CN110287953B - Water level automatic identification method and device - Google Patents
Water level automatic identification method and device Download PDFInfo
- Publication number
- CN110287953B CN110287953B CN201910417536.6A CN201910417536A CN110287953B CN 110287953 B CN110287953 B CN 110287953B CN 201910417536 A CN201910417536 A CN 201910417536A CN 110287953 B CN110287953 B CN 110287953B
- Authority
- CN
- China
- Prior art keywords
- water gauge
- water
- strip
- gauge
- water level
- 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.)
- Active
Links
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
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Fluid Mechanics (AREA)
- Measurement Of Levels Of Liquids Or Fluent Solid Materials (AREA)
Abstract
The embodiment of the invention provides a method and a device for automatically identifying water level, wherein the method comprises the following steps: extracting a water gauge region from a water gauge image to be identified, and segmenting the water gauge region to obtain a plurality of strip-shaped regions of the head part of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region; acquiring a water gauge number corresponding to the vector and a water gauge zero elevation corresponding to the water gauge number according to the vector formed by the respective heights of all the strip-shaped areas at the head of the water gauge; and acquiring the last boundary above the water surface in the boundaries of all the strip-shaped areas of the water gauge measuring part, acquiring the intersection point of the last boundary and the water surface and the water level reading of the intersection point, and adding the water level reading and the zero elevation of the water gauge to acquire the water level identification result of the water gauge image to be identified. The embodiment of the invention realizes automatic identification of the water level, and the method is simple and efficient and has high identification accuracy.
Description
Technical Field
The invention belongs to the technical field of water level monitoring, and particularly relates to a water level automatic identification method and device.
Background
The water level gauge is widely applied to soft soil foundation treatment, port and wharf and other projects and is used for observing the change of underground water level and ocean tide water level.
The manual observation and reading of the water gauge is an important means for navigation channel personnel to acquire the water level. Under the condition of a digital navigation channel, an automatic water level station automatically acquires the water level mode to gradually replace a manual observation and reading mode, and adopts a bubble type water level meter. However, the water temperature, the water tightness and the water level are greatly changed, so that the balance relation between the air pipe pressure and the water level is broken, and the accuracy of water level collection is influenced. Therefore, the water level of the water gauge is manually observed and read to be compared with the water level collected by the automatic water level station at present, and the method is the most effective method for improving the accuracy rate of the water level collected by the automatic water level station.
The method for obtaining the final water level by comparing the manually observed water level with the water level collected by the automatic water level station generally comprises four steps of observing and reading, looking up the 0-point elevation of the water gauge corresponding to the water gauge number, calculating the water level and measuring the water level ratio. Wherein, the water level observing and reading is completed within three minutes by adopting a water gauge for observing and reading for multiple times, and the water level observing and reading result with the highest frequency in the multiple times of observing and reading results is taken as final observing and reading data; then inquiring 0-point elevation of the water gauge pile according to the serial number of the water gauge pile, adding the final observation and reading data and the 0-point elevation, and calculating to obtain a final observation and reading water level; and finally comparing the final observing and reading water level with the water level acquired by the automatic water level station in real time, and if the error between the final observing and reading water level and the water level acquired by the automatic water level station is within a preset range, if the error is less than 5 cm, taking the manual observing and reading water level as the correct water level, otherwise, taking the water level acquired by the automatic water level station as the correct water level.
The higher the frequency of the comparison measurement is, the more accurate the water level data is, the comparison measurement needs a professional to observe and read on site each time, the distribution of water levels in the area under jurisdiction of individual channel is dense, the workload is large, and errors are easy to occur due to the need of calculation.
Disclosure of Invention
In order to overcome the problems of time and labor waste, poor accuracy and high error probability of the existing water level obtaining method or at least partially solve the problems, embodiments of the present invention provide a water level automatic identification method and apparatus.
According to a first aspect of the embodiments of the present invention, there is provided a water level automatic identification method, including:
extracting a water gauge region from a water gauge image to be identified, and segmenting the water gauge region to obtain a plurality of strip-shaped regions of the head part of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region;
acquiring a water gauge number corresponding to the vector and a water gauge zero elevation corresponding to the water gauge number according to the vector formed by the respective heights of all the strip-shaped areas at the head of the water gauge; wherein, the incidence relation between the water gauge number and the zero elevation of the water gauge is stored in advance;
and acquiring the last boundary above the water surface in the boundaries of all the strip-shaped areas of the water gauge measuring part, acquiring the intersection point of the last boundary and the water surface and the water level reading of the intersection point, and adding the water level reading and the zero elevation of the water gauge to acquire the water level identification result of the water gauge image to be identified.
According to a second aspect of embodiments of the present invention, there is provided an automatic water level recognition apparatus, including:
extracting a water gauge region from a water gauge image to be identified, and segmenting the water gauge region to obtain a plurality of strip-shaped regions of the head part of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region;
acquiring a water gauge number corresponding to the vector and a water gauge zero elevation corresponding to the water gauge number according to the vector formed by the respective heights of all the strip-shaped areas at the head of the water gauge; wherein, the incidence relation between the water gauge number and the zero elevation of the water gauge is stored in advance;
and acquiring the last boundary above the water surface in the boundaries of all the strip-shaped areas of the water gauge measuring part, acquiring the intersection point of the last boundary and the water surface and the water level reading of the intersection point, and adding the water level reading and the zero elevation of the water gauge to acquire the water level identification result of the water gauge image to be identified.
According to a third aspect of the embodiments of the present invention, there is also provided an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor calls the program instruction to perform the method for automatically identifying a water level provided in any one of the various possible implementations of the first aspect.
According to a fourth aspect of embodiments of the present invention, there is also provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the automatic water level recognition method provided in any one of the various possible implementations of the first aspect.
