CN115330818A - Picture segmentation method and computer readable storage medium thereof - Google Patents
Picture segmentation method and computer readable storage medium thereof Download PDFInfo
- Publication number
- CN115330818A CN115330818A CN202211166411.9A CN202211166411A CN115330818A CN 115330818 A CN115330818 A CN 115330818A CN 202211166411 A CN202211166411 A CN 202211166411A CN 115330818 A CN115330818 A CN 115330818A
- Authority
- CN
- China
- Prior art keywords
- processed
- picture
- pixel
- value
- image
- 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
- 230000011218 segmentation Effects 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001914 filtration Methods 0.000 claims abstract description 45
- 238000001514 detection method Methods 0.000 claims description 10
- 239000003550 marker Substances 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 238000003709 image segmentation Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 235000002864 food coloring agent Nutrition 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G06T5/70—
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Abstract
The invention provides a picture segmentation method and a computer readable storage medium thereof, wherein the method comprises the following steps: detecting a noise point on a picture to be processed by using a filtering window to obtain a noise point to be processed; when the number of the noise points to be processed in the filtering window is larger than a preset threshold value, denoising the picture to be processed in the corresponding filtering window; sliding a filtering window until the whole picture to be processed is traversed; and segmenting the denoised picture to be processed by utilizing the optimal segmentation threshold value to obtain the segmented picture to be processed. According to the method, firstly, the image to be processed is filtered by using the filtering window, then the optimal segmentation threshold value is obtained based on the correlation degree between the average image to be processed and the image to be processed after denoising, and the background area of the image to be processed can be stripped out by segmenting the image based on the segmentation threshold value, so that the outline and the texture of the target area are clearer.
Description
Technical Field
The invention relates to the technical field of image segmentation, in particular to a picture segmentation method and a computer readable storage medium thereof.
Background
For many digital image processing techniques, segmentation of an image is an important process. For example, image segmentation may be used to generate depth maps for three-dimensional imaging, object recognition, artificial coloring, and so on, which relate to many fields of power equipment monitoring, urban rail transit, big data analysis, medical image processing, and so on.
The existing method for dividing the image is mainly to divide the image based on the gray scale interval of the image, and the basic principle is to select a proper gray scale range, then traverse all pixels of the image, classify the gray scale value in the gray scale range as a target area, and classify the gray scale value outside the gray scale range as a background area. Therefore, the existing image segmentation method generally divides an image into two parts by setting a single gray threshold, but because the determination of the gray threshold depends on the subjective consciousness of workers, the method for segmenting the image by directly depending on the single gray threshold cannot well distinguish a target area from a background area.
Disclosure of Invention
The invention aims to provide a picture segmentation method and a computer readable storage medium thereof, and aims to solve the problem that the existing picture segmentation method cannot well distinguish a target area from a background area.
A picture segmentation method comprises the following steps:
step 1: acquiring a picture to be processed;
step 2: preprocessing the picture to be processed by using a median filtering method to obtain a preprocessed picture to be processed;
and step 3: detecting each image point in the filtering window by using an image point category detection model to obtain a category value of each image point;
and 4, step 4: taking the corresponding image points larger than the class value as noise points to be processed;
and 5: when the number of the noise points to be processed in the filtering window is larger than a preset threshold value, denoising the picture to be processed in the corresponding filtering window;
step 6: sliding the filtering window, and returning to the step 3 until the whole to-be-processed picture is traversed to obtain a denoised to-be-processed picture;
and 7: taking any point on the denoised picture to be processed as a center to obtain a neighborhood window, and calculating the gray average value of all pixel points in the neighborhood window;
and 8: taking the gray average value of the corresponding pixel points as the output of the central pixel point to obtain an average value to-be-processed picture;
and step 9: obtaining an optimal segmentation threshold according to the correlation between the image to be processed with the mean value and the image to be processed after denoising;
step 10: and segmenting the denoised picture to be processed by utilizing the optimal segmentation threshold value to obtain the segmented picture to be processed.
Preferably, the image point class detection model is:
F ij ＝|x ij -y ij |
wherein, F ij Indicates the class value, x, of the picture to be processed at (i, j) ij Representing the grey value, y, of a pixel point of the picture to be processed at the (i, j) position ij And (5) representing the gray value of the pixel point of the preprocessed to-be-processed picture at the (i, j) position.
