CN108764229A - A kind of water gauge automatic distinguishing method for image based on computer vision technique - Google Patents
A kind of water gauge automatic distinguishing method for image based on computer vision technique Download PDFInfo
- Publication number
- CN108764229A CN108764229A CN201810535364.8A CN201810535364A CN108764229A CN 108764229 A CN108764229 A CN 108764229A CN 201810535364 A CN201810535364 A CN 201810535364A CN 108764229 A CN108764229 A CN 108764229A
- Authority
- CN
- China
- Prior art keywords
- water gauge
- character
- water
- image
- gauge
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/23—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on positionally close patterns or neighbourhood relationships
-
- 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
- G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
-
- 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
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
- G06V30/1478—Inclination or skew detection or correction of characters or of image to be recognised of characters or characters lines
Abstract
The invention discloses a kind of water gauge automatic distinguishing method for image based on computer vision technique, includes the following steps:S1, water gauge character words laws and institutions are made:The standard gauge character that different angle takes is intercepted and does deformation and normalized, as water gauge Character mother plate;The template made under the conditions of same water gauge character different angle, deformation etc. constitutes the template group of the water gauge character;The template group of different water gauge characters constitutes water gauge character dictionary;The present invention reduces influence of the illumination to image color, efficiently solves the problems, such as that water gauge Target Segmentation is difficult under complex background condition, improves the accuracy rate of water gauge and background segment;Character identification rate is improved, for imperfect or water gauge image there are unusual character, effective identification of same achievable character;Water gauge accuracy of reading rate is high, and water level result of calculation worst error meets actual water level monitoring requirements within 4mm.
Description
Technical field
The present invention relates to water level detecting technical fields, and in particular to a kind of water gauge image based on computer vision technique from
Dynamic recognition methods.
Background technology
Existing water gauge is generally adopted by the partitioning algorithm based on edge with background segment method, is such as based on gray level image
The processing such as it is filtered, enhances;Or identify water gauge boundary using hough transformation, this method can remove most of background and
Noise, but the influence of the factors such as segmentation effect is easily illuminated by the light, waterfront line, can not effectively be partitioned into water gauge;
And for the identification of water gauge graduation mark, the existing quarter for extracting water gauge by Projection Analysis, K-means clusterings etc.
Degree line reads to obtain water gauge, and calculating process is simple, effective, but for the complete water gauge image of no shooting or graduation mark
There is damaged water gauge image that cannot then accurately identify.Identification for water gauge character, existing character identifying method have classification and
Matching can solve the problems, such as water gauge character localized loss or number is fuzzy etc. leads to recognition failures to a certain extent.But it makes
The sample-rich degree of work is insufficient, cannot identify that character identification rate is low for the water gauge character picture of non-horizontal shooting;And for
The computational methods of water level mostly use the mathematical relationship of intercharacter, the error of existing water level result of calculation presence ± 1cm to miss
Difference is larger.
It is influenced and is caused by the complex backgrounds such as water wave and waterfront line in conclusion existing water gauge image-recognizing method exists
It is larger that water gauge image is not easy to divide, sample-rich degree deficiency leads to that water gauge character identification rate is not high, water level calculates error.
Invention content
The shortcomings that it is an object of the invention to overcome the prior art with it is insufficient, provide a kind of based on computer vision technique
Water gauge automatic distinguishing method for image, this method can realize that water gauge is effectively divided from background under the complex backgrounds such as water wave, different journeys
Degree tilts effective identification of lower water gauge character and high-precision water level value calculates.
The purpose of the invention is achieved by the following technical solution:
A kind of water gauge automatic distinguishing method for image based on computer vision technique, includes the following steps:
S1, water gauge character words laws and institutions are made:The standard gauge character that different angle takes is intercepted and does deformation and returns
One change is handled, as water gauge Character mother plate;The template made under the conditions of same water gauge character different angle, deformation etc. is constituted
The template group of the character;The template group of different water gauge characters constitutes water gauge character dictionary;
S2 stands water gauge in the waters that need to be detected, and obtains water gauge image by camera, water gauge image is input to meter
Following processing is carried out in calculation machine:
S2.1, computer read water gauge image;
S2.2, background segment:First to the water gauge image of acquisition, i.e. RGB image carries out down-sampling, and will be after down-sampling
Image is converted into HSV images;Then operation is carried out out to HSV images with circular configuration element, extracts water gauge profile and background
Image;The background extracted is subtracted with HSV images;Finally by OSTU Threshold segmentations water gauge and background, and pass through area denoising
Water gauge image peripheral area is less than to the noise remove of predetermined threshold value;
S2.3, water gauge detection:Water gauge edge is detected using Canny operators, is converted to water gauge edge image in conjunction with hough
Carry out straight-line detection;Water gauge bianry image is rotated according to the angle of inclination of the water gauge left and right edges detected;To slant correction
Rear water gauge image carry out it is horizontal projected with vertical direction, according to after projection row pixel and in first value and the last one
Value is all higher than zero point, with row pixel and in first value and the last one value be all higher than zero point, this four point determines
The position at water gauge edge up and down, and be cut into;
S2.4, water gauge Character segmentation:Two big images such as left and right are divided by the center line for the water gauge being cut into,
And floor projection is carried out to left figure, the up-and-down boundary of water gauge character is oriented, water gauge character is gone out according to boundary segmentation and is removed more
Remaining background;The water gauge character boundary being partitioned into is normalized;
S2.5, water gauge character recognition:By the water gauge character split in S2.4 respectively with the water gauge character that is made in S1
Each water gauge Character mother plate group of dictionary is matched, and realizes the automatic identification of water gauge character;Utilize number and character in water gauge
It is character that " E ", which is alternately arranged, left side of the digital corresponds to right sideFeature, correct with check water gauge character recognition result;
S2.6, water level calculate:Each water gauge character " E " orHeight be 5cm, one of peak, that is, black horizontal stripe
Height be 1cm, the distance between paddy i.e. two black horizontal stripes be 1cm;To the practical feelings of water gauge character image in water
Condition is analyzed, and floor projection is carried out at the same time, by the mathematical relationship of intercharacter, according to the peak being projected out, the ratio between paddy
Calculate accurate water gauge reading hc;Water level h is calculated according to water gauge reading3=h1-h2=h1-h+hc, wherein h is that water gauge is long
Degree, hcFor the reading of the height, that is, water gauge of water gauge in water, h2Expose the surface the height of part for water gauge, h1For water gauge peak
To water-bed height;
S3, computer export water level numerical value h3。
Preferably, in the S2.5, specific matching process is:According to following formula (1),
By water gauge character, that is, target character w to be identifiedqWith any character w in Character mother plate groupiIt is matched, is calculated
Similarity Sim (w between the twoq,wi);Wherein m, n respectively represent the line number of character picture matrix, columns,It is to be identified
Water gauge character wqAverage gray,For template character wiAverage gray, i=1,2,3 ... ..., 7;
According to following formula (2),
Sim(wq,Sw)=maxSim (wq,wi), wi∈Sw (2)
With character w to be identifiedqWith Character mother plate group SwInterior each character similarity Sim (wq,wi) maximum value as wqWith
SwSimilarity, be denoted as Sim (wq,Sw);
According to following formula (3),
With character w to be identifiedqWith each Character mother plate group similarity Sim (w in character dictionary Sq,Sw) maximum value conduct
wqWith the similarity of S, it is denoted as Sim (wq,S);
According to following formula (4),
Export character w to be identifiedqWith the matching result Q (w of water gauge character dictionary Sq,S);Wherein r is and wqMost like mould
Character representated by plate character group, W are water gauge character set, and W={ 0,1,2,3,4,5,6,7,8,9, E }, Null indicate wqMatching
It is unsuccessful, None- identified.
Preferably, in the S2.6, water gauge reads hcCalculating process be:
1. if water gauge left side is " E " by the character of water submerged, floor projection is made to the character picture, after projection
Image is in the feature at " peak valley peak valley peak ", then water gauge is read:
Wherein, hcUnit is cm, and m is the value of numerical character minimum in recognition result, l1It exposes the surface part for character
Highly, l2For character " E " orProject the width at the latter peak, l1With l2Ratio be exactly that the character exposes the surface part
Height value (unit cm);
2. if water gauge left side is number by the character of water submerged, intercept on the right side of itIn the same manner into
Row is handled, then water gauge is read:
The present invention has advantageous effect below compared with prior art:
(1) present invention reduces influence of the illumination to image color, efficiently solves the water gauge mesh under complex background condition
The difficult problem of mark segmentation, improves the accuracy rate of water gauge and background segment;
(2) present invention improves character identification rate, for imperfect or water gauge image there are unusual character, equally may be used
Realize effective identification of character;
(3) water gauge accuracy of reading rate of the present invention is high, and water level result of calculation worst error meets actual water level within 4mm
Monitoring requirements.
Description of the drawings
Fig. 1 is the overview flow chart of the present invention;
Fig. 2 is background segment flow chart of the present invention;
Fig. 3 is multi-template matching character recognition algorithm flow chart of the present invention;
Fig. 4 is that water gauge of the present invention reading calculates schematic diagram;
Fig. 5 is the level measuring schematic diagram of the present invention.
Specific implementation mode
Present invention will now be described in further detail with reference to the embodiments and the accompanying drawings, but embodiments of the present invention are unlimited
In this.
The basic principle of the present invention is to obtain water gauge image using camera, is handled and is acquired by digital image processing techniques
The image arrived is read with computer simulation eye recognition water gauge, automatic to read water level numerical value.This method not by water quality, water temperature, contain
The external interferences factors such as sand amount influence, strong applicability.Realize the automatic acquisition of water level, including following three aspects:Water gauge with
Effective segmentation, water gauge character or the effective identification of graduation mark and accurately calculating for water level of background.
As shown in Fig. 1~5, a kind of water gauge automatic distinguishing method for image based on computer vision technique, including following steps
Suddenly:
(1) water gauge character words laws and institutions are made:The standard gauge character that different angle takes is intercepted and does deformation and returns
One change is handled, as water gauge Character mother plate;The template made under the conditions of same water gauge character different angle, deformation etc. is constituted
The template group of the water gauge character;The template group of different water gauge characters constitutes water gauge character dictionary;
(2) water gauge is stood in the waters that need to be detected, water gauge image is obtained by camera, water gauge image is input to meter
Following processing is carried out in calculation machine:
(2.1) computer read water gauge image;
(2.2) background segment:As shown in Fig. 2, first to the water gauge image of acquisition, i.e. RGB image carries out down-sampling, and will
Image after down-sampling is converted into HSV images;Then operation is carried out out to HSV images with circular configuration element, extracts water gauge
Profile and background image;The background extracted is subtracted with HSV images;Finally by OSTU Threshold segmentations water gauge and background, and lead to
Cross the noise remove that water gauge image peripheral area is less than predetermined threshold value by area denoising;
To eliminate water wave, the complex backgrounds such as waterfront line, effectively divide water gauge and background, down-sampling is carried out, by RGB to image
Color space is converted into HSV color spaces, background is extracted with morphological method is enhanced, binaryzation, denoising
Realize water gauge and background segment.
(2.3) water gauge detects:Water gauge edge is detected using Canny operators, is converted to water gauge edge image in conjunction with hough
Carry out straight-line detection;Water gauge bianry image is rotated according to the angle of inclination of the water gauge left and right edges detected;To slant correction
Rear water gauge image carry out it is horizontal projected with vertical direction, according to after projection row pixel and in first value and the last one
Value is all higher than zero point, with row pixel and in first value and the last one value be all higher than zero point, this four point determines
The position at water gauge edge up and down, and be cut into;
(2.4) water gauge Character segmentation:Two big images such as left and right are divided by the center line for the water gauge being cut into,
And floor projection is carried out to left figure, the up-and-down boundary of water gauge character is oriented, water gauge character is gone out according to boundary segmentation and is removed more
Remaining background;The water gauge character boundary being partitioned into is normalized;
(2.5) water gauge character recognition:By the water gauge character split in (2.4) respectively with (1) in make water gauge word
Each water gauge Character mother plate group of symbol dictionary is matched, and realizes the automatic identification of water gauge character;Utilize number and word in water gauge
It is character that symbol " E ", which is alternately arranged, left side of the digital corresponds to right sideFeature, correct with check water gauge character recognition result;
Specifically, as shown in figure 3, multi-template matching water gauge character recognition algorithm:It, will to improve water gauge character identification rate
The standard gauge character that different angle takes intercepts and does normalized, as template to enrich water gauge character
Template;The template that water gauge character w makes in different situations constitutes set Sw, the template set of all water gauge characters, which is constituted, to be gathered
S then has SwIt is contained in S;Specifically matching process is:According to following formula (1),
By water gauge character (i.e. target character) w to be identifiedqWith any character w in Character mother plate groupiIt is matched, is counted
Similarity Sim (w between the twoq,wi);Wherein m, n respectively represent the line number of character picture matrix, columns,To wait knowing
Other water gauge character wqAverage gray,For template character wiAverage gray, i=1,2,3 ... ..., 7;
According to following formula (2),
Sim(wq,Sw)=maxSim (wq,wi), wi∈Sw (2)
With character w to be identifiedqWith Character mother plate group SwInterior each character similarity Sim (wq,wi) maximum value as wqWith
SwSimilarity, be denoted as Sim (wq,Sw);
According to following formula (3),
With character w to be identifiedqWith each Character mother plate group similarity Sim (w in character dictionary Sq,Sw) maximum value conduct
wqWith the similarity of S, it is denoted as Sim (wq,S)。
According to following formula (4),
Export character w to be identifiedqWith the matching result Q (w of water gauge character dictionary Sq,S);Wherein r is and wqMost like mould
Character representated by plate character group, W are water gauge character set, and W={ 0,1,2,3,4,5,6,7,8,9, E }, Null indicate wqMatching
It is unsuccessful, None- identified.
(2.6) water level calculates:Each water gauge character " E " orHeight be 5cm, one of peak, that is, black horizontal stripe
Height be 1cm, the distance between paddy i.e. two black horizontal stripes be 1cm;To the practical feelings of water gauge character image in water
Condition is analyzed, and floor projection is carried out at the same time, by the mathematical relationship of intercharacter, according to the peak being projected out, the ratio between paddy
Calculate accurate water gauge reading hc;
Specifically, as shown in figure 4, the calculating of water level mainly reads h by water gaugecIt obtains, to obtain accurate water gauge
Read hcIt is analyzed it is necessary to the actual conditions to water gauge character image in water:
1. if water gauge left side is " E " by the character of water submerged, floor projection is made to the character picture, after projection
Image is in the feature at " peak valley peak valley peak ", then water gauge is read:
Wherein, hcUnit is cm, and m is the value of numerical character minimum in recognition result, l1It exposes the surface part for character
Highly, l2For character " E " orProject the width at the latter peak, l1With l2Ratio be exactly that the character exposes the surface part
Height value (unit cm);
2. if water gauge left side is number by the character of water submerged, intercept on the right side of itIn the same manner into
Row is handled, then water gauge is read:
As shown in figure 5, calculating water level h according to water gauge reading3=h1-h2=h1-h+hc, wherein h is water gauge length, hc
For the reading of the height, that is, water gauge of water gauge in water, h2Expose the surface the height of part for water gauge, h1For water gauge peak to the bottom
Height and the basin peak level over the years, the data can be obtained by Hydrologic monitoring station;
(3) computer output water level numerical value h3。
The present invention reduces influence of the illumination to image color, efficiently solves the water gauge target point under complex background condition
Difficult problem is cut, the accuracy rate of water gauge and background segment is improved, as shown in table 1 below, dividing method items evaluation of the present invention
It is above the prior art;
1 dividing method performance of table compares
Method | Dice coefficients | IoU | Precision | Recall |
Document [2] method | 0.770 | 0.637 | 0.708 | 0.896 |
Document [3] method | 0.823 | 0.700 | 0.702 | 0.995 |
The method of the present invention | 0.971 | 0.943 | 0.954 | 0.989 |
Note:Water level letters of document [2] Chen Cui, Liu Zhengwei, Chen Xiaosheng, Luo Manna, Niu Zhixing, the Ruan Cong based on image procossing
It ceases and automatically extracts technology [J] Water Conservancy Informations, 2016, (01):48-55;Document [3] Gao Xiaoliang, Wang Zhiliang, Wang Xin, Liu Ji
Video real time water level detection algorithm [J] Zhengzhou University journals (Edition) of the big based on HSV space, 2010,42 (03):75-
79。
The present invention improves character identification rate, equally can be real for imperfect or water gauge image there are unusual character
Effective identification of existing character;
Water gauge accuracy of reading rate of the present invention is high, and water level result of calculation worst error meets actual water level monitoring within 4mm
Demand, as shown in table 2 below:
2 experimental data table of table
Serial number | Angle of inclination/° | Conventional template match cognization rate/% | Experimental identification rate/% | Artificial reading/cm | Test reading/cm | Error/cm |
1 | -5.0 | 57.1 | 100 | 42.1 | 42.1 | 0 |
2 | -3.7 | 71.4 | 100 | 48.5 | 48.9 | +0.4 |
3 | -7.8 | 75.0 | 100 | 49.0 | 48.9 | -0.1 |
4 | -1.5 | 83.3 | 100 | 37.2 | 37.2 | 0 |
5 | -2.7 | 71.4 | 100 | 32.0 | 31.8 | -0.2 |
6 | -1.0 | 85.7 | 100 | 31.9 | 31.9 | 0 |
7 | -4.3 | 62.5 | 100 | 37.8 | 37.8 | 0 |
8 | -4.3 | 87.5 | 100 | 37.5 | 37.5 | 0 |
9 | 1.0 | 75.0 | 100 | 37.6 | 37.6 | 0 |
10 | -1.0 | 71.4 | 100 | 31.9 | 31.9 | 0 |
Mean value | - | 74.0 | 100 | - | - | - |
Above-mentioned is the preferable embodiment of the present invention, but embodiments of the present invention are not limited by the foregoing content,
He it is any without departing from the spirit and principles of the present invention made by changes, modifications, substitutions, combinations, simplifications, should be
The substitute mode of effect, is included within the scope of the present invention.
Claims (3)
1. a kind of water gauge automatic distinguishing method for image based on computer vision technique, which is characterized in that include the following steps:
S1, water gauge character words laws and institutions are made:The standard gauge character that different angle takes is intercepted and does deformation and normalization
Processing, as water gauge Character mother plate;The template made under the conditions of same water gauge character different angle, deformation etc. constitutes the water
The template group of ruler character;The template group of different water gauge characters constitutes water gauge character dictionary;
S2 stands water gauge in the waters that need to be detected, and obtains water gauge image by camera, water gauge image is input to computer
It is handled below middle progress:
S2.1, computer read water gauge image;
S2.2, background segment:First to the water gauge image of acquisition, i.e. RGB image carries out down-sampling, and by the image after down-sampling
It is converted into HSV images;Then operation is carried out out to HSV images with circular configuration element, extracts water gauge profile and background image;
The background extracted is subtracted with HSV images;Finally by OSTU Threshold segmentations water gauge and background, and by area denoising by water gauge
Image peripheral area is less than the noise remove of predetermined threshold value;
S2.3, water gauge detection:Water gauge edge is detected using Canny operators, and water gauge edge image is carried out in conjunction with hough transformation
Straight-line detection;Water gauge bianry image is rotated according to the angle of inclination of the water gauge left and right edges detected;After slant correction
The progress of water gauge image is horizontal to be projected with vertical direction, is worth according to first of the row pixel after projection in and the last one value is equal
Point more than zero, with row pixel and in first value and the last one value be all higher than zero point, this four point determines water gauge
The position at edge up and down, and be cut into;
S2.4, water gauge Character segmentation:Two big images such as left and right are divided by the center line for the water gauge being cut into, and right
Left figure carry out floor projection, orient the up-and-down boundary of water gauge character, according to boundary segmentation go out water gauge character and remove it is extra
Background;The water gauge character boundary being partitioned into is normalized;
S2.5, water gauge character recognition:By the water gauge character split in S2.4 respectively with the water gauge character dictionary that is made in S1
Each water gauge Character mother plate group matched, realize water gauge character automatic identification;It is handed over character " E " using number in water gauge
It is character for arrangement, left side of the digital correspondence right sideFeature, correct with check water gauge character recognition result;
S2.6, water level calculate:Each water gauge character " E " orHeight be 5cm, the height of one of peak, that is, black horizontal stripe
Degree is 1cm, and the distance between paddy i.e. two black horizontal stripes is 1cm;To water gauge character in water image actual conditions into
Row analysis, is carried out at the same time floor projection, by the mathematical relationship of intercharacter, is calculated according to the peak being projected out, the ratio between paddy
Go out accurate water gauge reading hc;Water level h is calculated according to water gauge reading3=h1-h2=h1-h+hc, wherein h is water gauge length, hc
For the reading of the height, that is, water gauge of water gauge in water, h2Expose the surface the height of part for water gauge, h1For water gauge peak to the bottom
Height;
S3, computer export water level numerical value h3。
2. the water gauge automatic distinguishing method for image according to claim 1 based on computer vision technique, which is characterized in that
In the S2.5, specific matching process is:According to following formula (1),
By water gauge character, that is, target character w to be identifiedqWith any character w in Character mother plate groupiBoth it is matched, calculate
Between similarity Sim (wq,wi);Wherein m, n respectively represent the line number of character picture matrix, columns,For water gauge to be identified
Character wqAverage gray,For template character wiAverage gray, i=1,2,3 ... ..., 7;
According to following formula (2),
Sim(wq,Sw)=maxSim (wq,wi), wi∈Sw (2)
With character w to be identifiedqWith Character mother plate group SwInterior each character similarity Sim (wq,wi) maximum value as wqWith Sw's
Similarity is denoted as Sim (wq,Sw);
According to following formula (3),
With character w to be identifiedqWith each Character mother plate group similarity Sim (w in water gauge character dictionary Sq,Sw) maximum value as wq
With the similarity of S, it is denoted as Sim (wq,S);
According to following formula (4),
Export character w to be identifiedqWith the matching result Q (w of water gauge character dictionary Sq,S);Wherein r is and wqMost like template word
Character representated by symbol group, W are water gauge character set, and W={ 0,1,2,3,4,5,6,7,8,9, E }, Null indicate wqMatching not at
Work(, None- identified.
3. the water gauge automatic distinguishing method for image according to claim 1 based on computer vision technique, which is characterized in that
In the S2.6, water gauge reads hcCalculating process be:
1. if water gauge left side is " E " by the character of water submerged, floor projection is made to the character picture, according to the image after projection
In the feature at " peak valley peak valley peak ", then water gauge is read:
Wherein, hcUnit is cm, and m is the value of numerical character minimum in recognition result, l1Expose the surface the height of part for character
Degree, l2For character " E " orProject the width at the latter peak, l1With l2Ratio be exactly that the character exposes the surface the height of part
Angle value (unit cm);
2. if water gauge left side is number by the character of water submerged, intercept on the right side of itLocated in the same manner
