CN112945897B - Continuous terahertz image non-uniformity correction method - Google Patents

Continuous terahertz image non-uniformity correction method Download PDF

Info

Publication number
CN112945897B
CN112945897B CN202110102378.2A CN202110102378A CN112945897B CN 112945897 B CN112945897 B CN 112945897B CN 202110102378 A CN202110102378 A CN 202110102378A CN 112945897 B CN112945897 B CN 112945897B
Authority
CN
China
Prior art keywords
image
terahertz
intensity
continuous
lstm network
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.)
Active
Application number
CN202110102378.2A
Other languages
Chinese (zh)
Other versions
CN112945897A (en
Inventor
袁飞
周松斌
程韬波
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.)
Institute of Intelligent Manufacturing of Guangdong Academy of Sciences
Original Assignee
Institute of Intelligent Manufacturing of Guangdong Academy of Sciences
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 Institute of Intelligent Manufacturing of Guangdong Academy of Sciences filed Critical Institute of Intelligent Manufacturing of Guangdong Academy of Sciences
Priority to CN202110102378.2A priority Critical patent/CN112945897B/en
Publication of CN112945897A publication Critical patent/CN112945897A/en
Application granted granted Critical
Publication of CN112945897B publication Critical patent/CN112945897B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/3581—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N2021/1765—Method using an image detector and processing of image signal
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2201/00—Features of devices classified in G01N21/00
    • G01N2201/12—Circuits of general importance; Signal processing
    • G01N2201/127—Calibration; base line adjustment; drift compensation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
    • Y02P70/50—Manufacturing or production processes characterised by the final manufactured product

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Toxicology (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a method for correcting non-uniformity of a continuous terahertz image, which relates to the technical field of terahertz imaging, and is characterized in that terahertz intensity signals generated by pixels of a continuous terahertz detector are taken as time sequence signals, the prediction capability of an LSTM network on the time sequence signals is utilized, the next terahertz intensity signals are predicted according to part of terahertz intensity signals generated by pixel detection, prediction data are non-uniform background data corresponding to the current terahertz image, and finally the prediction data are utilized to carry out rotation translation type non-uniformity correction on the current image. According to the invention, additional hardware equipment is not required to be added, the normal work of the detector is not required to be interrupted, and a large amount of complex statistical calculation and related information calculation analysis are not required to be repeated; the method utilizes the prediction function of the LSTM network on the time sequence signal, overcomes the influence caused by environmental fluctuation, has strong generalization capability and improves the signal-to-noise ratio of the continuous terahertz image.