Preferably, the step 5: when the number of the noise points to be processed in the filtering window is larger than a preset threshold value, denoising the picture to be processed in the corresponding filtering window, including:
step 5.1: calculating the mean value of the pseudo pixels according to the gray median values of all the pixel points in the filtering window; wherein, the calculation formula of the pseudo pixel mean difference is as follows:
wherein, the first and the second end of the pipe are connected with each other,
representing the mean difference of the false pixels of the pixel points (a, b) in the region with the size of (2n + 1) x (2n + 1) of the filtering window, mean (a, b) representing the gray level median of the pixel points (a, b) in the filtering window, and x (k, l) representing the gray level of the pixel points at the (k, l) position;
and step 5.2: and constructing a filtering window denoising model by using the pseudo pixel mean square error.
Preferably, said step 5.2: constructing a filtering window denoising model by using the pseudo pixel mean square error, comprising the following steps of:
the formula is adopted:
constructing a filter window denoising model; wherein f (a, b) represents the gray value of the pixel point (a, b) after denoising, D is an adjustable coefficient, and x (a, b) represents the gray value of the pixel point (a, b) in the filter window.
Preferably, the step 7: obtaining an optimal segmentation threshold according to the correlation between the image to be processed with the mean value and the de-noised image to be processed, including:
step 7.1: extracting the gray values of the denoised picture to be processed and the mean value picture to be processed at the same position to form a pixel mark group;
and 7.2: constructing an objective function using the set of pixel labels;
step 7.3: acquiring a preset pixel segmentation group, and continuously adjusting the preset pixel segmentation group until the value of the target function is maximum;
step 7.4: and taking the pixel segmentation group corresponding to the maximum value of the objective function as an optimal segmentation threshold value.
Preferably, said step 7.2: constructing an objective function using the set of pixel labels, comprising:
step 7.2.1: obtaining the mark group probability according to the occurrence times of the pixel mark groups;
step 7.2.2: obtaining the pixel value distribution probability of the denoised picture to be processed and the picture to be processed with the mean value according to the tag group probability; wherein the pixel value distribution probability is:
wherein, mu Tm Representing the pixel value distribution probability, mu, of the de-noised picture to be processed Tn Probability of pixel value distribution, p, representing the mean to be processed picture mn Representing the probability of the marker group, M representing the length of the denoised picture to be processed, N representing the width of the denoised picture to be processed, F mn Represents the number of occurrences of the pixel mark group (m, n), and m, n =0,1,2, \8230l;
step 7.2.3: and constructing an objective function according to the pixel value distribution probability.
Preferably, the objective function is:
where (s, t) represents the initial pixel segmentation group,
representing the probability of the distribution of the target pixel values,
representing the background pixel value distribution probability.
The present invention also provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps in one of the above-mentioned picture segmentation methods.
The picture segmentation method and the computer readable storage medium thereof provided by the invention have the beneficial effects that: compared with the prior art, the image segmentation method has the advantages that the image to be processed is filtered by utilizing the filtering window, then the optimal segmentation threshold value is obtained based on the correlation degree between the image to be processed with the mean value and the image to be processed after denoising, the background area of the image to be processed can be stripped out by segmenting the image based on the segmentation threshold value, and the outline and the texture of the target area are clearer.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 shows a flowchart of a picture segmentation method according to an embodiment of the present invention.
Detailed Description
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", and the like, indicate orientations and positional relationships based on those shown in the drawings, and are used only for convenience of description and simplicity of description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise explicitly stated or limited, the terms "mounted," "connected," "fixed," and the like are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The invention aims to provide a picture segmentation method and a computer readable storage medium thereof, aiming at solving the problem that the existing image segmentation method can not distinguish a target area from a background area well.
Referring to fig. 1, a method for dividing a picture includes:
step 1: acquiring a picture to be processed;
and 2, step: preprocessing the picture to be processed by using a median filtering method to obtain a preprocessed picture to be processed;
and step 3: detecting each image point in the filtering window by using an image point class detection model to obtain a class value of each image point;
in the embodiment of the present invention, the image point class detection model is:
F ij ＝|x ij -y ij |
wherein, F ij Indicates the class value, x, of the picture to be processed at (i, j) ij Representing the grey value, y, of a pixel point of the picture to be processed at the (i, j) position ij And (5) representing the gray value of the pixel point of the preprocessed to-be-processed picture at the (i, j) position.
The image point category detection model is constructed based on the median filtering method, so that the difference between noise points and original pixel points can be detected from the angle of pixel distribution, and further the detection of the noise points is more accurate.
And 4, step 4: taking the corresponding image points larger than the class value as noise points to be processed;
and 5: when the number of the noise points to be processed in the filtering window is larger than a preset threshold value, denoising the picture to be processed in the corresponding filtering window;
the original filtering algorithm, such as the mean filtering algorithm, is to process the mean value of the pixel points in each neighborhood on the picture to be processed (whether containing noise or not), so the processed picture becomes fuzzy, but the invention can find out the noise on the picture to be processed by using the image point type detection model, and then the original pixel information of the picture to be processed can be kept while smoothing the noise in the picture by filtering the corresponding noise. In practical application, the invention can set corresponding detection interval values according to actual situations.
Further, the step 5 comprises:
step 5.1: calculating the mean difference of the pseudo pixels according to the gray median values of all the pixel points in the filtering window; wherein, the calculation formula of the mean square error of the false pixels is as follows:
wherein the content of the first and second substances,
representing the mean difference of the false pixels of the pixel points (a and b) in a region with the size of (2n + 1) x (2n + 1) of a filtering window, mean (a and b) representing the gray level median of the pixel points (a and b) in the filtering window, and x (k and l) representing the gray level of the pixel points at the (k and l) positions;
step 5.2: and constructing a filtering window denoising model by using the pseudo pixel average difference.
In an embodiment of the present invention, step 5.2 comprises:
the formula is adopted:
constructing a filter window denoising model; wherein f (a, b) represents the gray value of the pixel point (a, b) after denoising, D is an adjustable coefficient, and x (a, b) represents the gray value of the pixel point (a, b) in the filter window.
Step 6: sliding the filtering window, and returning to the step 3 until the whole to-be-processed picture is traversed to obtain a denoised to-be-processed picture;
based on the filter window denoising model, the method can be used for denoising the picture to be processed in the corresponding filter window, so that the problem that certain characteristic gradients in the picture to be processed disappear by using the conventional denoising method (such as median filter denoising, mean filter denoising and the like) can be solved, original information of the picture can be retained to the maximum extent, and the interpretation effect of the picture can be improved.
And 7: taking any point on the denoised picture to be processed as a center to obtain a neighborhood window, and calculating the gray level average value of all pixel points in the neighborhood window;
further, step 7 includes:
step 7.1: extracting the gray values of the denoised picture to be processed and the mean value picture to be processed at the same position to form a pixel mark group;
in practical application, the pixel gray values of the denoised image to be processed and the average image to be processed at the position (i, j) are set to be m and n respectively, so that the gray values of the denoised image to be processed and the average image to be processed at the same position form a pixel marker group (m, n).
Step 7.2: constructing an objective function using the set of pixel labels;
in an embodiment of the invention, step 7.2 comprises:
step 7.2.1: obtaining the mark group probability according to the times of the occurrence of the pixel mark group;
step 7.2.2: obtaining the pixel value distribution probability of the denoised picture to be processed and the mean value picture to be processed according to the mark group probability; wherein the pixel value distribution probability is:
wherein, mu Tm Representing the pixel value distribution probability, mu, of the de-noised picture to be processed Tn Representing the pixel value distribution probability, p, of the mean to-be-processed picture mn Representing the probability of the marker group, M representing the length of the denoised picture to be processed, N representing the width of the denoised picture to be processed, F mn Represents the number of occurrences of a pixel mark group (m, n), and m, n =0,1,2, \ 8230; L;
step 7.2.3: and constructing an objective function according to the pixel value distribution probability. The objective function is:
wherein (s, t) represents the initialThe group of the pixel segments is divided into a plurality of groups,
representing the probability of the distribution of the target pixel values,
representing the background pixel value distribution probability.
Step 7.3: acquiring a preset pixel segmentation group, and continuously adjusting the preset pixel segmentation group until the value of the target function is maximum;
step 7.4: and taking the pixel segmentation group corresponding to the maximum value of the objective function as an optimal segmentation threshold value.
The image is segmented based on the principle of the histogram, the optimal segmentation threshold value can be obtained from the whole according to the probability of the gray value distribution of the image, the background region and the target region of the image to be processed can be segmented by utilizing the segmentation threshold value, and the target region of the image to be processed can be conveniently identified and extracted by workers.
And 8: taking the gray average value of the corresponding pixel points as the output of the central pixel point to obtain an average value to-be-processed picture;
and step 9: obtaining an optimal segmentation threshold according to the correlation between the image to be processed with the mean value and the image to be processed after denoising;
step 10: and segmenting the denoised picture to be processed by utilizing the optimal segmentation threshold value to obtain the segmented picture to be processed.
According to the method, firstly, the image to be processed is filtered by using the filtering window, then the optimal segmentation threshold value is obtained based on the correlation degree between the average image to be processed and the image to be processed after denoising, and the background area of the image to be processed can be stripped out by segmenting the image based on the segmentation threshold value, so that the outline and the texture of the target area are clearer.
Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the invention are the same as those of the image segmentation method in the technical scheme, and the detailed description is omitted herein.
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think of the technical scope of the present invention, and the technical scope of the present invention is covered by the modifications or alternatives. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (8)
1. A picture segmentation method is characterized by comprising the following steps:
step 1: acquiring a picture to be processed;
step 2: preprocessing the picture to be processed by using a median filtering method to obtain a preprocessed picture to be processed;
and step 3: detecting each image point in the filtering window by using an image point class detection model to obtain a class value of each image point;
and 4, step 4: taking the corresponding image points larger than the class value as noise points to be processed;
and 5: when the number of the noise points to be processed in the filtering window is larger than a preset threshold value, denoising the picture to be processed in the corresponding filtering window;
and 6: sliding the filtering window, and returning to the step 3 until the whole to-be-processed picture is traversed to obtain a denoised to-be-processed picture;
and 7: taking any point on the denoised picture to be processed as a center to obtain a neighborhood window, and calculating the gray average value of all pixel points in the neighborhood window;
and step 8: taking the gray average value of the corresponding pixel points as the output of the central pixel point to obtain an average value to-be-processed picture;
and step 9: obtaining an optimal segmentation threshold according to the correlation between the image to be processed with the mean value and the image to be processed after denoising;
step 10: and segmenting the denoised picture to be processed by utilizing the optimal segmentation threshold value to obtain the segmented picture to be processed.
2. The method of claim 1, wherein the image point class detection model is:
F ij ＝|x ij -y ij |
wherein, F ij Indicates the class value, x, of the picture to be processed at (i, j) ij Representing the grey value, y, of a pixel point of the picture to be processed at the (i, j) position ij And (5) representing the gray value of the pixel point of the preprocessed to-be-processed picture at the (i, j) position.
3. The picture segmentation method according to claim 1, wherein the step 5: when the number of the noise points to be processed in the filtering window is greater than a preset threshold value, denoising the picture to be processed in the corresponding filtering window, including:
step 5.1: calculating the mean difference of the pseudo pixels according to the gray median values of all the pixel points in the filtering window; wherein, the calculation formula of the pseudo pixel mean difference is as follows:
wherein, the first and the second end of the pipe are connected with each other,
representing the mean difference of the false pixels of the pixel points (a and b) in a region with the size of (2n + 1) x (2n + 1) of a filtering window, mean (a and b) representing the gray level median of the pixel points (a and b) in the filtering window, and x (k and l) representing the gray level of the pixel points at the (k and l) positions;
step 5.2: and constructing a filtering window denoising model by using the pseudo pixel average difference.
4. A picture segmentation method as claimed in claim 3, characterized in that said step 5.2: constructing a filtering window denoising model by using the pseudo pixel mean square error, comprising the following steps of:
the formula is adopted:
constructing a filter window denoising model; wherein f (a, b) represents the gray values of the pixel points (a, b) after denoising, D is an adjustable coefficient, and x (a, b) represents the gray values of the pixel points (a, b) in the filtering window.
5. The picture segmentation method according to claim 4, wherein the step 7: obtaining an optimal segmentation threshold according to the correlation between the image to be processed with the mean value and the de-noised image to be processed, including:
step 7.1: extracting the gray values of the denoised picture to be processed and the mean value picture to be processed at the same position to form a pixel mark group;
and 7.2: constructing an objective function using the set of pixel labels;
step 7.3: acquiring a preset pixel segmentation group, and continuously adjusting the preset pixel segmentation group until the value of the target function is maximum;
step 7.4: and taking the pixel segmentation group corresponding to the maximum value of the objective function as an optimal segmentation threshold value.
6. The picture segmentation method according to claim 5, wherein the step 7.2: constructing an objective function using the set of pixel labels, comprising:
step 7.2.1: obtaining the mark group probability according to the occurrence times of the pixel mark groups;
step 7.2.2: obtaining the pixel value distribution probability of the denoised picture to be processed and the mean value picture to be processed according to the mark group probability; wherein the pixel value distribution probability is:
wherein, mu Tm Representing the pixel value distribution probability, mu, of the de-noised picture to be processed Tn Representing the pixel value distribution probability, p, of the mean to-be-processed picture mn Representing the probability of a marker group, M representing the length of the denoised picture to be processed, N representing the width of the denoised picture to be processed, F mn Represents the number of occurrences of a pixel mark group (m, n), and m, n =0,1,2, \ 8230; L;
step 7.2.3: and constructing an objective function according to the pixel value distribution probability.
7. The method of claim 6, wherein the objective function is:
wherein (s, t) represents an initial pixel segmentation group,
representing the probability of the distribution of the target pixel values,
representing the background pixel value distribution probability.
8. The present invention also provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps in one of the above-mentioned picture segmentation methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211166411.9A CN115330818A (en) | 2022-09-23 | 2022-09-23 | Picture segmentation method and computer readable storage medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211166411.9A CN115330818A (en) | 2022-09-23 | 2022-09-23 | Picture segmentation method and computer readable storage medium thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115330818A true CN115330818A (en) | 2022-11-11 |
Family
ID=83914336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211166411.9A Pending CN115330818A (en) | 2022-09-23 | 2022-09-23 | Picture segmentation method and computer readable storage medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115330818A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110706171A (en) * | 2019-09-26 | 2020-01-17 | 中国电子科技集团公司第十一研究所 | Image noise reduction method and device |
-
2022
- 2022-09-23 CN CN202211166411.9A patent/CN115330818A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110706171A (en) * | 2019-09-26 | 2020-01-17 | 中国电子科技集团公司第十一研究所 | Image noise reduction method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115861135B (en) | Image enhancement and recognition method applied to panoramic detection of box body | |
| CN109086724B (en) | Accelerated human face detection method and storage medium | |
| CN115311309A (en) | Method and system for identifying and extracting focus of nuclear magnetic resonance image | |
| CN111027446B (en) | Coastline automatic extraction method of high-resolution image | |
| CN111178193A (en) | Lane line detection method, lane line detection device and computer-readable storage medium | |
| CN110415208A (en) | A kind of adaptive targets detection method and its device, equipment, storage medium | |
| CN111179295B (en) | Improved two-dimensional Otsu threshold image segmentation method and system | |
| CN114742968B (en) | Elevation map generation method based on building elevation point cloud | |
| CN113780110A (en) | Method and device for detecting weak and small targets in image sequence in real time | |
| CN115131351A (en) | Engine oil radiator detection method based on infrared image | |
| CN111144377A (en) | Dense area early warning method based on crowd counting algorithm | |
| CN106324708B (en) | Digitizing solution, the device of rainfall record drawing | |
| CN116824516B (en) | Road construction safety monitoring and management system | |
| CN114648547A (en) | Weak and small target detection method and device for anti-unmanned aerial vehicle infrared detection system | |
| CN107977608B (en) | Method for extracting road area of highway video image | |
| CN111753642B (en) | Method and device for determining key frame | |
| CN106815851B (en) | A kind of grid circle oil level indicator automatic reading method of view-based access control model measurement | |
| WO2024016632A1 (en) | Bright spot location method, bright spot location apparatus, electronic device and storage medium | |
| CN114742849B (en) | Leveling instrument distance measuring method based on image enhancement | |
| CN115330818A (en) | Picture segmentation method and computer readable storage medium thereof | |
| CN110427907A (en) | A kind of recognition pretreatment method for human face of grayscale image border detection and noise frame filling | |
| CN115471537A (en) | Monocular camera-based moving target distance and height measuring method | |
| CN113658153B (en) | Contour data feature point detection method and device | |
| CN108447045A (en) | A kind of SAR remote sensing images waters detection method based on SAT integrograms | |
| CN112734666B (en) | SAR image speckle non-local mean suppression method based on similarity value |
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 |