WO2024048741A1 - 調理動作推定装置、調理動作推定方法、および、調理動作推定プログラム - Google Patents
調理動作推定装置、調理動作推定方法、および、調理動作推定プログラム Download PDFInfo
- Publication number
- WO2024048741A1 WO2024048741A1 PCT/JP2023/031880 JP2023031880W WO2024048741A1 WO 2024048741 A1 WO2024048741 A1 WO 2024048741A1 JP 2023031880 W JP2023031880 W JP 2023031880W WO 2024048741 A1 WO2024048741 A1 WO 2024048741A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- cooking
- video
- action
- hand
- motion estimation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/251—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving models
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Definitions
- the present invention relates to a cooking motion estimation device, a cooking motion estimation method, and a cooking motion estimation program.
- Patent Document 1 discloses a technique for creating a recipe that captures the entire cooking process including cooking operations by capturing images with a camera fixed to a range hood.
- Patent Document 2 discloses a technique for generating a short video suitable for viewing by customers in a food section of a supermarket or the like from a video of a cooking scene.
- Patent Document 3 discloses a technology that allows a user to estimate the usage amount of a food ingredient or seasoning using only a video taken from above by a camera while cooking.
- Patent Document 4 discloses that the line of sight direction is recognized based on the position of the user's eyeballs from a cooking video taken from the front using two cameras fixed in the kitchen, and the user's current position and A technique for estimating work content from body orientation and line of sight direction has been disclosed.
- the present invention has been made in view of the above-mentioned problem, and the hand area estimated from the coordinates of the joint points recognized by posture recognition for each video frame overlaps with the cooking utensil area recognized by object recognition. It is an object of the present invention to provide a cooking motion estimation device, a cooking motion estimation method, and a cooking motion estimation program that can determine when the cooking utensil is being used and estimate the cooking motion from the type of the cooking utensil used. purpose.
- a cooking motion estimation device that includes a storage section and a control section, the storage section including a video database that stores cooking behavior videos of each user.
- the control unit includes a hand estimation unit that identifies the coordinates of joint points for each video frame forming the cooking action video and estimates a hand region, which is a coordinate region of the hand, based on posture recognition technology; a cooking utensil identification unit that specifies a cooking utensil area, which is a coordinate area of a cooking utensil, for each of the video frames constituting the cooking action video based on a recognition technology, and when the hand area and the cooking utensil area overlap; , a cooking operation estimator that estimates the cooking operation for each video frame from the type of the cooking utensil.
- the control unit includes a time setting unit that sets an elapsed time in association with the video frame, and a time setting unit that sets an elapsed time in association with the video frame, and a time setting unit that sets the cooking operation based on the cooking operation for each video frame.
- the present invention is characterized in that it further includes a classification calculation unit that calculates the cooking time and work amount for each cooking operation classification whose characteristics are identified.
- control unit may calculate a representative cooking time value for each cooking operation category and a cooking amount based on the cooking time and the work amount for each cooking operation category of all the users.
- the present invention is characterized in that it further includes a representative value acquisition unit that acquires a representative value of workload.
- control unit may determine whether or not the cooking time and/or the amount of work are outliers based on the representative value of cooking time and/or the representative value of work amount.
- the cooking method is characterized by further comprising an outlier identifying section that identifies the cooking action video in which the action is recorded.
- the cooking action video is set with attribute data indicating the user's attributes
- the classification calculation unit is configured to calculate the attribute data
- the method is characterized in that the cooking time and the amount of work are calculated for each attribute and each cooking operation category based on the cooking operation.
- the time setting unit further acquires order data of the cooking operation based on the cooking operation for each video frame
- the control unit further acquires order data of the cooking operation based on the cooking operation for each video frame.
- the cooking method further includes a cooking behavior acquisition unit that acquires cooking behavior data of the user based on the cooking time and the amount of work for each category, and the order data.
- the storage unit uses hand video frames in which a plurality of hand movements during cooking are recorded as teacher data, and inputs the video frames constituting the cooking action video.
- a model database storing a posture recognition model whose output is the hand region, and the hand estimator uses the posture recognition model to estimate the joints for each video frame constituting the cooking action video.
- the present invention is characterized in that the coordinates of a point are specified and the hand area, which is a coordinate area of the hand, is estimated.
- the storage unit uses a cooking utensil video frame in which a plurality of the cooking utensils are recorded as training data, inputs the video frame constituting the cooking action video, and outputs further comprising a model database storing an object recognition model in which the cooking utensil area is the cooking utensil region, and the cooking utensil specifying unit uses the object recognition model to determine the cooking utensil area for each of the video frames constituting the cooking action video.
- the method is characterized in that the cooking utensil area is specified as a coordinate area of the utensil.
- the attribute is a degree of cooking skill for identifying whether someone is good at cooking or not good at cooking.
- the cooking action video is a video recording the user's cooking from the side in any kitchen including the user's home kitchen.
- the storage unit may use the cooking video in which the hand region is labeled as training data, the hand region and the cooking utensil region as explanatory variables, and the cooking motion as a target variable.
- model storage means for storing a cooking motion estimation model that is a machine learning model, and the cooking motion estimation means uses the cooking motion estimation model when the hand region and the cooking utensil region overlap, The method is characterized in that the cooking operation for each video frame is estimated from the type of the cooking utensil.
- control unit may determine the ingredients for each of the video frames constituting the cooking action video based on the object recognition technology or the image region division technology for the video frames.
- the present invention is characterized by further comprising a foodstuff specifying means for specifying a foodstuff area that is a coordinate area of .
- the food specifying means further estimates intake nutrients from the food.
- the cooking motion estimation means further includes, when the hand region and the food material region overlap, or when the cooking utensil region and the food material region overlap, the cooking motion estimation means
- the method is characterized in that the cooking operation for each video frame is estimated from the type of video frame.
- the control unit specifies a seasoning region, which is a coordinate region of a seasoning, for each of the video frames constituting the cooking action video, based on the object recognition technology.
- the present invention is characterized by further comprising seasoning identifying means.
- the cooking motion estimation means further estimates the cooking motion for each video frame from the type of the seasoning when the hand region and the seasoning region overlap. It is characterized by
- the cooking action estimation method is a cooking action estimation method for causing a cooking action estimation device including a storage unit and a control unit to perform the cooking action estimation method, wherein the storage unit stores cooking action videos of each user.
- a video database to be stored; and based on posture recognition technology executed by the control unit, coordinates of joint points are specified for each video frame constituting the cooking action video, and a hand region that is a coordinate region of the hand is specified.
- the cooking action estimation program is a cooking action estimation program to be executed by a cooking action estimation device including a storage unit and a control unit, and the storage unit stores cooking action videos of each user.
- a video database to be stored; in the control unit, based on posture recognition technology, coordinates of joint points are specified for each video frame constituting the cooking action video, and a hand region that is a coordinate region of the hand is estimated; a cooking utensil identification step of specifying a cooking utensil area, which is a coordinate area of the cooking utensil, for each of the video frames constituting the cooking action video based on object recognition technology; If the cooking utensil areas overlap, a cooking action estimating step of estimating the cooking action for each video frame from the type of the cooking utensil is performed.
- the present invention it is possible to introduce an index that does not depend on the subjectivity of the observer into the observation of cooking behavior, reduce the effort required to observe behavior, and realize a survey targeting a large number of consumers. play. Furthermore, according to the present invention, since the behavioral video can be taken by the consumer himself using his own terminal such as a smartphone, it is not necessary to use special filming equipment or an observer's visit to the consumer's home. This has the effect that it is no longer necessary. Further, according to the present invention, it is possible to provide an objective and quantitative index of a consumer's cooking behavior from a cooking video taken by the consumer.
- the present invention by being able to quantitatively evaluate the time and amount of work for each cooking operation category, it is possible to extract actions that the user feels are burdensome during cooking, and to identify users who are performing characteristic actions. It has the effect of being able to do it. Further, according to the present invention, by using a moving image captured from the side rather than from an overhead view, it is possible to appropriately capture the vertical movement of the hand when cutting food with a knife, for example. . As a result, according to the present invention, it is possible to appropriately estimate the amount of work for each cooking operation (step).
- the cooking utensil is used. This has the effect that the cooking operation can be estimated from the type of cooking utensil used. Further, according to the present invention, from the cooking video data taken by the consumer himself/herself, the posture of the person in each frame of the video is recognized, the coordinates of each joint point are extracted, and the cooking utensils in each frame of the video are recognized.
- the type of cooking utensil and its coordinates are extracted, the cooking process is classified based on the extracted joint point data and cooking utensil data for each frame, and cooking behavior data such as time, order, amount of work, etc. of the classified cooking process is collected. This has the effect that it can be created.
- FIG. 1 is a block diagram showing an example of the configuration of a cooking motion estimation device according to the present embodiment.
- FIG. 2 is a flowchart illustrating an example of the cooking motion estimation process in this embodiment.
- FIG. 3 is a diagram illustrating an example of the cooking motion estimation process in this embodiment.
- FIG. 4 is a diagram illustrating an example of the cooking motion estimation process in this embodiment.
- FIG. 5 is a diagram illustrating an example of the cooking motion estimation process in this embodiment.
- FIG. 6 is a diagram illustrating an example of the cooking motion estimation process in this embodiment.
- FIG. 7 is a diagram illustrating an example of the cooking motion estimation process in this embodiment.
- FIG. 8 is a diagram showing an example of the cooking behavior analysis results in this embodiment.
- FIG. 1 is a block diagram showing an example of the configuration of a cooking motion estimation device according to the present embodiment.
- FIG. 2 is a flowchart illustrating an example of the cooking motion estimation process in this embodiment.
- FIG. 3 is a diagram illustrating
- FIG. 9 is a diagram showing an example of the cooking behavior analysis results in this embodiment.
- FIG. 10 is a diagram showing an example of the cooking behavior analysis results in this embodiment.
- FIG. 11 is a diagram showing an example of image region division in this embodiment.
- FIG. 12 is a diagram illustrating an example of cooking behavior analysis processing in this embodiment.
- the cooking motion estimation system according to the present embodiment can be configured by functionally or physically distributing and integrating arbitrary units (stand-alone type or system type).
- FIG. 1 is a block diagram showing an example of the configuration of a cooking motion estimation device 200 in this embodiment.
- the terminal device 100 is not only a digital camera or a web camera, but also a mobile terminal such as a mobile phone, a smartphone, a tablet terminal, a PHS or a PDA (Personal Digital Assistant), or a commonly available desktop or notebook type.
- the information processing device may be an information processing device such as a personal computer.
- the terminal device 100 includes a control section 102, a storage section 106, and an input/output section 112, and each section included in the terminal device 100 is communicably connected via an arbitrary communication path.
- the input/output unit 112 has a function of inputting/outputting (I/O) data including moving images, and digitally converts images (still images and moving images) taken with an image sensor such as a CCD image sensor or a CMOS image sensor. It is an image input unit (for example, a camera, etc.) that records as data.
- the input/output unit 112 may include, for example, a key input unit, a touch panel, a control pad (eg, a touch pad, a game pad, etc.), a mouse, a keyboard, a microphone, and the like.
- the input/output unit 112 may include a display unit (for example, a display composed of a liquid crystal or organic EL, a monitor, a touch panel, etc.) that displays (input/output) information such as application software. .
- the input/output unit 112 may include an audio output unit (for example, a speaker, etc.) that outputs audio information as audio.
- the input/output unit 112 may also include a fingerprint sensor, a camera (for example, an infrared camera, etc.) that can be used for iris authentication or face authentication, and/or a biosensor such as a vein sensor.
- the terminal device 100 has a function of being communicably connected to other devices via the network 300 and communicating data with the other devices.
- the network 300 has a function of connecting the terminal device 100 and other devices so that they can communicate with each other, and is, for example, the Internet and/or a LAN (Local Area Network).
- the storage unit 106 stores various databases, tables, and/or files.
- the storage unit 106 stores computer programs for providing instructions to a CPU (Central Processing Unit) to perform various processes in cooperation with an OS (Operating System).
- a RAM Random Access Memory
- ROM Read Only Memory
- HDD Hard Disk Drive
- SSD Solid State Drive
- the storage unit 106 may store image data recorded by the input/output unit 112, data received via the network 300, and/or input data input via the input/output unit 112, etc. good.
- the control unit 102 is a CPU or the like that collectively controls the terminal device 100.
- the control unit 102 has an internal memory for storing control programs such as an OS, programs that define various processing procedures, required data, etc., and performs various information processing based on these stored programs. Execute.
- the control unit 102 acquires image data recorded by the input/output unit 112 , reads character data (URL, etc.) included in the image data, transmits and receives data via the network 300 , and performs data transmission and reception via the input/output unit 112 It is also possible to perform various processes such as acquiring input data inputted by the user and displaying the data (screen) on the input/output unit 112.
- cooking motion estimation device 200 may be an information processing device such as a personal computer or a workstation.
- the cooking motion estimation device 200 includes a control section 202, a storage section 206, and an input/output section 212, and each section of the cooking motion estimation device 200 is communicably connected via an arbitrary communication path. There is.
- the cooking motion estimation device 200 is connected to other devices via a network 300 so as to be able to communicate with each other.
- the input/output unit 212 may have a function of performing data input/output (I/O).
- the input/output unit 212 may be, for example, a key input unit, a touch panel, a control pad (eg, a touch pad, a game pad, etc.), a mouse, a keyboard, a microphone, or the like.
- the input/output unit 212 may be a display unit (for example, a display configured with a liquid crystal or organic EL, a monitor, a touch panel, etc.) that displays (input/output) information such as application software.
- the input/output unit 212 may be an audio output unit (for example, a speaker, etc.) that outputs audio information as audio.
- the input/output unit 212 may be an image input unit (for example, a camera, etc.) that records images (still images and moving images) captured by an image sensor such as a CCD image sensor or a CMOS image sensor as digital data. Further, the input/output unit 212 may be a fingerprint sensor, a camera (for example, an infrared camera, etc.) that can be used for iris authentication or face authentication, and/or a biosensor such as a vein sensor.
- an image input unit for example, a camera, etc.
- a camera for example, an infrared camera, etc.
- a biosensor such as a vein sensor.
- the storage unit 206 stores various databases, tables, and/or files.
- the storage unit 206 stores a computer program that cooperates with the OS to give commands to the CPU to perform various processes.
- the storage unit 206 is a storage means such as RAM, ROM, HDD, and/or SSD, and stores various databases and tables.
- the storage unit 206 includes a video database 206a, a model database 206b, and a cooking database 206c.
- the video database 206a stores videos.
- the video database 206a may store cooking behavior videos of each user.
- the cooking action video may be set in association with attribute data indicating the user's attributes.
- attributes include degree of cooking skill to identify whether one is good at cooking or not good at cooking, age, gender, presence or absence of various cooking skills, presence or absence of product usage experience, and cooking behavior characteristics (for example, frying vegetables in one meal) (or dividing the stir-fried vegetables into two meals, etc.), and/or the tendency of responses to various questionnaires.
- the cooking action video may be a video recording the user's cooking from the side in any kitchen including the home kitchen of each user. Further, the cooking action video may be one shot by the terminal device 100.
- the model database 206b stores various machine learning models.
- the model database 206b uses hand video frames in which a plurality of hand movements during cooking are recorded as teacher data, inputs as video frames constituting a cooking action video, and outputs a posture recognition model as a hand region. You may remember it.
- the model database 206b stores an object recognition model whose training data is a cooking utensil video frame in which a plurality of cooking utensils are recorded, whose input is a video frame constituting a cooking action video, and whose output is a cooking utensil area. It's okay.
- the model database 206b stores a cooking motion estimation model that is a machine learning model that uses cooking videos with labeled hand regions as training data, hand regions and cooking utensil regions as explanatory variables, and cooking motions as an objective variable. It's okay.
- the cooking database 206c stores cooking data.
- the cooking database 206c includes order data, cooking action data, posture recognition technology data, hand area data, object recognition technology data, cooking utensil area data, cooking action data, cooking action classification, cooking time, amount of work, and cooking time.
- a representative value, a representative work amount value, and/or an outlier value may be stored.
- the control unit 202 is a CPU or the like that centrally controls the cooking motion estimation device 200.
- the control unit 202 has an internal memory for storing control programs such as an OS, programs that define various processing procedures, required data, etc., and performs various information processing based on these stored programs. Execute. Functionally, the control unit 202 is separated from a hand estimation unit 202a, a cooking utensil identification unit 202b, a cooking action estimation unit 202c, a time setting unit 202d, a classification calculation unit 202e, a cooking action acquisition unit 202f, and a representative value acquisition unit 202g. It includes a value specifying section 202h, a food specifying section 202i, and a seasoning specifying section 202j.
- the hand estimation unit 202a identifies the coordinates of the joint points for each video frame that constitutes the cooking action video, and estimates the hand region that is the coordinate region of the hand.
- the hand estimating unit 202a may specify the coordinates of the joint points for each video frame that constitutes the cooking action video based on posture recognition technology, and estimate the hand region that is the coordinate region of the hand.
- the hand estimating unit 202a may use the posture recognition model to specify the coordinates of the joint points for each video frame constituting the cooking action video, and estimate the hand region that is the coordinate region of the hand.
- the cooking utensil specifying unit 202b specifies a cooking utensil area, which is a coordinate area of the cooking utensil, for each video frame constituting the cooking action video.
- the cooking utensil identification unit 202b may specify a cooking utensil area, which is a coordinate area of the cooking utensil, for each video frame constituting the cooking action video based on object recognition technology.
- the cooking utensil identification unit 202b may use the object recognition model to specify a cooking utensil area, which is a coordinate area of the cooking utensil, for each video frame constituting the cooking action video.
- the cooking utensil identification unit 202b may specify the type of cooking utensil.
- the cooking motion estimation unit 202c estimates the cooking motion for each video frame based on the type of cooking utensil. Here, if the hand region and the cooking utensil area overlap, the cooking action estimating unit 202c may estimate the cooking action for each video frame based on the type of cooking utensil.
- the cooking action estimation unit 202c may estimate the cooking action for each video frame from the type of cooking utensil using the cooking action estimation model. Further, the cooking motion estimation unit 202c may estimate the cooking motion for each video frame based on the type of food when the hand region and the food region overlap, or when the cooking utensil region and the food material region overlap. Furthermore, when the hand region and the seasoning region overlap, the cooking motion estimating unit 202c may estimate the cooking motion for each video frame based on the type of seasoning.
- the time setting unit 202d sets the elapsed time in association with the video frame.
- the time setting unit 202d may acquire cooking operation order data based on the cooking operation for each video frame.
- the category calculation unit 202e calculates the cooking time and work amount for each cooking operation category that identifies the characteristics of the cooking operation.
- the classification calculation unit 202e may calculate the cooking time and work amount for each cooking action classification that identifies the characteristics of the cooking action based on the cooking action for each video frame.
- the classification calculation unit 202e may calculate the cooking time and work amount for each attribute and cooking operation classification based on the attribute data and the cooking operation for each video frame.
- the cooking behavior acquisition unit 202f acquires the user's cooking behavior data.
- the cooking behavior acquisition unit 202f may acquire the user's cooking behavior data based on the cooking time and amount of work for each cooking operation category, and the order data. Further, the cooking behavior acquisition unit 202f may output (display) cooking behavior data.
- the representative value acquisition unit 202g acquires the cooking time representative value and the workload representative value for each cooking operation category.
- the representative value acquisition unit 202g may acquire the representative cooking time value and the representative amount of work for each cooking action category based on the cooking time and work amount for each cooking action category of all users.
- the representative value may be an average value, a median value, or the like.
- the outlier identification unit 202h identifies a cooking action video in which a cooking operation with an outlier cooking time and/or work amount is recorded.
- the outlier identification unit 202h identifies a cooking action video in which a cooking operation with an outlier cooking time and/or work amount is recorded based on the cooking time representative value and/or work amount representative value. It's okay.
- the food identifying unit 202i identifies a food region, which is a coordinate region of the food, for each video frame constituting the cooking action video.
- the food identifying unit 202i may identify a food region, which is a coordinate region of food, for each video frame constituting the cooking action video based on object recognition technology or image region division technology for video frames. good.
- the food identifying unit 202i may estimate intake nutrients from the food.
- the seasoning identifying unit 202j identifies a seasoning region, which is a coordinate region of a seasoning, for each video frame that constitutes a cooking action video.
- the seasoning specifying unit 202j may specify the seasoning area, which is the coordinate area of the seasoning, for each video frame forming the cooking action video based on object recognition technology.
- FIG. 2 is a flowchart illustrating an example of the cooking motion estimation process in this embodiment.
- the hand estimation unit 202a of the cooking motion estimation device 200 calculates joint points for each video frame constituting the cooking behavior video of each user stored in the video database 206a, based on posture recognition technology.
- the coordinates are specified, and the hand area, which is the coordinate area of the hand, is estimated (step SA-1).
- the cooking utensil identification unit 202b of the cooking action estimation device 200 determines the coordinate area of the cooking utensil for each video frame constituting the cooking action video of each user stored in the video database 206a.
- the cooking utensil area and the type of cooking utensil are specified (step SA-2).
- the cooking action estimating unit 202c of the cooking action estimating device 200 estimates the cooking action for each video frame based on the type of cooking utensil (step SA-3).
- the time setting unit 202d of the cooking motion estimation device 200 sets the elapsed time in association with the video frame (step SA-4).
- the time setting unit 202d of the cooking operation estimation device 200 obtains cooking operation order data based on the cooking operation for each video frame (step SA-5).
- the category calculation unit 202e of the cooking operation estimation device 200 calculates the cooking time and work amount for each cooking skill level and each cooking operation category based on the attribute data and the cooking operation for each video frame ( Step SA-6).
- the cooking behavior acquisition unit 202f of the cooking behavior estimation device 200 acquires the user's cooking behavior data based on the cooking time and work amount for each cooking behavior category, and the order data, and transmits the cooking behavior data to the input/output unit. 212 (step SA-7).
- the representative value acquisition unit 202g of the cooking operation estimation device 200 acquires the representative value of cooking time and the representative value of workload for each cooking operation category based on the cooking time and workload for each cooking operation category of all users. (Step SA-8).
- the outlier identifying unit 202h of the cooking operation estimation device 200 determines, based on the cooking time representative value and/or the workload representative value, the cooking operation in which the cooking operation with the outlier cooking time and/or workload is recorded.
- the action video is identified (step SA-9), and the process ends.
- FIGS. 3 to 7 are diagrams illustrating an example of the cooking motion estimation process in this embodiment.
- the cooking action video is input
- the body movement estimation module using AI identifies the joint coordinates of the whole body and the hand
- the cooking utensil detection module uses AI.
- a process of specifying the category and coordinates of the cooking utensil and outputting the cooking behavior category using the cooking behavior determination module is executed.
- a cooking utensil image in which a plurality of cooking utensils such as knives, chopsticks, spatulas, tongs, and scissors are recorded is created as learning data, and the cooking utensil area is We are building an object recognition model that is a machine learning model that outputs.
- accuracy calculation in this embodiment may be performed by the Benjamini-Hochberg method using False Discovery Rate.
- the output results are uploaded to the cloud by performing AI analysis. is output above.
- Cooking behavior is determined based on the output data using a predetermined algorithm.
- the cooking behavior determination process may be performed using not only cooking videos taken by HUT in each user's home kitchen but also cooking videos taken by CLT (Central Location Test) in the same standard kitchen. good.
- FIGS. 8 to 10 are diagrams showing examples of cooking behavior analysis results in this embodiment.
- the cooking behavior in each user's home kitchen is quantified for double-pot meat cooking in which cabbage is stir-fried in two batches, and double-pot meat cooking in which cabbage is stir-fried in one batch.
- the average cooking time of the stir-frying process from about 100 home cooks was approximately 7 minutes 45 seconds for one time of stir-frying cabbage; Second time: Approximately 8 and a half minutes. In this way, in this embodiment, the average cooking behavior pattern of consumers can be grasped numerically.
- FIG. 9 in this embodiment, by analyzing outliers, the cooking behavior of double-pot meat cooking in which cabbage is stir-fried in two batches and double-pot meat cooking in which cabbage is stir-fried in one batch is determined. You can check the behavior that is the issue. That is, as shown in FIG. 9, in this embodiment, (videos of) people whose actions were extreme are extracted, and the actions of these people can be confirmed.
- Figure 9 shows the results regarding the cooking time of the stir-frying process and the amount of work in the stir-frying process, and the average value is shown as a bar, and each point shows the amount of work required for each individual.
- the person who took the longest cooking time when frying twice, the person who took the shortest cooking time, and the top 3 people with the largest amount of work are identified as outliers.
- the three people who worked a lot were moving the ingredients most of the time during stir-frying. It can be assumed that this was done by the three people who had a heavy workload and were concerned about the food being burnt.
- the person who took the longest stir-fry time found that the finished cabbage and peppers were soft. This suggests that it was difficult to know the end point of the stir-fry, or that they preferred a softer finish.
- a stratified analysis of cooking time between a group of good cookers and a group of poor cookers is performed, and comparison results are obtained.
- the people who were good at cooking when the frying process was compared between the people who were good at cooking and the people who were not good at cooking, the people who were not good at cooking showed a significant difference in the cooking time for the cutting process. You can see that it is getting longer.
- stratified analysis based on demographics and the like becomes possible, and cooking tasks can be extracted from a new perspective.
- estimation may be performed using machine learning by inputting a feature vector in which feature amounts for each frame are arranged in time series.
- learning may be performed without using time information of input feature vectors, or learning may be performed using time information and a time series model.
- the output layer may be trained as a model that performs regression to the estimated cooking action category, or a model that performs a binary judgment on whether or not the action is the action may be trained for each estimated cooking action category. good.
- Models that do not use time information include deep learning models such as SVM (Support Vector Machine), convolutional neural networks, and Transformer; models that use time information include LSTM (Long Short-Term Memory) and Transformer.
- a deep learning model such as the following can be used.
- As the teacher data data obtained by manually adding correct answer labels to independently acquired cooking videos may be used.
- FIG. 11 is a diagram showing an example of image region division in this embodiment.
- either one of the object detection algorithm similar to the cooking utensil identification shown in FIG. 6 and the area segmentation (Semantic Segmentation) algorithm shown in FIG. 11 is used, or two methods are used.
- the object detection algorithm similar to the cooking utensil identification shown in FIG. 6 and the area segmentation (Semantic Segmentation) algorithm shown in FIG. 11
- two methods are used.
- these in combination to recognize food ingredients and estimate the nutrients ingested, it can be used to identify nutrients (groups) that are likely to be deficient and encourage users to consume those nutrients (groups).
- food is recognized mainly by its appearance (for example, shape, size, color, etc.), and by recognizing the food to be used, it is possible to determine what kind of nutrients and how much should be taken into the finished meal by cooking. This makes it possible to estimate whether it is possible.
- seasonings are recognized mainly from their appearance (for example, shape, size, color, etc.). Furthermore, in this embodiment, by combining object detection technology and OCR (Optical Character Reader), seasonings with similar appearances are recognized separately (for example, seasonings with similar appearances are recognized separately).
- FIG. 12 is a diagram illustrating an example of the cooking behavior analysis process using the microwave-specific seasoning according to the present embodiment.
- FIG. 12 is a diagram illustrating an example of cooking behavior analysis processing in this embodiment.
- the subsequent time periods are determined as three processes: "preparation (before heating),” “microwave heating/steaming,” and “plating (after heating).”
- the time period determined to be ⁇ preparation (before heating)'' is determined to be ⁇ putting ingredients in the pouch'', and ⁇ (3)
- the time period determined as ⁇ Plate (after heating)'' is determined as ⁇ Remove'', and (4)
- the time period that overlaps with the region and the time period determined as "preparation (before heating)” is determined to be “kneading", and (4) the time period determined as "cutting” is determined as the area of the knife.
- all or part of the processes described as being performed automatically can be performed manually, or all of the processes described as being performed manually can be performed manually.
- some of the steps can be performed automatically using known methods.
- each illustrated component is functionally conceptual, and does not necessarily need to be physically configured as illustrated.
- the cooking operation estimation device 200 etc., especially each processing function performed by the control unit, all or any part of the processing functions are implemented by a CPU and a program interpreted and executed by the CPU. Alternatively, it may be realized as hardware using wired logic.
- the program is recorded on a non-temporary computer-readable recording medium containing programmed instructions for causing the information processing device to execute the processing described in this embodiment, and is stored in the terminal device 100 as necessary. be read mechanically. That is, a storage unit such as a ROM or an HDD (Hard Disk Drive) stores a computer program that cooperates with the OS to give instructions to the CPU and perform various processes. This computer program is executed by being loaded into the RAM, and constitutes a control unit in cooperation with the CPU.
- this computer program may be stored in an application program server connected to the terminal device 100, the cooking motion estimation device 200, etc. via an arbitrary network 300, and may be stored in whole or in part as necessary. It is also possible to download.
- a program for executing the processing described in this embodiment may be stored in a non-temporary computer-readable recording medium, or may be configured as a program product.
- this "recording medium” refers to memory cards, USB (Universal Serial Bus) memory, SD (Secure Digital) cards, flexible disks, magneto-optical disks, ROMs, EPROMs (Erasable Programmable Read Only). Memory), EEPROM (registration) Trademark) (Electrically Erasable and Programmable Read Only Memory), CD-ROM (Compact Disk Read Only Memory), MO (Ma gneto-Optical disc), DVD (Digital Versatile Disk), Blu-ray (registered trademark) Disc, etc. shall include any “portable physical medium”.
- a "program” is a data processing method written in any language or writing method, and does not matter in the form of source code or binary code. Note that a "program” is not necessarily limited to a unitary structure, but may be distributed as multiple modules or libraries, or may work together with separate programs such as an OS to achieve its functions. Including things. Note that well-known configurations and procedures can be used for the specific configuration and reading procedure for reading the recording medium in each device shown in this embodiment, and the installation procedure after reading.
- the various databases stored in the storage unit are storage devices such as memory devices such as RAM and ROM, fixed disk devices such as hard disks, flexible disks, and optical disks, and are used for various processing and website provision. Stores programs, tables, databases, web page files, etc.
- the terminal device 100, the cooking motion estimation device 200, etc. may be configured as an information processing device such as a known personal computer or a workstation, or may be configured as the information processing device to which any peripheral device is connected. It's okay. Further, the terminal device 100, the cooking motion estimation device 200, etc. may be realized by installing software (including programs, data, etc.) that causes the devices to realize the processing described in this embodiment.
- dispersion and integration of devices is not limited to what is shown in the diagram, and all or part of them can be functionally or physically divided into arbitrary units according to various additions or functional loads. It can be configured in a distributed/integrated manner. That is, the embodiments described above may be implemented in any combination, or the embodiments may be implemented selectively.
- the present invention is useful in the food industry and the information technology industry that produces and provides application software such as recipe sites.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
Description
まず、本発明の概要を説明する。
本実施形態に係る調理動作推定システムは、任意の単位で機能的または物理的に分散・統合して(スタンドアローン型またはシステム型でも)構成することができる。本実施形態においては、端末装置100、および、調理動作推定装置200を通信可能に接続した調理動作推定システムの構成の一例について、図1を参照して説明する。図1は、本実施形態における調理動作推定装置200の構成の一例を示すブロック図である。
図1において、端末装置100は、デジタルカメラもしくはWebカメラだけでなく、携帯電話、スマートフォン、タブレット端末、PHSもしくはPDA(Personal Digital Assistants)等の携帯端末、または、一般に市販されるデスクトップ型もしくはノート型のパーソナルコンピュータ等の情報処理装置等であってもよい。
図1において、調理動作推定装置200は、パーソナルコンピュータ、または、ワークステーション等の情報処理装置であってもよい。調理動作推定装置200は、制御部202と記憶部206と入出力部212とを備えており、調理動作推定装置200が備えている各部は、任意の通信路を介して通信可能に接続されている。調理動作推定装置200は、ネットワーク300を介して、他の装置と相互に通信可能に接続されている。
本実施形態に係る調理動作推定処理の一例について、図2から図12を参照して説明する。図2は、本実施形態における調理動作推定処理の一例を示すフローチャートである。
本発明は、上述した実施形態以外にも、請求の範囲に記載した技術的思想の範囲内において種々の異なる実施形態にて実施されてよいものである。
102 制御部
106 記憶部
112 入出力部
200 調理動作推定装置
202 制御部
202a 手推定部
202b 調理器具特定部
202c 調理動作推定部
202d 時間設定部
202e 区分算出部
202f 調理行動取得部
202g 代表値取得部
202h 外れ値特定部
202i 食材特定部
202j 調味料特定部
206 記憶部
206a 動画データベース
206b モデルデータベース
206c 調理データベース
212 入出力部
300 ネットワーク
Claims (18)
- 記憶部と制御部とを備えた調理動作推定装置であって、
前記記憶部は、
各ユーザの調理行動動画を記憶する動画記憶手段、
を備え、
前記制御部は、
姿勢認識技術に基づいて、前記調理行動動画を構成する動画フレーム毎に、関節点の座標を特定し、手の座標領域である手領域を推定する手推定手段と、
物体認識技術に基づいて、前記調理行動動画を構成する前記動画フレーム毎に、調理器具の座標領域である調理器具領域を特定する調理器具特定手段と、
前記手領域と前記調理器具領域とが重なる場合、前記調理器具の種類から前記動画フレーム毎の調理動作を推定する調理動作推定手段と、
を備えたことを特徴とする調理動作推定装置。 - 前記制御部は、
前記動画フレームに経過時間を紐付けて設定する時間設定手段と、
前記動画フレーム毎の前記調理動作に基づいて、前記調理動作の特徴を識別する調理動作区分毎の調理時間および作業量を算出する区分算出手段と、
を更に備えたことを特徴とする請求項1に記載の調理動作推定装置。 - 前記制御部は、
全ての前記ユーザの前記調理動作区分毎の前記調理時間および前記作業量に基づいて、前記調理動作区分毎の調理時間代表値および作業量代表値を取得する代表値取得手段、
を更に備えたことを特徴とする請求項2に記載の調理動作推定装置。 - 前記制御部は、
前記調理時間代表値および/または前記作業量代表値に基づいて、外れ値となる前記調理時間および/または前記作業量の前記調理動作が記録されている前記調理行動動画を特定する外れ値特定手段、
を更に備えたことを特徴とする請求項3に記載の調理動作推定装置。 - 前記調理行動動画は、
前記ユーザの属性を示す属性データが紐付けて設定され、
前記区分算出手段は、
前記属性データ、および、前記動画フレーム毎の前記調理動作に基づいて、前記属性毎、且つ、前記調理動作区分毎の前記調理時間および前記作業量を算出することを特徴とする請求項2に記載の調理動作推定装置。 - 前記時間設定手段は、
更に、前記動画フレーム毎の前記調理動作に基づいて、前記調理動作の順序データを取得し、
前記制御部は、
前記調理動作区分毎の前記調理時間および前記作業量、ならびに、前記順序データに基づいて、前記ユーザの調理行動データを取得する調理行動取得手段、
を更に備えたことを特徴とする請求項2に記載の調理動作推定装置。 - 前記記憶部は、
複数の調理中の手の動きが記録された手動画フレームを教師データとし、入力を前記調理行動動画を構成する前記動画フレームとし、出力を前記手領域とする姿勢認識モデルを記憶するモデル記憶手段、
を更に備え、
前記手推定手段は、
前記姿勢認識モデルを用いて、前記調理行動動画を構成する前記動画フレーム毎に、前記関節点の座標を特定し、前記手の座標領域である前記手領域を推定することを特徴とする請求項1に記載の調理動作推定装置。 - 前記記憶部は、
複数の前記調理器具が記録された調理器具動画フレームを教師データとし、入力を前記調理行動動画を構成する前記動画フレームとし、出力を前記調理器具領域とする物体認識モデルを記憶するモデル記憶手段、
を更に備え、
前記調理器具特定手段は、
前記物体認識モデルを用いて、前記調理行動動画を構成する前記動画フレーム毎に、前記調理器具の座標領域である前記調理器具領域を特定することを特徴とする請求項1に記載の調理動作推定装置。 - 前記属性は、
料理得意、または、料理不得意を識別するための料理得意度合であることを特徴とする請求項5に記載の調理動作推定装置。 - 前記調理行動動画は、
前記各ユーザの家庭のキッチンを含む任意のキッチンでの当該ユーザの調理を側面から記録した動画であることを特徴とする請求項1に記載の調理動作推定装置。 - 前記記憶部は、
前記手領域をラベリングした調理動画を教師データとし、前記手領域および前記調理器具領域を説明変数とし、前記調理動作を目的変数とする機械学習モデルである調理動作推定モデルを記憶するモデル記憶手段、
を更に備え、
前記調理動作推定手段は、
前記手領域と前記調理器具領域とが重なる場合、前記調理動作推定モデルを用いて、前記調理器具の種類から前記動画フレーム毎の前記調理動作を推定することを特徴とする請求項1に記載の調理動作推定装置。 - 前記制御部は、
前記物体認識技術、または、前記動画フレームに対する画像領域分割技術に基づいて、前記調理行動動画を構成する前記動画フレーム毎に、食材の座標領域である食材領域を特定する食材特定手段、
を更に備えたことを特徴とする請求項1に記載の調理動作推定装置。 - 前記食材特定手段は、
更に、前記食材から、摂取栄養素を推定することを特徴とする請求項12に記載の調理動作推定装置。 - 前記調理動作推定手段は、
更に、前記手領域と前記食材領域とが重なる場合、または、前記調理器具領域と前記食材領域とが重なる場合、前記食材の種類から前記動画フレーム毎の前記調理動作を推定することを特徴とする請求項12に記載の調理動作推定装置。 - 前記制御部は、
前記物体認識技術に基づいて、前記調理行動動画を構成する前記動画フレーム毎に、調味料の座標領域である調味料領域を特定する調味料特定手段、
を更に備えたことを特徴とする請求項1に記載の調理動作推定装置。 - 前記調理動作推定手段は、
更に、前記手領域と前記調味料領域とが重なる場合、前記調味料の種類から前記動画フレーム毎の前記調理動作を推定することを特徴とする請求項15に記載の調理動作推定装置。 - 記憶部と制御部とを備えた調理動作推定装置に実行させるための調理動作推定方法であって、
前記記憶部は、
各ユーザの調理行動動画を記憶する動画記憶手段、
を備え、
前記制御部で実行させる、
姿勢認識技術に基づいて、前記調理行動動画を構成する動画フレーム毎に、関節点の座標を特定し、手の座標領域である手領域を推定する手推定ステップと、
物体認識技術に基づいて、前記調理行動動画を構成する前記動画フレーム毎に、調理器具の座標領域である調理器具領域を特定する調理器具特定ステップと、
前記手領域と前記調理器具領域とが重なる場合、前記調理器具の種類から前記動画フレーム毎の調理動作を推定する調理動作推定ステップと、
を含むことを特徴とする調理動作推定方法。 - 記憶部と制御部とを備えた調理動作推定装置に実行させるための調理動作推定プログラムであって、
前記記憶部は、
各ユーザの調理行動動画を記憶する動画記憶手段、
を備え、
前記制御部において、
姿勢認識技術に基づいて、前記調理行動動画を構成する動画フレーム毎に、関節点の座標を特定し、手の座標領域である手領域を推定する手推定ステップと、
物体認識技術に基づいて、前記調理行動動画を構成する前記動画フレーム毎に、調理器具の座標領域である調理器具領域を特定する調理器具特定ステップと、
前記手領域と前記調理器具領域とが重なる場合、前記調理器具の種類から前記動画フレーム毎の調理動作を推定する調理動作推定ステップと、
を実行させるための調理動作推定プログラム。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2024544572A JPWO2024048741A1 (ja) | 2022-09-01 | 2023-08-31 | |
| US19/063,840 US20250201026A1 (en) | 2022-09-01 | 2025-02-26 | Cooking motion estimation device, cooking motion estimation method, and cooking motion estimation program |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2022-139367 | 2022-09-01 | ||
| JP2022139367 | 2022-09-01 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US19/063,840 Continuation US20250201026A1 (en) | 2022-09-01 | 2025-02-26 | Cooking motion estimation device, cooking motion estimation method, and cooking motion estimation program |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024048741A1 true WO2024048741A1 (ja) | 2024-03-07 |
Family
ID=90097943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2023/031880 Ceased WO2024048741A1 (ja) | 2022-09-01 | 2023-08-31 | 調理動作推定装置、調理動作推定方法、および、調理動作推定プログラム |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US20250201026A1 (ja) |
| JP (1) | JPWO2024048741A1 (ja) |
| WO (1) | WO2024048741A1 (ja) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119960318A (zh) * | 2025-04-11 | 2025-05-09 | 深圳鸿博智成科技有限公司 | 基于机器学习的智能烹饪优化系统及方法 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005088542A1 (ja) * | 2004-03-17 | 2005-09-22 | Matsushita Electric Industrial Co., Ltd. | 食材調理操作認識システム及び食材調理操作認識プログラム |
| JP2018005752A (ja) * | 2016-07-07 | 2018-01-11 | 株式会社日立システムズ | 振る舞い検知システム |
| JP2021022119A (ja) * | 2019-07-26 | 2021-02-18 | 日本電気株式会社 | 監視装置、監視方法、および、プログラム、並びに、監視システム |
-
2023
- 2023-08-31 WO PCT/JP2023/031880 patent/WO2024048741A1/ja not_active Ceased
- 2023-08-31 JP JP2024544572A patent/JPWO2024048741A1/ja active Pending
-
2025
- 2025-02-26 US US19/063,840 patent/US20250201026A1/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005088542A1 (ja) * | 2004-03-17 | 2005-09-22 | Matsushita Electric Industrial Co., Ltd. | 食材調理操作認識システム及び食材調理操作認識プログラム |
| JP2018005752A (ja) * | 2016-07-07 | 2018-01-11 | 株式会社日立システムズ | 振る舞い検知システム |
| JP2021022119A (ja) * | 2019-07-26 | 2021-02-18 | 日本電気株式会社 | 監視装置、監視方法、および、プログラム、並びに、監視システム |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119960318A (zh) * | 2025-04-11 | 2025-05-09 | 深圳鸿博智成科技有限公司 | 基于机器学习的智能烹饪优化系统及方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| US20250201026A1 (en) | 2025-06-19 |
| JPWO2024048741A1 (ja) | 2024-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11175790B2 (en) | System and method for providing real-time product interaction assistance | |
| JP7851769B2 (ja) | 統合ロボットキッチンシステム、及び、ロボットキッチンシステム | |
| RU2668408C2 (ru) | Устройства, системы и способы виртуализации зеркала | |
| US9646340B2 (en) | Avatar-based virtual dressing room | |
| US20210133850A1 (en) | Machine learning predictions of recommended products in augmented reality environments | |
| CN107862018B (zh) | 食材烹饪方法的推荐方法及装置 | |
| Shimada et al. | Kitchen scene context based gesture recognition: A contest in ICPR2012 | |
| JP2016009211A (ja) | ユーザ嗜好に合わせたワイン自動選定システム | |
| CN103810284A (zh) | 一种厨房管理方法和装置 | |
| CN108197635B (zh) | 烹饪方式的展示方法及装置、抽油烟机 | |
| WO2017005014A1 (zh) | 搜索匹配商品的方法及装置 | |
| US20210208753A1 (en) | Generating a user-specific user interface | |
| CN112579873A (zh) | 烹饪食谱推荐方法、装置、存储介质及电子设备 | |
| Plötz et al. | Activity recognition and healthier food preparation | |
| US20250201026A1 (en) | Cooking motion estimation device, cooking motion estimation method, and cooking motion estimation program | |
| JP2019219766A (ja) | 分析装置、分析システム、及び分析プログラム | |
| CN111241901A (zh) | 信息处理装置、存储介质及信息处理方法 | |
| JP7741074B2 (ja) | 行動認識装置、行動認識方法、及びプログラム | |
| Souček et al. | Showhowto: Generating scene-conditioned step-by-step visual instructions | |
| Castillo-Ortiz et al. | Evaluating culinary skill transfer: A deep learning approach to comparing student and chef dishes using image analysis | |
| CN105139248A (zh) | 一种可穿戴物品呈现的方法及装置 | |
| JP6868673B1 (ja) | 情報処理装置、情報処理方法、および情報処理プログラム | |
| EP4607432A1 (en) | Evaluation value estimation system, evaluation value estimation method, evaluation value estimation device, evaluation value estimation program, and storage medium on which said program is recorded | |
| CN119854628B (zh) | 一种图像拍摄交互方法及拍摄终端 | |
| Kim et al. | Mediating individual affective experience through the emotional photo frame |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23860503 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024544572 Country of ref document: JP |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2501001215 Country of ref document: TH |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 23860503 Country of ref document: EP Kind code of ref document: A1 |