Description

Continuous terahertz image non-uniformity correction method
Technical Field
The invention relates to the technical field of terahertz imaging, in particular to a continuous terahertz image non-uniformity correction method.
Background
The terahertz imaging technology and the application thereof are one of the important directions of terahertz technology research, and have wide application prospects in the aspects of nondestructive testing, security inspection, food and drug safety detection, medical treatment, biological imaging and the like. The imaging quality of the terahertz wave imaging system depends on the development of a terahertz source, a terahertz detector and an imaging technology, and although partial improvement of image quality is obtained by improving hardware of the terahertz wave imaging system at present, the terahertz wave imaging system is limited by factors such as a terahertz detector manufacturing process, an imaging light path, a working environment and the like, a series of problems such as non-uniform responsivity among different pixels and even blind pixels occur, so that non-uniformity correction processing needs to be carried out on terahertz images.
At present, terahertz image non-uniformity correction methods are mainly based on a calibration method and a scene-based method. The calibration-based method comprises one-point calibration, two-point calibration and multi-point calibration, however, the three methods need to periodically interrupt the work of the detector and irradiate with a terahertz source with specific power so as to perform calibration and correction. The scene-based method estimates the correction coefficient of the detector by using the acquired image, such as a time domain high-pass filter method, a neural network correction method and the like. The scene-based method utilizes imaging information in multiple scenes, can effectively estimate correction parameters in actual scenes, does not need to be calibrated again, but fixed mode noise remains when the scenes change, and imaging quality is affected.
In order to overcome the technical problems, a new correction method is urgently needed to be provided, and the non-uniformity correction processing is performed on the non-uniformity problem of the continuous terahertz detector, so that the terahertz imaging effect is better realized.
Disclosure of Invention
In view of the above, it is necessary to provide a method for correcting non-uniformity of a continuous terahertz image, in which terahertz intensity signals generated by pixels of a continuous terahertz detector are regarded as time sequence signals, the prediction capability of an LSTM network on the time sequence signals is utilized, next terahertz intensity signals are predicted according to part of terahertz intensity signals generated by the pixels, prediction data, that is, non-uniformity background data corresponding to a current terahertz image, is finally utilized to perform rotational translation type non-uniformity correction on the current image.
In order to realize the purpose, the invention is realized according to the following technical scheme:
a continuous terahertz image non-uniformity correction method comprises the following steps:
step S1: acquiring a non-uniform terahertz intensity image under the condition of no detection object by using a continuous terahertz imaging system, and constructing a background image sample set y; collecting terahertz intensity images when a terahertz source is turned off to form an image sample set z, wherein the number of the sample set z is M; the sizes of the images in the sets y and z are both mxn, wherein m is the number of imaging units of the continuous terahertz detector, namely the number of rows of a single image, and n is the number of columns of the single image;
step S2: constructing an LSTM network model for each imaging unit of the continuous terahertz detector, wherein m LSTM network models are constructed;
and step S3: using background sample image to set y image ith row n before 1 The intensity data is input, n-n after the ith line 1 Training the ith LSTM network model with the intensity data as expected values; repeating the steps until the LSTM network model training corresponding to m pixels of the continuous terahertz detector is completed;
and step S4: taking the image x to be non-uniformity corrected with the size of m multiplied by n, and taking the n before the ith row 1 Using the intensity data as the input of the ith LSTM network model after training to predict and generate n-n 1 (ii) intensity data;
step S5: repeating step S4 for each line of image x to generate mx (n-n) 1 ) Predicting the intensity image, and dividing the image by m × n 1 Image and prediction generated mx (n-n) 1 ) Merging of predicted pictures into an mxn sized picture
Figure GDA0003782636840000021
Step S6: for images
Figure GDA0003782636840000022
The ith row carries out the average value calculation to obtain the average value->
Figure GDA0003782636840000023
Step S7: calculating the bias parameter of the ith imaging unit of the terahertz detector for the image sample set z
Figure GDA0003782636840000024
The calculation formula is as follows:
Figure GDA0003782636840000025
wherein z is kij The ith row and the jth column of the kth image are taken as intensity values;
step S8: for each pixel x of the image x ij And carrying out non-uniformity correction, wherein the correction formula is as follows:
Figure GDA0003782636840000031
wherein,
Figure GDA0003782636840000032
is a pixel value x ij The corrected value, corrected for each pixel, constitutes a corrected image->
Figure GDA0003782636840000033
Compared with the prior art, the invention has the advantages and positive effects that:
compared with the non-uniformity correction method based on calibration, the method provided by the invention does not need to add extra hardware equipment and interrupt normal work; compared with a scene-based non-uniformity correction method, a large amount of complex statistical calculation and related information calculation analysis do not need to be repeated.
The method provided by the invention utilizes the prediction function of the LSTM network on the time sequence signal to realize the prediction of the following non-uniform background based on the pixels of the image part to be corrected. The method can correspondingly generate the non-uniform background corresponding to the current image, overcomes the influence caused by environmental fluctuation, and has strong generalization capability, and the non-uniform correction method improves the signal-to-noise ratio of the continuous terahertz image, provides a reliable image analysis source for the application of the continuous terahertz image, and enlarges the application range of the terahertz imaging system.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a continuous terahertz image non-uniformity correction method according to the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. It should be noted that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and all other embodiments obtained by those skilled in the art without any inventive work based on the embodiments of the present invention belong to the protection scope of the present invention.
