CN118212144A - Enhanced display method and system for high dynamic range infrared image - Google Patents
Enhanced display method and system for high dynamic range infrared image Download PDFInfo
- Publication number
- CN118212144A CN118212144A CN202410496814.2A CN202410496814A CN118212144A CN 118212144 A CN118212144 A CN 118212144A CN 202410496814 A CN202410496814 A CN 202410496814A CN 118212144 A CN118212144 A CN 118212144A
- Authority
- CN
- China
- Prior art keywords
- bit
- frame
- image data
- infrared image
- weighting coefficient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000009466 transformation Effects 0.000 claims abstract description 28
- 230000004927 fusion Effects 0.000 claims abstract description 26
- 238000004590 computer program Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 125000001475 halogen functional group Chemical group 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a method and a system for enhancing display of an infrared image with high dynamic range, which belong to the technical field of computer image processing, and the implementation of the method comprises the following steps: according to the histogram of the original 14-bit infrared image data, calculating K groups of parameters for piecewise linear transformation; respectively performing 14-bit to 8-bit piecewise linear transformation on the original infrared image data by using K groups of parameters to obtain a K frame 8-bit infrared image; calculating a weighting coefficient of each frame pixel point and a frame weighting coefficient of each frame by using the K frame 8-bit infrared image, and normalizing to obtain a normalized weighting coefficient of each frame; weighting and fusing the 8-bit infrared images of the K frames by using the normalized weighting coefficient of each frame to obtain 8-bit fused image data; and 8-bit detail images are extracted from the 14-bit infrared image data, and the detail images and 8-bit fusion image data are subjected to weighted fusion to obtain a final enhanced display image. The invention can meet the enhancement display requirements of various infrared scenes.
Description
Technical Field
The invention belongs to the technical field of computer image processing, and particularly relates to an enhanced display technology of an infrared image with a high dynamic range in the infrared technical field.
Background
The original infrared image data is generally 14 bits, the image display only needs 8 bits of data, and the image enhancement display technology is needed to complete from the original data to the image output display. The enhancement display of infrared images needs to solve two major technical difficulties: 1) When the scene temperature difference in the scene is large and the dynamic range of the effective data is far more than 256, all scenes are fully displayed. 2) When the temperature of the scenery in the scene is lower, the details of the image are enhanced, and the image noise is reduced.
Certain limitations and defects of the existing enhanced display algorithm occur when the infrared image data with high dynamic range are processed, for example, a single gray level transformation method based on a linear function, a logarithmic function and a power function is adopted, so that the scene contrast in the image is lowered, and partial scenes and details are 'covered'; the adoption of a probability distribution allocation method based on histogram statistics can lead to the fact that a small target is merged and lost due to small probability ratio of target data; the use of a block-based local automatic gain control algorithm (Automatic Gain Control, AGC) introduces "halos" from block to block; the method based on single detail enhancement (DIGITAL DETAIL ENHANCEMENT, DDE) can only preserve the edge information of the image, but cannot preserve the low frequency information differences between scenes.
Disclosure of Invention
The invention provides an enhanced display method and an enhanced display system for an infrared image with high dynamic range based on image fusion according to the characteristics of infrared image data and the technical difficulties of enhanced display, relates to piecewise linear transformation, image fusion and detail enhancement, and can meet the enhanced display requirements of various infrared scenes.
In order to achieve the above object, according to one aspect of the present invention, there is provided a high dynamic range infrared image enhancement display method based on image fusion, comprising:
According to the histogram of the original 14-bit infrared image data, calculating K groups of parameters for piecewise linear transformation;
respectively carrying out 14-bit to 8-bit piecewise linear transformation on the original 14-bit infrared image data by using K groups of parameters to obtain a K frame 8-bit infrared image;
According to the K frame 8-bit infrared image, calculating a weighting coefficient of each frame pixel point and a frame weighting coefficient of each frame, and normalizing the weighting coefficient of each frame pixel point and the frame weighting coefficient of each frame to obtain a normalized weighting coefficient of each frame;
Weighting and fusing the 8-bit infrared images of the K frames by using the normalized weighting coefficient of each frame to obtain 8-bit fused image data;
And 8-bit detail images are extracted from the original 14-bit infrared image data, and the detail images and 8-bit fusion image data are subjected to weighted fusion to obtain a final enhanced display image.