It manages, then water gauge is read:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810535364.8A CN108764229B (en) | 2018-05-29 | 2018-05-29 | Water gauge image automatic identification method based on computer vision technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810535364.8A CN108764229B (en) | 2018-05-29 | 2018-05-29 | Water gauge image automatic identification method based on computer vision technology |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108764229A true CN108764229A (en) | 2018-11-06 |
CN108764229B CN108764229B (en) | 2021-05-18 |
Family
ID=64003861
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810535364.8A Active CN108764229B (en) | 2018-05-29 | 2018-05-29 | Water gauge image automatic identification method based on computer vision technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108764229B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109711353A (en) * | 2018-12-28 | 2019-05-03 | 中国矿业大学 | A kind of drauht line area recognizing method based on machine vision |
CN109766886A (en) * | 2019-01-02 | 2019-05-17 | 南京林业大学 | A kind of water level recognition methods based on image recognition |
CN110031060A (en) * | 2019-05-14 | 2019-07-19 | 武汉大学 | The method and application of projective amplification water level measurement accuracy |
CN111626190A (en) * | 2020-05-26 | 2020-09-04 | 浙江大学 | Water level monitoring method for scale recognition based on clustering partitions |
CN111652089A (en) * | 2020-05-18 | 2020-09-11 | 纪义胜 | Water level automatic identification method and system based on image processing |
CN111998910A (en) * | 2020-08-26 | 2020-11-27 | 河海大学 | Visual measurement method and system for water level of multi-stage water gauge |
CN112329644A (en) * | 2020-11-06 | 2021-02-05 | 中冶赛迪重庆信息技术有限公司 | Reservoir water level monitoring method and system, medium and electronic terminal |
CN113221898A (en) * | 2021-04-16 | 2021-08-06 | 北京科技大学 | Automatic water level gauge reading method |
CN113392846A (en) * | 2021-06-16 | 2021-09-14 | 广州观必达数据技术有限责任公司 | Water gauge water level monitoring method and system based on deep learning |
US11443133B2 (en) | 2019-12-10 | 2022-09-13 | Ricoh Company, Ltd. | Computer vision system for industrial equipment gauge digitization and alarms |
CN115546235A (en) * | 2022-11-23 | 2022-12-30 | 成都见海科技有限公司 | Water level identification method and system based on image segmentation and storage medium |
CN115578695A (en) * | 2022-11-21 | 2023-01-06 | 昆明理工大学 | Water gauge water level machine vision detection method and device with free shooting visual angle |
CN116109869A (en) * | 2023-02-20 | 2023-05-12 | 北京科技大学 | Method and device for identifying reservoir water level fluctuation based on water bank image matching |
CN116222693A (en) * | 2023-05-10 | 2023-06-06 | 安徽省(水利部淮河水利委员会)水利科学研究院(安徽省水利工程质量检测中心站) | Natural river channel water level automatic monitoring method based on water gauge reflection |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070242884A1 (en) * | 2001-07-24 | 2007-10-18 | Dugan John P | Method for measuring water depths using visible images of shoaling ocean waves |
CN103487033A (en) * | 2013-09-22 | 2014-01-01 | 河海大学 | River surface photographic surveying method based on height-change homography |
KR20170086773A (en) * | 2016-01-19 | 2017-07-27 | 이현석 | Apparatus for visual water level assessment |
-
2018
- 2018-05-29 CN CN201810535364.8A patent/CN108764229B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070242884A1 (en) * | 2001-07-24 | 2007-10-18 | Dugan John P | Method for measuring water depths using visible images of shoaling ocean waves |
CN103487033A (en) * | 2013-09-22 | 2014-01-01 | 河海大学 | River surface photographic surveying method based on height-change homography |
KR20170086773A (en) * | 2016-01-19 | 2017-07-27 | 이현석 | Apparatus for visual water level assessment |
Non-Patent Citations (2)
Title |
---|
FRANCO LIN等: "《Applications of Image Recognition for Real-Time Water Level and Surface Velocity》", 《 2013 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA》 * |
陈翠 等: "《基于图像处理的水位信息自动提取技术》", 《水利信息化》 * |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109711353A (en) * | 2018-12-28 | 2019-05-03 | 中国矿业大学 | A kind of drauht line area recognizing method based on machine vision |
CN109711353B (en) * | 2018-12-28 | 2023-06-30 | 煤炭科学研究总院有限公司 | Ship waterline area identification method based on machine vision |
CN109766886A (en) * | 2019-01-02 | 2019-05-17 | 南京林业大学 | A kind of water level recognition methods based on image recognition |
CN109766886B (en) * | 2019-01-02 | 2023-04-28 | 南京林业大学 | Water level identification method based on image identification |
CN110031060A (en) * | 2019-05-14 | 2019-07-19 | 武汉大学 | The method and application of projective amplification water level measurement accuracy |
US11443133B2 (en) | 2019-12-10 | 2022-09-13 | Ricoh Company, Ltd. | Computer vision system for industrial equipment gauge digitization and alarms |
CN111652089A (en) * | 2020-05-18 | 2020-09-11 | 纪义胜 | Water level automatic identification method and system based on image processing |
CN111652089B (en) * | 2020-05-18 | 2023-09-19 | 纪义胜 | Automatic water level identification method and system based on image processing |
WO2021238030A1 (en) * | 2020-05-26 | 2021-12-02 | 浙江大学 | Water level monitoring method for performing scale recognition on the basis of partitioning by clustering |
CN111626190A (en) * | 2020-05-26 | 2020-09-04 | 浙江大学 | Water level monitoring method for scale recognition based on clustering partitions |
CN111998910A (en) * | 2020-08-26 | 2020-11-27 | 河海大学 | Visual measurement method and system for water level of multi-stage water gauge |
CN111998910B (en) * | 2020-08-26 | 2021-09-24 | 河海大学 | Visual measurement method and system for water level of multi-stage water gauge |
CN112329644A (en) * | 2020-11-06 | 2021-02-05 | 中冶赛迪重庆信息技术有限公司 | Reservoir water level monitoring method and system, medium and electronic terminal |
CN113221898A (en) * | 2021-04-16 | 2021-08-06 | 北京科技大学 | Automatic water level gauge reading method |
CN113392846A (en) * | 2021-06-16 | 2021-09-14 | 广州观必达数据技术有限责任公司 | Water gauge water level monitoring method and system based on deep learning |
CN115578695A (en) * | 2022-11-21 | 2023-01-06 | 昆明理工大学 | Water gauge water level machine vision detection method and device with free shooting visual angle |
CN115546235A (en) * | 2022-11-23 | 2022-12-30 | 成都见海科技有限公司 | Water level identification method and system based on image segmentation and storage medium |
CN116109869A (en) * | 2023-02-20 | 2023-05-12 | 北京科技大学 | Method and device for identifying reservoir water level fluctuation based on water bank image matching |
CN116109869B (en) * | 2023-02-20 | 2024-02-20 | 北京科技大学 | Method and device for identifying reservoir water level fluctuation based on water bank image matching |
CN116222693A (en) * | 2023-05-10 | 2023-06-06 | 安徽省(水利部淮河水利委员会)水利科学研究院(安徽省水利工程质量检测中心站) | Natural river channel water level automatic monitoring method based on water gauge reflection |
CN116222693B (en) * | 2023-05-10 | 2023-07-25 | 安徽省(水利部淮河水利委员会)水利科学研究院(安徽省水利工程质量检测中心站) | Natural river channel water level automatic monitoring method based on water gauge reflection |
Also Published As
Publication number | Publication date |
---|---|
CN108764229B (en) | 2021-05-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108764229A (en) | A kind of water gauge automatic distinguishing method for image based on computer vision technique | |
WO2021238030A1 (en) | Water level monitoring method for performing scale recognition on the basis of partitioning by clustering | |
CN108647681B (en) | A kind of English text detection method with text orientation correction | |
CN106960208B (en) | Method and system for automatically segmenting and identifying instrument liquid crystal number | |
CN104751187A (en) | Automatic meter-reading image recognition method | |
CN107491730A (en) | A kind of laboratory test report recognition methods based on image procossing | |
CN104680130A (en) | Chinese character recognition method for identification cards | |
CN116152231B (en) | Method for detecting impurities in lubricating oil based on image processing | |
CN111091124B (en) | Spine character recognition method | |
CN110084802B (en) | High-precision PCB chip pin center positioning method | |
CN107067000B (en) | A kind of recognition methods of bank note degree and device | |
CN112734729B (en) | Water gauge water level line image detection method and device suitable for night light supplement condition and storage medium | |
CN106874901B (en) | Driving license identification method and device | |
CN111476804B (en) | Efficient carrier roller image segmentation method, device, equipment and storage medium | |
CN113033558B (en) | Text detection method and device for natural scene and storage medium | |
CN112288693A (en) | Round hole detection method and device, electronic equipment and storage medium | |
CN108830270A (en) | Correctly divide the localization method of the language of the Manchus word central axes of each identification to language of the Manchus word | |
CN116452667B (en) | Target identification and positioning method based on image processing | |
Chen et al. | Method on water level ruler reading recognition based on image processing | |
CN107103608A (en) | A kind of conspicuousness detection method based on region candidate samples selection | |
CN107516315B (en) | Tunneling machine slag tapping monitoring method based on machine vision | |
CN109409356A (en) | A kind of multi-direction Chinese print hand writing detection method based on SWT | |
CN112734816B (en) | Heterologous image registration method based on CSS-Delaunay | |
Fan et al. | Skew detection in document images based on rectangular active contour | |
CN115438682B (en) | Method and device for determining decoding direction and decoding equipment |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |