CN111738208A - Method for extracting tracks in meteorological self-recording paper - Google Patents
Method for extracting tracks in meteorological self-recording paper Download PDFInfo
- Publication number
- CN111738208A CN111738208A CN202010683402.1A CN202010683402A CN111738208A CN 111738208 A CN111738208 A CN 111738208A CN 202010683402 A CN202010683402 A CN 202010683402A CN 111738208 A CN111738208 A CN 111738208A
- Authority
- CN
- China
- Prior art keywords
- recording paper
- data
- precipitation
- self
- axis direction
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method for extracting a track in weather self-recording paper, which comprises traversing a scanning picture set of a weather self-recording paper file, and carrying out image identification and information extraction on an electronic scanning piece of each piece of weather self-recording paper; performing pixel level analysis on specific colors on each weather self-recording paper picture, and extracting precipitation characteristic lines; acquiring precipitation record coordinate information of unit step length from the precipitation characteristic line, and converting the coordinate information into actual precipitation occurrence time and precipitation data; and finally, acquiring a weather self-recording paper track curve corresponding to each weather self-recording paper picture, verifying the weather self-recording paper track curve with the original picture, and recording the adjusted data into a warehouse. The invention can extract the precipitation minute-by-minute data before the automatic station and connect with the precipitation minute-by-minute data after the automatic station.
Description
Technical Field
The invention relates to the technical field of meteorological self-recording paper, in particular to a method for extracting a track in meteorological self-recording paper.
Background
Aiming at historical meteorological self-recording paper data before 2003, survey data of the equipment is not electronically stored directly through informatization equipment, but a curve is directly and physically drawn on the meteorological self-recording paper by observation equipment, in order to facilitate subsequent trial review of the historical meteorological observation data, the historical meteorological self-recording paper is scanned by a high-speed scanner and converted into pictures named in a format of site + time range + type, the pictures are uniformly stored in the storage equipment, the pictures of the meteorological data-contained self-recording paper for consulting the historical date are called when necessary, and the pictures are read and viewed manually. According to the technical scheme, the consulting efficiency is low, the time for reading the artificial data is increased, and the capabilities of deep mining, statistical analysis and the like based on the data cannot be realized.
Disclosure of Invention
The object of the present invention is to solve at least one of the technical drawbacks mentioned.
Therefore, the invention aims to provide a method for extracting the track in the weather self-recording paper, which can extract the minute-by-minute data of the precipitation before the automatic station and connect the minute-by-minute data of the precipitation after the automatic station.
In order to achieve the above object, the present invention provides a method for extracting a track from meteorological self-recording paper, comprising the following steps:
step S1, traversing the scanning picture set of the weather self-recording paper file, and carrying out image identification and information extraction on the electronic scanning piece of each piece of weather self-recording paper;
step S2, performing pixel level analysis on the specific color on each weather self-recording paper picture, and extracting precipitation characteristic lines;
step S3, acquiring precipitation record coordinate information of unit step length from the precipitation characteristic line, and converting the coordinate information into actual precipitation occurrence time and precipitation data;
identifying a plurality of continuous curves without precipitation from the data dot matrix, and temporarily transferring data of the curves without precipitation to another data set; then judging the peripheral continuity of the data, removing independent scattered discontinuous stains, carrying out unique data line processing, supplementing missing data and smoothing a curve;
and step S4, finally, acquiring a weather self-recording paper track curve corresponding to each weather self-recording paper picture, verifying the weather self-recording paper track curve with the original image, and recording the adjusted data into a warehouse.
In any of the above embodiments, in step S1, the weather self-recording paper file at least includes a ground wind direction and wind speed self-recording paper, a ground temperature self-recording paper, a ground humidity self-recording paper, and a ground air pressure self-recording paper.
In any of the above-described embodiments, it is preferable that, in step S1, when the image recognition and the information extraction are performed, the site, the type, and the recording time information are recognized by the image file name rule.
In any of the above schemes, preferably, in step S2, the specific steps of performing the pixel level analysis are as follows:
traversing image pixels, converting the color of each pixel point into HLS color space, comparing according to the HLS characteristic range of the color of the curve on the image, extracting a suspected curve from an image pixel matrix, and recording to a new pixel matrix by adopting a 0|1 binarization method.
In any of the above embodiments, in step S3, it is preferable that the gradient in the Y-axis direction is checked along the X-axis direction to determine whether there is a precipitation-free straight line, and if so, a plurality of precipitation-free straight lines are identified and recorded in the data set, and the straight lines are overflowed from the pixel matrix; if not, the impurities are judged and removed by checking whether the isolated dot matrix exists.
In any of the above aspects, it is preferable that the specific procedure of checking the gradient in the Y-axis direction along the X-axis direction is:
firstly, traversing the binary data matrix (X1, X2.. Xn) along the X-axis direction, then traversing the similar points with the distance not exceeding m pixels in the pixel points ((Xn, Y1), (Xn, Y2). (Xn, Yn)) along the Y-axis direction for a certain Xn, calculating the average value of the Y-axis direction, and converting the dense pixel set adjacent to the Y-axis direction into a numerical value point.
In any of the above embodiments, it is preferable that the specific steps of removing the discrete scattered discontinuous stains are as follows:
and m is the check length of the maximum stain range, traversing the binary data matrix (X1, X2.. Xn) along the X-axis direction, traversing the pixel points along the Y-axis direction, aiming at the point (Xn, Yn), traversing the points in the m pixel distance range of four quadrants around the point, if the point distance range boundary in the area range exceeds n pixels and n is less than m, considering the stain as the stain and removing the stain.
In any of the above schemes, preferably, the specific steps of supplementing missing data and smoothing the curve are: traversing the binary data matrix along the X-axis direction, if finding that a certain Xn has no data in the Y-axis direction, calculating the data of the Xn in the Y direction according to the previous data point (Xa, Ya) and the next data point (Xb, Yb), Yn = Ya + (Yb-Ya)/(Xb-Xa) × (Xn-Xa), and finally completing the curve.
In any of the above schemes, preferably, after supplementing missing data and smoothing a curve, a meteorological value at each moment is calculated in proportion, and coordinate information is converted into actual precipitation occurrence time and precipitation data.
In any of the above schemes, preferably, the specific step of converting the coordinate information into the actual precipitation occurrence time and precipitation amount data is:
a binarized data matrix (X1, X2.. Xn) obtained by binarization using 0|1, the lattice range of which is set to (X1, y 1) … (Xn, yn); setting the time range interval of the meteorological self-recording paper as 24 hours, setting the maximum rainfall record value v, setting the total length of pixels in the X-axis direction of a working area in the meteorological self-recording paper as s, setting the total length of pixels in the Y-axis direction as t, and calculating the rainfall amount of m at the moment h according to the unit step length of 1 minute, wherein when 0< = h < =23, 0< = m < =59 minutes;
obtaining pixel coordinates (Xe, Ye) corresponding to the moment of the precipitation characteristic line, wherein Xe = s (h 60 + m)/(24 60); traversing the pixel matrix Xe value in the Y-axis direction, and finding out a coordinate Ye in the Y-axis direction with the value of 1;
the precipitation V (h: m) = V × Ye/t at the time h: m.
The method for extracting the trace in the meteorological self-recording paper has the following beneficial effects:
1. the invention identifies the weather self-recording paper precipitation information picture to achieve digitization and upgrade. The rainfall information recorded by the rainfall self-recording paper is converted into digital rainfall data, and the rainfall minute-by-minute data before the automatic station can be extracted and connected with the rainfall minute-by-minute data after the automatic station.
2. The method is based on the computer image analysis principle, and carries out curve pixel extraction on the self-recording paper scanning image; and then, decontamination and completion processing are carried out on the curve, curve pixel data are converted into actual weather numerical data for conversion, and a document scanning piece of weather self-recording paper is converted into computer data, so that the efficiency of inquiring and researching historical precipitation data at present is improved.
3. The invention ensures that data exist in the range of a time period and can ensure data smoothness and jumping errors through data color extraction, line spotting, extraction of precipitation-free straight line data, removal of small impurities, removal of large interference impurities, line data normalization, line missing part compensation and the like.
4. The invention optimizes the extraction algorithm through image reduction, error control and algorithm optimization, and can carry out all-round statistics, query and overall trend analysis on historical data to provide basic technical conditions.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a principal flow diagram of the present invention;
fig. 2 is a detailed flow chart of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The invention provides a method for extracting a track in meteorological self-recording paper, which comprises the following steps as shown in figures 1-2:
step S1, traversing the scanning picture set of the weather self-recording paper file, and carrying out image identification and information extraction on the electronic scanning piece of each piece of weather self-recording paper;
the method can be expanded to the image recognition and information extraction of electronic scanning pieces of 'ground wind direction and wind speed self-recording paper', 'ground temperature self-recording paper', 'ground humidity self-recording paper' and 'ground air pressure self-recording paper'; and basic technical conditions are provided for extracting and storing all electronic scanning pictures in batches subsequently, and carrying out all-round statistics, query and overall trend analysis on historical data.
When image identification and information extraction are carried out, the information of sites, types and recording time is identified through the image file name rule.
Step S2, performing pixel level analysis on the specific color on each weather self-recording paper picture, and extracting precipitation characteristic lines;
because the curve in the weather self-recording paper is drawn by a weather device in a specific color, and the paper does not have the color, the invention traverses the image pixels, converts the color of each pixel point into HLS (wherein H is Hue of Hue, L is Light brightness, and S is Saturation of Saturration) color space, compares the HLS characteristic range of the color of the curve on the image, extracts a suspected curve from the image pixel matrix, records the suspected curve in a new pixel matrix by adopting a 0|1 binarization method, and generates a binarization data matrix (X1, X2.. Xn), namely after the curve of the specific color is identified, if the curve is a precipitation curve, the suspected curve is represented as 0, if the curve is not a curve, the curve is represented as 1, the background of the paper is removed, and only the curve is reserved.
Step S3, acquiring precipitation record coordinate information of unit step length from the precipitation characteristic line, and converting the coordinate information into actual precipitation occurrence time and precipitation data;
in a first step, a plurality of continuous curves without precipitation are identified from the data lattice, and the data of the curves without precipitation are temporarily transferred to another data set.
Traversing the binary data matrix (X1, X2.. Xn) along the X-axis direction, then traversing pixel points ((Xn, Y1), (Xn, Y2). (Xn, Yn)) along the Y-axis direction for a certain Xn, and generally drawing a line within 24 hours when the equipment originally draws a curve on the meteorological self-recording paper, so that the X-axis is time, the Y-axis is data such as precipitation, the curve length/24 hours/60 minutes of the X-axis is unit step size, and the value in the Y-axis direction is precipitation at the corresponding moment.
The weather self-recording paper is a straight line when recording because the weather self-recording paper does not rain for several days, and the weather self-recording paper can be reused on the next day and the third day. If it rains, the equipment is replaced with a new weather self-recording paper every other day. Therefore, there are 0-n straight lines and 0-1 curves on a weather self-recording paper image.
Therefore, for a certain Xn, when traversing the pixel points ((Xn, Y1), (Xn, Y2). (Xn, Yn)) along the Y-axis direction, a plurality of continuous curves (namely straight lines with the same vertical coordinate) without precipitation are identified from the data lattice, the data of the curves without precipitation are temporarily transferred to another data set, the straight lines are identified and transferred, and the purpose is to better process the curved curves and prevent data interference;
and the average value in the Y-axis direction is obtained from the close points with the distance not more than i pixels, and the dense pixel set adjacent in the Y-axis direction is converted into a numerical value point.
The method specifically comprises the following steps: firstly, traversing the binary data matrix (X1, X2.. Xn) along the X-axis direction, then traversing pixel points of the pixel matrix ((Xn, Y1), (Xn, Y2). (Xn, Yn)) along the Y-axis direction for a certain Xn, finding out a close point (Xn, Ya), (Xn, Yb). (Xn, Yi) with a value of 1 and a distance not exceeding i pixels, and calculating an average value in the Y-axis direction, wherein Y = (Ya, … Yi), and then the value point is (Xn, Sigma (Ya, … Yi)).
And secondly, analyzing the binary data matrix generated above, removing one or more isolated points, and realizing decontamination and interference reduction.
Checking the gradient in the Y-axis direction along the X-axis direction, judging whether straight lines without precipitation are included, if so, identifying a plurality of straight lines without precipitation and recording the straight lines into a data set, and overflowing the straight lines from the pixel matrix; if not, the impurities are judged and removed by checking whether the isolated dot matrix exists.
And setting k as the maximum stain range check length, traversing the binary data matrix (X1, X2.. Xn) along the X-axis direction, traversing the pixel points along the Y-axis direction, aiming at the point (Xn, Yn), traversing the points in the k pixel distance range of four quadrants, namely the front quadrant, the rear quadrant, the left quadrant and the right quadrant of the point, and if the point distance range boundary in the region range exceeds n pixels and n < k, determining that the stain is removed.
And thirdly, completing the missing lines and converting the missing lines into actual meteorological data.
Traversing the binary data matrix along the X-axis direction, if some Xn is found to have no data in the Y-axis direction, calculating the data of the Xn in the Y direction according to the previous data point (Xc, Yc) and the next data point (Xd, Yd), wherein Yn = Yc + (Yd-Yc)/(Xd-Xc) (Xn-Xc), and finally completing the curve.
And calculating the meteorological value of each moment according to the proportion, and converting the coordinate information into actual precipitation occurrence time and precipitation data.
The method specifically comprises the following steps: the matrix of binarized data (X1, X2.. Xn) is based on the 0|1 pixel matrix of the precipitation characteristic line extracted through the previous step, and the range of the included lattice is set to (X1, y 1) … (Xn, yn). Setting the time range interval of the weather self-recording paper as 24 hours (1440 minutes), setting the maximum precipitation record value v, setting the total length of pixels in the X-axis direction of the working area in the weather self-recording paper as s, setting the total length of pixels in the Y-axis direction as t, and then calculating the precipitation amount of m (0 < = m < =59 minutes when 0< = h < = 23) at the time h according to the unit step length of 1 minute:
calculating the pixel coordinate (Xe, Ye) corresponding to the moment of the precipitation characteristic line, wherein Xe = s (h 60 + m)/(24 60), traversing the Xe value of the pixel matrix in the Y-axis direction, and finding the coordinate Ye in the Y-axis direction with the value of 1;
the precipitation V (h: m) = V × Ye/t at the moment h: m;
and step S4, finally, acquiring a weather self-recording paper track curve corresponding to each weather self-recording paper picture, verifying the weather self-recording paper track curve with the original image, and recording the adjusted data into a warehouse.
The method comprises the steps of identifying a plurality of continuous curves without precipitation from a data dot matrix, and temporarily transferring data of the curves without precipitation to another data set; and judging the peripheral continuity of the data, removing independent scattered discontinuous stains, performing unique data line processing, supplementing missing data, smoothing a curve, converting curve pixel data into actual weather numerical data, converting a document scanning piece of weather self-recording paper into computer data, and improving the efficiency of inquiring and researching historical precipitation data at present.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made in the above embodiments by those of ordinary skill in the art without departing from the principle and spirit of the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. A method for extracting tracks in meteorological self-recording paper is characterized by comprising the following steps:
step S1, traversing the scanning picture set of the weather self-recording paper file, and carrying out image identification and information extraction on the electronic scanning piece of each piece of weather self-recording paper;
step S2, performing pixel level analysis on the specific color on each weather self-recording paper picture, and extracting precipitation characteristic lines;
step S3, acquiring precipitation record coordinate information of unit step length from the precipitation characteristic line, and converting the coordinate information into actual precipitation occurrence time and precipitation data;
identifying a plurality of continuous curves without precipitation from the data dot matrix, and temporarily transferring data of the curves without precipitation to another data set; then judging the peripheral continuity of the data, removing independent scattered discontinuous stains, carrying out unique data line processing, supplementing missing data and smoothing a curve;
and step S4, finally, acquiring a weather self-recording paper track curve corresponding to each weather self-recording paper picture, verifying the weather self-recording paper track curve with the original image, and recording the adjusted data into a warehouse.
2. The method for extracting the traces from the weather self-recording paper as claimed in claim 1, wherein in step S1, the weather self-recording paper file includes at least a ground wind direction and wind speed self-recording paper, a ground temperature self-recording paper, a ground humidity self-recording paper, and a ground air pressure self-recording paper.
3. The method for track extraction in weather self-recording paper as claimed in claim 1, wherein in step S1, when image recognition and information extraction are performed, the station, type, recording time information are recognized by image filename rule.
4. The method for extracting the track from the weather self-recording paper as claimed in claim 1, wherein in step S2, the specific steps of performing the pixel-level analysis are as follows:
traversing image pixels, converting the color of each pixel point into HLS color space, comparing according to the HLS characteristic range of the color of the curve on the image, extracting a suspected curve from an image pixel matrix, and recording to a new pixel matrix by adopting a 0|1 binarization method.
5. The method for extracting the track from the weather self-recording paper as claimed in claim 1, wherein in step S3, the gradient in the Y-axis direction is checked along the X-axis direction to determine whether there are any precipitation-free lines, and if so, a plurality of precipitation-free lines are identified and recorded in the data set, and the lines are overflowed from the pixel matrix; if not, the impurities are judged and removed by checking whether the isolated dot matrix exists.
6. The method for extracting the track in the weather self-recording paper as claimed in claim 5, wherein the specific process of checking the gradient in the Y-axis direction along the X-axis direction is as follows:
firstly, traversing the binary data matrix (X1, X2.. Xn) along the X-axis direction, then traversing the similar points with the distance not exceeding m pixels in the pixel points ((Xn, Y1), (Xn, Y2). (Xn, Yn)) along the Y-axis direction for a certain Xn, calculating the average value of the Y-axis direction, and converting the dense pixel set adjacent to the Y-axis direction into a numerical value point.
7. The method for extracting tracks from weather self-recording paper as claimed in claim 6, wherein the specific steps for removing the discrete scattered discontinuous spots are as follows:
and m is the check length of the maximum stain range, traversing the binary data matrix (X1, X2.. Xn) along the X-axis direction, traversing the pixel points along the Y-axis direction, aiming at the point (Xn, Yn), traversing the points in the m pixel distance range of four quadrants around the point, if the point distance range boundary in the area range exceeds n pixels and n is less than m, considering the stain as the stain and removing the stain.
8. The method for extracting the track in the weather self-recording paper as claimed in claim 7, wherein the step of supplementing the missing data and smoothing the curve comprises the following steps: traversing the binary data matrix along the X-axis direction, if finding that a certain Xn has no data in the Y-axis direction, calculating the data of the Xn in the Y direction according to the previous data point (Xa, Ya) and the next data point (Xb, Yb), Yn = Ya + (Yb-Ya)/(Xb-Xa) × (Xn-Xa), and finally completing the curve.
9. The method as claimed in claim 1, wherein the missing data is supplemented and the curve is smoothed, and then the weather value at each time is calculated proportionally, and the coordinate information is converted into actual precipitation occurrence time and precipitation data.
10. The method for extracting the track in the weather self-recording paper as claimed in claim 4, wherein the step of converting the coordinate information into the actual precipitation occurrence time and precipitation data comprises the following steps:
a binarized data matrix (X1, X2.. Xn) obtained by binarization using 0|1, the lattice range of which is set to (X1, y 1) … (Xn, yn); setting the time range interval of the meteorological self-recording paper as 24 hours, setting the maximum rainfall record value v, setting the total length of pixels in the X-axis direction of a working area in the meteorological self-recording paper as s, setting the total length of pixels in the Y-axis direction as t, and calculating the rainfall amount of m at the moment h according to the unit step length of 1 minute, wherein when 0< = h < =23, 0< = m < =59 minutes;
obtaining pixel coordinates (Xe, Ye) corresponding to the moment of the precipitation characteristic line, wherein Xe = s (h 60 + m)/(24 60); traversing the pixel matrix Xe value in the Y-axis direction, and finding out a coordinate Ye in the Y-axis direction with the value of 1;
the precipitation V (h: m) = V × Ye/t at the time h: m.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010683402.1A CN111738208A (en) | 2020-07-16 | 2020-07-16 | Method for extracting tracks in meteorological self-recording paper |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010683402.1A CN111738208A (en) | 2020-07-16 | 2020-07-16 | Method for extracting tracks in meteorological self-recording paper |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111738208A true CN111738208A (en) | 2020-10-02 |
Family
ID=72654707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010683402.1A Pending CN111738208A (en) | 2020-07-16 | 2020-07-16 | Method for extracting tracks in meteorological self-recording paper |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111738208A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113359216A (en) * | 2021-06-03 | 2021-09-07 | 山东捷瑞数字科技股份有限公司 | Method, system and storage medium for identification of recorded data of tipping-bucket rain gauge |
| CN114626458A (en) * | 2022-03-15 | 2022-06-14 | 中科三清科技有限公司 | High-voltage rear part identification method and device, storage medium and terminal |
| CN115409980A (en) * | 2022-09-02 | 2022-11-29 | 重庆众仁科技有限公司 | Method and system for correcting distorted image |
| CN115409825A (en) * | 2022-09-06 | 2022-11-29 | 重庆众仁科技有限公司 | Temperature-humidity pressure trace identification method based on image identification |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106326818A (en) * | 2015-06-30 | 2017-01-11 | 东南大学 | Method and device for digitizing paper hydrological data |
| CN106324708A (en) * | 2015-06-24 | 2017-01-11 | 李士进 | Digitization method and device of rainfall recording paper |
| DE102015218500A1 (en) * | 2015-09-25 | 2017-03-30 | Conti Temic Microelectronic Gmbh | Illumination and camera-based detection of raindrops on a pane |
-
2020
- 2020-07-16 CN CN202010683402.1A patent/CN111738208A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106324708A (en) * | 2015-06-24 | 2017-01-11 | 李士进 | Digitization method and device of rainfall recording paper |
| CN106326818A (en) * | 2015-06-30 | 2017-01-11 | 东南大学 | Method and device for digitizing paper hydrological data |
| DE102015218500A1 (en) * | 2015-09-25 | 2017-03-30 | Conti Temic Microelectronic Gmbh | Illumination and camera-based detection of raindrops on a pane |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113359216A (en) * | 2021-06-03 | 2021-09-07 | 山东捷瑞数字科技股份有限公司 | Method, system and storage medium for identification of recorded data of tipping-bucket rain gauge |
| CN114626458A (en) * | 2022-03-15 | 2022-06-14 | 中科三清科技有限公司 | High-voltage rear part identification method and device, storage medium and terminal |
| CN114626458B (en) * | 2022-03-15 | 2022-10-21 | 中科三清科技有限公司 | High-voltage rear part identification method and device, storage medium and terminal |
| CN115409980A (en) * | 2022-09-02 | 2022-11-29 | 重庆众仁科技有限公司 | Method and system for correcting distorted image |
| CN115409980B (en) * | 2022-09-02 | 2023-12-22 | 重庆众仁科技有限公司 | Distortion image correction method and system |
| CN115409825A (en) * | 2022-09-06 | 2022-11-29 | 重庆众仁科技有限公司 | Temperature-humidity pressure trace identification method based on image identification |
| CN115409825B (en) * | 2022-09-06 | 2023-09-12 | 重庆众仁科技有限公司 | Temperature, humidity and pressure trace identification method based on image identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111738208A (en) | Method for extracting tracks in meteorological self-recording paper | |
| CN108416355B (en) | Industrial field production data acquisition method based on machine vision | |
| KR100902491B1 (en) | System for processing digit image, and method thereof | |
| CN109344820B (en) | Digital ammeter reading identification method based on computer vision and deep learning | |
| US7680339B2 (en) | Image processing method and apparatus for edge detection in an image | |
| CN113989794B (en) | License plate detection and recognition method | |
| CN110363769B (en) | Image segmentation method for cantilever system of high-speed rail contact net supporting device | |
| CN111626145A (en) | Simple and effective incomplete form identification and page-crossing splicing method | |
| CN116168409B (en) | Automatic generation system applied to standard and patent analysis report | |
| CN110502605B (en) | Electric power asset LCC cost collection system based on artificial intelligence technology | |
| CN113393430A (en) | Thermal imaging image enhancement training method and device for fan blade defect detection | |
| CN117333893A (en) | OCR-based custom template image recognition method, system and storage medium | |
| CN114627463B (en) | Non-contact power distribution data identification method based on machine identification | |
| CN115082504B (en) | Light spot identification method for solar photovoltaic panel | |
| CN112907490B (en) | Pixel point extraction method, target information acquisition method and push bench control system | |
| CN116403200A (en) | License plate real-time identification system based on hardware acceleration | |
| CN112634240B (en) | Thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation | |
| CN115620289A (en) | OCR data acquisition method for old machine tool | |
| KR102585146B1 (en) | Pothole detection device and method based on deep learning | |
| CN114299307A (en) | Power transmission line image annotation method and related device | |
| CN114581901A (en) | Method for extracting edges of ancient building wall contaminated inscription character images | |
| CN112801963A (en) | Video image occlusion detection method and system | |
| CN115273108B (en) | Automatic collection method and system for artificial intelligent identification | |
| CN112052859A (en) | License plate accurate positioning method and device in free scene | |
| JP2004094427A (en) | Slip image processor and program for realizing the same device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201002 |