CN111241917B - Self-adaptive non-contact physiological acquisition cradle head camera device and method - Google Patents
Self-adaptive non-contact physiological acquisition cradle head camera device and method Download PDFInfo
- Publication number
- CN111241917B CN111241917B CN201911355609.XA CN201911355609A CN111241917B CN 111241917 B CN111241917 B CN 111241917B CN 201911355609 A CN201911355609 A CN 201911355609A CN 111241917 B CN111241917 B CN 111241917B
- Authority
- CN
- China
- Prior art keywords
- face
- image
- frame
- analysis
- acquisition
- 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.)
- Active
Links
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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
- G06V40/15—Biometric patterns based on physiological signals, e.g. heartbeat, blood flow
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Signal Processing (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The self-adaptive non-contact physiological acquisition cradle head camera device comprises an image acquisition module, an adjustment module, a storage module and an analysis processing module; the image acquisition module comprises a lens, an infrared controller, an infrared lamp, an infrared filter, an optical sensor, an image processing device and a coding device; the adjusting module comprises a preset point device, a self-adaptive adjusting device and a cradle head control device; the analysis processing module comprises a face detection device, a face acquisition device and a blood spectrum analysis device; the storage module comprises a memory; according to the invention, by setting the cradle head capable of adaptively adjusting the focal length, the size of the face image acquired by the cradle head can meet the detection requirement, and the condition that the distances between the detected person and the cradle head are different can be adapted.
Description
Technical Field
The invention relates to the field of image recognition, in particular to a self-adaptive non-contact physiological acquisition cradle head camera device and a method.
Background
With the development of scientific technology, the observation technology is also increasing, from the initial passing contact blood pressure detection device to the subsequent non-contact detection device. Since human skin is semitransparent, light can be transmitted to an arterial blood vessel layer below the skin, hemoglobin in the arterial blood vessel can absorb part of the transmitted light, and the rest light can form reflected light in the arterial blood vessel layer; with the contraction and relaxation of the heart beat of a human body, the hemoglobin density of arterial blood vessels fluctuates along with the heart beat, when the heart contracts, the hemoglobin density in arterial blood vessels becomes high, more transmitted light is absorbed, so that the intensity of reflected light becomes weak, whereas when the heart relaxes, the hemoglobin density in arterial blood vessels becomes low, less transmitted light is absorbed, so that the intensity of reflected light becomes strong, and therefore physiological/psychological indexes such as heart rate can be obtained through analysis of the change of reflected light. Therefore, the change of the reflected light is detected by the non-contact detection equipment, and physiological/psychological indexes such as heart rate, respiration, blood pressure psychological pressure and the like of the detected personnel can be obtained. However, in the course of the actual deployment implementation, it is not guaranteed that the person to be examined is camera-specific, since the camera for the acquired image is fixed. Meanwhile, for a plurality of detected personnel in one scene, the existing non-contact detection equipment can generate interference, and is difficult to quickly and accurately identify.
Disclosure of Invention
The invention aims to solve the defects of the prior art and provides a self-adaptive non-contact physiological acquisition cradle head camera device and a method, which have the advantages of simple structure and convenient use.
The self-adaptive non-contact physiological acquisition cradle head camera device comprises an image acquisition module, an adjustment module, a storage module and an analysis processing module; the image acquisition module comprises a lens, an infrared controller, an infrared lamp, an infrared filter, an optical sensor, an image processing device and a coding device; the adjusting module comprises a preset point device, a self-adaptive adjusting device and a cradle head control device; the analysis processing module comprises a face detection device, a face acquisition device and a blood spectrum analysis device; the storage module comprises a memory; the infrared lamp and the infrared filter are arranged between the lens of the pan-tilt camera and the optical sensor; the infrared controller is electrically connected with the infrared lamp and the infrared filter; the image processing device is electrically connected with the encoding device, the face detection device and the optical sensor; the memory is electrically connected with the encoding device and the blood spectrum physiological analysis device; the face detection device is also electrically connected with the preset point migration device, the self-adaptive adjustment device and the face acquisition device; the cradle head control device is electrically connected with the preset point migration device and the self-adaptive adjusting device; the human face acquisition device is also electrically connected with the blood spectrum physiological analysis device.
An adaptive non-contact physiological acquisition method, which relies on the cradle head camera device, comprises the following steps:
step 1: the image acquisition module acquires a frame image, performs preliminary processing on the frame image to obtain an uncompressed video stream and an encoded video stream, transmits the uncompressed video stream to the analysis processing module, and transmits the encoded video stream to the storage module;
step 2: the analysis processing module receives the uncompressed video stream, analyzes and processes the uncompressed video stream, and sends analysis processing results to the storage module and the adjusting module according to the analysis processing of the face frame image;
step 3: and (3) the adjusting module receives the analysis and processing result, adjusts the cradle head according to the analysis and processing result, and returns to the step (1).
Further, the step of acquiring the frame image in the step 1 and performing preliminary processing on the frame image includes:
step 1.1: the infrared controller judges whether to open the infrared mode according to a control instruction input by an operator; if the infrared module is turned on, the infrared lamp is turned on, and the infrared filter is turned on; if the infrared mode is not started, the infrared lamp is turned off, and the infrared filter is turned off;
step 1.2: the optical sensor receives natural light or infrared band light, converts the sensed optical signal into an electric signal and sends the electric signal to the image processing device;
step 1.3: the image processing device receives the electric signal, digitizes the electric signal to generate YUV or RGB frame images, and continuously outputs the frame images to the encoding device and the face detection device;
step 1.4: the encoding device receives the frame images, encodes the frame images according to an H.264/H.265 encoding protocol to form an encoded video stream, and sends the encoded video stream to the memory.
Further, the uncompressed video stream in step 1.3 is a frame image output by the image processing apparatus according to time sequence.
Further, in the step 2, the processing step of the analysis processing module for the uncompressed video stream includes:
step 2.1: the face detection device receives the uncompressed video stream sent by the image processing device, performs preliminary processing on the face frame image, and sends the image data information after the preliminary processing to the face acquisition device and the self-adaptive adjustment device;
step 2.2: the face acquisition device receives the image data information after preliminary processing, extracts face blood spectrum information from the image data information, and sends the extracted face blood spectrum information to the blood spectrum physiological analysis device;
step 2.3: the blood spectrum physiological analysis device receives the human face blood spectrum information, analyzes the physiological index to obtain a corresponding physiological index change curve, and transmits an analysis result to the memory;
the preliminary processing of the face frame image by the face detection device in the step 2.1 comprises an image processing main flow and a face database aging flow.
Further, the image processing main flow includes:
step 2.1.1: the face detection device performs initialization processing; the initialization processing comprises the steps of emptying a face database, setting a face ID to 0, setting a face detection device to a non-sampling state, and setting an acquisition frame number to 0;
step 2.1.2: the face detection device receives a frame of face frame image; if the received frame image format is YUV format, converting into RGB format;
step 2.1.3: the face detection device recognizes a face from the received face frame image, if a new face is detected, the face closest to the middle of the image is taken as the face of the frame image, a face ID is set, and the step 2.1.4 is performed; if the face with the face ID is detected, detecting an old face, and turning to the step 2.1.5; if no face exists in the received face frame image, turning to step 2.1.11;
step 2.1.4: the face detection device performs face comparison; the face comparison is to compare the face frame image of the detected new face with the faces in the face database, and if the comparison is successful, the face is proved to have been subjected to physiological index analysis, and the step 2.1.11 is shifted; if the comparison is unsuccessful, the frame image is required to be subjected to physiological index analysis, the frame image is transmitted to a human face database for storage, and an aging timer of the human face frame image is set as an initial set value;
step 2.1.5: the face detection device acquires face information, wherein the face information comprises a face rectangular frame for acquiring the frame image, a face angle face image and an image time stamp;
step 2.1.6: the face detection device carries out sampling state identification; if the sampling state is the sampling state, turning to the step 2.1.7; if not, go to step 2.1.8;
step 2.1.7: the face detection device sends the face rectangular frame and the face angle obtained in the step 2.1.5 to the self-adaptive adjusting device, and judges the sampling quality according to the feedback of the self-adaptive adjusting device; if the self-adaptive adjusting device returns to reach the sampling quality, setting the self-adaptive adjusting device to be in a sampling state, and turning to step 2.1.8; if the adaptive adjustment device returns to not reach the sampling quality, go to step 2.1.12;
step 2.1.8: the face detection device carries out face tracking detection on the face frame image to obtain face characteristic points and characteristic point coordinates; the feature point coordinates are coordinates of the face feature points in the frame image;
step 2.1.9: the face detection device sends the face ID, the face image, the image time stamp, the face rectangular frame, the face angle and the face feature point coordinates to the face acquisition device;
step 2.1.10: the face detection device judges whether the acquired frame number reaches a set value; if the acquisition frame number reaches the set value, turning to a step 2.1.11; if the number of acquired frames does not reach the set value, go to step 2.1.12;
step 2.1.11: the face detection device sends a preset point migration instruction to the preset point migration device, the preset point migration instruction is set to be in a non-sampling state, the preset time is waited for, and the step 2.1.2 is carried out;
step 2.1.12: the face detection device sends an adjusting instruction to the self-adaptive adjusting device, waits for the set time and goes to step 2.1.2.
Further, the aging process of the face database is as follows: firstly, setting an aging initial value; secondly, according to the face comparison in the step 2.1.4, if each comparison is successful, the aging timer is reduced by 1; and if the aging timer of the face ID is zero, deleting the face ID and the corresponding face map.
Further, the step of extracting the facial blood spectrum information by the facial acquisition device in the step 2.2 includes:
step 2.2.1: initializing a face acquisition device, wherein the face acquisition device comprises resetting face sampling ID to zero and acquiring frame number to zero;
step 2.2.2: the face acquisition device receives information of a face frame image, wherein the information comprises a face ID, a face image, an image time stamp, a face rectangular frame, a face angle and face feature point coordinates;
step 2.2.3: the face acquisition device judges whether the face ID is equal to the face sampling ID; if the face ID is equal to the face sampling ID, continuing to sample, and turning to step 2.2.5; otherwise, turning to step 2.2.4;
step 2.2.4: the face acquisition device clears the sampled data, resumes sampling, sets face sampling id=face ID, acquires frame number=0, and goes to step 2.2.2;
step 2.2.5: the face acquisition device divides face blocks according to coordinates of face feature points;
step 2.2.6: the face acquisition device extracts face blood spectrum information in a face frame image;
step 2.2.7: the face acquisition device judges whether the acquisition frame number meets a set value, if not, the step 2.2.2 is carried out;
step 2.2.8: the face acquisition device packages the face blood spectrum information with set time length and sends the face blood spectrum information to the blood spectrum physiological analysis device.
Further, in the step 2.3, the analysis of the physiological index of the blood spectrum physiological analysis device includes:
step 2.3.1: receiving a face blood spectrum information compression packet, and decompressing to obtain face blood spectrum information;
step 2.3.2: combining the human face blood spectrum information of the specific human face blocks according to the time sequence respectively; the combined human face blood spectrum information is human face blood spectrum information with set duration formed by splicing the contents of one or more human face blood spectrum information compression packets according to the analysis requirements of physiological indexes in time sequence; the specific face block is determined according to the detection target;
step 2.3.3: performing a physiological index analysis, the physiological index analysis comprising the steps of:
step 2.3.31: carrying out wavelet function filtering treatment on the face blood spectrum information with the set time length obtained in the step 2.3.2; the method aims at filtering out the information of non-target frequency bands;
step 2.3.32: slicing the filtered human face blood spectrum information according to a set time length;
step 2.3.33: carrying out Fourier transform on the face blood spectrum information after each slice to obtain a target frequency spectrum corresponding to the slice;
step 2.3.34: averaging each target frequency spectrum, and sequencing according to a time sequence to obtain a target change curve;
step 2.3.4: obtaining a final physiological index analysis result;
step 2.3.5: and (3) sending the physiological index analysis result obtained in the step (2.3.4) to a memory.
Further, in the step 3, the adjusting the pan-tilt includes shifting a preset point of the pan-tilt and adaptively adjusting the posture of the pan-tilt; the step of migrating the preset point comprises the following steps:
step 3.1: the preset point migration device configures preset points of the holder, wherein at least one preset point is arranged, and the preset points comprise a holder angle, a holder focal length and a preset point number; setting the serial number of the largest preset point as m, wherein m is more than or equal to 1;
step 3.2: the preset point migration device sets the serial number of the initial polling preset point as 1, and sends parameter information of the initial polling preset point to the holder and the zoom control module;
step 3.3: the preset point migration device receives a preset point migration instruction sent by the face detection device to perform preset point migration, if the preset point number where the cloud deck is located when receiving the instruction is i, i+1, and if i > m, i resets 1; parameter information of a preset point i is sent to a holder and a zoom control module;
the parameter information of the preset points in the step 3.2 and the step 3.3 comprises a holder angle, a holder focal length and a preset point number;
the self-adaptive adjustment of the cradle head posture comprises:
step 4.1: the self-adaptive adjusting device receives face parameters, including a face rectangular frame and face angle parameters sent by the face detection module;
step 4.2: the self-adaptive adjusting device judges whether the sampling requirement is met; if the width pixels of the rectangular frame of the human face and the angle of the human face are in the preset range, the sampling quality requirement is considered to be met, information reaching the sampling quality is sent to the human face detection device, and the step 4.1 is shifted;
step 4.3: the self-adaptive adjusting device calculates the optimal holder posture; comparing the width pixels of the rectangular frame of the human face with a preset range to obtain a focal length adjustment parameter, and comparing the angle of the human face with the preset range to obtain a cradle head angle adjustment parameter;
step 4.4: the self-adaptive adjusting device sends the posture adjusting parameters of the cradle head to the cradle head control device, and the step 4.1 is carried out; the pan-tilt posture adjustment parameters comprise pan-tilt angle adjustment parameters and focal length adjustment parameters.
The beneficial effects of the invention are as follows:
according to the invention, by setting the cradle head capable of adaptively adjusting the focal length, the size of the face image acquired by the cradle head can meet the detection requirement, and the condition that the distances between the detected person and the cradle head are different can be adapted.
The invention greatly accelerates the running speed of the device and reduces repeated detection of the same face by setting the face database and the face aging timer.
According to the invention, through setting and scanning the preset points by the holder, the holder camera can cover all detected personnel in the scene range set by detection.
Drawings
FIG. 1 is a structural diagram of the present invention;
FIG. 2 is a schematic view of the preset points of the pan-tilt camera of the present invention;
FIG. 3 is a block flow diagram of a face detection apparatus according to the present invention;
FIG. 4 is a block flow diagram of a face acquisition device of the present invention;
FIG. 5 is a block flow diagram of a blood spectrum physiological analysis device according to the present invention.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
Example 1
As shown in fig. 1, the self-adaptive non-contact physiological acquisition cradle head camera device comprises an image acquisition module, an adjustment module, a storage module and an analysis processing module. The image acquisition module is used for acquiring face images of detected people and comprises a lens, an infrared controller, an infrared lamp, an infrared filter, an optical sensor, an image processing device and a coding device. The adjusting module is used for adjusting shooting angles, focal lengths and the like of the cradle head camera and comprises a preset point device, a self-adaptive adjusting device and a cradle head control device. The analysis processing module comprises a face detection device, a face acquisition device and a blood spectrum analysis device. The memory module includes a memory.
The infrared controller is electrically connected with the infrared lamp and the infrared filter; the image processing device is electrically connected with the encoding device, the face detection device and the optical sensor; the memory is electrically connected with the encoding device and the blood spectrum physiological analysis device; the face detection device is also electrically connected with the preset point migration device, the self-adaptive adjustment device and the face acquisition device; the cradle head control device is electrically connected with the preset point migration device and the self-adaptive adjusting device; the face acquisition device is also electrically connected with the blood spectrum physiological analysis device
The infrared lamp and the infrared filter are arranged between the lens of the cradle head camera and the optical sensor. The infrared controller is electrically connected with the infrared lamp and the infrared filter, and can control the infrared lamp and the infrared filter to be turned on and off, and when the infrared lamp and the infrared filter are turned off, the optical sensor receives a natural light wave band to form a color image; when the infrared lamp and the infrared filter are turned on, the optical sensor receives the infrared light wave band to form a black-and-white image. The optical sensor is capable of receiving a natural light band or an infrared light band and converts a received light band signal into an electrical signal. The image processing device can receive the electric signals, convert the received electric signals into YUV or RGB frame images, and sequence the converted frame images according to the receiving time sequence to form an uncompressed video stream, and send the uncompressed video stream to the encoding device and the analysis processing module. The encoding device can receive the non-compressed video stream and encode the non-compressed video stream into an encoded video stream by H.264/H.265, and the encoded video stream is transmitted to the storage module.
The storage module can receive the coded video stream acquired by the image acquisition module and store the coded video stream, so that subsequent operations such as playback and video recording are facilitated; the storage module also receives the processing result of the analysis processing module. The storage module is electrically connected with a display device and can display the received processing result of the analysis processing module in real time.
The face detection device can receive the uncompressed video stream converted by the image processing device, compares the converted uncompressed video stream with a face database, if the comparison is successful, the face in the uncompressed video stream is detected by the physiological index, and the uncompressed video stream is associated with the successfully compared face in the face database for storage; if the comparison is unsuccessful, the face frame image in the uncompressed video stream is required to be detected in physiological indexes, the information of a face rectangular frame and face angles is obtained, and meanwhile, the face frame image is subjected to face database warehouse entry processing. The working states of the face detection device comprise a sampling state and a non-sampling state. The face database is stored in the storage module.
If the face detection device is in a sampling state, the face detection device starts to acquire face feature points, wherein the face feature points comprise face outlines, lips, noses, eyesockets, eyebrows and forehead. And then the face detection device transmits the face information to the face acquisition device, wherein the face information comprises a frame image of a face and face feature points. If the number of the acquired face frame images reaches a set value, controlling a preset point migration device to migrate the preset points; if the set value is not reached, the image acquisition module continues sampling.
If the face detection device is in a non-sampling state, the face rectangular frame and the face angle information are sent to the self-adaptive adjusting device, and the self-adaptive adjusting device analyzes whether the set sampling quality requirement is met or not. If the set sampling quality requirement is met, the face detection device starts to acquire face feature points; then the face detection device sends face information to the face acquisition device, wherein the face information comprises a frame image of a face and face feature points; then judging whether the number of the collected face frame images reaches a set value by a face detection device, and if the number of the collected face frame images reaches the set value, controlling a preset point migration device to migrate the preset point; if the set value is not reached, the image acquisition module continues sampling. If the set sampling quality requirement is not met, restarting analysis according to the acquired face frame image.
As shown in fig. 2, the preset point migration device can adjust the posture of the pan-tilt by configuring the position information of at least one preset point. The preset points are provided with numbers, the initial preset point number of the cradle head is a preset point position, the cradle head carries out posture adjustment according to the preset point migration instruction, and the cradle head posture comprises a cradle head angle and a cradle head camera lens focal length. The preset point migration instruction is sent out by the face detection device.
The self-adaptive adjusting device can analyze and judge whether the face frame image meets the sampling quality requirement set by the face acquisition device according to the size of the face rectangular frame and the face angle obtained by processing of the face detection device, and the judging process comprises the steps of judging whether the size of the face rectangular frame reaches a set value and judging whether the face angle is in a set range. And if the sampling quality requirement set by the face acquisition device is not met, adjusting the posture of the cradle head.
The cradle head control device can adjust the preset point of the cradle head or the gesture of the cradle head according to the instruction of the preset point migration device or the self-adaptive adjustment device.
The face acquisition device divides the face blocks according to the coordinate values of the face feature points in the face rectangular frame, and extracts RGB or gray value information from the face blocks. For a color image, extracting RGB information of a face block; for a black-and-white image, gray value information of a face image is extracted, and r=g=b=gray value. The face acquisition device performs the above processing on each frame of the uncompressed video stream, so as to obtain RGB or gray value sequence information of the face blocks ordered in time, namely face blood spectrum information of the uncompressed video stream in a corresponding time period.
The blood spectrum physiological analysis device receives the packed human face blood spectrum information from the human face acquisition device, and performs physiological index analysis on the human face blood spectrum information, wherein the physiological index analysis comprises analysis of heart rate, respiration and blood pressure.
A non-contact physiological acquisition method based on the self-adaptive non-contact physiological acquisition cradle head camera device comprises the following steps:
step 1: the image acquisition module acquires a frame image, performs preliminary processing on the frame image to obtain an uncompressed video stream and an encoded video stream, transmits the uncompressed video stream to the analysis processing module, and transmits the encoded video stream to the storage module;
step 2: the analysis processing module receives the uncompressed video stream, analyzes and processes the uncompressed video stream, and sends analysis processing results to the storage module and the adjusting module according to the analysis processing of the face frame image;
step 3: and (3) the adjusting module receives the analysis and processing result, adjusts the cradle head according to the analysis and processing result, and returns to the step (1).
The step 1 of obtaining a frame image and performing preliminary processing on the frame image comprises the following steps:
step 1.1: the infrared controller judges whether to open the infrared mode according to a control instruction input by an operator; if the infrared module is turned on, the infrared lamp is turned on, and the infrared filter is turned on; if the infrared mode is not started, the infrared lamp is turned off, and the infrared filter is turned off;
step 1.2: the optical sensor receives natural light or infrared band light, converts the sensed optical signal into an electric signal and sends the electric signal to the image processing device;
step 1.3: the image processing device receives the electric signal, digitizes the electric signal to generate YUV or RGB frame images, and continuously outputs the frame images to the encoding device and the face detection device;
step 1.4: the encoding device receives the frame images, encodes the frame images according to an H.264/H.265 encoding protocol to form an encoded video stream, and sends the encoded video stream to the memory.
In the step 1.3, the frame images are ordered according to time sequence in the process that the image processing device continuously outputs the frame images, and the frame image sequence ordered according to time sequence forms an uncompressed video stream.
In the step 2, the processing step of the analysis processing module for the uncompressed video stream includes:
step 2.1: the face detection device receives the uncompressed video stream sent by the image processing device, performs preliminary processing on the face frame image, and sends the image data information after the preliminary processing to the face acquisition device and the self-adaptive adjustment device;
step 2.2: the face acquisition device receives the image data information after preliminary processing, extracts face blood spectrum information from the image data information, and sends the extracted face blood spectrum information to the blood spectrum physiological analysis device;
step 2.3: the blood spectrum physiological analysis device receives the human face blood spectrum information, analyzes the physiological index to obtain a corresponding physiological index change curve, and transmits an analysis result to the memory.
As shown in fig. 3, the preliminary processing of the face frame image by the face detection apparatus in step 2.1 includes an image processing main flow and a face database aging flow, where the image processing main flow includes:
step 2.1.1: the face detection device performs initialization processing; the initialization processing comprises the steps of emptying a face database, setting a face ID to 0, setting a face detection device to a non-sampling state, and setting an acquisition frame number to 0;
step 2.1.2: receiving a frame of face frame image; if the received frame image format is YUV format, converting into RGB format;
step 2.1.3: recognizing a human face from the received human face frame image, if a new human face is detected, taking the human face closest to the middle part of the image as the human face of the frame image, setting a human face ID, and turning to step 2.1.4; if the face with the face ID is detected, detecting an old face, and turning to the step 2.1.5; if no face exists in the received face frame image, turning to step 2.1.11;
step 2.1.4: face comparison is carried out; the face comparison is to compare the face frame image of the detected new face with the faces in the face database, and if the comparison is successful, the face is proved to have been subjected to physiological index analysis, and the step 2.1.11 is shifted; if the comparison is unsuccessful, the frame image is required to be subjected to physiological index analysis, the frame image is transmitted to a human face database for storage, and an aging timer of the human face frame image is set as an initial set value;
step 2.1.5: acquiring face information, wherein the face information comprises a face rectangular frame for acquiring the frame image, a face angle face image and an image time stamp;
step 2.1.6: identifying a sampling state; if the sampling state is the sampling state, turning to the step 2.1.7; if not, go to step 2.1.8;
step 2.1.7: the face rectangular frame and the face angle obtained in the step 2.1.5 are sent to the self-adaptive adjusting device, and the sampling quality is judged according to the feedback of the self-adaptive adjusting device; if the self-adaptive adjusting device returns to reach the sampling quality, setting the self-adaptive adjusting device to be in a sampling state, and turning to step 2.1.8; if the adaptive adjustment device returns to not reach the sampling quality, go to step 2.1.12;
step 2.1.8: carrying out face tracking detection on the face frame image to obtain face characteristic points and characteristic point coordinates; the feature point coordinates are coordinates of the face feature points in the frame image;
step 2.1.9: transmitting the face ID, the face image, the image time stamp, the face rectangular frame, the face angle and the face feature point coordinates to a face acquisition device;
step 2.1.10: judging whether the acquisition frame number reaches a set value or not; if the acquisition frame number reaches the set value, turning to a step 2.1.11; if the number of acquired frames does not reach the set value, go to step 2.1.12;
step 2.1.11: transmitting a preset point migration instruction to a preset point migration device, setting the preset point migration instruction to a non-sampling state, waiting for a set time, and turning to step 2.1.2;
step 2.1.12: and sending an adjusting instruction to the self-adaptive adjusting device, waiting for the set time, and turning to step 2.1.2.
Setting face IDs in the step 2.1.3 to be set in sequence; the detected new face is a face which is different from the existing face ID in the face frame image of the frame; the detected old face is the face with the detected existing face ID.
The aging process of the face database is as follows: firstly, setting an aging initial value; secondly, according to the face comparison in the step 2.1.4, if each comparison is successful, the aging timer is reduced by 1; and if the aging timer of a certain face ID is zero, deleting the face ID and the corresponding face map.
As shown in fig. 4, the step of extracting the facial blood spectrum information by the facial acquisition device in the step 2.2 includes:
step 2.2.1: initializing a face acquisition device, wherein the face acquisition device comprises resetting face sampling ID to zero and acquiring frame number to zero;
step 2.2.2: receiving information of a face frame image, wherein the information comprises a face ID, a face image, an image time stamp, a face rectangular frame, a face angle and face feature point coordinates;
step 2.2.3: judging whether the face ID is equal to the face sampling ID; if the face ID is equal to the face sampling ID, continuing to sample, and turning to step 2.2.5; otherwise, turning to step 2.2.4;
step 2.2.4: clearing the sampled data, restarting sampling, setting face sampling ID=face ID, collecting frame number=0, and turning to step 2.2.2;
step 2.2.5: dividing the face blocks according to the coordinates of the face feature points;
step 2.2.6: extracting human face blood spectrum information in a human face frame image;
step 2.2.7: judging whether the acquisition frame number meets a set value, if not, turning to step 2.2.2;
step 2.2.8: and packaging the face blood spectrum information with the set time length and sending the face blood spectrum information to a blood spectrum physiological analysis device.
Wherein, the face blood spectrum information in step 2.2.6 includes RGB or gray value information of face blocks, different physiological indexes correspond to block information of different face blocks, wherein, for color images, RGB information of face blocks is extracted; for a black-and-white image, gray value information of a face image is extracted, and r=g=b=gray value. In this embodiment, in order to improve accuracy, a plurality of relevant block information may be collected for the physiological index to be analyzed at the same time.
As shown in fig. 5, in the step 2.3, the physiological index analysis of the blood spectrum physiological analysis device includes:
step 2.3.1: receiving a face blood spectrum information compression packet, and decompressing to obtain face blood spectrum information;
step 2.3.2: combining the human face blood spectrum information of the specific human face blocks according to the time sequence respectively; the combined human face blood spectrum information is human face blood spectrum information with set duration formed by splicing the contents of one or more human face blood spectrum information compression packets according to the analysis requirements of physiological indexes in time sequence; the specific face block is determined according to a detection target, for example, heart rate detection corresponds to a specific heart rate detection block;
step 2.3.3: performing a physiological index analysis, the physiological index analysis comprising the steps of:
step 2.3.31: carrying out wavelet function filtering treatment on the face blood spectrum information with the set time length obtained in the step 2.3.2; the method aims at filtering out information of non-target frequency bands, and takes heart rate analysis as an example, wavelet function filtering can be performed to filter out information of non-heart rate frequency bands;
step 2.3.32: slicing the filtered human face blood spectrum information according to a set time length;
step 2.3.33: carrying out Fourier transform on the facial blood spectrum information after each slice to obtain a target frequency spectrum corresponding to the slice, such as a heart rate frequency spectrum;
step 2.3.34: averaging each target frequency spectrum, and sequencing according to a time sequence to obtain a target change curve, such as a heart rate change curve;
step 2.3.4: selecting the target change curve of the specific block to obtain a final physiological index analysis result with the best signal quality; wherein the signal quality is determined according to the signal-to-noise ratio;
step 2.3.5: and (3) sending the physiological index analysis result obtained in the step (2.3.4) to a memory.
In the step 3, the adjusting the pan-tilt includes the migration of the preset point of the pan-tilt and the self-adaptive adjustment of the posture of the pan-tilt.
The step of migrating the preset point comprises the following steps:
step 3.1: configuring preset points of a holder, wherein a plurality of preset points can be configured, the number of the preset points is at least one, and the preset points comprise a holder angle, a holder focal length, a preset point number and the like; setting the serial number of the largest preset point as m, wherein m is more than or equal to 1;
step 3.2: setting the serial number of an initial polling preset point as 1, and sending parameter information of the initial polling preset point to the holder and the zoom control module;
step 3.3: the method comprises the steps of receiving a preset point migration instruction sent by a face detection device to perform preset point migration, setting the preset point number where a cloud deck receives the instruction as i, i+1, and if i > m, resetting 1; and sending parameter information of the preset point i to the holder and the zoom control module.
The parameter information of the preset points in step 3.2 and step 3.3 includes a pan-tilt angle, a pan-tilt focal length, a preset point number, and the like.
The step of adaptively adjusting the posture of the cradle head comprises the following steps:
step 4.1: the face receiving parameters comprise parameters such as a face rectangular frame, a face angle and the like sent by a face receiving detection module;
step 4.2: judging whether the sampling requirement is met; if the width pixels of the rectangular frame of the human face and the angle of the human face are in the preset range, the sampling quality requirement is considered to be met, information reaching the sampling quality is sent to the human face detection device, and the step 4.1 is shifted;
step 4.3: calculating the optimal holder posture; comparing the width pixels of the rectangular frame of the human face with a preset range to obtain a focal length adjustment parameter, and comparing the angle of the human face with the preset range to obtain a cradle head angle adjustment parameter;
step 4.4: transmitting the cradle head posture adjustment parameters to a cradle head control device, and turning to step 4.1; the pan-tilt posture adjustment parameters comprise pan-tilt angle adjustment parameters and focal length adjustment parameters.
Step 4.3, wherein in the embodiment, the optimal cradle head gesture is that the width pixels of the rectangular frame of the human face are between 150 and 250; the left and right angles of the human face are 0-15 degrees, and the up and down angles are 0-30 degrees.
Example two
A non-infrared self-adaptive non-contact physiological acquisition cradle head camera device comprises an image acquisition module, an adjustment module, a storage module and an analysis processing module. The image acquisition module is used for acquiring a face image of the detected person and comprises an optical sensor, an image processing device and an encoding device.
The foregoing description of the embodiments of the invention is not intended to limit the invention in any way, but rather to make simple modifications, equivalent variations or modifications without departing from the technical solution of the invention, all falling within the scope of the invention.
Claims (7)
1. The self-adaptive non-contact physiological acquisition method is characterized by comprising the following steps of:
step 1: the image acquisition module acquires a frame image, performs preliminary processing on the frame image to obtain an uncompressed video stream and an encoded video stream, transmits the uncompressed video stream to the analysis processing module, and transmits the encoded video stream to the storage module;
step 2: the analysis processing module receives the uncompressed video stream, analyzes and processes the uncompressed video stream, and sends analysis processing results to the storage module and the adjusting module according to the analysis processing of the face frame image;
step 3: the adjusting module receives the analysis and processing result and adjusts the cradle head according to the analysis and processing result, and the step 1 is returned; in the step 2, the processing step of the analysis processing module for the uncompressed video stream includes:
step 2.1: the face detection device receives the uncompressed video stream sent by the image processing device, performs preliminary processing on the face frame image, and sends the image data information after the preliminary processing to the face acquisition device and the self-adaptive adjustment device;
step 2.2: the face acquisition device receives the image data information after preliminary processing, extracts face blood spectrum information from the image data information, and sends the extracted face blood spectrum information to the blood spectrum physiological analysis device;
step 2.3: the blood spectrum physiological analysis device receives the human face blood spectrum information, analyzes the physiological index to obtain a corresponding physiological index change curve, and transmits an analysis result to the memory;
the preliminary processing of the face frame image by the face detection device in the step 2.1 comprises an image processing main flow and a face database aging flow;
the image processing main flow includes:
step 2.1.1: the face detection device performs initialization processing; the initialization processing comprises the steps of emptying a face database, setting a face ID to 0, setting a face detection device to a non-sampling state, and setting an acquisition frame number to 0;
step 2.1.2: the face detection device receives a frame of face frame image; if the received frame image format is YUV format, converting into RGB format;
step 2.1.3: the face detection device recognizes a face from the received face frame image, if a new face is detected, the face closest to the middle of the image is taken as the face of the frame image, a face ID is set, and the step 2.1.4 is performed; if the face with the face ID is detected, detecting an old face, and turning to the step 2.1.5; if no face exists in the received face frame image, turning to step 2.1.11;
step 2.1.4: the face detection device performs face comparison; the face comparison is to compare the face frame image of the detected new face with the faces in the face database, and if the comparison is successful, the face is proved to have been subjected to physiological index analysis, and the step 2.1.11 is shifted; if the comparison is unsuccessful, the frame image is required to be subjected to physiological index analysis, the frame image is transmitted to a human face database for storage, and an aging timer of the human face frame image is set as an initial set value;
step 2.1.5: the face detection device acquires face information, wherein the face information comprises a face rectangular frame for acquiring the frame image, a face angle face image and an image time stamp;
step 2.1.6: the face detection device carries out sampling state identification; if the sampling state is the sampling state, turning to the step 2.1.7;
if not, go to step 2.1.8;
step 2.1.7: the face detection device sends the face rectangular frame and the face angle obtained in the step 2.1.5 to the self-adaptive adjusting device, and judges the sampling quality according to the feedback of the self-adaptive adjusting device; if the self-adaptive adjusting device returns to reach the sampling quality, setting the self-adaptive adjusting device to be in a sampling state, and turning to step 2.1.8; if the adaptive adjustment device returns to not reach the sampling quality, go to step 2.1.12;
step 2.1.8: the face detection device carries out face tracking detection on the face frame image to obtain face characteristic points and characteristic point coordinates; the feature point coordinates are coordinates of the face feature points in the frame image;
step 2.1.9: the face detection device sends the face ID, the face image, the image time stamp, the face rectangular frame, the face angle and the face feature point coordinates to the face acquisition device;
step 2.1.10: the face detection device judges whether the acquired frame number reaches a set value; if the acquisition frame number reaches the set value, turning to a step 2.1.11; if the number of acquired frames does not reach the set value, go to step 2.1.12;
step 2.1.11: the face detection device sends a preset point migration instruction to the preset point migration device, the preset point migration instruction is set to be in a non-sampling state, the preset time is waited for, and the step 2.1.2 is carried out;
step 2.1.12: the face detection device sends an adjusting instruction to the self-adaptive adjusting device, waits for the set time and goes to step 2.1.2.
2. The method according to claim 1, wherein the step of acquiring the frame image in the step 1 and performing the preliminary processing on the frame image comprises:
step 1.1: the infrared controller judges whether to open the infrared mode according to a control instruction input by an operator;
if the infrared module is turned on, the infrared lamp is turned on, and the infrared filter is turned on; if the infrared mode is not started, the infrared lamp is turned off, and the infrared filter is turned off;
step 1.2: the optical sensor receives natural light or infrared band light, converts the sensed optical signal into an electric signal and sends the electric signal to the image processing device;
step 1.3: the image processing device receives the electric signal, digitizes the electric signal to generate YUV or RGB frame images, and continuously outputs the frame images to the encoding device and the face detection device;
step 1.4: the encoding device receives the frame images, encodes the frame images according to an H.264/H.265 encoding protocol to form an encoded video stream, and sends the encoded video stream to the memory.
3. The adaptive non-contact physiological acquisition method according to claim 2, wherein the non-compressed video stream in step 1.3 is a frame image output by the image processing device in time sequence.
4. The adaptive non-contact physiological acquisition method according to claim 1, wherein the face database aging process is as follows: firstly, setting an aging initial value; secondly, according to the face comparison in the step 2.1.4, if each comparison is successful, the aging timer is reduced by 1; and if the aging timer of the face ID is zero, deleting the face ID and the corresponding face map.
5. The method according to claim 1, wherein the step of extracting the face blood spectrum information by the face acquisition device in step 2.2 comprises:
step 2.2.1: initializing a face acquisition device, wherein the face acquisition device comprises resetting face sampling ID to zero and acquiring frame number to zero;
step 2.2.2: the face acquisition device receives information of a face frame image, wherein the information comprises a face ID, a face image, an image time stamp, a face rectangular frame, a face angle and face feature point coordinates;
step 2.2.3: the face acquisition device judges whether the face ID is equal to the face sampling ID; if the face ID is equal to the face sampling ID, continuing to sample, and turning to step 2.2.5; otherwise, turning to step 2.2.4;
step 2.2.4: the face acquisition device clears the sampled data, resumes sampling, sets face sampling id=face ID, acquires frame number=0, and goes to step 2.2.2;
step 2.2.5: the face acquisition device divides face blocks according to coordinates of face feature points;
step 2.2.6: the face acquisition device extracts face blood spectrum information in a face frame image;
step 2.2.7: the face acquisition device judges whether the acquisition frame number meets a set value, if not, the step 2.2.2 is carried out;
step 2.2.8: the face acquisition device packages the face blood spectrum information with set time length and sends the face blood spectrum information to the blood spectrum physiological analysis device.
6. The adaptive non-contact physiological acquisition method according to claim 5, wherein in the step 2.3, the physiological index analysis of the blood spectrum physiological analysis device includes:
step 2.3.1: receiving a face blood spectrum information compression packet, and decompressing to obtain face blood spectrum information;
step 2.3.2: combining the human face blood spectrum information of the specific human face blocks according to the time sequence respectively; the combined human face blood spectrum information is human face blood spectrum information with set duration formed by splicing the contents of one or more human face blood spectrum information compression packets according to the analysis requirements of physiological indexes in time sequence; the specific face block is determined according to the detection target;
step 2.3.3: performing a physiological index analysis, the physiological index analysis comprising the steps of:
step 2.3.31: carrying out wavelet function filtering treatment on the face blood spectrum information with the set time length obtained in the step 2.3.2;
step 2.3.32: slicing the filtered human face blood spectrum information according to a set time length;
step 2.3.33: carrying out Fourier transform on the face blood spectrum information after each slice to obtain a target frequency spectrum corresponding to the slice;
step 2.3.34: averaging each target frequency spectrum, and sequencing according to a time sequence to obtain a target change curve;
step 2.3.4: obtaining a final physiological index analysis result;
step 2.3.5: and (3) sending the physiological index analysis result obtained in the step (2.3.4) to a memory.
7. The adaptive non-contact physiological acquisition method according to claim 6, wherein in the step 3, the adjusting pan-tilt comprises pan-tilt preset point migration and adaptive adjustment of pan-tilt posture; the step of migrating the preset point comprises the following steps:
step 3.1: the preset point migration device configures preset points of the holder, wherein at least one preset point is arranged, and the preset points comprise a holder angle, a holder focal length and a preset point number; setting the serial number of the largest preset point as m, wherein m is more than or equal to 1;
step 3.2: the preset point migration device sets the serial number of the initial polling preset point as 1, and sends parameter information of the initial polling preset point to the holder and the zoom control module;
step 3.3: the preset point migration device receives a preset point migration instruction sent by the face detection device to perform preset point migration, if the preset point number where the cloud deck is located when receiving the instruction is i, i+1, and if i > m, i resets 1; parameter information of a preset point i is sent to a holder and a zoom control module;
the parameter information of the preset points in the step 3.2 and the step 3.3 comprises a holder angle, a holder focal length and a preset point number;
the step of adaptively adjusting the posture of the cradle head comprises the following steps:
step 4.1: the self-adaptive adjusting device receives face parameters, including a face rectangular frame and face angle parameters sent by the face detection module;
step 4.2: the self-adaptive adjusting device judges whether the sampling requirement is met; if the width pixels of the rectangular frame of the human face and the angle of the human face are in the preset range, the sampling quality requirement is considered to be met, information reaching the sampling quality is sent to the human face detection device, and the step 4.1 is shifted;
step 4.3: the self-adaptive adjusting device compares the width pixels of the rectangular frame of the human face with a preset range to obtain a focal length adjusting parameter, and compares the angle of the human face with the preset range to obtain a holder angle adjusting parameter;
step 4.4: the self-adaptive adjusting device sends the posture adjusting parameters of the cradle head to the cradle head control device, and the step 4.1 is carried out; the pan-tilt posture adjustment parameters comprise pan-tilt angle adjustment parameters and focal length adjustment parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911355609.XA CN111241917B (en) | 2019-12-25 | 2019-12-25 | Self-adaptive non-contact physiological acquisition cradle head camera device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911355609.XA CN111241917B (en) | 2019-12-25 | 2019-12-25 | Self-adaptive non-contact physiological acquisition cradle head camera device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111241917A CN111241917A (en) | 2020-06-05 |
| CN111241917B true CN111241917B (en) | 2023-08-22 |
Family
ID=70874074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911355609.XA Active CN111241917B (en) | 2019-12-25 | 2019-12-25 | Self-adaptive non-contact physiological acquisition cradle head camera device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111241917B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7027621B1 (en) * | 2001-03-15 | 2006-04-11 | Mikos, Ltd. | Method and apparatus for operator condition monitoring and assessment |
| CN106355169A (en) * | 2016-11-11 | 2017-01-25 | 成都优势互动科技有限公司 | Infrared living body face image acquisition device, identification device and treatment method thereof |
| CN107483889A (en) * | 2017-08-24 | 2017-12-15 | 北京融通智慧科技有限公司 | The tunnel monitoring system of wisdom building site control platform |
| CN108898122A (en) * | 2018-07-03 | 2018-11-27 | 河南亚视软件技术有限公司 | A kind of Intelligent human-face recognition methods |
| CN109325933A (en) * | 2017-07-28 | 2019-02-12 | 阿里巴巴集团控股有限公司 | A kind of reproduction image-recognizing method and device |
| CN109391775A (en) * | 2018-10-22 | 2019-02-26 | 哈尔滨工业大学（深圳） | A kind of intelligent shooting tripod head control method and system based on recognition of face |
| CN109583426A (en) * | 2018-12-23 | 2019-04-05 | 广东腾晟信息科技有限公司 | A method of according to image identification face |
| CN109977828A (en) * | 2019-03-18 | 2019-07-05 | 北京中科虹霸科技有限公司 | A kind of method and apparatus that camera holder automatic pitching is adjusted |
| CN110008811A (en) * | 2019-01-21 | 2019-07-12 | 北京工业职业技术学院 | Face identification system and method |
| CN110321781A (en) * | 2019-05-06 | 2019-10-11 | 苏宁金融服务(上海)有限公司 | A kind of signal processing method and device for heed contacted measure |
| CN110365947A (en) * | 2019-08-07 | 2019-10-22 | 杭州泽铭睿股权投资有限公司 | A kind of baby's monitor camera can detecte baby's heartbeat breathing |
| CN110420011A (en) * | 2019-08-07 | 2019-11-08 | 杭州泽铭睿股权投资有限公司 | A kind of video camera with blood spectroscopic optics image imaging function |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190205655A1 (en) * | 2017-12-31 | 2019-07-04 | Google Llc | Infant monitoring system with video-based temperature baselining and elevated temperature detection |
-
2019
- 2019-12-25 CN CN201911355609.XA patent/CN111241917B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7027621B1 (en) * | 2001-03-15 | 2006-04-11 | Mikos, Ltd. | Method and apparatus for operator condition monitoring and assessment |
| CN106355169A (en) * | 2016-11-11 | 2017-01-25 | 成都优势互动科技有限公司 | Infrared living body face image acquisition device, identification device and treatment method thereof |
| CN109325933A (en) * | 2017-07-28 | 2019-02-12 | 阿里巴巴集团控股有限公司 | A kind of reproduction image-recognizing method and device |
| CN107483889A (en) * | 2017-08-24 | 2017-12-15 | 北京融通智慧科技有限公司 | The tunnel monitoring system of wisdom building site control platform |
| CN108898122A (en) * | 2018-07-03 | 2018-11-27 | 河南亚视软件技术有限公司 | A kind of Intelligent human-face recognition methods |
| CN109391775A (en) * | 2018-10-22 | 2019-02-26 | 哈尔滨工业大学（深圳） | A kind of intelligent shooting tripod head control method and system based on recognition of face |
| CN109583426A (en) * | 2018-12-23 | 2019-04-05 | 广东腾晟信息科技有限公司 | A method of according to image identification face |
| CN110008811A (en) * | 2019-01-21 | 2019-07-12 | 北京工业职业技术学院 | Face identification system and method |
| CN109977828A (en) * | 2019-03-18 | 2019-07-05 | 北京中科虹霸科技有限公司 | A kind of method and apparatus that camera holder automatic pitching is adjusted |
| CN110321781A (en) * | 2019-05-06 | 2019-10-11 | 苏宁金融服务(上海)有限公司 | A kind of signal processing method and device for heed contacted measure |
| CN110365947A (en) * | 2019-08-07 | 2019-10-22 | 杭州泽铭睿股权投资有限公司 | A kind of baby's monitor camera can detecte baby's heartbeat breathing |
| CN110420011A (en) * | 2019-08-07 | 2019-11-08 | 杭州泽铭睿股权投资有限公司 | A kind of video camera with blood spectroscopic optics image imaging function |
Non-Patent Citations (1)
| Title |
|---|
| 秦金亮 等.基于不同考试应激强度的血谱分析.《第二十二届全国心理学学术会议摘要集》.2019,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111241917A (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778695B (en) | Multi-person rapid heart rate detection method based on video | |
| CN109820499B (en) | High anti-interference heart rate detection method based on video, electronic equipment and storage medium | |
| US11998353B2 (en) | Camera having transdermal optical imaging function | |
| EP2994880A1 (en) | Device for obtaining a vital sign of a subject | |
| US20120212631A1 (en) | Methods and systems for providing a combination of media data and metadata | |
| CN111414785A (en) | Identification system and identification method | |
| KR101787828B1 (en) | Heartrate measuring system using skin color filter | |
| CN111297339B (en) | Method and device for generating signal of photoplethysmography | |
| CN111241917B (en) | Self-adaptive non-contact physiological acquisition cradle head camera device and method | |
| CN114557685B (en) | Non-contact type exercise robust heart rate measurement method and measurement device | |
| CN111166302A (en) | Device and method for monitoring physiological indexes in real time in non-contact manner | |
| CN112364329A (en) | Face authentication system and method combining heart rate detection | |
| CN112668539A (en) | Biological characteristic acquisition and identification system and method, terminal equipment and storage medium | |
| CN108090410B (en) | Non-contact type facial heart rate monitoring spinning and monitoring method | |
| CN115147769A (en) | Physiological parameter robustness detection method based on infrared video | |
| CN113598741B (en) | Atrial fibrillation evaluation model training method, atrial fibrillation evaluation method and atrial fibrillation evaluation device | |
| CN113693573B (en) | Video-based non-contact multi-physiological-parameter monitoring system and method | |
| CN110960194B (en) | Ear phase acquisition device and acquisition method | |
| CN116989892A (en) | Portable multispectral video image recording and analyzing processing system and method | |
| CN113920387A (en) | Construction method and detection method of short-time rPPG signal detection model | |
| CN115205270B (en) | Non-contact blood oxygen saturation detection method and system based on image processing | |
| JP2006268639A (en) | Method and device for recognizing motion of object, input device by recognition of motion, and storage medium recording program for recognizing motion of object | |
| JP6727894B2 (en) | Processing device, processing method, and program | |
| CN111195133A (en) | Device and method capable of detecting fatigue in real time | |
| CN111195119A (en) | Glasses device and method for detecting physiology in real time |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |