A control method, system and electronic device for an oven
By installing a camera and depth sensor inside the oven, combined with image recognition and 3D model generation technology, automated food cutting is achieved, solving the problem of uneven cutting in traditional manual methods and improving cutting accuracy and cooking efficiency.
Patent Information
- Application Number
- CN202510040458.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-10
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2045-01-10
AI Technical Summary
Traditional steaming and baking equipment requires manual cutting, which results in uneven cutting of the food, affecting the heating and flavor absorption. In addition, the operation is cumbersome, time-consuming and labor-intensive.
By installing a camera, depth sensor, and cutting blade inside the oven, and using image recognition and 3D model generation technology, the oven can automatically identify the types of ingredients and plan the cutting path, thus achieving automated flower-cutting.
It improves the precision and consistency of food cutting, reduces manual intervention, enhances cooking efficiency, provides a convenient user experience, and reduces labor intensity and risk.
Smart Images

Figure CN120023869B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of smart kitchen appliance technology, and in particular to a control method, system and electronic device for an oven. Background Technology
[0002] In the cooking process, scoring ingredients is a common technique, especially when preparing baked or steamed ingredients. Scoring can effectively increase the surface area of the ingredients, promote even heating and flavor absorption, and thus improve the taste and quality of the dish.
[0003] Traditional steam-roasting equipment requires manual cutting of ingredients, which relies on experience and skill. Improper operation can lead to uneven cutting, affecting the food's heating and flavor absorption. Furthermore, manual operation is tedious and time-consuming. Therefore, there is an urgent need for an intelligent steam-roasting system that can automatically cut ingredients to improve cutting precision and optimize cooking results. Summary of the Invention
[0004] To address at least one of the aforementioned technical problems, this disclosure provides a control method, system, and electronic device for an oven.
[0005] According to a first aspect of the present disclosure, a method for controlling an oven is provided, wherein a camera, a depth sensor, and a cutting blade are disposed inside the oven, and food is placed at the bottom of the oven; the method includes:
[0006] Acquire a two-dimensional image of the food ingredient captured by the camera;
[0007] Based on a preset image recognition model, the types of food corresponding to the two-dimensional image are identified;
[0008] A three-dimensional model of the food ingredient is generated based on the depth map measured by the depth sensor and the two-dimensional image.
[0009] Based on the type of food corresponding to the two-dimensional image and the three-dimensional model of the food, the cutting information is determined, including the cutting type, cutting width, cutting depth, cutting speed, and cutting angle.
[0010] Based on the cutting information and the three-dimensional model of the food ingredient, plan the cutting path of the cutting tool;
[0011] Based on the cutting path, the cutting blade is controlled to cut the food ingredient.
[0012] In one embodiment, determining the cutting information based on the type of food corresponding to the two-dimensional image and the three-dimensional model of the food includes:
[0013] Establish a cutting information database; the cutting information database contains first cutting data, the first cutting data includes the name of each type of food, multiple cutting types corresponding to each type of food and their cutting parameters, the cutting parameters being the cutting width, the cutting speed and the cutting angle corresponding to the target cutting type of the target food;
[0014] Determine the first cutting data in the cutting information database corresponding to the type of food corresponding to the two-dimensional image;
[0015] Based on the three-dimensional model of the food ingredient, the thickness information of the food ingredient is extracted; the thickness information is the data information of the three-dimensional model in the vertical direction.
[0016] Based on the thickness information of the food ingredient, a second cutting data is determined; the second cutting data is the cutting depth.
[0017] In one embodiment, the preset image recognition model is a food ingredient image recognition model, which is trained using the following method:
[0018] Acquire sample food images, the sample food images including annotation data to indicate the type of food;
[0019] The sample food images are input into the food image recognition model to obtain classification prediction results;
[0020] The loss value is calculated based on the difference between the labeled data and the classification prediction results;
[0021] Based on the loss value, the parameters of the food image recognition model are adjusted.
[0022] In one embodiment, planning the cutting path of the cutting tool based on the cutting information and the three-dimensional model of the food ingredient includes:
[0023] Based on the three-dimensional model of the food ingredient, the cutting type, and the cutting width, multiple cutting lines are determined; each cutting line is tangent to the upper surface of the three-dimensional model of the food ingredient.
[0024] Based on the cutting lines, the cutting angles, and the cutting depths, multiple cutting regions are determined inside the food ingredient;
[0025] Based on the multiple cutting areas, the cutting path of the cutting tool is planned.
[0026] In one embodiment, controlling the cutting blade to cut the food ingredient based on the cutting path includes:
[0027] Determine the coordinates of each of the plurality of cutting lines;
[0028] Based on the coordinates of the initial cutting line among the plurality of cutting lines, the cutting tool is moved to the initial cutting line;
[0029] Based on the cutting path and the coordinates of each cutting line, the cutting tool is controlled to cut the food at the cutting speed.
[0030] In one embodiment, the cutting type includes dicing and shredding;
[0031] The determination of multiple cutting lines based on the three-dimensional model of the food ingredient, the cutting type, and the cutting width includes:
[0032] When the cutting type is the block type or the filament type, multiple first cutting lines and multiple second cutting lines are determined; each first cutting line and each second cutting line is tangent to the upper surface of the three-dimensional model, the distance between adjacent first cutting lines is consistent with the cutting width, the distance between adjacent second cutting lines is consistent with the cutting width, and the first cutting lines are perpendicular to the second cutting lines.
[0033] In one embodiment, the cutting type includes a slice type;
[0034] The determination of multiple cutting lines based on the three-dimensional model of the food ingredient, the cutting type, and the cutting width further includes:
[0035] When the cutting type is the slice type, multiple third cutting lines are determined; each third cutting line is tangent to the upper surface of the three-dimensional model, and the distance between adjacent third cutting lines is the same as the cutting width.
[0036] In one embodiment, generating a three-dimensional model of the food ingredient based on the depth map measured by the depth sensor and the two-dimensional image includes:
[0037] By fusing the depth map and the two-dimensional image, a four-channel image including color information and depth information is obtained;
[0038] Based on the depth information, each pixel in the four-channel image is mapped to a three-dimensional space to generate point cloud data; each point in the point cloud data includes three-dimensional coordinates and the color information.
[0039] Based on the point cloud data, a three-dimensional model of the food ingredient is constructed.
[0040] According to a second aspect of the present disclosure, a control system for an oven is provided, wherein a camera, a depth sensor, and a cutting blade are disposed inside the oven, and food is placed at the bottom of the oven; the system includes:
[0041] The acquisition module is used to acquire a two-dimensional image of the food ingredient captured by the camera;
[0042] The recognition module is used to identify the type of food corresponding to the two-dimensional image based on a preset image recognition model;
[0043] A generation module is used to generate a three-dimensional model of the food ingredient based on the depth map measured by the depth sensor and the two-dimensional image.
[0044] The determining module is used to determine cutting information based on the type of food corresponding to the two-dimensional image and the three-dimensional model of the food. The cutting information includes cutting type, cutting width, cutting depth, cutting speed, and cutting angle.
[0045] The planning module is used to plan the cutting path of the cutting tool based on the cutting information and the three-dimensional model of the food ingredient;
[0046] The control module is used to control the cutting blade to cut the food ingredient based on the cutting path.
[0047] According to a third aspect of the present disclosure, an electronic device is provided, including at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the oven control method as described in the first aspect above by executing the instructions stored in the memory.
[0048] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.
[0049] Implementing this disclosure will have the following beneficial effects:
[0050] By determining matching cutting information based on the characteristics of different ingredients, the oven can handle a variety of foods, increasing its applicability and flexibility. Through a combination of cameras and depth sensors, it can automatically identify ingredients and generate their 3D models. Based on the 3D model of the ingredients and the cutting information, the path of the cutting blades can be precisely planned, thereby ensuring the accuracy and consistency of cutting, improving the quality of food processing, and achieving a high level of intelligence for the oven without human intervention. The automated cutting process reduces manual preparation time, improves cooking efficiency, provides users with a convenient user experience, and reduces the labor intensity and risks of manual cutting.
[0051] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description
[0052] To more clearly illustrate the technical solutions and advantages in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0053] Figure 1 A schematic flowchart of a method for controlling an oven according to an embodiment of the present disclosure is shown.
[0054] Figure 2 A schematic diagram of the process for determining cutting information according to an embodiment of the present disclosure is shown.
[0055] Figure 3 A flowchart illustrating a training method for a food image recognition model according to an embodiment of the present disclosure is shown.
[0056] Figure 4 A flowchart illustrating the cutting path of a cutting tool according to an embodiment of the present disclosure is shown.
[0057] Figure 5 A schematic diagram illustrating the process of generating a three-dimensional model of food ingredients according to an embodiment of the present disclosure is shown.
[0058] Figure 6 A schematic diagram of the control system of an oven according to an embodiment of the present disclosure is shown.
[0059] Figure 7 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation
[0060] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0061] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.
[0062] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.
[0063] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.
[0064] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.
[0065] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.
[0066] To address the limitations of traditional ovens, this disclosure provides an intelligent oven equipped with a camera, depth sensor, and cutting blades inside, with food placed at the bottom of the oven. Figure 1 A flowchart illustrating a control method for an oven according to an embodiment of the present disclosure is shown, as follows: Figure 1 The above methods include:
[0067] S101. Acquire a two-dimensional image of the food captured by the camera.
[0068] This disclosure does not limit the location of the camera. In one embodiment, the camera is fixedly mounted on the side wall inside the oven, and a rotatable platform is provided inside the oven on which the food is placed. The camera captures images from multiple angles by rotating the platform to ensure comprehensive coverage of all parts of the food and obtain a complete two-dimensional image.
[0069] S102. Based on a preset image recognition model, identify the types of ingredients corresponding to the two-dimensional image.
[0070] The preset image recognition model is a food image recognition model. Figure 3 A flowchart illustrating a training method for a food image recognition model according to an embodiment of the present disclosure is shown. Figure 3 The food image recognition model was trained using the following method:
[0071] S301. Obtain sample food images, which include annotation data to indicate the types of food ingredients.
[0072] The sample food images cover a variety of food types, each with different shapes and sizes to ensure the model's generalization ability. For example, they include various specific ingredients from different categories such as vegetables, fruits, meats, and fish. The sample food images have sufficiently high resolution to ensure clear details for easy model recognition, and there are enough sample food images for each type to ensure effective model training.
[0073] The sample food images were preprocessed, including resizing, standardization, and data augmentation. Image processing libraries such as OpenCV and PIL were used to resize the images to a uniform size. Data augmentation was performed on the sample food images by rotating, scaling, cropping, and flipping to increase the diversity of training samples and improve the robustness of the model. Images with different lighting conditions, backgrounds, and angles were added to simulate image acquisition in a real oven environment.
[0074] S302. Input the sample food images into the food image recognition model to obtain the classification prediction results.
[0075] This disclosure does not limit the food image recognition model. In one embodiment, the food image recognition model is AlexNet, a Convolutional Neural Network (CNN) model. AlexNet includes multiple convolutional layers, pooling layers, and fully connected layers. The convolutional layers are used to extract local features of the image, the pooling layers are used for dimensionality reduction and extraction of main features, and the fully connected layers are used to map the features to the classification result.
[0076] S303. Calculate the loss value based on the difference between the labeled data and the classification prediction results.
[0077] The input sample food images are passed through the AlexNet model for forward propagation to obtain the classification prediction results of the output layer. The cross-entropy loss function is used to calculate the difference between the classification prediction results and the labeled data. The cross-entropy loss function can quantify the difference between the probability distribution output by the model and the actual distribution. Through the feedback mechanism of the loss function, the model parameters are continuously adjusted, enabling the model to be continuously optimized during training, thereby improving its performance and robustness in practical applications.
[0078] S304. Adjust the parameters of the food image recognition model based on the loss value.
[0079] Based on the loss value, the gradient of each layer's parameters is calculated using the backpropagation algorithm. An optimizer, such as the Adam optimizer, is used to update the model's parameters according to the calculated gradients, gradually reducing the loss value. The loss value is calculated by comparing the difference between labeled data and classification prediction results, and the model parameters are continuously adjusted to gradually improve the model's recognition accuracy, ultimately achieving high-precision recognition of different ingredients.
[0080] The model is trained on a large number of food images to learn and adapt to the characteristics of various foods, improving its recognition ability in diverse and complex environments and ensuring accurate classification of different types and shapes of food. The food image recognition model with high accuracy and strong adaptability can significantly improve the user experience when using a smart oven and reduce the inconvenience caused by recognition errors.
[0081] S103. Based on the depth map and two-dimensional image measured by the depth sensor, generate a three-dimensional model of the food ingredients.
[0082] This disclosure does not limit the location of the depth sensor. In one embodiment, the depth sensor is fixed to the upper side wall inside the oven, opposite or adjacent to the camera, and at the same height as the camera to ensure that depth information can be acquired from the same perspective. The rotatable platform is activated and rotated at predetermined angular intervals, for example, 10 degrees each time. At each angular interval, the camera captures a two-dimensional image, and the depth sensor acquires a depth map. By controlling the rotation angle of the platform, images and depth information can be captured at different angular intervals, ensuring that every part of the food is accurately recorded.
[0083] Figure 5 This diagram illustrates a process for generating a three-dimensional model of food ingredients according to an embodiment of the present disclosure, such as... Figure 5 Methods for generating 3D models of food ingredients include:
[0084] S501, fuse the depth map and the two-dimensional image to obtain a four-channel image including color information and depth information.
[0085] Specifically, the process involves acquiring two-dimensional images captured by a camera and depth maps measured by a depth sensor; calibrating the camera and depth sensor using a calibration board to ensure alignment of their viewpoints and coordinate systems; in one embodiment, a checkerboard pattern can be used for calibration; calculating the intrinsic and extrinsic parameters of the camera and depth sensor, where intrinsic parameters describe the internal optical characteristics of the devices, such as focal length and principal point coordinates, and extrinsic parameters describe the relative position and orientation between the devices, such as rotation matrices and translation vectors; in one embodiment, the corner points of the calibration board can be detected using the computer vision algorithm OpenCV to calculate the intrinsic and extrinsic parameters; and finally, transforming the coordinate system of the depth map to the coordinate system of the camera using the intrinsic and extrinsic parameters. In this process, each pixel is mapped one-to-one with the 2D image and the depth map. When the resolutions of the 2D image and the depth map are different, one of them is resized, usually by adjusting the resolution of the depth map to match the size of the 2D image. In one embodiment, an interpolation method can be used to adjust the resolution of the depth map to match the resolution of the 2D image. A four-channel image matrix is initialized to store the fused RGB and depth information. The four-channel information of each pixel includes three color channels (RGB) and one depth channel. The 2D image and the depth map are traversed pixel by pixel, and the RGB values of the 2D image and the depth values of the corresponding pixels are combined into the four-channel image.
[0086] By fusing depth maps and 2D images, the generated four-channel images provide richer data, helping to capture the shape and structure of ingredients more accurately.
[0087] S502. Based on depth information, each pixel in the four-channel image is mapped to three-dimensional space to generate point cloud data.
[0088] Specifically, color and depth information are extracted from the four-channel image; intrinsic parameters are used to convert the two-dimensional coordinates of each pixel into three-dimensional coordinates; the depth information is used to map each pixel into three-dimensional space; and the three-dimensional coordinates and color information of each pixel are combined to form point cloud data. Each point in the point cloud data includes three-dimensional coordinates and color information, which can be used to construct a high-resolution three-dimensional model.
[0089] S503. Based on point cloud data, construct a 3D model of the ingredients.
[0090] Specifically, before constructing the 3D model, the point cloud data needs to be preprocessed. This disclosure does not limit the preprocessing method and may include steps such as noise removal and downsampling. After preprocessing, surface reconstruction is performed, which converts the preprocessed point cloud data into a 3D mesh model. This disclosure does not limit the surface reconstruction method and may use convex hull algorithms or triangular mesh reconstruction methods. The generated 3D model is then post-processed. This disclosure does not limit the post-processing method and may use mesh simplification and hole filling. Simplifying the mesh reduces the number of triangles and improves rendering efficiency, while filling holes in the 3D model improves the model's integrity, thereby improving the quality of the 3D model. Generating an accurate 3D model helps the oven accurately identify ingredients and provide personalized cooking operations, offering users a more convenient and intelligent user experience.
[0091] S104. Determine the cutting information based on the type of food and the three-dimensional model of the food corresponding to the two-dimensional image.
[0092] This disclosure does not limit the cutting information. In one embodiment, the cutting information includes cutting type, cutting width, cutting depth, cutting speed, and cutting angle.
[0093] In one embodiment, cutting information can be determined using automated methods. Figure 2 This diagram illustrates a flowchart of determining cutting information according to an embodiment of the present disclosure, such as... Figure 2 The method for determining the cutting information is as follows:
[0094] S201. Establish a cutting information database.
[0095] The cutting information database contains first cutting data, which includes the name of each type of food ingredient, multiple cutting types corresponding to each type of food ingredient, and their cutting parameters. The cutting parameters are the cutting width, cutting speed, and cutting angle corresponding to the target cutting type of the target food ingredient. This disclosure does not limit the cutting type; it can be a dicing type, a shredding type, or a slicing type. Each cutting type has applicable cutting width, cutting speed, and cutting angle. The cutting width refers to the distance between two adjacent cuts made by the cutting tool on the food ingredient; the cutting speed refers to the speed at which the cutting tool moves when cutting the food ingredient; and the cutting angle refers to the angle of inclination of the cutting tool relative to the surface of the food ingredient.
[0096] This disclosure does not limit the method of obtaining the first cutting data; it can be obtained by actual testing of the ingredients or by consulting a professional chef.
[0097] This disclosure does not limit the specific design of the cutting information database. In one embodiment, the cutting information database includes an ingredient type table, a cutting type table, and a cutting parameter table. Specifically, the ingredient type table includes a primary key IngredientID and an ingredient name IngredientName; the cutting type table includes a primary key CuttingTypeID and a cutting type CuttingTypeName; and the cutting parameter table includes a primary key ParameterID, a foreign key IngredientID, a foreign key CuttingTypeID, a cutting width CuttingWidth, a cutting speed CuttingSpeed, and a cutting angle CuttingAngle. The foreign key IngredientID is used to associate with the ingredient type, and the foreign key CuttingTypeID is used to associate with the cutting type. By establishing a cutting information database, suitable cutting types and cutting parameters can be selected according to different types of ingredients, ensuring that each ingredient achieves the best cutting effect.
[0098] S202. Determine the first cutting data corresponding to the type of food in the cutting information database.
[0099] Specifically, a connection is established between a food image recognition model and a cutting information database; based on the output of the food image recognition model, the name of the food type is extracted; in the cutting information database, the corresponding first cutting data is queried based on the extracted food type name. In one embodiment, one food type can correspond to multiple suitable cutting types, and the user can select a default mode to determine the cutting type. In the default mode, the oven will randomly select a cutting type.
[0100] By applying the cutting information database, suitable cutting data can be quickly found and matched, improving the efficiency of cutting path planning, reducing processing time, and enhancing overall work efficiency.
[0101] S203. Based on the 3D model of the ingredients, extract the thickness information of the ingredients.
[0102] S204. Based on the thickness information of the ingredients, determine the second cutting data.
[0103] The thickness information refers to the vertical data of the 3D model, and the second cutting data is the cutting depth. Specifically, the height data of the 3D model is analyzed to determine the thickness range of the food in the vertical direction; based on the thickness range, the second cutting data, i.e., the cutting depth, is determined. This disclosure does not specifically limit the cutting depth; in one embodiment, the cutting depth is greater than the minimum value and less than the maximum value in the thickness range. Extracting the thickness information of the food based on the 3D model allows for the development of personalized cutting schemes according to the actual size of the food, adapting to food of different shapes and thicknesses, avoiding over- or under-cutting, ensuring cutting accuracy, and improving the quality of food processing.
[0104] In one embodiment, the user can select a manual mode to determine the cutting type. In manual mode, the oven prompts the user to select the cutting type via an external display screen. After selecting the cutting type, the user is prompted to manually enter the cutting information.
[0105] S105. Based on the cutting information and the three-dimensional model of the ingredients, plan the cutting path of the cutting tool.
[0106] Figure 4 A flowchart illustrating the cutting path of a cutting tool according to an embodiment of this disclosure is shown. Figure 4 Methods for planning the cutting path of a cutting tool include:
[0107] S401. Based on the 3D model of the ingredients, the cutting type, and the cutting width, determine multiple cutting lines.
[0108] Each cutting line is tangent to the upper surface of the 3D model of the food ingredient. In one embodiment, when the cutting type is either dicing or shredding, multiple first cutting lines and multiple second cutting lines are determined. Each first cutting line and each second cutting line is tangent to the upper surface of the 3D model. The distance between adjacent first cutting lines is the same as the cutting width, and the distance between adjacent second cutting lines is the same as the cutting width. The first cutting lines are perpendicular to the second cutting lines. By determining the first and second cutting lines for dicing or shredding respectively, and ensuring that the first and second cutting lines are perpendicular, the shape of the cut food ingredient can be precisely controlled.
[0109] In one embodiment, when the cutting type is a slice, multiple third cutting lines are determined, each third cutting line being tangent to the upper surface of the three-dimensional model, and the distance between adjacent third cutting lines being consistent with the cutting width.
[0110] Determining the spacing between adjacent cutting lines based on the cutting width ensures that the width of each part of the food is consistent, guaranteeing uniform cutting. Clearly defining multiple cutting lines reduces ineffective operations during the cutting process, improves cutting efficiency, allows for rapid planning and execution of cutting operations, and shortens processing time.
[0111] Based on the 3D model of the ingredients and the cutting type, the cutting line tangent to the surface of the ingredients is determined to ensure the accuracy of the cutting path, making the cutting process more precise and reducing errors. Multiple cutting lines can be flexibly determined according to different cutting types and cutting widths to adapt to various ingredients and cutting needs, providing diverse cutting solutions.
[0112] S402. Based on each cutting line, cutting angle, and cutting depth, determine multiple cutting zones inside the food.
[0113] Specifically, each cutting line is extended downwards at a set cutting angle. This disclosure does not limit the cutting angle; it can be a right angle or an oblique angle, depending on the cutting requirements. Combined with the determined cutting depth, the cutting lines are extended inside the food to the set cutting depth, ensuring that the cut does not exceed the thickness of the food. Based on the extended cutting lines, multiple cutting areas, i.e., cutting surfaces, are determined. By combining cutting lines, cutting angles, and cutting depth, multiple cutting areas inside the food are precisely determined, making the path planning of the cutting tool more rational and efficient, reducing unnecessary tool movement, and improving cutting efficiency.
[0114] S403. Based on multiple cutting areas, plan the cutting path of the cutting tool.
[0115] Specifically, the initial cutting position of the cutting tool is determined, usually the cutting area where the edge cutting line is located; all cutting areas are sorted, and the cutting order is determined according to preset rules.
[0116] This disclosure does not limit the preset rules. In one embodiment, when the cutting type is dicing or shredding, the preset rule is to cut sequentially according to the arrangement order of the cutting areas where the first cutting line is located, and then cut sequentially according to the arrangement order of the cutting areas where the second cutting line is located. In one embodiment, when the cutting type is slicing, the preset rule is to cut sequentially according to the arrangement order of the cutting areas where the third cutting line is located.
[0117] S106. Based on the cutting path, control the cutting blade to cut the food.
[0118] Specifically, the coordinates of each of the multiple cutting lines are determined; based on the coordinates of the initial cutting line, the cutting tool is moved to the initial cutting line; based on the cutting path and the coordinates of each cutting line, the cutting tool is controlled to cut the food at the aforementioned set cutting speed. By precisely positioning and moving the cutting tool to each cutting line according to its coordinates, accurate cutting of the food is achieved.
[0119] By determining the coordinates of each cutting line and moving the cutting blade according to these coordinates, precise cutting of food can be achieved, ensuring accuracy and consistency. By controlling the cutting blade to cut food at a set cutting speed, cutting efficiency can be improved, saving time and labor costs. Based on a pre-set cutting path and speed, the stability and reliability of cutting can be improved, reducing the possibility of errors.
[0120] Figure 6 This diagram illustrates a block diagram of a control system for an oven according to an embodiment of the present disclosure. The oven interior includes a camera, a depth sensor, and a cutting blade. Food is placed at the bottom of the oven, such as... Figure 6 The system includes:
[0121] The acquisition module is used to acquire a two-dimensional image of the food ingredient captured by the camera;
[0122] The recognition module is used to identify the type of food corresponding to the two-dimensional image based on a preset image recognition model;
[0123] A generation module is used to generate a three-dimensional model of the food ingredient based on the depth map measured by the depth sensor and the two-dimensional image.
[0124] The determining module is used to determine cutting information based on the type of food corresponding to the two-dimensional image and the three-dimensional model of the food. The cutting information includes cutting type, cutting width, cutting depth, cutting speed, and cutting angle.
[0125] The planning module is used to plan the cutting path of the cutting tool based on the cutting information and the three-dimensional model of the food ingredient;
[0126] The control module is used to control the cutting blade to cut the food ingredient based on the cutting path.
[0127] In some embodiments, the system provided in this disclosure may have functions or include modules that can be used to execute the methods described in the above method embodiments. The specific implementation of these methods can be referred to the description in the above method embodiments, and for the sake of brevity, they will not be repeated here.
[0128] This disclosure also proposes an electronic device, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured for the method described above.
[0129] Electronic devices can be provided as terminals, servers, or other forms of devices.
[0130] Figure 7 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. For example, electronic device 1900 may be provided as a server. (Refer to...) Figure 7The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the methods described above.
[0131] Electronic device 1900 may also include a power supply component 1926 configured to perform power management of electronic device 1900, a wired or wireless network interface 1950 configured to connect electronic device 1900 to a network, and an input / output (I / O) interface 1958. Electronic device 1900 can operate on an operating system stored in memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.
[0132] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.
[0133] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.
[0134] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.
[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which includes one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions specified in the blocks may occur in a different order than those specified in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0136] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.
Claims
1. A control method of an oven, characterized by, The oven is equipped with a camera, a depth sensor, and a cutting blade. Food is placed at the bottom of the oven. The method includes: Acquire a two-dimensional image of the food ingredient captured by the camera; Based on a preset image recognition model, the types of food corresponding to the two-dimensional image are identified; A three-dimensional model of the food ingredient is generated based on the depth map measured by the depth sensor and the two-dimensional image. Based on the type of food corresponding to the two-dimensional image and the three-dimensional model of the food, cutting information is determined. The cutting information includes cutting type, cutting width, cutting depth, cutting speed, and cutting angle. The cutting width is the distance between two adjacent cuts made by the cutting tool on the food. The cutting speed is the speed at which the cutting tool moves when cutting the food. The cutting angle is the tilt angle of the cutting tool relative to the surface of the food. Based on the three-dimensional model of the food ingredient, the cutting type, and the cutting width, multiple cutting lines are determined; each cutting line is tangent to the upper surface of the three-dimensional model of the food ingredient. Each of the cutting lines is extended inside the food ingredient to the cutting depth according to the cutting angle, and multiple cutting areas inside the food ingredient are determined based on the extended cutting lines. Based on the multiple cutting areas, the cutting path of the cutting tool is planned; Based on the cutting path, the cutting blade is controlled to cut the food ingredient.
2. The control method of an oven according to claim 1, characterized in that, The step of determining the cutting information based on the type of food corresponding to the two-dimensional image and the three-dimensional model of the food includes: Establish a cutting information database; the cutting information database contains first cutting data, the first cutting data includes the name of each type of food, multiple cutting types corresponding to each type of food and their cutting parameters, the cutting parameters being the cutting width, the cutting speed and the cutting angle corresponding to the target cutting type of the target food; Determine the first cutting data in the cutting information database corresponding to the type of food corresponding to the two-dimensional image; Based on the three-dimensional model of the food ingredient, the thickness information of the food ingredient is extracted; the thickness information is the data information of the three-dimensional model in the vertical direction. Based on the thickness information of the food ingredient, a second cutting data is determined; the second cutting data is the cutting depth.
3. The control method of an oven according to claim 1, wherein The preset image recognition model is a food ingredient image recognition model, which is trained using the following method: Acquire sample food images, the sample food images including annotation data to indicate the type of food; The sample food images are input into the food image recognition model to obtain classification prediction results; The loss value is calculated based on the difference between the labeled data and the classification prediction results; Based on the loss value, the parameters of the food image recognition model are adjusted.
4. The control method of an oven according to claim 1, wherein The step of controlling the cutting blade to cut the food ingredient based on the cutting path includes: Determine the coordinates of each of the plurality of cutting lines; Based on the coordinates of the initial cutting line among the plurality of cutting lines, the cutting tool is moved to the initial cutting line; Based on the cutting path and the coordinates of each cutting line, the cutting tool is controlled to cut the food at the cutting speed.
5. The control method of an oven according to claim 1, wherein The cutting types include dicing and shredding; The determination of multiple cutting lines based on the three-dimensional model of the food ingredient, the cutting type, and the cutting width includes: When the cutting type is the block type or the filament type, multiple first cutting lines and multiple second cutting lines are determined; each first cutting line and each second cutting line is tangent to the upper surface of the three-dimensional model, the distance between adjacent first cutting lines is consistent with the cutting width, the distance between adjacent second cutting lines is consistent with the cutting width, and the first cutting lines are perpendicular to the second cutting lines.
6. The control method of an oven according to claim 1, wherein The cutting type includes slicing type; The determination of multiple cutting lines based on the three-dimensional model of the food ingredient, the cutting type, and the cutting width further includes: When the cutting type is the slice type, multiple third cutting lines are determined; each third cutting line is tangent to the upper surface of the three-dimensional model, and the distance between adjacent third cutting lines is the same as the cutting width.
7. The control method of an oven according to claim 1, wherein The process of generating a three-dimensional model of the food ingredient based on the depth map measured by the depth sensor and the two-dimensional image includes: By fusing the depth map and the two-dimensional image, a four-channel image including color information and depth information is obtained; Based on the depth information, each pixel in the four-channel image is mapped to a three-dimensional space to generate point cloud data; each point in the point cloud data includes three-dimensional coordinates and the color information. Based on the point cloud data, a three-dimensional model of the food ingredient is constructed.
8. A control system of an oven, characterized in that, The oven is equipped with a camera, a depth sensor, and a cutting blade. Food is placed at the bottom of the oven. The system includes: The acquisition module is used to acquire a two-dimensional image of the food ingredient captured by the camera; The recognition module is used to identify the type of food corresponding to the two-dimensional image based on a preset image recognition model; A generation module is used to generate a three-dimensional model of the food ingredient based on the depth map measured by the depth sensor and the two-dimensional image. The determining module is used to determine cutting information based on the type of food corresponding to the two-dimensional image and the three-dimensional model of the food. The cutting information includes cutting type, cutting width, cutting depth, cutting speed, and cutting angle. The cutting width is the distance between two adjacent cuts made by the cutting tool on the food. The cutting speed is the speed at which the cutting tool moves when cutting the food. The cutting angle is the tilt angle of the cutting tool relative to the surface of the food. The planning module is used to determine multiple cutting lines based on the three-dimensional model of the food ingredient, the cutting type, and the cutting width; each cutting line is tangent to the upper surface of the three-dimensional model of the food ingredient; each cutting line is extended into the food ingredient at the cutting angle to the cutting depth; based on the extended cutting lines, multiple cutting areas inside the food ingredient are determined; and based on the multiple cutting areas, the cutting path of the cutting tool is planned. A control module is configured to control the cutting tool to cut the food material based on the cutting path.
9. An electronic device, comprising: The control method of the oven comprises the following steps: acquiring a cutting path of a cutting tool of the oven; and controlling the cutting tool to cut food material based on the cutting path.
Citation Information
Patent Citations
Intelligent vegetable washing and cutting method and all-in-one machine
CN113158848A
Electric oven with stir-frying function
CN216822949U
Method of removing tissue from food product
US20200113224A1