The embodiment of the invention provides a water level automatic identification method and a device, wherein the method comprises the steps of analyzing an acquired water gauge image to be identified, and acquiring a water gauge number according to the characteristics of the head of a water gauge in the water gauge image to be identified so as to determine a zero elevation of the water gauge corresponding to the water gauge number; and determining a water level reading on the water gauge according to the intersection point of the last boundary line of the water gauge measuring part above the water surface and the water surface in the water gauge image to be identified, adding the zero elevation of the water gauge and the water level reading on the water gauge, and automatically identifying a water level result according to the water level image to be identified.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic overall flow chart of an automatic water level identification method according to an embodiment of the present invention;
fig. 2 is a schematic view of a side-unfolded structure of a water level in the automatic water level identification method according to the embodiment of the present invention;
fig. 3 is a schematic view of a gray scale image of a water gauge region in the automatic water level identification method according to the embodiment of the present invention;
fig. 4 is a schematic diagram of a horizontal edge point image of a water gauge region in the automatic water level identification method according to the embodiment of the present invention;
fig. 5 is a schematic view of an overall structure of an automatic water level recognition apparatus according to an embodiment of the present invention;
fig. 6 is a schematic view of an overall structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic overall flow chart of an automatic water level identification method according to an embodiment of the present invention, where the method includes: s101, extracting a water gauge region from a water gauge image to be identified, and segmenting the water gauge region to obtain a plurality of strip-shaped regions of the head of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region;
the water gauge image to be identified is an image containing the water gauge and used for identifying the water level. In order to realize automatic recognition of the water level, the water level is recognized by analyzing the photographed water gauge image to be recognized, and it is necessary to use a special water gauge including a head and a measuring part, as shown in fig. 2. In order to facilitate the identification of any angle, the water gauge has horizontal omnibearing visibility; in order to be compatible with the functions of the traditional water gauge, the water gauge comprises two parts of water gauge number and water gauge measurement as the traditional water gauge. As shown in fig. 2, the head of the water gauge is designed in an omnibearing parallel manner similar to a one-dimensional code, and is used for marking the water gauge code, and acquiring the water gauge number according to the water gauge code, so as to acquire the zero elevation corresponding to the water gauge number, and the water gauge code is adopted to facilitate automatic identification. The measuring part of the water gauge is in a spiral multi-strip design with equal bandwidth and is used for automatically reading water level readings, so that the water level can be seen in all directions. The water gauge can be engraved with water level readings and is suitable for manual readings. In order to be beneficial to upgrading of future hardware, the water gauge adopts a sleeve type design, and can be conveniently sleeved on an existing traditional water gauge by means of an installation foundation of the existing water gauge.
The water gauge area is the area occupied by the water gauge in the image to be identified. The water gauge region is extracted from the water gauge image to be recognized according to the shape and/or color of the water gauge, and the embodiment is not limited to the method of extracting the water gauge region. The water gauge is approximately rectangular, the color of the water gauge is generally different from the color of the surrounding environment of the water gauge, as shown in fig. 2, the area filled by oblique lines in fig. 2 is one color, such as blue, the area filled by vertical lines is another color, such as red, the color of two adjacent strip-shaped areas at the head part of the water gauge is different, and the color of two adjacent strip-shaped areas at the measuring part of the water gauge is different. And dividing the water gauge area to obtain a plurality of strip-shaped areas of the head part of the water gauge and a plurality of strip-shaped areas of the measuring part of the water gauge in the water gauge area. Since the water gauge head must be above the water surface, the water gauge area includes the complete water gauge head. And when the water quality is turbid, the water gauge measuring part in the water gauge area is a water gauge measuring part positioned above the water surface and is not complete. As shown in fig. 2, the strip-shaped area at the head of the water gauge is an area between two adjacent circular arc lines and is divided into a 0-strip area, a 1-strip area, a 2-strip area, a 3-strip area, a 4-strip area, a 5-strip area and a last-strip area from top to bottom. Each strip-shaped area of the water gauge measuring part is an area between two adjacent spiral lines. Because the colors of two adjacent strip-shaped regions are different, the water gauge region is divided according to the colors, namely the strip-shaped region of the head part of the water gauge and the strip-shaped region of the measuring part of the water gauge.
S102, acquiring a water gauge number corresponding to a vector and a water gauge zero elevation corresponding to the water gauge number according to the vector formed by the respective heights of all the strip-shaped areas at the head of the water gauge; wherein, the incidence relation between the water gauge number and the zero elevation of the water gauge is stored in advance;
for example, the band-shaped area of the head of the water gauge includes a 1 band, a 2 band and a 3 band, wherein the height of the 1 band is 16mm, the height of the 2 band is 8mm, the height of the 3 band is 24mm, mm is mm, and the diameter of the water gauge is 40 mm. Assuming a preset unit height of 8mm, the 1 band, 2 band and 3 band are each 2,1 and 3 units high, respectively. And acquiring the water gauge number corresponding to the vector according to the vector formed by the heights of the three zones, such as (2,1,3), wherein each vector corresponds to one water gauge number, and the corresponding relation between the vector and the water gauge number is predetermined. The water gauge number is the unique identification of each water gauge. And each water gauge number corresponds to a zero elevation of the water gauge, namely the water level elevation when the measurement part of the water gauge is 0 reading. And acquiring the zero elevation of the water gauge corresponding to the water gauge number according to the incidence relation between the water gauge number and the zero elevation of the water gauge.
S103, obtaining the last boundary above the water surface in the boundaries of all the strip-shaped areas of the water gauge measuring part, obtaining the intersection point of the last boundary and the water surface and the water level reading of the intersection point, and adding the water level reading and the zero elevation of the water gauge to obtain the water level identification result of the water gauge image to be identified.
Wherein the last boundary above the water surface in the boundaries of all the strip-shaped areas of the water gauge measuring part is the last spiral line t (x) of the water gauge measuring part above the water surface z (x). When the water quality is not transparent, the last spiral line above the water surface is the last spiral line of the water gauge measuring part in the water gauge area. When the water quality is transparent, the last spiral line on the water surface is determined according to the gray value of the water gauge measuring part in the water gauge area. And acquiring the intersection point of the last spiral line on the water surface and the water surface. And determining the distance between the intersection point and the top end of the water gauge measuring part according to the number of the strip-shaped areas between the intersection point and the top end of the water gauge measuring part and the height of each strip-shaped area. The preset water level reading at the top end of the water gauge measuring part is used for subtracting the distance to obtain the water level reading of the intersection point, so that errors caused by the fact that the absolute water level value is increased due to the fact that the water level bottom is lifted due to long-term sediment accumulation at the bottom of the riverbed are avoided, and accuracy of water level identification is improved. And adding the water level reading of the intersection point and the zero elevation of the water gauge to obtain a water level identification result of the water gauge image to be identified. In order to avoid the problem of manual reading of the traditional water gauge, and simultaneously consider the established camera networks such as the two banks of the water bank and the river channel and the city, the embodiment modifies the camera from a single image sensor into an intelligent sensor for automatically identifying the water level by designing and developing a matched intelligent identification method for the water gauge. In addition, can also compare the water level result that acquires in this embodiment with the water level that automatic water level station gathered, when the water level needs to be rectified, adopt the water level of artifical reading or the water level that automatic water level station gathered to carry out automatic correction to this embodiment automatic identification's water level.
In the embodiment, the acquired water gauge image to be identified is analyzed, and the water gauge number is acquired according to the characteristics of the head of the water gauge in the water gauge image to be identified, so that the zero elevation of the water gauge corresponding to the water gauge number is determined; and determining a water level reading on the water gauge according to the intersection point of the last boundary line of the water gauge measuring part above the water surface and the water surface in the water gauge image to be identified, adding the zero elevation of the water gauge and the water level reading on the water gauge, and automatically identifying a water level result according to the water level image to be identified.
On the basis of the above embodiment, before the step of extracting the water gauge region from the water gauge image to be recognized, the method further includes: preprocessing the water gauge image to be identified; wherein the preprocessing comprises distortion correction, gray stretching, binaryzation, corrosion and skeleton refinement; the distortion correction specifically includes: establishing a relation between the accurate position and the actual position of each pixel in the water gauge image to be identified based on the random forest model; and correcting the position of each pixel in the water gauge image to be identified according to the relation between the accurate position and the actual position of each pixel in the water gauge image to be identified.
Specifically, after the water gauge image to be identified is acquired, a series of preprocessing such as distortion correction, gray stretching, binarization, corrosion, skeleton refinement and the like needs to be performed on the water gauge image to be identified. Due to the influence of various uncertain factors such as the type of an optical lens, the reliability of a photosensitive element, the quality deviation of partial components and the like, the actual optical imaging device cannot ideally accord with the pinhole imaging principle, and the position of a point in a three-dimensional world between an actual imaging point and a theoretical imaging point on an image imaging surface deviates, so that the image acquired by the device generates various forms of distortion. Because the acquisition of the water gauge image to be identified adopts a wide-angle lens, the lens configuration is easy to cause distortion. From the actual imaging results, only a small portion of the image near the central field of view is faithfully and can be considered as an undistorted image of light passing through the aperture under ideal conditions. Image distortion is a problem that the computer vision field has sought to overcome. When the water level is measured using the water gauge image to be identified, the correction of the image distortion will be related to the accuracy of the water level detection. The embodiment is different from a general traditional image correction method, a virtual normal image is constructed by adopting a random forest model, and a distortion coefficient, namely the relationship between the accurate position and the actual position of each pixel in the water gauge image to be identified is obtained according to the normal image and the corresponding distorted image. And correcting the distorted image according to the distortion coefficient. And recovering degraded parts in the water gauge image to be identified by adopting a correction method of the distorted image.
The distortion causes the pixel in the water gauge image to be identified to be shifted, and as a result, the object image formed by the pixel in the water gauge image to be identified is distorted. For one frame of image, the farther the pixel is from the center of the optical axis, the greater the degree of actual pixel deviation from the ideal pixel, and the more distortion is generated on the whole to-be-identified water gauge image. And the distortion in the vicinity of the optical axis is small to an almost negligible degree, so that it can be regarded as an ideal imaging region where no distortion occurs. The image distortion error is divided into radial distortion and tangential distortion. Because the water level rises and falls along the radial direction, the pixel points in the water gauge image to be identified in the embodiment mainly generate radial distortion, and tangential distortion is not considered. And then, carrying out direction correction on the preprocessed water gauge image to be identified through Hough change, so that the water gauge in the water gauge image to be identified is in a vertical orientation.
On the basis of the above embodiment, in this embodiment, each strip-shaped region of the water gauge head is a first color or a second color, the two adjacent strip-shaped regions of the water gauge head are different in color, and the boundary of each strip-shaped region of the water gauge head is arc-shaped; each strip-shaped area of the water gauge measuring part is of a third color or a fourth color, the colors of two adjacent strip-shaped areas of the water gauge measuring part are different, and the boundary of each strip-shaped area of the water gauge measuring part is spiral; correspondingly, the step of extracting the water gauge region from the water gauge image to be identified specifically comprises the following steps: and extracting the water gauge area from the water gauge image to be identified according to the color of each strip area of the head of the water gauge and the color of each strip area of the measuring part of the water gauge.
Specifically, as shown in fig. 2, in order to facilitate the extraction of the water gauge region and the division of the strip regions of the water gauge head and the water gauge measuring part, the color of two adjacent strip regions of the water gauge head in the embodiment is different, wherein the region filled with oblique lines is a first color, such as blue, and the region filled with vertical lines is a second color, such as red. The color of two adjacent strip-shaped areas of the water gauge measuring part is different, and the third color of the water gauge measuring part can be the same as or different from the first color of the head part of the water gauge; the fourth color of the measuring portion of the water gauge may be the same as or different from the second color of the head portion of the water gauge. Since the water gauge code needs to be determined by the adjacency of the height of each strip-shaped area of the water gauge head, the height of each strip-shaped area of the water gauge head may be the same or different. The height of each banded region of water gauge measuring part is the same, and the boundary design of water gauge measuring part banded region is the heliciform because consider the refraction principle of the surface of water, and the helix can take place the refraction in the surface of water below to lead to the refraction back water level reading can produce the error, consequently set up banded regional boundary into the helix. The inclination angle of the spiral line is determined according to the vertical width K of the strip-shaped area and the radius r of the bottom surface of the water gauge. Let tan α be 2K/2 pi r K/pi r, which is the tangent of the helix angle α, i.e., the vertical width K of the band-shaped region divided by the product of the pipe radius r and pi. The purpose of this setting of the angle of inclination α is to ensure the consistency of the calculation, returning to the origin in the horizontal direction after one revolution of the helix. But at the same time it is ensured that the width of the strip-shaped area is as large as possible so that it is clearly visible at a distance. And extracting the water gauge region from the water gauge image to be identified according to the color distribution of the water gauge head and the water gauge measuring part strip region. In addition, scales can be made on the measuring part of the water gauge, so that manual reading is facilitated. When the color of the strip-shaped area of the water gauge measuring part is red or blue. In the red strip-shaped area, the color of the scale is yellow; in the blue band-shaped area, the color of the scale is green.
On the basis of the foregoing embodiment, in this embodiment, the step of dividing the water gauge region to obtain a plurality of strip-shaped regions of the head portion of the water gauge and a plurality of strip-shaped regions of the measurement portion of the water gauge in the water gauge region specifically includes: dividing the water gauge region based on a superpixel algorithm to obtain a plurality of strip-shaped regions of the head of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region; and in the segmentation process, segmenting the water gauge region based on an energy function of the similarity of the neighborhood pixels in the water gauge region, and optimizing the energy function.
Specifically, after the water gauge region is obtained, the water gauge region is segmented based on a superpixel algorithm, the water gauge region is segmented based on an energy function of neighborhood pixel similarity in the water gauge region in the superpixel segmentation process, and the energy function is further optimized, so that a strip-shaped region of the head of the water gauge in the water gauge region and a strip-shaped region of a measuring part in the water gauge region are accurately positioned. First, the water gauge area is converted into a grayscale image, as shown in fig. 3. Then, the edge points of the water gauge region in the horizontal direction, i.e. the horizontal edge points, are calculated according to the gray scale image of the water gauge region, as shown in fig. 4, the horizontal edge points are projected to the horizontal direction, the phase angle of each horizontal edge point is recorded, and the energy e (x) of each horizontal edge phase angle is defined according to the following formula. Where x represents a longitudinal coordinate in the direction from the bottom to the top of the water gauge area:
wherein the content of the first and second substances,
is the ith horizontal edge point at the x position, N is the number of the horizontal edge points at the x position, i is 1 … N,
as horizontal edge points
The phase angle of (c). And then searching the x position of the first phase angle energy larger than the preset threshold value from bottom to top according to the x, namely the position of the boundary line between the head of the water gauge and the measuring part. The horizontal edge points of the positions of the measuring part of the water gauge are all in one direction, and the phase angle ranges from 0 to 90 degrees, as shown in figure 4. However, the head is different in that the horizontal edge points of the head are circular and have a phase angle of between 0 and 90 degrees, as well as greater than 90 degrees. When a plurality of edge points are present at a horizontal position and are located on the circular line, the phase angle of all the edge points at the horizontal position is ideally 180 degrees, but for fault tolerance, the threshold value may be set to a value slightly smaller than 180 degrees, for example 150 degrees, and the threshold value may be adjusted slightly according to the image quality, and may be increased appropriately if the edge is sharp.
On the basis of the foregoing embodiment, in this embodiment, the step of obtaining the water gauge number corresponding to the vector according to the vector formed by the heights of the strip regions of the head of the water gauge specifically includes: determining a set of all vectors formed by heights with the total height smaller than the preset total height upper limit in preset number according to the preset number of the strip-shaped areas of the water gauge head and the preset total height upper limits of all the strip-shaped areas of the water gauge head, and sequencing the vectors in the set; wherein the preset total height upper limit and the height of the vector in the set are multiples of a preset unit height; and searching vectors formed by the heights of the strip areas at the head of the water gauge from the set, wherein the sequence number of the searched vectors is used as the water gauge number corresponding to the vector.
For example, the tape-like region of the water gauge head is 3, and the upper limit of the preset total height of the 3 tape-like regions of the water gauge head is 64 mm. The preset unit height is 8mm, and the upper limit of the preset total height is 8 unit heights. Vectors (x, y, z) comprising 3 heights having a total height of less than 8 unit heights are identified as (1,1,1), (1,1,2), (1,1,3), (1,1,4), (1,1,5), (1,1,6), (1,2,1), (1,2,2), (1,2,3), (1,2,4), (1,2,5), (1,3,1), (1,3,2), (1,3,3), (1,3,4), (1,4,1), (1,4,2), (1,4,3), (1,5,1), (1,5,2), (1,6,1), (2,1,2), (2,1,3), (2,1,4), (2,1,5), (2,2,1), (2,2,2), (2,2,3), (2,2,4), (2,3,1), (2,3,2), (2,3,3), (2,4,1), (2,4,2), (2,5,1), (3,1,2), (3,1,3), (3,1,4), (3,2,1), (3,2,2), (3,2,3), (3,3,1), (3,3,2), (3,4,1), (4,1,2), (4,1,3), (4,2,1), (4,2,2), (4,2, 3,1), (5,1,2), (5,2,1) and (6,1,1) wherein x, y and z are the results of the calculation of the height of 3 banded regions divided by the height. The number of constituting vectors is C38There are 56 height vectors for the 56 usable water rule heads. The vectors are placed in a set and sorted in the order above. For example, when the vector of the respective heights of the three bands is (2,1,3), the vector (2,1,3) is the 24 th vector in the set, and 24 is numbered as the water gauge.
On the basis of the foregoing embodiments, in this embodiment, the step of acquiring the intersection point of the last boundary and the water surface specifically includes: when the water quality in the water gauge image to be identified is transparent, acquiring the curvature change of each point on the last boundary, and taking the point with the maximum curvature change as the intersection point of the last boundary and the water surface; and when the water quality in the water gauge image to be identified is not transparent, taking the lowest point on the last boundary as the intersection point of the last boundary and the water surface.
Specifically, when the water quality measured by the water gauge is transparent, although the water gauge measuring part below the water surface is still clearly visible, due to the refraction of water, the intersection point of the last spiral line t (x) above the water surface and the water surface z (x) can be obtained by analyzing the curvature change of each point on t (x), and the point with the largest curvature change is taken as the intersection point of the last spiral line t (x) above the water surface and the water surface z (x). When the water quality measured by the water gauge is opaque, the intersection point of the last spiral line t (x) above the water surface in the water gauge area and the water surface z (x) is the lowest point of t (x) in the water gauge area.
On the basis of the foregoing embodiments, the step of obtaining the water level identification result of the water gauge image to be identified in this embodiment specifically includes: acquiring a water level identification result of a water gauge image to be identified of any water gauge shot for multiple times within a preset time period; correspondingly, the step of obtaining the water level identification result of the water gauge image to be identified further comprises the following steps: calculating the average value of all water level identification results of the water gauge; if the difference value between any one water level identification result of the water gauge and the average value is larger than a preset threshold value, rejecting the water level identification result; and taking the average value of the remaining water level identification results after the water gauge is removed as the final water level identification result of the water gauge.
Specifically, in water level identification, the water surface cannot be kept calm due to wind waves, and if no still water equipment is provided, certain influence is brought to measurement. All the wave heights can be determined only by measuring the wavelength, and then the value of the hydrostatic surface when waves exist is determined, but the water level corresponding to the parameters cannot be accurately and timely measured every time when waves exist, so that the method of measuring and averaging for multiple times is adopted as the hydrostatic surface water level in the embodiment. The specific method comprises the steps of firstly obtaining water level identification results for multiple times within a preset time period delta t according to the water level automatic identification method in the embodiment, and obtaining an average value of the water level identification results; and then calculating the difference between each water level identification result and the average value one by one, if the absolute value of the difference corresponding to any water level identification result is greater than a preset threshold, rejecting the water level identification result, and otherwise, leaving the water level identification result. The purpose of doing so is to remove gross errors in the water level recognition result, improving the measurement accuracy. And then, the remaining water level identification result is used for obtaining an average value and then a rounding result is used as a final water level identification result at a certain moment in delta t time.
In another embodiment of the present invention, an automatic water level identification device is provided, which is used for implementing the method in the foregoing embodiments. Therefore, the description and definition in the embodiments of the automatic water level identification method described above can be used for understanding the execution modules in the embodiments of the present invention. Fig. 5 is a schematic diagram of an overall structure of an automatic water level identification apparatus according to an embodiment of the present invention, where the apparatus includes an extraction module 501, an acquisition module 502, and an identification module 503; wherein:
the extraction module 501 is configured to extract a water gauge region from a water gauge image to be identified, and segment the water gauge region to obtain a plurality of strip-shaped regions at the head of the water gauge and a plurality of strip-shaped regions at the measurement part of the water gauge in the water gauge region;
the water gauge image to be identified is an image containing the water gauge and used for identifying the water level. The water gauge area is the area occupied by the water gauge in the image to be identified. The extraction module 501 extracts a water gauge region from the water gauge image to be recognized according to the shape and/or color of the water gauge, and the embodiment is not limited to the method of extracting the water gauge region. The water gauge is approximately rectangular in shape, the color of the water gauge is generally different from the color of the surrounding environment of the water gauge, the color of two adjacent strip-shaped areas at the head of the water gauge is different, and the color of the two adjacent strip-shaped areas at the measuring part of the water gauge is different. And dividing the water gauge area to obtain a plurality of strip-shaped areas of the head part of the water gauge and a plurality of strip-shaped areas of the measuring part of the water gauge in the water gauge area. Since the water gauge head must be above the water surface, the water gauge area includes the complete water gauge head. And when the water quality is turbid, the water gauge measuring part in the water gauge area is a water gauge measuring part positioned above the water surface and is not complete. Each strip-shaped area of the water gauge measuring part is an area between two adjacent spiral lines. Because the colors of two adjacent strip-shaped regions are different, the water gauge region is divided according to the colors, namely the strip-shaped region of the head part of the water gauge and the strip-shaped region of the measuring part of the water gauge.
The obtaining module 502 is configured to obtain a water gauge number corresponding to the vector and a water gauge zero elevation corresponding to the water gauge number according to the vector formed by the respective heights of all the strip-shaped areas at the head of the water gauge; wherein, the incidence relation between the water gauge number and the zero elevation of the water gauge is stored in advance;
each vector corresponds to a water gauge number, and the corresponding relation between the vectors and the water gauge numbers is predetermined. The water gauge number is the unique identification of each water gauge. And each water gauge number corresponds to a zero elevation of the water gauge, namely the water level elevation when the measurement part of the water gauge is 0 reading. The obtaining module 302 obtains the zero elevation of the water gauge corresponding to the water gauge number according to the association relationship between the water gauge number and the zero elevation of the water gauge.
The identification module 503 is configured to obtain a last boundary located above the water surface among the boundaries of all the strip-shaped areas of the water gauge measurement portion, obtain an intersection of the last boundary and the water surface, and a water level reading of the intersection, add the water level reading and the water gauge zero elevation, and obtain a water level identification result of the water gauge image to be identified.
Wherein the last boundary above the water surface in the boundaries of all the strip-shaped areas of the water gauge measuring part is the last spiral line of the water gauge measuring part above the water surface. When the water quality is not transparent, the last spiral line above the water surface is the last spiral line of the water gauge measuring part in the water gauge area. When the water quality is transparent, the last spiral line on the water surface is determined according to the gray value of the water gauge measuring part in the water gauge area. The identification module 503 acquires the intersection of the last helix on the water surface with the water surface. And determining the distance between the intersection point and the top end of the water gauge measuring part according to the number of the strip-shaped areas between the intersection point and the top end of the water gauge measuring part and the height of each strip-shaped area. The preset water level reading at the top end of the water gauge measuring part is used for subtracting the distance to obtain the water level reading of the intersection point, so that errors caused by the fact that the absolute water level value is increased due to the fact that the water level bottom is lifted due to long-term sediment accumulation at the bottom of the riverbed are avoided, and accuracy of water level identification is improved. And adding the water level reading of the intersection point and the zero elevation of the water gauge to obtain a water level identification result of the water gauge image to be identified.
In the embodiment, the acquired water gauge image to be identified is analyzed, and the water gauge number is acquired according to the characteristics of the head of the water gauge in the water gauge image to be identified, so that the zero elevation of the water gauge corresponding to the water gauge number is determined; and determining a water level reading on the water gauge according to the intersection point of the last boundary line of the water gauge measuring part above the water surface and the water surface in the water gauge image to be identified, adding the zero elevation of the water gauge and the water level reading on the water gauge, and automatically identifying a water level result according to the water level image to be identified.
On the basis of the embodiment, the embodiment further comprises a preprocessing module for preprocessing the water gauge image to be identified; wherein the preprocessing comprises distortion correction, gray stretching, binaryzation, corrosion and skeleton refinement; the preprocessing module is specifically configured to: establishing a relation between the accurate position and the actual position of each pixel in the water gauge image to be identified based on the random forest model; and correcting the position of each pixel in the water gauge image to be identified according to the relation between the accurate position and the actual position of each pixel in the water gauge image to be identified.
On the basis of the above embodiment, in this embodiment, each strip-shaped region of the water gauge head is a first color or a second color, the two adjacent strip-shaped regions of the water gauge head are different in color, and the boundary of each strip-shaped region of the water gauge head is arc-shaped; each strip-shaped area of the water gauge measuring part is of a third color or a fourth color, the colors of two adjacent strip-shaped areas of the water gauge measuring part are different, and the boundary of each strip-shaped area of the water gauge measuring part is spiral; correspondingly, the extraction module is specifically configured to: and extracting the water gauge area from the water gauge image to be identified according to the color of each strip area of the head of the water gauge and the color of each strip area of the measuring part of the water gauge.
On the basis of the foregoing embodiment, the extraction module in this embodiment is specifically configured to: dividing the water gauge region based on a superpixel algorithm to obtain a plurality of strip-shaped regions of the head of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region; and in the segmentation process, segmenting the water gauge region based on an energy function of the similarity of the neighborhood pixels in the water gauge region, and optimizing the energy function.
On the basis of the foregoing embodiment, the obtaining module in this embodiment is specifically configured to: determining a set of all vectors formed by heights with the total height smaller than the preset total height upper limit in preset number according to the preset number of the strip-shaped areas of the water gauge head and the preset total height upper limits of all the strip-shaped areas of the water gauge head, and sequencing the vectors in the set; wherein the preset total height upper limit and the height of the vector in the set are multiples of a preset unit height; and searching vectors formed by the heights of the strip areas at the head of the water gauge from the set, wherein the sequence number of the searched vectors is used as the water gauge number corresponding to the vector.
On the basis of the foregoing embodiments, the identification module in this embodiment is specifically configured to: when the water quality in the water gauge image to be identified is transparent, acquiring the curvature change of each point on the last boundary, and taking the point with the maximum curvature change as the intersection point of the last boundary and the water surface; and when the water quality in the water gauge image to be identified is not transparent, taking the lowest point on the last boundary as the intersection point of the last boundary and the water surface.
On the basis of the foregoing embodiments, the identification module in this embodiment is specifically configured to: acquiring a water level identification result of a water gauge image to be identified of any water gauge shot for multiple times within a preset time period; correspondingly, the water gauge further comprises an optimization module used for calculating the average value of all water level identification results of the water gauge; if the difference value between any one water level identification result of the water gauge and the average value is larger than a preset threshold value, rejecting the water level identification result; and taking the average value of the remaining water level identification results after the water gauge is removed as the final water level identification result of the water gauge.
The embodiment provides an electronic device, and fig. 6 is a schematic view of an overall structure of the electronic device according to the embodiment of the present invention, where the electronic device includes: at least one processor 601, at least one memory 602, and a bus 603; wherein the content of the first and second substances,
the processor 601 and the memory 602 communicate with each other via a bus 603;
the memory 602 stores program instructions executable by the processor 601, and the processor calls the program instructions to perform the methods provided by the above method embodiments, for example, the method includes: extracting a water gauge region from a water gauge image to be identified, and segmenting the water gauge region to obtain a plurality of strip-shaped regions of the head part of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region; acquiring a water gauge number corresponding to the vector and a water gauge zero elevation corresponding to the water gauge number according to the vector formed by the respective heights of all the strip-shaped areas at the head of the water gauge; and acquiring the last boundary above the water surface in the boundaries of all the strip-shaped areas of the water gauge measuring part, acquiring the intersection point of the last boundary and the water surface and the water level reading of the intersection point, and adding the water level reading and the zero elevation of the water gauge to acquire the water level identification result of the water gauge image to be identified.
The present embodiments provide a non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the methods provided by the above method embodiments, for example, including: extracting a water gauge region from a water gauge image to be identified, and segmenting the water gauge region to obtain a plurality of strip-shaped regions of the head part of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region; acquiring a water gauge number corresponding to the vector and a water gauge zero elevation corresponding to the water gauge number according to the vector formed by the respective heights of all the strip-shaped areas at the head of the water gauge; and acquiring the last boundary above the water surface in the boundaries of all the strip-shaped areas of the water gauge measuring part, acquiring the intersection point of the last boundary and the water surface and the water level reading of the intersection point, and adding the water level reading and the zero elevation of the water gauge to acquire the water level identification result of the water gauge image to be identified.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. An automatic water level identification method is characterized by comprising the following steps:
extracting a water gauge region from a water gauge image to be identified, and segmenting the water gauge region to obtain a plurality of strip-shaped regions of the head part of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region;
acquiring a water gauge number corresponding to the vector and a water gauge zero elevation corresponding to the water gauge number according to the vector formed by the respective heights of all the strip-shaped areas at the head of the water gauge; wherein, the incidence relation between the water gauge number and the zero elevation of the water gauge is stored in advance;
acquiring the last boundary above the water surface in the boundaries of all strip-shaped areas of the water gauge measuring part, acquiring the intersection point of the last boundary and the water surface and the water level reading of the intersection point, and adding the water level reading and the zero elevation of the water gauge to acquire the water level identification result of the water gauge image to be identified; wherein, the boundary of each strip-shaped area of the water gauge measuring part is in a spiral shape;
wherein the step of obtaining the intersection of the last boundary and the water surface specifically comprises:
when the water quality in the water gauge image to be identified is transparent, acquiring the curvature change of each point on the last boundary, and taking the point with the maximum curvature change as the intersection point of the last boundary and the water surface;
and when the water quality in the water gauge image to be identified is not transparent, taking the lowest point on the last boundary as the intersection point of the last boundary and the water surface.
2. The automatic water level identification method according to claim 1, wherein the step of extracting the water gauge region from the water gauge image to be identified further comprises:
preprocessing the water gauge image to be identified;
wherein the preprocessing comprises distortion correction, gray stretching, binaryzation, corrosion and skeleton refinement;
the distortion correction specifically includes:
establishing a relation between the accurate position and the actual position of each pixel in the water gauge image to be identified based on the random forest model;
and correcting the position of each pixel in the water gauge image to be identified according to the relation between the accurate position and the actual position of each pixel in the water gauge image to be identified.
3. The automatic water level recognition method according to claim 1, wherein each strip region of the water gauge head is a first color or a second color, the colors of two adjacent strip regions of the water gauge head are different, and the boundary of each strip region of the water gauge head is in a circular arc shape;
each strip-shaped area of the water gauge measuring part is of a third color or a fourth color, and the colors of two adjacent strip-shaped areas of the water gauge measuring part are different;
correspondingly, the step of extracting the water gauge region from the water gauge image to be identified specifically comprises the following steps:
and extracting the water gauge area from the water gauge image to be identified according to the color of each strip area of the head of the water gauge and the color of each strip area of the measuring part of the water gauge.
4. The method for automatically identifying the water level according to claim 3, wherein the step of dividing the water gauge region to obtain a plurality of strip-shaped regions of the head of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region specifically comprises:
dividing the water gauge region based on a superpixel algorithm to obtain a plurality of strip-shaped regions of the head of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region;
and in the segmentation process, segmenting the water gauge region based on an energy function of the similarity of the neighborhood pixels in the water gauge region, and optimizing the energy function.
5. The method for automatically identifying the water level according to claim 1, wherein the step of obtaining the water gauge number corresponding to the vector according to the vector formed by the heights of the strip areas at the head of the water gauge specifically comprises:
determining a set of all vectors formed by heights with the total height smaller than the preset total height upper limit in preset number according to the preset number of the strip-shaped areas of the water gauge head and the preset total height upper limits of all the strip-shaped areas of the water gauge head, and sequencing the vectors in the set; wherein the preset total height upper limit and the height of the vector in the set are multiples of a preset unit height;
and searching vectors formed by the heights of the strip areas at the head of the water gauge from the set, wherein the sequence number of the searched vectors is used as the water gauge number corresponding to the vector.
6. The automatic water level identification method according to any one of claims 1 to 5, wherein the step of obtaining the water level identification result of the water gauge image to be identified specifically comprises:
acquiring a water level identification result of a water gauge image to be identified of any water gauge shot for multiple times within a preset time period;
correspondingly, the step of obtaining the water level identification result of the water gauge image to be identified further comprises the following steps:
calculating the average value of all water level identification results of the water gauge;
if the difference value between any one water level identification result of the water gauge and the average value is larger than a preset threshold value, rejecting the water level identification result;
and taking the average value of the remaining water level identification results after the water gauge is removed as the final water level identification result of the water gauge.
7. An automatic water level recognition apparatus, comprising:
the extraction module is used for extracting a water gauge region from a water gauge image to be identified, segmenting the water gauge region and obtaining a plurality of strip-shaped regions of the head of the water gauge and a plurality of strip-shaped regions of the measuring part of the water gauge in the water gauge region;
the acquisition module is used for acquiring a water gauge number corresponding to the vector and a water gauge zero elevation corresponding to the water gauge number according to the vector formed by the respective heights of all the strip-shaped areas at the head of the water gauge; wherein, the incidence relation between the water gauge number and the zero elevation of the water gauge is stored in advance;
the identification module is used for acquiring the last boundary above the water surface in the boundaries of all the strip-shaped areas of the water gauge measuring part, acquiring the intersection point of the last boundary and the water surface and the water level reading of the intersection point, and adding the water level reading and the zero elevation of the water gauge to acquire the water level identification result of the water gauge image to be identified; wherein, the boundary of each strip-shaped area of the water gauge measuring part is in a spiral shape;
wherein the identification module is specifically configured to:
when the water quality in the water gauge image to be identified is transparent, acquiring the curvature change of each point on the last boundary, and taking the point with the maximum curvature change as the intersection point of the last boundary and the water surface;
and when the water quality in the water gauge image to be identified is not transparent, taking the lowest point on the last boundary as the intersection point of the last boundary and the water surface.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method for automatic water level recognition according to any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for automatic water level identification according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910417536.6A CN110287953B (en) | 2019-05-20 | 2019-05-20 | Water level automatic identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910417536.6A CN110287953B (en) | 2019-05-20 | 2019-05-20 | Water level automatic identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110287953A CN110287953A (en) | 2019-09-27 |
| CN110287953B true CN110287953B (en) | 2021-02-26 |
Family