Example 1
As shown in FIG. 1, the invention provides a dynamic non-uniformity correction method based on a long-short-term memory neural (LSTM) network, aiming at the non-uniformity problem of a continuous terahertz detector. According to the method, terahertz intensity signals generated by pixels of a continuous terahertz detector are regarded as time sequence signals, the prediction capability of an LSTM network on the time sequence signals is utilized, the next terahertz intensity signals are predicted according to part of terahertz intensity signals generated by pixel detection, prediction data, namely non-uniform background data corresponding to a current terahertz image, are used for performing rotation translation type non-uniform correction on the current image.
Firstly, acquiring a non-uniform terahertz intensity image under the condition of no detection object by using a continuous terahertz imaging system, and constructing an image sample set y; and (3) forming an image sample set z by the terahertz intensity image when the terahertz source is turned off, wherein the sizes of the images in the set y and the set z are both mxn. And then constructing a long-term and short-term memory neural network model for each imaging unit of the terahertz detector, and training the model by using the image set y. In the training process, the first n1 intensity data of the ith row of a certain intensity image in y are taken as the input of the ith LSTM network, and the last n-n1 intensity data are taken as the expected output. Inputting the first n1 columns of data of the intensity image x to be corrected to the trained m LSTM networks, predicting and generating n-n1 columns of terahertz intensity values, and combining the predicted and generated intensity data and the first n1 columns of intensity data into an m multiplied by n image
Figure GDA0003782636840000041
The image is a non-uniform background image corresponding to the image x to be corrected. Recalculated the image pick>
Figure GDA0003782636840000042
Mean of intensity data in ith row>
Figure GDA0003782636840000043
Figure GDA0003782636840000044
As a gain correction factor for the imaging unit. Then, carrying out mean calculation on the intensity image in the image sample set x according to lines, and carrying out mean result->
Figure GDA0003782636840000045
As a bias correction coefficient for the ith imaging unit. Finally, a correction formula is utilized to treat the pixel x in the corrected intensity image x ij And (6) carrying out correction.
Specifically, the continuous terahertz image non-uniformity correction method provided by the invention comprises the following steps:
step S1: acquiring a non-uniform terahertz intensity image under the condition of no detection object by using a continuous terahertz imaging system, and constructing a background image sample set y; collecting terahertz intensity images when a terahertz source is turned off to form an image sample set z, wherein the number of the sample set z is M; the sizes of the images in the sets y and z are both mxn, wherein m is the number of imaging units of the continuous terahertz detector, namely the number of rows of a single image, and n is the number of columns of the single image;
step S2: constructing an LSTM network model for each imaging unit of the continuous terahertz detector, wherein m LSTM network models are constructed;
and step S3: using background sample image to set y image ith row n before 1 The intensity data is input, n-n after the ith line 1 Training the ith LSTM network model with the intensity data as expected values; repeating the steps until the LSTM network model training corresponding to m pixels of the continuous terahertz detector is completed;
and step S4: taking the image x to be non-uniformity corrected with the size of m multiplied by n, and taking the n before the ith row 1 Using the intensity data as the input of the i-th LSTM network model after training to predict and generate n-n 1 (ii) intensity data;
step S5: repeating step S4 for each line of image x to generate mx (n-n) 1 ) Predicting the intensity image, and dividing the image by m × n 1 Image and prediction generated mx (n-n) 1 ) Merging of predicted images into an m × n sized image
Figure GDA0003782636840000051
Step S6: for images
Figure GDA0003782636840000052
The ith row carries out the average value calculation to obtain the average value->
Figure GDA0003782636840000053
Step S7: calculating the bias parameter of the ith imaging unit of the terahertz detector for the image sample set z
Figure GDA0003782636840000054
The calculation formula is as follows:
Figure GDA0003782636840000055
wherein z is kij The ith row and the jth column of the kth image are taken as intensity values;
step S8: for each pixel x of the image x ij And carrying out non-uniformity correction, wherein the correction formula is as follows:
Figure GDA0003782636840000056
wherein,
Figure GDA0003782636840000057
is a pixel value x ij The corrected value, corrected for each pixel, constitutes a corrected image->
Figure GDA0003782636840000058
Compared with the prior art, the method provided by the invention does not need to add extra hardware equipment and interrupt normal work compared with the calibration-based non-uniformity correction method; compared with a scene-based nonuniformity correction method, a large amount of complex statistical calculation and related information calculation analysis are not required to be repeated.
The method provided by the invention utilizes the prediction function of the LSTM network on the time sequence signal to realize the prediction of the following non-uniform background based on the pixels of the image part to be corrected. The method can correspondingly generate the non-uniform background corresponding to the current image, overcomes the influence caused by environmental fluctuation, and has strong generalization capability, the non-uniform correction method improves the signal-to-noise ratio of the continuous terahertz image, provides a reliable image analysis source for the application of the continuous terahertz image, and enlarges the application range of the terahertz imaging system.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that various changes and modifications can be made by those skilled in the art without departing from the spirit of the invention, and these changes and modifications are all within the scope of the invention. Therefore, the protection scope of the present invention should be subject to the appended claims.

Claims (1)

1. A continuous terahertz image non-uniformity correction method is characterized by comprising the following steps:
step S1: acquiring a non-uniform terahertz intensity image under the condition of no detection object by using a continuous terahertz imaging system, and constructing a background image sample set y; collecting terahertz intensity images when a terahertz source is turned off to form an image sample set z, wherein the number of the sample set z is M; the sizes of the images in the sets y and z are both mxn, wherein m is the number of imaging units of the continuous terahertz detector, namely the number of rows of a single image, and n is the number of columns of the single image;
step S2: constructing an LSTM network model for each imaging unit of the continuous terahertz detector, wherein m LSTM network models are constructed;
and step S3: using background sample image to set y image ith row n before 1 The intensity data is input, n-n after the ith line 1 Training the ith LSTM network model with the intensity data as expected values; repeating the steps until the LSTM network model training corresponding to the m imaging units of the continuous terahertz detector is completed;
and step S4: taking the image x to be non-uniformity corrected with the size of m multiplied by n, and taking the n before the ith row 1 Using the intensity data as the input of the ith LSTM network model after training to predict and generate n-n 1 (ii) intensity data;
step S5: repeating step S4 for each line of image x to generate mx (n-n) 1 ) Predicting the intensity image, and moving the image x front by m × n 1 Image and prediction generated mx (n-n) 1 ) Merging of predicted pictures into an mxn sized picture
Figure FDA0003791831340000011
Step S6: for images
Figure FDA0003791831340000012
The ith row carries out the average value calculation to obtain the average value->
Figure FDA0003791831340000013
Step S7: calculating the bias parameter of the ith imaging unit of the terahertz detector for the image sample set z
Figure FDA0003791831340000014
The calculation formula is as follows:
Figure FDA0003791831340000015
wherein z is kij The ith row and the jth column of the kth image are used as the intensity value;
step S8: for each pixel x of the image x ij And carrying out non-uniformity correction, wherein the correction formula is as follows:
Figure FDA0003791831340000016
wherein,
Figure FDA0003791831340000017
is a pixel value x ij The corrected value, corrected for each pixel, constitutes a corrected image->
Figure FDA0003791831340000018
CN202110102378.2A 2021-01-26 2021-01-26 Continuous terahertz image non-uniformity correction method Active CN112945897B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110102378.2A CN112945897B (en) 2021-01-26 2021-01-26 Continuous terahertz image non-uniformity correction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110102378.2A CN112945897B (en) 2021-01-26 2021-01-26 Continuous terahertz image non-uniformity correction method

Publications (2)

Publication Number Publication Date
CN112945897A CN112945897A (en) 2021-06-11
CN112945897B true CN112945897B (en) 2023-04-07

Family

ID=76236828

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110102378.2A Active CN112945897B (en) 2021-01-26 2021-01-26 Continuous terahertz image non-uniformity correction method

Country Status (1)

Country Link
CN (1) CN112945897B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113804758B (en) * 2021-08-10 2024-03-08 广东省科学院智能制造研究所 Magnetic pulse knocker with energy feedback function

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101666682A (en) * 2009-08-06 2010-03-10 重庆邮电大学 Neural network nonuniformity correction method based on scene statistics
CN106644078A (en) * 2016-12-30 2017-05-10 电子科技大学 Terahertz image non-uniformity correction method
CN109632693A (en) * 2018-12-10 2019-04-16 昆明理工大学 A kind of tera-hertz spectra recognition methods based on BLSTM-RNN
CN109709624A (en) * 2019-02-27 2019-05-03 中国科学院上海技术物理研究所 A method of determining that infrared detector dodges member based on LSTM model
WO2019183843A1 (en) * 2018-03-28 2019-10-03 西安电子科技大学 Interframe registration and adaptive step size-based non-uniformity correction method for infrared image
WO2019209194A1 (en) * 2018-04-27 2019-10-31 Aselsan Elektroni̇k Sanayi̇ Ve Ti̇caret Anoni̇m Şi̇rketi̇ A method for confident registration-based non-uniformity correction using spatio-temporal update mask

