Overflow detection method and system, range hood, and storage medium

Abstract

The present invention provides a pot overflow detection method and system, a range hood, and a storage medium. The pot overflow detection method comprises: acquiring point cloud data of a first region within a preset distance from the center of a pot lid in real time; obtaining a fluctuation value of the pot lid based on the point cloud data of the first region; and generating an alarm signal when the fluctuation value exceeds a preset range. The present invention obtains the fluctuation value of the pot lid (pot handle) from the point cloud data of the first region within a preset distance from the center of the pot lid, determines the degree of pot overflow based on the fluctuation value, and generates an alarm signal to warn when pot overflow or the risk of pot overflow exists.

Description

Technical Field

[0001] The present invention relates to the technical field of kitchenware, and in particular to a pot overflow detection method and system, a range hood, and a storage medium. Background Art

[0002] There are currently three methods for detecting overflow:

[0003] 1) Design a pot with overflow detection function or design an adaptive pot lid to prevent overflow. Disadvantages: difficult to use in real life, strange shape and cannot interact with the user.

[0004] 2) The stove is equipped with a temperature probe that can detect overflowing pots through temperature changes. Disadvantage: Smart stoves that detect overflowing pots through temperature changes cannot sense oil smoke and are prone to misjudgment based solely on temperature information.

[0005] 3) Install a camera on the range hood to collect images of the stove to monitor whether the pot is overflowing. Disadvantage: Using a camera to collect images will affect user privacy. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to overcome the defects of the methods for detecting overflowing pots in the prior art, and to provide an overflowing pot detection method and system, a range hood and a storage medium.

[0007] The present invention solves the above technical problems through the following technical solutions:

[0008] The present invention provides a pot overflow detection method, which comprises:

[0009] Real-time acquisition of point cloud data of the first area within a preset distance range from the center of the pot lid;

[0010] Obtaining a fluctuation value of the pot lid based on the point cloud data of the first area;

[0011] When the fluctuation value exceeds a preset range, an alarm signal is generated.

[0012] Preferably, before the step of acquiring point cloud data of a first area within a preset distance range from the center of the pot cover in real time, the pot overflow detection method further comprises:

[0013] Acquire total area point cloud data of a total detection area, where the total detection area covers a stove surface;

[0014] Obtaining a grayscale image containing the pot based on the total area point cloud data;

[0015] Identify the grayscale image to obtain the center coordinates of the pot cover;

[0016] The step of obtaining point cloud data of a first area within a preset distance from the center of the pot lid in real time specifically includes:

[0017] The first area point cloud data is extracted from the total area point cloud data according to the center coordinates.

[0018] Preferably, before the step of generating an alarm signal, the overflow detection method further comprises:

[0019] Extracting second area point cloud data of a preset smoke detection area from the total area point cloud data, wherein the second area point cloud data includes the number of point clouds;

[0020] Obtaining a smoke volume evaluation value based on the number of point clouds;

[0021] Obtaining a pot overflow evaluation value based on the fluctuation value and the smoke amount evaluation value;

[0022] When the fluctuation value exceeds a preset range, the step of generating an alarm signal specifically includes:

[0023] When the overflow evaluation value exceeds a preset range, an alarm signal is generated.

[0024] Preferably, the second area point cloud data further includes position data of the point cloud;

[0025] After the step of extracting the second area point cloud data of the preset smoke detection area from the total area point cloud data, the overflow detection method further includes:

[0026] obtaining a disturbance weight based on the position data;

[0027] The step of obtaining the overflow evaluation value based on the fluctuation value and the smoke volume evaluation value specifically includes:

[0028] An overflow evaluation value is obtained based on the fluctuation value, the smoke amount evaluation value and the disturbance weight.

[0029] Preferably, the step of obtaining a smoke volume evaluation value based on the number of point clouds specifically includes:

[0030] The ratio of the number of point clouds to the reference number of point clouds in a normal overflowing state is used as the smoke quantity evaluation value.

[0031] Preferably, the step of obtaining the fluctuation value of the pot lid based on the first area point cloud data specifically includes:

[0032] Based on the point cloud data of the first area, position data of each point cloud within a preset distance range from the center of the pot lid in a preset period is obtained;

[0033] Based on the position data, obtain position change data of each point cloud in the xyz three-axis directions within a preset period;

[0034] A fluctuation value is obtained based on the position change data, the x-axis direction fluctuation coefficient, the y-axis direction fluctuation coefficient, and the z-axis direction fluctuation coefficient.

