Household appliance control method and device and range hood

Abstract

The invention relates to a household appliance control method and device and a range hood. The method comprises the following steps: acquiring an effective palm image of a user in a target area; performing edge detection and feature recognition on the obtained effective palm image to obtain an edge detection result and a feature recognition result of the effective palm image; determining the height of the user based on the edge detection result of the effective palm image; adjusting the height of the household appliance based on the height of the user; determining the age group of the user based on the feature recognition result of the effective palm image; based on the age group of the user, according to a preset corresponding relationship between the age group and the parameter, adjusting the parameter of the household appliance; the parameters are one or more of lighting parameters and sound parameters of the household appliances. By the adoption of the method, the problem that according to an existing range hood control method, customized services cannot be carried out according to the actual situation of a user can be solved.

Description

Technical Field

[0001] The present application relates to the technical field of household electrical appliances, and in particular to a control method and device for household electrical appliances and a range hood. Background Art

[0002] With the development of electronic technology, smart devices are gradually being widely used, and people's requirements for smart devices are gradually increasing. As an indispensable kitchen appliance in modern household smart devices, range hoods have also gradually increased people's requirements for their intelligence.

[0003] Existing range hood designs are mostly installed at a fixed height, which cannot adapt to the height differences of users and the diverse layouts of kitchens, and there is a problem of insufficient customized services. In order to improve the customized services of range hoods, the existing technology introduces hand-waving sensing control technology to reduce the inconvenience caused by contact operation. However, in actual application, hand-waving sensing control technology may cause troubles to specific user groups and the hand state during cooking. On the other hand, due to the distance limitation, it cannot provide customized services according to the actual situation of users.

[0004] With regard to the problem that the existing range hood control methods cannot provide customized services according to the actual conditions of users, no effective solution has been proposed yet. Summary of the invention

[0005] Based on this, it is necessary to provide a control method and device for household appliances and a range hood to address the above technical issues.

[0006] In a first aspect, the present application provides a method for controlling a household appliance. The method comprises the following steps:

[0007] Acquire the user's valid palm image in the target area;

[0008] Performing edge detection and feature recognition on the acquired valid palm image to obtain an edge detection result and a feature recognition result of the valid palm image;

[0009] Determining the height of the user based on the edge detection result of the valid palm image;

[0010] Adjusting the height of the household appliance based on the height of the user;

[0011] Determining the age group of the user based on the feature recognition result of the valid palm image;

[0012] Based on the age group of the user, the parameters of the home appliance are adjusted according to the correspondence between the preset age group and the parameters; the parameters are one or more of the lighting parameters and sound parameters of the home appliance.

[0013] In one embodiment, the step of obtaining a valid palm image of the user in the target area includes the following steps:

[0014] Acquire a first image using a photographing device;

[0015] Based on the first image, determining whether there is a palm image in the target area;

[0016] When the palm image exists in the target area, acquiring a second image by using the photographing device at a preset time interval;

[0017] Based on the first image and the second image, determining whether the palm state of the user changes;

[0018] When the palm state of the user does not change, the palm image in the target area in the first image or the palm image in the target area in the second image is used as the valid palm image of the user in the target area.

[0019] In one embodiment, performing edge detection and feature recognition on the acquired valid palm image to obtain edge detection results and feature recognition results of the valid palm image includes the following steps:

[0020] Performing edge detection on the acquired valid palm image to obtain a palm contour of the valid palm image;

[0021] Based on the palm contour of the valid palm image, palmprint feature recognition is performed on the acquired valid palm image to obtain the palmprint feature of the valid palm image.

[0022] In one embodiment, the palm contour of the valid palm image is used to perform palmprint feature recognition on the acquired valid palm image to obtain the palmprint feature of the valid palm image, comprising the following steps:

[0023] Based on the palm contour of the valid palm image, acquiring the convex hull and convex defects of the valid palm image;

[0024] The palmprint feature recognition is performed on the acquired effective palm image through the convex hull and the convex defect of the effective palm image to obtain the palmprint feature of the effective palm image.

[0025] In one of the embodiments, after edge detection and feature recognition are performed on the acquired valid palm image to obtain the edge detection result and feature recognition result of the valid palm image, the following steps are also included:

[0026] Based on the feature recognition result of the valid palm image and the pre-stored historical feature recognition results, determining whether the user corresponding to the valid palm image is a known user;

[0027] When the user corresponding to the valid palm image is the known user, the edge detection result and the historical feature recognition result corresponding to the known user are used to adjust the edge detection result and the feature recognition result of the valid palm image.

[0028] In one embodiment, the determining whether the user corresponding to the valid palm image is a known user based on the feature recognition result of the valid palm image and the pre-stored historical feature recognition results comprises the following steps:

[0029] Based on the feature recognition result of the valid palm image and the pre-stored historical feature recognition results, determining the number of matches between the key feature points in the feature recognition result of the valid palm image and the pre-stored historical feature recognition results;

[0030] When the number of matches between the feature recognition result of the valid palm image and the key feature points in the pre-stored historical feature recognition result is greater than or equal to a preset matching number threshold, determining that the user corresponding to the valid palm image is the known user;

[0031] When the number of matches between the feature recognition result of the valid palm image and the key feature points in the pre-stored historical feature recognition result is less than the preset matching number threshold, it is determined that the user corresponding to the valid palm image is not the known user.

