CN113299368A - System and method for assisting group health diet - Google Patents

System and method for assisting group health diet Download PDF

Info

Publication number
CN113299368A
CN113299368A CN202110553955.XA CN202110553955A CN113299368A CN 113299368 A CN113299368 A CN 113299368A CN 202110553955 A CN202110553955 A CN 202110553955A CN 113299368 A CN113299368 A CN 113299368A
Authority
CN
China
Prior art keywords
food
human body
information
host
calculating
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.)
Pending
Application number
CN202110553955.XA
Other languages
Chinese (zh)
Inventor
郭浩
陆杰
邓志扬
雷杰
马瑞
罗欣颖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Agricultural University
Original Assignee
China Agricultural University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Agricultural University filed Critical China Agricultural University
Priority to CN202110553955.XA priority Critical patent/CN113299368A/en
Publication of CN113299368A publication Critical patent/CN113299368A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/60—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Geometry (AREA)
  • Human Computer Interaction (AREA)
  • Nutrition Science (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The invention discloses a system and a method for assisting group health diet. The food information collector is used for obtaining a depth map of food, and the human body information collector is used for obtaining a depth map and weight of a human body; the computer host is a general computer for running a host end application program; the host application program is used for user login and calculating the information obtained by the information collector; the mobile phone end application program is used for user login, diet condition analysis result query, diet suggestion query and personal information maintenance; the cloud data server comprises a data storage module and a data analysis and calculation module. The invention provides rapid, scientific and accurate diet recording and diet health analysis management service, and plays a role of a group dietician.

Description

System and method for assisting group health diet
Technical Field
The invention relates to a system and a method for assisting group health diet, in particular to a system and a method for assisting group health diet in the fields of image recognition, food nutrition and mobile phone application development.
Background
With the development of society, the living standard of people is higher and higher, but the situation that people have health problems due to unreasonable diet is more and more, and people pay more and more attention to the health of their diet. Meanwhile, many software related to healthy diet also appears, but the software has the problems that the nutrition analysis is unreasonable, the fact-based analysis is not carried out according to the body type of the user, or the user needs to estimate the food intake by himself, so that the estimation is not accurate, the manual input is complicated, and the like.
The conventional intelligent healthy diet management system is used for calculating calorie intake according to two-dimensional images shot by using APP or inputting types eaten today by voice, comparing the calorie intake with a numerical value set by a user and judging whether the current day intake exceeds the standard or not. However, this method cannot identify the volume of food, thereby causing inaccuracy in estimating calorie intake. And the nutrition model is not comprehensive, the calorie can only measure the total calorie taken in by food, but the energy supply ratio of the taken food in the nutrition, namely the ratio of three substances, namely carbohydrate, protein and fat, for supplying energy to human bodies is also important, and other vitamins beneficial to the human bodies also need to be considered. The system takes the factors into consideration.
At present, another healthy diet management method in the prior art is to measure and calculate food intake according to an APP shot two-dimensional image or food number input, and recommend dishes, cooking modes and recommended meal schemes for a user according to comprehensive analysis of information such as exercise amount and physical conditions input by the user. However, the method also has the problems that the food intake estimation by photographing is not accurate enough, and the manual information input is tedious.
Therefore, it is important to develop a system which can accurately, conveniently and quantitatively determine the food nutrient intake of a user and reasonably and scientifically provide all-around dietary suggestions according to the body of the user.
Disclosure of Invention
To achieve the above objects, the present invention provides a system and method for rapidly and precisely monitoring and analyzing the nutrient intake status of a user and providing reasonable dietary suggestions according to the user's own physical information. Can accurately record the nutrient intake condition and physical condition of the user, give scientific and reasonable dietary suggestions and is beneficial to the physical health of the user.
The invention provides a system for assisting group health diet, which comprises a food information collector, a human body information collector, a calculation host, a host application program, a mobile phone application program and a cloud data server, and is characterized in that: the human body information collector comprises a first camera and an integrated weighing scale and is used for obtaining the body information of a person; the food information collector comprises a second camera and is used for obtaining a depth map of food; the computer host is used for running an application program at the host end and displaying a login interface and the real-time running state of the system; the host application program comprises a user login module, a food information automatic extraction module, a human body information automatic extraction module and an information reporting module; the mobile phone end application program is used for connecting a user with a computing host and starting an automatic food information extraction module and an automatic human body information extraction module in the host end application program; and for the user to view personal dietary advice and dietary or physical conditions; the cloud data server comprises a data storage module and a data analysis and calculation module.
In the above system for assisting group health diet, the first camera and the second camera are depth cameras.
The invention also provides a method for assisting the healthy diet of the population, which is characterized by comprising the following steps:
step S1: the user starts the system;
step S2: the human body information collector and the food information collector collect information, the human body information collector obtains a depth image and human body weight data of the human body information collector, and the food information collector obtains the depth image collected by the food information collector;
step S3: the calculation host computer processes data, including identifying the type of food, segmenting the food, calculating the volume of the food, and calculating the body shape information of the human body by using the depth image and the weight data of the human body;
step S4: the calculation host uploads the data in the step S3;
step S5: and the cloud server calculates the content of each macronutrient ingested by the user according to the uploaded food volume and type information, analyzes the content according to the data uploaded by the S4 and gives a diet suggestion.
In the method for assisting healthy diet of the group, the food volume calculating process in step S2 is: a) setting an initial plane P according to the arrangement form of the equipment, so that a plane normal vector Pv of the initial plane P is parallel to the Z axis; b) registering the food point cloud with the initial plane P such that the plane in which the food is placed coincides with the initial plane P; c) segmenting the food foreground; d) mapping the segmentation result in step c) to a three-dimensional space; e) and calculating the volume of the three-dimensional space, and calculating and obtaining the content of various nutrients of the shot food according to the nutrient database of the food.
In the method for assisting healthy diet of the group, the method for mapping the segmentation result to the three-dimensional space in the food volume calculation process d) in the step S3 uses the following formula:
Figure BDA0003076378750000031
wherein ZcThe distance between the camera and the food; u and v are X-axis coordinates and Y-axis coordinates of a certain food pixel point in a pixel coordinate system; xw、Yw、ZwFor food in the world coordinate systemThree-dimensional coordinates; f. ofx、fyIs the length of the focal spot in the corresponding direction; u. ofo、voIs the optical center in the pixel coordinate system; the letter R represents a rotation matrix, the letter T represents a conversion matrix, and three-dimensional space coordinates are obtained through calculation.
In the method for assisting healthy diet of the population, the food volume calculating process in step S2 is characterized in that the method for calculating the three-dimensional space volume in step e) includes: and (3) taking the food point cloud as an upper curved surface, defining the upper curved surface as F, and taking an initial plane P as a lower plane, and calculating the volume of the three-dimensional space according to an integral formula.
In the method for assisting healthy diet of the group, in the step S2, in the process of calculating the food volume, the integral formula in the step e) is:
Figure BDA0003076378750000032
S＝1mm2
Hi＝fz-pz
wherein p isz∈P，pzIs the ordinate of the initial plane, fz∈F，fzIs the ordinate of the midpoint of the food point cloud, S is the unit area of the integration on the XY plane, HiThe distance between a certain point of the upper curved surface F and the initial plane P, namely the distance between the certain point of the upper curved surface F and the Z-axis direction of the corresponding point of the lower plane P is represented by V, and the finally calculated three-dimensional space volume of the food is represented by V.
In the method for assisting healthy diet of the group, the process of calculating the body shape information in step S3 is as follows: (a) the first camera shoots a human body, and the calculation host reads a human body single visual angle depth map collected by the first camera; (b) segmenting the depth map in the step (a) to obtain a human body depth map, obtaining human body point cloud data according to the segmented depth map, and extracting human body skeleton data according to the human body point cloud data; (c) carrying out human body posture fitting; (d) carrying out human body shape fitting; (e) estimating parameters of waist and hip circumferences of the human body; (f) the calculation host calculates the body shape information of the human body according to the height, the weight, the waist circumference and the hip circumference of the human body.
Compared with the prior art, the invention has the beneficial effects that:
the method can quickly, accurately and quantitatively record the food nutrient intake condition of the user, is more accurate than the traditional estimation manual input and photographing input, does not need the reference of a standard plate, is more convenient and quick, and is suitable for all people in a restaurant. And the analysis of the diet proposal combines the physical condition of each person, and considers each nutrient of the human body, thereby being more reasonable.
Drawings
FIG. 1 is a perspective view of a device for assisting in the health of a group in an embodiment of the present invention;
FIG. 2 is a left side view of FIG. 1;
FIG. 3 is a flow chart of a method of assisting a group health diet system of the present invention;
FIG. 4 is a diagram of a standard coordinate system in accordance with an embodiment of the present invention;
FIG. 5 is a schematic view of the registration of a food plane with an initial plane in one embodiment of the present invention;
FIG. 6 is a graph of image segmentation results in one embodiment of the present invention;
FIG. 7 is a two-dimensional to three-dimensional mapping of food items in one embodiment of the invention;
FIG. 8 is a schematic illustration of a three-dimensional volume calculation in accordance with an embodiment of the present invention;
FIG. 9 is a diagram illustrating the result of food type recognition according to another embodiment of the present invention;
figure 10 is a schematic representation of a human body physique assay in one embodiment of the invention.
The numbers in the figure are as follows: the system comprises a first camera 1, a support 2, a second camera 3, a computer 4, a display screen 5 and steps S1-S5.
Detailed Description
The invention is described in further detail below with reference to the figures and the examples, but without limiting the invention.
The apparatus used in the present invention is described below with reference to fig. 1-2: fig. 1 is a perspective view of an auxiliary group health diet device according to an embodiment of the present invention, and fig. 2 is a left side view of fig. 1, the auxiliary group health diet device including a human body information collector, a food information collector, and a computing host. The human body information collector comprises a first camera 1 and a weight scale 6, wherein the first camera 1 is a depth camera, is arranged above the bracket 2 and is used for shooting a human body in an oblique direction and downwards to obtain a depth image of the human body; the weighing scale 6 is arranged right in front of the device and used for obtaining the weight of a human body, and is connected with the calculation host 4 through Bluetooth. The food information collector comprises a second camera 3, the second camera 3 is another depth camera, is arranged below the support 2 and inside the first camera 1 and the calculation host computer and is used for vertically shooting food downwards and obtaining depth images of the food. The computer 4 is connected with the bracket 2, is a general computer, can be used as a platform for placing food to be tested, and is provided with a display screen 5 for displaying the running state of the program of the computer end and displaying the two-dimensional code of the computer.
Referring to fig. 3-10, a general flowchart of a diet system and method for assisting group health according to an embodiment of the present invention is shown in fig. 3:
step S1: firstly, a user starts a system, and the specific process is as follows: a user places a dinner plate into a calculation host 4 of the system, stands on a weight scale 6, then opens a mobile phone application program, scans a two-dimensional code on a display screen of the calculation host 4, enters an operation interface, and starts an automatic human body information extraction module and an automatic food information extraction module on the calculation host 4; or directly starting the modules in a software login module of a host-side application program to prepare for information acquisition.
Step S2: the information acquisition device acquires information, and the specific process is as follows: the calculation host 4 acquires a depth image acquired by the food information acquisition device, and calculates the volume of food according to the depth image. The specific calculation process of the food volume is as follows:
a) setting an initial plane P according to the placing form of the equipment, so that a plane normal vector Pv of the initial plane P is parallel to the Z axis, as shown in FIG. 4;
b) registering the food point cloud with the initial plane P in step a) such that the plane in which the food is placed coincides with the initial plane P as shown in fig. 5;
c) the food point cloud is segmented by a two-dimensional detection algorithm, and the image obtained by food shooting and the image segmented by the two-dimensional detection algorithm are compared as shown in figure 6;
d) mapping the two-dimensional food point cloud segmentation result in step c) to a three-dimensional space, the mapping from two-dimensional to three-dimensional is shown in fig. 7. Inputting the two-dimensional pixel coordinates into the following formula one:
Figure BDA0003076378750000051
wherein ZcThe distance between the camera and the food; u and v are X-axis coordinates and Y-axis coordinates of a certain food pixel point in a pixel coordinate system; xw、Yw、ZwThree-dimensional coordinates of food in a world coordinate system; f. ofx、fyIs the length of the focal spot in the corresponding direction; u. ofo、voIs the optical center in the pixel coordinate system; the letter R represents a rotation matrix, the letter T represents a conversion matrix, and three-dimensional space coordinates are obtained through calculation.
e) Calculating the volume of the three-dimensional space: the food point cloud is used as an upper curved surface, the upper curved surface is defined as F, the initial plane P is a lower plane, the three-dimensional space volume is calculated according to the following integral formula, and the calculation schematic diagram is shown in FIG. 8. The operation can be performed by using an integral formula, and the specific operation method is shown in the following formula two:
Figure BDA0003076378750000061
S＝1mm2
Hi＝fz-pz
wherein p isz∈P，pzIs the ordinate of the initial plane, fz∈F，fzIs the longitudinal coordinate of the midpoint of the food point cloud, and S is the integral on the XY planeUnit area, HiThe distance between a certain point of the upper curved surface F and the initial plane P, namely the distance between the certain point of the upper curved surface F and the Z-axis direction of the corresponding point of the lower plane P is represented by V, and the finally calculated three-dimensional space volume of the food is represented by V.
Meanwhile, the computer identifies the type of the food through a deep learning algorithm, as shown in fig. 9, which is a schematic diagram of the type of the food identified by the information collector when the food is a steamed stuffed bun in another embodiment.
And calculating the content of various nutrients of the shot food according to the constructed food density database, the type and the volume of the food and the nutrient database of the food. The calculation can be performed using the following equation three:
W＝ρ*V*k
rho is the density of the food, W is the content of a certain nutrient in the food, V is the volume of the food, and k is the content of a certain nutrient in the unit mass of the food.
The food density database is a database for storing different food densities. The food nutrient database is constructed according to the Chinese food ingredient table, and the database of the content of various nutrients of different foods.
Step S3: the calculation host 4 primarily processes data, specifically includes calculating body shape information according to a body depth map acquired by the first camera 1 and weight information weighed by the weight scale 6, and the specific calculation process is shown in fig. 10, and the text expression is as follows:
(a) the first camera 1 shoots a human body, and the calculation host 4 reads a single visual angle depth map of the human body collected by the first camera 1;
(b) carrying out contour segmentation on the collected depth map to obtain a human body depth map, obtaining human body point cloud data according to the segmented depth map, and extracting human body skeleton data according to the human body point cloud data;
(c) carrying out human body posture fitting: calculating a rotation matrix R for transforming the skeleton data of the template model to the human body point cloud skeleton data, and further optimizing the posture parameter theta of the human body parametric model based on the rotation matrix R;
(d) carrying out human body shape fitting: after the human body posture fitting in the step (c) is carried out, establishing a corresponding relation between the template model after posture deformation and human body point cloud data, and solving a morphological deformation parameter beta of the template model;
(e) estimating specific information of the waist, the hip circumference and the like of the human body, predefining a surface circumferential path of body scale parameters according to the characteristic of consistent topology of the fitted human body model, defining the path as a set of vertexes, and calculating the circumferential path corresponding to the model according to the shape of the human body fitted in the step (d), wherein the length of the circumferential path is the sum of the lengths of adjacent edges of defined path points, so as to obtain the estimation of the information of the waist, the hip circumference and the like of the human body. (f) The calculating host 3 calculates the body mass index BMI of the human body according to the height and the weight of the human body, wherein the body mass index BMI is m/h2Wherein h is height (in meters) and m is body weight (in kg). The central obesity index C, L of human body can also be calculated1Is waist circumference (unit cm), L2For hip circumference (in cm), the calculation procedure is: c ═ L1/L2；
Step S4: calculating the uploading data of the host 4, and uploading two types of body information of the content W of a certain nutrient substance, the body mass index BMI and the central obesity index C of the food obtained by calculation to a cloud server;
step S5: the cloud server calculates and stores data, gives dietary suggestions according to the BMI, the central obesity index C and the content of various nutrients of food ingested by the user on the day and an information base constructed according to Chinese resident dietary guidelines, and stores nutrient intake information, body information and dietary suggestions.
For example: the cloud server obtains the body information of the user according to the body information data uploaded by the host terminal, wherein the BMI is 22.03kg/m2The central obesity index is 0.85. The cloud server reads that the age and gender information of the user is 20 years old, the gender is female, and the physical labor type is light physical labor.
The system learns that the BMI value is between 18.5 and 23.9 and is normal weight according to a knowledge base constructed by 'Chinese resident dietary guidelines'; central obesity index C0.85 <0.9 is also normal. The system thus determines that the user is not required to lose weight and analyzes it as normal population. The cloud server is according to the following formula:
daily required calorie (kcal) is one kilogram of standard body weight required calorie (kcal) multiplied by standard body weight (kilogram)
Wherein, per kilogram of standard body weight the required calorie is referred to table 1:
TABLE 1 reference table of calories per kilogram standard body weight of the population
Figure BDA0003076378750000071
The theoretical energy requirement of the human body is 1800 kilocalories.
That is, it means that in order to maintain the metabolic balance of the human body, at least 1800 kcal of food should be taken, and according to the requirement of the dietary guidelines of Chinese residents, for a person with an energy demand of 1800 kcal, the intake of each nutrient should be as shown in the following table 2:
TABLE 2 dietary guidelines of Chinese residents' recommendations for nutrient intake by normal population
Figure BDA0003076378750000081
(continuation watch)
Figure BDA0003076378750000082
The nutrient intake condition table of the user at a certain day shown in the following table 3 can be obtained through the content data of each nutrient of the food at the current day stored in the cloud data server:
TABLE 3 nutrient intake by the user on a certain day
Figure BDA0003076378750000083
(continuation watch)
Figure BDA0003076378750000084
The cloud data server compares the two tables, and finds that the difference between the protein intake of the user and the standard value is large and reaches fifty percent, so that the serious shortage of the protein intake of the user today can be judged, and the cloud data server calculates the conclusion: the protein intake is seriously low, the daily diet of the user pays attention to the protein intake, and the mobile phone end application program reminds the user that yesterday protein intake is seriously insufficient at eight points in the morning, suggests that more foods with high protein content are eaten, and gives a menu.
The user can check nutrient intake information, body information, diet suggestions and the like of historical dates at any time through the mobile phone end application program.
It is to be understood that changes may be made in the particular embodiments of the invention described herein without departing from the spirit and scope of the invention as defined in the appended claims.

Claims (8)

1. The utility model provides a system of supplementary healthy diet of crowd, includes food information collector, human information collector, calculation host computer, host computer end application, cell-phone end application and high in the clouds data server, its characterized in that:
the human body information collector comprises a first camera and an integrated weighing scale and is used for obtaining the body information of a person; the food information collector comprises a second camera and is used for obtaining a depth map of food; the computer host is used for running an application program at the host end and displaying a login interface and the real-time running state of the system; the host application program comprises a user login module, a food information automatic extraction module, a human body information automatic extraction module and an information reporting module; the mobile phone end application program is used for connecting a user with a computing host and starting an automatic food information extraction module and an automatic human body information extraction module in the host end application program; and for the user to view personal dietary advice and dietary or physical conditions; the cloud data server comprises a data storage module and a data analysis and calculation module.
2. The system of claim 1, wherein the first camera and the second camera are both depth cameras.
3. A method of assisting a healthy diet in a population, comprising the steps of:
step S1: the user starts the system;
step S2: the human body information collector and the food information collector collect information, the human body information collector obtains a depth image and human body weight data of the human body information collector, and the food information collector obtains the depth image collected by the food information collector;
step S3: the calculation host computer processes data, including identifying the type of food, segmenting the food, calculating the volume of the food, and calculating the body shape information of the human body by using the depth image and the weight data of the human body;
step S4: the calculation host uploads the data in the step S3;
step S5: and the cloud server calculates the content of the nutrients ingested by the user according to the uploaded food volume and type information, analyzes the content according to the data uploaded by the S4 and gives a diet suggestion.
4. The method according to claim 3, wherein the food volume calculating process in the step S3 is: a) setting an initial plane P according to the arrangement form of the equipment, so that a plane normal vector Pv of the initial plane P is parallel to the Z axis; b) registering the food point cloud with the initial plane P such that the plane in which the food is placed coincides with the initial plane P; c) segmenting the food foreground; d) mapping the segmentation result in step c) to a three-dimensional space; e) and calculating the volume of the three-dimensional space, and calculating to obtain the content of the nutrients of the shot food according to the nutrient database of the food.
5. The method as set forth in claim 4, wherein the method of mapping the segmentation result to the three-dimensional space in the step d) calculates the three-dimensional space coordinates using the following formula:
Figure FDA0003076378740000021
wherein ZcThe distance between the camera and the food; u and v are X-axis coordinates and Y-axis coordinates of a certain food pixel point in a pixel coordinate system; xw、Yw、ZwThree-dimensional coordinates of food in a world coordinate system; f. ofx、fyIs the length of the focal spot in the corresponding direction; u. ofo、voIs the optical center in the pixel coordinate system; the letter R represents a rotation matrix and T represents a transformation matrix.
6. The method of claim 4, wherein the method of calculating the volume in three-dimensional space in step e) is: and (3) taking the food point cloud as an upper curved surface, defining the upper curved surface as F, and taking an initial plane P as a lower plane, and calculating the volume of the three-dimensional space according to an integral formula.
7. The method of claim 6, wherein the integral formula is:
Figure FDA0003076378740000022
S＝1mm2
Hi＝fz-pz
wherein p isz∈P，pzIs the ordinate of the initial plane, fz∈F，fzIs the ordinate of the midpoint of the food point cloud, S is the unit area of the integration on the XY plane, HiThe distance between a certain point of the upper curved surface F and the initial plane P, namely the distance between the certain point of the upper curved surface F and the Z-axis direction of the corresponding point of the lower plane P is represented by V, and the finally calculated three-dimensional space volume of the food is represented by V.
8. The method as set forth in claim 3, wherein the process of calculating the human body shape information in step S3 is as follows: (a) the first camera shoots a human body, and the calculation host reads a human body single visual angle depth map collected by the first camera; (b) segmenting the depth map in the step (a) to obtain a human body depth map, obtaining human body point cloud data according to the segmented depth map, and extracting human body skeleton data according to the human body point cloud data; (c) carrying out human body posture fitting; (d) carrying out human body shape fitting; (e) estimating parameters of waist and hip circumferences of the human body; (f) the calculation host calculates the body shape information of the human body according to the height, the weight, the waist circumference and the hip circumference of the human body.
CN202110553955.XA 2021-05-20 2021-05-20 System and method for assisting group health diet Pending CN113299368A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110553955.XA CN113299368A (en) 2021-05-20 2021-05-20 System and method for assisting group health diet

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110553955.XA CN113299368A (en) 2021-05-20 2021-05-20 System and method for assisting group health diet

Publications (1)

Publication Number Publication Date
CN113299368A true CN113299368A (en) 2021-08-24

Family

ID=77323286

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110553955.XA Pending CN113299368A (en) 2021-05-20 2021-05-20 System and method for assisting group health diet

Country Status (1)

Country Link
CN (1) CN113299368A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114974512A (en) * 2022-05-30 2022-08-30 中国银行股份有限公司 Recommendation method and device for meal information

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105662346A (en) * 2016-01-05 2016-06-15 京东方科技集团股份有限公司 Intelligent wearable device
CN105787279A (en) * 2016-03-16 2016-07-20 上海电机学院 Healthy diet adjustment and analysis system
CN106446508A (en) * 2016-08-30 2017-02-22 陈维 Intelligent chopstick prediction system and method for performing prediction by using system
CN106599597A (en) * 2016-12-22 2017-04-26 深圳Tcl数字技术有限公司 Health management method, health management device, health management system based on TV set and TV set
TWI653601B (en) * 2017-11-09 2019-03-11 統一企業股份有限公司 Personalized health recommendation method
CN109655019A (en) * 2018-10-29 2019-04-19 北方工业大学 Cargo volume measurement method based on deep learning and three-dimensional reconstruction
CN109875562A (en) * 2018-12-21 2019-06-14 鲁浩成 A kind of human somatotype monitoring system based on the more visual analysis of somatosensory device
CN111063419A (en) * 2019-12-27 2020-04-24 南京舜国宸智能科技有限公司 Intelligent healthy diet management system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105662346A (en) * 2016-01-05 2016-06-15 京东方科技集团股份有限公司 Intelligent wearable device
CN105787279A (en) * 2016-03-16 2016-07-20 上海电机学院 Healthy diet adjustment and analysis system
CN106446508A (en) * 2016-08-30 2017-02-22 陈维 Intelligent chopstick prediction system and method for performing prediction by using system
CN106599597A (en) * 2016-12-22 2017-04-26 深圳Tcl数字技术有限公司 Health management method, health management device, health management system based on TV set and TV set
TWI653601B (en) * 2017-11-09 2019-03-11 統一企業股份有限公司 Personalized health recommendation method
CN109655019A (en) * 2018-10-29 2019-04-19 北方工业大学 Cargo volume measurement method based on deep learning and three-dimensional reconstruction
CN109875562A (en) * 2018-12-21 2019-06-14 鲁浩成 A kind of human somatotype monitoring system based on the more visual analysis of somatosensory device
CN111063419A (en) * 2019-12-27 2020-04-24 南京舜国宸智能科技有限公司 Intelligent healthy diet management system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114974512A (en) * 2022-05-30 2022-08-30 中国银行股份有限公司 Recommendation method and device for meal information

Similar Documents

Publication Publication Date Title
WO2020103417A1 (en) Bmi evaluation method and device, and computer readable storage medium
CN107238427A (en) Intelligent nutrition scale system and the method that diet suggestion is provided
CN108597582B (en) Method and device for executing fast R-CNN neural network operation
CN107731278A (en) A kind of food recognition methods, nutrient health analysis method, system and device
Pouladzadeh et al. You are what you eat: So measure what you eat!
CN104778374A (en) Automatic dietary estimation device based on image processing and recognizing method
CN107397530B (en) Traditional Chinese medicine constitution and emotion distinguishing and conditioning system
CN106709525A (en) Method for measuring food nutritional component by means of camera
CN109102860A (en) A kind of Shandong cuisine nutrition formula method of ordering based on wechat platform
CN102214269A (en) Information processing apparatus, information outputting method and computer program storage device
WO2018107872A1 (en) Method and device for predicting body type
CN112017756A (en) Dietary nutrition analysis method based on face recognition self-service meal-making system
CN105260594A (en) Individual nutrition evaluation system
Stütz et al. Can mobile augmented reality systems assist in portion estimation? A user study
CN111599438A (en) Real-time diet health monitoring method for diabetic patient based on multi-modal data
CN111401103B (en) Real-time collection system and method for personal dietary nutrition intake
CN109064286A (en) A kind of Shandong cuisine nutrition formula food-ordering device based on wechat platform
CN113299368A (en) System and method for assisting group health diet
CN115131783A (en) User diet nutrient component information autonomous perception method based on machine vision
CN207113999U (en) Intelligent nutrition scale system
CN117078955B (en) Health management method based on image recognition
CN108537329A (en) A kind of method and apparatus carrying out operation using Volume R-CNN neural networks
CN111652044A (en) Dietary nutrition analysis method based on convolutional neural network target detection
CN114360690B (en) Method and system for managing diet nutrition of chronic disease patient
CN114359299B (en) Diet segmentation method and diet nutrition management method for chronic disease patients

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination