Meal monitoring system

Abstract

To provide a meal monitoring system that obtains an intake situation of a meal of an object person in more detail.SOLUTION: A meal monitoring system 10 which includes an imaging unit installed on a table and a monitoring device 20, and can communicate with a management server 40, includes: an imaging section (camera 36) that can capture images of a meal of an object person to be watched or monitored; an imaging control section (control section 22) that controls the imaging section so as to capture images in chronological order during a meal; and an acquisition processing section (control section 22) that processes the images to detect a meal amount and acquires an intake situation of a meal based on changes in the meal amount. A manager K of the object person accesses the management server 40 via a network NW from a mobile terminal M of the object person, a personal computer or the like.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] This specification discloses a dietary monitoring system. [Background technology]

[0002] Conventionally, there have been proposals for monitoring the eating status of a subject for the purpose of managing the eating habits of the subject, etc. For example, Patent Document 1 describes a method for processing images at the start and end of a meal to quantify the amount of leftover food, and for calculating the calorie intake and the amount of ingredients that are lacking due to the leftover food. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2004-154261 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the above-mentioned Patent Document 1, it is possible to obtain the intake result of the entire meal from images taken at the start and end of the meal. However, this is insufficient for obtaining detailed intake conditions of the meal, such as changes in the intake pace during the meal.

[0005] The main objective of the present disclosure is to obtain more detailed information about a subject's dietary intake. [Means for solving the problem]

[0006] In order to achieve the above-mentioned main object, the present disclosure has adopted the following means.

[0007] The dietary monitoring system of the present disclosure comprises: An imaging unit capable of imaging the subject's meal; An imaging control unit that controls the imaging unit so as to capture images in time series during a meal; an acquisition processing unit that processes the image to detect an amount of food eaten and acquires a food intake status based on a change in the amount of food eaten; The gist of the invention is to provide the following:

[0008] In the dietary monitoring system of the present disclosure, images of a meal are captured in chronological order, the images are processed to detect the amount of food eaten, and the dietary intake status of the subject is obtained based on changes in the amount of food eaten, making it possible to obtain more detailed information about the subject's dietary intake status. [Brief description of the drawings]

[0009] [Figure 1] 1 is a diagram showing an outline of the configuration of a residence 1 equipped with a meal monitoring system 10. [Diagram 2] 1 is a block diagram showing an outline of the configuration of a meal monitoring system 10. [Diagram 3] 11 is a flowchart showing an example of a meal monitoring process. [Figure 4] 11 is a flowchart showing an example of an intake status acquisition process. [Diagram 5] FIG. 13 is an explanatory diagram showing an example of an intake state. [Figure 6] 11 is a flowchart showing an example of an intake status reporting process. [Figure 7] FIG. 11 is an explanatory diagram showing an example of notification content. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] An embodiment of the present disclosure will be described with reference to the drawings. Fig. 1 is a configuration diagram showing an outline of the configuration of a residence 1 equipped with a meal monitoring system 10. Fig. 2 is a block diagram showing an outline of the configuration of the meal monitoring system 10.

[0011] Residence 1 is the residence of subject T to be watched over or monitored, and is equipped with a meal monitoring system 10 for monitoring (acquiring) the meal intake status of subject T. Subject T is, for example, an elderly person living alone, but may also be a person recuperating. Residence 1 may be a one-room type residence, or a residence with a divided living room, dining room, and kitchen. Residence 1 is also equipped with a table (dining table) 2, chairs 4, a refrigerator 6, a microwave 8, lighting 9, and the like. For example, subject T sits on chair 4 and eats a meal at table 2.

[0012] The meal monitoring system 10 includes an imaging unit 30 installed on the table 2 and a monitoring device 20, and is configured to be able to communicate with a management server 40. The imaging unit 30 includes a base 32 installed on the table 2, an arm 34 supported by the base 32, and a camera 36 attached to the upper end of the arm 34. The camera 36 is capable of capturing an image of at least an imaging range A (shown by a dotted line in FIG. 1) on the table 2. The imaging range A is the range in which the meal (dishes) is served. Therefore, the camera 36 is capable of capturing an image of the meal (dishes, tray) served within the imaging range A. Note that the imaging unit 30 may be configured such that the camera 36 can capture an image of the imaging range A, and for example, the camera 36 may be disposed within the lighting 9.

