CN110795981A - Face recognition interaction method and system for hyperbaric oxygen chamber - Google Patents
Face recognition interaction method and system for hyperbaric oxygen chamber Download PDFInfo
- Publication number
- CN110795981A CN110795981A CN201910583194.5A CN201910583194A CN110795981A CN 110795981 A CN110795981 A CN 110795981A CN 201910583194 A CN201910583194 A CN 201910583194A CN 110795981 A CN110795981 A CN 110795981A
- Authority
- CN
- China
- Prior art keywords
- face
- user
- monitored
- oxygen chamber
- hyperbaric oxygen
- 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
Links
Images
Classifications
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61G—TRANSPORT, PERSONAL CONVEYANCES, OR ACCOMMODATION SPECIALLY ADAPTED FOR PATIENTS OR DISABLED PERSONS; OPERATING TABLES OR CHAIRS; CHAIRS FOR DENTISTRY; FUNERAL DEVICES
- A61G10/00—Treatment rooms or enclosures for medical purposes
- A61G10/02—Treatment rooms or enclosures for medical purposes with artificial climate; with means to maintain a desired pressure, e.g. for germ-free rooms
- A61G10/023—Rooms for the treatment of patients at over- or under-pressure or at a variable pressure
- A61G10/026—Rooms for the treatment of patients at over- or under-pressure or at a variable pressure for hyperbaric oxygen therapy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Pulmonology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Emergency Medicine (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a face recognition interaction method and system for a hyperbaric oxygen chamber, which are used for acquiring a face image of a user to be monitored in the hyperbaric oxygen chamber through a 3D structured light depth camera, processing the face image and obtaining a 3D face model. And identifying the three-dimensional facial expression of the user to be monitored, extracting the 3D characteristics of the human face and identifying the facial action according to the 3D model of the human face. Judging the hyperbaric oxygen chamber feeling of the user to be monitored according to the three-dimensional facial expression recognition result, matching the human face 3D feature extraction result with a preset human face authority library to acquire the control authority of the user to be monitored, and matching the facial action recognition result with a preset human face instruction set to acquire the control instruction of the user to be monitored. And judging whether to execute the control instruction of the user to be monitored according to the control authority of the user to be monitored. The medical staff operation control system solves the problems that the medical staff operation is not standard and the operation is performed by irrelevant responsible staff, accurately identifies the cabin operation permission of the operating staff, and prevents medical accidents caused by misoperation.
Description
Technical Field
The invention relates to a face recognition interaction method and system for a hyperbaric oxygen chamber, and belongs to the technical field of hyperbaric oxygen chambers.
Background
The hyperbaric oxygen chamber therapy has unique curative effect and wide development prospect in hyperbaric oxygen clinical medicine, a patient is placed in an environment with the atmospheric pressure higher than that of the hyperbaric oxygen chamber to absorb pure oxygen, the concentration of the absorbed oxygen is 85% -99%, the oxygen content is several times of that of the absorbed oxygen under normal pressure, the oxygen tension and the oxygen content can be effectively improved, and the hyperbaric oxygen chamber therapy has special curative effect on treating acute and chronic hypoxic diseases. Since both the erroneous recognition of the administrative authority and the erroneous operation of the patient may cause serious medical accidents, the face recognition system mounted on the intelligent hyperbaric oxygen chamber needs to have very high accuracy.
Traditional face recognition techniques may produce a result of a leaf-blinding eye that does not see taishan mountain. The traditional camera and acquisition equipment based on 2D face recognition usually predict and assume based on a small amount of samples, judge texture information, mouth size, interocular distance and the like of a face through a written program, and obtain information of a two-dimensional plane. However, from the perspective of the algorithm, no matter how strong the illumination is, how accurate the angle processing is, no deeper information such as the degree of the concave eyes, the height of the nose, and even the related information of the face is known.
The 2D face recognition system has some bugs, and when the 2D face recognition system encounters an attack at a biosensor level, a database attack and other attack means, great damage can be caused. An attacker breaks the existing security system through still photos, human face videos and other modes. Therefore, with the development of anti-spoofing means, liveness detection techniques have come up. The technology generally adopts a mode of cooperating with command actions, such as left turning, right turning, mouth opening, blinking and the like of a human face. But the user experience effect brought by the way of completing identity authentication through user cooperation is not good; furthermore, this technique cannot prevent video attacks or attacks of face synthesis techniques.
In order to solve the two problems, a novel camera, namely a binocular camera, is released in the camera market. The binocular camera obtains a synchronous exposure image through the calibrated double cameras by utilizing a bionics principle, and then calculates the third dimension depth information of the pixel points of the obtained two-dimensional image. However, for a computer, the depth information obtained by two cameras is not particularly accurate, because the depth information is affected by light and other factors, and the error is large; in addition, the performance requirements on the computing unit are very high, which makes the production and miniaturization of the binocular system difficult. A rapid, safe and reliable human face recognition interaction technical scheme for the hyperbaric oxygen chamber environment is needed.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a face recognition interaction method and system for a hyperbaric oxygen chamber, which solve the problems that medical care personnel are not standard in operation and operate by irrelevant responsible personnel, accurately recognize the operating cabin permission of the operating personnel and can prevent medical accidents caused by misoperation.
The technical scheme for solving the technical problems is as follows: a face recognition interaction method for a hyperbaric oxygen chamber comprises the following steps:
acquiring a face image of a user to be monitored in the hyperbaric oxygen chamber through a 3D structured light depth camera, processing the face image of the user to be monitored by using a 3D structured light algorithm, and obtaining a 3D face model;
identifying three-dimensional facial expressions, human face 3D feature extraction and facial action of the user to be monitored according to the human face 3D model;
judging hyperbaric oxygen chamber feeling of a user to be monitored according to the three-dimensional facial expression recognition result, wherein the hyperbaric oxygen chamber feeling comprises a plurality of preset comfort level models, matching the human face 3D feature extraction result with a preset human face authority library to acquire the control authority of the user to be monitored, and matching the facial action recognition result with a preset human face instruction set to acquire the control instruction of the user to be monitored;
judging whether to execute the control instruction of the user to be monitored according to the control authority of the user to be monitored, a) enabling the user to be monitored to have the control authority of the control instruction, and adjusting or early warning the hyperbaric oxygen chamber according to the control instruction and the comfort level model; b) and stopping responding to the control instruction of the user to be monitored when the user to be monitored does not have the control authority of the control instruction.
As an optimal scheme of the hyperbaric oxygen chamber face recognition interaction method, a single-frame/multi-frame infrared face image with speckles/stripes of a user to be monitored is acquired through a 3D structure optical depth camera; and 3D face point cloud reconstruction is carried out according to the infrared face image information, and the 3D face point cloud reconstruction comprises the step of obtaining 3D face point clouds of a plurality of angles through space coordinate rotation.
And as a preferred scheme of the hyperbaric oxygen chamber face recognition interaction method, performing complementary processing on the 3D face point cloud and the RGB colorful face image, and judging that the face image is a real face or a forged face according to the 3D face point cloud.
As a preferred scheme of the hyperbaric oxygen chamber face recognition interaction method, the three-dimensional facial expression comprises eyebrow lifting, mouth turning and blinking, and the comfort model type of the hyperbaric oxygen chamber is judged according to the three-dimensional facial expression recognition result; the facial actions comprise lifting eyebrows, lefting mouth, blinking, raising head, lowering head, shaking head or covering face; and sending the three-dimensional facial expression and facial action to medical care personnel.
As an optimal scheme of the hyperbaric oxygen chamber face recognition interaction method, acquiring and recognizing voice information of a user to be monitored in the hyperbaric oxygen chamber, and adjusting or early warning the hyperbaric oxygen chamber according to a voice recognition result and a preset voice operation instruction set and control authority of the user to be monitored; and sending the voice information to medical staff for doctor-patient communication.
And as a preferred scheme of the hyperbaric oxygen chamber face recognition interaction method, when the user to be monitored does not have the control authority of the control instruction, the three-dimensional facial expression and the facial action are sent to the medical care personnel with the control authority.
The embodiment of the invention also provides a face recognition interaction system for the hyperbaric oxygen chamber, which comprises:
the image acquisition module is used for acquiring a face image of a user to be monitored in the hyperbaric oxygen chamber through the 3D structured light depth camera;
the face model construction module is used for processing the face image of the user to be monitored by using a 3D structured light algorithm and obtaining a 3D face model;
the feature recognition module is used for recognizing the three-dimensional facial expression, the human face 3D feature and the facial action of the user to be monitored according to the human face 3D model;
the judging module is used for judging the hyperbaric oxygen chamber feeling of the user to be monitored according to the three-dimensional facial expression recognition result, and the hyperbaric oxygen chamber feeling comprises a plurality of preset comfort level models;
the first matching module is used for matching the face 3D feature extraction result with a preset face authority library to acquire the control authority of the user to be monitored;
the second matching module is used for matching the facial action recognition result with a preset human face instruction set to acquire a control instruction of the user to be monitored;
the response module is used for judging whether to execute the control instruction of the user to be monitored according to the control authority of the user to be monitored, a) the user to be monitored has the control authority of the control instruction, and the hyperbaric oxygen chamber is adjusted or early warned according to the control instruction and the comfort model; b) and stopping responding to the control instruction of the user to be monitored when the user to be monitored does not have the control authority of the control instruction.
As a preferred scheme of the hyperbaric oxygen chamber face recognition interactive system, the face model construction module acquires a single-frame/multi-frame infrared face image with speckles/stripes of a user to be monitored through a 3D structure optical depth camera; and 3D face point cloud reconstruction is carried out according to the infrared face image information, and the 3D face point cloud reconstruction comprises the step of obtaining 3D face point clouds of a plurality of angles through space coordinate rotation.
The system is used as a preferred scheme of the face recognition interaction system of the hyperbaric oxygen chamber, and further comprises a voice module for acquiring voice information of a user to be monitored in the hyperbaric oxygen chamber, recognizing the voice information, and adjusting or early warning the hyperbaric oxygen chamber according to a voice recognition result and the control authority of the user to be monitored.
As the preferred scheme of the hyperbaric oxygen chamber face recognition interactive system, the system further comprises an interactive module used for the doctor-patient communication between the user to be monitored and the medical staff.
According to the method, the face image of the user to be monitored in the hyperbaric oxygen chamber is obtained through the 3D structured light depth camera, the face image of the user to be monitored is processed by utilizing a 3D structured light algorithm, and a 3D face model is obtained. And identifying the three-dimensional facial expression of the user to be monitored, extracting the 3D characteristics of the human face and identifying the facial action according to the 3D model of the human face. Judging whether the hyperbaric oxygen chamber of the user to be monitored feels according to the three-dimensional facial expression recognition result, wherein the hyperbaric oxygen chamber feels comprise a plurality of preset comfort level models, matching the human face 3D feature extraction result with a preset human face authority library to acquire the control authority of the user to be monitored, and matching the facial action recognition result with a preset human face instruction set to acquire the control instruction of the user to be monitored. And judging whether to execute the control instruction of the user to be monitored according to the control authority of the user to be monitored. The invention can monitor the facial expression of the patient and automatically adjust or pre-warn the hyperbaric oxygen chamber when the patient feels uncomfortable. Aiming at the patient with inconvenient movement, the intelligent oxygen chamber is controlled by the patient through voice, and the communication between the patient and medical care personnel is realized. The invention solves the problems that the operation of medical care personnel is not standard and operation is carried out by irrelevant responsible personnel, and the like, accurately identifies the operating cabin permission of the operating personnel, and can prevent medical accidents caused by misoperation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
FIG. 1 is a schematic flow chart of a face recognition interaction method for a hyperbaric oxygen chamber according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a human face recognition interaction technology for a hyperbaric oxygen chamber according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a face recognition interaction system for a hyperbaric oxygen chamber according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1 and 2, a face recognition interaction method for a hyperbaric oxygen chamber is provided, which comprises the following steps:
s1: acquiring a face image of a user to be monitored in the hyperbaric oxygen chamber through a 3D structured light depth camera, processing the face image of the user to be monitored by using a 3D structured light algorithm, and obtaining a 3D face model;
s2: identifying three-dimensional facial expressions, human face 3D feature extraction and facial action of the user to be monitored according to the human face 3D model;
s3: judging hyperbaric oxygen chamber feeling of a user to be monitored according to the three-dimensional facial expression recognition result, wherein the hyperbaric oxygen chamber feeling comprises a plurality of preset comfort level models, matching the human face 3D feature extraction result with a preset human face authority library to acquire the control authority of the user to be monitored, and matching the facial action recognition result with a preset human face instruction set to acquire the control instruction of the user to be monitored;
s4: judging whether to execute the control instruction of the user to be monitored according to the control authority of the user to be monitored, a) enabling the user to be monitored to have the control authority of the control instruction, and adjusting or early warning the hyperbaric oxygen chamber according to the control instruction and the comfort level model; b) and stopping responding to the control instruction of the user to be monitored when the user to be monitored does not have the control authority of the control instruction.
In one embodiment of the hyperbaric oxygen chamber face recognition interaction method, a single-frame/multi-frame infrared face image with speckles/stripes of a user to be monitored is acquired through a 3D structured light depth camera; and 3D face point cloud reconstruction is carried out according to the infrared face image information, and the 3D face point cloud reconstruction comprises the step of obtaining 3D face point clouds of a plurality of angles through space coordinate rotation. And performing complementary processing on the 3D face point cloud and the RGB colorful face image, and judging that the face image is a real face or a forged face according to the 3D face point cloud. Specifically, after the structured light projects specific light information to the surface of the object, the light information is collected by the camera, and the information such as the position and the depth of the object is calculated according to the change of the light signal caused by the object, so that the whole three-dimensional space is restored. When a laser beam irradiates the surface of an object, the reflected laser beam carries information such as direction, distance and the like. The laser beam is scanned according to a certain track, reflected laser point information can be recorded while scanning, and a large number of laser points can be obtained due to extremely fine scanning, so that 3D human face point cloud can be formed. And the 3D face point cloud and the RGB colorful face image are fused and complemented, so that a more accurate 3D face model is obtained.
In one embodiment of the hyperbaric oxygen chamber face recognition interaction method, the three-dimensional facial expressions comprise eyebrow lifting, mouth turning and blinking, and the comfort model types of the hyperbaric oxygen chamber are judged according to the three-dimensional facial expression recognition result; the facial actions comprise lifting eyebrows, lefting mouth, blinking, raising head, lowering head, shaking head or covering face; and sending the three-dimensional facial expression and facial action to medical care personnel. And when the user to be monitored does not have the control authority of the control instruction, sending the three-dimensional facial expression and the facial action to medical personnel with the control authority.
Specifically, by analyzing the 3D face model obtained by recognition, three-dimensional facial actions of the patient, such as eyebrow lifting, mouth turning, blinking and the like, can be extracted and obtained, and the control of the hyperbaric oxygen chamber and the communication between the patient who is inconvenient to move and cannot communicate with medical staff by voice are realized by combining a predefined face instruction set. Can protect mask, video and other fraud means. The accuracy of face authority management can be greatly improved, and medical accidents caused by false recognition can be prevented.
In one embodiment of the face recognition interaction method for the hyperbaric oxygen chamber, voice information of a user to be monitored in the hyperbaric oxygen chamber is obtained and recognized, and the hyperbaric oxygen chamber is adjusted or early warned according to a voice recognition result and a preset voice operation instruction set and control authority of the user to be monitored; and sending the voice information to medical staff for doctor-patient communication. Specifically, for the patient who can perform voice communication, voice recognition and analysis are performed through an intelligent voice system to obtain an operating instruction of the intelligent oxygen chamber; or the mandarin modulation is carried out to realize the communication between the patient and the medical care personnel. Intelligent speech recognition technology is now well established, such as Siri in apple, bixby in samsung, science news fly speech, and hectic speech. Wherein, the domestic science news and the Baidu have quite powerful strength in the intelligent voice technology. Therefore, the hyperbaric oxygen chamber can be used for both products.
Referring to fig. 3, an embodiment of the present invention further provides a face recognition interaction system for a hyperbaric oxygen chamber, including:
the image acquisition module 1 is used for acquiring a face image of a user to be monitored in the hyperbaric oxygen chamber through the 3D structured light depth camera;
the face model construction module 2 is used for processing the face image of the user to be monitored by using a 3D structured light algorithm and obtaining a 3D face model;
the feature recognition module 3 is used for recognizing the three-dimensional facial expression, the 3D face feature and the facial action of the user to be monitored according to the 3D face model;
the judging module 4 is used for judging the hyperbaric oxygen chamber feeling of the user to be monitored according to the three-dimensional facial expression recognition result, wherein the hyperbaric oxygen chamber feeling comprises a plurality of preset comfort level models;
the first matching module 5 is used for matching the face 3D feature extraction result with a preset face authority library to acquire the control authority of the user to be monitored;
the second matching module 6 is used for matching the facial action recognition result with a preset face instruction set to acquire a control instruction of the user to be monitored;
the response module 7 is used for judging whether to execute the control instruction of the user to be monitored according to the control authority of the user to be monitored, a) the user to be monitored has the control authority of the control instruction, and the hyperbaric oxygen chamber is adjusted or early warned according to the control instruction and the comfort model; b) and stopping responding to the control instruction of the user to be monitored when the user to be monitored does not have the control authority of the control instruction.
In one embodiment of the hyperbaric oxygen chamber face recognition interactive system, the face model construction module 2 acquires a single-frame/multi-frame infrared face image with speckles/stripes of a user to be monitored through a 3D structured light depth camera; and 3D face point cloud reconstruction is carried out according to the infrared face image information, and the 3D face point cloud reconstruction comprises the step of obtaining 3D face point clouds of a plurality of angles through space coordinate rotation.
Specifically, the 3D structured light depth camera comprises five parts, namely an infrared emitter, an infrared camera, a visible light camera, an internal point cloud reconstruction unit and an image processing unit. The infrared emitter emits infrared light sources such as dot matrixes (speckles)/stripes and the like to acquire single-frame/multi-frame images with the speckles/stripes; the method comprises the following steps that an infrared camera receives infrared IR image information of the surface of an object and is used for reconstructing a 3D face point cloud; and rotating the 3D face point cloud through the space coordinate to obtain the 3D face point cloud with various angles. The 3D face point clouds can be complemented with RGB color face images to obtain a more accurate 3D face model.
In an embodiment of the hyperbaric oxygen chamber face recognition interaction system, the hyperbaric oxygen chamber face recognition interaction system further comprises a voice module 8, wherein the voice module 8 is used for acquiring and recognizing voice information of a user to be monitored in the hyperbaric oxygen chamber, and adjusting or early warning the hyperbaric oxygen chamber according to a voice recognition result and a preset voice operation instruction set and control authority of the user to be monitored. In addition, the monitoring system further comprises an interaction module 9, wherein the interaction module 9 is used for the user to be monitored to communicate with the medical staff for doctors and patients.
According to the method, the face image of the user to be monitored in the hyperbaric oxygen chamber is obtained through the 3D structured light depth camera, the face image of the user to be monitored is processed by utilizing a 3D structured light algorithm, and a 3D face model is obtained. And identifying the three-dimensional facial expression of the user to be monitored, extracting the 3D characteristics of the human face and identifying the facial action according to the 3D model of the human face. Judging whether the hyperbaric oxygen chamber of the user to be monitored feels according to the three-dimensional facial expression recognition result, wherein the hyperbaric oxygen chamber feels comprise a plurality of preset comfort level models, matching the human face 3D feature extraction result with a preset human face authority library to acquire the control authority of the user to be monitored, and matching the facial action recognition result with a preset human face instruction set to acquire the control instruction of the user to be monitored. And judging whether to execute the control instruction of the user to be monitored according to the control authority of the user to be monitored. The invention can monitor the facial expression of the patient and automatically adjust or pre-warn the hyperbaric oxygen chamber when the patient feels uncomfortable. Aiming at the patient with inconvenient movement, the intelligent oxygen chamber is controlled by the patient through voice, and the communication between the patient and medical care personnel is realized. The embodiment of the invention realizes the monitoring of the patient experience by analyzing the three-dimensional facial expression of the patient to identify the comfort degree of the patient. If the patient feels uncomfortable, the hyperbaric oxygen chamber is immediately adjusted by combining the data collected by the intelligent vital sign sensor and the intelligent equipment operation sensor, or medical personnel is informed to take further measures. By analyzing the 3D face model obtained by recognition, the three-dimensional facial actions of the patient, such as eyebrow lifting, mouth turning, blinking and the like, can be extracted, and the control of the oxygen chamber and the communication between the patient who is inconvenient to move and cannot perform voice communication and medical care personnel are realized by combining a predefined face instruction set. For the patient who can carry out voice communication, voice recognition and analysis are carried out through an intelligent voice system to obtain an operating instruction of the intelligent oxygen chamber; or the mandarin modulation is carried out to realize the communication between the patient and the medical care personnel. The invention solves the problems that the operation of medical care personnel is not standard and operation is carried out by irrelevant responsible personnel, and the like, accurately identifies the operating cabin permission of the operating personnel, and can prevent medical accidents caused by misoperation.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A face recognition interaction method for a hyperbaric oxygen chamber is characterized by comprising the following steps:
acquiring a face image of a user to be monitored in the hyperbaric oxygen chamber through a 3D structured light depth camera, processing the face image of the user to be monitored by using a 3D structured light algorithm, and obtaining a 3D face model;
identifying three-dimensional facial expressions, human face 3D feature extraction and facial action of the user to be monitored according to the human face 3D model;
judging hyperbaric oxygen chamber feeling of a user to be monitored according to the three-dimensional facial expression recognition result, wherein the hyperbaric oxygen chamber feeling comprises a plurality of preset comfort level models, matching the human face 3D feature extraction result with a preset human face authority library to acquire the control authority of the user to be monitored, and matching the facial action recognition result with a preset human face instruction set to acquire the control instruction of the user to be monitored;
judging whether to execute the control instruction of the user to be monitored according to the control authority of the user to be monitored, a) enabling the user to be monitored to have the control authority of the control instruction, and adjusting or early warning the hyperbaric oxygen chamber according to the control instruction and the comfort level model; b) and stopping responding to the control instruction of the user to be monitored when the user to be monitored does not have the control authority of the control instruction.
2. The hyperbaric oxygen chamber face recognition interaction method according to claim 1, characterized in that a single frame/multi-frame infrared face image with speckles/stripes of a user to be monitored is acquired by a 3D structured light depth camera; and 3D face point cloud reconstruction is carried out according to the infrared face image information, and the 3D face point cloud reconstruction comprises the step of obtaining 3D face point clouds of a plurality of angles through space coordinate rotation.
3. The hyperbaric oxygen chamber face recognition interaction method of claim 2, wherein the 3D face point cloud and the RGB colorful face image are subjected to complementary processing, and the face image is judged to be a real face or a forged face according to the 3D face point cloud.
4. The hyperbaric chamber face recognition interaction method of claim 1, wherein the three-dimensional facial expressions comprise eyebrow lifting, mouth skimming and eye blinking, and the comfort model type of the hyperbaric chamber is determined according to the three-dimensional facial expression recognition result; the facial actions comprise lifting eyebrows, lefting mouth, blinking, raising head, lowering head, shaking head or covering face; and sending the three-dimensional facial expression and facial action to medical care personnel.
5. The hyperbaric oxygen chamber face recognition interaction method of claim 1, wherein voice information of a user to be monitored in the hyperbaric oxygen chamber is acquired and recognized, and the hyperbaric oxygen chamber is adjusted or pre-warned according to a voice recognition result and a preset voice operation instruction set and control authority of the user to be monitored; and sending the voice information to medical staff for doctor-patient communication.
6. The hyperbaric chamber face recognition interaction method of claim 1, wherein when the user to be monitored does not have the control authority of the control instruction, the three-dimensional facial expression and facial movement are sent to the medical staff with the control authority.
7. A hyperbaric oxygen chamber face recognition interaction system is characterized by comprising:
the image acquisition module is used for acquiring a face image of a user to be monitored in the hyperbaric oxygen chamber through the 3D structured light depth camera;
the face model construction module is used for processing the face image of the user to be monitored by using a 3D structured light algorithm and obtaining a 3D face model;
the feature recognition module is used for recognizing the three-dimensional facial expression, the human face 3D feature and the facial action of the user to be monitored according to the human face 3D model;
the judging module is used for judging the hyperbaric oxygen chamber feeling of the user to be monitored according to the three-dimensional facial expression recognition result, and the hyperbaric oxygen chamber feeling comprises a plurality of preset comfort level models;
the first matching module is used for matching the face 3D feature extraction result with a preset face authority library to acquire the control authority of the user to be monitored;
the second matching module is used for matching the facial action recognition result with a preset human face instruction set to acquire a control instruction of the user to be monitored;
the response module is used for judging whether to execute the control instruction of the user to be monitored according to the control authority of the user to be monitored, a) the user to be monitored has the control authority of the control instruction, and the hyperbaric oxygen chamber is adjusted or early warned according to the control instruction and the comfort model; b) and stopping responding to the control instruction of the user to be monitored when the user to be monitored does not have the control authority of the control instruction.
8. The hyperbaric oxygen chamber face recognition interaction system of claim 7, wherein the face model construction module acquires a single-frame/multi-frame infrared face image with speckles/stripes of a user to be monitored through a 3D structured optical depth camera; and 3D face point cloud reconstruction is carried out according to the infrared face image information, and the 3D face point cloud reconstruction comprises the step of obtaining 3D face point clouds of a plurality of angles through space coordinate rotation.
9. The hyperbaric oxygen chamber face recognition interaction system of claim 7, further comprising a voice module for acquiring and recognizing voice information of a user to be monitored in the hyperbaric oxygen chamber, and adjusting or early warning the hyperbaric oxygen chamber according to a preset voice operation instruction set and control authority of the user to be monitored according to a voice recognition result.
10. The hyperbaric oxygen chamber face recognition interaction system of claim 7, further comprising an interaction module for the user to be monitored to communicate with a medical staff for medical and patient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910583194.5A CN110795981A (en) | 2019-07-01 | 2019-07-01 | Face recognition interaction method and system for hyperbaric oxygen chamber |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910583194.5A CN110795981A (en) | 2019-07-01 | 2019-07-01 | Face recognition interaction method and system for hyperbaric oxygen chamber |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110795981A true CN110795981A (en) | 2020-02-14 |
Family
ID=69426867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910583194.5A Pending CN110795981A (en) | 2019-07-01 | 2019-07-01 | Face recognition interaction method and system for hyperbaric oxygen chamber |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110795981A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111772990A (en) * | 2020-06-01 | 2020-10-16 | 王艳苓 | Negative pressure oxygenation control platform and method based on personnel identification |
| CN113609885A (en) * | 2020-06-22 | 2021-11-05 | 王英婷 | Adaptive cabin door switch control system and method |
| WO2023178769A1 (en) * | 2022-03-24 | 2023-09-28 | 安康泰(烟台)生命科学研究院有限公司 | Oxygen inhalation health management system based on infrared thermal imaging |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106384590A (en) * | 2016-09-07 | 2017-02-08 | 上海联影医疗科技有限公司 | Voice control device and voice control method |
| CN106845191A (en) * | 2016-12-28 | 2017-06-13 | 北京怡和嘉业医疗科技股份有限公司 | For the authorization method and device of therapy apparatus |
| WO2017181769A1 (en) * | 2016-04-21 | 2017-10-26 | 腾讯科技（深圳）有限公司 | Facial recognition method, apparatus and system, device, and storage medium |
| CN107665334A (en) * | 2017-09-11 | 2018-02-06 | 广东欧珀移动通信有限公司 | Intelligent control method and device based on expression |
| CN108090474A (en) * | 2018-01-17 | 2018-05-29 | 华南理工大学 | A kind of hotel service robot system linked up based on cloud voice with mood sensing |
| CN108197558A (en) * | 2017-12-28 | 2018-06-22 | 广东欧珀移动通信有限公司 | Face identification method, device, storage medium and electronic equipment |
| CN109886697A (en) * | 2018-12-26 | 2019-06-14 | 广州市巽腾信息科技有限公司 | Method, apparatus and electronic equipment are determined based on the other operation of expression group |
-
2019
- 2019-07-01 CN CN201910583194.5A patent/CN110795981A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017181769A1 (en) * | 2016-04-21 | 2017-10-26 | 腾讯科技（深圳）有限公司 | Facial recognition method, apparatus and system, device, and storage medium |
| CN106384590A (en) * | 2016-09-07 | 2017-02-08 | 上海联影医疗科技有限公司 | Voice control device and voice control method |
| CN106845191A (en) * | 2016-12-28 | 2017-06-13 | 北京怡和嘉业医疗科技股份有限公司 | For the authorization method and device of therapy apparatus |
| CN107665334A (en) * | 2017-09-11 | 2018-02-06 | 广东欧珀移动通信有限公司 | Intelligent control method and device based on expression |
| CN108197558A (en) * | 2017-12-28 | 2018-06-22 | 广东欧珀移动通信有限公司 | Face identification method, device, storage medium and electronic equipment |
| CN108090474A (en) * | 2018-01-17 | 2018-05-29 | 华南理工大学 | A kind of hotel service robot system linked up based on cloud voice with mood sensing |
| CN109886697A (en) * | 2018-12-26 | 2019-06-14 | 广州市巽腾信息科技有限公司 | Method, apparatus and electronic equipment are determined based on the other operation of expression group |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111772990A (en) * | 2020-06-01 | 2020-10-16 | 王艳苓 | Negative pressure oxygenation control platform and method based on personnel identification |
| CN113609885A (en) * | 2020-06-22 | 2021-11-05 | 王英婷 | Adaptive cabin door switch control system and method |
| WO2023178769A1 (en) * | 2022-03-24 | 2023-09-28 | 安康泰(烟台)生命科学研究院有限公司 | Oxygen inhalation health management system based on infrared thermal imaging |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105518711B (en) | Biopsy method, In vivo detection system and computer program product | |
| CN104834901B (en) | A kind of method for detecting human face, apparatus and system based on binocular stereo vision | |
| US8984622B1 (en) | User authentication through video analysis | |
| US9750420B1 (en) | Facial feature selection for heart rate detection | |
| CN105612533B (en) | Living body detection method, living body detection system, and computer program product | |
| WO2021143266A1 (en) | Method and apparatus for detecting living body, electronic device and storage medium | |
| US20170337352A1 (en) | Confidential information occlusion using augmented reality | |
| CN110795981A (en) | Face recognition interaction method and system for hyperbaric oxygen chamber | |
| CN108875485A (en) | A kind of base map input method, apparatus and system | |
| US20160341961A1 (en) | Context-based augmented reality content delivery | |
| TWI617948B (en) | Module, method and computer readable medium for eye-tracking correction | |
| CN104933344A (en) | Mobile terminal user identity authentication device and method based on multiple biological feature modals | |
| CN107563304A (en) | Unlocking terminal equipment method and device, terminal device | |
| WO2020135125A1 (en) | Living body detection method and device | |
| JP2015088096A (en) | Information processor and information processing method | |
| JP2015088095A (en) | Information processor and information processing method | |
| US20220262163A1 (en) | Method of face anti-spoofing, device, and storage medium | |
| JP2015088098A (en) | Information processor and information processing method | |
| JP2007163864A (en) | Display control apparatus, display control method, display control program, and display control program recording medium | |
| KR20160009972A (en) | Iris recognition apparatus for detecting false face image | |
| Mussi et al. | A novel ear elements segmentation algorithm on depth map images | |
| US20160217565A1 (en) | Health and Fitness Monitoring via Long-Term Temporal Analysis of Biometric Data | |
| WO2020019346A1 (en) | Biometric identification method, device, system, and terminal device | |
| JP2021077333A (en) | Line-of-sight detection method, line-of-sight detection device, and control program | |
| JP2021077265A (en) | Line-of-sight detection method, line-of-sight detection device, and control program |
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 |