[0032] In one embodiment, determining the height of the user based on the edge detection result of the valid palm image comprises the following steps:

[0033] Based on the palm contour of the valid palm image, obtaining the circumference length of the palm in the valid palm image;

[0034] Determining the gender of the user based on the circumference of the palm;

[0035] The height of the user is determined based on the gender of the user and the circumference of the palm.

[0036] In one embodiment, determining the age group of the user based on the feature recognition result of the valid palm image comprises the following steps:

[0037] Determining geometric features of palm lines of the palm based on the palm print features of the valid palm image;

[0038] Performing a scale analysis on the palm lines of the palm according to the geometric features of the palm lines of the palm, and obtaining a scale analysis result of the palm lines of the palm;

[0039] Based on the scale analysis result of the palm lines of the palm, the age group of the user is determined.

[0040] In a second aspect, the present application also provides a control device for household electrical appliances. The device comprises:

[0041] An acquisition module is used to acquire a valid palm image of the user in the target area;

[0042] A detection module, used to perform edge detection and feature recognition on the acquired valid palm image to obtain an edge detection result and a feature recognition result of the valid palm image;

[0043] A height determination module, used to determine the height of the user based on the edge detection result of the valid palm image;

[0044] A height adjustment module, used for adjusting the height of the household appliance based on the height of the user;

[0045] An age determination module, used to determine the age group of the user based on the feature recognition result of the valid palm image;

[0046] And a parameter adjustment module, which is used to adjust the parameters of the home appliance based on the age group of the user and according to the corresponding relationship between the preset age group and the parameter; the parameter is one or more of the lighting parameters and sound parameters of the home appliance.

[0047] In a third aspect, the present application further provides a range hood. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the control method of the household appliance described in the first aspect when executing the computer program.

[0048] The control method, device and range hood of the household appliance described above obtain the effective palm image of the user in the target area, and perform edge detection and feature recognition on the obtained effective palm image to obtain the edge detection result and feature recognition result of the effective palm image, and then determine the height of the user based on the edge detection result of the effective palm image, and adjust the height of the household appliance based on the height of the user. It determines the height of the user by establishing a connection between the edge of the palm and the height, and adjusts the height of the household appliance according to the height of the user. In addition, it performs feature recognition on the palm, obtains the age group of the user based on the palm feature recognition result, and adjusts the parameters of the household appliance according to the age group of the user, thereby obtaining the user's information through the effective palm image, and providing customized services based on the user's information, solving the problem that the existing range hood control method cannot provide customized services according to the actual situation of the user.

[0049] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0051] Figure 1 A hardware structure block diagram of a terminal of a method for controlling a household appliance provided in an embodiment of the present application;

[0052] Figure 2 A flowchart of a method for controlling a household appliance provided in one embodiment of the present application;

[0053] Figure 3 A flowchart of a method for controlling a household appliance provided in a preferred embodiment of the present application;

[0054] Figure 4 This is a structural block diagram of a control device for household appliances provided in one embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0056] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0057] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a hardware structure block diagram of a terminal of the method for controlling household appliances of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0058] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the control method of the household appliance in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0059] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0060] In this embodiment, a method for controlling a household appliance is provided. Figure 2 is a flow chart of the control method of the household appliance of this embodiment. Figure 2 As shown, the process includes the following steps:

[0061] Step S210: Acquire a valid palm image of the user in the target area.

[0062] The above-mentioned target area can be an area set according to specific needs, and is a specific area where it is necessary to determine whether a palm is present. This target area can be an area in the field of view of the camera, and specifically can be an area of ​​a rectangular frame or other shapes in the image captured by the camera. The above-mentioned valid palm image can be a palm image that is located in the target area and meets the requirements of clarity and completeness. The above-mentioned acquisition of the valid palm image of the user in the target area can be the acquisition of the valid palm image of the user in the target area by using a photographing device. The above-mentioned photographing device can be a photographing device installed on or outside a home appliance. The above-mentioned photographing device can be one or more cameras.

[0063] Specifically, the above-mentioned acquisition of the valid palm image of the user in the target area can utilize a photographing device to capture a first image and a second image in which a palm image exists in the target area, and determine the palm image in the target area in the first image or the palm image in the target area in the second image as the valid palm image of the user in the target area.

[0064] This step obtains the valid palm image of the user in the target area, so as to perform edge detection and feature recognition based on the obtained valid palm image, obtain the edge detection result and feature recognition result of the valid palm image, and then determine the user information based on the edge detection result and feature recognition result of the valid palm image.

[0065] Step S220, edge detection and feature recognition are performed on the acquired valid palm image to obtain edge detection results and feature recognition results of the valid palm image.

[0066] The above-mentioned edge detection result may be a palm contour. The above-mentioned feature recognition result may be a palm print feature and a key feature point of the palm. The above-mentioned palm print feature may include a palm print line feature and a palm print feature point. Among them, the above-mentioned palm print line feature may be the position of the main line and the secondary line of the palm print line, as well as the geometric features of the palm print line, as well as the starting point, end point, bifurcation point, interruption point and other features of the main line, and the distribution, density and shape and other features of the secondary line.

[0067] Step S230: determining the height of the user based on the edge detection result of the valid palm image.

[0068] Among them, the above-mentioned determination of the user's height based on the edge detection result of the effective palm image can be to determine the circumference of the user's palm according to the edge detection result of the effective palm image, and then determine the user's height according to the circumference of the user's palm.

[0069] Step S240: adjusting the height of the home appliance based on the height of the user.

[0070] The height of the home appliance can be adjusted based on the height of the user, according to a preset adjustment method, to a position that matches the height of the user. For example, the height of the home appliance can be adjusted based on the height of the user, according to preset height and home appliance height parameters, to a position that matches the height of the user.

[0071] For example, the hanging height of the range hood is raised or lowered according to the height of the user. Specifically, if the standard hanging height of the range hood is H1, the standard height of the user corresponding to the standard hanging height of the range hood is LI.

[0072] If the user's height L is greater than the standard height LI, the range hood can be raised. The calculation formula for the raised height H is:

[0073]

[0074] If the user's height L is less than the standard height LI, the range hood can be lowered. The calculation formula for the lowered height H is:

[0075]

[0076] Preferably, different standard heights of users can be set according to the gender of the users, and then the hanging height of the range hood can be raised or lowered according to the actual height of the users and the standard height of the users.

[0077] Step S250, determining the age group of the user based on the feature recognition result of the valid palm image.

[0078] As age increases, palm wrinkles increase, and palm lines become twisted and deepened. Based on this, the palm print features of the user's palm can be determined based on the feature recognition results of the effective palm image, and then the user's age group can be determined based on the palm features of the user's palm. Specifically, the corresponding relationship between the palm print features and the age group can be pre-set, and the age group corresponding to the palm print features can be selected as the user's age group based on the palm print features. The user's age group can also be predicted through a neural network model, specifically, the historical palm print features and the age corresponding to the palm print features can be used as input data, the neural network model is trained, and a complete neural network model is obtained. The feature recognition results of the effective palm image are input into the complete neural network model, and the user's age is output to determine the user's age group.

[0079] Step S260, based on the age group of the user, adjust the parameters of the home appliance according to the preset correspondence between the age group and the parameters; the parameters are one or more of the lighting parameters and sound parameters of the home appliance.

[0080] The lighting parameters may be parameters of the brightness of the lighting lamp or control parameters of the atmosphere lamp. The sound parameters may be the volume of the sound. The adjusting of the parameters of the home appliance based on the age group of the user according to the preset correspondence between the age group and the parameters may be based on the age group of the user according to the preset correspondence between the age group and the parameters, adjusting one or more of the parameters of turning on and off the atmosphere lamp, the brightness parameters of the lighting or the volume parameters of the sound.

[0081] In the above steps S210 to S260, by acquiring the valid palm image of the user in the target area, and performing edge detection and feature recognition on the acquired valid palm image, the edge detection result and feature recognition result of the valid palm image are obtained, and then the height of the user is determined based on the edge detection result of the valid palm image, and the height of the home appliance is adjusted based on the height of the user. It determines the height of the user by establishing a connection between the edge of the palm and the height, and adjusts the height of the home appliance according to the height of the user. In addition, it performs feature recognition on the palm, and obtains the age group of the user according to the palm feature recognition result, and adjusts the parameters of the home appliance according to the age group of the user, so as to obtain the user's information through the valid palm image, and provide customized services according to the user's information, thereby solving the problem that the existing range hood control method cannot provide customized services according to the actual situation of the user.

[0082] In one embodiment, based on step S210, obtaining a valid palm image of the user in the target area includes:

[0083] Step S211: Acquire a first image using a photographing device.

[0084] Step S212: based on the first image, determine whether there is a palm image in the target area.

[0085] It should be noted that in this step, if there is no palm image in the target area, the first image at this time is deleted, and the first image is re-acquired by the shooting device, and the determination of whether there is a palm image in the target area is continued until it is determined that there is a palm image in the target area through the captured first image. In this first image, there is a palm image in the target area in the image.

[0086] Step S213: when there is a palm image in the target area, a second image is acquired by using a photographing device at a preset time interval.

[0087] The above-mentioned preset time interval can be the shooting interval between the first image and the second image, which can be determined according to the specific situation. It should be noted that, because it is necessary to determine whether the state of the palm has changed within the time interval between the shooting of the first image and the second image through the first image and the second image, the preset time interval cannot be a longer time length. If the preset time interval is too long, the captured second image will be invalid because the interval between the first image and the preset time interval is too long. The preset time interval cannot be set to a particularly short time length. If the preset time interval is too short, it will be impossible to determine whether the palm state has changed through the first image and the second image. For example, the preset time interval can be set to 1S. This step obtains the second image by setting a suitable preset time interval, and determines whether the user's palm state has changed according to the first image and the second image, so as to facilitate judging whether there is a misjudgment, whether the user performs other operations, or whether the user has an erroneous operation of staying in the target area for too short a time according to the palm state information.

[0088] Step S214: determining whether the state of the user's palm has changed based on the first image and the second image.

[0089] In this step, the palm state may be information such as the position of the fingers on the palm and the posture of the palm. The above-mentioned determination of whether the palm state of the user has changed based on the first image and the second image may be performed by using a machine learning model or image segmentation technology, such as threshold segmentation, edge detection, contour detection, etc., to separate the palm area from the first image and the second image respectively, and then perform key point detection or feature extraction on the palm area images of the first image and the second image respectively, and then compare the feature points or features between the palm area image of the first image and the palm area image of the second image to analyze whether the position of the fingers or the posture of the palm in the two images has changed. When the position of the fingers or the posture of the palm in the two images has changed, it is determined that the palm state of the user has changed; when the position of the fingers and the posture of the palm in the two images have not changed, it is determined that the palm state of the user has not changed.

[0090] Step S215, when the state of the user's palm has not changed, the palm image in the target area in the first image or the palm image in the target area in the second image is used as a valid palm image of the user in the target area.

[0091] In the above steps S211 to S215, the first image and the second image are acquired by the shooting device, and whether the state of the user's palm has changed is determined based on the first image and the second image. When the state of the user's palm has not changed, the palm image in the target area of ​​the first image or the palm image in the target area of ​​the second image is used as the valid palm image of the user in the target area. By acquiring the valid palm image of the user in the target area, it is convenient to perform edge detection and feature recognition based on the acquired valid palm image, obtain the edge detection result and feature recognition result of the valid palm image, and then determine the user information based on the edge detection result and feature recognition result of the valid palm image.

[0092] Furthermore, in one embodiment, step S220, edge detection and feature recognition are performed on the acquired valid palm image to obtain edge detection results and feature recognition results of the valid palm image, including:

[0093] Step S222: performing edge detection on the acquired valid palm image to obtain the palm contour of the valid palm image.

[0094] Among them, the edge detection of the acquired effective palm image to obtain the palm contour of the effective palm image can be performed by using a preset method to perform edge detection on the acquired effective palm image to obtain the palm contour of the effective palm image. The preset method can be one or more of the Canny edge detection algorithm, Sobel operator edge detection, Prewitt operator edge detection, etc. The canny edge detection algorithm can also first use "cv2.RETR_EXTERNAL" to detect the external contour of the effective palm image, and then use "cv2.CHAIN_APPROX_SIMPLE" to compress redundant points in the horizontal, vertical and diagonal directions.

[0095] Preferably, before edge detection is performed on the acquired effective palm image to obtain the palm contour of the effective palm image, operations such as grayscale, denoising and contrast enhancement can be performed on the acquired effective palm image to improve the image quality, so that the results of subsequent edge detection are more accurate, the palm prints of the palm are clearer, and palm print feature recognition of the acquired effective palm image is facilitated.

[0096] Step S224, based on the palm contour of the valid palm image, palm print feature recognition is performed on the acquired valid palm image to obtain the palm print feature of the valid palm image.

[0097] Based on the palm contour of the effective palm image, palmprint feature recognition is performed on the acquired effective palm image to obtain the palmprint features of the effective palm image. The convex hull and convex defects of the effective palm image can be obtained through the palm contour of the effective palm image, and then the palmprint features of the effective palm image are obtained through the convex hull and convex defects of the effective palm image.

[0098] Preferably, the palm contour based on the effective palm image is used to perform palm print feature recognition on the acquired effective palm image to obtain the palm print features of the effective palm image. It can also be that the main lines of the palm prints of the effective palm image are detected by an edge detection algorithm, such as Canny edge detection or Hough transform. Then, a preset feature point extraction method, such as SIFT (Scale-Invariant Feature Transform, a feature descriptor based on scale invariance) method, SURF (Speeded Up Robust Features, a fast version of SIFT) method, Chain Code method or Hough Transform method, etc., is used to extract key feature points of the effective palm image. The above key feature points can be bifurcation points, endpoints, etc., and a texture extraction method, such as local binary method or Gabor filter, etc., is used to extract the texture features of the palm prints of the effective palm image, and then the geometric features of the palm print lines of the effective palm image are determined through the distance and angle between the key feature points of the effective palm image.

[0099] The above steps S222 to S224, by obtaining the palm contour of the effective palm image and the palm print features of the effective palm image, facilitate the subsequent determination of the user's height based on the palm contour, and determine the user's age group based on the palm print features of the effective palm image, and then, provide customized services based on the user's height and age group, thereby solving the problem that the existing range hood control method cannot provide customized services based on the user's actual situation.

[0100] Specifically, in one embodiment, the above step S224, based on the palm contour of the valid palm image, performs palmprint feature recognition on the acquired valid palm image to obtain the palmprint features of the valid palm image, includes:

[0101] Step S2242, based on the palm contour of the valid palm image, obtain the convex hull and convex defect of the valid palm image.

[0102] The convex hull is the smallest convex polygon constructed by the palm contour point set of the effective palm image, that is, the smallest part that contains the palm contour point set of the effective palm image and has no depression. The convex defect can be a concave area formed between the convex hull and the palm contour point set of the effective palm image. The convex hull and convex defects of the effective palm image are obtained based on the palm contour of the effective palm image. The convex hull and convex defects of the effective palm image can be obtained by using a preset method through the palm contour of the effective palm image. Specifically, the convex hull of the effective palm image can be obtained by using the "convexHull" function of OpenCV based on the palm contour of the effective palm image, and then the convex defects of the effective palm image can be obtained by using the "convexityDefects" function of OpenCV. It can also be based on the palm contour of the effective palm image, according to the neural network model, to obtain the convex hull and convex defects of the effective palm image.

[0103] In one embodiment, the calculation of the convex hull of the valid palm image can be implemented by "hull = cv2.convexHull (hand_contour, returnPoints = False)", and the calculation of the convexity defects of the valid palm image can be implemented by "defects = cv2.convexityDefects (hand_contour, hull)".

[0104] Step S2244, performing palmprint feature recognition on the acquired valid palm image through the convex hull and convex defect of the valid palm image to obtain the palmprint features of the valid palm image.

[0105] The specific process of obtaining the palm print features of a valid palm image may include:

[0106] The first step is to initialize an empty list to store feature points. The specific process is as follows:

[0107] "finger_tips=[]

[0108] finger_valleys = []"

[0109] The second step is to extract the starting point, end point and farthest point of the convex defect. The specific process is as follows:

[0110] “if defects is not None:

[0111] for iin range(defects.shape[0]):

[0112] s,e,f,d=defects[i,0]

[0113] start=tuple(hand_contour[s][0])

[0114] end=tuple(hand_contour[e][0])

[0115] far=tuple(hand_contour[f][0])

[0116] finger_tips.append(start)

[0117] finger_valleys.append(far)"

[0118] The third step is to obtain the starting point and the farthest point of the convex defect. The specific process is as follows:

[0119] "cv2.circle(frame,start,5,(0,255,0),-1)

[0120] cv2.circle(frame,far,5,(0,0,255),-1)”

[0121] Specifically, the convex defect information may be used to locate key feature points of the effective palm image, such as intersection points or end points of lines, and then the feature vectors of the palm lines of the effective palm image may be constructed based on the positions and directions of the key feature points.

[0122] In the above steps S2242 to S2244, the convex hull and convex defect of the effective palm image are obtained based on the palm contour of the effective palm image, and then the palm print features of the effective palm image are obtained according to the convex hull and convex defect of the effective palm image. The acquisition of the palm print features of the effective palm image facilitates the subsequent determination of the user's age group according to the palm print features of the effective palm image, and then, customized services are provided according to the user's age group, which solves the problem that the existing range hood control method cannot provide customized services according to the actual situation of the user.

[0123] Furthermore, in one embodiment, after step S220, the method further includes:

[0124] Step S270, based on the feature recognition result of the valid palm image and the pre-stored historical feature recognition results, it is determined whether the user corresponding to the valid palm image is a known user.

[0125] The above-mentioned pre-stored historical feature recognition results may be historical feature recognition results corresponding to historical users. The above-mentioned feature recognition results based on the valid palm image and the pre-stored historical feature recognition results may be used to determine whether the user corresponding to the valid palm image is a known user. The feature recognition results based on the valid palm image and the pre-stored historical feature recognition results may be compared with the pre-stored historical feature recognition results. When the feature recognition results of the valid palm image match the pre-stored historical feature recognition results, it is determined that the user corresponding to the valid palm image is a known user. When the feature recognition results of the valid palm image do not match the pre-stored historical feature recognition results, it is determined that the user corresponding to the valid palm image is not a known user. Whether the feature recognition result of the above-mentioned valid palm image matches the pre-stored historical feature recognition result can be determined based on the number of matches between the key feature points in the feature recognition result of the valid palm image and the key feature points in the historical feature recognition result. When the number of matches between the feature recognition result of the valid palm image and the key feature points in the pre-stored historical feature recognition result is greater than or equal to a preset matching number threshold, it is determined that the feature recognition result of the valid palm image matches the pre-stored historical feature recognition result. When the number of matches between the feature recognition result of the valid palm image and the key feature points in the pre-stored historical feature recognition result is less than the preset matching number threshold, it is determined that the feature recognition result of the valid palm image does not match the pre-stored historical feature recognition result. The above-mentioned key feature points can be key feature points at the fingertips, key feature points at the base of the fingers, and key feature points at the wrists.

[0126] Step S280: When the user corresponding to the valid palm image is a known user, the edge detection result and the historical feature recognition result corresponding to the known user are used to adjust the edge detection result and the feature recognition result of the valid palm image.

[0127] In this step, when the user corresponding to the valid palm image is a known user, the key feature points in the valid palm image are divided into feature points that can match the historical recognition results and feature points that cannot match the historical recognition results according to the feature recognition results of the valid palm image and the matching of the pre-stored historical feature recognition results. The above-mentioned use of the edge detection results and historical feature recognition results corresponding to the known user to adjust the edge detection results and feature recognition results of the valid palm image can be based on the feature points that cannot match the historical recognition results among the key feature points in the valid palm image, averaging the positions of the feature points that cannot match the historical recognition results and the closest feature points in the known user corresponding to the valid palm image, using the averaged position as the position of the feature points that cannot match the historical recognition results, updating the positions of the key feature points in the valid palm image, and then adjusting the edge detection results and feature recognition results of the valid palm image based on the updated positions of the key feature points in the valid palm image.

[0128] In the above steps S270 to S280, whether the user corresponding to the valid palm image is a known user is determined based on the feature recognition result of the valid palm image and the pre-stored historical feature recognition results. When the user corresponding to the valid palm image is a known user, the edge detection result and the feature recognition result of the valid palm image are adjusted using the edge detection result and the historical feature recognition result corresponding to the known user, so that the edge detection result and the feature recognition result of the valid palm image are more accurate, which is convenient for the subsequent determination of the user's height according to the palm contour, and the determination of the user's age group according to the palm print features of the valid palm image. Furthermore, customized services are provided according to the user's height and age group, which solves the problem that the existing range hood control method cannot provide customized services according to the actual situation of the user.

[0129] In addition, in one embodiment, the above step S270, based on the feature recognition result of the valid palm image and the pre-stored historical feature recognition result, determines whether the user corresponding to the valid palm image is a known user, including:

[0130] Step S272, based on the feature recognition result of the valid palm image and the pre-stored historical feature recognition results, determine the number of matches between the key feature points in the feature recognition result of the valid palm image and the pre-stored historical feature recognition results.

[0131] The above-mentioned determination of the number of matches between the key feature points in the feature recognition result of the valid palm image and the pre-stored historical feature recognition results can be performed by using a preset feature point matching method to determine the number of matches between the key feature points in the feature recognition result of the valid palm image and the pre-stored historical feature recognition results. Among them, the above-mentioned preset feature point matching method can be one or more feature point matching methods such as SIFT and SURF. It should be noted that the above-mentioned preset feature point matching method is not specifically limited in this embodiment, as long as the preset feature point matching method can be used to determine the number of matches between the key feature points in the feature recognition result of the valid palm image and the pre-stored historical feature recognition results.

[0132] Step S274: when the number of matches between the feature recognition result of the valid palm image and the key feature points in the pre-stored historical feature recognition results is greater than or equal to a preset matching number threshold, the user corresponding to the valid palm image is determined to be a known user.

[0133] The above preset matching number threshold can be specifically set according to specific circumstances, and this embodiment does not make any specific limitation here.

[0134] Step S276: When the number of matches between the feature recognition result of the valid palm image and the key feature points in the pre-stored historical feature recognition results is less than a preset matching number threshold, it is determined that the user corresponding to the valid palm image is not a known user.

[0135] In the above steps S272 to S276, based on the feature recognition result of the valid palm image and the pre-stored historical feature recognition result, the number of matches of key feature points in the feature recognition result of the valid palm image and the pre-stored historical feature recognition result is determined, and then according to the number of matches of key feature points in the feature recognition result of the valid palm image and the pre-stored historical feature recognition result, it is determined whether the user corresponding to the valid palm image is a known user. By determining whether the user is a known user, the edge detection result and the historical feature recognition result corresponding to the known user can be used to adjust the edge detection result and the feature recognition result of the valid palm image when the user is determined to be a known user.

[0136] In one embodiment, based on step S230, determining the height of the user based on the edge detection result of the valid palm image includes:

[0137] Step S232, based on the palm contour of the valid palm image, obtain the circumference length of the palm in the valid palm image.

[0138] In this step, the palm contour based on the valid palm image can be used to obtain the circumference of the palm in the valid palm image. The palm contour of the valid palm image can be approximated based on the palm contour of the valid palm image. Specifically, the palm contour of the valid palm image can be approximated using the "vc2.approxPolyDP()" function in OpenCV, and then, based on the approximated palm contour, the circumference of the palm in the valid palm image can be obtained. Specifically, the circumference of the palm in the valid palm image can be calculated using "perimeter=vc2.arcLength(hand_contour, true)" in OpenCV.

[0139] Step S234, determining the gender of the user based on the circumference of the palm.

[0140] In general, the palm of an adult male is usually larger than that of an adult female. The palm of an adult is larger than that of a child. Based on this, a first threshold and a second threshold can be set. Among them, the first threshold is greater than the second threshold. The first threshold can be used to distinguish the circumference of a male palm from the circumference of a female palm, and the second threshold can be used to distinguish the circumference of an adult palm from the circumference of a child's palm. When the circumference of the palm is greater than the first threshold, the judgment result is more inclined to male, and the user's gender is determined to be male. When the circumference of the palm is less than the first threshold, the judgment result is more inclined to a child, and the user can be determined to be a child. An alarm device can be set for the child. When the user is determined to be a child, the alarm device is activated and the alarm starts. When the alarm duration reaches the preset time length, and during this period, no second user (adult) unlocks the alarm, the fan will be automatically turned off and the anti-pinch and anti-head functions will be turned on. If the circumference of the palm is less than or equal to the first threshold, and greater than or equal to the second threshold, the judgment result is more inclined to female, and the user's gender is determined to be female.

[0141] Step S236, determining the user's height based on the user's gender and the circumference of the palm.

[0142] Specifically, based on the user's gender and the circumference of the palm, the calculation process for determining the user's height is as follows:

[0143] If the user is determined to be male, the relationship between the circumference of the palm and the user's height is:

[0144] Circumference of the palm × 0.8 = User's height × 0.56 - 100 ÷ 6.5

[0145] If the user is determined to be a female, the relationship between the circumference of the palm and the user's height is:

[0146] Circumference of palm × 0.8 = user's × 0.49 - 100 ÷ 8

[0147] Based on this, the user's height can be determined based on the user's gender and the circumference of the palm.

[0148] In the above steps S232 to S236, the circumference of the palm in the valid palm image is obtained based on the palm contour of the valid palm image, the gender of the user is determined based on the circumference of the palm, and the height of the user is determined based on the gender of the user and the circumference of the palm, and customized services are provided according to the height of the user.

[0149] In addition, in one embodiment, the above step S250, based on the feature recognition result of the valid palm image, determines the age group of the user, including:

[0150] Step S252: determining the geometric features of the palm lines based on the feature recognition result of the valid palm image.

[0151] The geometric features of the palm lines of the palm may be the length of the palm lines, the width of the lines, the curvature of the lines, the relative position of the lines, the distance between the lines, the angle between the lines, etc.

[0152] Step S254, performing scale analysis on the palm lines according to the geometric features of the palm lines, and obtaining scale analysis results of the palm lines.

[0153] The scale analysis of the palm lines may be an analysis of the depth, length, width, curvature, etc. of the lines. The scale analysis result of the palm lines may be a depth analysis result, a length analysis result, a width analysis result, a curvature analysis result, etc. of the lines of the user.

[0154] Step S256, determining the age group of the user based on the scale analysis result of the palm lines.

[0155] The above-mentioned determination of the user's age group based on the scale analysis result of the palm lines can be performed by presetting the corresponding relationship between the scale analysis result of the palm lines and the age group, and selecting the age group corresponding to the scale analysis result of the palm lines as the user's age group according to the scale analysis result of the palm lines. It can also be performed by predicting the user's age group through a neural network model, specifically, the scale analysis result of the palm lines of the historical palms and the age corresponding to the scale analysis result of the palm lines of the palms can be used as input data, the neural network model can be trained to obtain a complete neural network model, the scale analysis result of the palm lines of the valid palm image can be input into the complete neural network model, the user's age can be output, and the user's age group can be determined.

[0156] In the above steps S252 to S256, the geometric features of the palm lines are determined based on the feature recognition results of the valid palm image, and the scale analysis results of the palm lines are obtained based on the geometric features of the palm lines. Then, based on the scale analysis results of the palm lines, the age group of the user is determined. By determining the age group of the user, customized services are provided according to the age group of the user.

[0157] The present embodiment is described and illustrated below through preferred embodiments.

[0158] Figure 3 1 is a flow chart of a method for controlling a household appliance provided by a preferred embodiment of the present application. Figure 3 As shown, the control method of the household appliance includes the following steps:

[0159] Step S301, initializing the camera of the shooting device;

[0160] Step S302, checking whether the camera of the shooting device is turned on, if the camera is not turned on, executing step S301; if the camera is turned on, executing step S303;

[0161] Step S303, using a photographing device to photograph an image to obtain a first image;

[0162] Step S304, identifying the first image to determine whether there is a palm image in the target area; if there is no palm image in the target area, executing step S301; if there is a palm image in the target area, executing step S305;

[0163] Step S305, acquiring a second image using a photographing device at a preset time interval;

[0164] Step S306, judging whether the state of the user's palm changes during the interval between the first image and the second image according to the first image and the second image; if the state of the user's palm changes, executing step S301; if the state of the user's palm does not change, executing step S307;

[0165] Step S307, determining the palm image in the target area in the first image or the palm image in the target area in the second image as a valid palm image of the user in the target area;

[0166] Step S308, performing edge detection and feature recognition on the acquired valid palm image to obtain edge detection results and feature recognition results of the valid palm image;

[0167] Step S309, determining the height of the user based on the edge detection result of the valid palm image;

[0168] Step S310, adjusting the height of the home appliance based on the height of the user;

[0169] Step S311, determining the age group of the user based on the feature recognition result of the valid palm image;

[0170] Step S312: Based on the age group of the user, the parameters of the home appliance are adjusted according to the corresponding relationship between the preset age group and the parameters.

[0171] In the above steps S301 to S312, by acquiring the valid palm image of the user in the target area, and performing edge detection and feature recognition on the acquired valid palm image, the edge detection result and feature recognition result of the valid palm image are obtained, and then the height of the user is determined based on the edge detection result of the valid palm image, and the height of the home appliance is adjusted based on the height of the user. It determines the height of the user by establishing a connection between the edge of the palm and the height, and adjusts the height of the home appliance according to the height of the user. In addition, it performs feature recognition on the palm, and obtains the age group of the user according to the palm feature recognition result, and adjusts the parameters of the home appliance according to the age group of the user, so as to obtain the user's information through the valid palm image, and provide customized services according to the user's information, thereby solving the problem that the existing range hood control method cannot provide customized services according to the actual situation of the user.

[0172] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0173] Based on the same inventive concept, a control device for household appliances is also provided in this embodiment, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can be a combination of software and / or hardware that implements predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0174] In one embodiment, Figure 4 is a structural block diagram of a control device for household appliances provided in an embodiment of the present application, such as Figure 4 As shown, the control device of the household appliance comprises:

[0175] An acquisition module 41 is used to acquire a valid palm image of the user in the target area;

[0176] A detection module 42 is used to perform edge detection and feature recognition on the acquired valid palm image to obtain edge detection results and feature recognition results of the valid palm image;

[0177] A height determination module 43, used to determine the height of the user based on the edge detection result of the valid palm image;

[0178] A height adjustment module 44, used to adjust the height of the home appliance based on the height of the user;

[0179] An age determination module 45, for determining the age group of the user based on the feature recognition result of the valid palm image;

[0180] And a parameter adjustment module 46 is used to adjust the parameters of the home appliance based on the user's age group according to the preset correspondence between the age group and the parameter; the parameter is one or more of the lighting parameters and sound parameters of the home appliance.

[0181] The control device for the above-mentioned household appliance obtains the effective palm image of the user in the target area, and performs edge detection and feature recognition on the obtained effective palm image to obtain the edge detection result and feature recognition result of the effective palm image, and then determines the height of the user according to the edge detection result of the effective palm image, and adjusts the height of the household appliance based on the height of the user. It determines the height of the user by establishing a connection between the edge of the palm and the height, and adjusts the height of the household appliance according to the height of the user. In addition, it performs feature recognition on the palm, obtains the age group of the user according to the palm feature recognition result, and adjusts the parameters of the household appliance according to the age group of the user, thereby obtaining the user's information through the effective palm image, and providing customized services based on the user's information, solving the problem that the existing range hood control method cannot provide customized services according to the actual situation of the user.

[0182] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0183] In one embodiment, a range hood is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, any one of the control methods for household appliances in the above embodiments is implemented.

[0184] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0185] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited thereto.

[0186] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0187] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for controlling a household appliance, characterized in that: The method comprises: Acquire the user's valid palm image in the target area; Performing edge detection and feature recognition on the acquired valid palm image to obtain an edge detection result and a feature recognition result of the valid palm image; Determining the height of the user based on the edge detection result of the valid palm image; Adjusting the height of the household appliance based on the height of the user; Determining the age group of the user based on the feature recognition result of the valid palm image; Based on the age group of the user, the parameters of the home appliance are adjusted according to the correspondence between the preset age group and the parameters; the parameters are one or more of the lighting parameters and sound parameters of the home appliance.

2. The control method of household electrical appliances according to claim 1, characterized in that: The step of obtaining a valid palm image of the user in the target area includes: Acquire a first image using a photographing device; Based on the first image, determining whether there is a palm image in the target area; When the palm image exists in the target area, acquiring a second image by using the photographing device at a preset time interval; Based on the first image and the second image, determining whether the palm state of the user changes; When the palm state of the user does not change, the palm image in the target area in the first image or the palm image in the target area in the second image is used as the valid palm image of the user in the target area.

3. The control method of household electrical appliances according to claim 1, characterized in that: The performing edge detection and feature recognition on the acquired valid palm image to obtain edge detection results and feature recognition results of the valid palm image includes: Performing edge detection on the acquired valid palm image to obtain a palm contour of the valid palm image; Based on the palm contour of the valid palm image, palmprint feature recognition is performed on the acquired valid palm image to obtain the palmprint feature of the valid palm image.

4. The control method of household electrical appliances according to claim 3, characterized in that: The palm contour of the valid palm image is based on the palm print feature recognition of the acquired valid palm image to obtain the palm print feature of the valid palm image, including: Based on the palm contour of the valid palm image, acquiring the convex hull and convex defects of the valid palm image; The palmprint feature recognition is performed on the acquired effective palm image through the convex hull and the convex defect of the effective palm image to obtain the palmprint feature of the effective palm image.

5. The control method of household electrical appliances according to claim 1, characterized in that: After edge detection and feature recognition are performed on the acquired valid palm image to obtain edge detection results and feature recognition results of the valid palm image, the method further includes: Based on the feature recognition result of the valid palm image and the pre-stored historical feature recognition results, determining whether the user corresponding to the valid palm image is a known user; When the user corresponding to the valid palm image is the known user, the edge detection result and the historical feature recognition result corresponding to the known user are used to adjust the edge detection result and the feature recognition result of the valid palm image.

6. The control method of household electrical appliances according to claim 5, characterized in that: The determining, based on the feature recognition result of the valid palm image and the pre-stored historical feature recognition results, whether the user corresponding to the valid palm image is a known user includes: Based on the feature recognition result of the valid palm image and the pre-stored historical feature recognition results, determining the number of matches between the key feature points in the feature recognition result of the valid palm image and the pre-stored historical feature recognition results; When the number of matches between the feature recognition result of the valid palm image and the key feature points in the pre-stored historical feature recognition result is greater than or equal to a preset matching number threshold, determining that the user corresponding to the valid palm image is the known user; When the number of matches between the feature recognition result of the valid palm image and the key feature points in the pre-stored historical feature recognition result is less than the preset matching number threshold, it is determined that the user corresponding to the valid palm image is not the known user.

7. The control method of household electrical appliances according to claim 1, characterized in that: The step of determining the height of the user based on the edge detection result of the valid palm image comprises: Based on the palm contour of the valid palm image, obtaining the circumference length of the palm in the valid palm image; Determining the gender of the user based on the circumference of the palm; The height of the user is determined based on the gender of the user and the circumference of the palm.

8. The method for controlling a household appliance according to claim 1, characterized in that: The determining the age group of the user based on the feature recognition result of the valid palm image includes: Determining geometric features of palm lines of the palm based on the palm print features of the valid palm image; Performing a scale analysis on the palm lines of the palm according to the geometric features of the palm lines of the palm, and obtaining a scale analysis result of the palm lines of the palm; The age group of the user is determined based on the scale analysis result of the palm lines of the palm.

9. A control device for household electrical appliances, characterized in that: The device comprises: An acquisition module is used to acquire a valid palm image of the user in the target area; A detection module, used to perform edge detection and feature recognition on the acquired valid palm image to obtain an edge detection result and a feature recognition result of the valid palm image; A height determination module, used to determine the height of the user based on the edge detection result of the valid palm image; A height adjustment module, used for adjusting the height of the household appliance based on the height of the user; An age determination module, used to determine the age group of the user based on the feature recognition result of the valid palm image; And a parameter adjustment module, which is used to adjust the parameters of the home appliance based on the age group of the user and according to the corresponding relationship between the preset age group and the parameter; the parameter is one or more of the lighting parameters and sound parameters of the home appliance.

10. A smoke extractor, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method for controlling a household appliance according to any one of claims 1 to 8 are implemented.

Images