[0013] The monitoring device 20 includes a control unit 22, a storage unit 24, and a communication unit 26. The control unit 22 is configured as a microprocessor with a CPU as its core, and includes a ROM, a RAM, and the like in addition to the CPU. The control unit 22 outputs an image capture instruction to the camera 36 of the image capture unit 30, inputs an image captured by the camera 36 and detection signals from various sensors, and executes various processes including image processing of the input image. Examples of the various sensors include a human sensor 2a that detects a target person T provided on the underside of the table 2, an opening / closing sensor 6a that detects the opening / closing operation of the door of the refrigerator 6, and an opening / closing sensor 8a that detects the opening / closing operation of the door of the microwave oven 8. The human sensor 2a is configured as, for example, an infrared sensor. Also, each of the opening / closing sensors 6a and 8a is configured as, for example, a magnetic detection sensor. The storage unit 24 is configured as an HDD, an SSD, or the like, and stores various information such as an image captured by the camera 36 and the processing results of the control unit 22. The communication unit 26 transmits various information such as the processing results of the control unit 22 to the management server 40 via a network NW such as the Internet.

[0014] The management server 40 comprises a control unit 42, a storage unit 44, and a communication unit 46. The control unit 42 is configured as a microprocessor with a CPU at its core, and is equipped with a ROM, a RAM, etc. in addition to the CPU. The storage unit 44 is configured with an HDD, an SSD, etc., and receives and stores information on the subject T transmitted from the monitoring device 20. The communication unit 46 is connected to the communication units 26 of one or more monitoring devices 20 via the network NW, and exchanges information with the communication units 26 of the monitoring devices 20. In addition, the administrator K of the subject T can access the management server 40 via the network NW from his / her own mobile terminal M, personal computer, etc.

[0015] The following is a description of the operation of the monitoring device 20 when monitoring (obtaining) the food intake status of the subject T. Fig. 3 is a flowchart showing an example of a meal monitoring process. This process is executed by the control unit 22 of the monitoring device 20.

[0016] In the meal monitoring process, the control unit 22 first judges whether or not it is time to start monitoring the intake status of the meal (S100). In this embodiment, the control unit 22 judges that it is time to start monitoring when it detects the subject T (subject T sitting on the chair 4) around the table 2 based on the detection signal from the human sensor 2a, detects the opening and closing operation of the door of the refrigerator 6 based on the detection signal from the opening and closing sensor 6a, or detects the opening and closing operation of the door of the microwave oven 8 based on the detection signal from the opening and closing sensor 8a. When it judges that it is time to start monitoring, the control unit 22 causes the camera 36 to capture the image of the imaging range A and processes the image (S110). Next, the control unit 22 judges whether or not it has detected a meal (cooking) from the image as a result of the image processing in S110 (S120) and whether or not it has detected at least one of the movement of the hand of the subject T and the movement of eating utensils (S130). In the image processing at S110, the presence or absence of tableware (plates) or food (dishes) in the image, the presence or absence and movement of the subject T's hands and eating utensils such as chopsticks, spoons, and forks are determined based on feature amounts such as the shapes, areas, and colors (pixel values) of the tableware, food, hands, and eating utensils. Note that each feature amount is obtained by well-known machine learning using an image in which the presence or absence of tableware, food, hands, and eating utensils, and the contents of the meal (type of food) have been determined in advance, and for example, those stored in a discrimination model (not shown) in the storage unit 24 are used.

[0017] When the control unit 22 determines that no meal has been detected from the image, or that even if a meal has been detected, the control unit 22 has not detected hand movement or eating utensil movement, it determines whether a predetermined time has passed since the determination in S100 (S140). When the control unit 22 determines that the predetermined time has not passed, it returns to S110. On the other hand, when the control unit 22 determines that the predetermined time has passed without detecting a meal, hand movement, or eating utensil movement from the image, it determines that a meal has not started and returns to S100. When the control unit 22 determines that a meal has been detected from the image and that hand movement or eating utensil movement has been detected, it further processes the image (start image) to detect the amount of food eaten at the start S(0) (initial amount of food eaten, maximum amount of food eaten) based on the area of ​​the food for each dish (S150), and executes an intake status acquisition process (S160). In S150, the control unit 22 detects the area of ​​the food for each dish from the image and calculates the area of ​​the area to calculate the amount of food eaten S(0) for each dish. The control unit 22 also determines the detected meal contents based on the feature quantities of the discrimination model described above. If information on the meal contents can be appropriately acquired, such as the meal of the subject T being arranged or cooked by the manager K or delivered by a food delivery company, the control unit 22 may acquire the meal contents and the meal amount S(0) based on that information.

[0018] Fig. 4 is a flow chart showing an example of the intake status acquisition process. Fig. 5 is an explanatory diagram showing an example of the acquired intake status. In S150, as shown in Fig. 5, for example, four dishes a-d and their meal contents and meal amounts S(0) are detected from the start image. As an example, dish a is "rice" (staple food) with meal amount Sa(0), dish b is "hamburger steak" (main dish) with meal amount Sb(0), dish c is "vegetable salad" (side dish) with meal amount Sc(0), and dish d is "miso soup" (soup) with meal amount Sd(0).

[0019] In the intake status acquisition process of Fig. 4, the control unit 22 waits for the timing to capture an image (S200), and when it determines that the timing has come, it causes the camera 36 to capture an image (meal image) (S210). The timing to capture an image is set to occur at a predetermined time interval, for example, every tens of seconds or every few minutes (for example, every minute). Next, the control unit 22 processes the captured meal images to detect the amount of food eaten S(n) based on the area of ​​the food for each dish (S220). Note that the n in the amount of food eaten S(n) indicates the amount of food eaten detected from the image captured at the nth capture timing in the intake status acquisition process, and is assigned in order starting from value 1.

[0020] Next, the control unit 22 calculates the difference ΔS between the previously detected amount of food S(n-1) and the current amount of food S(n), i.e., the difference ΔS (amount of change) between the amount of food S(n) detected from two images that are one after the other in the time series, for each dish, and divides it by the amount of food eaten S(0) at the start to calculate the intake pace (decrease rate) P for each dish (S230). The control unit 22 then determines whether the intake of the meal is complete and whether all the dishes have been cleared (S240). The control unit 22 determines that the intake of the meal is complete when the amount of food eaten S(n) of each dish in the eating image processed in S220 is all zero. The control unit 22 also determines that the dishes have been cleared when no dishes are detected in the eating image processed in S220. If there is food remaining on any of the dishes (if any amount of food eaten S(n) is not zero), the control unit 22 makes a negative determination in S240 and returns to S200 to repeat the process. That is, each time an image capture timing occurs, the control unit 22 causes the camera 36 to capture an image during a meal, detects the amount of food eaten S(n) for each dish, and repeats the process of dividing the difference ΔS from the previous time by the amount of food eaten S(0) at the start of the meal to calculate the intake pace P. This makes it possible to obtain the intake pace P during a meal in chronological order.

[0021] As shown in FIG. 5, the meal amounts Sa(1), Sb(1), Sc(1), and Sd(1) of each of the dishes a to d are detected from the image captured at the first image capture timing t1. In addition, the difference ΔS between these meal amounts and the meal amounts Sa(0), Sb(0), Sc(0), and Sd(0) at the start are calculated, and the intake paces Pa, Pb, Pc, and Pd are calculated by dividing the difference ΔS by the meal amounts Sa(0), Sb(0), Sc(0), and Sd(0) at the start. For example, the first difference ΔS of the dish a is Sa(0)-Sa(1), and the intake pace Pa is ΔS / Sa(0). In addition, at the image capture timing t1, for example, the intake pace Pc of the "vegetable salad" of the dish c is the highest (e.g., 11%), the next highest intake pace Pd of the "miso soup" of the dish d is the highest (e.g., 6%), and the intake paces Pa and Pb of the "rice" and "hamburger steak" are not consumed and are 0%. Similar processing is also performed at the second imaging timing t2 and the third imaging timing t3 to calculate the meal amount S(n) and the intake pace P. From such intake status, it is possible to grasp, for example, the tendency of subject T to mainly consume "vegetable salad" and "miso soup" at the start of a meal (for example, from t1 to t3).

[0022] Furthermore, when the control unit 22 determines that the meal has been completed or all the tableware has been cleared while repeating the processes of S200 to S240, it sets the meal amount S(n) calculated last for each tableware as the meal amount S(E) at the end (S250). Next, the control unit 22 calculates the intake ratio R for each tableware by dividing the difference between the meal amount S(0) at the start and the meal amount S(E) at the end by the meal amount S(0) (S260). That is, the intake ratio R(%) is calculated as (S(0)-S(E)) / S(0). The control unit 22 then transmits the intake status including the intake pace P and the intake ratio R to the management server 40 (S270), and ends the intake status acquisition process. Note that the intake pace P may transmit all time-series data, or may calculate and transmit the average intake pace Pave, which is the average value of the data.

[0023] In S250, if the meal (dish) has a meal amount S(n) of 0 detected at any time during the intake status acquisition process, the meal amount S(E) at the end is set to 0. In the example of FIG. 5, the meal amount Sc(*1) of the "vegetable salad" in dish c is 0 at the image capture time t*1, and the meal amount Sd(*2) of the "miso soup" in dish d is 0 at the image capture time t*2. Therefore, the meal amount Sc(E) and the meal amount Sd(E) are both 0. In addition, the intake ratios Rc and Rd are both 100%. In addition, when the dish is cleared with food remaining on it, the control unit 22 sets the meal amount S(n) detected from the eating image captured immediately before that to the meal amount S(E) at the end. For example, if the image captured at imaging timing t*3 in Fig. 5 is the last image captured when the dishes are cleared, the meal amounts Sa(*3) and Sb(*3) detected at imaging timing t*3 become the meal amounts Sa(E) and Sb(E) of dishes a and b, respectively. For example, the meal amount Sa(E) is set to 60% of the meal amount Sa(0), and the intake ratio Ra is set to 40%, and the meal amount Sb(E) is set to 15% of the meal amount Sb(0), and the intake ratio Rb is set to 85%.

[0024] In this embodiment, the intake pace P is not calculated after the meal amount S(n) becomes 0. Therefore, for example, the intake pace Pc is not calculated after the imaging timing t*1, and the intake pace Pd is not calculated after the imaging timing t*2. In this way, when calculating the average intake pace Pave, even if the total meal time is longer because another meal took longer, for example, the average intake pace Pave can be calculated appropriately based on the individual meal times until the meal with each dish is finished. For the same reason, the average intake pace Pave may be calculated excluding the time when the intake pace P is 0%.

[0025] Next, a description will be given of the operation of the management server 40. Fig. 6 is a flow chart showing an example of an intake status notifying process. This process is executed by the control unit 42 of the management server 40.

[0026] In the intake status notifying process, the control unit 42 first determines whether it is time to notify the intake status (S300). The timing for notifying the intake status may be, for example, periodically, such as at a predetermined time interval, when the intake status transmitted in S270 is received and stored in the storage unit 44 (when the meal is finished), or when a notification request is made by the manager K. If the control unit 42 determines that it is not time to notify, it ends the intake status notifying process.

[0027] Furthermore, when the control unit 42 determines in S300 that it is time to notify, it acquires the intake status of the corresponding subject T from the storage unit 44 (S310). Next, the control unit 42 sets the notification content (explanation of the intake status) based on the average intake pace Pave and the intake ratio R from the acquired intake status (S320). Next, the control unit 42 transmits the intake status and the notification content to the mobile terminal M of the manager K or the like by email or the like (S330), and ends the intake status notification process. Note that as the intake status, the overall status may be transmitted as shown in FIG. 5, or a part of the status such as the intake ratio R for each meal content and the average intake pace Pave may be transmitted.

[0028] FIG. 7 is an explanatory diagram showing an example of the notification contents. For example, the control unit 42 compares the average intake pace Pave for each meal content (dish) with a threshold value Pref (predetermined intake pace) and compares the intake ratio R for each meal content with a threshold value Rref (predetermined intake ratio) to set the notification contents. If any of the average intake paces Pave is equal to or greater than the threshold value Pref, the control unit 42 sets that there was no meal with a noticeable delay in the intake pace, and if any of the average intake paces Pave is less than the threshold value Pref, sets that there was a meal with a noticeable delay in the intake pace, including the meal content (dish name). In addition, if any of the intake ratios R is equal to or greater than the threshold value Rref, the control unit 42 sets that there was almost no leftovers, and if any of the intake ratios R is less than the threshold value Rref, sets that there was a meal with a lot of leftovers, including the meal content. The notification contents set in this way are transmitted together with the intake status, so that the manager K can easily grasp the overview of the intake status.

[0029] Here, the correspondence between the components of this embodiment and the components of the present disclosure will be clarified. The imaging unit 30 (camera 36) of this embodiment corresponds to the imaging section, the control unit 22 that executes S200 and S210 of the intake status acquisition process corresponds to the imaging control section, and the control unit 22 that executes S220 and S230 (S250 and S260) of the intake status acquisition process corresponds to the acquisition processing section.

[0030] As described above, the meal monitoring system 10 captures images during a meal in chronological order, processes the images to detect the amount of food eaten S(n), and obtains the meal intake status of the subject T based on the change in the amount of food eaten S(n) (the difference ΔS), thereby making it possible to obtain more detailed information about the subject's meal intake status.

[0031] In addition, the meal monitoring system 10 processes the start image to detect the meal amount S(0) at the start, and obtains the intake pace P by dividing the difference ΔS of the meal amount S(n) by the meal amount S(0). This allows the subject T's intake status during the meal to be obtained in more detail. In addition, the intake pace P can be obtained more appropriately than, for example, obtaining the intake pace P by dividing the meal amount S(0) by the meal time from the start to the end of the meal. In addition, the manager K can, for example, consider whether the meal contents are appropriate or to improve the meal contents based on the intake pace P. In improving the meal contents, for example, if there is a noticeable delay in the intake pace P of a meat-based main dish such as "hamburger steak", it is possible to consider improvements such as changing it to a smaller size to make it easier to eat, or changing it to another main dish such as a fish-based dish.

[0032] Furthermore, the meal monitoring system 10 detects the amount of food eaten S(n) for each dish and obtains the intake status for each dish based on the change in the amount of food eaten S(n) for each dish, so that it is possible to obtain more detailed intake status of the subject T during a meal. For example, information such as the order of intake for each meal content (the order in which meals were started and finished) can be easily obtained.

[0033] Furthermore, the meal monitoring system 10 processes the image to detect the meal amount S(n) based on the area of ​​the meal region, so that the intake status during a meal can be obtained through simple processing.

[0034] Furthermore, the meal monitoring system 10 processes an image at the start of a meal to detect the amount of food eaten at the start S(0), and processes an image at the end of the meal to detect the amount of food eaten at the end S(E), and obtains an intake ratio R based on the difference between the amount of food eaten S(0) and the amount of food eaten S(E). This allows for even more detailed information to be obtained about the intake status of the subject T during a meal. Furthermore, based on the intake ratio R, the manager K can, for example, consider whether the meal contents are appropriate or how to improve the meal contents. For example, when there is a noticeable amount of "rice" left uneaten (low intake ratio R), improvements such as suggesting a review of the amount of food eaten or changing the staple food to another food such as "porridge" or noodles can be considered.

[0035] Furthermore, in the meal monitoring system 10, after the opening and closing actions are detected by the opening and closing sensors 6a, 8a attached to the refrigerator 6 and microwave oven 8, if a meal is detected from the images and the subject T's hand movements or eating utensil movements are detected, it is determined that the subject T has started eating and is eating, and the camera 36 is controlled to capture images at predetermined time intervals. In this way, by using the detection of the opening and closing actions and the detection of the meal and the movements of the hands and eating utensils from the images, it is possible to accurately determine when the subject T is eating (start of eating) and appropriately obtain the intake status.

[0036] It goes without saying that the present disclosure is in no way limited to the above-described embodiment, and can be embodied in various forms as long as it falls within the technical scope of the present disclosure.

[0037] In the above-described embodiment, the opening and closing operations are detected by the opening and closing sensor 6a of the refrigerator 6 and the opening and closing sensor 8a of the microwave oven 8, but this is not limited to the above. For example, cooking-related operations may be detected by a sensor that detects the operation of the heating button of the microwave oven 8. Furthermore, the sensor is not limited to being attached to the refrigerator 6 or the microwave oven 8, but may be attached to an electrical appliance that stores or cooks food and can detect operations related to taking out or cooking food.

[0038] In the embodiment, the control unit 22 determines that the monitoring start timing has come when any one of the detection of the target person T around the table 2, the detection of the opening and closing operation of the door of the refrigerator 6, and the detection of the opening and closing operation of the door of the microwave oven 8 is established, but this is not limited thereto. For example, the control unit 22 may determine that the monitoring start timing has come when both the detection of the opening and closing operation of at least one of the doors of the refrigerator 6 and the microwave oven 8 and the detection of the target person T around the table 2 are established within a predetermined time. In addition, the control unit 22 may determine the monitoring start timing based on only one of the detection of the opening and closing operation of at least one of the doors of the refrigerator 6 and the microwave oven 8 and the detection of the target person T around the table 2, and may not include a sensor (one of the human sensor 2a and the opening and closing sensors 6a and 8a) that is not used for the determination. In addition, although the opening and closing operations of both the door of the refrigerator 6 and the door of the microwave oven 8 can be detected, it is also possible to detect only one of them and not include one of the opening and closing sensors 6a and 8a. Furthermore, the human presence sensor 2a and the opening / closing sensors 6a and 8a are merely examples, and the control unit 22 may determine the monitoring start timing based on detection signals from sensors other than these or on the establishment of other conditions.

[0039] In the embodiment, the control unit 22, after determining that the monitoring start timing has arrived, processes the image captured by the camera 36 to detect eating and detects the movement of the subject T's hands and eating utensils, and determines that the subject T is eating, but this is not limited to the above. The control unit 22, after determining that the monitoring start timing has arrived, may process the image captured by the camera 36 to detect eating and determine that the subject T is eating, even if the movement of the subject T's hands and eating utensils is not detected. That is, the process of S130 may be omitted. Alternatively, the control unit 22 may determine that the subject T is eating when it processes the image to detect eating and detects the movement of the subject T's hands and eating utensils without determining whether the monitoring start timing has arrived. That is, the process of S100 may be omitted and, for example, the process of S110 may be performed every predetermined time, and the human sensor 2a and the opening and closing sensors 6a and 8a may not be provided. In addition, the method is not limited to detecting the amount of food eaten S(n) by capturing an image every predetermined time, and the amount of food eaten S(n) may be detected every time the movement of the subject T's hands or the movement of eating utensils is detected from the image. Furthermore, the present invention is not limited to capturing images (still images), but may capture moving images and generate and process still images from the moving image data.

[0040] In the embodiment, the intake ratio R is obtained based on the difference between the meal amount S(0) at the start and the meal amount S(E) at the end, but this is not limited to this and it is not necessary to obtain the intake ratio R. Also, in the embodiment, the intake pace P is obtained by dividing the difference ΔS in the meal amount S(n) by the meal amount S(0), but this is not limited to this and it is not necessary to obtain the intake pace P. For example, it is sufficient to obtain the intake status during a meal, such as the intake order for each meal content as described above.

[0041] In the embodiment, the amount of food eaten S(n) is detected based on the area of ​​the food region, but this is not limiting. That is, the amount of food eaten S(n) is not limited to being detected from two-dimensional information (area), but may be detected from three-dimensional information (volume) that includes height information. In this case, the camera 36 may be positioned so that it can capture an image of the tableware from diagonally above, and the height of the food may be detected from the image. Furthermore, the amount of food eaten S(n) may be detected not only based on the image, but also based on the detection value of a sensor such as Lidar (Light Detection and Ranging).

[0042] In the embodiment, the amount of food eaten S(n) is detected for each dish and the intake status is obtained for each dish, but this is not limited to the above. For example, the intake status may be obtained based on the amount of food eaten S(n) obtained by adding up the area of ​​the food eaten for each dish, and the intake pace of the entire meal, rather than that for each dish. Furthermore, the amount of food eaten S(n) is not limited to a value based on the area, and may be the calories of the meal, etc.

[0043] This specification also discloses the technical idea of ​​changing "the meal monitoring system according to claim 1 or 2" in claim 4 at the time of the application to "the meal monitoring system according to any one of claims 1 to 3", the technical idea of ​​changing "the meal monitoring system according to claim 1 or 2" in claim 5 at the time of the application to "the meal monitoring system according to any one of claims 1 to 4", the technical idea of ​​changing "the meal monitoring system according to claim 1 or 2" in claim 6 at the time of the application to "the meal monitoring system according to any one of claims 1 to 5", and the technical idea of ​​changing "the meal monitoring system according to claim 1 or 2" in claim 7 at the time of the application to "the meal monitoring system according to any one of claims 1 to 6". [Industrial Applicability]

[0044] The present disclosure is applicable to the technical field of monitoring food intake. [Explanation of symbols]

[0045] 1 residence, 2 table, 2a motion sensor, 4 chair, 6 refrigerator, 6a, 8a opening / closing sensor, 8 microwave oven, 9 lighting, 10 meal monitoring system, 20 monitoring device, 22 control unit, 24 memory unit, 26 communication unit, 30 imaging unit, 32 base, 34 arm, 36 camera, 40 management server, 42 control unit, 44 memory unit, 46 communication unit, A imaging range, M mobile terminal, K administrator, NW network, T target person.

Claims

1. An imaging unit capable of imaging the subject's meal; An imaging control unit that controls the imaging unit so as to capture images in time series during a meal; an acquisition processing unit that processes the image to detect an amount of food eaten and acquires a food intake status based on a change in the amount of food eaten; A food monitoring system comprising:

2. the acquisition processing unit processes the image at the start of the meal to detect the amount of food eaten at the start, and acquires an intake pace as the intake status by dividing an amount of change in the amount of food eaten by the amount of food eaten at the start. The dietary monitoring system of claim 1 .

3. the acquisition processing unit detects the amount of food eaten for each dish, and acquires the intake status for each dish based on a change in the amount of food eaten for each dish. A diet monitoring system according to claim 1 or 2.

4. The acquisition processing unit detects the amount of food eaten based on an area of ​​a food region in the image. A diet monitoring system according to claim 1 or 2.

5. the acquisition processing unit processes an image at the start of a meal to detect an amount of food eaten at the start of the meal, and processes an image at the end of the meal to detect an amount of food eaten at the end of the meal, and acquires an intake ratio based on a difference between the amount of food eaten at the start of the meal and the amount of food eaten at the end of the meal. A diet monitoring system according to claim 1 or 2.

6. A sensor is attached to an electrical appliance for storing or cooking food and is capable of detecting an operation related to taking out or cooking food; the imaging control unit, after the motion is detected by the sensor, processes the image captured by the imaging unit to detect a meal, and controls the imaging unit to capture an image at predetermined time intervals as a meal. A diet monitoring system according to claim 1 or 2.

7. The imaging control unit processes the image captured by the imaging unit, and when a meal and a movement of the person's hands or a movement of eating utensils are detected, the imaging control unit controls the imaging unit to capture images at predetermined time intervals as if the person is eating. A diet monitoring system according to claim 1 or 2.

Images