CN106370396A - Method and device for detecting light source - Google Patents
Method and device for detecting light source Download PDFInfo
- Publication number
- CN106370396A CN106370396A CN201510443746.4A CN201510443746A CN106370396A CN 106370396 A CN106370396 A CN 106370396A CN 201510443746 A CN201510443746 A CN 201510443746A CN 106370396 A CN106370396 A CN 106370396A
- Authority
- CN
- China
- Prior art keywords
- image
- light source
- characteristic
- information
- spectrum information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 43
- 238000001228 spectrum Methods 0.000 claims abstract description 29
- 238000003384 imaging method Methods 0.000 claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims abstract description 19
- 230000003287 optical effect Effects 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 9
- 238000001914 filtration Methods 0.000 claims abstract description 8
- 238000003709 image segmentation Methods 0.000 claims abstract description 7
- 238000004020 luminiscence type Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 7
- 238000013519 translation Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 4
- 230000011664 signaling Effects 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 230000004907 flux Effects 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 2
- 235000013350 formula milk Nutrition 0.000 description 8
- 238000012360 testing method Methods 0.000 description 4
- 230000007423 decrease Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000023077 detection of light stimulus Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention is applicable to the technical field of optical detection, and provides a method of detecting a light source. The method comprises steps: a to-be-detected light source passes through a small hole imaging lens to form an inverted real image; an image sensor receives the inverted real image, light signals are converted to image digital signals, and a to-be-processed image is acquired; the to-be-processed image is subjected to discrete Fourier transform to acquire characteristic spectrum information; based on the characteristic spectrum information, image reconstruction is carried out; characteristic image segmentation and extraction are carried out on digital signals of the reconstructed image to obtain a characteristic sub image; the characteristic sub image and the to-be-processed image are subjected to filtering operation processing, and a characteristic matrix is outputted; and the characteristic matrix is converted to obtain characteristic information of the to-be-detected light source. The small hole imaging lens is used for imaging, the small hole imaging has the characteristics of small light flux, infinite field depth, and automatic zooming, the overexposure problem can be solved and precise requirements on the image sensor position can be reduced; and through the characteristic spectrum information extraction and image reconstruction, interference can be eliminated, and the anti-interference performance is improved.
Description
Technical field
The invention belongs to technical field of optical detection, particularly to a kind of light source detection method and detection means.
Background technology
The detection of light source is the steps necessary before light source product dispatches from the factory, and mainly includes brightness, color, colour temperature etc.
The detection of feature, current light source detection method mainly adopts artificial visual detection method and automatic testing method.
Artificial visual detection method, is to rely on human eye visually to judge light source performance to after light source energising, this detection method
Rely on the subjective judgment of human eye it is impossible to accurate quantification analyzes light source characteristic, and workload is big, efficiency is low.
Automatic testing method pass through hardware system image pick-up card, optical lens, dark slide, accurate transmission mechanism,
Control device, ccd and computer etc. carry out the on-line checking of light source characteristic.Automatic testing method relies primarily on
To ensure accuracy of detection, there is imaging overexposure optical issue, before optical lens, need dark slide to drop in hardware performance
Low light source intensity, or need precise control time of exposure, structurally and operationally complicated；And, it is anti-interference
Ability, for example, affected larger by external environment light, and light source and relative position of lens occur slightly
Deviation then cannot focus, cause image blur, rotation etc., lead to not analysis output correct result.
Content of the invention
It is an object of the invention to provide a kind of light source detection method is it is intended to solve traditional automatic light source detection side
Overexposure optical issue that method exists simultaneously improves the capacity of resisting disturbance of detecting system.
The present invention is achieved in that a kind of light source detection method, comprises the steps:
The light that light source to be detected sends is made to form inverted real image by pinhole imaging system camera lens；
Described inverted real image is received by imageing sensor, and the optical signalling of described inverted real image is converted to
Image digital signal, obtains pending image；
Described pending image is carried out with discrete Fourier transform, obtains characteristic frequency spectrum information；
Image reconstruction is carried out based on described characteristic frequency spectrum information, obtains the reconstructed image number eliminating interference information
Word signal；
Described reconstructed image digital signal is carried out with characteristic image segmentation extract, obtain comprising light source spy to be detected
The feature sub-image of property information；
Described feature sub-image and described pending image are done filtering operation process, output characteristics eigenmatrix；
Line translation is entered to described property feature matrix, obtains the characteristic information of light source to be detected.
Another object of the present invention is to providing a kind of light source detection device, comprising:
Pinhole imaging system camera lens, is used for treating and detects that light source is imaged, obtain inverted real image；
Imageing sensor, is arranged at the image space of described pinhole imaging system camera lens, for receiving described inverted real image simultaneously
Convert optical signals into image digital signal, to obtain pending image；
Image pre-processing module, is connected with the outfan of described image sensor, for described pending figure
As carrying out discrete Fourier transform, obtain characteristic frequency spectrum information；
Image reconstruction module, is connected with the outfan of described image pretreatment module, for based on described feature
Spectrum information carries out image reconstruction, obtains the reconstructed image digital signal eliminating interference information；
Subimage extraction module, is connected with the outfan of described image reconstructed module, for described reconstruct image
Extract as digital signal carries out characteristic image segmentation, obtain comprising the feature subgraph of light source characteristic information to be detected
Picture；
Data analysis module, is connected with the outfan of described subimage extraction module and described image sensor,
Process for described feature sub-image and described pending image are done filtering operation, output characteristics eigenmatrix,
And line translation is entered to described property feature matrix, obtain the characteristic information of light source to be detected.
The present invention using pinhole imaging system camera lens treat detection light source be imaged, pinhole imaging system have luminous flux little,
The unlimited depth of field, the feature of autozoom, are easy to limit the light entering detecting system using the little feature of luminous flux
Energy, effectively solving overexposure optical issue；The unlimited depth of field, autozoom make the position of imageing sensor need not
Strict restriction, structure design is more flexible, and decreases the detection error that position deviation is brought；The present embodiment
The interference such as shake, inclination is eliminated by characteristic frequency spectrum information retrieval and image reconstruction, improves this detection side
The anti-interference of method.
Brief description
Fig. 1 is the flow chart of light source detection method provided in an embodiment of the present invention；
Fig. 2 is the structural representation of light source detection device provided in an embodiment of the present invention.
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, below in conjunction with accompanying drawing and reality
Apply example, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only
Only in order to explain the present invention, it is not intended to limit the present invention.
Below in conjunction with specific embodiment, implementing of the present invention is described in detail:
Refer to Fig. 1, the embodiment of the present invention provides a kind of light source detection method, comprises the steps:
In step s101, make the light that light source to be detected sends pass through pinhole imaging system camera lens and form handstand in fact
Picture；
In step s102, described inverted real image, and the optics by inverted real image are received by imageing sensor
Signal is converted to image digital signal, obtains pending image；
In step s103, pending image is carried out with discrete Fourier transform, obtain characteristic frequency spectrum information；
In step s104, feature based spectrum information carries out image reconstruction, obtains and eliminates interference information
Reconstructed image digital signal；
In step s105, reconstructed image digital signal is carried out with characteristic image segmentation and extracts, obtain comprising to treat
The feature sub-image of detection light source characteristic information；
In step s106, feature sub-image and pending image are done filtering operation and processes, output characteristics is special
Levy matrix；
In step s107, line translation is entered to property feature matrix, obtain the characteristic information of light source to be detected.
The embodiment of the present invention is treated detection light source using pinhole imaging system camera lens and is imaged, and pinhole imaging system has light
Flux is little, the unlimited depth of field, the feature of autozoom, is easy to limit enter using the little feature of luminous flux and detects
The light energy of system, effectively solving overexposure optical issue；The unlimited depth of field, autozoom make imageing sensor
Position need not strictly limit, and structure design is more flexible, and decreases the detection error that site error is brought；
The present embodiment eliminates the interference such as shake, inclination by characteristic frequency spectrum information retrieval and image reconstruction, improves
The anti-interference of this detection method.
In the present embodiment, light source to be detected generally includes multiple luminescence units, and the led of such as array sends out
Optic panel, there is led display floater of dot structure etc., each luminescence unit can pass through pinhole imaging system
Camera lens forms a picture point, and formed inverted real image contains the picture point of whole luminescence units.
In above-mentioned steps s102, imageing sensor receives the picture of light source, and optical signalling is changed into image
Digital signal, this image processing signal contains the two-dimensional discrete data matrix of the gray value representing each picture point
F (x, y), this data matrix characterizes the state of each picture point, such as brightness size；
In above-mentioned steps s103, discrete Fourier transform is carried out to this two-dimensional discrete data matrix f (x, y),
Obtain characteristic frequency spectrum information f (u, v), its transform is:
In formula, x=0,1 ..., m-1；Y=0,1 ..., n-1, u=0,1 ..., m-1；V=0,1 ..., n-1, m, n
For positive integer.
After obtaining characteristic frequency spectrum information, carry out above-mentioned steps s104, select specific u and v value series to enter
Row image reconstruction.Reconstructed image f2The transformation for mula of (x, y) is:
In formula, x=0,1 ..., m-1；Y=0,1 ..., n-1, u=0,1 ..., m-1；V=0,1 ..., n-1, m, n
For positive integer.
Fourier transformation and image reconstruction are carried out based on above-mentioned formula, the interference in former pending image can be believed
Breath removes, and obtains reconstructed image digital signal.
Further, the reconstructed image removing interference is carried out with the extraction of feature sub-image, this feature subimage
Contain the property feature to be detected of light source to be detected.Pass through filtering etc. again to process, obtain property feature matrix,
The characteristic information that line translation obtains light source to be detected is entered to property feature matrix.
Above-mentioned light source detection method is based primarily upon following device and implements, the present invention further provides a kind of inspection of light source
Survey device, such as Fig. 2, this light source detection device includes:
Pinhole imaging system camera lens 1, is used for treating and detects that light source 2 is imaged, obtain inverted real image；
Imageing sensor 3, is arranged at the image space of pinhole imaging system camera lens 1, for receiving inverted real image and by light
Learn signal and be converted to image digital signal, to obtain pending image；
Image pre-processing module 4, is connected with the outfan of imageing sensor 3, for entering to pending image
Row discrete Fourier transform, obtains characteristic frequency spectrum information；
Image reconstruction module 5, is connected with the outfan of image pre-processing module 4, for feature based frequency spectrum
Information carries out image reconstruction, obtains the reconstructed image digital signal eliminating interference information；
Subimage extraction module 6, is connected with the outfan of image reconstruction module 5, for reconstructed image number
Word signal carries out characteristic image segmentation and extracts, and obtains comprising the feature sub-image of light source characteristic information to be detected；
Data analysis module 7, is connected with the outfan of subimage extraction module 6 and imageing sensor 3, uses
Process in feature sub-image and pending image are done filtering operation, output characteristics eigenmatrix, and to characteristic
Eigenmatrix enters line translation, obtains the characteristic information of light source to be detected.
Further, light source 2 to be detected generally includes multiple luminescence units, such as led array light source, led
Display floater etc..Each luminescence unit forms a picture point by pinhole imaging system camera lens, and inverted real image comprises often
The picture point of individual luminescence unit, this inverted real image has and the light source identical regularity of distribution.For array distribution
Luminescence unit, pending image comprises two-dimensional discrete data matrix f (x, y) representing the gray value of picture point.
Further, this light source detection device can also include the output mould being connected with data analysis module 7
Block 8, for exporting testing result.
Same as above, image pre-processing module 4 carries out discrete Fourier transform to pending image, obtains special
Levy the step of spectrum information particularly as follows:
Two-dimensional discrete data matrix f (x, y) is carried out with Fourier transformation, obtains characteristic frequency spectrum information f (u, v),
Its transform is:
In formula, x=0,1 ..., m-1；Y=0,1 ..., n-1, u=0,1 ..., m-1；V=0,1 ..., n-1, m, n
For positive integer.
Further, image reconstruction module 5 feature based spectrum information carries out image reconstruction, and acquisition eliminates
The step of the reconstructed image digital signal of interference information particularly as follows:
Select specific u and v value series, reconstructed image f2(x, y), tectonic transition formula is:
In formula, in formula, x=0,1 ..., m-1；Y=0,1 ..., n-1, u=0,1 ..., m-1；V=0,1 ..., n-1,
M, n are positive integer.
Light source detection device provided in an embodiment of the present invention is treated detection light source using pinhole imaging system camera lens and is become
Picture, pinhole imaging system has the characteristics that luminous flux is little, the unlimited depth of field, autozoom, using the little spy of luminous flux
Levy and be easy to limit the light energy entering detecting system, effectively solving overexposure optical issue；The unlimited depth of field, automatically change
Jiao makes the position of imageing sensor need not strictly limit, and structure design is more flexible, and it is inclined to decrease position
The detection error brought；Characteristic frequency spectrum information is extracted by image pre-processing module, by image reconstruction module
Carry out image reconstruction, eliminate the interference such as shake, inclination, improve the anti-interference of this detection method, and
And do not increase the complexity of device and easily operated.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all at this
Any modification, equivalent and improvement made within bright spirit and principle etc., should be included in the present invention
Protection domain within.
Claims (10)
1. a kind of light source detection method is it is characterised in that comprise the steps:
The light that light source to be detected sends is made to form inverted real image by pinhole imaging system camera lens；
Described inverted real image is received by imageing sensor, and the optical signalling of described inverted real image is converted to
Image digital signal, obtains pending image；
Described pending image is carried out with discrete Fourier transform, obtains characteristic frequency spectrum information；
Image reconstruction is carried out based on described characteristic frequency spectrum information, obtains the reconstructed image number eliminating interference information
Word signal；
Described reconstructed image digital signal is carried out with characteristic image segmentation extract, obtain comprising light source spy to be detected
The feature sub-image of property information；
Described feature sub-image and described pending image are done filtering operation process, output characteristics eigenmatrix；
Line translation is entered to described property feature matrix, obtains the characteristic information of light source to be detected.
2. light source detection method as claimed in claim 1 is it is characterised in that described light source to be detected includes
Multiple luminescence units, each described luminescence unit by described pinhole imaging system camera lens formed a picture point, described fall
Vertical real image comprises the picture point of the plurality of luminescence unit.
3. light source detection method as claimed in claim 2 is it is characterised in that described pending image comprises
Represent two-dimensional discrete data matrix f (x, y) of described picture point gray value；
Described carries out discrete Fourier transform to described pending image, the step obtaining characteristic frequency spectrum information
Particularly as follows:
Described two-dimensional discrete data matrix f (x, y) is carried out with Fourier transformation, obtains characteristic frequency spectrum letter
Breath f (u, v), its transform is:
In formula, x=0,1 ..., m-1；Y=0,1 ..., n-1, u=0,1 ..., m-1；V=0,1 ..., n-1, m, n
For positive integer.
4. light source detection method as claimed in claim 3 it is characterised in that described based on described feature
Spectrum information carries out image reconstruction, and the step obtaining the reconstructed image digital signal eliminating interference information is concrete
For:
Select specific u and v value series, reconstructed image f2(x, y), tectonic transition formula is:
In formula, in formula, x=0,1 ..., m-1；Y=0,1 ..., n-1, u=0,1 ..., m-1；V=0,1 ..., n-1,
M, n are positive integer.
5. a kind of light source detection device is it is characterised in that include:
Pinhole imaging system camera lens, is used for treating and detects that light source is imaged, obtain inverted real image；
Imageing sensor, is arranged at the image space of described pinhole imaging system camera lens, for receiving described inverted real image simultaneously
Convert optical signals into image digital signal, to obtain pending image；
Image pre-processing module, is connected with the outfan of described image sensor, for described pending figure
As carrying out discrete Fourier transform, obtain characteristic frequency spectrum information；
Image reconstruction module, is connected with the outfan of described image pretreatment module, for based on described feature
Spectrum information carries out image reconstruction, obtains the reconstructed image digital signal eliminating interference information；
Subimage extraction module, is connected with the outfan of described image reconstructed module, for described reconstruct image
Extract as digital signal carries out characteristic image segmentation, obtain comprising the feature subgraph of light source characteristic information to be detected
Picture；
Data analysis module, is connected with the outfan of described subimage extraction module and described image sensor,
Process for described feature sub-image and described pending image are done filtering operation, output characteristics eigenmatrix,
And line translation is entered to described property feature matrix, obtain the characteristic information of light source to be detected.
6. light source detection device as claimed in claim 5 is it is characterised in that described light source to be detected includes
Multiple luminescence units, each described luminescence unit by described pinhole imaging system camera lens formed a picture point, described fall
Vertical real image comprises the picture point of the plurality of luminescence unit.
7. light source detection device as claimed in claim 6 is it is characterised in that the plurality of luminescence unit becomes
Array is distributed, and described pending image comprises the two-dimensional discrete data matrix representing the gray value of described picture point
f(x,y).
8. light source detection device as claimed in claim 7 is it is characterised in that described image pretreatment module
Described pending image is carried out with discrete Fourier transform, obtain the step of characteristic frequency spectrum information particularly as follows:
Described two-dimensional discrete data matrix f (x, y) is carried out with Fourier transformation, obtains characteristic frequency spectrum letter
Breath f (u, v), its transform is:
In formula, x=0,1 ..., m-1；Y=0,1 ..., n-1, u=0,1 ..., m-1；V=0,1 ..., n-1, m, n
For positive integer.
9. light source detection device as claimed in claim 8 is it is characterised in that described image reconstructed module base
Carry out image reconstruction in described characteristic frequency spectrum information, obtain the reconstructed image digital signal eliminating interference information
Step particularly as follows:
Select specific u and v value series, reconstructed image f2(x, y), tectonic transition formula is:
In formula, in formula, x=0,1 ..., m-1；Y=0,1 ..., n-1, u=0,1 ..., m-1；V=0,1 ..., n-1,
M, n are positive integer.
10. light source detection device as claimed in claim 5 is it is characterised in that also include and described data
The output module that analysis module is connected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510443746.4A CN106370396B (en) | 2015-07-24 | 2015-07-24 | A kind of light source detection method and detection device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510443746.4A CN106370396B (en) | 2015-07-24 | 2015-07-24 | A kind of light source detection method and detection device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106370396A true CN106370396A (en) | 2017-02-01 |
| CN106370396B CN106370396B (en) | 2019-02-15 |
Family
ID=57880854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510443746.4A Active CN106370396B (en) | 2015-07-24 | 2015-07-24 | A kind of light source detection method and detection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106370396B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117147104A (en) * | 2023-08-10 | 2023-12-01 | 深圳市海目芯微电子装备科技有限公司 | Measurement device for parallel half angle of light source and method for measuring parallel half angle of light source |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS593238A (en) * | 1982-06-30 | 1984-01-09 | Nippon Kogaku Kk <Nikon> | Automatic lens meter |
| CN102681365A (en) * | 2012-05-18 | 2012-09-19 | 中国科学院光电技术研究所 | Projection objective wave aberration detection device and method |
| CN102928201A (en) * | 2012-10-24 | 2013-02-13 | 北京控制工程研究所 | Target simulating system of dynamic selenographic imaging sensor |
| CN203275067U (en) * | 2013-04-22 | 2013-11-06 | 志圣科技（广州）有限公司 | Simple optical angle recorder |
| CN203298878U (en) * | 2013-05-03 | 2013-11-20 | 内蒙古工业大学 | Fringe contrast and carrier frequency adjustable loop point diffraction interference wavefront sensor |
| CN203965128U (en) * | 2014-06-12 | 2014-11-26 | 中国科学院上海技术物理研究所 | Large visual field camera nonlinear distortion means for correcting |
-
2015
- 2015-07-24 CN CN201510443746.4A patent/CN106370396B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS593238A (en) * | 1982-06-30 | 1984-01-09 | Nippon Kogaku Kk <Nikon> | Automatic lens meter |
| CN102681365A (en) * | 2012-05-18 | 2012-09-19 | 中国科学院光电技术研究所 | Projection objective wave aberration detection device and method |
| CN102928201A (en) * | 2012-10-24 | 2013-02-13 | 北京控制工程研究所 | Target simulating system of dynamic selenographic imaging sensor |
| CN203275067U (en) * | 2013-04-22 | 2013-11-06 | 志圣科技（广州）有限公司 | Simple optical angle recorder |
| CN203298878U (en) * | 2013-05-03 | 2013-11-20 | 内蒙古工业大学 | Fringe contrast and carrier frequency adjustable loop point diffraction interference wavefront sensor |
| CN203965128U (en) * | 2014-06-12 | 2014-11-26 | 中国科学院上海技术物理研究所 | Large visual field camera nonlinear distortion means for correcting |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117147104A (en) * | 2023-08-10 | 2023-12-01 | 深圳市海目芯微电子装备科技有限公司 | Measurement device for parallel half angle of light source and method for measuring parallel half angle of light source |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106370396B (en) | 2019-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Davis et al. | Real-time observation of taxa-specific plankton distributions: an optical sampling method | |
| CN107229930A (en) | A kind of pointer instrument numerical value intelligent identification Method and device | |
| CN103344583B (en) | A kind of praseodymium-neodymium (Pr/Nd) component concentration detection system based on machine vision and method | |
| CN102353519A (en) | Resolving power measuring device and resolving power evaluation method for three-generation dim light image intensifier | |
| CN109635806A (en) | Ammeter technique for partitioning based on residual error network | |
| CN110958450B (en) | Imaging system space testing device, contrast and frequency testing method | |
| CN111339902A (en) | Liquid crystal display number identification method and device of digital display instrument | |
| Ravikumar et al. | Digital image processing-a quick review | |
| CN109711253A (en) | Numerical Recognition Method of Electric Meter Based on Convolutional Neural Network and Recurrent Neural Network | |
| He et al. | Wildfire detection for transmission line based on improved lightweight YOLO | |
| Duan | LED: A large-scale real-world paired dataset for event camera denoising | |
| CN117994573A (en) | Infrared dim target detection method based on superpixel and deformable convolution | |
| CN109840905A (en) | Power equipment rusty stain detection method and system | |
| CN102298710A (en) | Cat eye effect target identification method based on compressive sensing theory | |
| CN106370396A (en) | Method and device for detecting light source | |
| Ghosh et al. | A low cost data acquisition system from digital display instruments employing image processing technique | |
| CN114037771B (en) | A few-photon imaging method based on deep learning | |
| CN106934339A (en) | A kind of target following, the extracting method of tracking target distinguishing feature and device | |
| Bindhu et al. | Analytical study on digital image processing applications | |
| CN115937492A (en) | An Infrared Image Recognition Method for Substation Equipment Based on Feature Recognition | |
| Wang et al. | Objective evaluation of low-light-level image intensifier resolution based on a model of image restoration and an applied model of image filtering | |
| CN114140743A (en) | Method, device and equipment for identifying black screen image and storage medium | |
| CN113781513A (en) | Method and system for detecting leakage of water supply pipeline of power plant | |
| CN114140681A (en) | A method and device for detecting distant faint star targets | |
| CN109376713A (en) | An embedded face detection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |