阅读说明：本技术 肺活量检测平台和方式 (Vital capacity detection platform and mode ) 是由 孙紫阳 李绍园 于 2021-09-27 设计创作，主要内容包括：一种肺活量检测平台和方式,包括：设置在体检室内的显示屏、摄像头、存储器、读写器、控制器、肺活量测试仪以及配置给受试者的身份卡；所述显示屏、存储器、读写器、肺活量测试仪与摄像头均同控制器电连接；所述摄像头用于采集体检室现场的图像并传送到控制器中；所述显示屏用于显示控制器传送来的受试者的肺活量值；所述肺活量测试仪用于采集受试者吹气的气压值并传送至控制器中；有效避免了现有技术中肺活量的检测存在着防作弊手段不足、受试者出现假冒者来进行肺活量检测的缺陷。(A spirometry detection platform and method, comprising: the physical examination system comprises a display screen, a camera, a memory, a reader-writer, a controller, a vital capacity tester and an identity card configured for a subject, wherein the display screen, the camera, the memory, the reader-writer, the controller and the vital capacity tester are arranged in a physical examination room; the display screen, the memory, the reader-writer, the vital capacity tester and the camera are all electrically connected with the controller; the camera is used for collecting the on-site image of the physical examination room and transmitting the on-site image to the controller; the display screen is used for displaying the lung capacity value of the subject transmitted by the controller; the vital capacity tester is used for collecting the air pressure value of the air blowing of the testee and transmitting the air pressure value to the controller; the defects that in the prior art, the detection of the vital capacity has insufficient anti-cheating means and a test subject appears a counterfeiter to detect the vital capacity are effectively overcome.)

1. A spirometric detection platform, comprising:

the physical examination system comprises a display screen, a camera, a memory, a reader-writer, a controller, a vital capacity tester and an identity card configured for a subject, wherein the display screen, the camera, the memory, the reader-writer, the controller and the vital capacity tester are arranged in a physical examination room;

the display screen, the memory, the reader-writer, the vital capacity tester and the camera are all electrically connected with the controller;

the camera is used for collecting the on-site image of the physical examination room and transmitting the on-site image to the controller;

the display screen is used for displaying the lung capacity value of the subject transmitted by the controller;

the vital capacity tester is used for collecting the air pressure value of the air blowing of the testee and transmitting the air pressure value to the controller;

the ID card is stored with a subject ID, and the memory is stored with a subject ID and a mapping table of the subject picture; the subject ID is a unique identifier assigned to the subject. The identity card can be an RFID radio frequency card and the reader can be an RFID reader.

2. The platform of claim 1, wherein the reader is configured to read a subject ID from the ID card and transmit the subject ID to the controller, and the controller is configured to receive a pressure value of the air blown by the subject to calculate the lung capacity of the subject; and is also used for judging whether the subject has cheating behavior according to the images of the physical examination room scene.

3. The platform of claim 1, wherein the spirometry measuring instrument comprises a box body, the left and right sides of the box body are respectively provided with a handle, the front side of the box body is provided with a funnel-shaped air blowing opening communicated with the interior of the box body, and an air inlet of the air blowing opening extends out of the box body. The air outlet of the air blowing port extends into the box body, an air pressure sensor is arranged in the air outlet, and the air pressure sensor is electrically connected with the controller.

4. The spirometry detection platform as recited in claim 1, wherein the controller is configured to control the camera to capture images of a physical examination room site and transmit the images to the controller.

5. The platform of claim 1, wherein the controller is further configured to retrieve a picture of the subject mapped to the subject ID from the mapping table according to the subject ID, compare the picture of the subject with the image of the subject, prompt on the display screen that the spirometry is not allowed if the picture of the subject does not match the image of the subject, and prompt on the display screen that the spirometry is allowed if the picture of the subject matches the image of the subject.

6. The platform of claim 1, wherein the controller is further configured to calculate the lung capacity of the subject according to the airflow pressure value and transmit the calculated lung capacity to the display screen for display;

the controller is also used for detecting the images of the physical examination room site in real time, and if the images of other people are detected to appear in the images of the physical examination room site, the controller controls the display screen to display that the vital capacity detection is not allowed, and terminates the vital capacity detection.

7. A method of a spirometric platform, comprising:

step 1: when the vital capacity detection is needed, the controller controls the camera to collect the on-site images of the physical examination room and transmit the images to the controller;

step 2: the subject enters a physical examination room, the configured identity card allows the reader-writer to read the ID of the subject in the identity card and transmits the ID to the controller, and meanwhile, the subject faces the camera, and the camera acquires the image of the subject and transmits the image to the controller;

and step 3: the controller takes a subject picture which has a mapping relation with the subject ID from the mapping table according to the subject ID, compares the subject picture with the image of the subject, prompts on the display screen that the vital capacity detection is not allowed if the compared subject picture does not accord with the image of the subject, and prompts on the display screen that the vital capacity detection is allowed if the compared subject picture accords with the image of the subject;

and 4, step 4: after the fact that the vital capacity detection is allowed is indicated on the display screen, the testee covers the air inlet of the air blowing port on the mouth to blow air;

and 5: when the air flow generated by blowing passes through the air pressure sensor, the air pressure sensor transmits the acquired air pressure value of the air flow to the controller;

step 6: the controller calculates the lung capacity of the subject according to the air pressure value of the air flow and transmits the lung capacity to the display screen for display.

8. The system of claim 7, wherein the method for calculating the lung capacity of the subject from the airflow pressure value by the controller comprises: calculating corresponding instantaneous flow according to the air pressure value of the air flow, and accumulating and summing to obtain the vital capacity;

when the vital capacity detection is carried out, the controller also detects the images of the physical examination room site in real time, and controls the display screen to display that the vital capacity detection is not allowed and terminate if the images of other people appear in the images of the physical examination room site.

9. The system of claim 7, wherein the controller further performs a real-time detection method of the live images of the physical examination room, specifically comprising:

step A-1: using a YOLOv5 deep neural network pre-trained on a data set COCO containing large-scale human body morphological images to perform human body detection on a physical examination room scene picture, and outputting a rectangular frame with a human body area;

step A-2: if a plurality of rectangular frames are detected, the other persons are considered to appear, the display screen is controlled to display that the vital capacity detection is not allowed, and the vital capacity detection is terminated.

10. The method of claim 7, wherein the comparing the picture of the subject with the image of the subject comprises:

step 3-1: collecting face image data sets X and ID of all subjects;

step 3-2: carrying out feature extraction on the face image X by using a ResNet-50 deep neural network pre-trained on a large-scale data set ImageNet to obtain an image feature Z;

step 3-3: constructing a two-layer fully-connected neural network classifier model, taking the human face image characteristics Z as input, and taking ID as a prediction target;

step 3-4: constructing a classification loss function for the classifier, which is specifically shown in formula (1):

wherein L represents the classification loss, N represents the number of images, L represents the cross entropy loss function, f represents the classifier, z_iRepresenting the extracted features of the i-th training image, y_iAn ID indicating the ith image.

Step 3-5: iteratively updating classifier parameters end to end based on random gradient descent, and learning a classifier model;

step 3-6: after the training of the classifier is finished, extracting the image characteristics of the subject by using a pre-training ResNet-50 model used in the step 3-2, and using the extracted image characteristics as the input of the classifier to predict the ID of the subject; if the predicted ID is not consistent with the ID in the identity card, prompting that the vital capacity detection is not allowed on the display screen, otherwise, prompting that the vital capacity detection is allowed on the display screen.

Technical Field

The invention relates to the technical field of vital capacity detection, in particular to a vital capacity detection platform and a vital capacity detection mode.

Background

The vital capacity (visual capacity) measurement refers to the volume of air that is exhausted with effort after the maximum inspiration is detected. Comprises three parts of tidal volume, supplementary inspiration volume and supplementary expiration volume. Tidal volume refers to the volume inhaled or exhaled by the lungs in one respiratory cycle, the maximum volume inhaled outside the tidal volume is the inspiratory supplement volume, the maximum volume exhaled outside the tidal volume is the expiratory supplement volume, and the volume remaining in the lungs after the maximum exhalation is the residual volume. There are large individual differences. Affected by age, sex, stature, respiratory muscle strength, and lung and thoracic elasticity. In general, the stronger the body, the larger it is. Studies have shown that it is highly correlated with the maximum oxygen uptake. Is often used as an index for evaluating the quality of human body.

In practical application, the detection of the vital capacity has the defect of insufficient anti-cheating means, namely the problem that a test person appears a counterfeiter to detect the vital capacity.

Disclosure of Invention

In order to solve the problems, the invention provides a platform and a method for detecting the vital capacity, which effectively overcome the defects that the detection of the vital capacity in the prior art has insufficient anti-cheating means and a test subject appears a counterfeiter to detect the vital capacity.

To overcome the defects in the prior art, the invention provides a solution for a vital capacity detection platform and a vital capacity detection method, which specifically comprises the following steps:

a spirometry detection platform, comprising:

the physical examination system comprises a display screen, a camera, a memory, a reader-writer, a controller, a vital capacity tester and an identity card configured for a subject, wherein the display screen, the camera, the memory, the reader-writer, the controller and the vital capacity tester are arranged in a physical examination room;

the display screen, the memory, the reader-writer, the vital capacity tester and the camera are all electrically connected with the controller;

the camera is used for collecting the on-site image of the physical examination room and transmitting the on-site image to the controller;

the display screen is used for displaying the lung capacity value of the subject transmitted by the controller;

the vital capacity tester is used for collecting the air pressure value of the air blowing of the testee and transmitting the air pressure value to the controller;

the ID card is stored with a subject ID, and the memory is stored with a subject ID and a mapping table of the subject picture; the subject ID is a unique identifier assigned to the subject. The identity card can be an RFID radio frequency card and the reader can be an RFID reader.

Further, the reader-writer is used for reading the ID of the subject in the identity card and transmitting the ID to the controller, and the controller is used for receiving the air pressure value of the air blowing of the subject to calculate the lung capacity of the subject; and is also used for judging whether the subject has cheating behavior according to the images of the physical examination room scene.

Furthermore, the vital capacity tester comprises a box body, handles are arranged on the left side and the right side of the box body, a funnel-shaped air blowing opening communicated with the inside of the box body is formed in the front side of the box body, and an air inlet of the air blowing opening extends out of the box body. The air outlet of the air blowing port extends into the box body, an air pressure sensor is arranged in the air outlet, and the air pressure sensor is electrically connected with the controller.

Further, the controller is used for controlling the camera to collect images of the physical examination room on site and transmit the images to the controller.

Further, the controller is configured to retrieve a picture of the subject mapped with the subject ID from the mapping table according to the subject ID, compare the picture of the subject with the image of the subject, prompt on the display screen that the vital capacity detection is not allowed if the picture of the subject does not match the image of the subject, and prompt on the display screen that the vital capacity detection is allowed if the picture of the subject matches the image of the subject.

Further, the controller is also used for calculating the lung capacity of the subject according to the air pressure value of the air flow and transmitting the lung capacity to the display screen for displaying.

Further, the controller is also used for detecting the images of the physical examination room site in real time, and if the images of other people are detected to appear in the images of the physical examination room site, the controller controls the display screen to display that the vital capacity detection is not allowed, and terminates the vital capacity detection.

A method of a spirometric detection platform, comprising:

step 1: when the vital capacity detection is needed, the controller controls the camera to collect the on-site images of the physical examination room and transmit the images to the controller;

step 2: the subject enters a physical examination room, the configured identity card allows the reader-writer to read the ID of the subject in the identity card and transmits the ID to the controller, and meanwhile, the subject faces the camera, and the camera acquires the image of the subject and transmits the image to the controller;

and step 3: the controller takes a subject picture which has a mapping relation with the subject ID from the mapping table according to the subject ID, compares the subject picture with the image of the subject, prompts on the display screen that the vital capacity detection is not allowed if the compared subject picture does not accord with the image of the subject, and prompts on the display screen that the vital capacity detection is allowed if the compared subject picture accords with the image of the subject;

and 4, step 4: after the fact that the vital capacity detection is allowed is indicated on the display screen, the testee covers the air inlet of the air blowing port on the mouth to blow air;

and 5: when the air flow generated by blowing passes through the air pressure sensor, the air pressure sensor transmits the acquired air pressure value of the air flow to the controller;

step 6: the controller calculates the lung capacity of the subject according to the air pressure value of the air flow and transmits the lung capacity to the display screen for display.

Further, the method for calculating the lung capacity of the subject according to the airflow pressure value by the controller comprises the following steps: and calculating corresponding instantaneous flow according to the air pressure value of the air flow, and accumulating and summing to obtain the vital capacity.

Furthermore, when the vital capacity detection is carried out, the controller also detects the images of the physical examination room site in real time, and controls the display screen to display that the vital capacity detection is not allowed and terminate if the images of other people appear in the images of the physical examination room site.

Further, the controller also provides a real-time method for detecting the on-site images of the physical examination room, which specifically comprises the following steps:

step A-1: using a YOLOv5 deep neural network pre-trained on a data set COCO containing large-scale human body morphological images to perform human body detection on a physical examination room scene picture, and outputting a rectangular frame with a human body area;

step A-2: if a plurality of rectangular frames are detected, the other persons are considered to appear, the display screen is controlled to display that the vital capacity detection is not allowed, and the vital capacity detection is terminated.

Further, the method for comparing the picture of the subject with the image of the subject specifically includes:

step 3-1: collecting face image data sets X and ID of all subjects;

step 3-2: carrying out feature extraction on the face image X by using a ResNet-50 deep neural network pre-trained on a large-scale data set ImageNet to obtain an image feature Z;

step 3-3: constructing a two-layer fully-connected neural network classifier model, taking the human face image characteristics Z as input, and taking ID as a prediction target;

step 3-4: constructing a classification loss function for the classifier, which is specifically shown in formula (1):

where L represents the classification loss, N represents the number of images,representing a cross entropy loss function, f representing a classifier, z_iRepresenting the extracted features of the i-th training image, y_iAn ID indicating the ith image.

Step 3-5: iteratively updating classifier parameters end to end based on random gradient descent, and learning a classifier model;

step 3-6: after the training of the classifier is finished, extracting the image characteristics of the subject by using a pre-training ResNet-50 model used in the step 3-2, and using the extracted image characteristics as the input of the classifier to predict the ID of the subject; if the predicted ID is not consistent with the ID in the identity card, prompting that the vital capacity detection is not allowed on the display screen, otherwise, prompting that the vital capacity detection is allowed on the display screen.

The invention has the beneficial effects that:

the controller takes a subject picture which has a mapping relation with the subject ID from a mapping table according to the subject ID, then compares the subject picture with the image of the subject, and prompts on a display screen that the vital capacity detection is not allowed if the compared subject picture does not conform to the image of the subject; when the vital capacity detection is carried out, the controller also detects the images of the physical examination room site in real time, and controls the display screen to display that the vital capacity detection is not allowed if the images of other people appear in the images of the physical examination room site; therefore, the cheating behavior of the vital capacity detection is effectively avoided. The defects that in the prior art, the detection of the vital capacity has insufficient anti-cheating means and a test subject appears a counterfeiter to detect the vital capacity are effectively overcome.

Drawings

FIG. 1 is a partial flow diagram of a manner of the spirometry detection platform of the present invention.

Fig. 2 is a partial block diagram of the spirometry detection platform of the present invention.

Detailed Description

The invention will be further described with reference to the following figures and examples.

As shown in fig. 1-2, a spirometry testing platform includes:

the physical examination system comprises a display screen, a camera, a memory, a reader-writer, a controller, a vital capacity tester and an identity card configured for a subject, wherein the display screen, the camera, the memory, the reader-writer, the controller and the vital capacity tester are arranged in a physical examination room;

the display screen, the memory, the reader-writer, the vital capacity tester and the camera are all electrically connected with the controller;

the camera is used for collecting the on-site image of the physical examination room and transmitting the on-site image to the controller;

the display screen is used for displaying the lung capacity value of the subject transmitted by the controller;

the vital capacity tester is used for collecting the air pressure value of the air blowing of the testee and transmitting the air pressure value to the controller;

the ID card is stored with a subject ID, and the memory is stored with a subject ID and a mapping table of the subject picture; the subject ID is a unique identifier assigned to the subject. The identity card can be an RFID radio frequency card and the reader can be an RFID reader.

The reader-writer is used for reading the ID of the testee in the identity card and transmitting the ID to the controller, and the controller is used for receiving the air pressure value of the air blown by the testee to calculate the lung capacity of the testee; and is also used for judging whether the subject has cheating behavior according to the images of the physical examination room scene.

The vital capacity tester comprises a box body, the left side and the right side of the box body are respectively provided with a handle, the front side of the box body is provided with a funnel-shaped air blowing opening communicated with the inside of the box body, and an air inlet of the air blowing opening extends out of the box body. The air outlet of the air blowing port extends into the box body, an air pressure sensor is arranged in the air outlet, and the air pressure sensor is electrically connected with the controller.

The controller is used for controlling the camera to collect images of the physical examination room on site and transmit the images to the controller.

The controller is further configured to retrieve a picture of the subject mapped to the subject ID from the mapping table based on the subject ID, compare the picture of the subject with the image of the subject, prompt on the display screen that the spirometry is not allowed if the picture of the subject does not correspond to the image of the subject, and prompt on the display screen that the spirometry is allowed if the picture of the subject corresponds to the image of the subject.

The controller is also used for calculating the lung capacity of the subject according to the air pressure value of the air flow and transmitting the lung capacity to the display screen for display.

The controller is also used for detecting the images of the physical examination room site in real time, and if the images of other people are detected to appear in the images of the physical examination room site, the controller controls the display screen to display that the vital capacity detection is not allowed, and terminates the vital capacity detection.

The controller takes a subject picture which has a mapping relation with the subject ID from the mapping table according to the subject ID, compares the subject picture with the image of the subject, and prompts on a display screen that the vital capacity detection is not allowed if the compared subject picture does not conform to the image of the subject; when the vital capacity detection is carried out, the controller also detects the images of the physical examination room site in real time, and controls the display screen to display that the vital capacity detection is not allowed if the images of other people appear in the images of the physical examination room site; therefore, the cheating behavior of the vital capacity detection is effectively avoided.

A method of a spirometric detection platform, comprising:

step 1: when the vital capacity detection is needed, the controller controls the camera to collect the on-site images of the physical examination room and transmit the images to the controller;

step 2: the subject enters a physical examination room, the configured identity card allows the reader-writer to read the ID of the subject in the identity card and transmits the ID to the controller, and meanwhile, the subject faces the camera, and the camera acquires the image of the subject and transmits the image to the controller;

and step 3: the controller takes a subject picture which has a mapping relation with the subject ID from the mapping table according to the subject ID, compares the subject picture with the image of the subject, prompts on the display screen that the vital capacity detection is not allowed if the compared subject picture does not accord with the image of the subject, and prompts on the display screen that the vital capacity detection is allowed if the compared subject picture accords with the image of the subject;

and 4, step 4: after the fact that the vital capacity detection is allowed is indicated on the display screen, the testee covers the air inlet of the air blowing port on the mouth to blow air;

and 5: when the air flow generated by blowing passes through the air pressure sensor, the air pressure sensor transmits the acquired air pressure value of the air flow to the controller;

step 6: the controller calculates the lung capacity of the subject according to the air pressure value of the air flow and transmits the lung capacity to the display screen for display.

The method for calculating the lung capacity of the subject according to the airflow pressure value by the controller comprises the following steps: and calculating corresponding instantaneous flow according to the air pressure value of the air flow, and accumulating and summing to obtain the vital capacity.

When the vital capacity detection is carried out, the controller also detects the images of the physical examination room site in real time, and controls the display screen to display that the vital capacity detection is not allowed and terminate if the images of other people appear in the images of the physical examination room site.

The controller also discloses a real-time method for detecting the on-site images of the physical examination room, which specifically comprises the following steps:

step A-1: using a YOLOv5 deep neural network pre-trained on a data set COCO containing large-scale human body morphological images to perform human body detection on a physical examination room scene picture, and outputting a rectangular frame with a human body area;

step A-2: if a plurality of rectangular frames are detected, the other persons are considered to appear, the display screen is controlled to display that the vital capacity detection is not allowed, and the vital capacity detection is terminated.

The method for comparing the picture of the subject with the image of the subject specifically comprises the following steps:

step 3-1: collecting face image data sets X and ID of all subjects;

step 3-2: carrying out feature extraction on the face image X by using a ResNet-50 deep neural network pre-trained on a large-scale data set ImageNet to obtain an image feature Z;

step 3-3: constructing a two-layer fully-connected neural network classifier model, taking the human face image characteristics Z as input, and taking ID as a prediction target;

step 3-4: constructing a classification loss function for the classifier, which is specifically shown in formula (1):

where l represents the classification loss, N represents the number of images,representing a cross entropy loss function, f representing a classifier, z_iRepresenting the extracted features of the i-th training image, y_iAn ID indicating the ith image.

Step 3-5: iteratively updating classifier parameters end to end based on random gradient descent, and learning a classifier model;

step 3-6: after the training of the classifier is finished, extracting the image characteristics of the subject by using a pre-training ResNet-50 model used in the step 3-2, and using the extracted image characteristics as the input of the classifier to predict the ID of the subject; if the predicted ID is not consistent with the ID in the identity card, prompting that the vital capacity detection is not allowed on the display screen, otherwise, prompting that the vital capacity detection is allowed on the display screen.

The controller takes a subject picture which has a mapping relation with the subject ID from the mapping table according to the subject ID, compares the subject picture with the image of the subject, and prompts on a display screen that the vital capacity detection is not allowed if the compared subject picture does not conform to the image of the subject; when the vital capacity detection is carried out, the controller also detects the images of the physical examination room site in real time, and controls the display screen to display that the vital capacity detection is not allowed if the images of other people appear in the images of the physical examination room site; therefore, the cheating behavior of the vital capacity detection is effectively avoided.

The present invention has been described above in an illustrative manner by way of embodiments, and it will be apparent to those skilled in the art that the present disclosure is not limited to the embodiments described above, and various changes, modifications and substitutions can be made without departing from the scope of the present invention.