * | 2014-06-23 | 2016-08-11 | Unlimited Optics Corp. | Method for measuring performance parameters and detecting bad pixels of an infrared focal plane array module |
| CN106373094A (en) * | 2016-08-25 | 2017-02-01 | 中国科学院长春光学精密机械与物理研究所 | Non-uniformity correction method and apparatus for infrared image |
| CN106525245A (en) * | 2016-11-03 | 2017-03-22 | 浙江大学 | Rapid sequential blind pixel detection and correction method based on tri-gradient thresholds |
| CN107431771A (en) * | 2015-03-06 | 2017-12-01 | 菲力尔系统公司 | Abnormal pixel detects |
| CN108513075A (en) * | 2018-04-17 | 2018-09-07 | 烟台艾睿光电科技有限公司 | A kind of image processing method, device, equipment, medium and infrared imaging device |
-
2019
- 2019-01-15 CN CN201910035186.7A patent/CN109767441B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980283A (en) * | 2010-10-21 | 2011-02-23 | 电子科技大学 | Method for dynamically compensating blind pixel |
| US20140270568A1 (en) * | 2013-03-14 | 2014-09-18 | Drs Rsta, Inc. | Method and system for noise reduction in video systems |
| US20160234489A1 (en) * | 2014-06-23 | 2016-08-11 | Unlimited Optics Corp. | Method for measuring performance parameters and detecting bad pixels of an infrared focal plane array module |
| CN107431771A (en) * | 2015-03-06 | 2017-12-01 | 菲力尔系统公司 | Abnormal pixel detects |
| CN106373094A (en) * | 2016-08-25 | 2017-02-01 | 中国科学院长春光学精密机械与物理研究所 | Non-uniformity correction method and apparatus for infrared image |
| CN106525245A (en) * | 2016-11-03 | 2017-03-22 | 浙江大学 | Rapid sequential blind pixel detection and correction method based on tri-gradient thresholds |
| CN108513075A (en) * | 2018-04-17 | 2018-09-07 | 烟台艾睿光电科技有限公司 | A kind of image processing method, device, equipment, medium and infrared imaging device |
Non-Patent Citations (1)
| Title |
|---|
| 宋海漫: "红外图像盲元检测及误判盲元修正算法", 《中国优秀硕士学位论文全文数据库（电子期刊）信息科技辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021134713A1 (en) * | 2019-12-31 | 2021-07-08 | 深圳市大疆创新科技有限公司 | Infrared image processing method and apparatus |
| CN111612773A (en) * | 2020-05-22 | 2020-09-01 | 北京富吉瑞光电科技有限公司 | Thermal infrared imager and real-time automatic blind pixel detection processing method |
| CN111612773B (en) * | 2020-05-22 | 2021-02-02 | 北京富吉瑞光电科技股份有限公司 | Thermal infrared imager and real-time automatic blind pixel detection processing method |
| CN113252207A (en) * | 2021-07-15 | 2021-08-13 | 广东电网有限责任公司江门供电局 | Electrical equipment metal surface temperature difference detection method and system |
| CN113781580A (en) * | 2021-09-10 | 2021-12-10 | 北京安酷智芯科技有限公司 | Method and device for quickly identifying blind pixels, electronic equipment and storage medium |
| CN113781580B (en) * | 2021-09-10 | 2024-03-26 | 北京安酷智芯科技有限公司 | Method and device for quickly identifying blind pixels, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109767441B (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109767441A (en) | A kind of automatic detection blind element labeling method | |
| US9846927B2 (en) | Systems and methods for haziness detection | |
| CN103996174B (en) | Method for performing hole repair on Kinect depth images | |
| US10654422B2 (en) | View friendly monitor systems | |
| CN103886107B (en) | Robot localization and map structuring system based on ceiling image information | |
| US10455147B2 (en) | Image processing method | |
| US20180063511A1 (en) | Apparatus and method for detecting object automatically and estimating depth information of image captured by imaging device having multiple color-filter aperture | |
| TW201032178A (en) | Method and system for foreground detection using multi-modality fusion graph cut | |
| KR102406804B1 (en) | Method and system for automatically detecting objects in image based on deep learning | |
| CN105245786A (en) | Self-timer method based on intelligent light measurement, self-timer system and photographing terminal | |
| US20160277724A1 (en) | Depth assisted scene recognition for a camera | |
| US20140362281A1 (en) | Exposure control device, imaging device, image display device, and exposure control method | |
| CN104021527B (en) | Rain and snow removal method in image | |
| KR101630286B1 (en) | Apparatus for separating foreground from background and method thereof | |
| CN106550227B (en) | A kind of image saturation method of adjustment and device | |
| WO2016197494A1 (en) | Method and device for adjusting focusing area | |
| CN106023108A (en) | Image defogging algorithm based on boundary constraint and context regularization | |
| CN104506850A (en) | Method and device for judging video occlusion | |
| Anderson et al. | Augmenting depth camera output using photometric stereo. | |
| CN106846395B (en) | Method and system for calculating area of target graph in photo | |
| CN105046670A (en) | Image rain removal method and system | |
| CN110428397A (en) | A kind of angular-point detection method based on event frame | |
| EP2989611A1 (en) | Moving object detection | |
| US20230033956A1 (en) | Estimating depth based on iris size | |
| CN106485265B (en) | Image identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |