Video-based flow measurement method and intelligent flow measurement system

Abstract

The invention relates to a video-based flow measurement method and an intelligent flow measurement system. The method comprises the following steps: extracting a flow velocity analysis reference image from a recorded video; establishing an analysis point on the first flow velocity analysis reference image of the time sequence; determining a change vector of each analysis point according to other flow velocity analysis reference images of the time sequence; selecting an analysis area on the first flow velocity analysis reference image of the time sequence according to the length and the direction concentration ratio of the change vector; extracting an analysis image from the flow velocity analysis reference image corresponding to the analysis area, and performing feature extraction on the analysis image to obtain a flow velocity feature; and calculating the average moving speed of the flow velocity characteristics to obtain the flow measurement speed. According to the video-based flow measurement method and the intelligent flow measurement system disclosed by the invention, the grabbing area is determined based on local feature analysis, feature grabbing is performed in the grabbing area, and then the flow velocity is measured based on the grabbed features, so that the relatively accurate water flow velocity can be obtained.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a video-based flow measurement method and an intelligent flow measurement system. Background Art

[0002] Flow velocity measurement is one of the important tasks in hydrological monitoring. Currently, there are two commonly used methods: manual detection and instrument detection. Manual detection mainly relies on hydrologists. For example, experienced hydrologists can even estimate the flow velocity of the river more accurately. However, this method can only be used for estimation. A more accurate method still needs to rely on the placement of target objects.

[0003] Instrument detection methods include flow meter measurement and acoustic detection. These methods are mainly used for measuring ships, and have the problems of large equipment and manpower investment and high cost. At the same time, the measurement range is limited and is not suitable for river flow measurement scenarios over a large range.

[0004] A newer method uses machine vision to perform analysis, which can capture water features and then analyze them to obtain the water flow velocity. With the maturity of high-precision digital cameras, drones and related algorithms, this method has begun to have obvious advantages in measurement coverage and measurement costs.

[0005] However, for river velocity measurement scenarios where some surface features are relatively lacking, machine vision methods have the problem of difficulty in capturing features. Summary of the invention

[0006] The present application provides a video-based flow measurement method and an intelligent flow measurement system, which determine a capture area based on local feature analysis and perform feature capture within the capture area, and then measure the flow velocity based on the captured features, thereby obtaining a relatively accurate water flow velocity.

[0007] The above-mentioned purpose of the present application is achieved through the following technical solutions:

[0008] In a first aspect, the present application provides a video-based flow measurement method, comprising:

[0009] Extracting a flow velocity analysis reference image from the recorded video, the number of the flow velocity analysis reference images is multiple, and the multiple flow velocity analysis reference images are distributed at intervals in a time series;

[0010] Establish analysis points on the first velocity analysis reference image of the time series, and the analysis points are distributed in the form of an MxN matrix, where M and N are both natural numbers greater than zero;

[0011] Determine the change vector of each analysis point based on other flow velocity analysis reference images of the time series;

[0012] An analysis area is selected on the first velocity analysis reference image of the time series according to the length and directional concentration of the change vector;

[0013] Extracting an analysis image on a velocity analysis reference image corresponding to the analysis area and performing feature extraction on the analysis image to obtain a velocity feature;

[0014] Calculate the average moving speed of the flow velocity characteristics and obtain the measured flow velocity.

[0015] In a possible implementation manner of the first aspect, determining the change vector of each analysis point according to other flow velocity analysis reference images of the time series includes:

[0016] Creating a change region based on the analysis point, where the analysis point is located at the center of the change region;

[0017] Obtaining a local flow velocity analysis reference image corresponding to the changed area, wherein the number of the local flow velocity analysis reference images is multiple;

[0018] Use the same extraction interval to extract all local velocity analysis reference images to obtain local change features;

[0019] The local change features are matched and the change vector of the corresponding analysis point is determined according to the movement of the local change features.

[0020] In a possible implementation manner of the first aspect, matching the local change features includes:

[0021] The local change features are converted into points and line segments for representation. Points have area features, and line segments have length features.

[0022] Use the obtained points and line segments to construct a feature grid;

[0023] Different feature grids are matched to determine the movement of the feature grids, where the movement of the feature grids includes direction and movement speed.

[0024] In a possible implementation manner of the first aspect, when the local change feature cannot be obtained, a new extraction interval is replaced.

[0025] In a possible implementation manner of the first aspect, after obtaining the feature grid, the method further includes calculating the sparsity of the feature grid and adjusting the starting point and / or the ending point of the extraction interval according to the sparsity of the feature grid.

[0026] In a possible implementation manner of the first aspect, adjusting the starting point and / or the ending point of the extraction interval according to the sparsity of the feature grid includes:

[0027] Calculate the individual area and area mean of each grid in the feature grid;

[0028] The dispersion of the individual area is calculated based on the individual area and the area mean of each grid;

[0029] Adjust the starting point and the end point of the extraction interval according to the discreteness so that the discreteness is within the set interval;

[0030] When adjusting the starting point and / or the end point of the extraction interval fails to make the discreteness fall within the set interval, a new extraction interval is replaced.

[0031] In a possible implementation manner of the first aspect, extracting an analysis image on a flow velocity analysis reference image corresponding to the analysis area and performing feature extraction on the analysis image to obtain the flow velocity feature includes:

[0032] The analysis image is extracted using the same extraction interval to obtain local change features;

[0033] The local change features are converted into points and line segments for representation. Points have area features, and line segments have length features.

[0034] Use the obtained points and line segments to construct a feature grid;

[0035] Use the feature grid as a velocity feature.

[0036] In a second aspect, the present application provides a video-based flow measurement device, comprising:

[0037] An image extraction unit is used to extract a flow velocity analysis reference image from the recorded video, wherein the number of the flow velocity analysis reference images is multiple, and the multiple flow velocity analysis reference images are distributed at intervals in a time series;

[0038] An image processing unit, used for establishing analysis points on the first velocity analysis reference image of the time series, wherein the analysis points are distributed in the form of an MxN matrix, where M and N are both natural numbers greater than zero;

[0039] a change vector processing unit, for determining a change vector of each analysis point according to other flow velocity analysis reference images of the time series;

[0040] An analysis region processing unit, used for selecting an analysis region on the first flow velocity analysis reference image of the time series according to the length and directional concentration of the change vector;

[0041] A feature extraction unit is used to extract an analysis image on a flow velocity analysis reference image corresponding to the analysis area and perform feature extraction on the analysis image to obtain a flow velocity feature;

[0042] The result calculation unit is used to calculate the average moving speed of the flow velocity characteristics to obtain the measured flow velocity.

[0043] In a third aspect, the present application provides an intelligent flow measurement system, the system comprising:

[0044] one or more memories for storing instructions; and

[0045] One or more processors, used to call and run the instructions from the memory to execute the method as described in the first aspect and any possible implementation of the first aspect.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium comprising:

[0047] Program, when the program is executed by a processor, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0048] In a fifth aspect, the present application provides a computer program product, comprising program instructions. When the program instructions are executed by a computing device, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0049] In a sixth aspect, the present application provides a chip system, which includes a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0050] The chip system may be composed of chips, or may include chips and other discrete devices.

[0051] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic flowchart of the steps of a flow measurement method provided in this application.

[0053] Figure 2 This is a schematic diagram of obtaining a flow velocity analysis reference image provided by the present application.

[0054] Figure 3 It is a schematic diagram of establishing an analysis point provided by this application.

[0055] Figure 4 It is a schematic diagram of a change vector belonging to an analysis point provided by the present application.

[0056] Figure 5It is a schematic diagram of the locations of analysis points and change areas provided by this application.

[0057] Figure 6 It is a schematic diagram of a characteristic grid provided in this application.

[0058] Figure 7 This is a schematic diagram of the principle of obtaining a motion vector provided by the present application. DETAILED DESCRIPTION

[0059] The technical solution in this application is further described in detail below in conjunction with the accompanying drawings.

[0060] This application discloses a video-based flow measurement method, please refer to Figure 1 In some examples, the video-based flow measurement method disclosed in the present application includes the following steps:

[0061] S101, extracting a flow velocity analysis reference image from a recorded video, wherein the number of the flow velocity analysis reference images is multiple, and the multiple flow velocity analysis reference images are distributed at intervals in a time series;

[0062] S102, establishing analysis points on the first velocity analysis reference image of the time series, the analysis points being distributed in the form of an MxN matrix, where M and N are both natural numbers greater than zero;

[0063] S103, determining a change vector of each analysis point according to other flow velocity analysis reference images of the time series;

[0064] S104, selecting an analysis area on the first velocity analysis reference image of the time series according to the length and direction concentration of the change vector;

[0065] S105, extracting an analysis image from the flow velocity analysis reference image corresponding to the analysis area and performing feature extraction on the analysis image to obtain flow velocity features;

[0066] S106, calculating the average moving speed of the flow velocity characteristics to obtain the measured flow velocity.

[0067] In step S101, flow velocity analysis reference images are first extracted from the recorded video. The number of flow velocity analysis reference images is multiple and these flow velocity analysis reference images are spaced apart in a time series. The flow velocity analysis reference images are generated by an image acquisition device carried by a drone or by an image acquisition device deployed at a fixed position.

[0068] See also Figure 2 ,The reference images for flow velocity analysis are distributed at intervals in the time series, and the interval time can be fixed or not fixed, which is not limited here.

[0069] In step S102, analysis points are established on the first velocity analysis reference image in the time series. The analysis points are distributed in the form of an MxN matrix, where M and N are both natural numbers greater than zero, such as Figure 3 As shown, the function of the analysis point is to determine the flow direction at the location of the analysis point.

[0070] In step S103, the change vector of each analysis point is determined based on other velocity analysis reference images in the time series, where the change vector includes two reference dimensions: direction and length. Then, in step S104, an analysis region is selected on the first velocity analysis reference image in the time series based on the length and direction concentration of the change vector, where the number of analysis regions obtained can be one or more.

[0071] The criterion for selecting the analysis area is that the analysis points in the analysis area are traceable, and the change vector corresponding to the analysis area can maintain consistency in direction. Here, the direction error is generally controlled within 10°. Of course, the direction error can also be adjusted according to the actual detection accuracy.

[0072] For example, Figure 4 In the analysis, the analysis points in the dotted area need to be discarded.

[0073] In step S105, an analysis image is extracted from the velocity analysis reference image corresponding to the analysis area and features are extracted from the analysis image to obtain velocity features. The velocity features here refer to solids that are below the water surface and in a flowing state.

[0074] Finally, in step S106, the average moving speed of the flow velocity feature is calculated to obtain the measured flow velocity. The purpose of calculating the average moving speed of the flow velocity feature is to make the calculation result more accurate.

[0075] In some examples, the specific manner of determining the change vector of each analysis point based on other flow velocity analysis reference images of the time series is as follows:

[0076] S201, creating a change region based on an analysis point, where the analysis point is located at the center of the change region;

[0077] S202, obtaining a local flow velocity analysis reference image corresponding to the changed area, wherein the number of the local flow velocity analysis reference images is multiple;

[0078] S203, extracting all local velocity analysis reference images using the same extraction interval to obtain local change features;

[0079] S204, matching the local change features and determining the change vector of the corresponding analysis point according to the movement of the local change features.

[0080] In step S201 to step S204, a change region is first created based on the analysis point, and the analysis point is located at the center of the change region, such as Figure 5 Then, a local flow velocity analysis reference image corresponding to the change region is obtained, and the number of the local flow velocity analysis reference images is multiple.

[0081] The local flow velocity analysis reference image is obtained by cropping the flow velocity analysis reference image. The basis for cropping is the size of the changing area. Combined with the content mentioned above, each flow velocity analysis reference image in the time series needs to be cropped using the changing area to obtain the local flow velocity analysis reference image.

[0082] After obtaining the local flow velocity analysis reference image, all local flow velocity analysis reference images are extracted using the same extraction interval to obtain local change features. The extraction interval is a numerical range, for example, 34-68 is used as the extraction interval.

[0083] At this time, some content can be extracted from the local flow velocity analysis reference image. These contents are part of the local flow velocity analysis reference image, but not all. The purpose of using the extraction interval is to reduce the difficulty of subsequent matching, because the local change features obtained at this time have a certain degree of recognition.

[0084] For the local change features obtained, it is necessary to make a judgment, the specific method is as follows:

[0085] Quantity judgment: count the number of local change features. The counted number must be greater than or equal to the set number. The value range of the set number is generally 5-8.

[0086] Distance judgment: Count the distances between adjacent local change features, and then calculate the average of the obtained distances. The obtained distance average needs to be greater than or equal to the set distance, which is generally 10-15 pixels.

[0087] For coverage area judgment, the ratio of the area enclosed by the local change features to the area of ​​the local flow velocity analysis reference image generally needs to be greater than or equal to 5%.

[0088] When the above conditions cannot be met, the extraction interval needs to be adjusted, specifically by replacing a new extraction interval or using multiple extraction intervals to extract content.

[0089] In some possible implementations, when the local change feature cannot be obtained, a new extraction interval is replaced.

[0090] The specific method of matching local change features is as follows:

[0091] S301, converting the local change features into points and line segments for representation, where the points have area features and the line segments have length features;

[0092] S302, constructing a feature grid using the obtained points and line segments;

[0093] S303, matching different feature grids to determine the movement of the feature grids, where the movement of the feature grids includes direction and movement speed.

[0094] In step S301 to step 303, the local variation features are converted into feature grids, such as Figure 6 As shown, the specific method is to convert the local change features into points and line segments for representation, where the points have area features and the line segments have length features.

[0095] The specific method of converting local change features into points and line segments for representation is determined based on the area and length of the local features. The length here has a reference value. Local change features that are smaller than the length reference value are represented by points and areas, otherwise they are represented by line segments and lengths.

[0096] Then, the obtained points and line segments are used to construct a feature grid. The specific construction method is to connect the points and line segments in a certain way. For the construction of multiple feature grids at the same analysis point, the same connection method needs to be used.

[0097] In some possible implementations, after obtaining the feature grid, the sparsity of the feature grid is calculated, and the specific method is as follows:

[0098] S401, calculating the individual area and area mean of each grid in the feature grid;

[0099] S402, calculating the discreteness of the individual area according to the individual area and the area mean of each grid;

[0100] S403, adjusting the starting point and the end point of the extraction interval according to the discreteness, so that the discreteness is within the set interval;

[0101] When adjusting the starting point and / or the end point of the extraction interval fails to make the discreteness fall within the set interval, a new extraction interval is replaced.

[0102] The sparsity of the feature grid refers to the average area value of the grids in the feature grid. The average area value is calculated as the ratio of the total area of ​​the feature grid to the total number of grids, and the ratio is obtained by calculation.

[0103] Then calculate the ratio of the number of grids smaller than this ratio to the total number of grids. This ratio generally needs to be less than 0.2-0.25, that is, the number of small-area grids in the feature grid needs to be controlled within a small range. Too many small-area grids in the feature grid will increase the difficulty of matching the feature grid later.

[0104] When the sparsity of the feature grid does not meet the requirements, the starting point and / or end point of the extraction interval is adjusted according to the sparsity of the feature grid, which will cause some local change features to disappear and / or new local change features to be added. The process stops until the sparsity of the feature grid meets the requirements.

[0105] In some examples, the specific method of extracting an analysis image from a flow velocity analysis reference image corresponding to the analysis area and performing feature extraction on the analysis image to obtain the flow velocity feature is:

[0106] S501, extracting the analysis image using the same extraction interval to obtain local change features;

[0107] S502, converting the local change features into points and line segments for representation, where the points have area features and the line segments have length features;

[0108] S503, constructing a feature grid using the obtained points and line segments;

[0109] S504, taking the characteristic grid as a flow velocity feature.

[0110] The contents in step S501 to step S504 are the same as the method of obtaining the feature grid described in the above content, and will not be repeated here.

[0111] After obtaining the flow velocity features, the flow velocity features need to be matched. The matching method is to calculate the similarity of the two feature grids. When the two feature grids are matched successfully, the moving speed of the feature grid is calculated. The moving speed has two dimensions: value and direction.

[0112] The matching method of two feature grids is to place the two feature grids obtained in the same coordinate system, and then determine whether the corresponding points and line segments can overlap. This process involves movement, which is represented by a movement vector. The movement vector has two modes of movement and rotation.

[0113] Whether two corresponding points coincide is determined by calculating the distance between the two points, which must be less than or equal to a set value. Whether two corresponding line segments coincide is determined by calculating the average of the distances between the two ends of the two line segments, which must be less than or equal to another set value.

[0114] In the above process, one of the feature grids needs to be moved and rotated.

[0115] After the match is successful, the movement vector is used as the moving speed of the feature grid. After all the feature grids are matched, multiple movement vectors will be obtained, such as Figure 7 As shown, at this time, the matching number of the feature grids is required to be greater than or equal to a set value or a set ratio.

[0116] At this point, multiple moving vectors are obtained. Now it is necessary to calculate the average moving speed of the flow velocity characteristics to obtain the measured flow velocity. The specific method is to merge the moving vectors recorded in the above content to obtain a synthetic vector, and then use the length value of the synthetic vector as the measured flow velocity.

[0117] The present application also provides a video-based flow measurement device, comprising:

[0118] An image extraction unit is used to extract a flow velocity analysis reference image from the recorded video, wherein the number of the flow velocity analysis reference images is multiple, and the multiple flow velocity analysis reference images are distributed at intervals in a time series;

[0119] An image processing unit, used for establishing analysis points on the first velocity analysis reference image of the time series, wherein the analysis points are distributed in the form of an MxN matrix, where M and N are both natural numbers greater than zero;

[0120] a change vector processing unit, for determining a change vector of each analysis point according to other flow velocity analysis reference images of the time series;

[0121] An analysis region processing unit, used for selecting an analysis region on the first flow velocity analysis reference image of the time series according to the length and directional concentration of the change vector;

[0122] A feature extraction unit is used to extract an analysis image on a flow velocity analysis reference image corresponding to the analysis area and perform feature extraction on the analysis image to obtain a flow velocity feature;

[0123] The result calculation unit is used to calculate the average moving speed of the flow velocity characteristics to obtain the measured flow velocity.

[0124] Further, determining the change vector of each analysis point according to other flow velocity analysis reference images of the time series includes:

[0125] Creating a change region based on the analysis point, where the analysis point is located at the center of the change region;

[0126] Obtaining a local flow velocity analysis reference image corresponding to the changed area, wherein the number of the local flow velocity analysis reference images is multiple;

[0127] Use the same extraction interval to extract all local velocity analysis reference images to obtain local change features;

[0128] The local change features are matched and the change vector of the corresponding analysis point is determined according to the movement of the local change features.

[0129] Furthermore, matching the local change features includes:

[0130] The local change features are converted into points and line segments for representation. Points have area features, and line segments have length features.

[0131] Use the obtained points and line segments to construct a feature grid;

[0132] Different feature grids are matched to determine the movement of the feature grids, where the movement of the feature grids includes direction and movement speed.

[0133] Furthermore, when the local change feature cannot be obtained, a new extraction interval is replaced.

[0134] Furthermore, after obtaining the feature grid, the method further includes calculating the sparsity of the feature grid and adjusting the starting point and / or the ending point of the extraction interval according to the sparsity of the feature grid.

[0135] Further, adjusting the starting point and / or the end point of the extraction interval according to the sparsity of the feature grid includes:

[0136] Calculate the individual area and area mean of each grid in the feature grid;

[0137] The dispersion of the individual area is calculated based on the individual area and the area mean of each grid;

[0138] Adjust the starting point and the end point of the extraction interval according to the discreteness so that the discreteness is within the set interval;

[0139] When adjusting the starting point and / or the end point of the extraction interval fails to make the discreteness fall within the set interval, a new extraction interval is replaced.

[0140] Furthermore, an analysis image is extracted from the velocity analysis reference image corresponding to the analysis area and features are extracted from the analysis image to obtain velocity features including:

[0141] The analysis image is extracted using the same extraction interval to obtain local change features;

[0142] The local change features are converted into points and line segments for representation. Points have area features, and line segments have length features.

[0143] Use the obtained points and line segments to construct a feature grid;

[0144] Use the feature grid as a velocity feature.

[0145] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0146] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0147] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in this application are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.

[0148] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0149] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0150] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0151] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0152] It should also be understood that in various embodiments of the present application, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present application.

[0153] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0154] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a computer-readable storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0155] The present application also provides an intelligent flow measurement system, the system comprising:

[0156] one or more memories for storing instructions; and

[0157] One or more processors are used to call and run the instructions from the memory to execute the method as described above.

[0158] The present application also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device and the network device perform operations of the terminal device and the network device corresponding to the above method.

[0159] The present application also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0160] The chip system may be composed of chips, or may include chips and other discrete devices.

[0161] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.

[0162] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0163] Optionally, the computer instructions are stored in a memory.

[0164] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0165] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0166] The non-volatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.

[0167] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus RAM.

[0168] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A video-based flow measurement method, characterized in that: include: Extracting a flow velocity analysis reference image from the recorded video, the number of the flow velocity analysis reference images is multiple, and the multiple flow velocity analysis reference images are distributed at intervals in a time series; Establish analysis points on the first velocity analysis reference image of the time series, and the analysis points are distributed in the form of an MxN matrix, where M and N are both natural numbers greater than zero; Determine the change vector of each analysis point based on other flow velocity analysis reference images of the time series; An analysis area is selected on the first velocity analysis reference image of the time series according to the length and directional concentration of the change vector; Extracting an analysis image on a velocity analysis reference image corresponding to the analysis area and performing feature extraction on the analysis image to obtain a velocity feature; Calculate the average moving speed of the flow velocity characteristics and obtain the measured flow velocity.

2. The video-based flow measurement method according to claim 1, characterized in that: Determining the change vector of each analysis point based on other flow velocity analysis reference images of the time series includes: Creating a change region based on the analysis point, where the analysis point is located at the center of the change region; Obtaining a local flow velocity analysis reference image corresponding to the changed area, wherein the number of the local flow velocity analysis reference images is multiple; Use the same extraction interval to extract all local velocity analysis reference images to obtain local change features; The local change features are matched and the change vector of the corresponding analysis point is determined according to the movement of the local change features.

3. The video-based flow measurement method according to claim 2, characterized in that: Matching local change features includes: The local change features are converted into points and line segments for representation. Points have area features, and line segments have length features. Use the obtained points and line segments to construct a feature grid; Different feature grids are matched to determine the movement of the feature grids, where the movement of the feature grids includes direction and movement speed.

4. The video-based flow measurement method according to claim 2 or 3, characterized in that: When the local change characteristics cannot be obtained, a new extraction interval is replaced.

5. The video-based flow measurement method according to claim 3, characterized in that: After the feature grid is obtained, the method further includes calculating the sparsity of the feature grid and adjusting the starting point and / or the end point of the extraction interval according to the sparsity of the feature grid.

6. The video-based flow measurement method according to claim 5, characterized in that: Adjusting the starting point and / or the end point of the extraction interval according to the sparsity of the feature grid includes: Calculate the individual area and area mean of each grid in the feature grid; The dispersion of the individual area is calculated based on the individual area and the area mean of each grid; Adjust the starting point and the end point of the extraction interval according to the discreteness so that the discreteness is within the set interval; When adjusting the starting point and / or the end point of the extraction interval fails to make the discreteness fall within the set interval, a new extraction interval is replaced.

7. The video-based flow measurement method according to claim 1, characterized in that: Extract the analysis image on the velocity analysis reference image corresponding to the analysis area and perform feature extraction on the analysis image to obtain the velocity features including: The analysis image is extracted using the same extraction interval to obtain local change features; The local change features are converted into points and line segments for representation. Points have area features, and line segments have length features. Use the obtained points and line segments to construct a feature grid; Use the feature grid as a velocity feature.

8. A video-based flow measurement device, characterized in that: include: An image extraction unit is used to extract a flow velocity analysis reference image from the recorded video, wherein the number of the flow velocity analysis reference images is multiple, and the multiple flow velocity analysis reference images are distributed at intervals in a time series; An image processing unit, used for establishing analysis points on the first velocity analysis reference image of the time series, wherein the analysis points are distributed in the form of an MxN matrix, where M and N are both natural numbers greater than zero; a change vector processing unit, for determining a change vector of each analysis point according to other flow velocity analysis reference images of the time series; An analysis region processing unit, used for selecting an analysis region on the first flow velocity analysis reference image of the time series according to the length and directional concentration of the change vector; A feature extraction unit is used to extract an analysis image on a flow velocity analysis reference image corresponding to the analysis area and perform feature extraction on the analysis image to obtain a flow velocity feature; The result calculation unit is used to calculate the average moving speed of the flow velocity characteristics to obtain the measured flow velocity.

9. An intelligent flow measurement system, characterized in that: The system comprises: one or more memories for storing instructions; and One or more processors, configured to call and execute the instructions from the memory to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the method according to any one of claims 1 to 7 is executed.

Images