In some alternative embodiments, the computing the K sets of parameters for piecewise linear transformation from the histogram of the original 14-bit infrared image data includes:
Counting the original 14-bit infrared image data to obtain a histogram H [ n ] (n=0, 16383), calculating to obtain K groups of parameters (agc_down k,agc_upk) for piecewise linear transformation according to H [ n ], wherein k=0, K-1, [ agc_down k,agc_upk ] is a transformation window of the kth frame image, wherein,
Group 0 parameter (agc_down 0,agc_up0) satisfiesMx_0 represents the statistical maximum value, satisfyingAnd/>Mn_0 represents a statistical minimum, satisfying/>And is also provided withWd represents a window threshold value, and T represents the total number of pixels of one frame of image data;
Group 1 parameters (agc_Down 1,agc_up1) satisfy Wherein mx_1 represents a statistical maximum value satisfyingAnd/>Mn_1 represents a statistical minimum, satisfying/>And is also provided withP=1.0/(K-1), wd1 represents a window threshold value;
Group i parameters (agc_down i,agc_upi), i=2,.. Wherein mn_i represents a statistical minimum value, satisfyingAnd/>P=1.0xi/(K-1), wd1 and wd2 are window thresholds;
The K-1 group parameter (agc_Down K-1,agc_upK-1) satisfies Wherein mn K-1 represents a statistical minimum, satisfying/>And/>Wd3, wd4, wd5 represent window thresholds.
In some alternative embodiments, the performing 14-bit to 8-bit piecewise linear transformation on the original 14-bit infrared image data with K sets of parameters to obtain K-frame 8-bit infrared images, respectively, includes:
The obtained 8-bit infrared image of the K frame is recorded as D k, k=0, a.k-1, where the piecewise linear transform is expressed as: O (i, j) is original 14-bit image data, D k (i, j) is 8-bit infrared image data of the kth frame, and (i, j) is coordinates of a pixel point within the frame.
In some alternative embodiments, the point weighting factor for D 0 is PW 0(i,j)=1,Dk and the point weighting factor for D 0 isWhere u k represents the mean of the gaussian and delta k represents the variance of the gaussian.
In some alternative embodiments, D 0 has a frame weight of FW (0) =1.0, D 1 has a frame weight of FW (1) =1.5, and D k has a frame weight of deta k_base=(agc_downk-1+agc_upk-1)/2-(agc_downk+agc_upk)/2
K=2..k-2, d K-1 has a frame weighting factor of FW (K-1) =1.5.
In some alternative embodiments, the method comprisesAnd obtaining a normalized weighting coefficient of each frame.
In some alternative embodiments, the method comprisesAnd carrying out weighted fusion on the 8-bit infrared images of the K frames to obtain 8-bit fusion image data F (i, j).
In some alternative embodiments, the method comprisesA final enhanced display image is obtained, where O detail (i, j) is an 8-bit detail map obtained from O (i, j), G (i, j) is the final enhanced display image, and a, b are coefficients.
According to another aspect of the present invention, there is provided a high dynamic range infrared image enhancement display system based on image fusion, comprising:
According to the histogram of the original 14-bit infrared image data, calculating K groups of parameters for piecewise linear transformation;
The linear transformation module is used for respectively carrying out 14-bit to 8-bit piecewise linear transformation on the original 14-bit infrared image data by using K groups of parameters to obtain K frames of 8-bit infrared images;
the weighting module is used for calculating the weighting coefficient of each frame pixel point and the frame weighting coefficient of each frame according to the K frame 8-bit infrared image, and normalizing the weighting coefficient of each frame pixel point and the frame weighting coefficient of each frame to obtain a normalized weighting coefficient of each frame;
the weighting fusion module is used for weighting and fusing the 8-bit infrared images of the K frames by the normalized weighting coefficient of each frame to obtain 8-bit fused image data;
And the enhancement module is used for extracting 8-bit detail images from the original 14-bit infrared image data, and carrying out weighted fusion on the detail images and 8-bit fusion image data to obtain a final enhanced display image.
According to another aspect of the present invention there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of any of the methods described above.
In general, the above technical solutions conceived by the present invention, compared with the prior art, enable the following beneficial effects to be obtained:
The method for obtaining the K frame 8-bit infrared image by calculating the single frame 14-bit infrared image data and the two-level weighted fusion method based on the points and the frames are key points of the method. When the scene temperature difference is smaller, the infrared image data difference is small, and the obtained K frame 8-bit image data difference is not large; when scene temperature difference is large, infrared image data difference is large, obtained K frame 8 bit image data difference is also large, interested scenes in the K frame images are selectively fused into one frame of image through weighting coefficients, and the method creatively converts the problem of enhancing display of the infrared images with high dynamic range into the problem of image fusion among series of images with different 'exposure time' in the same scale of the same scene. The method can better enhance the display effect aiming at various scenes.
Drawings
FIG. 1 is a flow chart of a method provided by an embodiment of the present invention;
FIG. 2 is a flowchart for extracting detailed diagrams provided by an embodiment of the present invention;
Fig. 3 is a series of diagrams related to a scene 1 (thermos) method according to the present invention, where fig. (a) to (F) are respectively 6 frames of 8-bit images obtained after step S1 is completed, fig. G is a fused image F obtained after step S3 is completed, fig. h is a detailed diagram extracted from original data, and fig. i is a final enhanced display effect diagram G;
Fig. 4 is a series of diagrams related to a scene 2 (road and car at high temperature) in the method according to the present invention, where fig. (a) to (F) are 6 frames of 8-bit images obtained after step S1 is completed, fig. (G) is a fused image F obtained after step S3 is completed, fig. h is a detailed diagram extracted from original data, and fig. i is a final enhanced display effect diagram G.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
According to the enhancement display method based on the adaptive weighted fusion processing of the 14-bit high dynamic range infrared image, firstly, 8-bit infrared image data of K frames meeting fusion requirements is obtained by piecewise linear transformation according to a histogram of original infrared image data, then, a point weighting coefficient and a frame weighting coefficient are calculated according to parameters of piecewise linear transformation and the 8-bit image data, the K-frame 8-bit image data is weighted and fused, and then, the frame image data is fused with a detail image extracted from the original infrared image data, so that final display image data is obtained. The resolution of the image is m×n, the total number of pixels of the image data of one frame is T, (i, j) is the coordinates of points in the frame, as shown in fig. 1, and the specific steps are as follows:
Step S1: calculating from a frame of 14-bit original infrared image data to obtain K frame of 8-bit infrared image data;
in the embodiment of the present invention, step S1 may be implemented by:
The raw infrared image data is counted to obtain a histogram H [ n ] (n=0, 16383). From H [ n ], a set of parameters (agc_down k,agc_upk) for piecewise linear transformation is calculated, where k=0,..k-1, [ agc_down k,agc_upk ] is a transformation window of the kth frame image, and the calculation formula is as follows:
(1) Group 0 parameters (agc_down 0,agc_up0)
In the formula (i),
Mx_0: statistical maximum value of meetingAnd/>
Mn_0: statistics of minimum value satisfiesAnd/>
Wd: window threshold, wd=511 in the example.
(2) Group 1 parameters (agc_down 1,agc_up1)
In the formula (i),
Mx_1: statistical maximum value of meetingAnd/>
Mn_1: statistics of minimum value satisfiesAnd/>
Wd1: the window threshold value is in the embodiment wr1=255.
(3) Group i parameters (agc_down i,agc_upi), i=2,..
In the formula (i),
Mn_i, statistics minimum value, satisfiesAnd/>p=1.0×i/(K-1)。
Wd1, wd2, window threshold, in the example shown wd1=255, wd2=256.
(4) K-1 set of parameters (agc_Down K-1,agc_upK-1)
In the formula (i),
Mn K-1: statistics of minimum value satisfiesAnd/>
Wd3, wd4, wd5 window threshold values, in the example shown, wd 3=30, wd 4=512, and wd 5=256.
And (3) respectively performing 14-bit to 8-bit piecewise linear transformation on the original infrared image data by using the K groups of parameters to obtain an 8-bit infrared image of a K frame, which is recorded as D k, k=0.
The piecewise linear transformation formula is as follows:
where O (i, j) is the original 14-bit image data, D k (i, j) is the 8-bit infrared image data, and (i, j) is the coordinates of the pixel point within the frame.
Step S2: calculating a point weighting coefficient PW k (i, j) and a frame weighting coefficient FW (k), and normalizing;
in the embodiment of the present invention, step S2 may be implemented by:
For ease of analysis calculation, the image data D k (i, j) is normalized to the [0:1] interval, and the point weighting coefficient PW k (i, j) is calculated as follows:
1)D0:PW0(i,j)=1。
2)Dk:
In the method, in the process of the invention,
U k: the mean of the gaussian function.
Delta k: variance of the gaussian function.
Let u 1=0.8,uK-1 =0.3 in the example, and other u k=0.5,δk =1.0.
The frame weighting coefficient FW (k) is calculated as follows:
1) D 0: in the embodiment, FW (0) =1.0
2) D 1: in the embodiment, FW (1) =1.5
3)Dk:k=2,...,K-2
detak_base=(agc_downk-1+agc_upk-1)/2-(agc_downk+agc_upk)/2
4) D K-1: in the embodiment, FW (K-1) =1.5
The weighting coefficient normalization processing formula is as follows:
step S3: weighting and fusing the K frame 8-bit infrared image data:
In the embodiment of the present invention, step S3 may be implemented by:
The fusion formula is as follows:
Step S4: and carrying out weighted fusion with the detail graph in the original infrared image data to carry out detail enhancement.
In an embodiment of the present invention, a detailed image extraction process in original infrared image data is shown in fig. 2, and includes:
p1: carrying out convolution filtering on the original infrared data and a 3 multiplied by 3 edge operator; p2: setting a filtering result mean value; p3: performing 14-bit to 8-bit piecewise linear transformation; p4: an 8-bit detail map is obtained.
The image detail enhancement technique is described in the form of a formula as follows:
G(i,j)=a×F(i,j)+b×Odetail(i,j)
a+b=1
In the formula, O detail (i, j) is an 8-bit detail drawing obtained from O (i, j), and G (i, j) is a final enhancement display result of the method of the present invention, and in the embodiment, a=0.2 and b=0.8 are set.
The difference of the infrared image data in the scenes shown in fig. 3 and fig. 4 reaches about 8000, the value range of K is [4,9], where k=6 is taken, and D 0 in fig. (a) is an effect diagram of a commonly adopted method, which can balance the display requirements of various scene targets, but "force is not centered" when processing the infrared image data with high dynamic range. Fig. (a) to (F) are 6-frame 8-bit images obtained after step S1 is completed, fig. (G) is a fused image F obtained after step S3 is completed, fig. (h) is a detailed image extracted from the original data, and fig. (i) is a final enhanced display effect image G. By carefully observing and comparing the series of images related in fig. 3 and fig. 4, it is not difficult to find that the method of the present invention can effectively improve the contrast and brightness of most of the target scenes in the scene, and can display more scenes and details in the 8-bit image. In addition, different enhancement display effects can be achieved by adjusting the relevant parameters and coefficients in the embodiment. The method can obtain better enhanced display effect aiming at various complex scenes, is suitable for being transplanted in an FPGA, can be applied to infrared imaging equipment and a photoelectric system, and has larger engineering application value.
It should be noted that each step/component described in the present application may be split into more steps/components, or two or more steps/components or part of operations of the steps/components may be combined into new steps/components, according to the implementation needs, to achieve the object of the present application.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. The high dynamic range infrared image enhancement display method based on image fusion is characterized by comprising the following steps of:
According to the histogram of the original 14-bit infrared image data, calculating K groups of parameters for piecewise linear transformation;
respectively carrying out 14-bit to 8-bit piecewise linear transformation on the original 14-bit infrared image data by using K groups of parameters to obtain a K frame 8-bit infrared image;
According to the K frame 8-bit infrared image, calculating a weighting coefficient of each frame pixel point and a frame weighting coefficient of each frame, and normalizing the weighting coefficient of each frame pixel point and the frame weighting coefficient of each frame to obtain a normalized weighting coefficient of each frame;
Weighting and fusing the 8-bit infrared images of the K frames by using the normalized weighting coefficient of each frame to obtain 8-bit fused image data;
And 8-bit detail images are extracted from the original 14-bit infrared image data, and the detail images and 8-bit fusion image data are subjected to weighted fusion to obtain a final enhanced display image.
2. The method of claim 1, wherein computing K sets of parameters for piecewise linear transformation from the histogram of the original 14-bit infrared image data comprises:
Counting the original 14-bit infrared image data to obtain a histogram H [ n ] (n=0, 16383), calculating to obtain K groups of parameters (agc_down k,agc_upk) for piecewise linear transformation according to H [ n ], wherein k=0, K-1, [ agc_down k,agc_upk ] is a transformation window of the kth frame image, wherein,
Group 0 parameter (agc_down 0,agc_up0) satisfiesMx_0 represents the statistical maximum, satisfying/>And/>Mn_0 represents a statistical minimum, satisfying/>And/>Wd represents a window threshold value, and T represents the total number of pixels of one frame of image data;
Group 1 parameters (agc_Down 1,agc_up1) satisfy Wherein mx_1 represents a statistical maximum value satisfying/>And/>Mn_1 represents a statistical minimum, satisfying/>And/>P=1.0/(K-1), wd1 represents a window threshold value;
Group i parameters (agc_down i,agc_upi), i=2,.. Wherein mn_i represents a statistical minimum value, satisfyingAnd/>P=1.0xi/(K-1), wd1 and wd2 are window thresholds;
The K-1 group parameter (agc_Down K-1,agc_upK-1) satisfies Wherein mn K-1 represents a statistical minimum, satisfying/>And/>Wd3, wd4, wd5 represent window thresholds.
3. The method of claim 2, wherein the performing a 14-bit to 8-bit piecewise linear transformation on the original 14-bit infrared image data with the K sets of parameters, respectively, to obtain the K-frame 8-bit infrared image comprises:
The obtained 8-bit infrared image of the K frame is recorded as D k, k=0, a.k-1, where the piecewise linear transform is expressed as: O (i, j) is original 14-bit image data, D k (i, j) is 8-bit infrared image data of the kth frame, and (i, j) is coordinates of a pixel point within the frame.
4. A method according to claim 3, wherein the point weighting factor for D 0 is PW 0(i,j)=1,Dk and the point weighting factor for D 0 isWhere u k represents the mean of the gaussian and delta k represents the variance of the gaussian.
5. The method of claim 4 wherein D 0 has a frame weight of FW (0) =1.0, D 1 has a frame weight of FW (1) =1.5, and D k has a frame weight of FW (1) =1.0
The frame weighting coefficient of D K-1 is FW (K-1) =1.5.
6. The method according to claim 5, characterized by that, byAnd obtaining a normalized weighting coefficient of each frame.
7. The method according to claim 6, characterized by that, byAnd carrying out weighted fusion on the 8-bit infrared images of the K frames to obtain 8-bit fusion image data F (i, j).
8. The method according to claim 7, characterized by that, byA final enhanced display image is obtained, where O detail (i, j) is an 8-bit detail map obtained from O (i, j), G (i, j) is the final enhanced display image, and a, b are coefficients.
9. A high dynamic range infrared image enhancement display system based on image fusion, comprising:
According to the histogram of the original 14-bit infrared image data, calculating K groups of parameters for piecewise linear transformation;
The linear transformation module is used for respectively carrying out 14-bit to 8-bit piecewise linear transformation on the original 14-bit infrared image data by using K groups of parameters to obtain K frames of 8-bit infrared images;
the weighting module is used for calculating the weighting coefficient of each frame pixel point and the frame weighting coefficient of each frame according to the K frame 8-bit infrared image, and normalizing the weighting coefficient of each frame pixel point and the frame weighting coefficient of each frame to obtain a normalized weighting coefficient of each frame;
the weighting fusion module is used for weighting and fusing the 8-bit infrared images of the K frames by the normalized weighting coefficient of each frame to obtain 8-bit fused image data;
And the enhancement module is used for extracting 8-bit detail images from the original 14-bit infrared image data, and carrying out weighted fusion on the detail images and 8-bit fusion image data to obtain a final enhanced display image.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410496814.2A CN118212144A (en) | 2024-04-24 | 2024-04-24 | Enhanced display method and system for high dynamic range infrared image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410496814.2A CN118212144A (en) | 2024-04-24 | 2024-04-24 | Enhanced display method and system for high dynamic range infrared image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118212144A true CN118212144A (en) | 2024-06-18 |
Family
ID=91456275
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410496814.2A Pending CN118212144A (en) | 2024-04-24 | 2024-04-24 | Enhanced display method and system for high dynamic range infrared image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118212144A (en) |
-
2024
- 2024-04-24 CN CN202410496814.2A patent/CN118212144A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kumar et al. | Image smog restoration using oblique gradient profile prior and energy minimization | |
CN110827229B (en) | Infrared image enhancement method based on texture weighted histogram equalization | |
CN111210393B (en) | Color image enhancement method, system and storage medium based on edge extraction | |
Xiao et al. | Scene‐aware image dehazing based on sky‐segmented dark channel prior | |
CN114418904B (en) | Infrared image enhancement method based on improved histogram equalization and enhanced high-pass filtering | |
CN109255799B (en) | Target tracking method and system based on spatial adaptive correlation filter | |
CN113592750B (en) | Infrared enhancement method based on gradient histogram | |
CN112070717A (en) | Power transmission line icing thickness detection method based on image processing | |
CN112508963A (en) | SAR image segmentation method based on fuzzy C-means clustering | |
CN116862809A (en) | Image enhancement method under low exposure condition | |
CN118212144A (en) | Enhanced display method and system for high dynamic range infrared image | |
CN112037137A (en) | Method and device for eliminating fuzzy region of insulator disc surface edge in infrared image | |
CN114998186B (en) | Method and system for detecting surface scab defect of copper starting sheet based on image processing | |
CN116343051A (en) | Geological environment monitoring method and system based on remote sensing image | |
CN115661111A (en) | Self-adaptive enhancement method for gastrointestinal low-light-level image of capsule endoscope | |
Wang et al. | Adaptive Bright and Dark Channel Combined with Defogging Algorithm Based on Depth of Field | |
CN112348760A (en) | Image processing method and system | |
CN106780398A (en) | A kind of image de-noising method based on noise prediction | |
Yin et al. | Enhancement of Low-Light Image using Homomorphic Filtering, Unsharp Masking, and Gamma Correction | |
CN114742732B (en) | Infrared image enhancement method based on detail richness | |
CN116778261B (en) | Raw oil grade classification method based on image processing | |
CN113763294B (en) | Quick preprocessing method and system for weld image based on dynamic CLAHE | |
CN116563136B (en) | Side-scan sonar image denoising method, system, storage medium and execution system | |
CN117409275B (en) | Multi-angle radar image processing method | |
CN116681629B (en) | Visible light image self-adaptive contrast enhancement method and system for main transformer of transformer substation |
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 |