CN114677324B - Water depth detection method and system - Google Patents
Water depth detection method and system Download PDFInfo
- Publication number
- CN114677324B CN114677324B CN202210063742.3A CN202210063742A CN114677324B CN 114677324 B CN114677324 B CN 114677324B CN 202210063742 A CN202210063742 A CN 202210063742A CN 114677324 B CN114677324 B CN 114677324B
- Authority
- CN
- China
- Prior art keywords
- water
- wave
- target area
- water wave
- water surface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 620
- 238000001514 detection method Methods 0.000 title claims abstract description 55
- 230000003068 static effect Effects 0.000 claims abstract description 41
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims abstract description 28
- 230000003287 optical effect Effects 0.000 claims description 38
- 238000000034 method Methods 0.000 claims description 27
- 238000005286 illumination Methods 0.000 claims description 26
- 230000008859 change Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000009825 accumulation Methods 0.000 description 20
- 238000001914 filtration Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 14
- 238000004458 analytical method Methods 0.000 description 10
- 239000012530 fluid Substances 0.000 description 10
- 210000002569 neuron Anatomy 0.000 description 10
- 238000012549 training Methods 0.000 description 10
- 239000003086 colorant Substances 0.000 description 8
- 238000009792 diffusion process Methods 0.000 description 6
- 238000013507 mapping Methods 0.000 description 6
- 239000002245 particle Substances 0.000 description 6
- 238000011176 pooling Methods 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000002146 bilateral effect Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 230000005484 gravity Effects 0.000 description 4
- 230000000630 rising effect Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 238000009423 ventilation Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
- G01F23/30—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm by floats
- G01F23/64—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm by floats of the free float type without mechanical transmission elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/10024—Color image
-
- 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)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Fluid Mechanics (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The application provides a water depth detection method and a water depth detection system, which are used for solving the technical problem of poor water depth detection and early warning performance of a mine tunnel in the prior art. The water depth detection method comprises the following steps: providing disturbing force for the water surface of the target area and illuminating; acquiring a water surface video of the target area; preprocessing the image of the water surface video frame by frame, and adaptively constructing a binary image; identifying wave crests and wave troughs of the water waves by using a convolutional neural network algorithm; establishing a static water wave state according to the water wave crest and the water wave trough; generating a dynamic water wave state according to the plurality of static water wave states; according to the dynamic water wave state, at least determining water wave information; and calculating the water depth according to the water wave information. According to the water depth detection method, the water surface wave of the target area is identified by providing disturbing force for the water surface of the target area and illuminating. According to the water wave information of the water surface of the target area, the current water depth can be calculated, so that real-time monitoring is realized, and the early warning performance is high.
Description
Technical Field
The application relates to the technical field of water depth detection, in particular to a water depth detection method and system.
Background
The mine tunnel operation is complex, and the mine tunnel operation has various scenes needing water depth detection in the actual mine tunnel operation. When the mine hole is blasted, ravines are easily formed in the mine hole. In the subsequent mining hole operation process, if water flow occurs, the water flow flows into the gully, and the depth of the gully water flow cannot be visually seen. Even if water is pumped to the water accumulation area, time is required. And safety accidents are very easy to occur when workers pass through ravines with unknown depths.
In implementing the prior art, the inventors found that:
Mine hole water depth detection in the prior art is usually inspected by security inspection personnel, and when manpower resources are wasted, warning can not be sent out timely, and early warning performance is poor.
Therefore, a solution for detecting the water depth is needed to solve the technical problem of poor water depth detection and early warning performance of the mine tunnel in the prior art.
Disclosure of Invention
The embodiment of the application provides a water depth detection scheme which is used for solving the technical problem of poor water depth detection and early warning performance of a mine tunnel in the prior art.
Specifically, the water depth detection method comprises the following steps:
Providing disturbing force for the water surface of the target area and illuminating;
acquiring a water surface video of the target area;
Denoising the image of the water surface video frame by frame to generate a preprocessing file;
Inputting the preprocessed file into a color space model, and identifying color space data of the preprocessed file;
according to the color space data of the preprocessing file, a binary image is adaptively constructed;
identifying the water wave optical characteristics of the water surface in the binary image by using a convolutional neural network algorithm;
Identifying wave crests and wave troughs of the water waves according to the optical characteristics of the water waves on the water surface in the binary image;
Establishing a static water wave state according to the water wave crest and the water wave trough;
generating a dynamic water wave state according to the plurality of static water wave states;
according to the dynamic water wave state, at least determining the water wave wavelength, the water wave speed and the water wave number;
Calculating the water depth according to the water wave wavelength, the water wave speed and the water wave number;
wherein the water wave optical characteristics of the water surface comprise a water wave reflection illumination texture or a water wave refraction illumination texture.
Further, the water depth detection method further comprises the following steps:
Providing disturbing force for the water surface of the target area at intervals of preset time length and illuminating;
Calculating the water depth of a preset interval duration;
Calculating the water depth change rate;
And when the water depth change rate exceeds a preset threshold value, sending out an alarm signal.
Further, the water depth detection method further comprises the following steps:
And when the water depth change rate exceeds a preset threshold value and maintains the preset rise duration, sending an alarm signal.
Further, the water depth detection method further comprises the following steps:
Placing a buoy on the water surface of the target area;
identifying a float position in the binary image by using a convolutional neural network algorithm;
and identifying the wave crest and the wave trough of the water wave according to the floating position in the binary image.
Further, the outer surface of the buoy emits light or reflects light, so that the position of the buoy can be conveniently identified according to brightness.
The embodiment of the application also provides a water depth detection system.
Specifically, a water depth detection system includes:
the disturbance device is used for providing disturbance force for the water surface of the target area;
the illumination device is used for illuminating the water surface of the target area;
The camera device is used for shooting a water surface video of the target area;
The acquisition module is used for acquiring the water surface video of the target area;
the preprocessing module is used for denoising the image of the water surface video frame by frame to generate a preprocessing file;
The data conversion module is used for inputting the preprocessing file into a color space model and identifying color space data of the preprocessing file;
the output module is used for adaptively constructing a binary image according to the color space data of the preprocessed file;
The identification module is used for identifying the water wave optical characteristics of the water surface in the binary image by using a convolutional neural network algorithm; the method is also used for identifying wave crests and wave troughs according to the water wave optical characteristics of the water surface in the binary image;
The modeling module is used for establishing a static water wave state according to the water wave crest and the water wave trough; the dynamic water wave state is generated according to the plurality of static water wave states;
the calculation module is used for determining at least the wave wavelength, the wave velocity and the wave number of the water wave according to the dynamic water wave state; the water depth is calculated according to the water wave wavelength, the water wave speed and the water wave number;
wherein the water wave optical characteristics of the water surface comprise a water wave reflection illumination texture or a water wave refraction illumination texture.
