Start-stop control method, system and equipment for rotary dining table and medium
Through lidar and gesture recognition technology, users' pick-up actions are identified, and the automatic start-stop control of the rotating dining table is realized, which solves the problems of inconvenient operation and insufficient accuracy of the traditional rotating dining table, and improves the user experience and automatic control capabilities of the dining table.
Patent Information
- Application Number
- CN202410983261.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-12
AI Technical Summary
Traditional rotating dining tables require manual operation by users, which leads to users always pay attention to the rotation state of the dining table, distracting attention, and reducing the comfort and pleasure of dining. The sensing range and accuracy of the existing technology are limited, making it easy to operate incorrectly.
Lidar is used to collect point cloud data above the dining table, combine it with a pre-trained gesture recognition model to identify the user's food clipping action, and control the start and stop of the dining table through the rotation control unit to achieve automatic rotation control.
It improves the user experience, enhances the accuracy and reliability of the automated control of the dining table, reduces the rate of misoperation, and improves the convenience and comfort of dining.
Smart Images

Figure CN118939011A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent control technology, and in particular to a start-stop control method, system, device and medium for a rotating dining table. Background Art
[0002] In the catering industry, revolving tables have always been loved by consumers for their unique convenience and sociability. However, with the advancement of technology and the continuous changes in consumer demand, traditional revolving tables require users to always pay attention to the rotation status of the table and use manual operation to start and stop the revolving table, which distracts users' attention to a certain extent and reduces the comfort and pleasure of dining. Summary of the invention
[0003] In view of this, the purpose of the embodiments of the present invention is to provide a start and stop control method, system, device and medium for a rotating dining table to solve one or more technical problems existing in the prior art and provide at least one beneficial option or create conditions.
[0004] On the one hand, an embodiment of the present invention provides a start-stop control method for a rotating dining table, the method being applied to a rotating dining table, the rotating dining table comprising a dining table body, a rotating mechanism for driving the dining table body to rotate, a laser radar for collecting point cloud data in a space above the dining table body, a data processing unit, and a rotation control unit; the data processing unit is connected to the laser radar and the rotation control unit, respectively, and the rotation control unit is connected to the rotating mechanism;
[0005] The method comprises the following steps:
[0006] In response to the start-stop control command, the laser radar is triggered to scan the space above the dining table body and generate point cloud data;
[0007] After receiving the point cloud data sent by the laser radar, the data processing unit uses the pre-trained gesture recognition model to analyze and process the point cloud data to identify the user's gestures;
[0008] The data processing unit sends a corresponding control instruction to the rotation control unit based on the user's gesture action, so as to control the start and stop of the rotation mechanism through the rotation control unit.
[0009] Optionally, the data processing unit sends a corresponding control instruction to the rotation control unit based on the user's gesture action, so as to control the start and stop of the rotation mechanism through the rotation control unit, including:
[0010] Identify whether the user's gesture action is a food picking action. When it is identified that the user's gesture action is a food picking action, the data processing unit sends a stop rotation instruction to the rotation control unit to control the rotation mechanism to stop rotating through the rotation control unit.
[0011] Optionally, the data processing unit sends a corresponding control instruction to the rotation control unit based on the user's gesture action, so as to control the start and stop of the rotation mechanism through the rotation control unit, further comprising:
[0012] After the rotation control unit controls the rotation mechanism to stop rotating, when it is recognized that the user's gesture action is not a food picking action, the data processing unit sends an instruction to continue rotating to the rotation control unit, so as to control the rotation mechanism through the rotation control unit to continue driving the dining table body to rotate.
[0013] Optionally, the gesture recognition model is trained in the following manner:
[0014] Acquire a gesture data set, wherein input data of the gesture data set is a feature vector, and output data is a gesture category corresponding to the feature vector;
[0015] A deep learning model is constructed, and the deep learning model is trained using the gesture data set to obtain a gesture recognition model.
[0016] Optionally, the using a pre-trained gesture recognition model to analyze and process the point cloud data to recognize the user's gesture action includes:
[0017] Preprocessing the point cloud data, and extracting a feature vector representing the gesture from the preprocessed point cloud data;
[0018] The feature vector is input into a gesture recognition model to obtain a corresponding gesture category.
[0019] Optionally, extracting a feature vector representing the gesture from the preprocessed point cloud data includes:
[0020] One or more of trajectory features, 3D convolution features, and depth features are extracted from the preprocessed point cloud data as feature vectors.
[0021] Optionally, the method further comprises:
[0022] A correspondence between the user's gesture action and the control command is established, and the correspondence is:
[0023] When the gesture category is the action of picking up food, the corresponding control instruction is to stop the table from rotating;
[0024] When the gesture category is a non-food-picking action, the corresponding control instruction is for the dining table to continue rotating.
[0025] On the other hand, an embodiment of the present invention provides a start-stop control system for a rotating dining table, the system being applied to a rotating dining table, the rotating dining table comprising a dining table body, a rotating mechanism for driving the dining table body to rotate, a laser radar for collecting point cloud data in the space above the dining table body, a data processing unit, and a rotation control unit; the data processing unit is connected to the laser radar and the rotation control unit, respectively, and the rotation control unit is connected to the rotating mechanism;
[0026] The system comprises:
[0027] The first module is used to respond to the start-stop control command, trigger the laser radar to scan the space above the dining table body, and generate point cloud data;
[0028] The second module is used to receive the point cloud data sent by the laser radar through the data processing unit, and use the pre-trained gesture recognition model to analyze and process the point cloud data to identify the user's gesture action;
[0029] The third module is used to send corresponding control instructions to the rotation control unit based on the user's gesture action through the data processing unit, so as to control the start and stop of the rotation mechanism through the rotation control unit.
[0030] In another aspect, an embodiment of the present invention provides an electronic device, including:
[0031] at least one processor;
[0032] at least one memory for storing at least one program;
[0033] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.
[0034] On the other hand, an embodiment of the present invention provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to perform the above method.
[0035] The embodiments of the present invention include the following beneficial effects: In this embodiment, the point cloud data in the space above the dining table body is collected by laser radar; the point cloud data collected by the laser radar is received by the data processing unit, and the point cloud data is analyzed and processed by the gesture recognition model to identify the user's gesture action, and then send a corresponding control instruction to the rotation control unit to control the start and stop of the rotation mechanism through the rotation control unit. The present invention adopts laser radar and gesture recognition technology to realize the start and stop function of the rotating dining table by identifying the person's food picking action, which greatly improves the user's dining experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0037] Figure 1 It is a schematic flow chart of the steps of a method for starting and stopping a rotating dining table provided by an embodiment of the present invention;
[0038] Figure 2 is a topological diagram of a revolving dining table provided by an embodiment of the present invention;
[0039] Figure 3 It is a structural block diagram of a start-stop control system of a rotating dining table provided by an embodiment of the present invention;
[0040] Figure 4 It is a structural block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0042] It should be noted that, although the device schematic diagram is divided into modules and the flow chart shows a logical order, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flow chart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0044] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.
[0045] The block diagrams shown in the accompanying drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or in one or more hardware charging modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0046] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.
[0047] First, several technical terms involved in the present invention are explained below:
[0048] Area array lidar: also known as flash radar, is a laser radar technology different from scanning radar. Its receiving chip is a two-dimensional pixel array. As the name implies, a single "flash" can obtain information about the entire two-dimensional field of view. This technology uses a laser pulse from the transmitting end to illuminate the entire target field of view. When the laser pulse reaches the surface of the object, it is reflected back to the sensor chip, and then processed by the back end to obtain 3D point cloud information. Area array lidar avoids problems such as motion artifacts in scanning radar, and has the advantages of low cost, high frame rate, high reliability, and easier integration.
[0049] Point cloud: refers to a collection of points of target surface features, usually obtained by measuring instruments. These point sets represent the three-dimensional coordinates (XYZ) of the object surface and possible other properties, such as laser reflection intensity (Intensity) or color information (RGB). In reverse engineering, point clouds are the basis of reverse modeling and can be used to create or reconstruct three-dimensional models of objects. According to the technology and method of obtaining point clouds, they can be divided into sparse point clouds and dense point clouds. Sparse point clouds are usually obtained using a 3D coordinate measuring machine, while dense point clouds may be obtained using a 3D laser scanner or a photographic scanner.
[0050] Gesture recognition: is a topic in computer science that uses mathematical algorithms to recognize human gestures. These gestures can come from the movement of various parts of the human body, but generally refer to the movement of the face and hands. The core technology of gesture recognition usually includes steps such as gesture segmentation, gesture analysis, and gesture recognition. Users can use simple gestures to control or interact with devices, allowing computers to understand and respond to human behavior. Gesture recognition technology has applications in many fields, such as virtual reality, augmented reality, human-computer interaction, etc.
[0051] The rotating dining table in the related art is usually rotated and controlled in the following ways:
[0052] Manual rotation: Rotation is achieved by manually turning the turntable on the edge of the dining table. The disadvantage of this method is that continuous force is required during the rotation process and it is difficult to control the rotation speed.
[0053] Electric rotation: The dining table is driven to rotate by a motor. This method can achieve uniform rotation, but a stop button or switch needs to be manually operated to stop.
[0054] Millimeter-wave radar sensing: Millimeter-wave radar is used to sense human hand movements to control the start and stop of the revolving dining table. However, due to the characteristics of millimeter-wave radar, its sensing range and accuracy are limited and it is easily interfered with.
[0055] Voice control method: The start and stop of the revolving dining table is controlled by using voice recognition technology to recognize the commands issued by the user, but the recognition accuracy of this method will be greatly reduced in a noisy environment.
[0056] The revolving dining table in the related art has the following disadvantages:
[0057] The operation is inconvenient. In the prior art, manual operation is used to stop the rotation of the dining table, which requires the user to always pay attention to the rotation status of the dining table, which distracts the user's attention to a certain extent and reduces the comfort and pleasure of dining.
[0058] The sensing range and accuracy are limited. Even if there are dining tables that use millimeter-wave radar and voice control technology to achieve automatic control of rotating dining tables, their sensing range and accuracy are limited. Millimeter-wave radar may be affected by obstacles, reflections and other factors, resulting in inaccurate sensing; while voice control technology is easily affected by environmental noise, user accents and other factors, resulting in reduced recognition accuracy.
[0059] The misoperation rate is high. Due to the limitations of millimeter-wave radar and voice control technology, they may be misoperated. For example, when a user accidentally waves his arms or makes a sound while dining, the system may misjudge it as the user's action of picking up food, causing the rotating table to stop or start unexpectedly. Because millimeter-wave detection technology has no clear detection boundary, if the sensitivity is not adjusted sensitively enough, it will cause the hand to reach out to pick up food, but the hand will not be detected and the rotation will not stop; if the sensitivity is adjusted too sensitively, the action at the edge of the table may also cause the table to stop rotating.
[0060] In the rotating dining table using millimeter wave detection, there are requirements for the thickness of the table. Different tables need to adjust different sensitivities, which is not conducive to mass production of products.
[0061] In a revolving dining table that uses millimeter wave detection, the food placed on the table will affect the sensitivity and thus the detection sensitivity.
[0062] In order to solve the problems in the background technology, the present invention provides a start-stop control method, system, device and medium for a rotating dining table. Laser radar and gesture recognition technology are used to realize the start-stop function of the rotating dining table by identifying people's food-picking actions, which greatly improves the user experience.
[0063] like Figure 1 and Figure 2 As shown, Figure 1 A start-stop control method for a rotating dining table provided in an embodiment of the present invention is applied to a rotating dining table, wherein the rotating dining table includes a dining table body, a rotating mechanism for driving the dining table body to rotate, a laser radar for collecting point cloud data in the space above the dining table body, a data processing unit, and a rotation control unit; the data processing unit is connected to the laser radar and the rotation control unit respectively, and the rotation control unit is connected to the rotating mechanism;
[0064] The following is an explanation of the table body, rotating mechanism, laser radar, data processing unit, rotating control unit and power module in the rotating table:
[0065] Dining table body: It is the main part of the revolving dining table, used to place tableware and food.
[0066] Rotating mechanism: It includes motor, reducer and turntable, etc., which are used to drive the table body to rotate. The motor drives the turntable to rotate through the reducer, thereby realizing the rotation of the table.
[0067] Laser radar: It is installed at the top center of the dining table body and is used to collect point cloud data in the space above the dining table body. The laser radar adopts a planar array design and can cover a large scanning range.
[0068] Data processing unit: connected to the laser radar, used to receive the point cloud data collected by the laser radar and run the gesture recognition model to analyze and process the point cloud data. The data processing unit can be implemented with a high-performance embedded processor or microcontroller.
[0069] Rotation control unit: connected to the data processing unit, used to receive the rotation command sent by the data processing unit and control the start and stop and rotation speed of the motor. The rotation control unit can be implemented by circuits such as motor drivers or relays.
[0070] Power module: Provides power supply for the entire system, including stable operating voltage and current for components such as motors, lidar, data processing units, and rotation control units. The power module can be powered by AC or batteries.
[0071] The method comprises the following steps:
[0072] S100, in response to the start-stop control command, triggering the laser radar to scan the space above the dining table body and generate point cloud data;
[0073] S200, after receiving the point cloud data sent by the laser radar, the data processing unit uses a pre-trained gesture recognition model to analyze and process the point cloud data to recognize the user's gesture action;
[0074] S300: The data processing unit sends a corresponding control instruction to the rotation control unit based on the user's gesture action, so as to control the start and stop of the rotation mechanism through the rotation control unit.
[0075] Specifically, the start-stop control method of the rotating dining table of the present invention includes the following implementation steps:
[0076] Setting up LiDAR: Setting up an area array LiDAR on the top of the revolving dining table. This LiDAR can scan the space within a certain range above the dining table and generate corresponding point cloud data.
[0077] Collecting data: The LiDAR collects point cloud data in the space above the dining table in real time and transmits the data to the data processing unit.
[0078] Gesture recognition: After receiving the point cloud data, the data processing unit uses the gesture recognition model to analyze and process the point cloud data to identify the user's action of picking up food. The gesture recognition model includes but is not limited to a gesture recognition model based on deep learning. The gesture recognition model is obtained by training a large amount of gesture data and can accurately identify the user's action of picking up food.
[0079] Control rotation: When the gesture recognition model recognizes the user's action of picking up food, the data processing unit sends a command to the rotation control unit to stop rotating. After receiving the command, the rotation control unit controls the motor to stop rotating, realizing the function of stopping when picking up food.
[0080] Continue to rotate: When the user completes the action of picking up food and puts down the tableware, the laser radar continues to collect data, and the data processing unit re-performs gesture recognition. If the action of picking up food is not recognized, the data processing unit sends a command to the rotation control unit to continue rotating, and the rotation control unit controls the motor to continue rotating the table.
[0081] In some embodiments, the data processing unit sends a corresponding control instruction to the rotation control unit based on the user's gesture action, so as to control the start and stop of the rotation mechanism through the rotation control unit, including:
[0082] Identify whether the user's gesture action is a food picking action. When it is identified that the user's gesture action is a food picking action, the data processing unit sends a stop rotation instruction to the rotation control unit to control the rotation mechanism to stop rotating through the rotation control unit.
[0083] In some embodiments, the data processing unit sends a corresponding control instruction to the rotation control unit based on the user's gesture action, so as to control the start and stop of the rotation mechanism through the rotation control unit, further comprising:
[0084] After the rotation control unit controls the rotation mechanism to stop rotating, when it is recognized that the user's gesture action is not a food picking action, the data processing unit sends an instruction to continue rotating to the rotation control unit, so as to control the rotation mechanism through the rotation control unit to continue driving the dining table body to rotate.
[0085] In some embodiments, the gesture recognition model is trained in the following manner:
[0086] S210, obtaining a gesture data set, wherein input data of the gesture data set is a feature vector, and output data is a gesture category corresponding to the feature vector;
[0087] S220, constructing a deep learning model, and training the deep learning model using the gesture data set to obtain a gesture recognition model.
[0088] Specifically, a gesture recognition model based on deep learning is used to train a large amount of gesture data so that the gesture recognition model can accurately recognize the user's food-grabbing action. The specific implementation of the gesture recognition model includes steps such as feature extraction, classifier training, and recognition result output.
[0089] In gesture recognition, the input data of the gesture data set is the feature vector extracted from the point cloud data in the feature extraction stage. These feature vectors are the key information used by the gesture recognition model to characterize and distinguish different gestures. The output data of the gesture data set is the gesture category corresponding to the feature vector, which is the annotation information of the gesture data set, that is, each feature vector in the data set has been marked or classified in advance as a food picking action or a non-food picking action. The gesture recognition model trained in the method of the present invention can recognize food picking actions and non-food picking actions.
[0090] In the classifier training phase, the labeled gesture dataset is used to train the classifier. By optimizing the parameters and structure of the classifier, it can accurately map the input feature vector to the corresponding gesture category.
[0091] In some embodiments, the use of a pre-trained gesture recognition model to analyze and process the point cloud data to identify whether the user's gesture action is a food picking action includes:
[0092] S110, preprocessing the point cloud data, and extracting a feature vector representing the gesture from the preprocessed point cloud data;
[0093] S120, inputting the feature vector into a gesture recognition model to obtain a corresponding gesture category, and then determining whether the gesture category is a food picking action.
[0094] In the feature extraction stage, feature vectors that can represent gestures are extracted from the preprocessed point cloud data. These feature vectors need to be able to distinguish different gestures and have a certain degree of robustness to conditions such as noise and lighting.
[0095] In the recognition result output stage, the gesture recognition model converts the gesture category output by the classifier into a control instruction and sends it to the rotation control unit. When the user's picking action is recognized, the command to stop the rotation is output; when the picking action is not recognized, the command to continue the rotation is output.
[0096] In some embodiments, extracting a feature vector representing a gesture from the preprocessed point cloud data includes:
[0097] One or more of trajectory features, 3D convolution features, and depth features are extracted from the preprocessed point cloud data as feature vectors.
[0098] For example, the feature vector that can be used to characterize the action of picking up food can be:
[0099] Trajectory features: The motion trajectory of the user when picking up food can be used as an important feature. Trajectory features include trajectory length, speed, acceleration, direction, etc.
[0100] 3D convolutional features: For point cloud data, 3D convolutional neural networks can be used to extract spatiotemporal features. 3D convolutional features can capture both the shape and motion information of gestures.
[0101] Deep features: Train a deep learning model (such as a convolutional neural network, recurrent neural network, or graph convolutional network) to recognize the action of picking up food, and extract the output of the middle layer of the model as a feature vector;
[0102] Multimodal fusion features: Combine and fuse the above different types of features to fully utilize the advantages of various features.
[0103] In some embodiments, the method further comprises:
[0104] A correspondence between the user's gesture action and the control command is established, and the correspondence is:
[0105] When the gesture category is the action of picking up food, the corresponding control instruction is to stop the table from rotating;
[0106] When the gesture category is a non-food-picking action, the corresponding control instruction is for the dining table to continue rotating.
[0107] Compared with the prior art, the advantages of the present invention are:
[0108] The use of laser radar and gesture recognition technology realizes the function of picking up food and stopping, improving user experience and convenience.
[0109] LiDAR has the characteristics of high precision and strong anti-interference ability, and can accurately identify users' food-picking actions in various environments.
[0110] The design of the revolving dining table is simple and practical, easy to manufacture and maintain.
[0111] The gesture recognition model can be optimized and new functions can be added through software upgrades, which has good scalability.
[0112] See also Figure 3 The embodiment of the present invention provides a start-stop control system for a rotating dining table, which is applied to a rotating dining table. The rotating dining table includes a dining table body, a rotating mechanism for driving the dining table body to rotate, a laser radar for collecting point cloud data in the space above the dining table body, a data processing unit, and a rotation control unit; the data processing unit is connected to the laser radar and the rotation control unit respectively, and the rotation control unit is connected to the rotating mechanism;
[0113] The system comprises:
[0114] The first module is used to respond to the start-stop control command, trigger the laser radar to scan the space above the dining table body, and generate point cloud data;
[0115] The second module is used to receive the point cloud data sent by the laser radar through the data processing unit, and use the pre-trained gesture recognition model to analyze and process the point cloud data to identify the user's gesture action;
[0116] The third module is used to send corresponding control instructions to the rotation control unit based on the user's gesture action through the data processing unit, so as to control the start and stop of the rotation mechanism through the rotation control unit.
[0117] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0118] See also Figure 4 , an embodiment of the present invention provides an electronic device, including:
[0119] at least one processor;
[0120] at least one memory for storing at least one program;
[0121] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.
[0122] It can be seen that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0123] In addition, the embodiment of the present application also discloses a computer program product or a computer program, and the computer program product or the computer program is stored in a computer-readable storage medium. The processor of the computer device can read the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device performs the above method. Similarly, the contents in the above method embodiment are all applicable to the storage medium embodiment, and the functions specifically implemented by the storage medium embodiment are the same as those in the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method embodiment.
[0124] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the charging modules may be selected according to actual needs to achieve the purpose of the present embodiment.
[0125] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional charging modules / units in the systems and devices may be implemented as software, firmware, hardware, or appropriate combinations thereof.
[0126] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example: a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0127] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0128] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0129] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0130] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0131] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.
[0132] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.
Claims
1. A start-stop control method for a rotating dining table, It is characterized in that The method is applied to a rotating dining table, which includes a dining table body, a rotating mechanism for driving the dining table body to rotate, a laser radar for collecting point cloud data in the space above the dining table body, a data processing unit and a rotating control unit; the data processing unit is connected to the laser radar and the rotating control unit respectively, and the rotating control unit is connected to the rotating mechanism; The method comprises the following steps: In response to the start-stop control command, the laser radar is triggered to scan the space above the dining table body and generate point cloud data; After receiving the point cloud data sent by the laser radar, the data processing unit uses the pre-trained gesture recognition model to analyze and process the point cloud data to identify the user's gestures; The data processing unit sends a corresponding control instruction to the rotation control unit based on the user's gesture action, so as to control the start and stop of the rotation mechanism through the rotation control unit.
2. The method according to claim 1, It is characterized in that The data processing unit sends a corresponding control instruction to the rotation control unit based on the user's gesture action, so as to control the start and stop of the rotation mechanism through the rotation control unit, including: Identify whether the user's gesture action is a food picking action. When it is identified that the user's gesture action is a food picking action, the data processing unit sends a stop rotation instruction to the rotation control unit to control the rotation mechanism to stop rotating through the rotation control unit.
3. The method according to claim 2, It is characterized in that The data processing unit sends a corresponding control instruction to the rotation control unit based on the user's gesture action, so as to control the start and stop of the rotation mechanism through the rotation control unit, and further includes: After the rotation control unit controls the rotation mechanism to stop rotating, when it is recognized that the user's gesture action is not a food picking action, the data processing unit sends an instruction to continue rotating to the rotation control unit, so as to control the rotation mechanism through the rotation control unit to continue driving the dining table body to rotate.
4. The method according to claim 1, It is characterized in that The gesture recognition model is trained in the following way: Acquire a gesture data set, wherein input data of the gesture data set is a feature vector, and output data is a gesture category corresponding to the feature vector; A deep learning model is constructed, and the deep learning model is trained using the gesture data set to obtain a gesture recognition model.
5. The method according to claim 1, It is characterized in that The method of using a pre-trained gesture recognition model to analyze and process the point cloud data to recognize the user's gestures includes: Preprocessing the point cloud data, and extracting a feature vector representing the gesture from the preprocessed point cloud data; The feature vector is input into a gesture recognition model to obtain a corresponding gesture category.
6. The method according to claim 5, It is characterized in that The step of extracting a feature vector representing the gesture from the preprocessed point cloud data comprises: One or more of trajectory features, 3D convolution features, and depth features are extracted from the preprocessed point cloud data as feature vectors.
7. The method according to claim 1, It is characterized in that The method further comprises: A correspondence between the user's gesture action and the control command is established, and the correspondence is: When the gesture category is the action of picking up food, the corresponding control instruction is to stop the table from rotating; When the gesture category is a non-food-picking action, the corresponding control instruction is for the dining table to continue rotating.
8. A start-stop control system for a rotating dining table. It is characterized in that The system is applied to a rotating dining table, which includes a dining table body, a rotating mechanism for driving the dining table body to rotate, a laser radar for collecting point cloud data in the space above the dining table body, a data processing unit and a rotating control unit; the data processing unit is connected to the laser radar and the rotating control unit respectively, and the rotating control unit is connected to the rotating mechanism; The system comprises: The first module is used to respond to the start-stop control command, trigger the laser radar to scan the space above the dining table body, and generate point cloud data; The second module is used to receive the point cloud data sent by the laser radar through the data processing unit, and use the pre-trained gesture recognition model to analyze and process the point cloud data to identify the user's gesture action; The third module is used to send corresponding control instructions to the rotation control unit based on the user's gesture action through the data processing unit, so as to control the start and stop of the rotation mechanism through the rotation control unit.
9. An electronic device, It is characterized in that include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a program executable by a processor stored therein, It is characterized in that The processor-executable program is used to perform the method according to any one of claims 1 to 7 when executed by the processor.
