CN114061693A - Method for identifying water surface line by means of water gauge - Google Patents
Method for identifying water surface line by means of water gauge Download PDFInfo
- Publication number
- CN114061693A CN114061693A CN202111323116.5A CN202111323116A CN114061693A CN 114061693 A CN114061693 A CN 114061693A CN 202111323116 A CN202111323116 A CN 202111323116A CN 114061693 A CN114061693 A CN 114061693A
- Authority
- CN
- China
- Prior art keywords
- water
- water gauge
- line
- gauge
- picture
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 188
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000009286 beneficial effect Effects 0.000 abstract description 5
- 238000005520 cutting process Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
- G01F23/04—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm by dip members, e.g. dip-sticks
Landscapes
- Physics & Mathematics (AREA)
- Fluid Mechanics (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method for identifying a water surface line by depending on a water gauge, which has the basic principle that pictures of the water gauge and a standard water gauge in a picture are compared line by line, the position of the water surface is determined by a line-by-line similarity combined probability statistics method, the similarity between the part above the water surface of the water gauge and the standard water gauge is high, the similarity between the part below the water surface of the water gauge and the standard water gauge is low, and the method is used as a basis for identifying the water surface according to the method and is combined with the reading of the water levels at the top end and the bottom end of the calibrated water gauge to calculate the water level corresponding to the water surface. Different from the traditional water level acquisition technology, the original data acquired by equipment such as a radar water level gauge, a bubble water level gauge and the like cannot be interpreted visually, the method can directly mark the identified water level on a picture, the original data can be interpreted visually, and the method is beneficial to improving the precision of data results.
Description
Technical Field
The invention is applied to the field of video water level identification, and relates to a method for identifying a water surface line by means of a water gauge.
Background
In traditional water level collection, radar wave frequency is directly returned by radar water level gauge equipment, air pressure is directly returned by the bubble water level gauge, data such as air pressure and frequency cannot be directly connected with the water level, the equipment needs to be converted to a certain degree to obtain the water level, the air pressure and the frequency cannot be interpreted for an ordinary user, the user can only adopt a final result after the equipment is converted, and the result is correct or not cannot be checked.
Compared with the traditional water level identification, the water level line is identified through the image, the water level is further converted, the identified water level can be calibrated on the picture in the identification algorithm, the picture with the water level line is calibrated as the original data, and the accuracy of the numerical value can be judged.
Therefore, it is significant to rely on the water gauge to identify the water surface line and mark the water surface line on the picture.
Disclosure of Invention
The method for identifying the water surface line by depending on the water gauge has the basic principle that the water gauge pictures in the picture and the standard water gauge pictures are compared line by line, the position of the water surface is determined by combining line-by-line similarity with probability statistics, the identified water surface line is directly marked on the pictures by depending on the method, and the pictures are used as original data, so that the method can be used for observing and reading the accuracy of the data and is beneficial to improving the precision of data results.
In order to achieve the above object, the technical solution provided by the present invention is as follows:
1. the water gauge is fixedly installed in water, a camera is installed on a vertical rod on the water side, the camera fixedly shoots the water gauge in the river, and the relative positions of the water gauge and the water surface on a shot picture are relatively fixed.
In actual use, the water gauge is arranged at a position close to the bank of a river channel or a reservoir, and the camera is arranged on the upright post at the bank.
In actual use, the standard water gauge picture is selected from the series of pictures and is obtained by cutting, and the cut picture only contains the water gauge part.
In practical use, a template file is usually required to be made for each water gauge, and the template file comprises information of a picture of a standard water gauge, the position and the size of the picture of the standard water gauge in the picture, and the like.
In practical use, before picture comparison, the offset of the water gauge picture is also corrected, and the process usually includes taking a small block from the standard water gauge, taking the block to perform comparison search near the corresponding position in the target picture, and regarding the position with the highest pixel matching degree as the real position of the water gauge in the picture.
2. The water gauge and the water surface are relatively fixed in relative positions on the shot pictures, the camera is required to be fixedly installed, when each picture is shot, the position of the camera is fixed, the height of the camera is fixed when a lens in the camera irradiates the water gauge, the inclination angle is fixed, the rotation angle is fixed, the focal length is fixed, and the zoom magnification is fixed.
In practical use, certain requirements are also set on the pixels of the picture, and the width of the water gauge pixels in the picture is preferably larger than 70.
3. The standard water gauge picture is selected from a series of pictures shot by the camera, and when the standard water gauge picture is selected, pictures in a dry season need to be selected as much as possible, so that the water gauge is ensured to be exposed on the water surface in a large number.
4. And counting the similarity line by line, namely performing black-and-white single-valued processing on the water gauge picture and the standard water gauge picture in advance, wherein the similarity is determined when the same pixel points of the water gauge picture and the standard water gauge picture are black or white at the same time, otherwise, the similarity is not similar, and counting the similarity line by line, wherein the similarity is counted from top to bottom or from bottom to top one by one when the percentage of similarity of each line is greater than a given line similarity threshold value.
In practical work, the standard water gauge is stored in a template file after being subjected to black and white single-valued processing, and fig. 2 is a water gauge picture subjected to black and white single-valued processing; the method includes the steps of conducting comparison and analysis on a black and white single-valued water gauge picture and a black and white single-valued stored standard water gauge.
Preferably, the comparison line by line shows that the similar threshold value is between 0.5 and 0.6, namely the line is similar, the line similar threshold value is stored in the template file in the actual work, and different threshold values can be set for different water gauges.
5 the continuous similar units are formed by similar rows from top to bottom or from bottom to top, a plurality of continuous similar units can be arranged in one photo, and the continuous similar units are distributed in the photo from top to bottom and are not mutually covered or overlapped.
In practice, successive similar units are deemed to be above the water surface after a certain height. Preferably a continuous cell height greater than 40 pixels can be considered above the water surface.
Like fig. 3, five similar units have a simple structure, the height of the similar unit on the water part is 421 pixels, and the rest of the similar units below 20 pixels are underwater parts.
In practice, the identification of the continuous similar units needs to consider some abnormal situations, for example, 1-2 pixels are suddenly different in height and can be ignored.
In actual work, the line similarity is a ratio, and the ratio is the number of similar pixels/standard water gauge width, namely the line similarity is between 0 and 1.
As shown in fig. 2, lines are drawn according to the line-by-line similarity, lines with high phase speed are long, lines with low similarity are short, lines are similar threshold lines, namely lines exceeding the threshold lines, and lines on the right side are drawn as similar lines.
6 the lowest pixel of the last continuous similar unit is the water line.
The invention has the advantages that:
the method for identifying the water surface line by depending on the water gauge has the basic principle that the water gauge pictures in the picture and the standard water gauge pictures are compared line by line, the position of the water surface is determined by combining line-by-line similarity with probability statistics, the identified water surface line is directly marked on the pictures by depending on the method, and the pictures are used as original data, so that the method can be used for observing and reading the accuracy of the data and is beneficial to improving the precision of data results.
Drawings
FIG. 1: and (5) a water line identification result.
FIG. 2: water line recognition schematic diagram.
FIG. 3: and comparing the images with similar units.
Detailed Description
The method for identifying the water surface line by depending on the water gauge has the basic principle that the water gauge pictures in the picture and the standard water gauge pictures are compared line by line, the position of the water surface is determined by combining line-by-line similarity with probability statistics, the identified water surface line is directly marked on the pictures by depending on the method, and the pictures are used as original data, so that the method can be used for observing and reading the accuracy of the data and is beneficial to improving the precision of data results.
In order to achieve the above object, the technical solution provided by the present invention is as follows:
1. the water gauge is fixedly installed in water, a camera is installed on a vertical rod on the water side, the camera fixedly shoots the water gauge in the river, and the relative positions of the water gauge and the water surface on a shot picture are relatively fixed.
In actual use, the water gauge is arranged at a position close to the bank of a river channel or a reservoir, and the camera is arranged on the upright post at the bank.
In actual use, the standard water gauge picture is selected from the series of pictures and is obtained by cutting, and the cut picture only contains the water gauge part.
In practical use, a template file is usually required to be made for each water gauge, and the template file comprises information of a picture of a standard water gauge, the position and the size of the picture of the standard water gauge in the picture, and the like.
In practical use, before picture comparison, the offset of the water gauge in the picture is also corrected, in the process, a small block is taken out from the standard water gauge, the block is taken out to be compared and searched near the corresponding position in the target picture, namely whether pixels are matched one by one is consistent or not, a similarity ratio is further obtained, and the position with the highest pixel matching degree is regarded as the real position of the water gauge in the picture.
In specific implementation, the water gauge stored in the template file is vertical, and is cut and stored after being rotated, and in comparison, the picture also needs to be rotated, cut and compared, and the rotation angle, the cutting position and the size of the picture are stored in the template file.
In specific implementation, the picture of the final calibration water line is also rotated.
In specific implementation, a specific software tool needs to be customized, and the storage and the production of various parameters required in the template file are assisted in a man-machine exchange mode.
When the method is specifically implemented, the template also stores water level values corresponding to the top end and the low end of the water gauge, after the water surface line is identified, the water level value corresponding to the water surface line can be calculated by combining the water level values of the top end and the low end of the water gauge, and the water level can be calibrated on the original picture besides the water surface line.
Preferably, during equipment fixing, the camera is 20 meters away from the water gauge, and the camera is preferably 3-4 meters away from the water surface.
In specific implementation, the camera can be a gun camera fixedly installed; or a ball machine capable of setting a preset point.
When the water gauge is specifically implemented, the water gauge needs to be regularly checked not to hang grass and be shielded by plants, the scale of the water gauge is not red, and the effect of the red water gauge on pictures at night is poor.
2. The water gauge and the water surface are relatively fixed in relative positions on the shot pictures, the camera is required to be fixedly installed, when each picture is shot, the position of the camera is fixed, the height of the camera is fixed when a lens in the camera irradiates the water gauge, the inclination angle is fixed, the rotation angle is fixed, the focal length is fixed, and the zoom magnification is fixed.
In practical use, certain requirements are also set on the pixels of the picture, and the width of the water gauge pixels in the picture is preferably larger than 70.
Preferably, the pixel size of the picture is 1920 × 1080.
3. The standard water gauge picture is selected from a series of pictures shot by the camera, and when the standard water gauge picture is selected, pictures in a dry season need to be selected as much as possible, so that the water gauge is ensured to be exposed on the water surface in a large number.
4. And counting the similarity line by line, namely performing black-and-white single-valued processing on the water gauge picture and the standard water gauge picture in advance, wherein the similarity is determined when the same pixel points of the water gauge picture and the standard water gauge picture are black or white at the same time, otherwise, the similarity is not similar, and counting the similarity line by line, wherein the similarity is counted from top to bottom or from bottom to top one by one when the percentage of similarity of each line is greater than a given line similarity threshold value.
In practical work, the standard water gauge is stored in a template file after being subjected to black and white single-valued processing, and fig. 2 is a water gauge picture subjected to black and white single-valued processing; the method includes the steps of conducting comparison and analysis on a black and white single-valued water gauge picture and a black and white single-valued stored standard water gauge.
Preferably, the comparison line by line shows that the similar threshold value is between 0.5 and 0.6, namely the line is similar, the line similar threshold value is stored in the template file in the actual work, and different threshold values can be set for different water gauges.
5 the continuous similar units are formed by similar rows from top to bottom or from bottom to top, a plurality of continuous similar units can be arranged in one photo, and the continuous similar units are distributed in the photo from top to bottom and are not mutually covered or overlapped.
In practice, successive similar units are deemed to be above the water surface after a certain height. Preferably, consecutive similar units having a height greater than 40 pixels are considered to be above the water surface.
Like fig. 3, five similar units have a simple structure, the height of the similar unit on the water part is 421 pixels, and the rest of the similar units below 20 pixels are underwater parts.
In practice, the identification of the continuous similar units needs to consider some abnormal situations, for example, 1-2 pixels are suddenly different in height and can be ignored.
In actual work, the line similarity is a ratio, and the ratio is the number of similar pixels/standard water gauge width, namely the line similarity is between 0 and 1.
As shown in fig. 2, lines are drawn according to the line-by-line similarity, lines with high phase speed are long, lines with low similarity are short, lines are similar threshold lines, namely lines exceeding the threshold lines, and lines on the right side are drawn as similar lines.
6 the lowest pixel of the last continuous similar unit is the water line.
During specific implementation, the underwater part can be preferentially determined through continuous dissimilarity, and then the water surface line is determined.
The invention has the advantages that:
the method for identifying the water surface line by depending on the water gauge has the basic principle that the water gauge pictures in the picture and the standard water gauge pictures are compared line by line, the position of the water surface is determined by combining line-by-line similarity with probability statistics, the identified water surface line is directly marked on the pictures by depending on the method, and the pictures are used as original data, so that the method can be used for observing and reading the accuracy of the data and is beneficial to improving the precision of data results.
Claims (6)
1. The method for identifying the water surface line by depending on the water gauge is characterized in that: the method comprises the steps of fixedly installing a water gauge in water, installing a camera on a vertical rod at the water edge, fixedly shooting a river water gauge by the camera, and relatively fixing the relative positions of the water gauge and the water surface on a shot picture.
2. The method for identifying the water surface line by the water gauge as claimed in claim 1 is characterized in that: the relative positions of the water gauge and the water surface on the shot pictures are relatively fixed, the camera is required to be fixedly installed, when each picture is shot, the position of the camera is fixed, the height of the camera is fixed when the lens in the camera irradiates the water gauge, the inclination angle is fixed, the rotating angle is fixed, the focal length is fixed, and the zoom magnification is fixed.
3. The method for identifying the water surface line by the water gauge as claimed in claim 1 is characterized in that: the standard water gauge picture is selected from a series of pictures shot by the camera, and when the standard water gauge picture is selected, pictures in a dry season need to be selected as much as possible, so that the water gauge is ensured to be exposed on the water surface in a large number.
4. The method for identifying the water surface line by the water gauge as claimed in claim 1 is characterized in that: and counting the similarity line by line, namely performing black-and-white single-valued processing on the water gauge picture and the standard water gauge picture in advance, wherein the similarity is determined when the same pixel points of the water gauge picture and the standard water gauge picture are black or white at the same time, otherwise, the similarity is not similar, and counting the similarity line by line, wherein the similarity is counted from top to bottom or from bottom to top one by one when the percentage of similarity of each line is greater than a given line similarity threshold value.
5. The method for identifying the water surface line by the water gauge as claimed in claim 1 is characterized in that: the continuous similar units are formed by similar rows from top to bottom or from bottom to top, a plurality of continuous similar units can be arranged in one photo, and the continuous similar units are distributed in the photo from top to bottom and are not mutually covered or overlapped.
6. The method for identifying the water surface line by the water gauge as claimed in claim 1 is characterized in that: and the lowest pixel position of the last continuous similar unit is the water surface line.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111323116.5A CN114061693A (en) | 2021-11-09 | 2021-11-09 | Method for identifying water surface line by means of water gauge |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111323116.5A CN114061693A (en) | 2021-11-09 | 2021-11-09 | Method for identifying water surface line by means of water gauge |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114061693A true CN114061693A (en) | 2022-02-18 |
Family
ID=80274381
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111323116.5A Pending CN114061693A (en) | 2021-11-09 | 2021-11-09 | Method for identifying water surface line by means of water gauge |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114061693A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105046212A (en) * | 2015-06-30 | 2015-11-11 | 浙江海洋学院 | Method for automatically identifying waterline scale |
CN108759973A (en) * | 2018-04-28 | 2018-11-06 | 南京昊控软件技术有限公司 | A kind of water level measurement method |
-
2021
- 2021-11-09 CN CN202111323116.5A patent/CN114061693A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105046212A (en) * | 2015-06-30 | 2015-11-11 | 浙江海洋学院 | Method for automatically identifying waterline scale |
CN108759973A (en) * | 2018-04-28 | 2018-11-06 | 南京昊控软件技术有限公司 | A kind of water level measurement method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107609557B (en) | Pointer instrument reading identification method | |
CN111255636B (en) | Method and device for determining tower clearance of wind generating set | |
CN106778823B (en) | Automatic identification method for reading of pointer instrument | |
CN109919975B (en) | Wide-area monitoring moving target association method based on coordinate calibration | |
CN107392929B (en) | Intelligent target detection and size measurement method based on human eye vision model | |
CN111369495B (en) | Panoramic image change detection method based on video | |
CN112818988A (en) | Automatic reading identification method and system for pointer instrument | |
CN111612846A (en) | Concrete crack width measuring method based on U-net CNN image recognition and pixel calibration | |
CN111832760B (en) | Automatic inspection method for well lid based on visual algorithm | |
CN108320310B (en) | Image sequence-based space target three-dimensional attitude estimation method | |
CN113269671A (en) | Bridge apparent panorama generation method based on local and global features | |
CN112132900A (en) | Visual repositioning method and system | |
CN115854895A (en) | Non-contact stumpage breast diameter measurement method based on target stumpage form | |
CN115886792A (en) | Livestock intelligent body size measuring method, system and device | |
CN114708208A (en) | Famous tea tender shoot identification and picking point positioning method based on machine vision | |
CN117095246A (en) | Polarization imaging-based deep learning pointer instrument reading identification method | |
CN111627059A (en) | Method for positioning center point position of cotton blade | |
CN116883483A (en) | Fish body measuring method based on laser camera system | |
CN114061693A (en) | Method for identifying water surface line by means of water gauge | |
CN111797832A (en) | Automatic generation method and system of image interesting region and image processing method | |
CN114283081B (en) | Depth recovery method based on pyramid acceleration, electronic device and storage medium | |
CN112991342B (en) | Water level line detection method, device and system based on water level gauge image | |
CN113065503B (en) | Seedling line identification method and device based on monocular camera and agricultural machinery | |
CN113971799A (en) | Vehicle nameplate information position detection method and system | |
CN112991372B (en) | 2D-3D camera external parameter calibration method based on polygon matching |
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 |