CN117333794A - River surface flow velocity measurement method and system based on scene integration - Google Patents
River surface flow velocity measurement method and system based on scene integration Download PDFInfo
- Publication number
- CN117333794A CN117333794A CN202311182599.0A CN202311182599A CN117333794A CN 117333794 A CN117333794 A CN 117333794A CN 202311182599 A CN202311182599 A CN 202311182599A CN 117333794 A CN117333794 A CN 117333794A
- Authority
- CN
- China
- Prior art keywords
- river
- result
- flow
- flow rate
- tracer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000010354 integration Effects 0.000 title claims abstract description 65
- 238000000691 measurement method Methods 0.000 title claims abstract description 33
- 239000000700 radioactive tracer Substances 0.000 claims abstract description 107
- 238000000034 method Methods 0.000 claims abstract description 73
- 239000002245 particle Substances 0.000 claims abstract description 41
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 230000003287 optical effect Effects 0.000 claims description 31
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000013527 convolutional neural network Methods 0.000 claims description 22
- 238000005259 measurement Methods 0.000 claims description 19
- 238000010586 diagram Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000003709 image segmentation Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims 1
- 238000000917 particle-image velocimetry Methods 0.000 description 7
- 238000000827 velocimetry Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000000037 particle-tracking velocimetry Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/269—Analysis of motion using gradient-based methods
-
- 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
-
- 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
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Indicating Or Recording The Presence, Absence, Or Direction Of Movement (AREA)
Abstract
The invention provides a river surface flow velocity measurement method and system based on scene integration, comprising the following steps: preprocessing river video data to obtain river morphology, river flow state, tracer existence information, tracer particle size and tracer density; determining scene type integral, and integrating corresponding different river velocity measuring methods to obtain a scene total integral; determining a river surface flow velocity calculated by adopting a river velocity measuring method corresponding to the highest scene total integral to obtain a first flow velocity result; according to different distribution speed intervals in which the first flow speed result is located, calculating the river surface flow speed by adopting different speed measuring methods to obtain a second flow speed result; and integrating the first flow rate result and the second flow rate result, and outputting an integrated flow rate result. According to the invention, the most suitable speed measuring method is determined by comparing the difference of various river surface speed measuring methods and combining different river section states in a river scene in an integral mode, and the accuracy of the speed measuring result is further improved according to the comprehensive flow velocity result.
Description
Technical Field
The invention relates to the technical field of hydrological flow measurement, in particular to a river surface flow velocity measurement method and system based on scene integration.
Background
In the current non-contact measuring river water flow velocity process, a non-contact measuring method is mainly adopted, and compared with the traditional method for placing instruments and related equipment in a river, the method has the advantages of low implementation cost, higher accuracy, environmental influence resistance and the like.
Currently, the non-contact method mainly includes: optical flow velocimetry (Optical Flow Velocimetry, OPV), large-scale particle image velocimetry (Large Scale Particle Image Velocimetry, LSPIV), spatiotemporal image velocimetry (Spatiotemporal Image Velocimetry, STIV), scale-invariant feature transform velocimetry (Scale Invariant Feature Transform Velocimetry, SIFTV), particle tracking velocimetry (Particle Tacking Velocimetry, PTV), and particle image velocimetry (Particle Image Velocimetry, PIV). However, when faced with different scenarios, the above methods have different drawbacks, such as the inability of OPV to measure high flow rates, and the accuracy of flow measurement of STIV is inferior to PIV, SIFTV and PTV when natural trace particles are present on the river cross-section.
Therefore, when facing different river section states, how to select an optimal flow velocity calculation method according to the scene so as to ensure that the obtained speed measurement result is accurate, and no effective solution exists yet.
Disclosure of Invention
The invention provides a river surface flow velocity measurement method and system based on scene integration, which are used for solving the defect that flow velocity information cannot be effectively and accurately obtained by adopting a single velocity measurement method when the river section state in the river surface velocity measurement is complex in the prior art.
In a first aspect, the present invention provides a river surface flow rate measurement method based on scene integration, including:
acquiring river video data, preprocessing the river video data, and acquiring river morphology, river flow state, tracer existence information, tracer particle size and tracer density of a video image;
determining scene type integral, and respectively integrating the river morphology, the river flow state, the tracer existence information, the tracer particle size and the tracer density based on the scene type integral, wherein the different river velocity measuring methods correspond to the tracer particle size and the tracer density to obtain a scene total integral;
determining a river surface flow velocity calculated by adopting a river velocity measuring method corresponding to the highest scene total integral to obtain a first flow velocity result;
according to different distribution speed intervals where the first flow speed result is located, calculating river surface flow speed by adopting different speed measuring methods to obtain a second flow speed result;
and integrating the first flow rate result and the second flow rate result, and outputting an integrated flow rate result.
According to the river surface flow velocity measuring method based on scene integration, after determining scene type integration, the river surface flow velocity measuring method further comprises the following steps:
and integrating different river velocity measuring methods corresponding to different terminal scenes based on the scene type integration to obtain a scene total integration.
According to the river surface flow velocity measurement method based on scene integration, provided by the invention, river video data are collected, the river video data are preprocessed, and the river morphology, the river flow state, the tracer existence information, the tracer particle size and the tracer density of video images are obtained, and the method comprises the following steps:
intercepting river video data with preset duration based on a preset video frame rate and a preset video frame size;
extracting frames from the river video data to obtain image frames, and converting the image frames into gray level images;
acquiring the river channel length and the river channel width of a river, and classifying the river channel length and the river channel width by adopting a convolutional neural network to obtain a river form;
calculating to obtain river flow state by a preset optical flow method;
image segmentation is carried out on the gray level diagram, a river surface tracer and a background in the gray level diagram are separated, the river surface tracer is classified by adopting a convolutional neural network, and the particle size and the number of the tracer are counted;
and carrying out grid division on the gray level map, and counting grid division results through a convolutional neural network to obtain tracer density.
According to the river surface flow velocity measurement method based on scene integration, which is provided by the invention, the river flow state is obtained by calculation through a preset optical flow method, and the method comprises the following steps:
carrying out optical flow estimation on the first frame image by adopting a Lucas-Kanade algorithm to obtain an optical flow direction and an optical flow speed;
and calculating the optical flow direction and the optical flow speed by using a convolutional neural network to obtain the river flow state.
According to the river surface flow velocity measurement method based on scene integration, which is provided by the invention, the gray level diagram is subjected to grid division, and the grid division result is counted through a convolutional neural network to obtain the tracer density, and the method comprises the following steps:
dividing the gray scale image into a plurality of grids based on a preset grid division size;
removing grid results with 0 in the grids by using the convolutional neural network, and calculating the average value of the characteristic points of the residual grids in the grids to obtain the number of the characteristic points in the unit grid;
the tracer density is determined from the number of feature points within the unit grid.
According to the river surface flow velocity measuring method based on scene integration, which is provided by the invention, integration is carried out on different river velocity measuring methods corresponding to different terminal scenes based on the scene type integration, so as to obtain the total scene integration, and the method comprises the following steps:
adopting the river form, the river flow state and the tracer existence information to combine to form different terminal scenes;
and accumulating any morphological integral in the river morphology, any flow integral in the river flow state and any existence integral in the tracer existence information to obtain a scene total integral.
According to the river surface flow velocity measuring method based on scene integration, which is provided by the invention, according to different distribution velocity intervals where the first flow velocity result is located, different velocity measuring methods are adopted to calculate the river surface flow velocity, so as to obtain a second flow velocity result, and the river surface flow velocity measuring method comprises the following steps:
if the first flow rate result is determined to be located in the first distribution speed interval, calculating the river surface flow rate by adopting an optical flow velocity (OPV) measuring method to obtain a second flow rate result;
if the first flow rate result is determined to be located in the second distribution speed interval, calculating the river surface flow rate by adopting the space-time image velocity measurement STIV to obtain a second flow rate result;
if the first flow rate result is determined to be located in the third distribution speed interval, calculating the river surface flow rate by adopting scale invariant feature transform velocity measurement SIFTV to obtain a second flow rate result;
the first distribution speed interval, the second distribution speed interval and the third distribution speed interval are adjacent speed intervals, and the values are sequentially increased.
According to the river surface flow velocity measuring method based on scene integration provided by the invention, the first flow velocity result and the second flow velocity result are synthesized, and the synthesized flow velocity result is output, which comprises the following steps:
comparing the first flow rate result with the second flow rate result to obtain a speed error calculation result;
and if the speed error calculation result is determined to be within a preset error percentage range, taking the first flow speed result as the comprehensive flow speed result, otherwise, carrying out weighting processing on the first flow speed result and the second flow speed result to obtain the comprehensive flow speed result.
In a second aspect, the present invention also provides a river surface flow rate measurement system based on scene integration, including:
the acquisition processing module is used for acquiring river video data, preprocessing the river video data and acquiring river morphology, river flow state, tracer existence information, tracer particle size and tracer density of a video image;
the integration module is used for determining scene type integration, and integrating the river morphology, the river flow state, the tracer existence information, the tracer particle size and the tracer density based on the scene type integration respectively to obtain scene total integration according to different river speed measuring methods corresponding to the tracer particle size and the tracer density;
the first calculation module is used for determining a river velocity measurement method corresponding to the highest scene total integral to calculate the river surface flow velocity, so as to obtain a first flow velocity result;
the second calculation module is used for calculating the river surface flow velocity according to different distribution velocity intervals in which the first flow velocity result is positioned by adopting different velocity measurement methods to obtain a second flow velocity result;
and the synthesis module is used for synthesizing the first flow rate result and the second flow rate result and outputting a synthesized flow rate result.
In a third aspect, the present invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a scene integration based river surface flow rate measurement method as described in any one of the above when the program is executed.
According to the river surface flow velocity measurement method and system based on scene integration, the most suitable velocity measurement method is determined by comparing the differences of various river surface velocity measurement methods and combining different river section states in a river scene in an integration mode, and the accuracy of the flow measurement result is further improved according to the comprehensive flow velocity result, so that the influence of the characteristics of a single flow velocity algorithm on the flow velocity result is avoided.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a river surface flow rate measurement method based on scene integration provided by the invention;
FIG. 2 is a schematic diagram of meshing provided by the present invention;
FIG. 3 is a flow chart of verification of different flow measurement methods provided by the present invention;
FIG. 4 is a schematic diagram of a river surface flow rate measurement system based on scene integration according to the present invention;
fig. 5 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a schematic flow chart of a river surface flow velocity measurement method based on scene integration according to an embodiment of the present invention, as shown in fig. 1, including:
step 100: acquiring river video data, preprocessing the river video data, and acquiring river morphology, river flow state, tracer existence information, tracer particle size and tracer density of a video image;
step 200: determining scene type integral, and respectively integrating the river morphology, the river flow state, the tracer existence information, the tracer particle size and the tracer density based on the scene type integral, wherein the different river velocity measuring methods correspond to the tracer particle size and the tracer density to obtain a scene total integral;
step 300: determining a river surface flow velocity calculated by adopting a river velocity measuring method corresponding to the highest scene total integral to obtain a first flow velocity result;
step 400: according to different distribution speed intervals where the first flow speed result is located, calculating river surface flow speed by adopting different speed measuring methods to obtain a second flow speed result;
step 500: and integrating the first flow rate result and the second flow rate result, and outputting an integrated flow rate result.
Specifically, in the embodiment of the invention, the river video data is acquired by the professional acquisition equipment erected on the side of the target river, and the acquired river video data is preprocessed to obtain the river morphology, the river flow state, the tracer existence information, the tracer particle size and the tracer density in the video image.
According to the river information of the multiple dimensions obtained, different integration systems are defined according to whether different river speed measuring methods are applicable to each scene, integration accumulation is carried out from each dimension, the most suitable river speed measuring method is determined according to the highest integration, a first flow speed result is obtained through calculation, and the first flow speed result is recorded as v a 。
Based on the first flow rate result v a The second flow velocity result v is calculated by adopting different river velocity measurement methods in three different distribution velocity intervals b 。
Finally, the first flow rate result v is compared a And a second flow rate result v b And outputting the comprehensive flow rate result.
According to the invention, the most suitable speed measuring method is determined by comparing the difference of various river surface speed measuring methods and combining different river section states in a river scene in an integral mode, and the accuracy of the speed measuring result is further improved according to the comprehensive flow velocity result.
Based on the above embodiment, collecting river video data, preprocessing the river video data, and obtaining river morphology, river flow state, tracer existence information, tracer particle size and tracer density of a video image, including:
intercepting river video data with preset duration based on a preset video frame rate and a preset video frame size;
extracting frames from the river video data to obtain image frames, and converting the image frames into gray level images;
acquiring the river channel length and the river channel width of a river, and classifying the river channel length and the river channel width by adopting a convolutional neural network to obtain a river form;
calculating to obtain river flow state by a preset optical flow method;
image segmentation is carried out on the gray level diagram, a river surface tracer and a background in the gray level diagram are separated, the river surface tracer is classified by adopting a convolutional neural network, and the particle size and the number of the tracer are counted;
and carrying out grid division on the gray level map, and counting grid division results through a convolutional neural network to obtain tracer density.
The river flow state is obtained by calculation through a preset optical flow method, and the method comprises the following steps:
carrying out optical flow estimation on the first frame image by adopting a Lucas-Kanade algorithm to obtain an optical flow direction and an optical flow speed;
and calculating the optical flow direction and the optical flow speed by using a convolutional neural network to obtain the river flow state.
The method for classifying the gray level image by using the convolutional neural network comprises the steps of:
dividing the gray scale image into a plurality of grids based on a preset grid division size;
removing grid results with 0 in the grids by using the convolutional neural network, and calculating the average value of the characteristic points of the residual grids in the grids to obtain the number of the characteristic points in the unit grid;
the tracer density is determined from the number of feature points within the unit grid.
Specifically, the embodiment of the invention is aimed at preprocessing river video images, and video data with a section of preset duration, such as one minute, is intercepted, wherein the video frame rate is 30fps/s, and the size of each frame is 1920 x 1080;
performing frame extraction processing on the video, converting the video image subjected to the frame extraction processing into a gray level image, separating a river surface tracer from a background through image segmentation, classifying the tracer by adopting a common convolutional neural network, and counting the particle size and the number of the tracer;
river morphology is detected, classification is performed according to the aspect ratio of the river channel through a convolutional neural network, and in the embodiment of the invention, the river channel is divided into curved river channels when the ratio of the width of the river channel to the length of the river channel is 1:3.
And identifying the river flow state, carrying out optical flow estimation on the first frame of image by a Lucas-Kanade algorithm, visualizing the optical flow, using arrows or color codes to represent the direction and speed of the optical flow, and counting the directions of all the arrows by a convolutional neural network to judge that the current river is laminar or turbulent.
And dividing grids according to 100 x 100 in the current frame picture, removing grid results with the statistical value of 0 through a convolutional neural network, and calculating the average value of the feature points in the n remaining grids. Let the number of feature points in a unit be x, the distribution density in the unit be x/10000 (p/px 2 ) The average density of the image is then obtained and the meshing is as shown in figure 2.
Based on the above examples, the present invention integrates the different flow methods by the integration principle shown in table 1, wherein the most suitable score is 3 points, generally 2 points, which can be 1 point, and can not be 0 point.
TABLE 1
The algorithm in Table 1 includes STIV, PTV, PIV, LSPIV and OPV, the river flow regime includes laminar flow and turbulent flow, the river shape includes straight river course and curved river course, the tracer existence information includes the presence and absence of tracer particles, the tracer particle size is divided into two sections with particle size greater than 5cm and less than or equal to 5cm, and the tracer density includes distribution density less than 10 per px 2 The distribution density is between 10 and 30 per px 2 The inter-and distribution density is more than 30/px 2 . And respectively giving different integrals to the scenes, and then summing to obtain the total integral of the scenes. Selecting the algorithm with the highest score to calculate the river surface flow velocity, and obtaining a flow velocity result v a 。
Based on the above embodiment, integrating the different river velocity measurement methods corresponding to the different terminal scenes based on the scene type integral to obtain a scene total integral, including:
adopting the river form, the river flow state and the tracer existence information to combine to form different terminal scenes;
and accumulating any morphological integral in the river morphology, any flow integral in the river flow state and any existence integral in the tracer existence information to obtain a scene total integral.
Specifically, on the basis of the general scene of the embodiment, the embodiment of the invention also considers the integral under the extreme scene, selects the algorithm with the highest score to calculate the river surface flow velocity, and obtains the flow velocity result v a 。
TABLE 2
The following four extreme scenarios are included in table 2:
(1) Laminar flow, straight river course and no trace particle;
(2) Turbulent flow, curved river channel and no trace particles;
(3) Laminar flow, straight river course and trace particles;
(4) Turbulence, bending of the river channel and presence of trace particles.
The embodiment of the invention considers several extreme scenes, and further accumulates the integration in the general scene to distinguish the application degree of different current measurement algorithms in different scenes.
Based on the above embodiment, according to different distribution speed intervals where the first flow speed result is located, calculating the river surface flow speed by using different speed measuring methods to obtain a second flow speed result, including:
if the first flow rate result is determined to be located in the first distribution speed interval, calculating the river surface flow rate by adopting an optical flow velocity (OPV) measuring method to obtain a second flow rate result;
if the first flow rate result is determined to be located in the second distribution speed interval, calculating the river surface flow rate by adopting the space-time image velocity measurement STIV to obtain a second flow rate result;
if the first flow rate result is determined to be located in the third distribution speed interval, calculating the river surface flow rate by adopting scale invariant feature transform velocity measurement SIFTV to obtain a second flow rate result;
the first distribution speed interval, the second distribution speed interval and the third distribution speed interval are adjacent speed intervals, and the values are sequentially increased.
Specifically, the embodiment of the invention pairs the streaming speed result v a Speed result interval identification is carried out, v a <0.5m/s, v is obtained by OPV calculation b ；0.5m/s<v a <5m/s, v is obtained by calculation using STIV b ；v a >5m/s, v is obtained by SIFTV calculation b The method comprises the steps of carrying out a first treatment on the surface of the According to v a The OPV is suitable for estimating the pixel tiny offset in different intervals of the velocity distribution, so that smaller velocity value can be calculated, the STIV needs to calculate the gray gradient change on one velocity measurement line, the gradient change is not obvious and difficult to estimate when the velocity is small, and the systematic error caused by the calculated angle when the velocity is large can not be increased rapidly due to the gradient change (tan value)Stable STFTV can then match large feature shifts.
Based on the above embodiment, synthesizing the first flow rate result and the second flow rate result, outputting a synthesized flow rate result, including:
comparing the first flow rate result with the second flow rate result to obtain a speed error calculation result;
and if the speed error calculation result is determined to be within a preset error percentage range, taking the first flow speed result as the comprehensive flow speed result, otherwise, carrying out weighting processing on the first flow speed result and the second flow speed result to obtain the comprehensive flow speed result.
Specifically, the embodiment of the invention calculates the error result by comparing the difference of the flow velocity results, if the error is<5%, then directly output v a The method comprises the steps of carrying out a first treatment on the surface of the On the contrary, for v a And v b Weighting to obtain v c Output v c For the final flow rate calculation result, the two calculation results are combined for comparison, and the verification logic flow is shown in fig. 3.
It can be understood that the invention extracts the characteristic points of the river cross section by utilizing the characteristics by comparing the differences among various flow velocity calculation methods, further obtains the states of the characteristic points, such as the size and the distribution density of the characteristic points, performs gradual scene integration, and selects a proper method for river surface flow velocity measurement; judging the obtained river surface flow velocity in a flow velocity interval, comparing results according to the current flow velocity interval optimal method, and obtaining a final result by adopting weighted average when the error result exceeds a set threshold value; and when the error result does not exceed the set threshold, directly outputting the original flow velocity result, and improving the accuracy of the flow measurement result.
The river surface flow rate measuring system based on scene integration provided by the invention is described below, and the river surface flow rate measuring system based on scene integration described below and the river surface flow rate measuring method based on scene integration described above can be correspondingly referred to each other.
Fig. 4 is a schematic structural diagram of a river surface flow rate measurement system based on scene integration according to an embodiment of the present invention, as shown in fig. 4, including: the system comprises an acquisition processing module 41, an integration module 42, a first calculation module 43, a second calculation module 44 and a synthesis module 45, wherein:
the acquisition processing module 41 is used for acquiring river video data, preprocessing the river video data, and acquiring river morphology, river flow state, tracer existence information, tracer particle size and tracer density of a video image; the integration module 42 is configured to determine a scene type integration, and integrate the river morphology, the river flow state, the tracer existence information, the tracer particle size and the tracer density based on the scene type integration, so as to obtain a scene total integration; the first calculating module 43 is configured to determine that a river surface flow velocity is calculated by using a river velocity measurement method corresponding to the highest total integral of the scene, so as to obtain a first flow velocity result; the second calculating module 44 is configured to calculate the river surface flow velocity according to different distribution velocity intervals in which the first flow velocity result is located by using different velocity measurement methods, so as to obtain a second flow velocity result; the integrating module 45 is configured to integrate the first flow rate result and the second flow rate result and output an integrated flow rate result.
Fig. 5 illustrates a physical schematic diagram of an electronic device, as shown in fig. 5, which may include: processor 510, communication interface (Communications Interface) 520, memory 530, and communication bus 540, wherein processor 510, communication interface 520, memory 530 complete communication with each other through communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a scene integration based river surface flow rate measurement method comprising: acquiring river video data, preprocessing the river video data, and acquiring river morphology, river flow state, tracer existence information, tracer particle size and tracer density of a video image; determining scene type integral, and respectively integrating the river morphology, the river flow state, the tracer existence information, the tracer particle size and the tracer density based on the scene type integral, wherein the different river velocity measuring methods correspond to the tracer particle size and the tracer density to obtain a scene total integral; determining a river surface flow velocity calculated by adopting a river velocity measuring method corresponding to the highest scene total integral to obtain a first flow velocity result; according to different distribution speed intervals where the first flow speed result is located, calculating river surface flow speed by adopting different speed measuring methods to obtain a second flow speed result; and integrating the first flow rate result and the second flow rate result, and outputting an integrated flow rate result.
Further, the logic instructions in the memory 530 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which when executed by a processor is implemented to perform the scene integration based river surface flow rate measurement method provided by the above methods, the method comprising: acquiring river video data, preprocessing the river video data, and acquiring river morphology, river flow state, tracer existence information, tracer particle size and tracer density of a video image; determining scene type integral, and respectively integrating the river morphology, the river flow state, the tracer existence information, the tracer particle size and the tracer density based on the scene type integral, wherein the different river velocity measuring methods correspond to the tracer particle size and the tracer density to obtain a scene total integral; determining a river surface flow velocity calculated by adopting a river velocity measuring method corresponding to the highest scene total integral to obtain a first flow velocity result; according to different distribution speed intervals where the first flow speed result is located, calculating river surface flow speed by adopting different speed measuring methods to obtain a second flow speed result; and integrating the first flow rate result and the second flow rate result, and outputting an integrated flow rate result. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the 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 scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A river surface flow rate measurement method based on scene integration, comprising:
acquiring river video data, preprocessing the river video data, and acquiring river morphology, river flow state, tracer existence information, tracer particle size and tracer density of a video image;
determining scene type integral, and respectively integrating the river morphology, the river flow state, the tracer existence information, the tracer particle size and the tracer density based on the scene type integral, wherein the different river velocity measuring methods correspond to the tracer particle size and the tracer density to obtain a scene total integral;
determining a river surface flow velocity calculated by adopting a river velocity measuring method corresponding to the highest scene total integral to obtain a first flow velocity result;
according to different distribution speed intervals where the first flow speed result is located, calculating river surface flow speed by adopting different speed measuring methods to obtain a second flow speed result;
and integrating the first flow rate result and the second flow rate result, and outputting an integrated flow rate result.
2. The scene integration-based river surface flow rate measurement method of claim 1, further comprising, after determining the scene type integration:
and integrating different river velocity measuring methods corresponding to different terminal scenes based on the scene type integration to obtain a scene total integration.
3. The scene integration-based river surface flow rate measurement method according to claim 1, wherein collecting river video data, preprocessing the river video data, and obtaining river morphology, river flow state, tracer existence information, tracer particle size and tracer density of video images, comprises:
intercepting river video data with preset duration based on a preset video frame rate and a preset video frame size;
extracting frames from the river video data to obtain image frames, and converting the image frames into gray level images;
acquiring the river channel length and the river channel width of a river, and classifying the river channel length and the river channel width by adopting a convolutional neural network to obtain a river form;
calculating to obtain river flow state by a preset optical flow method;
image segmentation is carried out on the gray level diagram, a river surface tracer and a background in the gray level diagram are separated, the river surface tracer is classified by adopting a convolutional neural network, and the particle size and the number of the tracer are counted;
and carrying out grid division on the gray level map, and counting grid division results through a convolutional neural network to obtain tracer density.
4. The method for measuring river surface flow rate based on scene integration according to claim 3, wherein the river flow regime is calculated by a preset optical flow method, comprising:
carrying out optical flow estimation on the first frame image by adopting a Lucas-Kanade algorithm to obtain an optical flow direction and an optical flow speed;
and calculating the optical flow direction and the optical flow speed by using a convolutional neural network to obtain the river flow state.
5. The method for measuring river surface flow rate based on post-screening treatment of claim 3, wherein the step of meshing the gray scale map, counting meshing results by a convolutional neural network to obtain tracer density comprises the steps of:
dividing the gray scale image into a plurality of grids based on a preset grid division size;
removing grid results with 0 in the grids by using the convolutional neural network, and calculating the average value of the characteristic points of the residual grids in the grids to obtain the number of the characteristic points in the unit grid;
the tracer density is determined from the number of feature points within the unit grid.
6. The river surface flow rate measuring method based on scene integration according to claim 2, wherein integrating different river velocity measuring methods corresponding to different terminal scenes based on the scene type integration to obtain a scene total integration comprises:
adopting the river form, the river flow state and the tracer existence information to combine to form different terminal scenes;
and accumulating any morphological integral in the river morphology, any flow integral in the river flow state and any existence integral in the tracer existence information to obtain a scene total integral.
7. The method for measuring river surface flow rate based on scene integration according to claim 1, wherein calculating river surface flow rate by using different velocity measurement methods according to different distribution speed intervals in which the first flow rate result is located, to obtain a second flow rate result, comprises:
if the first flow rate result is determined to be located in the first distribution speed interval, calculating the river surface flow rate by adopting an optical flow velocity (OPV) measuring method to obtain a second flow rate result;
if the first flow rate result is determined to be located in the second distribution speed interval, calculating the river surface flow rate by adopting the space-time image velocity measurement STIV to obtain a second flow rate result;
if the first flow rate result is determined to be located in the third distribution speed interval, calculating the river surface flow rate by adopting scale invariant feature transform velocity measurement SIFTV to obtain a second flow rate result;
the first distribution speed interval, the second distribution speed interval and the third distribution speed interval are adjacent speed intervals, and the values are sequentially increased.
8. The scene integration based river surface flow rate measurement method according to claim 1, wherein integrating the first flow rate result and the second flow rate result to output an integrated flow rate result comprises:
comparing the first flow rate result with the second flow rate result to obtain a speed error calculation result;
and if the speed error calculation result is determined to be within a preset error percentage range, taking the first flow speed result as the comprehensive flow speed result, otherwise, carrying out weighting processing on the first flow speed result and the second flow speed result to obtain the comprehensive flow speed result.
9. A river surface flow rate measurement system based on scene integration, comprising:
the acquisition processing module is used for acquiring river video data, preprocessing the river video data and acquiring river morphology, river flow state, tracer existence information, tracer particle size and tracer density of a video image;
the integration module is used for determining scene type integration, and integrating the river morphology, the river flow state, the tracer existence information, the tracer particle size and the tracer density based on the scene type integration respectively to obtain scene total integration according to different river speed measuring methods corresponding to the tracer particle size and the tracer density;
the first calculation module is used for determining a river velocity measurement method corresponding to the highest scene total integral to calculate the river surface flow velocity, so as to obtain a first flow velocity result;
the second calculation module is used for calculating the river surface flow velocity according to different distribution velocity intervals in which the first flow velocity result is positioned by adopting different velocity measurement methods to obtain a second flow velocity result;
and the synthesis module is used for synthesizing the first flow rate result and the second flow rate result and outputting a synthesized flow rate result.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the scene integration based river surface flow rate measurement method of any one of claims 1 to 8 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311182599.0A CN117333794A (en) | 2023-09-13 | 2023-09-13 | River surface flow velocity measurement method and system based on scene integration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311182599.0A CN117333794A (en) | 2023-09-13 | 2023-09-13 | River surface flow velocity measurement method and system based on scene integration |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117333794A true CN117333794A (en) | 2024-01-02 |
Family
ID=89276328
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311182599.0A Pending CN117333794A (en) | 2023-09-13 | 2023-09-13 | River surface flow velocity measurement method and system based on scene integration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117333794A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118425555A (en) * | 2024-07-03 | 2024-08-02 | 武汉大水云科技有限公司 | Photoelectric fusion-based water flow velocity measurement method and system |
-
2023
- 2023-09-13 CN CN202311182599.0A patent/CN117333794A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118425555A (en) * | 2024-07-03 | 2024-08-02 | 武汉大水云科技有限公司 | Photoelectric fusion-based water flow velocity measurement method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111160210B (en) | Video-based water flow rate detection method and system | |
| CN104408707B (en) | Rapid digital imaging fuzzy identification and restored image quality assessment method | |
| CN108665443B (en) | Infrared image sensitive area extraction method and device for mechanical equipment fault | |
| CN109376740A (en) | A kind of water gauge reading detection method based on video | |
| CN117333795A (en) | River surface flow velocity measurement method and system based on screening post-treatment | |
| CN108257125B (en) | Depth image quality non-reference evaluation method based on natural scene statistics | |
| CN115830514B (en) | Whole river reach surface flow velocity calculation method and system suitable for curved river channel | |
| CN113012157B (en) | Visual detection method and system for equipment defects | |
| CN111028263B (en) | Moving object segmentation method and system based on optical flow color clustering | |
| CN114299383A (en) | Remote sensing image target detection method based on integration of density map and attention mechanism | |
| WO2023130661A1 (en) | Method and apparatus for processing two-dimensional spectral doppler echocardiographic image | |
| CN111968081A (en) | Fish shoal automatic counting method and device, electronic equipment and storage medium | |
| CN117333794A (en) | River surface flow velocity measurement method and system based on scene integration | |
| CN111739011B (en) | Telegraph pole inclination detection method and device | |
| CN112204957A (en) | White balance processing method and device, movable platform and camera | |
| CN111241979B (en) | Real-time obstacle detection method based on image feature calibration | |
| CN115019052B (en) | Image recognition method, device, electronic equipment and storage medium | |
| CN113496159A (en) | Multi-scale convolution and dynamic weight cost function smoke target segmentation method | |
| CN111060887B (en) | Gm-APD laser radar low signal-to-noise ratio echo data signal extraction method based on concave-convex search | |
| CN107818287B (en) | Passenger flow statistics device and system | |
| CN110580697A (en) | Video image processing method and system for measuring thickness of fetal nape transparency from ultrasonic video image | |
| CN115984546A (en) | Sample base generation method for anomaly detection of fixed scene | |
| CN109886212A (en) | Method and apparatus for synthesizing field fingerprints from rolling fingerprints | |
| JP5419925B2 (en) | Passing object number measuring method, passing object number measuring apparatus, and program | |
| CN114677428A (en) | Power transmission line icing thickness detection method based on unmanned aerial vehicle image processing |
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 |