CN113378698A - Mountain area steep slope pebble river course average flow velocity measurement method utilizing image recognition - Google Patents
Mountain area steep slope pebble river course average flow velocity measurement method utilizing image recognition Download PDFInfo
- Publication number
- CN113378698A CN113378698A CN202110637890.7A CN202110637890A CN113378698A CN 113378698 A CN113378698 A CN 113378698A CN 202110637890 A CN202110637890 A CN 202110637890A CN 113378698 A CN113378698 A CN 113378698A
- Authority
- CN
- China
- Prior art keywords
- measuring
- river
- section
- flow velocity
- average flow
- 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
- 238000000691 measurement method Methods 0.000 title description 5
- 239000003086 colorant Substances 0.000 claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 50
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 61
- 238000005259 measurement Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000012937 correction Methods 0.000 claims description 15
- 150000001875 compounds Chemical class 0.000 claims description 6
- 238000011144 upstream manufacturing Methods 0.000 claims description 6
- 239000012286 potassium permanganate Substances 0.000 claims description 4
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical group [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 239000003795 chemical substances by application Substances 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000012360 testing method Methods 0.000 description 18
- 239000000975 dye Substances 0.000 description 8
- 239000002245 particle Substances 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 241001270131 Agaricus moelleri Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 239000000700 radioactive tracer Substances 0.000 description 2
- 230000035484 reaction time Effects 0.000 description 2
- 239000004576 sand Substances 0.000 description 2
- 239000013049 sediment Substances 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 238000006424 Flood reaction Methods 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000009918 complex formation Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 150000003109 potassium Chemical class 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
- G01P5/18—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft by measuring the time taken to traverse a fixed distance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Indicating Or Recording The Presence, Absence, Or Direction Of Movement (AREA)
Abstract
The invention discloses a method for measuring the average flow velocity of mountain steep slope gravel and river channels by utilizing image recognition, which solves the technical problem that the method for effectively measuring the average flow velocity of mountain steep slope gravel and river channels in the prior art is lacked. The method comprises the following steps: selecting a representative river reach as a measuring river reach and installing video equipment; collecting a coloring agent video; preprocessing a video; determining and binarizing the boundary of a coloring agent in the picture; obtaining the corresponding Euclidean distance value change at each moment by using different color spaces; counting the time of the Euclidean distance value of the corresponding color space of each section reaching the front edge of each section, the time of the maximum value reaching the section and the time of the mass center of the stain cloud group reaching the section; calculating three characteristic flow rates of the measured river reach; a representative average flow rate for the steep hill gravel bed was calculated. The method for measuring the average flow velocity of the steep-slope gravel river bed by utilizing the three characteristic velocities of the coloring agent has the advantages of simplicity, effectiveness and low cost.
Description
Technical Field
The invention relates to the technical field of river flow velocity measurement, in particular to a method for measuring average flow velocity of mountain steep slope gravel river channels by utilizing image recognition.
Background
The river bed of the steep slope river in the mountainous area generally consists of wide-grade egg gravel particles, the structural form of the bed surface is stable, and the egg gravel river bed widely exists in the mountainous area in the southwest of China in nature and is mainly concentrated in the three provinces of Yuanduichuan. The surface of the river bed usually has particles with larger sizes such as pebbles, gravels, boulders and the like carried by landslides, debris flows and torrential floods, shallow water flow is often formed when the flow rate is small in a dry period, namely, the pebble particles on the bed surface are in the same order of magnitude as the average water depth of the river channel, and compared with the deep water condition, the rough characteristic of the pebble-gravel bed surface is obviously highlighted, so that the changes of water flow, bed surface resistance and upstream river bed load starting transport are directly influenced. Compared with alluvial rivers, shallow water gravel type river channels in mountainous areas have not received corresponding attention. In addition to this, more important is the pebble river course in shallow waters, where aquatic organisms (benthonic animals, plants, microorganisms) evolve and grow under the influence of the water flow characteristics. After each flood, the aquatic habitat consisting of a plurality of gravel and river bed structures continues to grow and multiply after being damaged, so the biological diversity of the gravel river channel in the shallow water period is closely related to the overall development of the mountain river basin.
Mountain rivers have various micro landforms, and usually develop to form structures such as deep stepped ponds, ribs, clusters and the like. The average flow velocity of the river channel is a basic hydraulic factor reflecting the movement characteristics of the micro-landform water flow, and plays an important role in mountain torrent evolution, disaster prevention and control, water ecological restoration and the like. The complex riverbed structure and the complex riverbed shape of the mountainous river cause the average flow velocity of the riverway to have the characteristics of various complex formation mechanisms and difficult theoretical quantification, thereby further influencing the means for measuring the average flow velocity of the mountainous river.
Since the measurement of flow velocity of steep-slope gravel riverbed is challenging both in the field and in the laboratory, a large number of researchers have predicted the average flow velocity from the derived empirical flow resistance relationship. At present, the measurement of the average flow velocity of the river in the mountainous area mainly faces the following measurement problems: (1) the shallow water of the gravel-egg riverway has outstanding characteristics, and the depth of the water flow is the same as the particle size of the sediment; (2) the water depth of each form unit of the same river section has high anisotropy in space and time; (3) strong bed load transport fluctuations are caused by the movement and rapid changes of the pebble bed; (4) it is dangerous to measure in the vicinity of a rapid stream.
The existing shallow water measurement technology mainly focuses on slope surface flow measurement, and generally adopts tracer substances such as dyes of various colors, salts and floating substances for measurement. However, the applicant has found that the use of tracer material to measure flow rate of steep hill pebble river beds presents at least the following difficulties: compared with the slope surface flow, the steep-slope gravel bed flow has more unsubmerged particles and complex sediments, and the background color identification is influenced. Since image segmentation is the first step in image analysis and boundary detection, which is one of the most difficult tasks in image processing, it determines the accuracy of the final analysis result. When the flow velocity of the water tank is measured, shadow, transparency, highlight, reflection and the like are easily generated on the water surface by natural light, and the phenomenon of seriously influencing the confirmation of the diffusion boundary of the coloring agent is easily generated. Therefore, the stain boundaries based on the original image or the enhanced image are not easily separated by the traditional image segmentation algorithm, such as Roberts, Sobel and Prewitt operators, and further the progress of stain flow velocity from manual identification to automatic identification by a computer is hindered to a certain extent, so that effective image parameters need to be selected again for boundary identification. Therefore, it is necessary to develop a technology suitable for measuring the average flow velocity of the steep slope gravel river in the mountainous area.
Disclosure of Invention
The invention aims to provide a method for measuring the average flow velocity of mountain area steep slope gravel river channel by utilizing image recognition, and solves the technical problem that the method for effectively measuring the average flow velocity of mountain area steep slope gravel river channel is lacked in the prior art. The various technical effects that can be produced by the preferred technical solution of the present invention are described in detail below.
In order to achieve the purpose, the invention provides the following technical scheme:
the invention relates to a method for measuring average flow velocity of hilly region steep slope gravel river course by utilizing image recognition, which comprises the following steps:
s1: selecting a representative river reach as a measuring river reach, measuring the distance of the measuring river reach to be L, vertically installing a video recording device above the measuring river reach and recording the whole flowing water of the measuring river reach;
s2: the video recording equipment starts video recording after being installed, a coloring agent is poured into the center of the river channel at the upstream of the measuring river reach, and the video recording is stopped when the coloring agent is not found in the measuring river reach;
s3: cutting out a video of the coloring agent in the measuring river reach, and extracting each frame image of the coloring agent in the video according to the frame number;
s4: determining and binarizing the boundary of the coloring agent in the picture;
s5: separating the picture into different components according to different color spaces, counting component values of pixel points of a region with the colorant on each section in the pictures at all moments, obtaining average component values of the sections, and obtaining corresponding Euclidean distance value changes at each moment at each section by using the different color spaces;
s6: counting the time of the Euclidean distance value of the corresponding color space of each section reaching the front edge of each section, the time of the maximum value reaching the section and the time of the mass center of the stain cloud group reaching the section;
s7: obtaining three characteristic flow rates of the measured river reach through the slopes of the Euclidean distance values and the calculated time according to the time of the Euclidean distance values of the corresponding color spaces of each section reaching the front edge of each section, the time of the maximum value reaching the section and the calculated time of the mass center of the stain cloud cluster reaching the section;
s8: and multiplying the three characteristic flow rates obtained by using the coloring agent by a relevant correction coefficient to obtain a representative average flow rate of the steep-slope gravel river bed.
According to a preferred embodiment, in step S1, the distance L between the river reach and the river reach is 1-3 m; the video recording device is a camera or a video camera, and the number of frames for video recording is at least 25 frames/s.
According to a preferred embodiment, in step S2, the coloring agent is a saturated potassium permanganate solution.
According to a preferred embodiment, in step S4, the colorant region is divided using the H and S components of the HSV color space, wherein regions of H >150 and S >26 are determined as the regions where the colorant is present; and then performing edge protection and denoising by using a bilateral filter, and then performing binarization operation.
According to a preferred embodiment, in step S5, the picture is separated into different components according to GL, RGB and HSV color spaces.
According to a preferred embodiment, the Euclidean distance value of GL color space is calculated as:
EDGL(t)＝GL(t)-GLb
in the formula, EDGL(t) is the Euclidean distance value of GL color space, GL (t) is the average gray level of pixel points of each cross section with a dye agent area at t moment, t is time, GLbMeasuring GL value of the river reach river channel photo when no coloring agent appears;
the Euclidean distance value calculation formula of the HSV color space is as follows:
in the formula, EDHSV(t) is the Euclidean distance value of HSV color space, H (t), S (t), V (t) are respectively the H, S and V average values of pixel points of each section with a colorant area at the time t, t is the time, Hb，Sb，VbAre respectively asMeasuring H, S and V of the river section river channel photo when no coloring agent appears;
the Euclidean distance value calculation formula of the RGB color space is as follows:
in the formula, EDRGB(t) is the Euclidean distance value of RGB color space, R (t), G (t), B (t) are respectively the average values of R, G and B of the pixel points of each section with the colorant area at the time t, t is time, R is the average value of the R, G and Bb，Gb，BbR, G and B of the river section river channel photo are measured when no coloring agent appears.
According to a preferred embodiment, in step S6, the time when the centroid of the colorant cloud reaches the section n
The calculation formula of (2) is as follows:
in the formula (I), the compound is shown in the specification,
is at Ti nThe Euclidean distance values of different components on a time n section, n is the number of pixel points along the water flow direction or the position of the section, i is time count, and k is total measurement time.
According to a preferred embodiment, in step S7, the average flow velocity of the river reach is measured by the formula:
V＝dAC(n)/dt
wherein V is the characteristic average flow velocity of the river section measured by using the stain, AC (n) is the Euclidean distance value at the section n, and ED is the valueGL(t)，EDHSV(t)，EDRGB(t)。
According to a preferred embodiment, the calculation formula of the representative average flow velocity of the steep-slope gravel bed in step S8 is as follows:
Va＝α·Us；Va＝β·Up；Va＝γ·Uc；
in the formula, Us is the leading edge speed of the stain obtained by the method in the step S7, Up is the maximum arrival speed of the stain obtained by the method in the step S7, Uc is the centroid arrival speed of the stain cloud obtained by the method in the step S7, Va is the finally calculated average flow velocity, and α, β and γ are all correction coefficients.
According to a preferred embodiment, the correction coefficient calculation formula is determined according to the following formula:
α＝-0.622ln(Fr)+0.8998
β＝-0.869ln(Fr)+0.9874
γ＝-0.932ln(Fr)+0.9205
in the formula (I), the compound is shown in the specification,
is the Froude number, haFor measuring water depth, g is local gravity acceleration, and g is 9.81m/s2。
The method for measuring the average flow velocity of the steep slope gravel river in the mountainous area by utilizing image recognition at least has the following beneficial technical effects:
according to the mountain area steep slope gravel river course average flow velocity measurement method based on image recognition, firstly, the change trend of a coloring agent along with time is obtained through coloring agent tracing recognition, and then relevant correction parameters are determined according to a water tank test to obtain the river course average flow velocity; secondly, the technology for determining the boundary of the stain in the image can reduce the uncertainty caused by time error and observer reaction time, and meanwhile, the method can provide opportunities for batch processing of a large number of experimental results; and thirdly, the local flow field of the measuring section cannot be interfered by the coloring agent image recognition technology, so that the measured result is more accurate and reasonable.
The method for measuring the average flow velocity of the mountain steep slope gravel river channel by utilizing image recognition solves the technical problem that the method for effectively measuring the average flow velocity of the mountain steep slope gravel river channel is lacked in the prior art.
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, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of an average flow velocity measuring device for steep hill gravel river channels in mountainous areas by image recognition according to a preferred embodiment of the present invention;
FIG. 2 is a graph of the results of a preferred embodiment of stain boundary identification on a pebble river bed in accordance with the present invention;
FIG. 3(a) is a graph of the variation of Euclidean distance values over time for a section of the invention;
FIG. 3(b) is a graph of the time-distance relationship of Euclidean distance values of a section of the present invention to the section;
FIG. 4 is a graph of the relationship of a preferred embodiment of the three correction factors of the present invention.
In the figure: 1. a water tank; 2. a pool; 3. a flat-top weir; 4. a honeycomb tube; 5. a colorant pouring box; 6. PVC board; 7. measuring a segment marker post; 8. a video recorder; 9. a computer.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
The method for measuring the average flow velocity of the steep slope gravel river in the mountainous area by using image recognition according to the present embodiment is described in detail with reference to the accompanying drawings 1 to 4 of the specification.
In the method for measuring the average flow velocity of the mountain steep slope gravel river channel by using image recognition, the basic idea is to obtain the change trend of the coloring agent along with time through coloring agent tracing recognition, and then determine the relevant correction parameters according to a water tank test to obtain the average flow velocity of the river channel. Specifically, the method comprises the following steps:
s1: selecting a representative river reach as a measuring river reach, wherein the distance of the measuring river reach is L, and vertically installing a video recording device above the measuring river reach to record the whole flowing water of the measuring river reach. Preferably, the distance L of the measured river reach is 1-3 m; the video recording device is a camera or a video camera, and the number of frames for video recording is at least 25 frames/s. More preferably, the distance L of the river reach is 2 m.
S2: and starting video recording after the video recording equipment is installed, pouring the coloring agent into the center of the river channel at the upstream of the measuring river reach, and stopping video recording when the coloring agent is not found in the measuring river reach. Preferably, the coloring agent is a saturated potassium permanganate solution. The saturated potassium permanganate solution is red, which is convenient for observation.
S3: cutting out the video of the coloring agent in the measuring river reach, and extracting each frame image of the coloring agent in the video according to the frame number. And the video is cut to the area only reserved for measuring the river reach, so that the workload of picture processing can be reduced.
S4: and determining the boundary of the stain in the picture and carrying out binarization. Preferably, the dye region is divided by using H and S components of the HSV color space, wherein the regions with H >150 and S >26 are determined as the regions where the dyes exist; and then performing edge protection and denoising by using a bilateral filter, and then performing binarization operation. The preferred technical scheme of the embodiment can obviously determine the stain motion contour under the high-interference background based on the threshold H >150 and S >26 after the separation of the HSV color space.
S5: and separating the picture into different components according to different color spaces, counting the component values of pixel points of the areas with the colorant on each section in the pictures at all the moments, obtaining the average component value of the section, and obtaining the corresponding Euclidean distance value change at each moment by using the different color spaces at each section. Preferably, the picture is separated into different components according to GL, RGB and HSV color spaces.
More preferably, the Euclidean distance value in GL color space is calculated by the formula:
EDGL(t)＝GL(t)-GLb
in the formula, EDGL(t) is the Euclidean distance value of GL color space, GL (t) is the average gray level of pixel points of each cross section with a dye agent area at t moment, t is time, GLbMeasuring GL value of the river reach river channel photo when no coloring agent appears;
the Euclidean distance value calculation formula of the HSV color space is as follows:
in the formula, EDHSV(t) is the Euclidean distance value of HSV color space, H (t), S (t), V (t) are respectively the H, S and V average values of pixel points of each section with a colorant area at the time t, t is the time, Hb，Sb，VbRespectively measuring H, S and V of a river course photo of the river reach when no coloring agent appears;
the Euclidean distance value calculation formula of the RGB color space is as follows:
in the formula, EDRGB(t) is the Euclidean distance value of RGB color space, R (t), G (t), B (t) are respectively the average values of R, G and B of the pixel points of each section with the colorant area at the time t, t is time, R is the average value of the R, G and Bb，Gb，BbR, G and B of the river section river channel photo are measured when no coloring agent appears.
S6: and counting the time of the Euclidean distance value of the corresponding color space of each section to reach the front edge of each section, the time of the maximum value to reach the section and calculating the time of the mass center of the stain cloud to reach the section.
Preferably, the time of the mass center of the colorant cloud to reach the section n
The calculation formula of (2) is as follows:
in the formula (I), the compound is shown in the specification,
is at Ti nThe Euclidean distance values of different components on a time n section, n is the number of pixel points along the water flow direction or the position of the section, i is time count, and k is total measurement time.
S7: and obtaining three characteristic flow rates of the measured river reach according to the time of the Euclidean distance value of the corresponding color space of each section to reach the front edge of each section, the time of the maximum value to reach the section and the calculated time of the mass center of the stain cloud cluster to reach the section by the slope of the Euclidean distance value and the calculated time. If the slope is obtained by utilizing the linear fitting relationship and the correlation coefficient is very high, the flow velocity change of the measured river reach is small, and the method is relatively stable and is suitable for being used as the representative average flow velocity of the river channel.
Preferably, in step S7, the calculation formula for measuring the average flow velocity of the river reach is:
V＝dAC(n)/dt
wherein V is the characteristic average flow velocity of the river section measured by using a stain, and AC (n) is the Euclidean distance value at the section n, and respectively EDGL(t)，EDHSV(t)，EDRGB(t) of (d). By calculating Euclidean distance value (ED)GL(t)，EDHSV(t)，EDRGB(t)) and the slope sides of the three times obtained in the step S6 obtain three characteristic flow rates of the measured river reach, namely Us, Up and Uc.
S8: and multiplying the three characteristic flow rates obtained by using the coloring agent by a relevant correction coefficient to obtain a representative average flow rate of the steep-slope gravel river bed.
Preferably, the calculation formula of the average flow velocity of the steep-slope gravel riverbed is as follows:
Va＝α·Us；Va＝β·Up；Va＝γ·Uc；
in the formula, Us is the leading edge speed of the stain obtained by the method in the step S7, Up is the maximum arrival speed of the stain obtained by the method in the step S7, Uc is the centroid arrival speed of the stain cloud obtained by the method in the step S7, Va is the finally calculated average flow velocity, and α, β and γ are all correction coefficients.
More preferably, the correction coefficient calculation formula is determined according to the following formula:
α＝-0.622ln(Fr)+0.8998
β＝-0.869ln(Fr)+0.9874
γ＝-0.932ln(Fr)+0.9205
in the formula (I), the compound is shown in the specification,
is the Froude number, haFor measuring water depth, g is local gravity acceleration, and g is 9.81m/s2。
In the method for measuring the average flow velocity of the steep hill gravel river channel in the mountainous area by using image recognition, firstly, the diffusion change of the coloring agent under the influence of water flow and terrain in the measured river section is obtained, and the change of the water flow velocity can be calculated out through the change of the concentration of the coloring agent; secondly, the technology for determining the boundary of the stain in the image can reduce the uncertainty caused by time error and observer reaction time, and meanwhile, the method can provide opportunities for batch processing of a large number of experimental results; and thirdly, the local flow field of the measuring section cannot be interfered by the coloring agent image recognition technology, so that the measured result is more accurate and reasonable. That is, the method for measuring the average flow velocity of the mountain area steep slope gravel river channel by using image recognition in the embodiment solves the technical problem that a method for effectively measuring the average flow velocity of the mountain area steep slope gravel river channel is lacked in the prior art.
The method for measuring the average flow velocity of the gravel and river on the steep slope in the mountainous area by using image recognition provided by the embodiment is explained in detail through an indoor glass water tank simulation test.
1. The purpose of the test is as follows: and (4) testing whether the method for measuring the average flow velocity of the steep slope gravel river channel in the mountainous area is reasonable and effective by using a water tank test result.
2. Test equipment: the main equipment is shown in Table 1
TABLE 1 Instrument and equipment for mountain area steep slope pebble river course average flow velocity measurement test
3. The test method comprises the following steps:
fig. 1 is a schematic diagram of a preferred embodiment of a mountain area steep slope pebble river course average flow velocity measuring device using image recognition. Referring to fig. 1, the measuring device comprises a water tank 1, a water basin 2, a video recorder 8 and a computer 9. Preferably, the water tank 2 is provided with a flat-top weir 3. Preferably, the water tank 1 is communicated with the water tank 2, and a honeycomb tube 4 is provided at a water outlet of the water tank 2 to allow water in the water tank 2 to slowly flow into the water tank 1. Preferably, two measuring section marking rods 7 are arranged on the water tank 1 to mark the positions of the measuring sections. Preferably, the water tank 1 is further provided with a coloring agent pouring box 5 and a PVC plate 6, wherein the coloring agent pouring box 5 is located upstream of the measuring section, and the PVC plate 6 is located at the tail of the water tank 1. Preferably, the video recorder 8 and the computer 9 are mounted above the measuring section. Prior to testing, the test apparatus was mounted in the configuration shown in fig. 1.
Preferably, the water tank 1 is a straight glass water tank, the length of the water tank 1 is 7.5 meters, the width is 0.4 meter, the height is 0.4 meter, and the gradient of the water tank 1 is 10 degrees. The 1m position of the inlet of the water tank 1 is provided with a transition region by using immobile large particles, and the immobile large particles cannot be started and coarsened even under the condition of the maximum flow velocity; non-uniform gravel bed sand is paved on the water tank 1 with the last 6.5 meters, and the paving thickness is 0.2 meters. And measuring 2 meters downstream at a position 4.5 meters away from the inlet of the water tank 1 as a measuring section shooting. The video recorder 8 is mounted on top of the measurement session so that the measurement session can be completely filmed into the video. The tail of the water tank 1 is fixed on the riverbed by a 0.2 m PVC plate 6 to prevent the bed sand from moving integrally.
Before each working condition is carried out, the small flow is started for 30 minutes, so that other impurities on the bed surface are removed, then the working condition flow is started, and the flow velocity is measured after the downstream has no bed load to move. The flow velocity measurement mainly comprises two methods, namely a traditional water depth-flow method, and a mountain area steep slope gravel river course average flow velocity measurement method utilizing image recognition provided by the embodiment.
The traditional water depth-flow method specifically comprises the following steps: 3 sections are selected by the measuring needle in the measuring section, 5 measuring points are selected for each section to obtain a corresponding water depth value h, and the water passing area A of the section can be obtained by knowing the positions of the 5 measuring points, so that the average flow speed of the section is equal to the flow Q of the known working condition divided by the water depth h. In the experiment, the pebble river bed changes violently, so that the average flow velocity of 3 sections measured by the traditional water depth-flow method is averaged again to obtain the representative average flow velocity Va of the measurement section.
The method for measuring the average flow velocity of the hilly area steep slope gravel river channel by utilizing image recognition specifically comprises the following steps: before the dye has been poured, the recorder 8 is switched on to record the measuring section, whereupon the dye is immediately poured upstream of the measuring section and the recorder 8 is switched off when all the dye has flowed off in the measuring section. And comparing and correcting the representative average flow velocity Va of the measurement section obtained by the traditional water depth-flow method with the flow velocity obtained by the mountain area steep slope gravel river channel average flow velocity measurement method by utilizing image recognition.
The tests are divided into 4 groups of tests according to the flow, each group of tests is repeated for 3 times, 12 groups of tests are accumulated, and test parameters and calculation parameters are summarized in a table 2.
TABLE 2 summary of test and calculated parameters
| Working conditions | Working condition A | Operating mode B | Operating mode C | Operating mode D |
| Flow Q (l/s) | 1.56 | 6.37 | 9.51 | 12.17 |
| Depth of water h (m) | 0.0187 | 0.0384 | 0.0442 | 0.0462 |
| Flow velocity Va (m/s) by water depth-flow method | 0.26 | 0.47 | 0.56 | 0.63 |
4. Stain edge recognition results: the photo of a video at a certain time in any selected test example is processed based on the step S4, and the graph of the dye boundary recognition effect is shown in fig. 2, so that the dye motion contour under the high-interference background can be obviously determined based on the threshold H >150 and S >26 after separation by using HSV color space.
5. Flow rate measurement results: the result shown in fig. 3(a) can be obtained by calculating the stain region obtained in step S4 according to steps S5 and S6. It can be seen from fig. 3(a) that the Euclidean distance value in the color space of each section of the measurement segment increases and then decreases with time, and the Euclidean distance value of the front section is larger than that of the rear section, which characterizes the propagation of the stain. Then, according to step S7, a time-distance relation of each cross section to the cross section is obtained, and a linear function having a slope of the measured segment average flow velocity U of the cross section obtained by using the Euclidean distance value is fitted by the least square method, and the result is shown in fig. 3 (b).
Of course, because the roughness of the gravel-gravel riverbed is large and is influenced by the trails behind large particles and the body resistance of the bed surface, the final average flow velocity of the gravel-gravel riverbed with the steep slope needs to be obtained by using a correction coefficient. The fitting effect of the correction coefficient formula in step 8 on the test example is shown in fig. 4, and the mean flow velocity dispersion points calculated by different Euclidean are distributed on three fitting curves of the correction coefficient, which indicates that the method of the present embodiment is reasonable and effective.
In the description of the present invention, it is to be noted that, unless otherwise specified, "a plurality" means two or more; the terms "upper", "lower", "left", "right", "inner", "outer", "front", "rear", "head", "tail", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, should not be construed as limiting the invention. Furthermore, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should also be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; may be directly connected or indirectly connected through an intermediate. The specific meaning of the above terms in the present invention can be understood as appropriate to those of ordinary skill in the art.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A method for measuring average flow velocity of mountain steep slope gravel river course by utilizing image recognition is characterized by comprising the following steps:
s1: selecting a representative river reach as a measuring river reach, measuring the distance of the measuring river reach to be L, vertically installing a video recording device above the measuring river reach and recording the whole flowing water of the measuring river reach;
s2: the video recording equipment starts video recording after being installed, a coloring agent is poured into the center of the river channel at the upstream of the measuring river reach, and the video recording is stopped when the coloring agent is not found in the measuring river reach;
s3: cutting out a video of the coloring agent in the measuring river reach, and extracting each frame image of the coloring agent in the video according to the frame number;
s4: determining and binarizing the boundary of the coloring agent in the picture;
s5: separating the picture into different components according to different color spaces, counting component values of pixel points of a region with the colorant on each section in the pictures at all moments, obtaining average component values of the sections, and obtaining corresponding Euclidean distance value changes at each moment at each section by using the different color spaces;
s6: counting the time of the Euclidean distance value of the corresponding color space of each section reaching the front edge of each section, the time of the maximum value reaching the section and the time of the mass center of the stain cloud group reaching the section;
s7: obtaining three characteristic flow rates of the measured river reach through the slopes of the Euclidean distance values and the calculated time according to the time of the Euclidean distance values of the corresponding color spaces of each section reaching the front edge of each section, the time of the maximum value reaching the section and the calculated time of the mass center of the stain cloud cluster reaching the section;
s8: and multiplying the three characteristic flow rates obtained by using the coloring agent by a relevant correction coefficient to obtain a representative average flow rate of the steep-slope gravel river bed.
2. The method for measuring the average flow velocity of the steep hill pebble river course in the mountainous area by using the image recognition according to claim 1, wherein in the step S1, the distance L of the measured river reach is 1-3 m; the video recording device is a camera or a video camera, and the number of frames for video recording is at least 25 frames/s.
3. The method for measuring the average flow velocity of the steep hill gravel river channel through image recognition according to claim 1, wherein in the step S2, the coloring agent is a saturated potassium permanganate solution.
4. The method for measuring the average flow velocity of the steep hill gravel river course in the mountainous area through the image recognition according to claim 1, wherein in step S4, the dye region is divided by using H and S components of HSV color space, wherein the regions with H >150 and S >26 are determined as the regions where the dye exists; and then performing edge protection and denoising by using a bilateral filter, and then performing binarization operation.
5. The method for measuring the average flow velocity of the mountain steep slope egg gravel river course by using image recognition according to claim 1, wherein in step S5, the picture is separated into different components according to GL, RGB and HSV color spaces.
6. The method for measuring the average flow velocity of the mountain steep slope egg gravel river channel by utilizing image recognition as claimed in claim 5, wherein the Euclidean distance value calculation formula of GL color space is as follows:
EDGL(t)＝GL(t)-GLb
in the formula, EDGL(t) is the Euclidean distance value of GL color space, GL (t) is the average gray level of pixel points of each cross section with a dye agent area at t moment, t is time, GLbMeasuring GL value of the river reach river channel photo when no coloring agent appears;
the Euclidean distance value calculation formula of the HSV color space is as follows:
in the formula, EDHSV(t) is the Euclidean distance value of HSV color space, H (t), S (t), V (t) are respectively the H, S and V average values of pixel points of each section with a colorant area at the time t, t is the time, Hb，Sb，VbRespectively measuring H, S and V of a river course photo of the river reach when no coloring agent appears;
the Euclidean distance value calculation formula of the RGB color space is as follows:
in the formula, EDRGB(t) is the Euclidean distance value of RGB color space, R (t), G (t), B (t) are respectively the average values of R, G and B of the pixel points of each section with the colorant area at the time t, t is time, R is the average value of the R, G and Bb，Gb，BbR, G and B of the river section river channel photo are measured when no coloring agent appears.
7. The method for measuring the average flow velocity of the steep slope egg gravel river course in the mountainous area through image recognition according to claim 1, wherein in the step S6, the time T for the mass center of the cloud cluster of the coloring agent to reach the section nc nThe calculation formula of (2) is as follows:
in the formula (I), the compound is shown in the specification,
is at Ti nThe Euclidean distance values of different components on a time n section, n is the number of pixel points along the water flow direction or the position of the section, i is time count, and k is total measurement time.
8. The method for measuring the average flow velocity of the steep hill gravel river channel by using the image recognition according to claim 1, wherein in the step S7, the calculation formula for measuring the average flow velocity of the river reach is as follows:
V＝dAC(n)/dt
wherein V is the characteristic average flow velocity of the river section measured by using the stain, AC (n) is the Euclidean distance value at the section n, and ED is the valueGL(t)，EDHSV(t)，EDRGB(t)。
9. The method for measuring the average flow velocity of the steep hill gravel river bed in the mountainous area by using the image recognition according to claim 1, wherein in the step S8, the calculation formula of the average flow velocity of the steep hill gravel river bed is as follows:
Va＝α·Us；Va＝β·Up；Va＝γ·Uc；
in the formula, Us is the leading edge speed of the stain obtained by the method in the step S7, Up is the maximum arrival speed of the stain obtained by the method in the step S7, Uc is the centroid arrival speed of the stain cloud obtained by the method in the step S7, Va is the finally calculated average flow velocity, and α, β and γ are all correction coefficients.
10. The method for measuring the average flow velocity of the mountain area steep slope pebble river course by utilizing image recognition according to claim 9, wherein the correction coefficient calculation formula is determined according to the following formula:
α＝-0.622ln(Fr)+0.8998
β＝-0.869ln(Fr)+0.9874
γ＝-0.932ln(Fr)+0.9205
in the formula (I), the compound is shown in the specification,
is the Froude number, haFor measuring water depth, g is local gravity acceleration, and g is 9.81m/s2。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110637890.7A CN113378698B (en) | 2021-06-08 | 2021-06-08 | Mountain area steep slope gravel river channel average flow velocity measurement method by utilizing image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110637890.7A CN113378698B (en) | 2021-06-08 | 2021-06-08 | Mountain area steep slope gravel river channel average flow velocity measurement method by utilizing image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113378698A true CN113378698A (en) | 2021-09-10 |
| CN113378698B CN113378698B (en) | 2022-07-29 |
Family
ID=77576544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110637890.7A Expired - Fee Related CN113378698B (en) | 2021-06-08 | 2021-06-08 | Mountain area steep slope gravel river channel average flow velocity measurement method by utilizing image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113378698B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114061902A (en) * | 2021-11-29 | 2022-02-18 | 重庆交通大学 | Real-time monitoring device, method and system for egg and gravel transportation based on image method |
| CN115100436A (en) * | 2022-08-29 | 2022-09-23 | 江苏永银化纤有限公司 | Colored silk dyeing method based on image recognition |
| CN117709240A (en) * | 2024-01-12 | 2024-03-15 | 北方工业大学 | Method and system for obtaining tundish water model speed cloud image based on image processing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106895807A (en) * | 2017-01-04 | 2017-06-27 | 四川大学 | A kind of river course vegetation group wake zone measurement of length method |
| CN107421853A (en) * | 2017-04-26 | 2017-12-01 | 青岛理工大学 | A kind of isoconcentrate rapid scan method of river transverse diffusion coeficient |
| CN109583703A (en) * | 2018-11-02 | 2019-04-05 | 河海大学 | A method of it quantitatively defining non-sticky bed-sit and starts critical indicator |
| CN112215903A (en) * | 2020-10-14 | 2021-01-12 | 四川大学锦江学院 | Method and device for detecting river flow velocity based on ultrasonic wave and optical flow method |
| CN112816646A (en) * | 2021-01-22 | 2021-05-18 | 同济大学 | Grid water quality monitoring-based riverway sewage outlet tracing method |
-
2021
- 2021-06-08 CN CN202110637890.7A patent/CN113378698B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106895807A (en) * | 2017-01-04 | 2017-06-27 | 四川大学 | A kind of river course vegetation group wake zone measurement of length method |
| CN107421853A (en) * | 2017-04-26 | 2017-12-01 | 青岛理工大学 | A kind of isoconcentrate rapid scan method of river transverse diffusion coeficient |
| CN109583703A (en) * | 2018-11-02 | 2019-04-05 | 河海大学 | A method of it quantitatively defining non-sticky bed-sit and starts critical indicator |
| CN112215903A (en) * | 2020-10-14 | 2021-01-12 | 四川大学锦江学院 | Method and device for detecting river flow velocity based on ultrasonic wave and optical flow method |
| CN112816646A (en) * | 2021-01-22 | 2021-05-18 | 同济大学 | Grid water quality monitoring-based riverway sewage outlet tracing method |
Non-Patent Citations (3)
| Title |
|---|
| XUFENG YAN 等: "flow structure and turbulece in partly-vegetated open channel", 《PROCEEDINGS OF THE SECOND CONFERENCE OF GLOBAL CHINESE SCHOLAR ON HYDRODYNAMI》 * |
| 叶晨 等: "山区河流漂石阶梯阵列对水流结构影响的试验研究", 《工程科学与技术》 * |
| 郑媛予 等: "山区浅水河道漂石对水流运动影响的试验研究", 《中国水利学会2016学术年会论文集》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114061902A (en) * | 2021-11-29 | 2022-02-18 | 重庆交通大学 | Real-time monitoring device, method and system for egg and gravel transportation based on image method |
| CN115100436A (en) * | 2022-08-29 | 2022-09-23 | 江苏永银化纤有限公司 | Colored silk dyeing method based on image recognition |
| CN117709240A (en) * | 2024-01-12 | 2024-03-15 | 北方工业大学 | Method and system for obtaining tundish water model speed cloud image based on image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113378698B (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113378698B (en) | Mountain area steep slope gravel river channel average flow velocity measurement method by utilizing image recognition | |
| Garde et al. | Mechanics of sediment transportation and alluvial stream problems | |
| Oehy et al. | Effects of obstacles and jets on reservoir sedimentation due to turbidity currents | |
| Yagci et al. | Reach-scale experiments on deposition process in vegetated channel: Suspended sediment capturing ability and backwater effect of instream plants | |
| CN109736259B (en) | Hydraulic determination method for mountain river compound beach utilization range and flood control safety position | |
| Wang et al. | Interactions between large boundary roughness and high inflow turbulence in open channel: A physical study into turbulence properties to enhance upstream fish migration | |
| Bakri et al. | Distribution pattern of water salinity analysis in Jeneberang river estuary using ArcGIS | |
| Tritthart et al. | Numerical study of morphodynamics and ecological parameters following alternative groyne layouts at the Danube River | |
| Sidorchuk et al. | Variability of shallow overland flow velocity and soil aggregate transport observed with digital videography | |
| Lin et al. | The study on morphological evolution process of gully headcut erosion in granite red soil hilly area based on an in situ scouring experiment | |
| Litts et al. | Mapping potential spawning substrate for Shortnose and Atlantic sturgeon in coastal plain rivers of Georgia using low-cost side-scan sonar | |
| Benson et al. | Measurement of peak discharge by indirect methods | |
| Fu et al. | Local hydraulic jump effects on sediment deposition in open-channel flume experiments | |
| Aziz et al. | Experimental study of morphological changes and flow structure around the vegetated groyne | |
| Wohl | Channel-unit hydraulics on a pool-riffle channel | |
| Vietz et al. | Flows that form: the hydromorphology of concave-bank bench formation in the Ovens River, Australia | |
| Santacruz et al. | River Velocity through LSPTV Technique using UAVs | |
| Rosero Legarda et al. | River Velocity through LSPTV Technique using UAVs | |
| Freire et al. | On ventilated corner baffles for box culvert barrel: a physical investigation | |
| Wong et al. | Reynolds stresses and secondary motion in box culvert barrel: Implications in terms of upstream fish passage at road crossings | |
| Gualtieri et al. | Observations of hydrodynamics and sediment transport in the Orinoco River | |
| Nagy | Hydraulic evaluation of emerged and submerged spur-dikes: temporal bed evolution and equilibrium state characteristics | |
| Barahimi et al. | Flow structure and shear stress in the presence of both ice cover on water surface and leafless vegetation in channel bed | |
| Camenen et al. | Field experiment on the dynamics of fine sediments over a gravel bar in an alpine gravel-bed river | |
| Kobayashi et al. | Field observations of vertical profiles of microplastic concentrations in a river |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220729 |