Video optical river surface velocity measurement method, device, equipment and medium

Abstract

The invention discloses a video optical river surface speed measurement method, device and equipment and a medium, and relates to the technical field of river reach flow monitoring. According to the method, the visible light video image and the thermal imaging video image are combined, when the visible light intensity is good, the visible light high-resolution video image is taken as a main part, and the temperature feature of the thermal imaging video image is superposed to the visible light video image in a pixel point matching mode, so that the recognition feature of the video image is improved; when the light intensity is weak, a thermal imaging image is used as a main video image, pixel fusion is carried out on the temperature information of the river reach surface and the water surface texture, floating objects and other features of visible light through pixel point matching and pixel-level video image fusion, the recognition features of the video images are improved, and the recognition accuracy is improved. Based on the visible light video image and the thermal imaging video image, multispectral river reach optical video flow velocity monitoring with all-weather adaptability is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of river section flow monitoring, in particular to a video optical river surface velocity measurement method, device, equipment and medium. BACKGROUND

[0002] In the water conservancy and environmental industries, the existing non-contact river section flow monitoring technology mainly uses radar wave velocity meters, radar scanning, video images and the like to monitor the surface flow velocity of the river section, and then inversely calculates the river section flow according to the surface flow velocity.

[0003] The existing non-contact river section surface video flow velocity monitoring simply uses a single video camera technology to give the surface flow velocity of the river, and then uses the flow velocity curve of the river from the ground to the surface to calculate the flow of the river.

[0004] The existing video optical flow velocity monitoring equipment is mostly single-camera visible light monitoring equipment. Although some equipment has night light compensation, there are still many problems in weak light and night river section surface flow velocity monitoring. The monitoring accuracy at night is generally low. Some optical video monitoring equipment uses CCTV monitoring cameras. When the optical fiber is weak or at night, the video image has a lot of noise, which greatly affects the subsequent video flow velocity calculation. The existing algorithm can realize rapid flow measurement to a certain extent, but has two obvious defects: 1. The video camera device itself is not suitable for multiple environments. There is a big gap in flow measurement at dusk, cloudy days, especially at night. Although there are studies on night light compensation, the effect of the light compensation lamp is greatly reduced due to the refraction and reflection of light on the river surface. Some scholars use diffuse reflection light compensation on the opposite bank, but the effect is quite limited. In addition, some optical cameras use near-infrared 850nm or 950nm to widen the monitoring range at night, but the near-infrared light is also weak at night, so it cannot form a good all-weather video optical flow velocity monitoring scheme in weak light and at night. 2. The existing method of measuring flow velocity or flow rate based on video images relies on the optical characteristics of image pixel texture, gradient and the like generated by water surface ripples, texture, floating objects and the like. The method is limited to natural visible light or slightly wider near-infrared spectrum, and the spectral feature range obtained is narrow, and more features of the water surface cannot be obtained. SUMMARY

[0005] The purpose of the present application is to provide a video optical river surface velocity measurement method, device, equipment and medium to realize all-weather video optical flow velocity monitoring.

[0006] To achieve the above purpose, the present application provides the following solutions.

[0007] In a first aspect, the application provides a video-optical river surface velocity measurement method, comprising:

[0008] simultaneously acquiring a visible light video image and a thermal imaging video image of a river section to be measured;

[0009] when the light condition when the visible light video image is acquired meets the visible light image shooting requirement, superimposing the thermal imaging video image with a preset transparency on the visible light video image to obtain a superimposed image as a target image;

[0010] when the light condition when the visible light video image is acquired does not meet the visible light image shooting requirement, performing feature fusion on the visible light video image and the thermal imaging video image to obtain a fused image as the target image;

[0011] performing river surface flow velocity calculation of the river section to be measured according to the target image.

[0012] In a second aspect, the application provides a video-optical river surface velocity measurement device, which applies the video-optical river surface velocity measurement method described above, and comprises a binocular camera device, an image processing device and an edge computing device connected in sequence.

[0013] The binocular camera device is configured to simultaneously acquire a visible light video image and a thermal imaging video image of a river section to be measured.

[0014] The image processing device is configured to, when the light condition when the visible light video image is acquired meets the visible light image shooting requirement, superimpose the thermal imaging video image with a preset transparency on the visible light video image to obtain a superimposed image as a target image; and when the light condition when the visible light video image is acquired does not meet the visible light image shooting requirement, perform feature fusion on the visible light video image and the thermal imaging video image to obtain a fused image as the target image.

[0015] The edge computing device is configured to perform river surface flow velocity calculation of the river section to be measured according to the target image.

[0016] In a third aspect, the application provides a computer device for local edge computing, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the video-optical river surface velocity measurement method described above.

[0017] In a fourth aspect, the application provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the video-optical river surface velocity measurement method described above.

[0018] According to the specific embodiments provided in the application, the application has the following technical effects.

[0019] The application provides a video optical river surface speed measurement method, device, equipment and medium, which combines a visible light video image and a thermal imaging video image, uses the visible light high-resolution video image as the main video image when the visible light intensity is good, matches the temperature characteristics of the thermal imaging video image to the visible light video image through pixel points to improve the identification characteristics of the video image, and uses the thermal imaging image as the main video image when the light intensity is weak, matches the pixel points and performs pixel-level video image fusion to fuse the temperature information of the river surface and the visible light water surface texture and floating object characteristics, thereby improving the identification characteristics of the video image. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description only constitute some embodiments of the application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0021] Figure 1 A flowchart of a video optical river surface speed measurement method provided by an embodiment of the application.

[0022] Figure 2 A process visualization schematic diagram of a video optical river surface speed measurement method provided by an embodiment of the application.

[0023] Figure 3 A principle diagram of a video optical river surface speed measurement method provided by an embodiment of the application.

[0024] Figure 4 A structural schematic diagram of a computer device for local edge computing provided by an embodiment of the application. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments only constitute some of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the application.

[0026] The above objects, features and advantages of the present application will become more apparent from the following detailed description considered in conjunction with the accompanying drawings and specific embodiments.

[0027] The embodiment of the present application considers the shortcomings of the existing river optical video flow rate monitoring scheme, such as low monitoring accuracy and poor adaptability in weak light and night conditions. By superimposing or fusing the visible light video image and the thermal imaging video image, additional water surface temperature features can be obtained, which not only increases the anchor features of the video image flow rate calculation and improves the accuracy of the video image flow rate calculation at night, but also widens the all-weather applicability of the video flow rate monitoring device at night and during the day. Specifically, by using the visible light + thermal imaging binocular camera method, since the image resolution of the thermal imaging camera is generally lower than that of the visible light camera, according to the intensity of the visible light, the visible light video image or the thermal imaging video image can be superimposed or pixel fused in different time periods as needed. When the visible light is good during the day, the temperature features of the thermal imaging video image are added to the visible light video image to calculate the flow rate of the river section. In weak light and at night, the resolution of the thermal imaging video image is improved by fusing the visible light and thermal imaging video images, and the image temperature features and part of the visible light video image features of the video image flow rate calculation under weak light and at night are increased, thereby widening the all-weather applicability of the video flow rate monitoring device.

[0028] In one exemplary embodiment, a video optical river surface velocity measurement method is provided, as shown in Figure 1 The method comprises the following steps 101-104.

[0029] Step 101, simultaneously acquiring a visible light video image and a thermal imaging video image of a river section to be measured.

[0030] Step 102, when the light condition for acquiring the visible light video image meets the visible light image shooting requirement, superimposing the thermal imaging video image with a preset transparency on the visible light video image to obtain a superimposed image as a target image. Exemplarily, the visible light image shooting requirement is that the light intensity is greater than a light intensity threshold.

[0031] Step 103, when the light condition for acquiring the visible light video image does not meet the visible light image shooting requirement, fusing the visible light video image and the thermal imaging video image to obtain a fused image as a target image.

[0032] Step 104, calculating the river surface flow rate of the river section to be measured according to the target image.

[0033] Implementing the above steps 101-104 can achieve the following technical effects.

[0034] This application addresses the shortcomings of existing optical video flow velocity calculation methods, which suffer from poor adaptability and low accuracy under low light and nighttime conditions. It employs a method that combines visible light and thermal imaging with binocular imaging and then overlays or fuses the video images. This not only adds temperature image pixel features to the video flow velocity calculation but also solves the applicability problem of video image flow velocity calculation under nighttime conditions. This not only improves the accuracy of flow velocity calculation under low light and nighttime conditions but also lays the foundation for future development of more spectral and highly adaptable non-contact video flow velocity monitoring.

[0035] In another exemplary embodiment, in step 101 above, the surface velocity of the river section to be measured is acquired using a binocular camera device with visible light and thermal imaging, respectively.

[0036] In another exemplary embodiment, to facilitate the overlay of visible light video images and thermal imaging video images, two black and white checkerboard markers are provided within the field of view of the visible light video images and the thermal imaging video images. The black and white checkerboard markers have different temperature characteristics when illuminated by a xenon lamp with a heat source.

[0037] In another exemplary embodiment, step 102 specifically includes steps 201-205.

[0038] Step 201: Extract and recognize image gradient features from the visible light video image to obtain the pixel coordinates of each black square in the two black and white checkerboard markers, forming a first pixel coordinate set and a second pixel coordinate set.

[0039] Step 202: Extract and recognize image gradient features from the thermal imaging video image to obtain the pixel coordinates of each black square in the two black and white checkerboard markers, forming a third pixel coordinate set and a fourth pixel coordinate set.

[0040] Step 203: Match the pixel coordinates in the first pixel coordinate set and the third pixel set to obtain the first set of matching point pairs.

[0041] Step 204: Match the pixel coordinates in the second pixel coordinate set and the fourth pixel coordinate set to obtain the second set of matching point pairs;

[0042] Step 205: Based on the first set of matching point pairs and the second set of matching point pairs, a thermal imaging video image with a preset transparency is superimposed on the visible light video image to obtain the superimposed image as the target image. For example, the preset transparency is 50%.

[0043] In another exemplary embodiment, step 103 above may be implemented using steps 301-308 as follows.

[0044] Step 301: Crop the visible light video image to obtain a cropped visible light video image; the size of the cropped visible light video image is the same as the size of the thermal imaging video image.

[0045] Step 302: Extract and recognize image gradient features from the visible light video image to obtain the pixel coordinates of each black square in the two black and white checkerboard markers, forming a first pixel coordinate set and a second pixel coordinate set.

[0046] Step 303: Extract and recognize image gradient features from the thermal imaging video image to obtain the pixel coordinates of each black square in the two black and white checkerboard markers, forming a third pixel coordinate set and a fourth pixel coordinate set.

[0047] Step 304: Match the pixel coordinates in the first pixel coordinate set and the third pixel set to obtain the first set of matching point pairs.

[0048] Step 305: Match the pixel coordinates in the second pixel coordinate set and the fourth pixel coordinate set to obtain the second set of matching point pairs.

[0049] Step 306: Align the thermal imaging video image and the cropped visible light video image according to the first set of matching point pairs and the second set of matching point pairs.

[0050] Step 307: Using structural similarity calculation, extract the structural similarity features between the aligned thermal imaging video image and the cropped visible light video image.

[0051] The formula for calculating structural similarity is as follows:

[0052]

[0053] Where x is a local window image of the thermal imaging video image, y is a local window image of the cropped visible light video image, and μ x and μ y Let σ be the mean local brightness of x and y, respectively. x and σ y The local contrast standard deviations for x and y are σ and y, respectively. xy Let C1 and C2 be the local covariances of x and y, and C1 and C2 be preset parameters related to the dynamic range L of the image, where C1 = (0.01 × L). 2 C2 = (0.03 × L) 2 .

[0054] Step 308: Based on the structural similarity features of the thermal imaging video image and the cropped visible light video image, an image fusion algorithm is used to fuse the features of the thermal imaging video image and the cropped visible light video image to obtain a fused image as the target image.

[0055] In another exemplary embodiment, in order to make the objectives, features and advantages of this application more apparent and understandable, in conjunction with Figure 2 and Figure 3 The video optical river surface velocity measurement method provided in the above embodiments will be described in detail, specifically including the following steps 401-415.

[0056] Step 401: The visible light and thermal imaging binocular camera devices acquire the surface velocity of the river section to be measured.

[0057] Step 402: Depending on the intensity of visible light at the scene, if the visible light is strong, then the acquired visible light video image will be the primary focus. In this case, the resolution of the visible light video image is usually above 1080P or 2160P.

[0058] Step 403: Place the black and white checkerboard markers at two locations within the field of view of the video image, and illuminate the black and white checkerboard markers with a heat source using xenon lamps, so that the black and white checkerboard markers form images with different temperature characteristics.

[0059] Step 404: Simultaneously acquire thermal imaging video images, so that the black and white checkerboard pattern has obvious image features in both thermal imaging video images and visible light video images.

[0060] Step 405: Extract image gradient features from the visible light video image. Taking a 12×6 black and white checkerboard as an example, obtain the image pixel coordinates of two black and white checkerboard markers as x1, x2...x40 (forming the first set of pixel coordinates) and y1, y2...y40 (forming the second set of pixel coordinates).

[0061] Step 406: Since the black and white checkerboard pattern has obvious image gradient features after being illuminated by the heat source light, the thermal imaging video image is subjected to image gradient feature extraction. The method for extracting image gradient features is to detect the difference calculation of image pixel values ​​to describe the rate of change of local areas of the image.

[0062] G(i,j)=dx(i,j)+dy(i,j);

[0063] Where G(i,j) is the feature change rate at pixel (i,j), dx(i,j) is the feature change rate in the x direction at pixel (i,j), and dy(i,j) is the feature change rate in the y direction at pixel (i,j).

[0064] Step 407: Taking a 12*6 black and white checkerboard as an example, obtain the image pixel coordinates of two black and white checkerboard markers in the video image field of view as xx1,xx2...xx40 (forming the third pixel coordinate set) and yy1,yy2...yy40 (forming the fourth pixel coordinate set).

[0065] Step 408: Typically, the resolution of a thermal imaging video image is 480P. When the natural visible light illumination is strong and good, the pixel positions of x1, x2...x40 and xx1, xx2...xx40, as well as y1, y2...y40 and yy1, yy2...yy40 are quickly matched. The visible light video image is used as the main video image channel, and a thermal imaging video image with 50% transparency is superimposed to form a partially overlapping visible light + thermal imaging superimposed image. At this time, the superimposed image is still 1080P or 2160P. The temperature characteristics of the thermal imaging video image are superimposed only on the original visible light video image to enhance the characteristics of the video image flow rate calculation.

[0066] Step 409: Calculate the surface velocity of the river section to be measured using edge computing equipment to form a surface velocity line or velocity field of the river section.

[0067] Step 410: If the visible light illumination is weak or at night, simultaneously acquire visible light video images and thermal imaging video images; repeat steps 405 and 406 to acquire the pixel positions that match x1, x2...x40 with xx1, xx2...xx40, and y1, y2...y40 with yy1, yy2...yy40.

[0068] Step 411: Using the 640*480 pixel thermal imaging video image as the main video channel, crop the visible light video image to a size of 640*480.

[0069] Step 412: Extract the structural similarity (SSIM) features of the thermal imaging video image and the structural similarity characteristics of the visible light video image.

[0070] Step 413: Create a new video image with a canvas of 1280*960. Use thermal imaging video image and visible light video image and extracted structural similarity features, and supplement with fusion methods such as image Poisson fusion or pyramid fusion to perform feature fusion on thermal imaging video image and cropped visible light video image to obtain fused image of 1280*960.

[0071] Step 414: The resolution of the fused image is increased to 960P. Using an edge computing device, the surface flow velocity of the river under low light or nighttime conditions is calculated based on the fused image.

[0072] Step 415: Calculate the river flow rate based on the river surface velocity using an edge computing device.

[0073] Based on the same inventive concept, this application also provides a video optical river surface velocity measurement device for implementing the video optical river surface velocity measurement method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more video optical river surface velocity measurement device embodiments provided below can be found in the limitations of the video optical river surface velocity measurement method described above, and will not be repeated here.

[0074] In one exemplary embodiment, a video optical river surface velocity measuring device is provided, comprising a binocular camera device, an image processing device, and an edge computing device connected in sequence; the binocular camera device is used to simultaneously acquire visible light video images and thermal imaging video images of the river section to be measured; the image processing device is used to superimpose a thermal imaging video image with a preset transparency onto the visible light video image when the illumination conditions at the time of acquiring the visible light video image meet the requirements for capturing the visible light image, to obtain a superimposed image as a target image; when the illumination conditions at the time of acquiring the visible light video image do not meet the requirements for capturing the visible light image, the visible light video image and the thermal imaging video image are fused to obtain a fused image as a target image; the edge computing device is used to calculate the river surface velocity of the river section to be measured based on the target image.

[0075] In one exemplary embodiment, a computer device for local edge computing is provided. This computer device may be a server or a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and databases. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a video optical river surface velocimetry method.

[0076] Those skilled in the art will understand that Figure 4The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer devices on which the present application is applied. Specific computer devices for local edge computing may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device for local edge computing is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0077] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0078] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0079] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0080] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0081] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0082] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A video optical method for measuring river surface velocity, characterized in that, include: Simultaneously acquire visible light video images and thermal imaging video images of the river section to be measured; Two black and white checkerboard markers are set within the field of view of the visible light video image and the thermal imaging video image. The black and white checkerboard markers have different temperature characteristics when illuminated by xenon lamps with heat sources. When the lighting conditions at the time of acquiring the visible light video image meet the requirements for capturing the visible light image, a thermal imaging video image with a preset transparency is superimposed on the visible light video image to obtain the superimposed image as the target image. When the lighting conditions when acquiring the visible light video image do not meet the requirements for capturing the visible light image, the visible light video image and the thermal imaging video image are fused to obtain a fused image as the target image. The surface velocity of the river section to be measured is calculated based on the target image.

2. The video optical river surface velocity measurement method according to claim 1, characterized in that, The step of superimposing a thermal imaging video image with preset transparency onto the visible light video image to obtain the superimposed image as the target image specifically includes: Image gradient feature extraction and recognition are performed on the visible light video image to obtain the pixel coordinates of each black square in the two black and white checkerboard markers, forming a first pixel coordinate set and a second pixel coordinate set. Image gradient feature extraction and recognition are performed on the thermal imaging video image to obtain the pixel coordinates of each black square in the two black and white checkerboard markers, forming a third pixel coordinate set and a fourth pixel coordinate set. Match the pixel coordinates in the first pixel coordinate set and the third pixel set to obtain the first set of matching point pairs; Match the pixel coordinates in the second pixel coordinate set and the fourth pixel coordinate set to obtain the second set of matching point pairs; Based on the first set of matching point pairs and the second set of matching point pairs, a thermal imaging video image with a preset transparency is superimposed on the visible light video image to obtain the superimposed image as the target image.

3. The video optical river surface velocity measurement method according to claim 1, characterized in that, The preset transparency is 50%.

4. The video optical river surface velocity measurement method according to claim 1, characterized in that, The visible light video image and the thermal imaging video image are fused to obtain a fused image as the target image, specifically including: The visible light video image is cropped to obtain a cropped visible light video image; the size of the cropped visible light video image is the same as the size of the thermal imaging video image. Image gradient feature extraction and recognition are performed on the visible light video image to obtain the pixel coordinates of each black square in the two black and white checkerboard markers, forming a first pixel coordinate set and a second pixel coordinate set. Image gradient feature extraction and recognition are performed on the thermal imaging video image to obtain the pixel coordinates of each black square in the two black and white checkerboard markers, forming a third pixel coordinate set and a fourth pixel coordinate set. Match the pixel coordinates in the first pixel coordinate set and the third pixel set to obtain the first set of matching point pairs; Match the pixel coordinates in the second pixel coordinate set and the fourth pixel coordinate set to obtain the second set of matching point pairs; Align the thermal imaging video image and the cropped visible light video image according to the first set of matching point pairs and the second set of matching point pairs; Structural similarity calculation is used to extract structural similarity features between aligned thermal imaging video images and cropped visible light video images; Based on the structural similarity features of the thermal imaging video image and the cropped visible light video image, an image fusion algorithm is used to fuse the features of the thermal imaging video image and the cropped visible light video image to obtain a fused image as the target image.

5. The video optical river surface velocity measurement method according to claim 4, characterized in that, The formula for calculating structural similarity is: Where x is a local window image of the thermal imaging video image, y is a local window image of the cropped visible light video image, and μ x and μ y Let σ be the mean local brightness of x and y, respectively. x and σ y The local contrast standard deviations for x and y are σ and y, respectively. xy Let C1 and C2 be the local covariances of x and y, and C1 and C2 be preset parameters related to the dynamic range L of the image, where C1 = (0.01 × L). 2 C2 = (0.03 × L) 2 .

6. The video optical river surface velocity measurement method according to claim 4, characterized in that, The image fusion algorithm is either the Poisson fusion algorithm or the pyramid fusion algorithm.

7. The video optical river surface velocity measurement method according to claim 1, characterized in that, Visible light image capture requires that the light intensity be greater than the light intensity threshold.

8. A video optical river surface velocity measuring device, characterized in that, The video optical river surface velocity measuring device applies the video optical river surface velocity measuring method according to any one of claims 1-7, and the video optical river surface velocity measuring device includes a binocular camera device, an image processing device, and an edge computing device connected in sequence. The binocular camera device is used to simultaneously acquire visible light video images and thermal imaging video images of the river section to be measured; The image processing device is used to superimpose a thermal imaging video image with a preset transparency onto the visible light video image when the illumination conditions at the time of acquiring the visible light video image meet the requirements for capturing a visible light image, thereby obtaining a superimposed image as the target image; when the illumination conditions at the time of acquiring the visible light video image do not meet the requirements for capturing a visible light image, the visible light video image and the thermal imaging video image are feature-fused to obtain a fused image as the target image. The edge computing device is used to calculate the surface velocity of the river section to be measured based on the target image.

9. A local edge computing computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the video optical river surface velocity measurement method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the video optical river surface velocity measurement method according to any one of claims 1-7.

Images