Smoke dynamic recognition method and related devices

Abstract

The embodiment of the present application provides a dynamic smoke recognition method and related devices, the method comprising: obtaining a target image of a to-be-detected area by a grayscale eigenvalue method; performing feature extraction on the target image to obtain feature data of the target image; performing data modeling operations based on the feature data to determine smoke status information of the to-be-detected area; determining smoke motion parameters based on feature data comparison of the target image; determining a first smoke type based on the smoke status information and the smoke motion parameters, which can improve the accuracy of smoke type discrimination.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a smoke dynamic identification method and related devices. Background Art

[0002] With the continuous acceleration of industrial development, it has caused a great burden on the environment. People pay more and more attention to environmental protection, such as identifying smoke in the environment and judging whether it is industrial smoke. If it is industrial smoke, it needs to be processed accordingly. In the existing scheme, when distinguishing smoke, a simple image processing method is usually used, for example, taking a smoke image and judging the type of smoke by judging the size of the smoke, etc., resulting in low accuracy in smoke type judgment. Summary of the invention

[0003] The embodiments of the present application provide a smoke dynamic recognition method and related devices, which can improve the accuracy of smoke type identification.

[0004] A first aspect of an embodiment of the present application provides a method for dynamic smoke recognition, the method comprising:

[0005] Acquire the target image of the area to be detected by using the grayscale eigenvalue method;

[0006] Extracting features from the target image to obtain feature data of the target image;

[0007] Performing data modeling operations according to the characteristic data to determine smoke status information of the area to be detected;

[0008] Determine smoke motion parameters by comparing the characteristic data of the target image;

[0009] A first smoke type is determined according to the smoke state information and the smoke motion parameter.

[0010] In combination with the first aspect, in a possible implementation manner, the characteristic data includes a grayscale value, and performing a data modeling operation according to the characteristic data to determine the smoke state information of the area to be detected includes:

[0011] Determining the smoke content in the area to be detected according to the grayscale value;

[0012] The smoke state information is determined according to the smoke content.

[0013] In combination with the first aspect, in a possible implementation manner, comparing the feature data of the target image to determine the smoke motion parameter includes:

[0014] Acquire a smoke contour of a smoke area in the feature data in the target image;

[0015] The smoke motion parameter is determined according to the change of the smoke contour.

[0016] In combination with the first aspect, in a possible implementation manner, determining the smoke motion parameter according to the smoke contour includes:

[0017] Obtaining M contour protrusion areas of the smoke contour;

[0018] Determining the smoke diffusion direction of each of the M protruding contour areas according to the M protruding contour areas;

[0019] Obtaining position information of the M contour protrusion areas in the smoke contour;

[0020] Determine a first reference smoke movement speed of the smoke in each of the M contour protrusion areas according to the position information and the smoke generation point;

[0021] Determining a second reference smoke movement speed of smoke in each of the M contour protruding areas according to contour shapes of the M contour protruding areas;

[0022] Determining a target smoke movement speed of the smoke in each of the M contour convex areas according to a first reference smoke movement speed of the smoke in each of the M contour convex areas and a second reference smoke movement speed of the smoke in each of the M contour convex areas;

[0023] The smoke diffusion direction of each of the M contour convex areas and the target smoke movement speed of the smoke in each of the M contour convex areas are determined as the smoke movement parameters.

[0024] In combination with the first aspect, in a possible implementation manner, the method further includes:

[0025] Acquiring morphological parameters of the wind force marker in the target image;

[0026] Determining wind parameters of the area to be detected according to the morphological parameters;

[0027] Determining environmental information of the area to be detected according to the target image;

[0028] Determining first type correction information according to the wind force parameter and the environmental information;

[0029] Acquiring the light intensity of the area to be detected;

[0030] Determining second type correction information according to the light intensity;

[0031] determining target correction information according to the first type of correction information and the second type of correction information;

[0032] The first smoke type is corrected according to the target correction information to obtain a second smoke type.

[0033] A second aspect of an embodiment of the present application provides a smoke dynamic recognition device, the device comprising:

[0034] An acquisition unit, used for acquiring a target image of the area to be detected;

[0035] An extraction unit, used for performing feature extraction on the target image to obtain feature data of the target image;

[0036] A first determining unit, used to determine the smoke state information of the area to be detected according to the characteristic data;

[0037] A second determining unit, configured to determine smoke motion parameters according to the target image;

[0038] The third determining unit is configured to determine a first smoke type according to the smoke state information and the smoke motion parameter.

[0039] In conjunction with the second aspect, in a possible implementation manner, the feature data includes a grayscale value, and the first determining unit is configured to:

[0040] Determining the smoke content in the area to be detected according to the grayscale value;

[0041] The smoke state information is determined according to the smoke content.

[0042] In conjunction with the second aspect, in a possible implementation manner, the second determining unit is configured to:

[0043] Acquire a smoke contour of a smoke area in the feature data in the target image;

[0044] The smoke motion parameter is determined according to the change of the smoke contour.

[0045] In conjunction with the second aspect, in a possible implementation manner, in determining the smoke motion parameter according to the smoke contour, the second determining unit is configured to:

[0046] Obtaining M contour protrusion areas of the smoke contour;

[0047] Determining the smoke diffusion direction of each of the M protruding contour areas according to the M protruding contour areas;

[0048] Obtaining position information of the M contour protrusion areas in the smoke contour;

[0049] Determine a first reference smoke movement speed of the smoke in each of the M contour protrusion areas according to the position information and the smoke generation point;

[0050] Determining a second reference smoke movement speed of smoke in each of the M contour protruding areas according to contour shapes of the M contour protruding areas;

[0051] Determining a target smoke movement speed of the smoke in each of the M contour convex areas according to a first reference smoke movement speed of the smoke in each of the M contour convex areas and a second reference smoke movement speed of the smoke in each of the M contour convex areas;

[0052] The smoke diffusion direction of each of the M contour convex areas and the target smoke movement speed of the smoke in each of the M contour convex areas are determined as the smoke movement parameters.

[0053] In conjunction with the second aspect, in a possible implementation manner, the device is further used for:

[0054] Acquiring morphological parameters of the wind force marker in the target image;

[0055] Determining wind parameters of the area to be detected according to the morphological parameters;

[0056] Determining environmental information of the area to be detected according to the target image;

[0057] Determining first type correction information according to the wind force parameter and the environmental information;

[0058] Acquiring the light intensity of the area to be detected;

[0059] Determining second type correction information according to the light intensity;

[0060] determining target correction information according to the first type of correction information and the second type of correction information;

[0061] The first smoke type is corrected according to the target correction information to obtain a second smoke type.

[0062] A third aspect of an embodiment of the present application provides a terminal, comprising a processor, an input device, an output device and a memory, wherein the processor, input device, output device and memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the step instructions in the first aspect of the embodiment of the present application.

[0063] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiments of the present application.

[0064] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

[0065] Implementing the embodiments of the present application has at least the following beneficial effects:

[0066] By acquiring a target image of an area to be detected and performing feature extraction on the target image to obtain feature data of the target image, smoke state information of the area to be detected is determined based on the feature data, smoke motion parameters are determined based on the target image, and a first smoke type is determined based on the smoke state information and the smoke motion parameters. Therefore, smoke state information can be acquired based on the feature data extracted from the feature, and the first smoke type can be determined based on the smoke state information and the smoke motion parameters, thereby improving the accuracy of determining the smoke type. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0068] Figure 1 A flow chart of a method for dynamic smoke recognition is provided for an embodiment of the present application;

[0069] Figure 2 A flow chart of another method for dynamic smoke recognition is provided for the embodiment of the present application;

[0070] Figure 3A schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0071] Figure 4 A structural schematic diagram of a smoke dynamic recognition device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0073] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0074] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0075] In order to better understand a method for dynamic smoke recognition provided by an embodiment of the present application, the following first briefly introduces the scenario in which the method for dynamic smoke recognition is applied. The method for dynamic smoke recognition can be applied to electronic devices, which can be computers, tablet computers, mobile phones, etc. In industrial production environments, it is necessary to identify smoke in the environment. For example, in a factory, smoke needs to be detected and identified. For another example, in the exhaust gas emission of a factory, smoke needs to be detected and identified to determine the type of smoke and perform corresponding processing. Specifically, the electronic device obtains a target image of the area to be detected through a camera, an industrial camera, etc., and the electronic device extracts features of the target image to obtain feature data of the target image. The feature data can be, for example, a grayscale value, etc. The electronic device determines the smoke state information of the area to be detected based on the feature data, the electronic device determines the smoke motion parameters based on the target image, and the electronic device determines the first smoke type based on the smoke state information and the smoke motion parameters. Therefore, the smoke state information can be obtained based on the feature data extracted by the feature, and the first smoke type is determined based on the smoke state information and the smoke motion parameters, thereby improving the accuracy of smoke type determination.

[0076] See also Figure 1 , Figure 1 The present invention provides a flow chart of a method for dynamic smoke recognition. Figure 1 As shown, the method is applied to an electronic device, and the method includes:

[0077] 101. Obtain the target image of the area to be detected by using the grayscale eigenvalue method.

[0078] When acquiring the target image, it can be acquired through an industrial camera. The industrial camera can specifically be: a 6-pin Hirose connector provides power and I / O, including 1 optical isolation input, 1 optical isolation output, and 1 bidirectional configurable non-isolated I / O. The industrial camera can output grayscale images, thereby improving image acquisition efficiency and reducing data processing pressure on the industrial control host. The grayscale feature value method can be to segment the grayscale features of the acquired image to obtain the target image.

[0079] In the area to be detected, the industrial camera can be fixed on a mobile vehicle, an aircraft or a fixed building. K industrial cameras can be used to collect images of the area to be detected, and the images collected by the K industrial cameras can be used as target images to detect the type of smoke. K industrial cameras and the industrial control host can realize automatic cross-detection without interfering with each other. Of course, one industrial camera can also be used to collect images to obtain the target image, so as to detect the type of smoke.

[0080] 102. Perform feature extraction on the target image to obtain feature data of the target image.

[0081] When extracting features from a target image, the target image may be processed to obtain a processed image, and features may be extracted from the processed image to obtain feature data.

[0082] The method for processing the target image may be: performing two optimization processes on the target image, specifically, the following may be performed:

[0083] First image optimization processing: perform target image processing shadow correction and image filtering to obtain the first reference image. For example, background segmentation and target capture are performed based on the characteristics of smoke in the metallurgical industry, which has irregular edge contours and a single tone with obvious grayscale differences from the surrounding environment.

[0084] Second image optimization processing:

[0085] The first reference image is enhanced and image normalized to obtain the second reference image. Specifically, the background of the first reference image is edge sharpened and grayscale deepened.

[0086] The second reference image is subjected to feature extraction to obtain feature data. The feature data may include grayscale values. Therefore, when the second reference image obtained after the target image is subjected to secondary processing is subjected to feature extraction, the accuracy of background segmentation and target capture can be effectively improved.

[0087] 103. Perform data modeling operations according to the characteristic data to determine smoke status information of the area to be detected.

[0088] When the characteristic data is a gray value, the smoke state information can be determined based on the smoke content determined by the gray value.

[0089] 104. Determine smoke motion parameters by comparing feature data of the target image.

[0090] The smoke in the target image may be subjected to contour detection, and the smoke motion parameters may be determined based on the detected smoke contour. The target image feature data comparison may be understood as comparing the feature data of the target image with the feature data of a preset image.

[0091] 105. Determine a first smoke type according to the smoke state information and the smoke motion parameter.

[0092] The first smoke type may be determined according to a preset mapping relationship between smoke state information, smoke motion parameters and smoke types. The mapping relationship may be set by historical data or empirical values, or may be obtained by training a network model.

[0093] In this example, a target image of the area to be detected is acquired, and feature extraction is performed on the target image to obtain feature data of the target image. The smoke state information of the area to be detected is determined based on the feature data. The smoke motion parameters are determined based on the target image. The first smoke type is determined based on the smoke state information and the smoke motion parameters. Therefore, the smoke state information can be acquired based on the feature data extracted from the feature, and the first smoke type can be determined based on the smoke state information and the smoke motion parameters, thereby improving the accuracy of determining the smoke type.

[0094] In a possible implementation, the characteristic data includes a grayscale value. A possible method for performing a data modeling operation based on the characteristic data to determine the smoke state information of the area to be detected includes:

[0095] A1. Determine the smoke content in the area to be detected according to the gray value;

[0096] A2. Determine the smoke status information according to the smoke content.

[0097] Among them, the smoke content in the area to be detected can be determined through the mapping relationship between the grayscale value and the smoke content. Specifically, the grayscale value statistics can be mapped to the actual smoke content through the smoke change law and related function mapping. For example, the pixel points with grayscale values ​​lower than or equal to the preset threshold are determined as smoke pixels, and the pixel points with grayscale values ​​higher than the preset threshold are determined as background pixels, etc.

[0098] The smoke state information can be determined again based on the mapping relationship between the smoke content and the smoke state information. The mapping relationship is set by empirical values ​​or historical data.

[0099] In this example, the smoke content is determined by the grayscale value, and the smoke state information is obtained according to the smoke content, thereby improving the accuracy and efficiency of determining the smoke state information.

[0100] In a possible implementation, a possible method for determining smoke motion parameters by comparing feature data of the target image includes:

[0101] B11, obtaining the smoke contour of the smoke area in the target image;

[0102] B12. Determine the smoke motion parameters according to the smoke contour.

[0103] The smoke contour can be determined according to the gray value or RGB value of the target image. Specifically, the smoke contour can be determined as the place where the gray value changes greatly. Of course, the smoke contour can also be determined by other methods, which are not specifically limited here.

[0104] When determining the smoke motion parameters, the smoke motion parameters may be determined according to the relevant parameters of the protruding area of ​​the smoke contour. The smoke motion parameters may include the smoke motion direction and motion speed.

[0105] In this example, by acquiring the smoke contour of the smoke area in the target image, the smoke motion parameters are determined according to the relevant parameters of the protruding area of ​​the smoke contour, so that the accuracy of the smoke motion parameter determination can be improved.

[0106] In a possible implementation, another possible method for determining smoke motion parameters by comparing the feature data of the target image includes:

[0107] B21, obtaining the smoke contour of the smoke area in the feature data in the target image;

[0108] B22. Determine the smoke motion parameters according to the change of the smoke contour

[0109] The method of obtaining the smoke contour of the smoke area in the feature data of the target image may refer to the method of step B11 in the aforementioned embodiment, which will not be described in detail here.

[0110] The change of the smoke profile can be characterized by the smoke movement direction and movement speed of the smoke profile, so that the movement parameters of the smoke can be determined according to the movement parameters of the smoke profile.

[0111] In a possible implementation, a possible method for determining the smoke motion parameter according to the smoke contour includes:

[0112] C1. Obtain M contour protrusion areas of the smoke contour;

[0113] C2. determining the smoke diffusion direction of each of the M protruding contour areas according to the M protruding contour areas;

[0114] C3, obtaining position information of the M contour protrusion areas in the smoke contour;

[0115] C4. determining a first reference smoke movement speed of the smoke in each of the M contour protruding areas according to the position information and the smoke generation point;

[0116] C5. determining a second reference smoke movement speed of smoke in each of the M contour protruding areas according to contour shapes of the M contour protruding areas;

[0117] C6. determining a target smoke movement speed of the smoke in each of the M contour convex areas according to a first reference smoke movement speed of the smoke in each of the M contour convex areas and a second reference smoke movement speed of the smoke in each of the M contour convex areas;

[0118] C7. The smoke diffusion direction of each of the M contour protruding areas and the target smoke movement speed of the smoke in each of the M contour protruding areas are determined as the smoke movement parameters.

[0119] M contour convex regions can be obtained according to the contour change of the smoke contour. For example, an arc-shaped region convex outward in the smoke contour is determined as a contour convex region. The outward is outside the region enclosed by the smoke contour.

[0120] The tangent of the vertex of the contour area can be determined, and the direction perpendicular to the tangent and outward can be determined as the smoke diffusion direction. Of course, the direction perpendicular to the tangent of all contour points in the contour protrusion area can also be determined as the smoke diffusion direction.

[0121] The position information of the protruding contour area can be understood as the position information of the vertex of the protruding contour area. Specifically, a coordinate system is established, and the vertex of the coordinate system is the point at the lower left corner of the target image. It can also be the position information of each contour point in the protruding contour area.

[0122] The smoke generation point is the point where smoke is generated, which can also be understood as the center point of the smoke generation area. The longer the distance between the position indicated by the position information and the smoke generation point, the smaller the first reference smoke movement speed; the shorter the distance between the position indicated by the position information and the smoke generation point, the larger the first reference smoke movement speed.

[0123] The sharper the contour shape of the contour protruding area, the greater the second reference smoke movement speed; the smoother the contour shape of the contour protruding area, the smaller the second reference smoke movement speed. The sharpness and smoothness of the contour shape can be understood as, the steeper the contour shape, the sharper it tends to be, and the flatter the contour shape, the smoother it tends to be. The closer the contour point is to the vertex of the contour protruding area, the smaller the second reference movement speed corresponding to the contour point is, and the farther the contour point is from the vertex of the contour protruding area, the smaller the second reference movement speed corresponding to the contour point is.

[0124] The average of the first reference smoke movement speed and the second reference smoke movement speed can be determined as the target smoke movement speed; the maximum value of the first reference smoke movement speed and the second reference smoke movement speed can be determined as the target smoke movement speed; the minimum value of the first reference smoke movement speed and the second reference smoke movement speed can be determined as the target smoke movement speed.

[0125] In this example, the diffusion direction of the smoke is determined by obtaining the protruding area of ​​the contour, and the target smoke movement speed is determined by the position information and shape of the protruding area of ​​the rectangular contour. The diffusion direction and target smoke movement speed are determined as smoke motion parameters, thereby improving the accuracy of determining the smoke motion parameters.

[0126] In a possible implementation, due to the influence of the environment on the smoke form, there may be a certain error in the smoke type determination, so the smoke type may be corrected, specifically including:

[0127] D1. Obtaining the morphological parameters of the wind force mark in the target image;

[0128] D2. determining the wind force parameters of the area to be detected according to the morphological parameters;

[0129] D3. Determine the environmental information of the area to be detected according to the target image;

[0130] D4. determining first type correction information according to the wind force parameter and the environmental information;

[0131] D5. Obtaining the light intensity of the area to be detected;

[0132] D6. Determine second type correction information according to the light intensity;

[0133] D7. determining target correction information according to the first type correction information and the second type correction information;

[0134] D8. Correct the first smoke type according to the target correction information to obtain a second smoke type.

[0135] Among them, the morphological parameters of the wind mark can be determined according to methods such as feature extraction, and the wind parameters of the area to be detected can be determined according to the mapping relationship between the morphological parameters and the wind parameters. Of course, the wind parameters can also be determined by other means, for example, by using a wind sensor, etc. The wind parameters may include the size of the wind, etc.

[0136] The information corresponding to the background image in the target image can be determined as the environmental information of the area to be detected. The target image can also be identified to determine the environmental information of the area to be detected. The environmental information may include the color of the environment, the weather conditions in the environment, etc.

[0137] When determining the first type of correction information, the greater the wind speed, the higher the correction strength of the correction information, and the smaller the wind speed, the lower the correction strength of the correction information; the greater the similarity between the color in the environmental information and the color of the smoke, the higher the correction strength of the correction information, and the smaller the similarity between the color in the environmental information and the color of the smoke, the lower the correction strength of the correction information; the worse the weather in the environmental information is, the higher the correction strength of the correction information, and the better the weather in the environmental information is, the lower the correction strength of the correction information.

[0138] The correction intensity can be understood as the correction amount when correcting the first smoke type. The greater the correction intensity, the greater the correction amount, and the smaller the correction intensity, the smaller the correction amount. The correction amount can represent the parameter by which the first smoke type is corrected to other smoke types. Bad weather can include various types of rain on rainy days, such as showers, light rain, heavy rain, heavy to torrential rain, etc. Good weather can include sunny days, etc.

[0139] The method for determining the second type of correction information according to the light intensity may be: determining an offset value between the light intensity and the light intensity of normal weather according to the light intensity, wherein the larger the offset value, the larger the correction amount of the second type of correction information, and the smaller the offset value, the smaller the correction amount of the second type of correction information. Normal weather may be understood as weather including a preset light intensity. The preset light intensity is set by an empirical value or historical data.

[0140] The average of the first type correction information and the second type correction information may be determined as the target correction information.

[0141] In this example, the first type of correction information is determined through wind parameters and environmental information, the second type of correction information is determined based on the light intensity, the target correction information is determined based on the first type of correction information and the second type of correction information, and the first smoke type is corrected based on the target correction information to obtain the second smoke type. Thus, the first smoke type can be corrected to obtain the second smoke type, thereby improving the accuracy of determining the smoke type.

[0142] In a possible implementation, the data may also be stored, specifically:

[0143] Cycle data saving method:

[0144] Set the cycle count clock and accumulate the count. For example: 0, 1...N;

[0145] The clock count is saved. The specified address is sent by sending the specified data;

[0146] Detect the clock value, N is the clock return signal, and the rest represent the corresponding program processing interface.

[0147] Cyclic data relationship comparison and data relationship mapping method:

[0148] Step 1 uses a cyclic data preservation method to save the first two data according to the mapping relationship.

[0149] Step 2 determines which relationship the first two data satisfy:

[0150] a. A>B data output 1

[0151] b. If A <= B, data output is 0

[0152] Step 3: Determine the previous data and the current data, and execute step 3)

[0153] Step 4 determines whether the outputs of step 3 and step 4 are both valid values ​​1. If so, the response is 1, otherwise it is 0.

[0154] See also Figure 2 , Figure 2 The present application provides a flowchart of another method for dynamic smoke recognition. Figure 2 As shown, the method includes:

[0155] 201. Acquire a target image of a to-be-detected area;

[0156] 202. Perform feature extraction on the target image to obtain feature data of the target image;

[0157] 203. Determine the smoke content in the area to be detected according to the gray value;

[0158] 204. Determine the smoke state information according to the smoke content;

[0159] 205. Acquire a smoke contour of a smoke area in the target image;

[0160] 206. Determine the smoke motion parameter according to the smoke contour;

[0161] 207. Determine a first smoke type according to the smoke state information and the smoke motion parameter.

[0162] In this example, by acquiring the smoke contour of the smoke area in the target image, the smoke motion parameters are determined according to the relevant parameters of the protruding area of ​​the smoke contour, so that the accuracy of the smoke motion parameter determination can be improved.

[0163] For the above embodiments, please refer to Figure 3 , Figure 3 A schematic diagram of the structure of a terminal provided in an embodiment of the present application, as shown in the figure, includes a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the program includes instructions for executing the following steps;

[0164] Acquire the target image of the area to be detected by using the grayscale eigenvalue method;

[0165] Extracting features from the target image to obtain feature data of the target image;

[0166] Performing data modeling operations according to the characteristic data to determine smoke status information of the area to be detected;

[0167] Determine smoke motion parameters by comparing the characteristic data of the target image;

[0168] A first smoke type is determined according to the smoke state information and the smoke motion parameter.

[0169] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that in order to realize the above functions, the terminal includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware 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.

[0170] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0171] In line with the above, see Figure 4 , Figure 4 The present invention provides a schematic diagram of a dynamic smoke recognition device. Figure 4 As shown, the device comprises:

[0172] An acquisition unit 401 is used to acquire a target image of a to-be-detected area by using a grayscale feature value method;

[0173] An extraction unit 402 is used to extract features from the target image to obtain feature data of the target image;

[0174] A first determining unit 403 is used to perform a data modeling operation according to the characteristic data to determine the smoke state information of the area to be detected;

[0175] A second determining unit 404 is used to determine smoke motion parameters according to the feature data comparison of the target image;

[0176] The third determining unit 405 is configured to determine a first smoke type according to the smoke state information and the smoke motion parameter.

[0177] In a possible implementation, the feature data includes a grayscale value, and the first determining unit 403 is configured to:

[0178] Determining the smoke content in the area to be detected according to the grayscale value;

[0179] The smoke state information is determined according to the smoke content.

[0180] In a possible implementation, the second determining unit 404 is configured to:

[0181] Acquire a smoke contour of a smoke area in the feature data in the target image;

[0182] The smoke motion parameter is determined according to the change of the smoke contour.

[0183] In a possible implementation, in determining the smoke motion parameter according to the smoke contour, the second determining unit 404 is configured to:

[0184] Obtaining M contour protrusion areas of the smoke contour;

[0185] Determining the smoke diffusion direction of each of the M protruding contour areas according to the M protruding contour areas;

[0186] Obtaining position information of the M contour protrusion areas in the smoke contour;

[0187] Determine a first reference smoke movement speed of the smoke in each of the M contour protrusion areas according to the position information and the smoke generation point;

[0188] Determining a second reference smoke movement speed of smoke in each of the M contour protruding areas according to contour shapes of the M contour protruding areas;

[0189] Determining a target smoke movement speed of the smoke in each of the M contour convex areas according to a first reference smoke movement speed of the smoke in each of the M contour convex areas and a second reference smoke movement speed of the smoke in each of the M contour convex areas;

[0190] The smoke diffusion direction of each of the M contour convex areas and the target smoke movement speed of the smoke in each of the M contour convex areas are determined as the smoke movement parameters.

[0191] In a possible implementation, the device is further used for:

[0192] Acquiring morphological parameters of the wind force marker in the target image;

[0193] Determining wind parameters of the area to be detected according to the morphological parameters;

[0194] Determining environmental information of the area to be detected according to the target image;

[0195] Determining first type correction information according to the wind force parameter and the environmental information;

[0196] Acquiring the light intensity of the area to be detected;

[0197] Determining second type correction information according to the light intensity;

[0198] determining target correction information according to the first type of correction information and the second type of correction information;

[0199] The first smoke type is corrected according to the target correction information to obtain a second smoke type.

[0200] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the dynamic smoke identification methods recorded in the above method embodiments.

[0201] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any one of the dynamic smoke identification methods recorded in the above method embodiments.

[0202] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0203] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0204] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which 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, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0205] 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.

[0206] In addition, the functional units in the various embodiments of the application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0207] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0208] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0209] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A smoke dynamic recognition method, characterized in that: The method comprises: Acquire the target image of the area to be detected by using the grayscale eigenvalue method; Extracting features from the target image to obtain feature data of the target image; Performing data modeling operations according to the characteristic data to determine smoke status information of the area to be detected; Determine smoke motion parameters by comparing the characteristic data of the target image; determining a first smoke type according to the smoke state information and the smoke motion parameter; The step of comparing the characteristic data of the target image to determine the smoke motion parameters includes: Acquire a smoke contour of a smoke area in the feature data in the target image; Determining the smoke motion parameters according to the change of the smoke profile; The step of determining the smoke motion parameter according to the smoke contour includes: Obtaining M contour protrusion areas of the smoke contour; Determining the smoke diffusion direction of each of the M protruding contour areas according to the M protruding contour areas; Obtaining position information of the M contour protrusion areas in the smoke contour; Determine a first reference smoke movement speed of the smoke in each of the M contour protrusion areas according to the position information and the smoke generation point; Determining a second reference smoke movement speed of smoke in each of the M contour protruding areas according to contour shapes of the M contour protruding areas; Determining a target smoke movement speed of the smoke in each of the M contour convex areas according to a first reference smoke movement speed of the smoke in each of the M contour convex areas and a second reference smoke movement speed of the smoke in each of the M contour convex areas; The smoke diffusion direction of each of the M contour convex areas and the target smoke movement speed of the smoke in each of the M contour convex areas are determined as the smoke movement parameters.

2. The method according to claim 1, characterized in that The characteristic data includes a grayscale value, and the data modeling operation is performed according to the characteristic data to determine the smoke state information of the area to be detected, including: Determining the smoke content in the area to be detected according to the grayscale value; The smoke state information is determined according to the smoke content.

3. The method according to claim 1, characterized in that The method further comprises: Acquiring morphological parameters of the wind force marker in the target image; Determining wind parameters of the area to be detected according to the morphological parameters; Determining environmental information of the area to be detected according to the target image; Determining first type correction information according to the wind force parameter and the environmental information; Acquiring the light intensity of the area to be detected; Determining second type correction information according to the light intensity; determining target correction information according to the first type of correction information and the second type of correction information; The first smoke type is corrected according to the target correction information to obtain a second smoke type.

4. A smoke dynamic identification device, characterized in that: The device comprises: An acquisition unit, used for acquiring a target image of the area to be detected by using a grayscale feature value method; An extraction unit, used for performing feature extraction on the target image to obtain feature data of the target image; A first determining unit, configured to perform a data modeling operation according to the characteristic data to determine the smoke state information of the area to be detected; A second determination unit is used to determine the smoke motion parameters according to the feature data comparison of the target image; a third determining unit, configured to determine a first smoke type according to the smoke state information and the smoke motion parameter; The second determining unit is used for: Acquire a smoke contour of a smoke area in the feature data in the target image; Determining the smoke motion parameters according to the change of the smoke profile; In the aspect of determining the smoke motion parameter according to the smoke contour, the second determining unit is used for: Obtaining M contour protrusion areas of the smoke contour; Determining the smoke diffusion direction of each of the M protruding contour areas according to the M protruding contour areas; Obtaining position information of the M contour protrusion areas in the smoke contour; Determine a first reference smoke movement speed of the smoke in each of the M contour protrusion areas according to the position information and the smoke generation point; Determining a second reference smoke movement speed of smoke in each of the M contour protruding areas according to contour shapes of the M contour protruding areas; Determining a target smoke movement speed of the smoke in each of the M contour convex areas according to a first reference smoke movement speed of the smoke in each of the M contour convex areas and a second reference smoke movement speed of the smoke in each of the M contour convex areas; The smoke diffusion direction of each of the M contour convex areas and the target smoke movement speed of the smoke in each of the M contour convex areas are determined as the smoke movement parameters.

5. The device according to claim 4, characterized in that The characteristic data includes a grayscale value, and the first determining unit is used for: Determining the smoke content in the area to be detected according to the grayscale value; The smoke state information is determined according to the smoke content.

6. A terminal, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 3.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 3.

Images