Detection method and device for cooking device and cooking device

Abstract

The invention relates to a detection method and device for a cooking device and the cooking device, the cooking device comprises a plurality of light sources, and the method comprises the following steps: obtaining a target area image and information of a plurality of shadow areas of a target object; obtaining a plurality of pieces of shadow distance information according to the plurality of pieces of shadow area information, wherein the shadow distance information represents the distance between the central position of the shadow area of the target object and the corresponding light source; obtaining position information of the target object according to the target area image, wherein the position information represents the position of the target object image in the target area image; and performing weighted calculation according to the distance information and the position information of the plurality of shadows to obtain the size information of the target object. Therefore, according to the target area image and the multiple shadow areas of the multiple light sources corresponding to the target object, the size information of the food materials can be accurately estimated, the accuracy of food material size measurement is improved, and therefore the cooking process can be accurately adjusted, and the cooking power, the cooking duration and the like can be adjusted.

Description

Technical Field

[0001] The present disclosure relates to the field of cooking equipment, and in particular to a detection method and device for a cooking device, and a cooking device. Background Art

[0002] Existing cooking equipment usually determines and adjusts the cooking time based on the weight or volume of the ingredients. For example, a special scale or measuring cup is used to measure the weight or volume of the ingredients, and then the preset cooking time is adjusted according to the weight or volume of the ingredients.

[0003] However, existing weight or volume measurement methods usually require the use of special equipment such as weighing machines or measuring cups, which increases costs and operational complexity. In addition, since ingredients come in different shapes and sizes, it is difficult to accurately capture the true volume of the ingredients when using weighing machines or measuring cups, which affects the accuracy of the cooking time. In addition, if the volume or size of the ingredients changes, they need to be re-measured and adjusted, and the cooking time cannot be monitored and adjusted in real time. Summary of the invention

[0004] In order to solve at least one of the above-mentioned technical problems, the present disclosure proposes a detection method and device for a cooking device, and a cooking device.

[0005] According to a first aspect of the present disclosure, a detection method for a cooking device is provided, wherein the cooking device comprises a plurality of light sources, and the detection method comprises:

[0006] Acquire a target area image and a plurality of shadow area information of a target object, wherein the target area image is an image corresponding to the target area in the cooking device, the target area image includes a target object image, and the shadow area information is used to indicate a shadow area of ​​the target object corresponding to the light source;

[0007] According to the plurality of shadow area information, a plurality of shadow distance information is respectively obtained, wherein the shadow distance information represents the distance between the center position of the shadow area of ​​the target object and the corresponding light source;

[0008] Obtaining position information of the target object according to the target area image, wherein the position information represents the position of the target object image in the target area image;

[0009] A weighted calculation is performed according to the plurality of shadow distance information and the position information to obtain the size information of the target object.

[0010] Optionally, obtaining a plurality of shadow distance information respectively according to the plurality of shadow area information includes:

[0011] Acquire a target shadow area center position, where the target shadow area center position is a shadow area center position corresponding to target shadow area information, where the target shadow area information is one of the plurality of shadow area information;

[0012] Acquire a first distance and a second distance corresponding to the center position of the target shadow area, wherein the first distance is the distance between the center position of the target shadow area and the corresponding light source in the horizontal direction, and the second distance is the distance between the center position of the target shadow area and the corresponding light source in the vertical direction;

[0013] Shadow distance information corresponding to the target shadow area is obtained according to the first distance and the second distance.

[0014] Optionally, obtaining the location information of the target object according to the target area image includes:

[0015] Performing recognition processing based on the target area image to obtain a target object image in the target area image;

[0016] The position of the bounding box corresponding to the target object image is used as the position information of the target object.

[0017] Optionally, before performing weighted calculation according to the plurality of shadow distance information and the position information to obtain the size information of the target object, the method further includes:

[0018] Acquire first weight parameter information and second weight parameter information, wherein the first weight parameter information includes weight parameters corresponding to the plurality of light sources respectively, and the second weight parameter information is a position weight parameter;

[0019] The step of performing weighted calculation according to the plurality of shadow distance information and the position information to obtain the size information of the target object includes:

[0020] The size information of the target object is obtained according to the first weighting information obtained based on the plurality of shadow distance information and the first weight parameter information, and the second weighting information obtained based on the position information and the second weight parameter information.

[0021] Optionally, the size information includes first size information, second size information and third size information, the first weight parameter information includes first sub-weight parameter information, second sub-weight parameter information and third sub-weight parameter information, and the second weight parameter information includes first sub-position weight parameter, second sub-position weight parameter and third sub-position weight parameter;

[0022] The obtaining the size information of the target object according to the first weighted information obtained based on the plurality of shadow distance information and the first weight parameter information, and the second weighted information obtained based on the position information and the second weight parameter information, comprises:

[0023] Obtaining first size information of the target object according to first sub-weighted information obtained based on the plurality of shadow distance information and the first sub-weighted parameter information, and second sub-weighted information obtained based on the position information and the first sub-position weight parameter;

[0024] Obtaining second size information of the target object according to third sub-weighting information obtained based on the plurality of shadow distance information and the second sub-weighting parameter information, and fourth sub-weighting information obtained based on the position information and the second sub-position weight parameter;

[0025] According to the fifth sub-weighted information obtained based on the multiple shadow distance information and the third sub-weight parameter information, and the sixth sub-weighted information obtained based on the position information and the third sub-position weight parameter, the third size information of the target object is obtained, and the first size information, the second size information and the third size information are respectively the extension lengths of the target object in three mutually perpendicular directions.

[0026] Optionally, before acquiring the first weight parameter information and the second weight parameter information, the step includes:

[0027] Acquire a plurality of sample data corresponding to a plurality of sample objects respectively, wherein the sample data includes size information, position information and a plurality of shadow distance information of the sample objects;

[0028] Training is performed based on the sample data to obtain the first weight parameter information and the second weight parameter information.

[0029] According to a second aspect of the present disclosure, a detection device for a cooking device is provided, wherein the cooking device comprises a plurality of light sources, and the detection device comprises:

[0030] an information acquisition unit, configured to acquire a target area image and a plurality of shadow area information of a target object, wherein the target area image is an image corresponding to a target area in the cooking device, the target area image includes a target object image, and the shadow area information is used to indicate a shadow area of ​​the target object corresponding to the light source;

[0031] A distance determination unit, configured to obtain a plurality of shadow distance information respectively according to the plurality of shadow area information, wherein the shadow distance information represents the distance between the center position of the shadow area of ​​the target object and the corresponding light source;

[0032] A position determination unit, configured to obtain position information of the target object according to the target area image, wherein the position information represents the position of the target object image in the target area image;

[0033] The size determination unit is used to perform weighted calculation according to the multiple shadow distance information and the position information to obtain the size information of the target object.

[0034] According to a third aspect of the present disclosure, a cooking device is provided, comprising a plurality of light sources and a detection device as described in the above technical solution.

[0035] Optionally, the cooking device includes a plurality of side walls, and a plurality of the light sources are spaced apart on the plurality of side walls.

[0036] According to a fourth aspect of the present disclosure, a cooking device is provided, comprising 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 detection method described in the above technical solution by executing the instructions stored in the memory.

[0037] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

[0038] The implementation of this disclosure has the following beneficial effects:

[0039] The present disclosure provides a detection method, device and cooking device for a cooking device, wherein the cooking device includes multiple light sources, and the detection method includes: obtaining a target area image and multiple shadow area information of a target object; obtaining multiple shadow distance information respectively according to the multiple shadow area information, wherein the shadow distance information represents the distance between the center position of the shadow area of ​​the target object and the corresponding light source; obtaining the position information of the target object according to the target area image, wherein the position information represents the position of the target object image in the target area image; performing weighted calculation according to the multiple shadow distance information and the position information to obtain the size information of the target object. Thus, the length, width, height and other size information of the food can be accurately estimated by using the target area image including the target object image and the multiple shadow areas of the target object corresponding to the multiple light sources, thereby improving the accuracy of the measurement, so that the cooking process can be accurately adjusted, the cooking power, cooking time, etc. can be adjusted, and the cooking effect can be ensured.

[0040] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions and advantages in the embodiments of this specification or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 A schematic diagram showing a flow chart of a detection method for a cooking device according to an embodiment of the present disclosure;

[0043] Figure 2 A schematic diagram showing a process of obtaining shadow distance information according to an embodiment of the present disclosure is shown;

[0044] Figure 3 A schematic diagram showing a process of obtaining location information of a target object according to an embodiment of the present disclosure;

[0045] Figure 4 A schematic diagram showing a process of determining size information of a target object according to an embodiment of the present disclosure;

[0046] Figure 5 A schematic diagram showing a process of determining first weight parameter information and second weight parameter information according to an embodiment of the present disclosure is shown;

[0047] Figure 6 A schematic structural diagram of a detection device for a cooking device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0050] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0051] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0052] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0053] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0054] Figure 1A flow chart of a detection method for a cooking device according to an embodiment of the present disclosure is shown. The detection method of the embodiment of the present invention can be applied to a cooking device, an intelligent terminal or a server, such as a control unit of a cooking device, or an intelligent terminal, a background server or a cloud server that is communicatively connected to the cooking device; the cooking device is a device for cooking food or a target object, for example, the cooking device is an oven, a steam oven or an electric stove, and the intelligent terminal is used to control the cooking device to cook and control the cooking process of the cooking device. The intelligent terminal can be a PC, a mobile phone, a tablet computer or other intelligent electronic device. This specification provides method operation steps such as the embodiments or flow charts, but more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one way of executing the steps among many, and does not represent the only execution order. When the actual system or server product is executed, it can be executed in the order of the methods shown in the embodiments or the drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment). As Figure 1 As shown, the above detection method includes:

[0055] Step S101, obtaining a target area image and multiple shadow area information of a target object, wherein the target area image is an image corresponding to the target area in the cooking device, the target area image includes a target object image, and the shadow area information is used to indicate a shadow area of ​​the target object corresponding to the light source.

[0056] Specifically, the cooking device is provided with an image acquisition component, which acquires images of a target area in the cooking device to generate the target area image. The target area includes an area for placing a target object, for example, an area for placing food ingredients. Accordingly, the target area image includes a target object image.

[0057] The cooking device includes a plurality of light sources, which are respectively arranged at different positions, and each light source can be switched on and off independently. Different light sources illuminate a target object, and the target object forms a shadow area corresponding to each light source, and the shadow area information is used to indicate the shadow area of ​​the target object corresponding to the light source.

[0058] Step S102 : obtaining a plurality of shadow distance information respectively according to the plurality of shadow area information, wherein the shadow distance information represents the distance between the center position of the shadow area of ​​the target object and the corresponding light source.

[0059] Specifically, the shadow area formed by any one of the multiple light sources irradiating the target object constitutes a two-dimensional geometric area, the geometric center of the shadow area constitutes its center position, and the shadow distance information represents the distance between the center position of the shadow area of ​​the target object and the corresponding light source, that is, the distance between the center position of the shadow area and the light source that irradiates the target object to form the shadow area.

[0060] Step S103: obtaining position information of the target object according to the target area image, wherein the position information represents the position of the target object image in the target area image.

[0061] Specifically, the target area image is an image corresponding to the target area including the target object, and the position parameters of the target object pattern in the target area image are obtained as the position information of the target object. Optionally, the position information includes at least two groups of position parameters, each group of position parameters is used to indicate the position of a preset position related to the target object pattern in the target area image, and different groups of position parameters correspond to different preset positions related to the target object pattern.

[0062] Exemplarily, the position information of the target object pattern includes four groups of position parameters, which are used to indicate the positions of the two ends of the target object pattern respectively corresponding to two mutually perpendicular directions, or the position information includes 2-4 groups of position parameters, which are used to indicate the positions corresponding to 2-4 vertices in a rectangular bounding box corresponding to the target object pattern, and the 2-4 vertices include at least one pair of diagonal vertices of the rectangular bounding box.

[0063] Step S104: performing weighted calculation based on the plurality of shadow distance information and the position information to obtain size information of the target object.

[0064] Specifically, the size information of the target object is used to indicate the extension length of the target object in at least one preset extension direction. The size information of the target object is obtained by performing a weighted sum calculation based on the plurality of shadow distance information, the position information and corresponding weight parameters.

[0065] Therefore, the embodiment of the present disclosure can accurately estimate the length, width, height and other size information of the food by including the target area image of the target object image and multiple shadow areas of the target object corresponding to multiple light sources, thereby improving the measurement accuracy, thereby being able to accurately adjust the cooking time and ensure the cooking effect.

[0066] In an optional embodiment, if Figure 2 As shown, the multiple shadow distance information is obtained respectively according to the multiple shadow area information, including:

[0067] Step S11 , obtaining a target shadow area center position, wherein the target shadow area center position is a shadow area center position corresponding to target shadow area information, and the target shadow area information is one of the plurality of shadow area information.

[0068] Specifically, the target shadow area information is used to indicate a target shadow area of ​​the target object corresponding to a set light source, and the target shadow area is a one- or two-dimensional geometric area, and the geometric center of the target shadow area constitutes the center position of the target shadow area.

[0069] Step S12, obtaining a first distance and a second distance corresponding to the center position of the target shadow area, wherein the first distance is the distance between the center position of the target shadow area and the corresponding light source in the horizontal direction, and the second distance is the distance between the center position of the target shadow area and the corresponding light source in the vertical direction.

[0070] Specifically, the distance between the center position of the target shadow area and the corresponding light source in the horizontal direction is obtained, and the distance is used as the first distance m; the distance between the center position of the target shadow area and the corresponding light source in the vertical direction is obtained, and the distance is used as the second distance n.

[0071] Exemplarily, the light source position of each light source is pre-stored, and the light source position includes the height position of the light source and the position in the horizontal plane. The first distance m is obtained according to the position of the center position of the target shadow area in the horizontal plane and the position of the light source in the horizontal plane. The second distance n is obtained according to the height position of the light source and the height position of the center position of the target shadow area (for example, the height position of the support surface supporting the target object).

[0072] Step S13: Obtain shadow distance information corresponding to the target shadow area according to the first distance and the second distance.

[0073] Specifically, the shadow distance information d satisfies the following relationship with the first distance m and the second distance n:

[0074]

[0075] In an optional embodiment, if Figure 3 As shown, obtaining the location information of the target object according to the target area image includes:

[0076] Step S21 : performing recognition processing based on the target area image to obtain a target object image in the target area image.

[0077] Specifically, the target area image may be processed for recognition through a deep learning model or an image recognition network to identify the target object image in the target area image.

[0078] Step S22: taking the location of the bounding box corresponding to the target object image as the location information of the target object.

[0079] Specifically, the bounding box corresponding to the target object image is a rectangular box corresponding to the area where the target object image is located, and the position information of the target object includes 2-4 groups of position parameters, and the 2-4 groups of position parameters are used to indicate the positions corresponding to 2-4 vertices in the rectangular bounding box corresponding to the target object pattern, and the 2-4 vertices include at least one pair of diagonal vertices of the rectangular bounding box, such as the upper left vertex and the lower right vertex, or the lower left vertex and the upper right vertex.

[0080] In an alternative embodiment, the relative position of the contour line of the target object image is used as the position information of the target object. For example, the endpoint positions of the contour line of the target object image in two mutually perpendicular directions are used as the position information of the target object, or the intersection position of the contour line of the target object image and two straight lines passing through the center position of the target object image and extending in two mutually perpendicular directions are used as the position information of the target object.

[0081] In an optional implementation, before performing weighted calculation according to the plurality of shadow distance information and the position information to obtain the size information of the target object, the method includes:

[0082] First weight parameter information and second weight parameter information are obtained, wherein the first weight parameter information includes weight parameters corresponding to the plurality of light sources respectively, and the second weight parameter information is a position weight parameter.

[0083] Accordingly, performing weighted calculation according to the plurality of shadow distance information and the position information to obtain the size information of the target object includes:

[0084] The size information of the target object is obtained according to the first weighting information obtained based on the plurality of shadow distance information and the first weight parameter information, and the second weighting information obtained based on the position information and the second weight parameter information.

[0085] Specifically, the first weight parameter information includes weight parameters corresponding to the multiple light sources respectively, and the multiple shadow distance information and the corresponding weight parameters are weighted and calculated to obtain the first weighted information. The first weight parameter information includes a weight parameter corresponding to the position information, and the position information and the corresponding weight parameter are weighted and calculated to obtain the second weighted information. The size information of the target object is obtained according to the first weighted information and the second weighted information.

[0086] In an optional implementation, the size information includes first size information, second size information and third size information, the first weight parameter information includes first sub-weight parameter information, second sub-weight parameter information and third sub-weight parameter information, the second weight parameter information includes first sub-position weight parameter, second sub-position weight parameter and third sub-position weight parameter; Figure 4 As shown, the size information of the target object is obtained according to the first weighted information obtained based on the plurality of shadow distance information and the first weight parameter information, and the second weighted information obtained based on the position information and the second weight parameter information, including:

[0087] Step S31, obtaining first size information of the target object according to first sub-weighted information obtained based on the multiple shadow distance information and the first sub-weighted parameter information, and second sub-weighted information obtained based on the position information and the first sub-position weight parameter.

[0088] Specifically, the first sub-weight parameter information includes weight parameters of the first sizes corresponding to the multiple light sources respectively, and a weighted sum calculation is performed based on the multiple shadow distance information and the first sub-weight parameter information to obtain the first sub-weight information.

[0089] Exemplarily, the first sub-weight parameter information includes weight parameters p1, p2, ..., p of the plurality of light sources corresponding to the first size, respectively. N , the multiple shadow distance information corresponding to the multiple light sources are d1, d2, ..., d N , N is the total number of light sources, then the first sub-weighted information D1 satisfies:

[0090] Exemplarily, the upper left vertex position of the target object pattern bounding box is (x1, y1), the lower right vertex position is (x2, y2), the position information of the target object is {x1, y1, x2, y2}, and the first sub-position weight parameter is {q1, q2, q3, q4}, then the second sub-weighted information D2 satisfies: Among them, z i is the ith value in {x1, y1, x2, y2}.

[0091] The first size information L1 of the target object satisfies: L1=D1+D2+b1, where b1 is a first constant length.

[0092] Step S32, obtaining second size information of the target object according to third sub-weighted information obtained based on the multiple shadow distance information and the second sub-weighted parameter information, and fourth sub-weighted information obtained based on the position information and the second sub-position weight parameter.

[0093] Specifically, the second sub-weight parameter information includes weight parameters of the second sizes corresponding to the multiple light sources respectively, and a weighted sum calculation is performed based on the multiple shadow distance information and the second sub-weight parameter information to obtain the third sub-weight information.

[0094] Exemplarily, the second sub-weight parameter information includes weight parameters h1, h2, ..., h of the plurality of light sources corresponding to the second size, respectively. N , N is the total number of light sources, then the third sub-weighted information D3 satisfies:

[0095]

[0096] Exemplarily, the upper left vertex position of the target object pattern bounding box is (x1, y1), the lower right vertex position is (x2, y2), the position information of the target object is {x1, y1, x2, y2}, and the second sub-weight parameter information is {s1, s2, s3, s4}, then the fourth sub-weighted information D4 satisfies: Among them, z i is the ith value in {x1, y1, x2, y2}.

[0097] The second size information L2 of the target object satisfies: L2=D3+D4+b2, where b2 is a second constant length.

[0098] Step S33, obtaining the third size information of the target object according to the fifth sub-weighted information obtained based on the multiple shadow distance information and the third sub-weighted parameter information, and the sixth sub-weighted information obtained based on the position information and the third sub-position weight parameter, wherein the first size information, the second size information and the third size information are respectively the extension lengths of the target object in three mutually perpendicular directions.

[0099] Specifically, the third sub-weight parameter information includes weight parameters of the multiple light sources corresponding to the third size respectively, and a weighted sum calculation is performed based on the multiple shadow distance information and the third sub-weight parameter information to obtain the fifth sub-weight information.

[0100] Exemplarily, the third sub-weight parameter information includes weight parameters k1, k2, ..., k N , N is the total number of light sources, then the fifth sub-weighted information D5 satisfies:

[0101]

[0102] Exemplarily, the upper left vertex position of the target object pattern bounding box is (x1, y1), the lower right vertex position is (x2, y2), the position information of the target object is {x1, y1, x2, y2}, and the third sub-weight parameter information is {t1, t2, t3, t4}, then the sixth sub-weight information D6 satisfies: Among them, z i is the ith value in {x1, y1, x2, y2}.

[0103] The third size information L3 of the target object satisfies: L3=D5+D6+b3, where b3 is a third constant length.

[0104] The first size information, the second size information, and the third size information are the extension lengths of the target object in different extension directions, specifically, the extension lengths of the target object in three mutually perpendicular directions. For example, the first size information, the second size information, and the third size information are the length, width, and height of the target object.

[0105] In an optional embodiment, if Figure 5 As shown, before obtaining the first weight parameter information and the second weight parameter information, the process includes:

[0106] Step S41 : acquiring a plurality of sample data corresponding to a plurality of sample objects respectively, wherein the sample data includes size information, position information and a plurality of shadow distance information of the sample objects.

[0107] Specifically, each sample object has known size information, the sample object is placed in the cooking device, and position information and multiple shadow distance information of the sample object are obtained.

[0108] Step S42: Perform training processing according to the sample data to obtain the first weight parameter information and the second weight parameter information.

[0109] According to the sample data, a SVM algorithm or a GBM algorithm is used to perform training based on the sample data to obtain the contribution degree of each light source to the size of the target object and the contribution degree of the relative position of the target object to the size of the target object, as well as the offset distance information, wherein the offset distance information includes a first constant length, a second constant length and / or a third constant length.

[0110] In an optional implementation, the acquiring the target area image and the information of multiple shadow areas of the target object includes:

[0111] In response to the size detection instruction, the target area image and multiple shadow area information of the target object are acquired.

[0112] Specifically, the size detection instruction is an instruction for instructing to detect the size of the target object. Optionally, the size detection instruction is generated based on the size detection operation of the user, for example, the user triggers the generation of the size detection instruction by clicking the "size recognition" option or pressing the "size recognition" button, or the size detection instruction is automatically generated by the cooking control unit, for example, the cooking control unit automatically generates the size detection instruction at the start of cooking and / or at a preset time during the cooking process based on a preset cooking control program, so as to automatically detect the size of the target object, so that the cooking control unit automatically adjusts the cooking process based on the actual size of the target object, such as adjusting the heating temperature or cooking time, to ensure the cooking effect.

[0113] The present disclosure provides a detection device for a cooking device, wherein the cooking device includes a plurality of light sources, such as Figure 6 As shown, the detection device comprises:

[0114] an information acquisition unit, configured to acquire a target area image and a plurality of shadow area information of a target object, wherein the target area image is an image corresponding to a target area in the cooking device, the target area image includes a target object image, and the shadow area information is used to indicate a shadow area of ​​the target object corresponding to the light source;

[0115] A distance determination unit, configured to obtain a plurality of shadow distance information respectively according to the plurality of shadow area information, wherein the shadow distance information represents the distance between the center position of the shadow area of ​​the target object and the corresponding light source;

[0116] A position determination unit, configured to obtain position information of the target object according to the target area image, wherein the position information represents the position of the target object image in the target area image;

[0117] The size determination unit is used to perform weighted calculation according to the multiple shadow distance information and the position information to obtain the size information of the target object.

[0118] In some embodiments, the functions or modules / units included in the detection device provided in the embodiments of the present disclosure can be used to execute the detection method described in the above embodiments. Its specific implementation can refer to the description of the above embodiments, and for the sake of brevity, it will not be repeated here.

[0119] The disclosed embodiment also provides a cooking device, which includes a plurality of light sources and a detection device as described in the above technical solution.

[0120] In an optional embodiment, the cooking device includes a plurality of side walls, and a plurality of the light sources are spaced apart on the plurality of side walls.

[0121] Optionally, the cooking device includes three side walls connected in sequence, which are a left side wall, a right side wall and a rear side wall, respectively. The rear ends of the left side wall and the right side wall are connected to the rear side wall respectively, and the front ends of the left side wall and the right side wall are provided with an openable and closable door body. The left side wall, the right side wall, the rear side wall and the door body enclose a cooking cavity of the cooking device, and the door body can be sealed with the left side wall and the right side wall to seal the cooking cavity of the cooking device.

[0122] The multiple light sources are respectively arranged on the three side walls, and the light sources are arranged at intervals on the inner surface of the side wall. Optionally, a light source array is provided on the side wall, and the light source array includes a plurality of light sources arranged in a preset number of rows and a preset number of columns, the preset number of rows is 2-6 rows, for example, 3 rows or 4 rows, and the number of columns is 3-8 rows, for example, 4 rows, 5 rows or 6 rows.

[0123] Optionally, a distance between two adjacent light sources in a horizontal direction is a1, and a distance between two adjacent light sources in a vertical direction is a2, and the values ​​of a1 and a2 may be the same or different.

[0124] Preferably, the light source array is distributed in a preset area of ​​the side wall, and the preset area is an area on the inner surface of the side wall whose distance from the top of the side wall is less than or equal to a preset height H, and the height of the side wall is H0, 0.3H0≤H≤0.75H0, for example, the value of H is 0.5H0, or 0.65H0.

[0125] Optionally, the cooking device further comprises a top wall respectively connected to the three side walls, and the image acquisition component is located on the top wall corresponding to a middle position or a middle area above the door body.

[0126] During the process of detecting the size of the target object, the multiple light sources in the cooking device are controlled to illuminate the target object one by one in sequence, so as to obtain the shadow area information of the target object corresponding to the illuminated light sources.

[0127] The presently disclosed embodiment also proposes a cooking device, characterized in that it includes 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 detection method described in the above technical solution by executing the instructions stored in the memory.

[0128] The embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor implements the detection method by executing the instructions stored in the memory.

[0129] The electronic device may be provided as a terminal, a server, or a device in other forms.

[0130] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A detection method for a cooking device, characterized in that: The cooking device includes a plurality of light sources, and the detection method includes: Acquire a target area image and a plurality of shadow area information of a target object, wherein the target area image is an image corresponding to the target area in the cooking device, the target area image includes a target object image, and the shadow area information is used to indicate a shadow area of ​​the target object corresponding to the light source; According to the plurality of shadow area information, a plurality of shadow distance information is respectively obtained, wherein the shadow distance information represents the distance between the center position of the shadow area of ​​the target object and the corresponding light source; Obtaining position information of the target object according to the target area image, wherein the position information represents the position of the target object image in the target area image; A weighted calculation is performed according to the plurality of shadow distance information and the position information to obtain the size information of the target object.

2. The detection method according to claim 1, characterized in that: The obtaining of multiple shadow distance information respectively according to the multiple shadow area information includes: Acquire a target shadow area center position, where the target shadow area center position is a shadow area center position corresponding to target shadow area information, where the target shadow area information is one of the plurality of shadow area information; Acquire a first distance and a second distance corresponding to the center position of the target shadow area, wherein the first distance is the distance between the center position of the target shadow area and the corresponding light source in the horizontal direction, and the second distance is the distance between the center position of the target shadow area and the corresponding light source in the vertical direction; Shadow distance information corresponding to the target shadow area is obtained according to the first distance and the second distance.

3. The detection method according to claim 1, characterized in that: The step of obtaining the location information of the target object according to the target area image includes: Performing recognition processing based on the target area image to obtain a target object image in the target area image; The position of the bounding box corresponding to the target object image is used as the position information of the target object.

4. The detection method according to claim 1, characterized in that: Before performing weighted calculation according to the plurality of shadow distance information and the position information to obtain the size information of the target object, the method includes: Acquire first weight parameter information and second weight parameter information, wherein the first weight parameter information includes weight parameters corresponding to the plurality of light sources respectively, and the second weight parameter information is a position weight parameter; The step of performing weighted calculation according to the plurality of shadow distance information and the position information to obtain the size information of the target object includes: The size information of the target object is obtained according to the first weighting information obtained based on the plurality of shadow distance information and the first weight parameter information, and the second weighting information obtained based on the position information and the second weight parameter information.

5. The detection method according to claim 4, characterized in that: The size information includes first size information, second size information and third size information, the first weight parameter information includes first sub-weight parameter information, second sub-weight parameter information and third sub-weight parameter information, and the second weight parameter information includes first sub-position weight parameter, second sub-position weight parameter and third sub-position weight parameter; The obtaining the size information of the target object according to the first weighted information obtained based on the plurality of shadow distance information and the first weight parameter information, and the second weighted information obtained based on the position information and the second weight parameter information, comprises: Obtaining first size information of the target object according to first sub-weighted information obtained based on the plurality of shadow distance information and the first sub-weighted parameter information, and second sub-weighted information obtained based on the position information and the first sub-position weight parameter; Obtaining second size information of the target object according to third sub-weighting information obtained based on the plurality of shadow distance information and the second sub-weighting parameter information, and fourth sub-weighting information obtained based on the position information and the second sub-position weight parameter; According to the fifth sub-weighted information obtained based on the multiple shadow distance information and the third sub-weight parameter information, and the sixth sub-weighted information obtained based on the position information and the third sub-position weight parameter, the third size information of the target object is obtained, and the first size information, the second size information and the third size information are respectively the extension lengths of the target object in three mutually perpendicular directions.

6. The detection method according to claim 4, characterized in that: Before obtaining the first weight parameter information and the second weight parameter information, the method includes: Acquire a plurality of sample data corresponding to a plurality of sample objects respectively, wherein the sample data includes size information, position information and a plurality of shadow distance information of the sample objects; Training is performed based on the sample data to obtain the first weight parameter information and the second weight parameter information.

7. A detection device for a cooking device, characterized in that: The cooking device comprises a plurality of light sources, and the detection device comprises: an information acquisition unit, configured to acquire a target area image and a plurality of shadow area information of a target object, wherein the target area image is an image corresponding to a target area in the cooking device, the target area image includes a target object image, and the shadow area information is used to indicate a shadow area of ​​the target object corresponding to the light source; A distance determination unit, configured to obtain a plurality of shadow distance information respectively according to the plurality of shadow area information, wherein the shadow distance information represents the distance between the center position of the shadow area of ​​the target object and the corresponding light source; A position determination unit, configured to obtain position information of the target object according to the target area image, wherein the position information represents the position of the target object image in the target area image; The size determination unit is used to perform weighted calculation according to the multiple shadow distance information and the position information to obtain the size information of the target object.

8. A cooking device, characterized in that: The cooking device comprises a plurality of light sources and a detection device as claimed in claim 7.

9. The cooking device according to claim 8, characterized in that: The cooking device comprises a plurality of side walls, and a plurality of light sources are arranged on the plurality of side walls at intervals.

10. A cooking device, characterized in that: It includes at least one processor and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the detection method as described in any one of claims 1 to 6 by executing the instructions stored in the memory.

Images