CN106778695B - Multi-person rapid heart rate detection method based on video - Google Patents
Multi-person rapid heart rate detection method based on video Download PDFInfo
- Publication number
- CN106778695B CN106778695B CN201710039731.0A CN201710039731A CN106778695B CN 106778695 B CN106778695 B CN 106778695B CN 201710039731 A CN201710039731 A CN 201710039731A CN 106778695 B CN106778695 B CN 106778695B
- Authority
- CN
- China
- Prior art keywords
- heart rate
- tracking
- face
- detection
- video
- 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
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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/164—Detection; Localisation; Normalisation using holistic features
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- 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
- G06V40/162—Detection; Localisation; Normalisation using pixel segmentation or colour matching
Abstract
The invention relates to the technical field of human health monitoring, and discloses a video-based multi-person rapid heart rate detection method. The method is characterized in that a plurality of face regions in a video input by a camera or an existing video are detected and tracked, the cheek regions are segmented, a time domain data sequence of the cheek regions is extracted and preprocessed, and then the time domain data sequence is converted into a frequency domain to extract the heart rate. Compared with the prior art, the method is based on an improved face detection algorithm and an improved tracking algorithm and accelerated by using a multithreading method, can realize the rapid heart rate detection of multiple persons, shortens the heart rate measurement time and improves the detection efficiency of physiological signals.
Description
Technical Field
The invention relates to the technical field of human health monitoring, in particular to a method for realizing rapid heart rate measurement of multiple persons.
Background
Heart rate is the number of beats per minute of the heart, which varies with age, sex, and other physiological conditions. The heart rate of the newborn is fast and can reach over 130 times/minute. There were significant individual differences in heart rate among normal adults at rest, averaging around 75 beats/minute (between 60 and 100 beats/minute). The same person has a slower heart rate when resting or sleeping and a faster heart rate when exercising or having mood swings. Therefore, the heart rate can fully reflect the physical condition of a person, is an important physiological parameter for self-health monitoring, and is also an important basis for doctors to diagnose diseases of patients.
Heart rate can be divided into contact measurement and non-contact measurement according to different measurement modes. One of the representatives of the contact measurement is a gold standard electrocardiogram (EEG) for measuring the heart rate, and in addition, a contact measurement method for wrapping a chest belt, a cuff or an electrode at the positions of a wrist, a fingertip, an earlobe and the like is also adopted.
However, the existing non-contact measurement method based on IPPG has the problems of sensitivity to light changes, low measurement speed, susceptibility to motion artifact of measurement results, low heart rate measurement result precision, most of heart rate measurements based on a single person, and the like.
Disclosure of Invention
1. The present invention is directed to solving at least one of the above problems.
2. Therefore, the invention aims to provide a video-based non-contact multi-person fast heart rate detection method, which can automatically detect and fast track the faces in videos which are acquired by a camera and contain a plurality of faces or videos containing a plurality of faces, and can obtain the heart rate of each person to be detected after analyzing and processing the acquired face regions.
3. The method comprises the following steps: the system comprises a video acquisition part, a face detection part, a face tracking part, an ROI (region of interest) color division frame extraction part, a time domain signal acquisition part, a time domain signal processing part, a heart rate calculation part, a face number and a heart rate display part;
4. the video acquisition part is used for selecting the working mode: firstly, a camera is started, and the camera is fixed after the position where the imaging equipment can clearly and completely image the face area is determined in the indoor environment of daily illumination; secondly, selecting a local existing video containing a face area;
5. the face detection part is used for detecting face areas from the video, returning the serial numbers of the face areas to the face serial number and heart rate display part and initializing the face tracking part;
6. and the human face tracking part is used for quickly tracking each human face area detected by the human face detection part.
7. The ROI tone framing extraction part is used for extracting the value of Hue (tone) components after RGB is converted into HSV in the color space of an ROI area of each frame of image in the video;
8. the time domain signal acquisition part is used for dividing the face in each frame of ROI area image into a cheek area, and measuring a gray average value of pixels and a time domain signal value X (t) of an H component of the cheek area for Hue (Hue) components in three color components of the area HSV;
9. the time domain signal processing part is used for obtaining the time domain signalThe signal value X (t) is subjected to noise suppression and signal detrending to obtain a processed time domain signal value
10. The heart rate calculating part is used for calculating the time domain signal value
Carrying out spectrum analysis and generating a spectrogram, and extracting peak frequency in a specified frequency band from the spectrogram to carry out heart rate calculation;
11. and the human face number and heart rate display part is used for displaying the number of each human face area marked by the human face detection part and the heart rate value corresponding to the human face area number obtained by the heart rate calculation part in the video.
Preferably, the video acquisition portion is implemented by a PC controlling the imaging device.
Preferably, the face detection part is realized by a classifier method of loading a nose, a mouth and a front face simultaneously.
Preferably, the face tracking part is realized by an improved method suitable for rapid compressed tracking of multiple persons.
Preferably, the ROI color framing extraction part is implemented by converting the color space from RGB into HSV and extracting the H component.
Preferably, the time domain signal acquisition part is realized by a method of extracting a gray mean value of the ROI area of the cheek.
Preferably, the time domain signal processing part is realized by mean filtering, wavelet denoising and moving average methods.
Preferably, the heart rate calculating part is implemented by a fast fourier transform method.
Preferably, the face number and heart rate display part is realized by a multithreading method.
Drawings
1. FIG. 1 is a step chart of the heart rate measuring method of the invention
2. FIG. 2 is a block diagram of the parts included in the present invention
3. FIG. 3 is a flow chart of a heart rate measuring method and a multithreading schematic diagram of the invention
4. FIG. 4 is a partial flow chart of the heart rate measurement method of the invention for face detection
5. FIG. 5 is a flow chart of a part of face tracking of the heart rate measurement method of the invention
6. FIG. 6 is a diagram showing the relationship between the positions of the target detection frame and the adjacent detection frame in the human face tracking part of the heart rate measurement method of the present invention
Detailed Description
1. For clearly illustrating the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
2. Fig. 1 is a diagram showing steps of a video-based multi-person fast heart rate measurement method according to the present invention.
3. Fig. 2 is a block diagram of the parts included in the video-based multi-person fast heart rate measurement method of the present invention.
4. Firstly, selecting working modes, the invention provides two working modes: firstly, directly carry out real-time heart rate detection to the testee through the camera, secondly the testee in local video carries out real-time heart rate and detects. In both working modes, the video needs to select an environment with proper illumination, and the imaging equipment can clearly and completely image the face area. The following steps are taken as an example of the first working method.
5. And secondly, starting the imaging equipment, carrying out video acquisition on the face of the object to be detected, decomposing the video input by the camera into an image sequence, converting the RGB image into a gray-scale image, and allowing the face to move and deflect within the range of the imaging scene in the acquisition process.
6. And thirdly, judging the current face detection state, starting a face detection part if no face is detected, returning the face number to a face number and heart rate display part until the face is detected, initializing a tracking part by using a detection result, and marking the face detection state as the detected face, wherein the working flow of the part is shown in figure 4.
7. Fourthly, a face tracking part is started, all faces detected currently are tracked respectively, a tracking module returns a tracking state, if the tracking is successful, the next step is continued, otherwise, the third step is returned, and the tracking process is shown in the figure 5; the search radius in the trace is updated according to fig. 6: the 8 frames with the numbers of 1-8 respectively represent the frames at 8 adjacent positions possibly existing around the current target frame, and the area of each frame represents the size of the face region tracked at different positions. As shown by the coordinate axes in the figure, the parameters of the target frame are assumed to be (x) respectively0,y0,w0,h0) The four parameters sequentially represent the abscissa, the ordinate, the width and the height of the top left corner of the rectangle corresponding to the target frame; similarly, the parameters of 8 tracking boxes can be assumed to be (x)i,yi,wi,hi) Wherein i is 1,2,3,4,5,6,7 and 8 in sequence; taking the calculation of the distance between the target frame and the upper right tracking frame as an example, the other cases are similar, and the condition is satisfied:
the minimum distance was found to be:
the search radius is then:
rsearch＝lmin*0.8
8. fifthly, performing mean filtering on each tracked face Region (ROI), segmenting a cheek region, extracting a gray mean value of an H component of the cheek region, and performing wavelet denoising, sliding filtering and signal de-trend on the obtained time domain signal X (t) to obtain a final time domain signal
9. And sixthly, performing fast Fourier transform on the time domain signal obtained in the previous step, and selecting the frequency with the maximum corresponding frequency spectrum value between 0.5Hz and 3Hz, wherein the frequency value corresponds to a numerical value per minute, namely the heart rate. The selected 0.5 Hz-3 Hz represents the condition that the heart rate is 30-180 beats/minute, the range of most heart rates is included, and the interference of other physiological signals is eliminated, and the implementation process of the step is shown as a thread 2 in fig. 3.
10. And seventhly, starting a thread 3, and displaying the heart rate data corresponding to different face numbers in a video in real time.
11. Has the advantages that: compared with the prior art, the invention provides a rapid multi-person heart rate measuring method based on image processing, the multi-person heart rate detection is accelerated by a multithreading method and an improved tracking algorithm, the false detection rate is reduced by the improved detection algorithm and the improved tracking algorithm, and the detection efficiency is improved.
Claims (10)
1. A video-based multi-person rapid heart rate detection method comprises the following steps:
s100, selecting a working mode, calling a program to automatically open a camera if the working mode is a direct working mode, calling the program to automatically read a video if the working mode is an indirect working mode, and then calling a face detection module to detect a face area in the video;
s200, transmitting the detected position information of the face area to a face tracking module, starting face tracking, realizing rapid tracking of the face of multiple persons, and simultaneously obtaining the gray average value of the tracked face area;
s300, processing the acquired image information and converting the image information into a time domain signal, then filtering, denoising and detrending the time domain signal to obtain preprocessed data, starting a thread 2, converting the preprocessed data into a frequency domain to obtain frequency domain data, and calculating a heart rate according to the frequency domain data;
s400, starting a thread 3, and displaying the number of each detection object and the heart rate value of each detection object in real time in a video;
the face Tracking module utilizes an improved compression Tracking (compression Tracking) algorithm, and inhibits the drift of a Tracking frame in the Tracking process by two methods, wherein the two methods are respectively as follows:
1) respectively calculating the distance under each position relation according to the 8 position relations between the current detection frame and the adjacent detection frame, and selecting the minimum distance l from the distancesminLet search radius rsearch＝lmin0.8, aliasing of feature extraction among tracking targets caused by overlarge search radius is avoided;
2) by utilizing the thought of ensemble learning, taking 45 positive samples with 4 pixel points as radiuses in a target area, and randomly selecting 50 negative samples in a ring with 8 inner radiuses and 12 outer radiuses outside the target area; taking 4 pixel points as the inner diameter and 6 pixel points as the outer diameter, taking 60 positive samples, and randomly selecting 60 negative samples in a circular ring with 12 as the inner radius and 16 as the outer radius outside a target area; and respectively sending the two groups of positive and negative samples into a classifier, and taking the average value of the maximum positions respectively returned by the classifier under the two conditions as the position of the tracking target.
2. The method for multi-person fast heart rate detection according to claim 1, wherein: the step S200 specifically includes the following steps:
s201, setting a new search radius according to the distance and the position relation between the tracking frame and the nearest tracking frame in the previous frame image;
s202, extracting features from samples collected near the tracking position according to the new search radius and mapping the features to a low-dimensional space to obtain a region to be classified;
s203, classifying the region pairs to be classified by using the two Bayesian classifiers obtained from the previous frame respectively, and selecting a rectangular frame which is most likely to be a target as a current tracking result;
if the current tracking object is judged to have moved to the edge in the whole video picture, the mark tracking is unsuccessful, the face detection module is restarted, and the current heart rate detection result is cleared, otherwise, the step S204 is executed;
s204, taking the target area of the current frame as the center, and taking two groups of positive and negative samples, wherein the two groups of positive and negative samples are respectively as follows:
1) taking 4 pixel points as radiuses in a target area, taking 45 positive samples, and randomly selecting 50 negative samples in a circular ring with 8 as an inner radius and 12 as an outer radius outside the target area;
2) taking 60 positive samples with 4 pixel points as inner diameter and 6 pixel points as outer diameter in a target area, and randomly selecting 60 negative samples in a circular ring with 12 as inner radius and 16 as outer radius outside the target area;
s205, calculating an integral image and a Haar feature extraction template of the original image;
s206, extracting the characteristics of the positive and negative samples according to the integral image and the obtained Haar characteristic extraction template, updating the Bayes classifier, obtaining a new classifier, and tracking the target in the current frame image by using the classifier.
3. The method for multi-person fast heart rate detection according to claim 1, wherein: the heart rate measurement is realized by using imaging equipment commonly used in daily life of a network camera or a mobile phone camera.
4. The method for multi-person fast heart rate detection according to claim 1, wherein: two working modes are selectable, and the human face area of the detected person can be directly detected through the camera, and the heart rate detection can also be carried out on the human face area in the local video.
5. The method for multi-person fast heart rate detection according to claim 1, wherein: the face detection module reduces false detection rate by loading three classifiers, namely a face classifier, a nose classifier and a mouth classifier, and reduces omission rate by performing histogram equalization on an image to be detected.
6. The method for multi-person fast heart rate detection according to claim 1, wherein: and after the face tracking module detects that the detected object moves out of the detection visual field, clearing the heart rate data of the object, quitting the face tracking module and restarting the face detection module.
7. The method for multi-person fast heart rate detection according to claim 1, wherein: the cheek area is divided from the face area, the heart rate signal is extracted, the influence of blinking of eyes and shielding of hair of the detected forehead on the ROI gray value is avoided, and the heart rate measurement precision is improved.
8. The method for multi-person fast heart rate detection according to claim 1, wherein: the heart rate detection is accelerated by utilizing multiple threads, the heart rate calculation part, the human face number and the heart rate display part respectively occupy independent threads, the work of other modules is not influenced, the operation speed is further accelerated, and the rapid detection of the heart rates of multiple people is realized.
9. The method for multi-person fast heart rate detection according to claim 1, wherein: the number and heart rate display part of the detection object marks the corresponding number on each face tracking frame in turn according to the sequence of the face detected by the face detection module, and displays the heart rate value corresponding to each tested person in turn in the video according to the sequence of the numbers from small to large.
10. A multi-person fast heart rate detection method based on video is mainly applied to a daily non-contact heart rate measurement system, and a network camera and a mobile phone camera imaging device are used for shooting video of a region containing a face to realize fast and automatic multi-person heart rate measurement; the video acquisition part is used for acquiring a section of color video image containing a plurality of face areas by means of a camera or selecting a local video file; the human face tracking part optimizes a compression tracking algorithm based on the idea that the human face between two frames of pictures can not generate large-amplitude position change; the ROI color sub-frame extracting part is used for extracting the value of an H (hue) component after converting RGB into HSV in the color space of each frame of picture; the time domain signal acquisition part is used for dividing a cheek region from each frame ROI region, solving a gray average value of an H component of the cheek region as a characteristic value of the frame image and generating a time domain signal X (t); the time domain signal processing part is used for carrying out noise suppression on the obtained time domain signal X (t), obtaining a processed time domain signal, and the heart rate calculating part is used for carrying out spectrum analysis on the time domain signal value, generating a spectrogram and extracting peak frequency in a specified frequency band from the spectrogram to carry out heart rate calculation;
the face Tracking part utilizes the improved compression Tracking (compression Tracking) algorithm of the invention, and inhibits the drift of a Tracking frame in the Tracking process by two methods, wherein the two methods are respectively as follows:
1) respectively calculating the distance under each position relation according to the 8 position relations between the current detection frame and the adjacent detection frame, and selecting the minimum distance l from the distancesminLet search radius rsearch＝lmin0.8, aliasing of feature extraction among tracking targets caused by overlarge search radius is avoided;
2) by utilizing the thought of ensemble learning, taking 45 positive samples with 4 pixel points as radiuses in a target area, and randomly selecting 50 negative samples in a ring with 8 inner radiuses and 12 outer radiuses outside the target area; taking 4 pixel points as the inner diameter and 6 pixel points as the outer diameter, taking 60 positive samples, and randomly selecting 60 negative samples in a circular ring with 12 as the inner radius and 16 as the outer radius outside a target area; and respectively sending the two groups of positive and negative samples into a classifier, and taking the average value of the maximum positions respectively returned by the classifier under the two conditions as the position of the tracking target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710039731.0A CN106778695B (en) | 2017-01-19 | 2017-01-19 | Multi-person rapid heart rate detection method based on video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710039731.0A CN106778695B (en) | 2017-01-19 | 2017-01-19 | Multi-person rapid heart rate detection method based on video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106778695A CN106778695A (en) | 2017-05-31 |
| CN106778695B true CN106778695B (en) | 2022-01-18 |
Family
ID=58944534
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710039731.0A Active CN106778695B (en) | 2017-01-19 | 2017-01-19 | Multi-person rapid heart rate detection method based on video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106778695B (en) |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330945A (en) * | 2017-07-05 | 2017-11-07 | 合肥工业大学 | A kind of examing heartbeat fastly method based on video |
| CN107334469A (en) * | 2017-07-24 | 2017-11-10 | 北京理工大学 | Non-contact more people's method for measuring heart rate and device based on SVMs |
| CN107506716A (en) * | 2017-08-17 | 2017-12-22 | 华东师范大学 | A kind of contactless real-time method for measuring heart rate based on video image |
| CN109871115B (en) * | 2017-12-04 | 2021-09-17 | 腾讯科技（深圳）有限公司 | Control method, device and computer readable storage medium in multimedia interaction |
| GB2572961A (en) * | 2018-04-16 | 2019-10-23 | Clinicco Ltd | System for vital sign detection from a video stream |
| TWI658815B (en) * | 2018-04-25 | 2019-05-11 | 國立交通大學 | Non-contact heartbeat rate measurement system, non-contact heartbeat rate measurement method and non-contact heartbeat rate measurement apparatus |
| CN109009052A (en) * | 2018-07-02 | 2018-12-18 | 南京工程学院 | The embedded heart rate measurement system and its measurement method of view-based access control model |
| CN109259748B (en) * | 2018-08-17 | 2020-04-07 | 西安电子科技大学 | System and method for extracting heart rate signal by processing face video through mobile phone |
| CN109480808A (en) * | 2018-09-27 | 2019-03-19 | 深圳市君利信达科技有限公司 | A kind of heart rate detection method based on PPG, system, equipment and storage medium |
| CN111281367A (en) * | 2018-12-10 | 2020-06-16 | 绍兴图聚光电科技有限公司 | Anti-interference non-contact heart rate detection method based on face video |
| CN110276271A (en) * | 2019-05-30 | 2019-09-24 | 福建工程学院 | Merge the non-contact heart rate estimation technique of IPPG and depth information anti-noise jamming |
| CN110866498B (en) * | 2019-11-15 | 2021-07-13 | 北京华宇信息技术有限公司 | Heart rate monitoring method |
| CN111540169A (en) * | 2020-04-24 | 2020-08-14 | 重庆城市管理职业学院 | Bus danger alarm method and system based on intelligent behavior monitoring |
| CN112890792A (en) * | 2020-11-25 | 2021-06-04 | 合肥工业大学 | Cloud computing cardiovascular health monitoring system and method based on network camera |
| CN112797840B (en) * | 2021-01-28 | 2023-03-10 | 杭州屹道科技有限公司 | Firearm handing-over device and working method thereof |
| CN113876311B (en) * | 2021-09-02 | 2023-09-15 | 天津大学 | Non-contact type multi-player heart rate efficient extraction device capable of adaptively selecting |
| CN113627396B (en) * | 2021-09-22 | 2023-09-05 | 浙江大学 | Rope skipping counting method based on health monitoring |
| CN116999044B (en) * | 2023-09-07 | 2024-04-16 | 南京云思创智信息科技有限公司 | Real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104138254A (en) * | 2013-05-10 | 2014-11-12 | 天津点康科技有限公司 | Non-contact type automatic heart rate measurement system and measurement method |
| CN104173051A (en) * | 2013-05-28 | 2014-12-03 | 天津点康科技有限公司 | Automatic noncontact respiration assessing system and assessing method |
| CN104337509A (en) * | 2013-07-26 | 2015-02-11 | 塔塔咨询服务有限公司 | Measurement of physiological parameter |
| CN104866805A (en) * | 2014-02-20 | 2015-08-26 | 腾讯科技（深圳）有限公司 | Real-time face tracking method and device |
| CN105930808A (en) * | 2016-04-26 | 2016-09-07 | 南京信息工程大学 | Moving object tracking method based on vector boosting template updating |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9854973B2 (en) * | 2014-10-25 | 2018-01-02 | ARC Devices, Ltd | Hand-held medical-data capture-device interoperation with electronic medical record systems |
-
2017
- 2017-01-19 CN CN201710039731.0A patent/CN106778695B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104138254A (en) * | 2013-05-10 | 2014-11-12 | 天津点康科技有限公司 | Non-contact type automatic heart rate measurement system and measurement method |
| CN104173051A (en) * | 2013-05-28 | 2014-12-03 | 天津点康科技有限公司 | Automatic noncontact respiration assessing system and assessing method |
| CN104337509A (en) * | 2013-07-26 | 2015-02-11 | 塔塔咨询服务有限公司 | Measurement of physiological parameter |
| CN104866805A (en) * | 2014-02-20 | 2015-08-26 | 腾讯科技（深圳）有限公司 | