CN114187195A - 2D (two-dimensional) forward-looking sonar image denoising method - Google Patents
2D (two-dimensional) forward-looking sonar image denoising method Download PDFInfo
- Publication number
- CN114187195A CN114187195A CN202111437098.3A CN202111437098A CN114187195A CN 114187195 A CN114187195 A CN 114187195A CN 202111437098 A CN202111437098 A CN 202111437098A CN 114187195 A CN114187195 A CN 114187195A
- Authority
- CN
- China
- Prior art keywords
- image
- noise
- target
- threshold
- segmentation
- 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 74
- 230000011218 segmentation Effects 0.000 claims abstract description 33
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000003384 imaging method Methods 0.000 claims abstract description 6
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 230000002708 enhancing effect Effects 0.000 claims description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 3
- 241001270131 Agaricus moelleri Species 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 6
- 238000007781 pre-processing Methods 0.000 abstract description 4
- 238000003672 processing method Methods 0.000 abstract description 3
- 238000007619 statistical method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000000877 morphologic effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20004—Adaptive image processing
-
- 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
- G06T2207/20061—Hough transform
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
A2D foresight sonar image denoising method comprises image acquisition (1), image preprocessing (2), threshold segmentation (3), noise segmentation (4), target enhancement (5) and region-of-interest extraction (6). According to the method, a traditional image processing method is fused with a self-adaptive threshold segmentation method, a Hough transform method and a clustering statistical method, the problem that image noise is too high due to load body noise, inter-sector interference and target echo characteristic unevenness in the imaging process of the forward-looking sonar is effectively solved, the background noise is well removed while the obstacle and the target effective area are kept, the high-quality region of interest is obtained, and a foundation is laid for subsequent further target identification and high-precision positioning work.
Description
Technical Field
The invention relates to a 2D (two-dimensional) forward-looking sonar image denoising method, in particular to an image noise removing method aiming at a 2D forward-looking sonar load image.
Background
The forward-looking sonar is an important load carried by underwater equipment, can be used for detecting underwater obstacles and moving and static targets in a large range, and is a basis for realizing autonomous obstacle avoidance and target identification and tracking. However, factors such as water noise, interference between load sectors, and target echo intensity non-uniformity introduce strong noise to the sonar image. Noise interference is still an important challenge facing sonar image target detection at present. Currently, there is no target detection method specially designed for sonar images, and most of related research methods are optimized for the imaging characteristics of acoustic images on the basis of an optical image processing method, so that the purposes of filtering noise and acquiring a target area are achieved. Images formed by different load devices in a complex marine environment are diversified and affected by insufficient samples, and the requirements of underwater equipment on target detection cannot be met in the existing research.
Disclosure of Invention
The technical problem solved by the invention is as follows: the defects of the prior art are overcome, the 2D forward-looking sonar image denoising method is provided, typical noises caused by the problems of water noise, interference among load sectors, target echo intensity unevenness and the like can be filtered, and the requirements of a task system are met through testing.
The technical solution of the invention is as follows: A2D forward-looking sonar image denoising method comprises the following steps:
obtaining a sonar image from a forward looking sonar in real time, carrying out primary segmentation by adopting a threshold method, then segmenting noise according to noise characteristics to obtain a noise image, then enhancing target display according to target characteristics, and finally fusing the primary segmentation, the noise segmentation and the target enhancement image to obtain a final region of interest.
Further, the threshold method adopts a global adaptive threshold segmentation algorithm based on histogram statistical characteristics.
Further, the global adaptive threshold segmentation algorithm based on histogram statistical features comprises the following steps:
firstly, counting 256 gray scales of 0-255 of an image, and establishing a gray scale histogram;
then, starting to calculate a threshold value;
finally, image traversal is performed with the threshold, with pixels above the threshold set to 255, and otherwise set to 0.
Further, the calculating the threshold value comprises the following steps:
when calculating the threshold, counting the number of pixels from 255 with high brightness to 0 with low brightness, recording the number of pixels as alpha, and continuously recording the gray value delta at the moment;
the reason for moving from 255 to 0 is that in a sonar image, a target often has strong reflection characteristics, and corresponds to a highlight point in the image, and the gray value is high, which is a foreground; the water body has weak reflection characteristics, corresponds to low bright points in the image, has low gray value and is a background;
then, when the counted pixel number α is greater than 500, the gray value δ at this time is found, which is the segmentation threshold.
Further, the method for segmenting the noise according to the noise characteristics is an improved Hough transform-based arc extraction method; when the arc is extracted in the improved Hough transform-based arc extraction method, a transverse scanning method is adopted for scanning the image.
Further, in the transverse scanning method adopted for scanning the image, the method for acquiring the angular resolution is
Where deg is the angular resolution, r is the pixel distance from the point to the sonar head, and value is the value of the angular resolution deg.
