CN110298806A - Infrared image enhancing method and system - Google Patents
Infrared image enhancing method and system Download PDFInfo
- Publication number
- CN110298806A CN110298806A CN201910601556.9A CN201910601556A CN110298806A CN 110298806 A CN110298806 A CN 110298806A CN 201910601556 A CN201910601556 A CN 201910601556A CN 110298806 A CN110298806 A CN 110298806A
- Authority
- CN
- China
- Prior art keywords
- detail subbands
- indicates
- infrared image
- enhanced
- low pass
- 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
- 230000002708 enhancing effect Effects 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 30
- 230000009466 transformation Effects 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 230000004927 fusion Effects 0.000 claims abstract description 6
- 230000015654 memory Effects 0.000 claims description 25
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims 1
- 238000003860 storage Methods 0.000 description 15
- 238000004590 computer program Methods 0.000 description 11
- 238000001228 spectrum Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 3
- NEBFIUZIGRTIFY-BJDJZHNGSA-N Ala-Met-Ser-Arg Chemical compound CSCC[C@H](NC(=O)[C@H](C)N)C(=O)N[C@@H](CO)C(=O)N[C@H](C(O)=O)CCCNC(N)=N NEBFIUZIGRTIFY-BJDJZHNGSA-N 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of infrared image enhancing method and systems, this method comprises: obtaining the corresponding Stationary Wavelet Transform result of infrared image and Saliency maps；Wherein, Stationary Wavelet Transform result includes: low pass subband and detail subbands；Low pass subband degree of comparing increase is handled, and linear enhancing processing is carried out to detail subbands, obtains enhanced low pass subband and enhanced detail subbands；Saliency maps are subjected to low-pass filtering and Threshold segmentation processing, the Saliency maps that obtain that treated；By enhanced detail subbands, Saliency maps carry out dot product processing, the detail subbands merged with treated；Detail subbands based on enhanced low pass subband and fusion carry out stationary wavelet inverse transformation, obtain enhanced infrared image.The present invention can effectively improve infrared image enhancement treatment effeciency and real-time.
Description
Technical field
The present invention relates to technical field of image processing, and in particular, to infrared image enhancing method and system.
Background technique
Image enhancement technique primarily to improve image recognition capability, selectively protrude image in it is interested
Feature cuts redundancy feature.The characteristics of due to infrared imagery technique, the generally existing contrast of infrared image is low, edge blurry and
The prominent unconspicuous problem of details, therefore need image enhancement technique just to improve the quality of infrared image.
Currently, main two class of infrared image enhancing method being applicable in the market, image enchancing method and base based on airspace
In the image enchancing method of transform domain.Spatial domain picture Enhancement Method is directly to handle the pixel in image, fundamentally
Say it is based on the transformation of the grey scale mapping of image, mapping transformation type used depends on the purpose of enhancing.Spatial domain picture
Enhancement Method mainly includes greyscale transformation, histogram equalization (HE), smooth and sharpening etc..Transform domain Enhancement Method first will figure
Image in image space is transformed into some form in other spaces, then carries out image enhancement using the special property in the space
Processing, last reconvert is into original image space, to obtain enhanced image.Common variation have wavelet transformation,
Fourier transformation and discrete cosine transform etc..
But the space complexity and time complexity of existing image enchancing method are higher, are difficult to meet the reality of system
The requirement of when property.
Summary of the invention
For the defects in the prior art, the object of the present invention is to provide a kind of infrared image enhancing method and systems, use
To improve infrared image enhancement treatment effeciency and real-time.
In a first aspect, a kind of infrared image enhancing method provided by the invention, comprising:
S1: the corresponding Stationary Wavelet Transform result of infrared image and Saliency maps are obtained；Wherein, the Stationary Wavelet Transform
Result includes: low pass subband and detail subbands；
S2: handling low pass subband degree of the comparing increase, and carries out at linear enhancing to the detail subbands
Reason, obtains enhanced low pass subband and enhanced detail subbands；
S3: carrying out low-pass filtering and Threshold segmentation for the Saliency maps and handle, the Saliency maps that obtain that treated；
S4: by enhanced detail subbands, Saliency maps carry out dot product processing with treated, details merged
Band；
S5: the detail subbands based on the enhanced low pass subband and the fusion carry out stationary wavelet inverse transformation, obtain
To enhanced infrared image.
Optionally, low pass subband degree of the comparing increase is handled in the S2, comprising:
CLAHE contrast enhancement processing is carried out to low pass subband, Processing Algorithm is as follows:
L '=(1- α) L+ α CLAHE (L)
Wherein: L indicates low pass subband, the enhanced low pass subband of L ' expression, and α indicates control intensity, and CLAHE (L) is indicated
Contrast self-adapting histogram equilibrium is limited, indicates multiplying.
Optionally, as follows to the Processing Algorithm of the linear enhancing processing of detail subbands progress in the S2:
V=2.5s/tM
Wherein: s indicates the coefficient amplitude in transform domain, and M indicates greatest coefficient amplitude, and t indicates the first enhancing parameter；HhTable
Showing horizontal direction detail subbands, sign () indicates sign function operation, and b indicates the second enhancing parameter, and v indicates intermediate parameters,
Tanh () indicates hyperbolic tangent function operation, and c indicates that third enhances parameter, and exp () indicates exponential function operation,Table
Show enhanced horizontal direction subband, HvIndicate vertical direction detail subbands,Indicate vertical direction detail subbands after enhancing, Hd
Indicate diagonal detail subbands,Indicate diagonal detail subbands after enhancing.
Optionally, the Saliency maps and each detail subbands are carried out to the element multiplication one by one of matrix in the S4, with
The calculation formula for obtaining fused detail subbands is as follows:
Wherein, H'hIndicate the horizontal direction detail subbands finally enhanced, H'vIndicate vertical direction details finally enhanced
Band, H'dIndicate the diagonal detail subbands finally enhanced, S indicates Saliency maps, the point multiplication operation of o representing matrix.
Second aspect, the present invention also provides a kind of infrared image enhancement systems, comprising: memory and processor, memory
In be stored with the executable instruction of the processor；Wherein, the processor is configured to next via the executable instruction is executed
Execute the infrared image enhancing method as described in any one of first aspect.
Compared with prior art, the embodiment of the present invention have it is following the utility model has the advantages that
Infrared image enhancing method provided by the invention and system, by obtaining the corresponding Stationary Wavelet Transform of infrared image
And Saliency maps as a result；Wherein, Stationary Wavelet Transform result includes: low pass subband and detail subbands；Low pass subband is carried out pair
It is handled than degree increase, and linear enhancing processing is carried out to detail subbands, obtain enhanced low pass subband and enhanced thin
Knot band；Saliency maps are subjected to low-pass filtering and Threshold segmentation processing, the Saliency maps that obtain that treated；It will be enhanced thin
Saliency maps carry out dot product processing, the detail subbands merged to knot band with treated；Based on enhanced low pass subband
With the detail subbands of fusion, stationary wavelet inverse transformation is carried out, enhanced infrared image is obtained.The embodiment of the present invention is using significantly
Property figure Stationary Wavelet Transform, multiple dimensioned multi-direction decomposition can be carried out to image, indicates the detailed information of image well, is had
Enhance conducive to the details of infrared image；In addition, Saliency maps can have robustness well to noise-containing infrared image；
Efficiency is higher, real-time is good.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is the schematic illustration for the infrared image enhancing method that one embodiment of the invention provides；
Fig. 2 (a) is the first infrared image；
Fig. 2 (b) is AMSR enhancing treated the first infrared image；
Fig. 2 (c) is BPDHE enhancing treated the first infrared image；
Fig. 2 (d) is CRM enhancing treated the first infrared image；
Fig. 2 (e) is EFF enhancing treated the first infrared image；
Fig. 2 (f) is homomorphic filtering enhancing treated the first infrared image；
Fig. 2 (g) is Natural Factor enhancing treated the first infrared image；
Fig. 2 (h) is one embodiment of the invention enhancing treated the first infrared image；
Fig. 3 (a) is the second infrared image；
Fig. 3 (b) is AMSR enhancing treated the second infrared image；
Fig. 3 (c) is BPDHE enhancing treated the second infrared image；
Fig. 3 (d) is CRM enhancing treated the second infrared image；
Fig. 3 (e) is EFF enhancing treated the second infrared image；
Fig. 3 (f) is homomorphic filtering enhancing treated the second infrared image；
Fig. 3 (g) is Natural Factor enhancing treated the second infrared image；
Fig. 3 (h) is one embodiment of the invention enhancing treated the second infrared image.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to the present invention
Protection scope.
Fig. 1 is the schematic illustration of infrared image enhancing method provided in an embodiment of the present invention, as shown in Figure 1, right first
Input picture carries out Stationary Wavelet Transform respectively and Saliency maps calculate；Secondly to after Stationary Wavelet Transform low pass subband with
Detail subbands degree of comparing enhancing and non-linear enhancing respectively；Meanwhile low-pass filtering and threshold are carried out to the Saliency maps of acquisition
Value segmentation；Then dot product is carried out to the result after non-linear enhanced result and Threshold segmentation and obtains new detail subbands；Most
It is enhanced red to obtain against Stationary Wavelet Transform with new detail subbands by the enhanced low pass subband of contrast afterwards
Outer image.
In conjunction with Fig. 1, infrared image enhancing method provided in this embodiment may include:
Step 1: obtaining the corresponding Stationary Wavelet Transform result of infrared image and Saliency maps；Wherein, Stationary Wavelet Transform
Result includes: low pass subband and detail subbands.
In the present embodiment, Stationary Wavelet Transform is carried out to infrared image I and obtains low pass subband L, detail subbands Hh、HvWith Hd；
Conspicuousness calculating is carried out to infrared image I, obtains the Saliency maps S of infrared image I.
Specifically, two-dimensional Fourier transform is carried out to infrared image I first, and takes natural logrithm.Specific formula for calculation is such as
Under:
P (f)=φ (F (I))
L (f)=log (A (f))
Wherein, F indicates two-dimensional Fourier transform,Amplitude operation and phase operation are respectively represented with φ, P (f) and L (f) divide
Phase spectrum and logarithmic spectrum are not represented, and A (f) indicates the phase after being fourier transformed to I, and F (I) indicates to carry out Fourier's change to I
It changes.
Further, the amplitude components of the spectrum are used with 3 × 3 mean filter hn(f) it is filtered, calculation formula is such as
Under:
V (f)=L (f) * hn(f)
Wherein: V (f) indicates the amplitude mean filter of spectrum as a result, hn(f) indicate that equal filter, * indicate convolution algorithm.
Further, spectrum residual error R (f) is calculated, calculation formula is as follows:
R (f)=L (f)-V (f)
Further seemingly, it to the logarithmic spectrum residual error fetching number and carries out inverse Fourier transform and obtains Saliency maps, calculation formula
It is as follows:
Wherein:Indicate the Saliency maps that inverse transformation obtains, F-1Indicate inverse Fourier transform.
However experiment is found, after the Saliency maps for obtaining piece image, can not be directly used in enhancing.Because calculating
To Saliency maps not to be bright be exactly dark, dynamic range very little.Therefore it can pass through corresponding threshold process, as needed
Bianry image after being divided.Because the Saliency maps of two-value are mutation in boundary.Therefore, the present invention by its into
The multiple low-pass filtering of row, keeps it smooth enough, finally to smoothly or result enhance.
The embodiment of the present invention takes logarithm to the amplitude components of the picture after carrying out discrete Fourier transform, calculates initial show
Work property figure.
Then, to initial Saliency mapsThreshold segmentation is carried out, bianry image is made, then uses mean filter
Device arrives final directly available Saliency maps S for its smoothing processing.
Wherein, G3×3Indicate that filtering core size is 3 × 3 mean filter, GmeanIndicate mean filter,Table
Show Saliency mapsBinary segmentation result, * indicate convolution algorithm.
Step 2: low pass subband degree of comparing increase being handled, and linear enhancing processing is carried out to detail subbands, is obtained
To enhanced low pass subband and enhanced detail subbands.
In the present embodiment, CLAHE contrast enhancement processing is carried out to low pass subband, Processing Algorithm is as follows:
L '=(1- α) L+ α CLAHE (L)
Step 3: Saliency maps are subjected to low-pass filtering and Threshold segmentation and are handled, the Saliency maps that obtain that treated.
