CN113781528A - River surface flow velocity measuring and calculating method based on optical flow calculation - Google Patents
River surface flow velocity measuring and calculating method based on optical flow calculation Download PDFInfo
- Publication number
- CN113781528A CN113781528A CN202110985752.8A CN202110985752A CN113781528A CN 113781528 A CN113781528 A CN 113781528A CN 202110985752 A CN202110985752 A CN 202110985752A CN 113781528 A CN113781528 A CN 113781528A
- Authority
- CN
- China
- Prior art keywords
- river
- image
- flow
- calculating
- optical 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.)
- Pending
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000004364 calculation method Methods 0.000 title claims abstract description 25
- 239000002245 particle Substances 0.000 claims abstract description 49
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 230000000007 visual effect Effects 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 238000005516 engineering process Methods 0.000 claims abstract description 7
- 230000000694 effects Effects 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 230000003068 static effect Effects 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 230000006835 compression Effects 0.000 claims description 6
- 238000007906 compression Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 230000003321 amplification Effects 0.000 claims description 3
- 238000010835 comparative analysis Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000012800 visualization Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 239000012530 fluid Substances 0.000 description 2
- 238000000917 particle-image velocimetry Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06N3/045—Combinations of networks
-
- 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
-
- G06T5/70—
-
- G06T5/90—
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention particularly relates to a river surface flow velocity measuring and calculating method based on optical flow calculation. The river surface flow velocity measuring and calculating method based on optical flow calculation comprises the steps of preprocessing collected river flow dynamic videos to generate a river flow data set; then combining a particle image speed measurement technology with a convolutional neural network model, and carrying out image data set training and testing on the convolutional neural network model, so that the estimation effect and robustness of complex flow are improved; and inputting the real-time river flow image into the trained convolutional neural network model, calculating the flow speed of the river surface, and performing visual output. According to the river surface flow velocity measuring and calculating method based on the optical flow calculation, the real-time performance of the traditional dense optical flow algorithm is compensated by means of the convolution network, the complicated flowing situation of the natural river can be visually operated, the complicated flowing situation is simplified, the estimation of the river surface flow velocity is realized, and the measuring and calculating cost is reduced.
Description
Technical Field
The invention relates to the technical field of stream video and artificial intelligence, in particular to a river surface flow velocity measuring and calculating method based on optical flow calculation.
Background
In recent years, with the general rise of smart cities and smart water conservancy, computer vision technology is continuously developed in the aspect of fluid motion research by combining hydrology and hydromechanics. The river flow velocity is the key for acquiring the hydrological information, real-time, effective and comprehensive hydrological information is mastered, so that people can effectively cope with frequent flood disasters in time, and the loss of manpower, material resources and financial resources brought by the people is reduced.
The traditional flow velocity measurement depends on various instruments, a propeller is driven to rotate by water flow, a traditional flow velocity instrument measurement method based on propeller rotating speed calculation is adopted, a flow velocity method for measurement through acoustic and optical Doppler effects is adopted, and the image method based on visual images is adopted for speed measurement, so that the method is more suitable for extreme environment flow measurement conditions.
The invention provides a river surface flow velocity measuring and calculating method based on optical flow calculation, aiming at realizing the flow velocity measuring and calculating of natural rivers with complex conditions.
Disclosure of Invention
In order to make up for the defects of the prior art, the invention provides a simple and efficient river surface flow velocity measuring and calculating method based on optical flow calculation.
The invention is realized by the following technical scheme:
a river surface flow velocity measuring and calculating method based on optical flow calculation is characterized by comprising the following steps: the method comprises the following steps:
firstly, video acquisition is carried out on the flowing condition of the river surface by using a camera, and the acquired dynamic video of the river flowing is preprocessed to generate a river flowing data set;
secondly, combining a particle image speed measurement technology with a convolutional neural network model, calculating the motion displacement of a rear frame relative to a front frame through the comparative analysis of actually flowing particle images of frames at certain intervals, and carrying out image data set training and testing on the convolutional neural network model to improve the estimation effect and robustness of complex flow;
and thirdly, inputting the real-time river flow image into the trained convolutional neural network model, calculating the flow speed of the river surface, and performing visual output.
In the first step, the specific implementation method is as follows:
1) acquiring a river flow dynamic video of a river surface area through an infrared camera, and transmitting the video to a laboratory operation center;
2) processing the river flow dynamic video into a static image and preprocessing the static image, including denoising and contrast enhancement;
3) a river flow data set is generated using the preprocessed static images.
In the second step, the specific implementation method is as follows:
1) generating a particle image motion data set by utilizing open source software;
2) and combining the river flow data set and the particle image motion data set to serve as a training set, and training the convolutional neural network model.
In the step 1), a particle image and an actual flow velocity field are generated by using the preprocessed static image, and then another particle image is symmetrically obtained from the generated flow velocity field, so that an image pair is obtained, and a particle image motion data set is formed.
In the step 1), PIVLab open source software is adopted to adjust different parameters to obtain particle images, and the particle images are subjected to rotation, translation, brightness change and Gaussian noise superposition operations to obtain particle image motion data sets.
The parameters include the particle density of the image, the diameter of the particles generated, the peak value of the particle gray scale, the particle distribution mode and random Gaussian noise.
The particle image motion data set was partitioned at a 7:3 ratio, with 7 pieces of data for training and 3 pieces of data for outcome testing.
In the step 2), an optical flow neural network Flowents is adopted to construct a visual model of particle image speed measurement optical flow characteristics based on deep learning, two images which are formed by superposing 3 channels and have the depth of 6 channels are used as network input images, a compression part is composed of a convolution layer, a pooling layer and a nonlinear ReLU layer, and the spatial information of the composed images input by the network is extracted through the compression part to form characteristics containing more channels;
the optical flow neural network Flowets comprises nine layers of convolution, a network amplification part consisting of an upsampling layer and a convolution layer improves the image resolution, the resolution of the finally predicted optical flow image is 1/4 of the resolution of a network input image, and the network outputs an image result comprising two channels which are two speed vectors of a speed vector field.
In the step 2), the spatial resolution of the river static image subjected to the centralized pretreatment of the river flow data is adjusted to 512 × 512, and the image pair which is adjacent and has a frame interval (0.04s) is used as input to train the optical flow neural network FlownetS, so that a trained convolutional neural network model is obtained.
In the third step, the trained convolutional neural network model extracts the optical flow characteristics of the real-time river flow image, and outputs a predicted optical flow field in an HSV (Hue, Saturation, lightness) visualization space.
The invention has the beneficial effects that: according to the river surface flow velocity measuring and calculating method based on the optical flow calculation, the real-time performance of the traditional dense optical flow algorithm is compensated by means of the convolution network, the complicated flowing situation of the natural river can be visually operated, the complicated flowing situation is simplified, the estimation of the river surface flow velocity is realized, and the measuring and calculating cost is reduced.
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 introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic diagram of a river surface flow velocity measuring and calculating method based on optical flow calculation.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the embodiment of the present invention. 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 embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, aiming at the application of a particle image velocimetry technology in the visualization of non-contact dynamic flow field calculation, the particle image velocimetry technology has good calculation effect in the measurement of two-dimensional and three-dimensional fluid velocity fields of laboratory scales. The river surface flow velocity measuring and calculating method based on optical flow calculation comprises the following steps:
firstly, video acquisition is carried out on the flowing condition of the river surface by using a camera, and the acquired dynamic video of the river flowing is preprocessed to generate a river flowing data set;
secondly, combining a particle image speed measurement technology with a convolutional neural network model, calculating the motion displacement of a rear frame relative to a front frame through the comparative analysis of actually flowing particle images of frames at certain intervals, and carrying out image data set training and testing on the convolutional neural network model to improve the estimation effect and robustness of complex flow;
and thirdly, inputting the real-time river flow image into the trained convolutional neural network model, calculating the flow speed of the river surface, and performing visual output.
In the first step, the specific implementation method is as follows:
1) acquiring a river flow dynamic video of a river surface area through an infrared camera, and transmitting the video to a laboratory operation center;
2) processing the river flow dynamic video into a static image and preprocessing the static image, including denoising and contrast enhancement;
3) a river flow data set is generated using the preprocessed static images.
In the second step, the specific implementation method is as follows:
1) generating a particle image motion data set by utilizing open source software;
2) and combining the river flow data set and the particle image motion data set to serve as a training set, and training the convolutional neural network model.
In the step 1), a particle image and an actual flow velocity field are generated by using the preprocessed static image, and then another particle image is symmetrically obtained from the generated flow velocity field, so that an image pair is obtained, and a particle image motion data set is formed.
In the step 1), PIVLab open source software is adopted to adjust different parameters to obtain particle images, and the particle images are subjected to rotation, translation, brightness change and Gaussian noise superposition operations to obtain particle image motion data sets.
The parameters include the particle density of the image, the diameter of the particles generated, the peak value of the particle gray scale, the particle distribution mode and random Gaussian noise.
The particle image motion data set was partitioned at a 7:3 ratio, with 7 pieces of data for training and 3 pieces of data for outcome testing.
In the step 2), an optical flow neural network Flowents is adopted to construct a visual model of particle image speed measurement optical flow characteristics based on deep learning, two images which are formed by superposing 3 channels and have the depth of 6 channels are used as network input images, a compression part is composed of a convolution layer, a pooling layer and a nonlinear ReLU layer, and the spatial information of the composed images input by the network is extracted through the compression part to form characteristics containing more channels;
as the convolution progresses further, the spatial resolution at which the multi-channel image features are extracted gradually decreases. The optical flow neural network Flowets comprises nine layers of convolution, a network amplification part consisting of an upsampling layer and a convolution layer improves the image resolution, the resolution of the finally predicted optical flow image is 1/4 of the resolution of a network input image, and the network outputs an image result comprising two channels which are two speed vectors of a speed vector field.
In the step 2), the spatial resolution of the river static image subjected to the centralized pretreatment of the river flow data is adjusted to 512 × 512, and the image pair which is adjacent and has a frame interval (0.04s) is used as input to train the optical flow neural network FlownetS, so that a trained convolutional neural network model is obtained.
In the third step, the trained convolutional neural network model extracts the optical flow characteristics of the real-time river flow image, and outputs a predicted optical flow field in an HSV (Hue, Saturation, lightness) visualization space.
The test result shows that the flow direction and the size of the real movement of the river are basically consistent, and the river surface flow velocity estimation algorithm of the large-flow water flow based on the optical flow convolution neural network has obvious advantages in the aspects of real-time performance, stability and flow field full-field measurement, and has extremely strong feasibility and application prospect.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A river surface flow velocity measuring and calculating method based on optical flow calculation is characterized by comprising the following steps: the method comprises the following steps:
firstly, video acquisition is carried out on the flowing condition of the river surface by using a camera, and the acquired dynamic video of the river flowing is preprocessed to generate a river flowing data set;
secondly, combining a particle image speed measurement technology with a convolutional neural network model, calculating the motion displacement of a rear frame relative to a front frame through the comparative analysis of actually flowing particle images of frames at certain intervals, and carrying out image data set training and testing on the convolutional neural network model to improve the estimation effect and robustness of complex flow;
and thirdly, inputting the real-time river flow image into the trained convolutional neural network model, calculating the flow speed of the river surface, and performing visual output.
2. The method for measuring and calculating the surface flow velocity of a river based on optical flow calculation according to claim 1, wherein: in the first step, the specific implementation method is as follows:
1) acquiring a river flow dynamic video of a river surface area through an infrared camera, and transmitting the video to a laboratory operation center;
2) processing the river flow dynamic video into a static image and preprocessing the static image, including denoising and contrast enhancement;
3) a river flow data set is generated using the preprocessed static images.
3. The method for measuring and calculating the surface flow velocity of a river based on optical flow calculation according to claim 1, wherein: in the second step, the specific implementation method is as follows:
1) generating a particle image motion data set by utilizing open source software;
2) and combining the river flow data set and the particle image motion data set to serve as a training set, and training the convolutional neural network model.
4. The method for measuring and calculating the surface flow velocity of a river based on optical flow calculation according to claim 3, wherein: in the step 1), a particle image and an actual flow velocity field are generated by using the preprocessed static image, and then another particle image is symmetrically obtained from the generated flow velocity field, so that an image pair is obtained, and a particle image motion data set is formed.
5. The method for measuring and calculating the surface flow velocity of a river based on optical flow calculation according to claim 4, wherein: in the step 1), PIVLab open source software is adopted to adjust different parameters to obtain particle images, and the particle images are subjected to rotation, translation, brightness change and Gaussian noise superposition operations to obtain particle image motion data sets.
6. The method for measuring and calculating the surface flow velocity of a river based on optical flow calculation according to claim 5, wherein: the parameters include the particle density of the image, the diameter of the particles generated, the peak value of the particle gray scale, the particle distribution mode and random Gaussian noise.
7. The method for measuring and calculating the surface flow velocity of a river based on optical flow calculation according to claim 5, wherein: the particle image motion data set was partitioned at a 7:3 ratio, with 7 pieces of data for training and 3 pieces of data for outcome testing.
8. The method for measuring and calculating the surface flow velocity of a river based on optical flow calculation according to claim 3, wherein: in the step 2), an optical flow neural network Flowents is adopted to construct a visual model of particle image speed measurement optical flow characteristics based on deep learning, two images which are formed by superposing 3 channels and have the depth of 6 channels are used as network input images, a compression part is composed of a convolution layer, a pooling layer and a nonlinear ReLU layer, and the spatial information of the composed images input by the network is extracted through the compression part to form characteristics containing more channels;
the optical flow neural network Flowets comprises nine layers of convolution, a network amplification part consisting of an upsampling layer and a convolution layer improves the image resolution, the resolution of the finally predicted optical flow image is 1/4 of the resolution of a network input image, and the network outputs an image result comprising two channels which are two speed vectors of a speed vector field.
9. The method for measuring and calculating the surface flow velocity of a river based on optical flow calculation according to claim 8, wherein: in the step 2), the spatial resolution of the river static image subjected to the centralized pretreatment of the river flow data is adjusted to 512 × 512, and the training of the optical neural network FlownetS is performed by taking adjacent image pairs with a frame interval of 0.04s as input, so as to obtain a trained convolutional neural network model.
10. The method for measuring and calculating the surface flow velocity of a river based on optical flow calculation according to claim 1, wherein: and in the third step, the trained convolutional neural network model extracts the optical flow characteristics of the real-time river flow image and outputs a predicted optical flow field in an HSV (hue, saturation and value) visual space.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110985752.8A CN113781528A (en) | 2021-08-26 | 2021-08-26 | River surface flow velocity measuring and calculating method based on optical flow calculation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110985752.8A CN113781528A (en) | 2021-08-26 | 2021-08-26 | River surface flow velocity measuring and calculating method based on optical flow calculation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113781528A true CN113781528A (en) | 2021-12-10 |
Family
ID=78839301
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110985752.8A Pending CN113781528A (en) | 2021-08-26 | 2021-08-26 | River surface flow velocity measuring and calculating method based on optical flow calculation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113781528A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115830514A (en) * | 2023-01-30 | 2023-03-21 | 武汉大水云科技有限公司 | Method and system for calculating surface flow velocity of whole river section of riverway with curve |
CN116843725A (en) * | 2023-08-30 | 2023-10-03 | 武汉大水云科技有限公司 | River surface flow velocity measurement method and system based on deep learning optical flow method |
CN117274316B (en) * | 2023-10-31 | 2024-05-03 | 广东省水利水电科学研究院 | River surface flow velocity estimation method, device, equipment and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106156734A (en) * | 2016-06-28 | 2016-11-23 | 浙江工业大学 | A kind of current speed-measuring method based on convolutional neural networks image recognition |
CN107590819A (en) * | 2017-08-03 | 2018-01-16 | 浙江工业大学 | A kind of river surface flow velocity method of estimation based on compressed sensing graphical analysis |
KR101996992B1 (en) * | 2018-11-13 | 2019-07-08 | 주식회사 하이드로셈 | Apparatus and Method for Measuring Flow Velocity of River using Optical Flow Image Processing |
CN111582076A (en) * | 2020-04-23 | 2020-08-25 | 安徽海德瑞丰信息科技有限公司 | Picture freezing detection method based on pixel motion intelligent perception |
CN111768047A (en) * | 2020-07-04 | 2020-10-13 | 江苏工程职业技术学院 | Water flow velocity prediction method based on multi-feature data and multi-model |
CN112287838A (en) * | 2020-10-29 | 2021-01-29 | 北京邮电大学 | Cloud and fog automatic identification method and system based on static meteorological satellite image sequence |
WO2021142441A1 (en) * | 2020-01-10 | 2021-07-15 | Marquette University | Systems and methods for remote sensing of river velocity using video and an optical flow algorithm |
CN113139989A (en) * | 2021-06-22 | 2021-07-20 | 浙江大学 | Particle image velocity measurement method and device based on deep learning |
-
2021
- 2021-08-26 CN CN202110985752.8A patent/CN113781528A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106156734A (en) * | 2016-06-28 | 2016-11-23 | 浙江工业大学 | A kind of current speed-measuring method based on convolutional neural networks image recognition |
CN107590819A (en) * | 2017-08-03 | 2018-01-16 | 浙江工业大学 | A kind of river surface flow velocity method of estimation based on compressed sensing graphical analysis |
KR101996992B1 (en) * | 2018-11-13 | 2019-07-08 | 주식회사 하이드로셈 | Apparatus and Method for Measuring Flow Velocity of River using Optical Flow Image Processing |
WO2021142441A1 (en) * | 2020-01-10 | 2021-07-15 | Marquette University | Systems and methods for remote sensing of river velocity using video and an optical flow algorithm |
CN111582076A (en) * | 2020-04-23 | 2020-08-25 | 安徽海德瑞丰信息科技有限公司 | Picture freezing detection method based on pixel motion intelligent perception |
CN111768047A (en) * | 2020-07-04 | 2020-10-13 | 江苏工程职业技术学院 | Water flow velocity prediction method based on multi-feature data and multi-model |
CN112287838A (en) * | 2020-10-29 | 2021-01-29 | 北京邮电大学 | Cloud and fog automatic identification method and system based on static meteorological satellite image sequence |
CN113139989A (en) * | 2021-06-22 | 2021-07-20 | 浙江大学 | Particle image velocity measurement method and device based on deep learning |
Non-Patent Citations (1)
Title |
---|
蔡声泽: "基于光流计算的复杂流动可视化测速算法研究", 《中国博士学位论文全文数据库 基础科学辑》, no. 2019, pages 1 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115830514A (en) * | 2023-01-30 | 2023-03-21 | 武汉大水云科技有限公司 | Method and system for calculating surface flow velocity of whole river section of riverway with curve |
CN116843725A (en) * | 2023-08-30 | 2023-10-03 | 武汉大水云科技有限公司 | River surface flow velocity measurement method and system based on deep learning optical flow method |
CN116843725B (en) * | 2023-08-30 | 2024-01-05 | 武汉大水云科技有限公司 | River surface flow velocity measurement method and system based on deep learning optical flow method |
CN117274316B (en) * | 2023-10-31 | 2024-05-03 | 广东省水利水电科学研究院 | River surface flow velocity estimation method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Deng et al. | Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework | |
CN113781528A (en) | River surface flow velocity measuring and calculating method based on optical flow calculation | |
Niu et al. | Unsupervised saliency detection of rail surface defects using stereoscopic images | |
CN110120020A (en) | A kind of SAR image denoising method based on multiple dimensioned empty residual error attention network | |
CN107644415A (en) | A kind of text image method for evaluating quality and equipment | |
Wei et al. | A coarse-to-fine multi-stream hybrid deraining network for single image deraining | |
CN112508991B (en) | Panda photo cartoon method with separated foreground and background | |
CN107292915A (en) | Method for tracking target based on convolutional neural networks | |
CN108764186A (en) | Personage based on rotation deep learning blocks profile testing method | |
CN103871039B (en) | Generation method for difference chart in SAR (Synthetic Aperture Radar) image change detection | |
Ranjan et al. | Learning human optical flow | |
Luan et al. | Extracting full-field subpixel structural displacements from videos via deep learning | |
Kawana et al. | Neural star domain as primitive representation | |
CN109584162A (en) | A method of based on the image super-resolution reconstruct for generating network | |
CN105898278A (en) | Stereoscopic video saliency detection method based on binocular multidimensional perception characteristic | |
Guo et al. | Application of computer aided modeling design in the expression techniques of sculpture art space | |
CN113112583A (en) | 3D human body reconstruction method based on infrared thermal imaging | |
Karimpouli et al. | Multistep Super Resolution Double-U-net (SRDUN) for enhancing the resolution of Berea sandstone images | |
CN114187263A (en) | Worn surface Lambert reflection separation method integrating prior guidance and domain adaptation | |
Ren et al. | Facial geometric detail recovery via implicit representation | |
CN114758070A (en) | Single-image three-dimensional human body fine reconstruction method based on cross-domain multitask | |
Gader | Fuzzy spatial relations based on fuzzy morphology | |
Schweri et al. | A physics-aware neural network approach for flow data reconstruction from satellite observations | |
Yang et al. | Feature-guided convolution for pencil rendering | |
Meng et al. | A Novel Steganography Algorithm Based on Instance Segmentation. |
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 |