ID=68002237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910417536.6A Active CN110287953B (en) | 2019-05-20 | 2019-05-20 | Water level automatic identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110287953B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112113638B (en) * | 2020-09-17 | 2024-02-02 | 北京慧怡科技有限责任公司 | Water meter function self-checking device and method |
| CN112308009B (en) * | 2020-11-12 | 2024-02-27 | 湖北九感科技有限公司 | Water gauge water level identification method and device |
| CN112523804B (en) * | 2020-12-10 | 2022-06-14 | 广东电网有限责任公司佛山供电局 | Cable tunnel drainage monitoring system and method |
| CN113435442B (en) * | 2021-05-07 | 2022-11-25 | 三峡大学 | Water level measuring method and device, water gauge and electronic equipment |
| CN114359841B (en) * | 2022-03-07 | 2022-06-03 | 武汉大水云科技有限公司 | Video water level identification method based on space-time average |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104677456A (en) * | 2015-02-10 | 2015-06-03 | 厦门精图信息技术股份有限公司 | Water level monitoring method based on computer image recognition, and water gauge and monitoring system of water level monitoring method |
| JP2015109058A (en) * | 2013-12-06 | 2015-06-11 | 三菱電機株式会社 | Tsunami monitoring system |
| CN107131925A (en) * | 2017-04-28 | 2017-09-05 | 南京邮电大学 | A kind of water level real-time monitoring method based on image procossing |
| CN107367310A (en) * | 2017-07-11 | 2017-11-21 | 华南理工大学 | A kind of river level remote monitoring method based on computer vision |
| CN107588823A (en) * | 2017-09-18 | 2018-01-16 | 河海大学 | Water gauge water level measurement method based on dual-waveband imaging |
| CN107833203A (en) * | 2017-10-19 | 2018-03-23 | 南京邮电大学 | A kind of horizontal plane identification and water level method for real-time measurement based on image procossing |
| CN108318101A (en) * | 2017-12-26 | 2018-07-24 | 北京市水利自动化研究所 | Water gauge water level video intelligent monitoring method based on deep learning algorithm and system |
| 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 |
| CN109186706A (en) * | 2018-08-24 | 2019-01-11 | 南京昊控软件技术有限公司 | A method of for the early warning of Urban Storm Flood flooding area |
| CN109443480A (en) * | 2018-11-02 | 2019-03-08 | 南京邮电大学 | Gauge positioning and water level measurement method based on image procossing |
| CN208860435U (en) * | 2018-11-26 | 2019-05-14 | 河南安宏信息科技有限公司 | A kind of water gauge that Image Acquisition is easily distinguished |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376740A (en) * | 2018-10-19 | 2019-02-22 | 天津天地伟业投资管理有限公司 | A kind of water gauge reading detection method based on video |
-
2019
- 2019-05-20 CN CN201910417536.6A patent/CN110287953B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015109058A (en) * | 2013-12-06 | 2015-06-11 | 三菱電機株式会社 | Tsunami monitoring system |
| CN104677456A (en) * | 2015-02-10 | 2015-06-03 | 厦门精图信息技术股份有限公司 | Water level monitoring method based on computer image recognition, and water gauge and monitoring system of water level monitoring method |
| CN107131925A (en) * | 2017-04-28 | 2017-09-05 | 南京邮电大学 | A kind of water level real-time monitoring method based on image procossing |
| CN107367310A (en) * | 2017-07-11 | 2017-11-21 | 华南理工大学 | A kind of river level remote monitoring method based on computer vision |
| CN107588823A (en) * | 2017-09-18 | 2018-01-16 | 河海大学 | Water gauge water level measurement method based on dual-waveband imaging |
| CN107833203A (en) * | 2017-10-19 | 2018-03-23 | 南京邮电大学 | A kind of horizontal plane identification and water level method for real-time measurement based on image procossing |
| CN108318101A (en) * | 2017-12-26 | 2018-07-24 | 北京市水利自动化研究所 | Water gauge water level video intelligent monitoring method based on deep learning algorithm and system |
| 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 |
| CN109186706A (en) * | 2018-08-24 | 2019-01-11 | 南京昊控软件技术有限公司 | A method of for the early warning of Urban Storm Flood flooding area |
| CN109443480A (en) * | 2018-11-02 | 2019-03-08 | 南京邮电大学 | Gauge positioning and water level measurement method based on image procossing |
| CN208860435U (en) * | 2018-11-26 | 2019-05-14 | 河南安宏信息科技有限公司 | A kind of water gauge that Image Acquisition is easily distinguished |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 人工神经网络在水文领域中的应用;周莺等;《水文水资源》;20180430;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110287953A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287953B (en) | Water level automatic identification method and device | |
| CN112949564B (en) | Pointer type instrument automatic reading method based on deep learning | |
| CN108759973B (en) | Water level measuring method | |
| CN108364280B (en) | Method and equipment for automatically describing structural crack and accurately measuring width | |
| CN109190538A (en) | A kind of fully-loaded stream river deposition coast band evolution analysis method based on remote sensing technology | |
| CN111950330A (en) | Pointer instrument indicating number detection method based on target detection | |
| CN112818988A (en) | Automatic reading identification method and system for pointer instrument | |
| CN109543596A (en) | A kind of water level monitoring method, apparatus, electronic equipment and storage medium | |
| CN114359841B (en) | Video water level identification method based on space-time average | |
| CN107631782B (en) | Water level detection method based on Harris angular point detection | |
| CN112699876A (en) | Automatic reading method for various meters of gas collecting station | |
| CN110909640A (en) | Method and device for determining water level line, storage medium and electronic device | |
| CN111950812B (en) | Method and device for automatically identifying and predicting rainfall | |
| CN109186706A (en) | A method of for the early warning of Urban Storm Flood flooding area | |
| CN113435442B (en) | Water level measuring method and device, water gauge and electronic equipment | |
| CN116011480B (en) | Water level acquisition method, device, equipment and medium based on two-dimension code identifier | |
| CN115760885B (en) | High-closure-degree wetland forest parameter extraction method based on consumer-level unmanned aerial vehicle image | |
| CN116721344A (en) | Vegetation detection method, device and equipment based on aerial photographing equipment | |
| CN115880683A (en) | Urban waterlogging ponding intelligent water level detection method based on deep learning | |
| JP2005346665A (en) | Shoreline extraction method and shoreline-extracting system | |
| CN115376131A (en) | Design and identification method of dot-shaped coding mark | |
| CN112308009B (en) | Water gauge water level identification method and device | |
| CN114998530A (en) | Water body monitoring method and device based on live-action three-dimensional terrain | |
| CN114049390A (en) | Wheat seedling planting density measuring device and method based on machine vision | |
| CN112991342A (en) | Water level line detection method, device and system based on water level gauge image |
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 |