[0035] Preferably, the fluctuation value β is calculated using the following formula: g :

[0036] β g =w x Δ x +w y Δ y +w z Δ z ;

[0037]

[0038]

[0039]

[0040] Where i represents a single point cloud within the preset range, n represents the number of point clouds within the preset range, Indicates the sum of the coordinates of the point cloud in the x-axis direction within the preset range. Indicates the sum of the coordinates of the point cloud in the y-axis direction within the preset range. Indicates the sum of the coordinates of the point cloud in the preset range in the z-axis direction, t represents the time point, t1 represents the preset time, Δ x Represents the position change data of all point clouds in the x-axis direction within time t1, Δ y Indicates the position change data of all point clouds in the y-axis direction within time t1, Δ z Represents the position change data of all point clouds in the z-axis direction within t1 time, w x represents the x-axis fluctuation coefficient, w y Indicates the y-axis fluctuation coefficient, w z Indicates the z-axis wave coefficient.

[0041] The present invention also provides a pot overflow detection system, which includes: a point cloud data acquisition module, a fluctuation value calculation module and an alarm generation module;

[0042] The point cloud data acquisition module is used to acquire point cloud data of a first area within a preset distance from the center of the pot lid in real time;

[0043] The fluctuation value calculation module is used to obtain the fluctuation value of the pot lid based on the first area point cloud data;

[0044] The alarm generating module is used to generate an alarm signal when the fluctuation value exceeds a preset range.

[0045] Preferably, the point cloud data acquisition module includes: a total area point cloud data unit and a first area point cloud data unit, and the overflow detection system further includes: a grayscale image calculation module and an image recognition module;

[0046] The total area point cloud data unit is used to obtain total area point cloud data of a total detection area, where the total detection area covers the stove surface;

[0047] The grayscale image calculation module is used to obtain a grayscale image containing the cookware based on the total area point cloud data;

[0048] The image recognition module is used to identify the grayscale image to obtain the center coordinates of the pot cover center;

[0049] The first area point cloud data unit is used to extract the first area point cloud data from the total area point cloud data according to the center coordinates.

[0050] Preferably, the point cloud data acquisition module further includes: a second area point cloud data unit, and the overflow detection system further includes: a smoke volume evaluation value calculation module and an overflow evaluation value calculation module;

[0051] The second area point cloud data unit is used to extract second area point cloud data of a preset smoke detection area from the total area point cloud data, wherein the second area point cloud data includes the number of point clouds;

[0052] The smoke volume evaluation value calculation module is used to obtain a smoke volume evaluation value based on the number of point clouds;

[0053] The overflow evaluation value calculation module is used to obtain the overflow evaluation value based on the fluctuation value and the smoke amount evaluation value;

[0054] The alarm generation module is specifically configured to generate an alarm signal when the overflow evaluation value exceeds a preset range.

[0055] Preferably, the second area point cloud data further includes position data of the point cloud;

[0056] The overflow detection system further includes: a disturbance weight calculation module;

[0057] The disturbance weight calculation module is used to obtain the disturbance weight based on the position data;

[0058] The overflow evaluation value calculation module is specifically used to obtain the overflow evaluation value based on the fluctuation value, the smoke volume evaluation value and the disturbance weight.

[0059] Preferably, the smoke quantity evaluation value calculation module is specifically used to take the ratio of the number of point clouds to the reference number of point clouds in a normal overflowing state as the smoke quantity evaluation value.

[0060] Preferably, the fluctuation value calculation module includes: a position data calculation unit, a position change data calculation unit and a fluctuation value calculation unit;

[0061] The position data calculation unit is used to obtain the position data of each point cloud within a preset distance range from the center of the pot cover in a preset period based on the first area point cloud data;

[0062] The position change data calculation unit is used to obtain the position change data of each point cloud in the xyz three-axis direction within a preset period based on the position data;

[0063] The fluctuation value calculation unit is used to obtain a fluctuation value based on the position change data, the fluctuation coefficient in the x-axis direction, the fluctuation coefficient in the y-axis direction, and the fluctuation coefficient in the z-axis direction.

[0064] Preferably, the fluctuation value β is calculated using the following formula: g :

[0065] β g =w x Δ x +w y Δ y +w z Δ z ;

[0066]

[0067]

[0068]

[0069] Where i represents a single point cloud within the preset range, n represents the number of point clouds within the preset range, Indicates the sum of the coordinates of the point cloud in the x-axis direction within the preset range. Indicates the sum of the coordinates of the point cloud in the y-axis direction within the preset range. Indicates the sum of the coordinates of the point cloud in the preset range in the z-axis direction, t represents the time point, t1 represents the preset time, Δ x Represents the position change data of all point clouds in the x-axis direction within time t1, Δ y Indicates the position change data of all point clouds in the y-axis direction within time t1, Δ z Represents the position change data of all point clouds in the z-axis direction within t1 time, w x represents the x-axis fluctuation coefficient, w yIndicates the y-axis fluctuation coefficient, w z Indicates the z-axis wave coefficient.

[0070] The present invention also provides a range hood comprising the aforementioned pan overflow detection system.

[0071] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which implements the aforementioned overflow detection method when executed by a processor.

[0072] The positive progressive effect of the present invention is that the fluctuation value of the pot lid (pot handle) is obtained through the point cloud data of the first area within a preset distance range from the center of the pot lid, the degree of overflow is judged according to the fluctuation value, and an alarm signal is generated to warn when there is overflow or overflow risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 This is a flow chart of the overflow detection method of Example 1 of the present invention.

[0074] Figure 2 This is a flow chart of a first specific implementation method of the overflow detection method of Example 1 of the present invention.

[0075] Figure 3 This is a flow chart of a second specific implementation of the overflow detection method of Example 1 of the present invention.

[0076] Figure 4 This is a flow chart of the third specific implementation of the overflow detection method of Example 1 of the present invention.

[0077] Figure 5 This is a flow chart of the fourth specific implementation of the overflow detection method of Example 1 of the present invention.

[0078] Figure 6 This is a flowchart of a specific implementation of step S12 in the overflow detection method of Example 1 of the present invention.

[0079] Figure 7 Schematic diagram of the module of the overflow detection system of Example 2 of the present invention. DETAILED DESCRIPTION

[0080] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples.

[0081] Example 1

[0082] This embodiment provides a method for detecting overflowing pot. Figure 1 , the overflow detection method includes:

[0083] S11. Acquire point cloud data of a first area within a preset distance range from the center of the pot lid in real time.

[0084] S12. Obtaining a fluctuation value of the pot lid based on the point cloud data of the first region.

[0085] S13. When the fluctuation value exceeds a preset range, an alarm signal is generated.

[0086] A TOF camera can be used to collect point cloud data. Its transmitter reflects infrared light, and its receiver receives the reflected infrared light. The camera can be mounted on the underside of the range hood, such as below the start switch or the lower edge of the range hood. The camera's lens is angled relative to the horizontal plane, allowing the camera's total detection area to cover the entire stovetop.

[0087] Overflowing occurs when there are too many ingredients in the pot and the heat is too strong, causing the soup to boil violently and overflow. Overflowing is often accompanied by the lid's violent fluctuations. Overflowing can be detected by measuring the fluctuation value of the lid.

[0088] Alarm signals control sound and light effects to achieve warning effects. For example, the alarm signal controls the beeping of a buzzer and the color, brightness, and flashing pattern of an indicator light. Multiple preset ranges can be set to correspond to different levels of overflow (including non-overflowing but close to overflowing), generating corresponding alarm signals to control the sound and light effects.

[0089] This embodiment obtains the fluctuation value of the pot lid (pot handle) through the point cloud data of the first area within a preset distance range from the center of the pot lid, judges the degree of overflowing according to the fluctuation value, and generates an alarm signal to warn when overflowing or overflowing risk exists.

[0090] This embodiment provides a first specific implementation method, referring to Figure 2 Before step S11, the overflow detection method further includes:

[0091] S101. Obtaining total area point cloud data of a total detection area, where the total detection area covers a stove surface.

[0092] S102: Obtain a grayscale image containing the cookware based on the total area point cloud data.

[0093] S103, identifying the grayscale image to obtain the center coordinates of the pot lid center.

[0094] Step S11 includes:

[0095] S111 . Extracting first area point cloud data from the total area point cloud data according to the center coordinates.

[0096] Among them, the three-dimensional point cloud data is projected onto a two-dimensional plane to obtain a grayscale image of the current stove surface as an input parameter of the object recognition module. The object recognition module is constructed in advance, and the grayscale images of various pots and pans placed on the stove scene collected offline are used as training sets. It is obtained through convolutional neural network training and can accurately identify the pot lid in the grayscale image. According to the pot lid identified by the object recognition module, the position of the pot lid in the image is obtained, and then the (x, y) coordinates of the pot lid in the stove scene are calculated. By locating the position of the pot lid, the position of the center of the pot lid is found, and the point cloud within a preset distance range (for example, 2 cm) from the center of the pot lid is part of the pot lid point cloud. The coordinates of the center of the pot lid are the mean of the coordinates of the outer edge of the pot lid.

[0097] This embodiment converts three-dimensional point cloud data into a two-dimensional grayscale image, and can use a trained object recognition module to accurately identify the pot cover in the grayscale image, thereby obtaining the center coordinates of the center of the pot cover, and extracting the first area point cloud data based on the center coordinates.

[0098] This embodiment provides a second specific implementation method based on the first specific implementation method. Figure 3 Before step S13, the overflow detection method further includes:

[0099] S1201. Extract second-region point cloud data of a preset smoke detection area from the total-region point cloud data, where the second-region point cloud data includes the number of point clouds.

[0100] S1202: Obtain a smoke volume evaluation value based on the number of point clouds.

[0101] S1203: Obtain an overflow evaluation value based on the fluctuation value and the smoke volume evaluation value.

[0102] Step S13 specifically includes:

[0103] S131. When the overflow evaluation value exceeds a preset range, an alarm signal is generated.

[0104] Among them, overflowing pot is often accompanied by the generation of a large amount of water vapor and smoke, and the degree of water vapor and smoke generation can be measured by the smoke volume evaluation value.

[0105] You can set the preset range based on the scenario, including but not limited to: the lid is completely covering the pot, and the lid handle is not in the center of the pot.

[0106] In this embodiment, an overflow evaluation value is obtained through the fluctuation value and the smoke volume evaluation value to evaluate the degree of overflow, and an alarm signal is generated to warn when overflow or overflow risk exists.

[0107] This embodiment provides a third specific implementation method based on the second specific implementation method. Figure 4 , the second area point cloud data also includes position data of the point cloud.

[0108] After step S1201, the overflow detection method further includes:

[0109] S12020. Obtain a disturbance weight based on the position data.

[0110] Step S1203 specifically includes:

[0111] S12031. Obtain an overflow evaluation value based on the fluctuation value, the smoke volume evaluation value, and the disturbance weight.

[0112] This embodiment adjusts the weight relationship between the fluctuation value and the smoke volume evaluation value in the overflow evaluation value by using the disturbance weight.

[0113] This embodiment provides a fourth specific implementation method based on the second specific implementation method. Figure 5 Step S1202 specifically includes:

[0114] S12021. The ratio of the number of point clouds to the reference number of point clouds under normal overflowing state is used as the smoke volume evaluation value.

[0115] The reference number of point clouds under normal overflowing conditions can be obtained based on experimental data.

[0116] This embodiment further provides a method for calculating the smoke volume evaluation value.

[0117] Reference Figure 6 , step S12 specifically includes:

[0118] S121. Obtain position data of each point cloud within a preset distance range from the center of the pot cover in a preset period based on the point cloud data of the first area.

[0119] S122 , obtaining position change data of each point cloud in the xyz three-axis directions within a preset period based on the position data.

[0120] S123. Obtain a fluctuation value based on the position change data, the x-axis direction fluctuation coefficient, the y-axis direction fluctuation coefficient, and the z-axis direction fluctuation coefficient.

[0121] To account for human interference, the variance of the current point cloud in the x- and y-directions is calculated and compared with reference variance values with human interference measured in multiple experiments to determine whether human interaction is currently occurring. Normally, soot particles are distributed evenly, resulting in larger variances in the point cloud in the x- and y-directions. However, if a hand or spatula is present in the area, the point cloud will be detected as a cluster of closely spaced, densely packed points with smaller variances, falling within a certain threshold range that can be determined experimentally.

[0122] This embodiment obtains the position change data of each point cloud in the xyz three-axis directions within a preset period through position data, and then calculates the fluctuation value, providing a specific implementation method for obtaining the fluctuation value.

[0123] In specific implementation, the following formula is used to calculate the fluctuation value β g :

[0124] β g =w x Δ x +w y Δ y +w z Δ z .

[0125]

[0126]

[0127]

[0128] Where i represents a single point cloud within the preset range, n represents the number of point clouds within the preset range, Indicates the sum of the coordinates of the point cloud in the x-axis direction within the preset range. Indicates the sum of the coordinates of the point cloud in the y-axis direction within the preset range. Indicates the sum of the coordinates of the point cloud in the preset range in the z-axis direction, t represents the time point, t1 represents the preset time, Δ x Represents the position change data of all point clouds in the x-axis direction within time t1, Δ y Indicates the position change data of all point clouds in the y-axis direction within time t1, Δ z Represents the position change data of all point clouds in the z-axis direction within t1 time, w x represents the x-axis fluctuation coefficient, w y Indicates the y-axis fluctuation coefficient, w z Indicates the z-axis wave coefficient.

[0129] This embodiment provides a specific calculation formula for the fluctuation value.

[0130] This embodiment converts three-dimensional point cloud data into a two-dimensional grayscale image, and can use a trained object recognition module to accurately identify the pot cover in the grayscale image, and then obtain the central coordinates of the center of the pot cover, extract the first area point cloud data according to the central coordinates, and then obtain the fluctuation value of the pot cover (pot handle) based on the first area point cloud data, extract the second area point cloud data of the preset smoke detection area from the total area point cloud data, and obtain the smoke volume evaluation value and disturbance weight based on the second area point cloud data, and then judge the degree of overflow according to the fluctuation value, smoke volume evaluation value and disturbance weight, and generate an alarm signal to warn when there is overflow and overflow risk.

[0131] Example 2

[0132] This embodiment provides a pan overflow detection system. Figure 7 The overflow detection system includes: a point cloud data acquisition module 1, a fluctuation value calculation module 2 and an alarm generation module 3.

[0133] The point cloud data acquisition module 1 is used to acquire point cloud data of a first area within a preset distance range from the center of the pot cover in real time.

[0134] The fluctuation value calculation module 2 is used to obtain the fluctuation value of the pot lid based on the first area point cloud data.

[0135] The alarm generating module 3 is used to generate an alarm signal when the fluctuation value exceeds a preset range.

[0136] A TOF camera can be used to collect point cloud data. Its transmitter reflects infrared light, and its receiver receives the reflected infrared light. The camera can be mounted on the underside of the range hood, such as below the start switch or the lower edge of the range hood. The camera's lens is angled relative to the horizontal plane, allowing the camera's total detection area to cover the entire stovetop.

[0137] Overflowing occurs when there are too many ingredients in the pot and the heat is too strong, causing the soup to boil violently and overflow. Overflowing is often accompanied by the lid's violent fluctuations. Overflowing can be detected by measuring the fluctuation value of the lid.

[0138] Alarm signals control sound and light effects to achieve warning effects. For example, the alarm signal controls the beeping of a buzzer and the color, brightness, and flashing pattern of an indicator light. Multiple preset ranges can be set to correspond to different levels of overflow (including non-overflowing but close to overflowing), generating corresponding alarm signals to control the sound and light effects.

[0139] This embodiment obtains the fluctuation value of the pot lid (pot handle) through the point cloud data of the first area within a preset distance range from the center of the pot lid, judges the degree of overflowing according to the fluctuation value, and generates an alarm signal to warn when overflowing or overflowing risk exists.

[0140] In specific implementation, the point cloud data acquisition module 1 includes: a total area point cloud data unit 101 and a first area point cloud data unit 102 , and the overflow detection system also includes: a grayscale image calculation module 4 and an image recognition module 5 .

[0141] The total area point cloud data unit 101 is used to obtain the total area point cloud data of the total detection area, where the total detection area covers the stove surface.

[0142] The grayscale image calculation module 4 is used to obtain a grayscale image containing the cookware based on the total area point cloud data.

[0143] The image recognition module 5 is used to recognize the grayscale image and obtain the center coordinates of the center of the pot cover.

[0144] The first region point cloud data unit 102 is configured to extract first region point cloud data from the total region point cloud data according to the center coordinates.

[0145] Among them, the three-dimensional point cloud data is projected onto a two-dimensional plane to obtain a grayscale image of the current stove surface as an input parameter of the object recognition module. The object recognition module is constructed in advance, and the grayscale images of various pots and pans placed on the stove scene collected offline are used as training sets. It is obtained through convolutional neural network training and can accurately identify the pot lid in the grayscale image. According to the pot lid identified by the object recognition module, the position of the pot lid in the image is obtained, and then the (x, y) coordinates of the pot lid in the stove scene are calculated. By locating the position of the pot lid, the position of the center of the pot lid is found, and the point cloud within a preset distance range (for example, 2 cm) from the center of the pot lid is part of the pot lid point cloud. The coordinates of the center of the pot lid are the mean of the coordinates of the outer edge of the pot lid.

[0146] This embodiment converts three-dimensional point cloud data into a two-dimensional grayscale image, and can use a trained object recognition module to accurately identify the pot cover in the grayscale image, thereby obtaining the center coordinates of the center of the pot cover, and extracting the first area point cloud data based on the center coordinates.

[0147] During specific implementation, the point cloud data acquisition module 1 further includes: a second area point cloud data unit 103 , and the overflow detection system further includes: a smoke volume evaluation value calculation module 6 and an overflow evaluation value calculation module 7 .

[0148] The second area point cloud data unit 103 is used to extract second area point cloud data of a preset smoke detection area from the total area point cloud data, where the second area point cloud data includes the number of point clouds.

[0149] The smoke volume evaluation value calculation module 6 is used to obtain a smoke volume evaluation value based on the number of point clouds.

[0150] The overflow evaluation value calculation module 7 is used to obtain the overflow evaluation value based on the fluctuation value and the smoke amount evaluation value.

[0151] The alarm generating module 3 is specifically used to generate an alarm signal when the overflow evaluation value exceeds a preset range.

[0152] Among them, overflowing pot is often accompanied by the generation of a large amount of water vapor and smoke, and the degree of water vapor and smoke generation can be measured by the smoke volume evaluation value.

[0153] You can set the preset range based on the scenario, including but not limited to: the lid is completely covering the pot, and the lid handle is not in the center of the pot.

[0154] In this embodiment, an overflow evaluation value is obtained through the fluctuation value and the smoke volume evaluation value to evaluate the degree of overflow, and an alarm signal is generated to warn when overflow or overflow risk exists.

[0155] During specific implementation, the second area point cloud data also includes position data of the point cloud.

[0156] The overflow detection system further includes: a disturbance weight calculation module 8.

[0157] The disturbance weight calculation module 8 is used to obtain the disturbance weight based on the position data.

[0158] The overflow evaluation value calculation module 7 is specifically used to obtain the overflow evaluation value based on the fluctuation value, the smoke volume evaluation value and the disturbance weight.

[0159] This embodiment adjusts the weight relationship between the fluctuation value and the smoke volume evaluation value in the overflow evaluation value by using the disturbance weight.

[0160] During specific implementation, the smoke quantity evaluation value calculation module 6 is specifically configured to use the ratio of the number of point clouds to the reference number of point clouds in a normal overflowing state as the smoke quantity evaluation value.

[0161] The reference number of point clouds under normal overflowing state can be obtained based on experimental data.

[0162] This embodiment further provides a method for calculating the smoke volume evaluation value.

[0163] During specific implementation, the fluctuation value calculation module 2 includes: a position data calculation unit 201 , a position change data calculation unit 202 and a fluctuation value calculation unit 203 .

[0164] The position data calculation unit 201 is used to obtain the position data of each point cloud within a preset distance range from the center of the pot cover in a preset period based on the point cloud data of the first area.

[0165] The position change data calculation unit 202 is used to obtain the position change data of each point cloud in the xyz three-axis directions within a preset period based on the position data.

[0166] The fluctuation value calculation unit 203 is used to obtain a fluctuation value based on the position change data, the fluctuation coefficient in the x-axis direction, the fluctuation coefficient in the y-axis direction, and the fluctuation coefficient in the z-axis direction.

[0167] To account for human interference, the variance of the current point cloud in the x- and y-directions is calculated and compared with reference variance values with human interference measured in multiple experiments to determine whether human interaction is currently occurring. Normally, soot particles are distributed evenly, resulting in larger variances in the point cloud in the x- and y-directions. However, if a hand or spatula is present in the area, the point cloud will be detected as a cluster of closely spaced, densely packed points with smaller variances, falling within a certain threshold range that can be determined experimentally.

[0168] This embodiment obtains the position change data of each point cloud in the xyz three-axis directions within a preset period through position data, and then calculates the fluctuation value, providing a specific implementation method for obtaining the fluctuation value.

[0169] In specific implementation, the following formula is used to calculate the fluctuation value β g :

[0170] β g =w x Δ x +w y Δ y +w z Δ z .

[0171]

[0172]

[0173]

[0174] Where i represents a single point cloud within the preset range, n represents the number of point clouds within the preset range, Indicates the sum of the coordinates of the point cloud in the x-axis direction within the preset range. Indicates the sum of the coordinates of the point cloud in the y-axis direction within the preset range. Indicates the sum of the coordinates of the point cloud in the preset range in the z-axis direction, t represents the time point, t1 represents the preset time, Δ x Represents the position change data of all point clouds in the x-axis direction within time t1, Δ y Indicates the position change data of all point clouds in the y-axis direction within time t1, Δ z Represents the position change data of all point clouds in the z-axis direction within t1 time, w x represents the x-axis fluctuation coefficient, w y Indicates the y-axis fluctuation coefficient, w zIndicates the z-axis wave coefficient.

[0175] This embodiment provides a specific calculation formula for the fluctuation value.

[0176] This embodiment converts three-dimensional point cloud data into a two-dimensional grayscale image, and can use a trained object recognition module to accurately identify the pot cover in the grayscale image, and then obtain the central coordinates of the center of the pot cover, extract the first area point cloud data according to the central coordinates, and then obtain the fluctuation value of the pot cover (pot handle) based on the first area point cloud data, extract the second area point cloud data of the preset smoke detection area from the total area point cloud data, and obtain the smoke volume evaluation value and disturbance weight based on the second area point cloud data, and then judge the degree of overflow according to the fluctuation value, smoke volume evaluation value and disturbance weight, and generate an alarm signal to warn when there is overflow and overflow risk.

[0177] Example 3

[0178] This embodiment provides a range hood, including the pan overflow detection system in Example 2.

[0179] This embodiment converts three-dimensional point cloud data into a two-dimensional grayscale image, and can use a trained object recognition module to accurately identify the pot cover in the grayscale image, and then obtain the central coordinates of the center of the pot cover, extract the first area point cloud data according to the central coordinates, and then obtain the fluctuation value of the pot cover (pot handle) based on the first area point cloud data, extract the second area point cloud data of the preset smoke detection area from the total area point cloud data, and obtain the smoke volume evaluation value and disturbance weight based on the second area point cloud data, and then judge the degree of overflow according to the fluctuation value, smoke volume evaluation value and disturbance weight, and generate an alarm signal to warn when there is overflow and overflow risk.

[0180] Example 4

[0181] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the overflow detection method provided in Example 1 is implemented.

[0182] The readable storage medium may include, but is not limited to, a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0183] In a possible implementation manner, the present invention can also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the overflow detection method described in Example 1.

[0184] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or entirely on the remote device.

[0185] Although specific embodiments of the present invention have been described above, those skilled in the art will appreciate that these are merely illustrative and that the scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, and such changes and modifications are intended to fall within the scope of the present invention.

Claims

1. A method for detecting an overflowing pot, characterized in that: The overflow detection method comprises: Real-time acquisition of point cloud data of the first area within a preset distance range from the center of the pot lid; Obtaining a fluctuation value of the pot lid based on the point cloud data of the first area; When the fluctuation value exceeds a preset range, an alarm signal is generated; Before the step of acquiring point cloud data of a first area within a preset distance range from the center of the pot cover in real time, the pot overflow detection method further includes: Acquire total area point cloud data of a total detection area, where the total detection area covers a stove surface; Obtaining a grayscale image containing the pot based on the total area point cloud data; Identify the grayscale image to obtain the center coordinates of the pot cover; The step of obtaining point cloud data of a first area within a preset distance from the center of the pot lid in real time specifically includes: extracting the first area point cloud data from the total area point cloud data according to the center coordinates; Before the step of generating an alarm signal, the overflow detection method further includes: Extracting second area point cloud data of a preset smoke detection area from the total area point cloud data, wherein the second area point cloud data includes the number of point clouds; Obtaining a smoke volume evaluation value based on the number of point clouds; Obtaining a pot overflow evaluation value based on the fluctuation value and the smoke amount evaluation value; When the fluctuation value exceeds a preset range, the step of generating an alarm signal specifically includes: When the overflow evaluation value exceeds a preset range, an alarm signal is generated.

2. The overflow detection method according to claim 1, wherein: The second area point cloud data also includes position data of the point cloud; After the step of extracting the second area point cloud data of the preset smoke detection area from the total area point cloud data, the overflow detection method further includes: obtaining a disturbance weight based on the position data; The step of obtaining the overflow evaluation value based on the fluctuation value and the smoke volume evaluation value specifically includes: An overflow evaluation value is obtained based on the fluctuation value, the smoke amount evaluation value and the disturbance weight.

3. The overflow detection method according to claim 1, wherein: The step of obtaining a smoke volume evaluation value based on the number of point clouds specifically includes: The ratio of the number of point clouds to the reference number of point clouds in a normal overflowing state is used as the smoke quantity evaluation value.

4. The overflow detection method according to claim 1, wherein: The step of obtaining the fluctuation value of the pot lid based on the first area point cloud data specifically includes: Based on the point cloud data of the first area, position data of each point cloud within a preset distance range from the center of the pot lid in a preset period is obtained; Based on the position data, obtain position change data of each point cloud in the xyz three-axis directions within a preset period; A fluctuation value is obtained based on the position change data, the x-axis direction fluctuation coefficient, the y-axis direction fluctuation coefficient, and the z-axis direction fluctuation coefficient.

5. The overflow detection method according to claim 4, wherein: The fluctuation value is calculated using the following formula : ； ； ； ； Where i represents a single point cloud within the preset range, n represents the number of point clouds within the preset range, Indicates the sum of the coordinates of the point cloud in the x-axis direction within the preset range. Indicates the sum of the coordinates of the point cloud in the y-axis direction within the preset range. Indicates the sum of the coordinates of the point cloud in the preset range in the z-axis direction, t represents the time point, t1 represents the preset time, Represents the position change data of all point clouds in the x-axis direction within time t1. Represents the position change data of all point clouds in the y-axis direction within time t1. Represents the position change data of all point clouds in the z-axis direction within time t1. represents the fluctuation coefficient in the x-axis direction, represents the fluctuation coefficient in the y-axis direction, Indicates the z-axis wave coefficient.

6. A pot overflow detection system, characterized in that: The overflow detection system includes: a point cloud data acquisition module, a fluctuation value calculation module and an alarm generation module; The point cloud data acquisition module is used to acquire point cloud data of a first area within a preset distance from the center of the pot lid in real time; The fluctuation value calculation module is used to obtain the fluctuation value of the pot lid based on the first area point cloud data; The alarm generating module is used to generate an alarm signal when the fluctuation value exceeds a preset range; The point cloud data acquisition module includes: a total area point cloud data unit and a first area point cloud data unit. The pot overflow detection system also includes: a grayscale image calculation module and an image recognition module; the total area point cloud data unit is used to obtain total area point cloud data of a total detection area, where the total detection area covers the stove surface; the grayscale image calculation module is used to obtain a grayscale image containing the pot based on the total area point cloud data; the image recognition module is used to identify the grayscale image to obtain the center coordinates of the pot lid; the first area point cloud data unit is used to extract the first area point cloud data from the total area point cloud data according to the center coordinates; The point cloud data acquisition module also includes: a second area point cloud data unit, and the overflow detection system also includes: a smoke quantity evaluation value calculation module and an overflow evaluation value calculation module; the second area point cloud data unit is used to extract the second area point cloud data of the preset smoke detection area from the total area point cloud data, and the second area point cloud data includes the number of point clouds; the smoke quantity evaluation value calculation module is used to obtain the smoke quantity evaluation value based on the number of point clouds; the overflow evaluation value calculation module is used to obtain the overflow evaluation value based on the fluctuation value and the smoke quantity evaluation value; the alarm generation module is specifically used to generate an alarm signal when the overflow evaluation value exceeds a preset range.

7. A range hood, characterized in that: Comprising the overflow detection system as described in claim 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the overflow detection method according to any one of claims 1 to 5 is implemented.

Images