Above-mentioned step 2,3 in no particular order, can also carry out simultaneously.
Step 4: by enhanced detail subbands, Saliency maps carry out dot product processing, the details merged with treated
Subband.
In the present embodiment, the Processing Algorithm for carrying out linear enhancing processing to detail subbands is as follows:
V=2.5s/tM
Step 5: the detail subbands based on enhanced low pass subband and fusion carry out stationary wavelet inverse transformation, are increased
Infrared image after strong.
In the present embodiment, to enhanced detail subbands H'h、H'v、H'dIt is carried out with enhanced low pass subband L' inverse steady
Wavelet transformation obtains enhanced infrared image
The present embodiment, by obtaining the corresponding Stationary Wavelet Transform result of infrared image and Saliency maps；Wherein, steady small
Wave conversion result includes: low pass subband and detail subbands；Low pass subband degree of comparing increase is handled, and to detail subbands
Linear enhancing processing is carried out, enhanced low pass subband and enhanced detail subbands are obtained；Saliency maps are subjected to low pass filtered
Wave and Threshold segmentation processing, the Saliency maps that obtain that treated；By enhanced detail subbands and treated Saliency maps into
The processing of row dot product, the detail subbands merged；Detail subbands based on enhanced low pass subband and fusion carry out steady small
Wave inverse transformation obtains enhanced infrared image.The present embodiment utilize Saliency maps Stationary Wavelet Transform, can to image into
The multiple dimensioned multi-direction decomposition of row, indicates the detailed information of image well, is conducive to the details enhancing of infrared image；In addition, aobvious
Work property figure can have robustness well to noise-containing infrared image；Efficiency is higher, real-time is good.
Simulation results show, for the present invention to noise-containing infrared image enhancement problem, enhancing image detail is clear, compares
Spend higher, visual effect is preferable, objectively evaluates that index is more excellent, and the real-time of the method for the present invention is good, is a kind of effective and feasible red
Outer image enchancing method.
Specifically, the enhancing result figure as shown in Fig. 2 (b)~Fig. 2 (h) and Fig. 3 (b)~Fig. 3 (h) is as it can be seen that the present invention
Enhancing image not only overall contrast is improved, the edge and surface texture of target object are also very clear.
In addition, superiority and advance in order to better illustrate the present invention, using common 6 typical image enhancements
Index is objectively evaluated to evaluate the objective matter for the enhancing result for obtaining enhancing result and method for distinguishing acquisition using the technology of the present invention
Amount.6 kinds of evaluation indexes are respectively as follows: GI-F, SSEQ, ES, ACG, EME and AVC, and other than SSEQ, these evaluation index values are higher
Illustrate that enhancing picture quality is better.The average value for objectively evaluating index of two groups of experimental images is as shown in table 1.
Table 1
As can be seen from Table 1, the present invention, which enhances obtain 6 of result and objectively evaluates index, is superior to other methods, therefore
The present invention can effectively improve the clarity and detailed information of image.
To sum up, the enhancing that the Stationary Wavelet Transform infrared image enhancing method proposed by the present invention based on Saliency maps obtains
Image visual effect is good, detailed information is abundant, contrast is high, high-efficient.
The contents of the present invention are not limited to cited by embodiment, and those of ordinary skill in the art are by reading description of the invention
And to any equivalent transformation that technical solution of the present invention is taken, all are covered by the claims of the invention.
The embodiment of the present invention also provides a kind of infrared image enhancement system, comprising: memory and processor are deposited in memory
Contain the executable instruction of the processor；Wherein, the processor is configured to execute via the executable instruction is executed
Above-mentioned infrared image enhancing method.
Optionally, memory, for storing program；Memory may include volatile memory (English: volatile
Memory), for example, random access memory (English: random-access memory, abbreviation: RAM), such as static random-access
Memory (English: static random-access memory, abbreviation: SRAM), double data rate synchronous dynamic random-access
Memory (English: Double Data Rate Synchronous Dynamic Random Access Memory, abbreviation:
DDR SDRAM) etc.；Memory also may include nonvolatile memory (English: non-volatile memory), such as fastly
Flash memory (English: flash memory).Memory 62 is used to store computer program (the application journey as realized the above method
Sequence, functional module etc.), computer instruction etc., above-mentioned computer program, computer instruction etc. can with partitioned storage at one or
In multiple memories.And above-mentioned computer program, computer instruction, data etc. can be called with device processed.
Above-mentioned computer program, computer instruction etc. can be with partitioned storages in one or more memories.On and
Computer program, computer instruction, data for stating etc. can be called with device processed.
Processor, for executing the computer program of memory storage, to realize in method that above-described embodiment is related to
Each step.It specifically may refer to the associated description in previous methods embodiment.
Processor and memory can be absolute construction, be also possible to the integrated morphology integrated.When processor and
When memory is absolute construction, memory, processor can be of coupled connections by bus.
In addition, the embodiment of the present application also provides a kind of computer readable storage medium, deposited in computer readable storage medium
Computer executed instructions are contained, when at least one processor of user equipment executes the computer executed instructions, user equipment
Execute above-mentioned various possible methods.
Wherein, computer-readable medium includes computer storage media and communication media, and wherein communication media includes being convenient for
From a place to any medium of another place transmission computer program.Storage medium can be general or specialized computer
Any usable medium that can be accessed.A kind of illustrative storage medium is coupled to processor, to enable a processor to from this
Read information, and information can be written to the storage medium.Certainly, storage medium is also possible to the composition portion of processor
Point.Pocessor and storage media can be located in ASIC.In addition, the ASIC can be located in user equipment.Certainly, processor and
Storage medium can also be used as discrete assembly and be present in communication equipment.
The application also provides a kind of program product, and program product includes computer program, and computer program is stored in readable
In storage medium, at least one processor of server can read computer program from readable storage medium storing program for executing, at least one
Reason device executes the method that computer program makes the server implementation embodiments of the present invention any.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or part of or all technical features are carried out etc.
With replacement；And these modifications or substitutions, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution
Range.
Claims (5)
1. a kind of infrared image enhancing method characterized by comprising
S1: the corresponding Stationary Wavelet Transform result of infrared image and Saliency maps are obtained；Wherein, the Stationary Wavelet Transform result
It include: low pass subband and detail subbands；
S2: handling low pass subband degree of the comparing increase, and carries out linear enhancing processing to the detail subbands, obtains
To enhanced low pass subband and enhanced detail subbands；
S3: carrying out low-pass filtering and Threshold segmentation for the Saliency maps and handle, the Saliency maps that obtain that treated；
S4: by enhanced detail subbands, Saliency maps carry out dot product processing, the detail subbands merged with treated；
S5: the detail subbands based on the enhanced low pass subband and the fusion carry out stationary wavelet inverse transformation, are increased
Infrared image after strong.
2. infrared image enhancing method according to claim 1, which is characterized in that in the S2 to the low pass subband into
Row contrast increase processing, comprising:
CLAHE contrast enhancement processing is carried out to low pass subband, Processing Algorithm is as follows:
L '=(1- α) L+ α CLAHE (L)
Wherein: L indicates low pass subband, the enhanced low pass subband of L ' expression, and α indicates control intensity, and CLAHE (L) indicates limitation
Contrast self-adapting histogram equilibrium indicates multiplying.
3. infrared image enhancing method according to claim 1, which is characterized in that in the S2 to the detail subbands into
The Processing Algorithm of line enhancing processing is as follows:
V=2.5s/tM
Wherein: s indicates the coefficient amplitude in transform domain, and M indicates greatest coefficient amplitude, and t indicates the first enhancing parameter；HhIndicate water
Square to detail subbands, sign () indicates sign function operation, and b indicates the second enhancing parameter, and v indicates intermediate parameters, tanh
() indicates hyperbolic tangent function operation, and c indicates that third enhances parameter, and exp () indicates exponential function operation,It indicates to increase
Horizontal direction subband after strong, HvIndicate vertical direction detail subbands,Indicate vertical direction detail subbands after enhancing, HdIt indicates
Diagonal detail subbands,Indicate diagonal detail subbands after enhancing.
4. infrared image enhancing method according to claim 3, which is characterized in that in the S4 by the Saliency maps with
Each detail subbands carry out the element multiplication one by one of matrix, as follows with the calculation formula for obtaining fused detail subbands:
Wherein, H 'hIndicate the horizontal direction detail subbands finally enhanced, H 'vIndicate the vertical direction detail subbands finally enhanced,
H′dIndicating the diagonal detail subbands finally enhanced, S indicates Saliency maps,The point multiplication operation of representing matrix.
5. a kind of infrared image enhancement system characterized by comprising memory and processor are stored in memory described
The executable instruction of processor；Wherein, the processor is configured to carry out perform claim requirement via the execution executable instruction
Infrared image enhancing method described in any one of 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910601556.9A CN110298806B (en) | 2019-07-04 | 2019-07-04 | Infrared image enhancement method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910601556.9A CN110298806B (en) | 2019-07-04 | 2019-07-04 | Infrared image enhancement method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110298806A true CN110298806A (en) | 2019-10-01 |
| CN110298806B CN110298806B (en) | 2022-04-12 |
Family
ID=68030473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910601556.9A Active CN110298806B (en) | 2019-07-04 | 2019-07-04 | Infrared image enhancement method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298806B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111709898A (en) * | 2020-06-20 | 2020-09-25 | 昆明物理研究所 | Infrared image enhancement method and system based on optimized CLAHE |
| CN112308114A (en) * | 2020-09-24 | 2021-02-02 | 赣州好朋友科技有限公司 | Method and device for sorting scheelite and readable storage medium |
| CN116580290A (en) * | 2023-07-11 | 2023-08-11 | 成都庆龙航空科技有限公司 | Unmanned aerial vehicle identification method, unmanned aerial vehicle identification device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2431919A1 (en) * | 2010-09-16 | 2012-03-21 | Thomson Licensing | Method and device of determining a saliency map for an image |
| CN104050638A (en) * | 2014-06-12 | 2014-09-17 | 杭州电子科技大学 | Saliency method infrared small target enhancing method combined with scale optimization |
| CN105184752A (en) * | 2015-09-23 | 2015-12-23 | 成都融创智谷科技有限公司 | Image processing method based on wavelet transform |
| CN107862666A (en) * | 2017-11-22 | 2018-03-30 | 新疆大学 | Mixing Enhancement Methods about Satellite Images based on NSST domains |
| CN108389158A (en) * | 2018-02-12 | 2018-08-10 | 河北大学 | A kind of infrared and visible light image interfusion method |
| CN109191417A (en) * | 2018-09-11 | 2019-01-11 | 中国科学院长春光学精密机械与物理研究所 | It is detected based on conspicuousness and improves twin-channel method for self-adaption amalgamation and device |
| US10249032B2 (en) * | 2010-04-23 | 2019-04-02 | Flir Systems Ab | Infrared resolution and contrast enhancement with fusion |
-
2019
- 2019-07-04 CN CN201910601556.9A patent/CN110298806B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10249032B2 (en) * | 2010-04-23 | 2019-04-02 | Flir Systems Ab | Infrared resolution and contrast enhancement with fusion |
| EP2431919A1 (en) * | 2010-09-16 | 2012-03-21 | Thomson Licensing | Method and device of determining a saliency map for an image |
| CN104050638A (en) * | 2014-06-12 | 2014-09-17 | 杭州电子科技大学 | Saliency method infrared small target enhancing method combined with scale optimization |
| CN105184752A (en) * | 2015-09-23 | 2015-12-23 | 成都融创智谷科技有限公司 | Image processing method based on wavelet transform |
| CN107862666A (en) * | 2017-11-22 | 2018-03-30 | 新疆大学 | Mixing Enhancement Methods about Satellite Images based on NSST domains |
| CN108389158A (en) * | 2018-02-12 | 2018-08-10 | 河北大学 | A kind of infrared and visible light image interfusion method |
| CN109191417A (en) * | 2018-09-11 | 2019-01-11 | 中国科学院长春光学精密机械与物理研究所 | It is detected based on conspicuousness and improves twin-channel method for self-adaption amalgamation and device |
Non-Patent Citations (8)
| Title |
|---|
| EHSAN NEZHADARYA 等: "Image Contrast Enhancement by Contourlet Transform", 《48TH INTERNATIONAL SYMPOSIUM ELMAR-2006》 * |
| GUNNAM SURYANARAYANA 等: "Infrared super-resolution imaging using multi-scale saliency and deep wavelet residuals", 《INFRARED PHYSICS & TECHNOLOGY》 * |
| JUFENG ZHAO 等: "Infrared image enhancement through saliency feature analysis based on multi-scale decomposition", 《INFRARED PHYSICS & TECHNOLOGY》 * |
| XIANG YI 等: "Dim and small infrared target fast detection guided by visual saliency", 《INFRARED PHYSICS & TECHNOLOGY》 * |
| 于天河: "小波变换和自适应变换相结合的图像增强方法", 《哈尔滨理工大学学报》 * |
| 张承泓 等: "基于视觉显著性与对比度增强的红外图像融合", 《红外技术》 * |
| 江泽涛 等: "一种基于对比度增强和柯西模糊函数的红外与弱可见光图像融合算法", 《光子学报》 * |
| 龚昌来: "一种基于平稳小波域的红外图像增强方法", 《激光与红外》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111709898A (en) * | 2020-06-20 | 2020-09-25 | 昆明物理研究所 | Infrared image enhancement method and system based on optimized CLAHE |
| CN111709898B (en) * | 2020-06-20 | 2023-05-23 | 昆明物理研究所 | Infrared image enhancement method and system based on optimized CLAHE |
| CN112308114A (en) * | 2020-09-24 | 2021-02-02 | 赣州好朋友科技有限公司 | Method and device for sorting scheelite and readable storage medium |
| CN116580290A (en) * | 2023-07-11 | 2023-08-11 | 成都庆龙航空科技有限公司 | Unmanned aerial vehicle identification method, unmanned aerial vehicle identification device and storage medium |
| CN116580290B (en) * | 2023-07-11 | 2023-10-20 | 成都庆龙航空科技有限公司 | Unmanned aerial vehicle identification method, unmanned aerial vehicle identification device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110298806B (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711481B (en) | Neural networks for drawing multi-label recognition, related methods, media and devices | |
| Yang et al. | BM3D-Net: A convolutional neural network for transform-domain collaborative filtering | |
| EP2950267B1 (en) | Image denoising method and image denoising apparatus | |
| Dey | Hands-On Image Processing with Python: Expert techniques for advanced image analysis and effective interpretation of image data | |
| Cho et al. | Weakly-and self-supervised learning for content-aware deep image retargeting | |
| Gu et al. | A brief review of image denoising algorithms and beyond | |
| Liu et al. | Cross-SRN: Structure-preserving super-resolution network with cross convolution | |
| CN110298806A (en) | Infrared image enhancing method and system | |
| US9569684B2 (en) | Image enhancement using self-examples and external examples | |
| CN111415323B (en) | Image detection method and device and neural network training method and device | |
| CN104285239A (en) | Image processing device, image processing method, program, print medium, and recording medium | |
| CN110335199A (en) | A kind of image processing method, device, electronic equipment and storage medium | |
| Couturier et al. | Image denoising using a deep encoder-decoder network with skip connections | |
| Gong et al. | Combining sparse representation and local rank constraint for single image super resolution | |
| CN103208097A (en) | Principal component analysis collaborative filtering method for image multi-direction morphological structure grouping | |
| CN110782406B (en) | Image denoising method and device based on information distillation network | |
| Kamble et al. | Performance evaluation of wavelet, ridgelet, curvelet and contourlet transforms based techniques for digital image denoising | |
| CN111681198A (en) | Morphological attribute filtering multimode fusion imaging method, system and medium | |
| Zhang et al. | Joint integral histograms and its application in stereo matching | |
| CN104657951A (en) | Multiplicative noise removal method for image | |
| CN109410246B (en) | Visual tracking method and device based on correlation filtering | |
| CN115063318A (en) | Adaptive frequency-resolved low-illumination image enhancement method and related equipment | |
| CN116798041A (en) | Image recognition method and device and electronic equipment | |
| CN115937302A (en) | Hyperspectral image sub-pixel positioning method combined with edge preservation | |
| Das et al. | A concise review of fast bilateral filtering |
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 |