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
IL173418A (en) * 2006-01-29 2013-10-31 Rafael Advanced Defense Sys Non-uniformity correction of images generated by focal plane arrays of photodetectors
US10929955B2 (en) * 2017-06-05 2021-02-23 Adasky, Ltd. Scene-based nonuniformity correction using a convolutional recurrent neural network

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101666682A (en) * 2009-08-06 2010-03-10 重庆邮电大学 Neural network nonuniformity correction method based on scene statistics
CN106644078A (en) * 2016-12-30 2017-05-10 电子科技大学 Terahertz image non-uniformity correction method
WO2019183843A1 (en) * 2018-03-28 2019-10-03 西安电子科技大学 Interframe registration and adaptive step size-based non-uniformity correction method for infrared image
WO2019209194A1 (en) * 2018-04-27 2019-10-31 Aselsan Elektroni̇k Sanayi̇ Ve Ti̇caret Anoni̇m Şi̇rketi̇ A method for confident registration-based non-uniformity correction using spatio-temporal update mask
CN109632693A (en) * 2018-12-10 2019-04-16 昆明理工大学 A kind of tera-hertz spectra recognition methods based on BLSTM-RNN
CN109709624A (en) * 2019-02-27 2019-05-03 中国科学院上海技术物理研究所 A method of determining that infrared detector dodges member based on LSTM model

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
A novel infrared focal plane non-uniformity correction method based on co-occurrence fliter and adaptive learning rate;Li Lingxiao et al;《IEEE Access》;20190327;第7卷;第40941-40950页 *
Non-uniformity correction algorithm for THz array detectors in high-resolution imaging applications;Rungroj Jintamethasawat et al;《International Journal of Infrared and Millimeter Waves》;20200619;第41卷;第940-956页 *
基于神经网络法的焦平面器件非均匀性校正技术研究;曹治国 等;《红外与激光工程》;20000229;第29卷(第1期);第65-68页 *
太赫兹成像技术与图像算法的研究;郑杰;《中国优秀硕士学位论文全文数据库 基础科学辑》;20180315(第3期);第A005-84页 *
太赫兹成像系统的性能评价模型和图像处理方法研究;田莉;《中国博士学位论文全文数据库 信息科技辑》;20190915(第9期);第I138-41页 *

Also Published As

Publication number Publication date
CN112945897A (en) 2021-06-11

Similar Documents

Publication Publication Date Title
Ma et al. Perceptual quality assessment for multi-exposure image fusion
CN111127435B (en) No-reference image quality evaluation method based on double-current convolution neural network
CN113011567B (en) Training method and device of convolutional neural network model
CN114972085B (en) Fine granularity noise estimation method and system based on contrast learning
CN109377457B (en) Pill coating image processing method and device, computer equipment and storage medium
CN106644078A (en) Terahertz image non-uniformity correction method
CN112668754B (en) Power equipment defect diagnosis method based on multisource characteristic information fusion
Du et al. Multi-focus image fusion algorithm based on pulse coupled neural networks and modified decision map
CN112945897B (en) Continuous terahertz image non-uniformity correction method
CN106686281B (en) Fuse circuit board noise suppression ability test system
CN114972339A (en) Data enhancement system for bulldozer structural member production abnormity detection
CN106709890A (en) Method and device for processing low-light video image
CN115689964A (en) Image enhancement method and device, electronic equipment and storage medium
CN112561818B (en) Image enhancement method and device, electronic equipment and storage medium
US20210125324A1 (en) Image signal processing
CN105005967A (en) Method and apparatus for correcting non-uniformity of infrared imaging based on combined space-time filtering
CN117333795A (en) River surface flow velocity measurement method and system based on screening post-treatment
Sur et al. Measuring the noise of digital imaging sensors by stacking raw images affected by vibrations and illumination flickering
CN111076815B (en) Hyperspectral image non-uniformity correction method
Yang et al. Latency Correction for Event-guided Deblurring and Frame Interpolation
CN115420386A (en) Unstable pixel testing method of infrared focal plane device based on relative current
CN115291055A (en) Weight-adaptive acousto-optic collaborative diagnosis method for external insulation of power equipment
CN107623841A (en) A kind of good vehicle-mounted monitoring system of monitoring effect
CN114372941A (en) Low-illumination image enhancement method, device, equipment and medium
CN112911164A (en) Exposure time adjusting method and system for camera for air tightness test

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