Further, the disturbance device is further used for providing disturbance force for the water surface of the target area at intervals of preset time length;
The lighting device is also used for lighting the water surface of the target area at intervals of preset time length;
the calculating module is also used for calculating the water depth of the preset interval duration; the method is also used for calculating the water depth change rate;
the water depth detection system further comprises an alarm module, wherein the alarm module is used for sending an alarm signal when the water depth change rate exceeds a preset threshold value.
Further, the alarm module is further configured to send an alarm signal when the water depth change rate exceeds a preset threshold and maintains a preset rise duration.
Further, the water depth detection system further comprises:
a float placed on the water surface of the target area;
The identification module is also used for identifying the float position in the binary image by using a convolutional neural network algorithm; and the device is also used for identifying the wave crest and the wave trough of the water wave according to the floating position in the binary image.
Further, the outer surface of the buoy emits light or reflects light, so that the position of the buoy can be conveniently identified according to brightness.
The technical scheme provided by the embodiment of the application has at least the following beneficial effects:
The water wave of the water surface of the target area is identified by providing disturbing force to the water surface of the target area and illuminating. According to the water wave information of the water surface of the target area, the current water depth can be calculated, so that real-time monitoring is realized, and the early warning performance is high.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
fig. 1 is a flow chart of a water depth detection method according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of a water depth detection system according to an embodiment of the present application.
100. Water depth detection system
11. Disturbance device
12. Lighting device
13. Image pickup apparatus
14. Acquisition module
15. Pretreatment module
16. Data conversion module
17. Output module
18. Identification module
19. Modeling module
20. Calculation module
21. Alarm module
22. And (5) floating.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, the application discloses a water depth detection method, which comprises the following steps:
s110: providing disturbing force to the water surface of the target area and illuminating.
It will be appreciated that the target area refers to a water depth observation area, such as a water accumulation area inside a mine cavity. The mine tunnel operation is complex, and the mine tunnel operation has various scenes needing water depth detection in the actual mine tunnel operation. According to the specific practice of mine tunnel operation, the following application provides a scene requiring detection of water depth: when the mine hole is blasted, ravines are easily formed in the mine hole. In the subsequent mining hole operation process, if water flow occurs, the water flow flows into the gully, and the depth of the gully water flow cannot be visually seen. Even if water is pumped to the water accumulation area, time is required. And when a worker passes through a gully with unknown depth, safety accidents are very easy to occur, so that the water depth of a target area needs to be detected so as to send out safety precaution.
The water surface of the target area is in a stationary state without a disturbance source, when the water surface is level. When the water surface of the target area is disturbed to be in a non-static state, the gravity of the water is used as a restoring force to return the fluid particles to the original balance position. However, due to inertia, the fluid particles do not stop but continue to move when they return to their equilibrium position. The gravity force can exert the restoring force, so that the fluid particles repeatedly oscillate, and finally water waves appear on the water surface. It is considered that there is no stable disturbance source on the water surface of the target area, so that a disturbance force needs to be provided to the water surface of the target area. Specifically, the inventor considers that mine tunnel operation is always provided with a ventilation pipeline, so wind energy is used as a disturbance source to provide disturbance force for the water surface of a target area. While considering that mine tunnel operations are typically performed in mines, it is also desirable to illuminate the water surface in the target area because there is no natural illumination inside the mine.
S120: and acquiring the water surface video of the target area.
It will be appreciated that the video file may be a multimedia file containing real-time audio, video information. The file format of the video file may be MPEG, AVI, ASF, MOV, 3GP, WMV, RM, RMVB, FLV/F4V. In a specific application scenario, the water surface video of the target area may be a video file obtained from a recorder or a camera and including the water surface content of the target area. In view of the subsequent analysis of the water surface of the target area, the application preferably takes a fixed position to capture a water surface video of the target area.
S130: and denoising the image of the water surface video frame by frame to generate a preprocessing file.
It can be understood that when the continuous image changes by more than 24 frames per second, according to the persistence of vision principle, the human eyes cannot distinguish the single static image; it appears as a smooth continuous visual effect, such that successive pictures are called videos.
Considering that the application scene of the application is usually the inside of a mine tunnel, such an environment does not have natural light beams and mechanical vibration exists during construction. Therefore, the acquired water surface picture of the target area usually has noise, namely, the image is blurred, the image characteristics are not obvious, and the subsequent analysis is easy to be difficult. For this purpose, the image of the water surface video needs to be denoised frame by frame. Specifically, the application adopts a denoising algorithm to denoise the image of the water surface video. The denoising algorithm can be specifically represented by mean filtering, median filtering, gaussian filtering, bilateral filtering or the like. Wherein the mean filtering uses the average value of adjacent pixels to replace the original pixel value. The median filtering uses the median of the convolution templates instead of the pixel values. The gaussian filtering uses coefficient values of a convolution template instead of pixel values, the coefficients decreasing with increasing distance from the center of the template. The bilateral filtering combines the spatial proximity of the image and the pixel value similarity to replace the pixel value.
The denoised water surface image has small blurring degree and smooth image, and is more beneficial to subsequent analysis. The denoised water surface image is recorded as a preprocessing file.
S140: inputting the preprocessed file into a color space model, and identifying color space data of the preprocessed file.
It is understood that the color space model is a mathematical model describing colors by numerical values. Specifically, the color space model can identify the synthesis proportion of red, green and blue primary colors of a single pixel point of the pretreatment file. The color space model may also identify the saturation or chromaticity of individual pixels of the preprocessed file. The color space model may also represent non-colors with one component and colors with two independent components, thereby identifying black and white pixels and color pixels in the preprocessed file.
S150: and adaptively constructing a binary image according to the color space data of the preprocessed file.
It will be appreciated that the binary image may be understood as having only two possible values or gray scale states for each pixel on the image. In other words, the gray value of any pixel point in the binary image is only 0 or 255, which represents black or white, respectively. After the color information of the binary image is simplified into black or white binary values, the data size of the binary image is smaller, and the processing speed is high.
Considering that the analysis object of the application is embodied as water surface information, and the black and white binary values of the binary image are just suitable for displaying edge information, the application preferably converts the preprocessed file into the binary image for analysis.
Specifically, the adaptively constructing the binary image according to the color space data of the preprocessed file may be performed by setting a pixel color judgment threshold, and setting the gray value of the pixel point to 255, that is, white, when the pixel color space data is greater than or equal to the pixel color judgment threshold. When the pixel color space data is smaller than the pixel color judgment threshold value, the gray value of the pixel point is set to be 0, namely black.
S160: and identifying the optical characteristics of the water wave on the water surface in the binary image by using a convolutional neural network algorithm.
It is understood that the water wave optical characteristics of the water surface include a water wave reflective illumination texture or a water wave refractive illumination texture. In particular, the water wave reflective illumination texture or the water wave refractive illumination texture may represent a spot that the water wave presents under illumination. The water wave optical characteristic may appear as a white region in the binary image.
Artificial intelligence deep learning methods are explained in detail in the literature. The principle description will be given here of the application of the convolutional neural network algorithm for deep learning with artificial intelligence in the embodiments of the present application.
The gray value coefficients of each pixel in a certain region can be regarded as forming an array. Different coefficients of gray values of pixels in a certain region correspond to different arrays. A reasonable or preferred array may allow for a relatively reasonable or relatively accurate identification of the water wave optical characteristics of the water surface in the binary image. The convolutional neural network algorithm is a process of obtaining a reasonable or preferable array through continuous training of historical samples, namely reasonable setting of gray value coefficients of all pixel points. The convolutional neural network algorithm may include an input layer, a convolutional layer, a pooling layer, one or more re-convolutional layers, a re-pooling layer, a fully-connected layer, and an output layer. The input layer is used for inputting training samples of the binary image; the output layer is used for outputting the water wave optical characteristic area. The number of feature detectors may be set in the convolutional neural network algorithm. The feature detector can detect features in training samples and samples to be classified of the pixel gray value coefficients. Convolutional neural network algorithms can gradually combine the identified primary features through multiple training to form advanced features. The convolution layer is used for identifying the fit degree of the training sample and the sample to be classified with the feature detector and outputting features or feature combinations. The pooling layer is used to de-detail or background de-noise to enhance the identified features. The full connection layer and the output layer are used for outputting the calculation result of the single task workload. The fully connected layer may be provided with several layers of neurons, with a first layer of neurons being connected to the identified feature or combination of features, each layer of neurons being connected to neurons between adjacent layers, and a last layer of neurons being connected to the output layer. The weights, or probabilities of occurrence, of features or feature combinations are optimized by a back propagation mechanism. The gray value coefficient of the pixel point is optimized, so that a reasonable or relatively accurate water wave optical characteristic area is obtained.
S170: and identifying the wave crest and the wave trough of the water wave according to the optical characteristics of the water wave on the water surface in the binary image.
It will be appreciated that the water wave has peaks and valleys. In general, in the case of illumination, the peaks or troughs of the water wave are used as boundaries, and the gray values on both sides of the boundary line are greatly different. In the binary image, only black or white pixels are present, and the boundary between the region formed by the black pixels and the region formed by the white pixels may be a crest line or a trough line. Meanwhile, under the condition that the disturbance force is stable, the wave crest or the wave trough of the water wave is in radian diffusion trend.
Therefore, after the water wave optical characteristics of the water surface in the binary image are identified, the water wave area in the image can be identified firstly according to the water wave optical characteristics of the water surface in the binary image. And then identify borderlines near the light spots in the water wave area. And then the wave crest and the wave trough can be identified according to the gray value of the pixel area near the boundary line and the shape of the pixel area.
S180: and establishing a static water wave state according to the water wave crest and the water wave trough.
The static water wave state can be established according to the water wave crest and the water wave trough in the binary diagram at the current moment. The static water wave state is used as the mapping of the water wave form at the current moment, and the wave height and the wave length of the water wave at the current moment can be obtained according to the static water wave state. Of course, the water wave state may not be the highest form of the water wave crest or the lowest form of the water wave trough at this time.
S190: and generating a dynamic water wave state according to the plurality of static water wave states.
S200: and according to the dynamic water wave state, at least determining the water wave wavelength, the water wave speed and the water wave number.
It can be understood that the static water wave state is obtained by converting a single-frame water surface image into a binary image and then identifying the binary image. Whereas a single static water wave state does not reflect the dynamic process of water wave diffusion. Therefore, after the water surface images of the multiple frames are converted into the binary images, water waves in a plurality of binary images are identified, and a plurality of static water wave states are established. The static water wave states can be regarded as dynamic water wave states after being arranged according to the time stamp of the water surface image. The dynamic water wave state is used as a mapping of water wave diffusion, and the various stages from generation to propagation of the ripple can be simulated according to the dynamic water wave state. And then parameters such as the propagation distance of the water wave, the wavelength of the water wave, the wave speed of the water wave, the wave number of the water wave and the like can be calculated according to the shooting angle of the video, the actual range parameter of the water accumulation region, the mapping relation of the water accumulation region in the video and the proportional relation between the dynamic water wave state and the water accumulation region in the video.
S210: and calculating the water depth according to the water wave wavelength, the water wave speed and the water wave number.
It can be understood that when the application scene of the application is the inside of a mine cavity, the accumulated water in the mine cavity is of limited water depth, and the water wave of the accumulated water is shallow water wave. The formula for calculating the wave velocity of the shallow water is expressed as:
Where c represents the wave velocity, λ represents the wavelength, k represents the wave number, and h represents the water depth.
Or the water depth can be calculated by adopting a linear water wave theory in consideration of different water qualities of the ponding of the mine tunnel. The formula of the linear water wave theory is expressed as:
where c represents wave velocity, σ represents surface tension coefficient, ρ represents fluid density, k represents wave number, and h represents water depth.
The following describes the specific implementation process of the water depth detection method provided by the application:
When water is accumulated in the mine cavity, the water accumulation area is used as a target area. Firstly, wind energy is provided for the water surface of a target area to serve as disturbance force, and the water surface of the target area is continuously disturbed to form water waves. Meanwhile, the water surface of the target area is illuminated, so that the water surface video of the target area can be conveniently shot.
And then acquiring the water surface video of the target area, denoising the image of the water surface video frame by frame, and generating a preprocessing file. Inputting the preprocessed file into a color space model, and identifying color space data of the preprocessed file. And then adaptively constructing a binary image according to the color space data of the preprocessed file.
And then a convolutional neural network algorithm is used for identifying the optical characteristics of the water waves on the water surface in the binary image. And identifying a water wave region in the image according to the water wave optical characteristics of the water surface in the binary image. And then identify borderlines near the light spots in the water wave area. And identifying the wave crest and the wave trough according to the gray value of the pixel area and the shape of the pixel area near the boundary line.
And establishing a static water wave state according to the water wave crest and the water wave trough. And generating a dynamic water wave state according to the plurality of static water wave states. And according to the dynamic water wave state, at least determining the water wave wavelength, the water wave speed and the water wave number.
And carrying the wave length, wave speed and wave number of the water wave into the following formula to calculate the current water depth.
In the formula, c represents wave velocity, lambda represents wavelength, k represents wave number, and h represents water depth.
It should be noted that considering that the rise of the water is a real-time dynamic process, if the water depth exceeds the safe water depth, safety accidents may be caused. The inventor designs to judge whether to send out an alarm signal according to the water depth change rate.
Specifically, in one embodiment of the present application, the water depth detection method further includes:
Providing disturbing force for the water surface of the target area at intervals of preset time length and illuminating;
Calculating the water depth of a preset interval duration;
Calculating the water depth change rate;
And when the water depth change rate exceeds a preset threshold value, sending out an alarm signal.
It should be noted that the mine tunnel is complex in operation, and only the water accumulation rising rate is considered to possibly cause erroneous judgment, so that factors of the water accumulation rising duration are also considered. Specifically, in another embodiment of the present application, the water depth detection method further includes:
And when the water depth change rate exceeds a preset threshold value and maintains the preset rise duration, sending an alarm signal.
It should be further noted that the inventor considers that misjudgment may occur when identifying the wave crest and the wave trough according to the optical characteristics of the water wave on the water surface in the binary image. For this reason, the inventor identifies the wave crest and the wave trough by placing a float on the water surface in the target area.
Specifically, in another embodiment of the present application, the water depth detection method further includes:
Placing a buoy on the water surface of the target area;
identifying a float position in the binary image by using a convolutional neural network algorithm;
and identifying the wave crest and the wave trough of the water wave according to the floating position in the binary image.
It will be appreciated that the float is used as a reference. Because the buoy is convenient to identify on the water surface, the accuracy of identifying the wave crest and the wave trough of the water wave can be greatly improved by placing the buoy on the water surface of the target area. The float has various expression forms, such as a sphere, a plate, a cylinder, etc. The present application is not limited to the expression form of the float, and any reference object which floats on the water surface and is easy to identify can be considered as the float according to the present application.
Further, the outer surface of the buoy emits light or reflects light, so that the position of the buoy can be conveniently identified according to brightness.
The following describes the specific implementation process of the water depth detection method provided by the application:
When water is accumulated in the mine cavity, the water accumulation area is used as a target area. And placing a buoy with luminous or reflective outer surface on the water surface of the target area.
And then wind energy is provided for the water surface of the target area to serve as a disturbing force, and the water surface of the target area is continuously disturbed to form water waves. Meanwhile, the water surface of the target area is illuminated, so that the water surface video of the target area can be conveniently shot.
And then acquiring the water surface video of the target area, denoising the image of the water surface video frame by frame, and generating a preprocessing file. Inputting the preprocessed file into a color space model, and identifying color space data of the preprocessed file. And then adaptively constructing a binary image according to the color space data of the preprocessed file.
A convolutional neural network algorithm is then used to identify the float locations in the binary map. And identifying the wave crest and the wave trough according to the floating position in the binary image. And then identify borderlines near the light spots in the water wave area. And identifying the wave crest and the wave trough according to the gray value of the pixel area and the shape of the pixel area near the boundary line.
And establishing a static water wave state according to the water wave crest and the water wave trough. And generating a dynamic water wave state according to the plurality of static water wave states. And according to the dynamic water wave state, at least determining the water wave wavelength, the water wave speed and the water wave number.
And carrying the wave length, wave speed and wave number of the water wave into the following formula to calculate the current water depth.
In the formula, c represents wave velocity, sigma represents surface tension coefficient, ρ represents fluid density, k represents wave number, and h represents water depth.
According to the water depth detection method provided by the embodiment of the application, the water surface wave of the target area is identified by providing the disturbing force to the water surface of the target area and illuminating. According to the water wave information of the water surface of the target area, the current water depth can be calculated, so that real-time monitoring is realized, and the early warning performance is high. And by identifying the position of the buoy, the water wave state of the water surface of the target area is simulated, and the accuracy of acquiring the water wave information is improved.
Referring to fig. 2, to support the water depth detection method, the present application further provides a water depth detection system 100, including:
a disturbance device 11 for providing disturbance force to the water surface of the target area;
An illumination device 12 for illuminating the water surface of the target area;
an imaging device 13 for capturing a water surface video of a target area;
An acquisition module 14, configured to acquire a water surface video of the target area;
The preprocessing module 15 is used for denoising the image of the water surface video frame by frame to generate a preprocessing file;
A data conversion module 16 for inputting the preprocessed file into the color space model, identifying color space data of the preprocessed file;
the output module 17 is used for adaptively constructing a binary image according to the color space data of the preprocessed file;
The identification module 18 is used for identifying the water wave optical characteristics of the water surface in the binary image by using a convolutional neural network algorithm; the method is also used for identifying wave crests and wave troughs according to the water wave optical characteristics of the water surface in the binary image;
the modeling module 19 is used for establishing a static water wave state according to the water wave crest and the water wave trough; the dynamic water wave state is generated according to the plurality of static water wave states;
A calculation module 20, configured to determine at least a water wave wavelength, a water wave velocity, and a water wave number according to the dynamic water wave state; and the device is also used for calculating the water depth according to the water wave wavelength, the water wave speed and the water wave number.
It will be appreciated that the target area refers to a water depth observation area, such as a water accumulation area inside a mine cavity. The mine tunnel operation is complex, and the mine tunnel operation has various scenes needing water depth detection in the actual mine tunnel operation. According to the specific practice of mine tunnel operation, the following application provides a scene requiring detection of water depth: when the mine hole is blasted, ravines are easily formed in the mine hole. In the subsequent mining hole operation process, if water flow occurs, the water flow flows into the gully, and the depth of the gully water flow cannot be visually seen. Even if water is pumped to the water accumulation area, time is required. However, when a worker passes through a gully of unknown depth, safety accidents are very easy to occur, so that the water depth detection system 100 is required to detect the water depth of a target area in real time so as to send out safety precautions.
The water surface of the target area is in a stationary state without a disturbance source, when the water surface is level. When the water surface of the target area is disturbed to be in a non-static state, the gravity of the water is used as a restoring force to return the fluid particles to the original balance position. However, due to inertia, the fluid particles do not stop but continue to move when they return to their equilibrium position. The gravity force can exert the restoring force, so that the fluid particles repeatedly oscillate, and finally water waves appear on the water surface. Considering that there is no stable disturbance source on the water surface of the target area, the disturbance device 11 is required to provide disturbance force to the water surface of the target area. Specifically, the inventor considers that mine tunnel operation is always provided with a ventilation pipeline, and therefore connects the disturbance device 11 to the ventilation pipeline, so that the disturbance device 11 can provide wind energy as a disturbance source to provide disturbance force to the water surface of the target area. Considering that mine tunnel work is usually performed in a mine, and because there is no natural light inside the mine, the lighting device 12 is also required to illuminate the water surface of the target area.
The image pickup device 13 is used for picking up water surface video of a target area. Specifically, in view of the analysis of the water surface of the target area by the subsequent water depth detection system 100, the present application preferably sets the image pickup device 13 to take a water surface video of the target area at a fixed position.
The acquiring module 14 is configured to acquire a water surface video of the target area. It will be appreciated that the video file may be a multimedia file containing real-time audio, video information. The file format of the video file may be MPEG, AVI, ASF, MOV, 3GP, WMV, RM, RMVB, FLV/F4V. In a specific application scenario, the water surface video of the target area is a video file containing the water surface content of the target area acquired from the image pickup device 13.
The preprocessing module 15 is configured to denoise the image of the water surface video frame by frame, and generate a preprocessed file. Considering that the application scene of the application is usually the inside of a mine tunnel, such an environment does not have natural light beams and mechanical vibration exists during construction. Therefore, the water surface image of the target area captured by the image capturing device 13 usually has noise, i.e., blurred images and insignificant image features, which easily makes subsequent analysis difficult. For this purpose, the preprocessing module 15 is required to denoise the image of the water surface video frame by frame. Specifically, the preprocessing module 15 adopts a denoising algorithm to denoise the image of the water surface video. The denoising algorithm can be specifically represented by mean filtering, median filtering, gaussian filtering, bilateral filtering or the like. Wherein the mean filtering uses the average value of adjacent pixels to replace the original pixel value. The median filtering uses the median of the convolution templates instead of the pixel values. The gaussian filtering uses coefficient values of a convolution template instead of pixel values, the coefficients decreasing with increasing distance from the center of the template. The bilateral filtering combines the spatial proximity of the image and the pixel value similarity to replace the pixel value.
The denoised water surface image has small blurring degree and smooth image, and is more beneficial to subsequent analysis. The preprocessing module 15 records the denoised water surface image as a preprocessing file.
The data conversion module 16 is configured to input the preprocessed file into a color space model, and identify color space data of the preprocessed file.
It is understood that the color space model is a mathematical model describing colors by numerical values. Specifically, the color space model can identify the synthesis proportion of red, green and blue primary colors of a single pixel point of the pretreatment file. The color space model may also identify the saturation or chromaticity of individual pixels of the preprocessed file. The color space model may also represent non-colors with one component and colors with two independent components, thereby identifying black and white pixels and color pixels in the preprocessed file.
The output module 17 is configured to adaptively construct a binary image according to the color space data of the preprocessed file.
It will be appreciated that the binary image may be understood as having only two possible values or gray scale states for each pixel on the image. In other words, the gray value of any pixel point in the binary image is only 0 or 255, which represents black or white, respectively. After the color information of the binary image is simplified into black or white binary values, the data size of the binary image is smaller, and the processing speed is high.
Considering that the analysis object of the application is embodied as water surface information, and the black and white binary values of the binary image are just suitable for displaying edge information, the application preferably converts the preprocessed file into the binary image for analysis.
Specifically, the output module 17 adaptively constructs a binary image according to the color space data of the preprocessed file, which may be represented by setting a pixel color judgment threshold, and when the pixel color space data is greater than or equal to the pixel color judgment threshold, the output module 17 sets the gray value of the pixel point to 255, that is, white. When the pixel color space data is smaller than the pixel color judgment threshold, the output module 17 sets the gray value of the pixel point to 0, that is, black.
The identification module 18 is used for identifying the water wave optical characteristics of the water surface in the binary image by using a convolutional neural network algorithm; and the device is also used for identifying the wave crest and the wave trough of the water wave according to the optical characteristics of the water wave on the water surface in the binary image.
It is understood that the water wave optical characteristics of the water surface include a water wave reflective illumination texture or a water wave refractive illumination texture. In particular, the water wave reflective illumination texture or the water wave refractive illumination texture may represent a spot that the water wave presents under illumination. The water wave optical characteristic may appear as a white region in the binary image.
Artificial intelligence deep learning methods are explained in detail in the literature. The principle description will be given here of the application of the convolutional neural network algorithm for deep learning with artificial intelligence in the embodiments of the present application.
The gray value coefficients of each pixel in a certain region can be regarded as forming an array. Different coefficients of gray values of pixels in a certain region correspond to different arrays. A reasonable or preferred array may allow for a relatively reasonable or relatively accurate identification of the water wave optical characteristics of the water surface in the binary image. The convolutional neural network algorithm is a process of obtaining a reasonable or preferable array through continuous training of historical samples, namely reasonable setting of gray value coefficients of all pixel points. The convolutional neural network algorithm may include an input layer, a convolutional layer, a pooling layer, one or more re-convolutional layers, a re-pooling layer, a fully-connected layer, and an output layer. The input layer is used for inputting training samples of the binary image; the output layer is used for outputting the water wave optical characteristic area. The number of feature detectors may be set in the convolutional neural network algorithm. The feature detector can detect features in training samples and samples to be classified of the pixel gray value coefficients. Convolutional neural network algorithms can gradually combine the identified primary features through multiple training to form advanced features. The convolution layer is used for identifying the fit degree of the training sample and the sample to be classified with the feature detector and outputting features or feature combinations. The pooling layer is used to de-detail or background de-noise to enhance the identified features. The full connection layer and the output layer are used for outputting the calculation result of the single task workload. The fully connected layer may be provided with several layers of neurons, with a first layer of neurons being connected to the identified feature or combination of features, each layer of neurons being connected to neurons between adjacent layers, and a last layer of neurons being connected to the output layer. The weights, or probabilities of occurrence, of features or feature combinations are optimized by a back propagation mechanism. The gray value coefficient of the pixel point is optimized, so that a reasonable or relatively accurate water wave optical characteristic area is obtained.
The water wave has peaks and valleys. In general, in the case of illumination, the peaks or troughs of the water wave are borderlines, and the gray values on both sides of the borderlines are greatly different. In the binary image, only black or white pixels are present, and the boundary between the region formed by the black pixels and the region formed by the white pixels may be a crest line or a trough line. Meanwhile, under the condition that the disturbance force is stable, the wave crest or the wave trough of the water wave is in radian diffusion trend. Therefore, after the identification module 18 identifies the water wave optical characteristics of the water surface in the binary image, the water wave area in the image can be first identified according to the water wave optical characteristics of the water surface in the binary image. The identification module 18 then identifies borderlines near the light spots in the water wave area. The identification module 18 can identify the wave crest and the wave trough according to the gray value of the pixel area near the boundary line and the shape of the pixel area.
The modeling module 19 is configured to establish a static water wave state according to the water wave crest and the water wave trough; and the dynamic water wave state is generated according to the plurality of static water wave states.
The modeling module 19 may establish a static water wave state based on the water wave peaks and the water wave troughs in the current binary image. The static water wave state is used as the mapping of the water wave form at the current moment, and the wave height and the wave length of the water wave at the current moment can be obtained according to the static water wave state. Of course, the water wave state may not be the highest form of the water wave crest or the lowest form of the water wave trough at this time.
The static water wave state is obtained by converting a single-frame water surface image into a binary image and then identifying the binary image. Whereas a single static water wave state does not reflect the dynamic process of water wave diffusion. Therefore, the modeling module 19 recognizes the water waves in the plurality of binary images after the multi-frame water surface image is converted into the binary image, and establishes a plurality of static water wave states. The static water wave states can be regarded as dynamic water wave states after being arranged according to the time stamp of the water surface image. The dynamic water wave state is used as a mapping of water wave diffusion, and the various stages from generation to propagation of the ripple can be simulated according to the dynamic water wave state. And then parameters such as the propagation distance of the water wave, the wavelength of the water wave, the wave speed of the water wave, the wave number of the water wave and the like can be calculated according to the shooting angle of the video, the actual range parameter of the water accumulation region, the mapping relation of the water accumulation region in the video and the proportional relation between the dynamic water wave state and the water accumulation region in the video.
The calculation module 20 is configured to determine at least a water wave wavelength, a water wave velocity, and a water wave number according to the dynamic water wave state; and the device is also used for calculating the water depth according to the water wave wavelength, the water wave speed and the water wave number.
The calculation module 20 may obtain parameters such as ripple propagation time, propagation distance, wave wavelength, wave velocity, wave number, etc. according to the dynamic wave state.
Considering that when the application scene of the application is the inside of a mine cavity, the accumulated water in the mine cavity is of limited water depth, and the water wave of the accumulated water is shallow water wave. The formula for calculating the wave velocity of the shallow water is expressed as:
Where c represents the wave velocity, λ represents the wavelength, k represents the wave number, and h represents the water depth.
Or the water depth can be calculated by adopting a linear water wave theory in consideration of different water qualities of the ponding of the mine tunnel. The formula of the linear water wave theory is expressed as:
where c represents wave velocity, σ represents surface tension coefficient, ρ represents fluid density, k represents wave number, and h represents water depth.
The following describes a specific implementation procedure of the water depth detection system 100 provided by the present application:
when water is accumulated in the mine cavity, the water accumulation area is used as a target area. Firstly, the disturbance device 11 provides wind energy for the water surface of the target area as disturbance force, and continuously disturbs the water surface of the target area to form water waves. At the same time, the illumination device 12 illuminates the water surface of the target area, so that the image pickup device 13 can pick up the water surface video of the target area.
The acquisition module 14 then acquires the surface video of the target area. The preprocessing module 15 denoises the image of the water surface video frame by frame to generate a preprocessing file. The data conversion module 16 inputs the preprocessed files into the color space model, identifying color space data of the preprocessed files. The output module 17 then adaptively constructs a binary image according to the color space data of the preprocessed file.
The identification module 18 then identifies the water wave optical characteristics of the water surface in the binary image using a convolutional neural network algorithm. The identification module 18 identifies the water wave region in the image based on the water wave optical characteristics of the water surface in the binary image. The identification module 18 then identifies borderlines near the light spots in the water wave area. The identification module 18 identifies the wave crest and the wave trough according to the gray value of the pixel area near the boundary line and the shape of the pixel area.
The modeling module 19 establishes a static water wave state based on the water wave peaks and the water wave troughs. The modeling module 19 then generates a dynamic water wave state based on the number of static water wave states. The calculation module 20 determines at least the water wave wavelength, the water wave velocity, and the water wave number according to the dynamic water wave state.
The calculation module 20 brings the wave length, wave velocity and wave number of the water into the following formula to calculate the current water depth.
In the formula, c represents wave velocity, lambda represents wavelength, k represents wave number, and h represents water depth.
It should be noted that considering that the rise of the water is a real-time dynamic process, if the water depth exceeds the safe water depth, safety accidents may be caused. The inventors devised an alarm module 21 for this purpose, said alarm module 21 determining whether to issue an alarm signal based on the rate of change of the water depth.
Specifically, in one embodiment of the present application, the disturbing device 11 is further configured to provide disturbing force to the water surface of the target area at a preset interval;
the lighting device 12 is further configured to illuminate the water surface of the target area at intervals of a preset duration;
The calculating module 20 is further configured to calculate a water depth of a preset interval duration; the method is also used for calculating the water depth change rate;
The water depth detection system 100 further comprises an alarm module 21 for sending an alarm signal when the water depth change rate exceeds a preset threshold.
It should be noted that the mine tunnel is complex in operation, and only the water accumulation rising rate is considered to possibly cause erroneous judgment, so that factors of the water accumulation rising duration are also considered. Specifically, in another embodiment of the present application, the alarm module 21 is further configured to send an alarm signal when the water depth change rate exceeds a preset threshold and maintains a preset rise duration.
It should be further noted that, the inventor considers that the recognition module 18 recognizes that the water wave crest and the water wave trough may be misjudged according to the optical characteristics of the water wave on the water surface in the binary image. For this purpose, the inventor recognizes the wave crest and the wave trough by placing a float 22 on the water surface in the target area.
Specifically, in yet another embodiment provided by the present application, the water depth detection system 100 further includes:
A float 22 placed on the water surface of the target area;
the identification module 18 is further configured to identify a location of a float in the binary image using a convolutional neural network algorithm; and the device is also used for identifying the wave crest and the wave trough of the water wave according to the floating position in the binary image.
It will be appreciated that the float 22 is used as a reference. Since the buoy 22 is easy to identify on the water surface, the accuracy of identifying the wave crest and the wave trough by the identifying module 18 can be greatly improved by placing the buoy 22 on the water surface in the target area. The float 22 may take a variety of forms, such as spheres, plates, cylinders, and the like. The present application is not limited to the expression form of the float 22, and any reference that floats on the water surface and is easy to identify can be considered as the float 22 according to the present application.
Further, the outer surface of the float 22 emits light or reflects light, which facilitates the identification of the float position based on brightness.
The following describes a specific implementation procedure of the water depth detection system 100 provided by the present application:
When there is water accumulation in the mine tunnel, the water depth detection system 100 takes the water accumulation area as a target area. A surface emitting or reflective float 22 is placed on the water surface in the target area.
The disturbance device 11 then provides wind energy to the water surface of the target area as a disturbance force, and continuously disturbs the water surface of the target area to form water waves. At the same time, the illumination device 12 illuminates the water surface of the target area, so that the image pickup device 13 can pick up the water surface video of the target area.
The acquisition module 14 then acquires the surface video of the target area. The preprocessing module 15 denoises the image of the water surface video frame by frame to generate a preprocessing file. The data conversion module 16 inputs the preprocessed files into the color space model, identifying color space data of the preprocessed files. The output module 17 then adaptively constructs a binary image according to the color space data of the preprocessed file.
The identification module 18 then identifies the location of the float in the binary image using a convolutional neural network algorithm. The identification module 18 identifies the wave crest and the wave trough according to the float position in the binary image. The identification module 18 then identifies borderlines near the light spots in the water wave area. The identification module 18 identifies the wave crest and the wave trough according to the gray value of the pixel area near the boundary line and the shape of the pixel area.
The modeling module 19 establishes a static water wave state based on the water wave peaks and the water wave troughs. The modeling module 19 then generates a dynamic water wave state based on the number of static water wave states. The calculation module 20 determines at least the water wave wavelength, the water wave velocity, and the water wave number according to the dynamic water wave state.
The calculation module 20 brings the wave length, wave velocity and wave number of the water into the following formula to calculate the current water depth.
In the formula, c represents wave velocity, sigma represents surface tension coefficient, ρ represents fluid density, k represents wave number, and h represents water depth.
According to the water depth detection system 100 provided by the embodiment of the application, the water wave on the water surface of the target area is identified by providing disturbing force to the water surface of the target area and illuminating. According to the water wave information of the water surface of the target area, the current water depth can be calculated, so that real-time monitoring is realized, and the early warning performance is high. And by identifying the position of the buoy, the water wave state of the water surface of the target area is simulated, and the accuracy of acquiring the water wave information is improved.
It should be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the statement "comprises one … …" does not exclude that an additional identical element is present in a process, method, article or apparatus that comprises the element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (6)
1. The water depth detection method is characterized by comprising the following steps of:
Providing disturbing force for the water surface of the target area and illuminating;
acquiring a water surface video of the target area;
Denoising the image of the water surface video frame by frame to generate a preprocessing file;
Inputting the preprocessed file into a color space model, and identifying color space data of the preprocessed file;
according to the color space data of the preprocessing file, a binary image is adaptively constructed;
identifying the water wave optical characteristics of the water surface in the binary image by using a convolutional neural network algorithm;
According to the water wave optical characteristics of the water surface in the binary image, identifying the water wave crest and the water wave trough, comprising: placing a buoy on the water surface of a target area, identifying the position of the buoy in a binary image by using a convolutional neural network algorithm, and identifying the wave crest and the wave trough of the water wave according to the position of the buoy in the binary image, wherein the outer surface of the buoy emits light or reflects light so as to be convenient for identifying the position of the buoy according to brightness;
Establishing a static water wave state according to the water wave crest and the water wave trough;
generating a dynamic water wave state according to the plurality of static water wave states;
according to the dynamic water wave state, at least determining the water wave wavelength, the water wave speed and the water wave number;
Calculating the water depth according to the water wave wavelength, the water wave speed and the water wave number;
wherein the water wave optical characteristics of the water surface comprise a water wave reflection illumination texture or a water wave refraction illumination texture.
2. The water depth detection method according to claim 1, wherein the water depth detection method further comprises:
Providing disturbing force for the water surface of the target area at intervals of preset time length and illuminating;
Calculating the water depth of a preset interval duration;
Calculating the water depth change rate;
And when the water depth change rate exceeds a preset threshold value, sending out an alarm signal.
3. The water depth detection method according to claim 2, wherein the water depth detection method further comprises:
And when the water depth change rate exceeds a preset threshold value and maintains the preset rise duration, sending an alarm signal.
4. A water depth detection system, comprising:
the disturbance device is used for providing disturbance force for the water surface of the target area;
the illumination device is used for illuminating the water surface of the target area;
The camera device is used for shooting a water surface video of the target area;
The acquisition module is used for acquiring the water surface video of the target area;
the preprocessing module is used for denoising the image of the water surface video frame by frame to generate a preprocessing file;
The data conversion module is used for inputting the preprocessing file into a color space model and identifying color space data of the preprocessing file;
the output module is used for adaptively constructing a binary image according to the color space data of the preprocessed file;
The identification module is used for identifying the water wave optical characteristics of the water surface in the binary image by using a convolutional neural network algorithm; and the method is also used for identifying the wave crest and the wave trough of the water wave according to the optical characteristics of the water wave on the water surface in the binary image, and comprises the following steps: placing a buoy on the water surface of a target area, identifying the position of the buoy in a binary image by using a convolutional neural network algorithm, and identifying the wave crest and the wave trough of the water wave according to the position of the buoy in the binary image, wherein the outer surface of the buoy emits light or reflects light so as to be convenient for identifying the position of the buoy according to brightness;
The modeling module is used for establishing a static water wave state according to the water wave crest and the water wave trough; the dynamic water wave state is generated according to the plurality of static water wave states;
the calculation module is used for determining at least the wave wavelength, the wave velocity and the wave number of the water wave according to the dynamic water wave state; the water depth is calculated according to the water wave wavelength, the water wave speed and the water wave number;
wherein the water wave optical characteristics of the water surface comprise a water wave reflection illumination texture or a water wave refraction illumination texture.
5. The water depth detection system of claim 4, wherein the disturbance device is further configured to provide a disturbance force to the water surface of the target area at predetermined intervals;
The lighting device is also used for lighting the water surface of the target area at intervals of preset time length;
the calculating module is also used for calculating the water depth of the preset interval duration; the method is also used for calculating the water depth change rate;
the water depth detection system further comprises an alarm module, wherein the alarm module is used for sending an alarm signal when the water depth change rate exceeds a preset threshold value.
6. The water depth detection system of claim 5, wherein the alarm module is further configured to signal an alarm when the rate of change of water depth exceeds a preset threshold and maintains a preset rise time period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210063742.3A CN114677324B (en) | 2022-01-20 | 2022-01-20 | Water depth detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210063742.3A CN114677324B (en) | 2022-01-20 | 2022-01-20 | Water depth detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114677324A CN114677324A (en) | 2022-06-28 |
| CN114677324B true CN114677324B (en) | 2024-06-07 |
Family
ID=82070872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210063742.3A Active CN114677324B (en) | 2022-01-20 | 2022-01-20 | Water depth detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114677324B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108120981A (en) * | 2017-12-27 | 2018-06-05 | 中科卫星应用德清研究院 | Shallow water depth radar remote sensing detection method |
| CN110674980A (en) * | 2019-09-12 | 2020-01-10 | 中交疏浚技术装备国家工程研究中心有限公司 | Real-time wave prediction method for engineering ship |
| CN113283437A (en) * | 2021-07-22 | 2021-08-20 | 中国海洋大学 | Submarine sand wave feature identification method |
| KR20210105487A (en) * | 2020-02-18 | 2021-08-27 | 단국대학교 산학협력단 | Method for estimation of river bed change rate using hyperspectral image |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050018882A1 (en) * | 2003-06-30 | 2005-01-27 | Iowa University Research Foundation | Controlled surface wave image velocimetry |
| US9046363B2 (en) * | 2012-04-27 | 2015-06-02 | SATOP GmbH | Using multispectral satellite data to determine littoral water depths despite varying water turbidity |
-
2022
- 2022-01-20 CN CN202210063742.3A patent/CN114677324B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108120981A (en) * | 2017-12-27 | 2018-06-05 | 中科卫星应用德清研究院 | Shallow water depth radar remote sensing detection method |
| CN110674980A (en) * | 2019-09-12 | 2020-01-10 | 中交疏浚技术装备国家工程研究中心有限公司 | Real-time wave prediction method for engineering ship |
| KR20210105487A (en) * | 2020-02-18 | 2021-08-27 | 단국대학교 산학협력단 | Method for estimation of river bed change rate using hyperspectral image |
| CN113283437A (en) * | 2021-07-22 | 2021-08-20 | 中国海洋大学 | Submarine sand wave feature identification method |
Non-Patent Citations (2)
| Title |
|---|
| Todd K. Holland.Application of the Linear Dispersion Relation with Respect to Depth Inversion and Remotely Sensed Imagery.《IEEE Transaction on Geoscience and Remote Sensing》.2001,第39卷(第9期),第2060-2072页. * |
| 一种无干扰全流程水深测试方法及 其在溃坝水流试验研究中的应用;刘鑫;《工程科学与技术》;20190531;第51卷(第3期);第52-58页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114677324A (en) | 2022-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460753B (en) | Method for detecting floating object on water | |
| CN110751630B (en) | Power transmission line foreign matter detection method and device based on deep learning and medium | |
| CN111415329A (en) | Workpiece surface defect detection method based on deep learning | |
| CN106770087A (en) | Greasy dirt remote sensing module, system and method | |
| CN112330593A (en) | Building surface crack detection method based on deep learning network | |
| CN112284619B (en) | Oil leakage real-time monitoring device and detection method | |
| CN113591592A (en) | Overwater target identification method and device, terminal equipment and storage medium | |
| CN112418028A (en) | Satellite image ship identification and segmentation method based on deep learning | |
| Wang et al. | Vision-based in situ monitoring of plankton size spectra via a convolutional neural network | |
| CN116087036A (en) | Device for identifying images of sediment plume of deep sea mining and image analysis method | |
| CN116777877A (en) | Circuit board defect detection method, device, computer equipment and storage medium | |
| CN111723656A (en) | Smoke detection method and device based on YOLO v3 and self-optimization | |
| CN112907138B (en) | Power grid scene early warning classification method and system from local to whole perception | |
| Madshaven et al. | Hole detection in aquaculture net cages from video footage | |
| CN114677324B (en) | Water depth detection method and system | |
| CN110738698B (en) | Floating type submarine data measurement method and device and electronic equipment | |
| KR102602439B1 (en) | Method for detecting rip current using CCTV image based on artificial intelligence and apparatus thereof | |
| KR101268596B1 (en) | Foreground extraction apparatus and method using CCB and MT LBP | |
| CN112686105B (en) | Fog concentration grade identification method based on video image multi-feature fusion | |
| CN115082833A (en) | Method and system for judging threat degree of water target | |
| CN114005064A (en) | Biological water body pollution early warning method and device based on machine vision technology | |
| TW201809671A (en) | An optical flow speed measuring module and the method thereof | |
| CN113012244A (en) | Egg freshness detection method based on inclusion module and Attention mechanism | |
| Zhang et al. | Fish target detection and speed estimation method based on computer vision | |
| CN117671472B (en) | Underwater multi-target group identification method based on dynamic visual sensor |
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 |