Furthermore, the method for enhancing the target display is a method of a fused radial compensation method and a clustering method; wherein
The radial compensation method is characterized in that the trailing and shadow characteristics in target imaging are utilized, scanning is performed sequentially from left to right along the radial direction of a sector, and pixel points meeting the width are reserved;
the clustering method is to analyze the region of interest blocks of the image and take the distance as the evaluation index of the similarity.
Further, in the radial compensation method, the resolution is 0.001 radian during scanning.
A computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method for denoising a 2D forward-looking sonar image.
A2D front-view sonar image denoising device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the 2D front-view sonar image denoising method.
Compared with the prior art, the invention has the advantages that:
(1) the invention integrates the traditional image processing method, the self-adaptive threshold segmentation, the Hough transform and the cluster statistical method, effectively solves the problem of overlarge image noise caused by load body noise, inter-sector interference and target echo characteristics in the imaging process of the forward-looking sonar, and realizes better removal of background noise and acquisition of a high-quality region of interest while keeping barriers and a target effective region.
(2) The invention can carry out seamless butt joint with subsequent obstacle and target detection technologies, tests on an underwater mobile platform, has good algorithm real-time performance, and meets the requirements of unmanned platforms such as AUV, ROV and the like.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a schematic diagram of an image processing process;
fig. 3 is a typical sonar image region-of-interest extraction contrast map.
Detailed Description
In order to better understand the technical solutions, the technical solutions of the present application are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.
The following describes in further detail a 2D forward-view sonar image denoising method provided by the embodiment of the present application with reference to drawings of the specification, and specific implementation manners may include (as shown in fig. 1 to 3): the method comprises the steps of image acquisition (1), image preprocessing (2), initial segmentation (3), noise segmentation (4), target enhancement (5) and region of interest extraction (6).
The image preprocessing in the step (2) comprises one or more of image median filtering, bilateral filtering and morphological open operation.
The initial segmentation in the step (3) adopts a global adaptive threshold segmentation algorithm based on histogram statistical features.
The processing in the step (4) adopts an improved Hough transform-based arc extraction method.
And (5) performing target enhancement by adopting a fused radial compensation method and a clustering method to reduce target fracture caused by nonuniform echo, and then further optimizing a target area by adopting a morphological filtering method.
In the solution provided by the embodiment of the present application, as shown in fig. 1, the steps of the present invention include image acquisition (1), image preprocessing (2), initial segmentation (3), noise segmentation (4), target enhancement (5), and region-of-interest extraction (6). Namely:
firstly, a sonar image is obtained from a forward looking sonar in real time, a threshold value method is adopted for preliminary segmentation, then noise is segmented according to noise characteristics to obtain a noise image, then target display is enhanced according to target characteristics, and finally the preliminary segmentation, the noise segmentation and the target enhancement image are fused to obtain a final region of interest.
It should be noted that the threshold method herein employs a global adaptive threshold segmentation algorithm based on histogram statistical features.
Firstly, carrying out statistics on 256 gray levels of 0-255 of an image, and establishing a gray level histogram.
Then, the calculation of the threshold value is started.
When calculating the threshold, the number of pixels is counted from the high luminance 255 to the low luminance 0, the number of pixels is represented as α, and the gradation value δ at this time is continuously recorded.
The reason for moving from 255 to 0 is that in a sonar image, a target often has strong reflection characteristics, and corresponds to a highlight point in the image, and the gray value is high, which is a foreground; the water body has weak reflection characteristics, corresponds to low bright points in the image, has low gray value and is a background.
Then, when the counted pixel number α is greater than 500, the gray value δ at this time is found, which is the segmentation threshold.
In the statistical process, if the number of pixels α is still not sufficient to 500 after the gray value δ is smaller than 100, the statistical process is stopped, and 100 is used as the segmentation threshold.
Finally, image traversal is performed with the threshold, with pixels above the threshold set to 255, and otherwise set to 0.
Fig. 2 is an image after threshold segmentation.
The noise segmentation mainly eliminates the body noise of sonar equipment. Due to the fact that the device sector inconsistency and the target strong reflection effect influence, annular noise can occur in a sonar image along with a high-intensity target, and the segmentation of a real target is influenced. In contrast, by analyzing the characteristics of the noise, a circular arc extraction method based on improved Hough transform is adopted.
When the arc is extracted, a horizontal scanning method is used for scanning the image. Among them, the angular resolution decreases as the distance from the sonar head increases. The angular resolution is obtained as follows:
the figure 3 in fig. 2 is the extracted arc noise.
Directly rejecting the arc noise based on the threshold segmentation may lose the target characteristics, and in the threshold segmentation, the target may be segmented into a plurality of small blocks due to the inconsistency of the target reflection intensity, as shown in fig. 2, No. 4. Therefore, target enhancement is required.
And (3) performing target enhancement by adopting a method of a fused radial compensation method and a clustering method.
The radial compensation method analyzes and utilizes the characteristics of 'trailing' and 'shadow' in target imaging, scans sequentially from left to right along the radial direction of the sector, and reserves pixel points meeting the width.
It should be noted that, when scanning and the resolution takes 0.001 radian, better results of the comprehensive time overhead and compensation effect can be obtained. Better enhancement results are obtained when 7 pixels are selected for the target pixel width.
The clustering method is to analyze the region of interest blocks of the image and take the distance as the evaluation index of the similarity.
Note that, for example, the pixel value of the pixel point P1 is (x)1,y1) The pixel value of the pixel point P2 is (x)2,y2) Then distance
Wherein x is the column where the pixel is located, and y is the row where the pixel is located.
It should be further noted that when the inter-region-of-interest block distance d is smaller than 4 pixels, the two regions of interest are considered as the same object to be segmented and are connected. And finally, filtering and enhancing the region of interest by sequentially utilizing a morphological open operation method and a morphological close operation method to finally obtain a final target region. The diagram No. 5 in fig. 2 is the finally extracted region of interest, and the diagram No. 6 in fig. 2 is the display of the target in the original image.
A computer-readable storage medium having stored thereon computer instructions which, when executed on a computer, cause the computer to perform the method of fig. 1.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Those skilled in the art will appreciate that those matters not described in detail in the present specification are well known in the art.
Claims (10)
1. A2D foresight sonar image denoising method is characterized by comprising the following steps:
obtaining a sonar image from a forward looking sonar in real time, carrying out primary segmentation by adopting a threshold method, then segmenting noise according to noise characteristics to obtain a noise image, then enhancing target display according to target characteristics, and finally fusing the primary segmentation, the noise segmentation and the target enhancement image to obtain a final region of interest.
2. The 2D forward-looking sonar image denoising method according to claim 1, comprising: the threshold method adopts a global self-adaptive threshold segmentation algorithm based on histogram statistical characteristics.
3. The 2D forward-looking sonar image denoising method according to claim 2, comprising: the global adaptive threshold segmentation algorithm based on the histogram statistical characteristics comprises the following steps:
firstly, counting 256 gray scales of 0-255 of an image, and establishing a gray scale histogram;
then, starting to calculate a threshold value;
finally, image traversal is performed with the threshold, with pixels above the threshold set to 255, and otherwise set to 0.
4. The 2D forward-looking sonar image denoising method according to claim 3, comprising: the calculating the threshold value comprises the following steps:
when calculating the threshold, counting the number of pixels from 255 with high brightness to 0 with low brightness, recording the number of pixels as alpha, and continuously recording the gray value delta at the moment;
the reason for moving from 255 to 0 is that in a sonar image, a target often has strong reflection characteristics, and corresponds to a highlight point in the image, and the gray value is high, which is a foreground; the water body has weak reflection characteristics, corresponds to low bright points in the image, has low gray value and is a background;
then, when the counted pixel number α is greater than 500, the gray value δ at this time is found, which is the segmentation threshold.
5. The 2D forward-looking sonar image denoising method according to claim 1, comprising: the method for segmenting the noise according to the noise characteristics is an improved Hough transform-based arc extraction method; when the arc is extracted in the improved Hough transform-based arc extraction method, a transverse scanning method is adopted for scanning the image.
6. The 2D forward-looking sonar image denoising method according to claim 5, comprising: in the transverse scanning method adopted for scanning the image, the method for acquiring the angular resolution is
Where deg is the angular resolution, r is the pixel distance from the point to the sonar head, and value is the value of the angular resolution deg.
7. The 2D forward-looking sonar image denoising method according to claim 1, comprising: the method for enhancing the target display is a method of a fused radial compensation method and a clustering method; wherein
The radial compensation method is characterized in that the trailing and shadow characteristics in target imaging are utilized, scanning is performed sequentially from left to right along the radial direction of a sector, and pixel points meeting the width are reserved;
the clustering method is to analyze the region of interest blocks of the image and take the distance as the evaluation index of the similarity.
8. The 2D forward-looking sonar image denoising method according to claim 7, comprising: in the radial compensation method, the resolution is 0.001 radian during scanning.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
10. A 2D forward-looking sonar image denoising device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: the processor, when executing the computer program, performs the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111437098.3A CN114187195A (en) | 2021-11-29 | 2021-11-29 | 2D (two-dimensional) forward-looking sonar image denoising method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111437098.3A CN114187195A (en) | 2021-11-29 | 2021-11-29 | 2D (two-dimensional) forward-looking sonar image denoising method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114187195A true CN114187195A (en) | 2022-03-15 |
Family
ID=80602936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111437098.3A Pending CN114187195A (en) | 2021-11-29 | 2021-11-29 | 2D (two-dimensional) forward-looking sonar image denoising method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114187195A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782464A (en) * | 2022-04-07 | 2022-07-22 | 中国人民解放军国防科技大学 | Reflection chromatography laser radar image segmentation method based on local enhancement of target region |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100485593B1 (en) * | 2004-08-11 | 2005-04-27 | (주) 넥스트칩 | A method for processing consecutive image input and a system thereof |
| CN110852959A (en) * | 2019-10-14 | 2020-02-28 | 江苏帝一集团有限公司 | Sonar image filtering method based on novel median filtering algorithm |
| CN111626966A (en) * | 2020-07-07 | 2020-09-04 | 哈尔滨工程大学 | Sonar image denoising model training method and device and readable storage medium thereof |
| CN112164079A (en) * | 2020-09-29 | 2021-01-01 | 东北电力大学 | Sonar image segmentation method |
| WO2021142996A1 (en) * | 2020-01-13 | 2021-07-22 | 五邑大学 | Point cloud denoising method, system, and device employing image segmentation, and storage medium |
-
2021
- 2021-11-29 CN CN202111437098.3A patent/CN114187195A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100485593B1 (en) * | 2004-08-11 | 2005-04-27 | (주) 넥스트칩 | A method for processing consecutive image input and a system thereof |
| CN110852959A (en) * | 2019-10-14 | 2020-02-28 | 江苏帝一集团有限公司 | Sonar image filtering method based on novel median filtering algorithm |
| WO2021142996A1 (en) * | 2020-01-13 | 2021-07-22 | 五邑大学 | Point cloud denoising method, system, and device employing image segmentation, and storage medium |
| CN111626966A (en) * | 2020-07-07 | 2020-09-04 | 哈尔滨工程大学 | Sonar image denoising model training method and device and readable storage medium thereof |
| CN112164079A (en) * | 2020-09-29 | 2021-01-01 | 东北电力大学 | Sonar image segmentation method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782464A (en) * | 2022-04-07 | 2022-07-22 | 中国人民解放军国防科技大学 | Reflection chromatography laser radar image segmentation method based on local enhancement of target region |
| CN114782464B (en) * | 2022-04-07 | 2023-04-07 | 中国人民解放军国防科技大学 | Reflection chromatography laser radar image segmentation method based on local enhancement of target region |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113781402B (en) | Method and device for detecting scratch defects on chip surface and computer equipment | |
| WO2018068599A1 (en) | Image processing method and system for gene sequencing | |
| CN104794721B (en) | A kind of quick optic disk localization method based on multiple dimensioned spot detection | |
| CN108229342B (en) | Automatic sea surface ship target detection method | |
| CN103839248B (en) | Image partition method and device | |
| CN112528868A (en) | Illegal line pressing judgment method based on improved Canny edge detection algorithm | |
| CN115147710A (en) | Sonar image target processing method based on heterogeneous filtering detection and level set segmentation | |
| CN105913425B (en) | A kind of more pig contour extraction methods based on adaptive oval piecemeal and wavelet transformation | |
| CN112258542A (en) | Infrared image target detection method and device, electronic equipment and storage medium | |
| CN116152115B (en) | Garbage image denoising processing method based on computer vision | |
| CN112164079A (en) | Sonar image segmentation method | |
| CN112529853A (en) | Method and device for detecting damage of netting of underwater aquaculture net cage | |
| WO2021056501A1 (en) | Feature point extraction method, movable platform and storage medium | |
| CN114187195A (en) | 2D (two-dimensional) forward-looking sonar image denoising method | |
| CN113205494B (en) | Infrared small target detection method and system based on adaptive scale image block weighting difference measurement | |
| CN107239761B (en) | Fruit tree branch pulling effect evaluation method based on skeleton angular point detection | |
| CN113538500A (en) | Image segmentation method and device, electronic equipment and storage medium | |
| CN117372827A (en) | Sonar image statistics enhancement algorithm based on boundary constraint | |
| CN111192280B (en) | Method for detecting optic disc edge based on local feature | |
| CN116128916B (en) | Infrared dim target enhancement method based on spatial energy flow contrast | |
| CN105740796B (en) | Lane line image binaryzation method after a kind of perspective transform based on grey level histogram | |
| CN117115193A (en) | Infrared ship positioning method based on line inhibition | |
| CN111178111A (en) | Two-dimensional code detection method, electronic device, storage medium and system | |
| CN113379639B (en) | Anti-interference detection tracking method for infrared target in complex environment | |
| CN113505811A (en) | Machine vision imaging method for hub production |
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 |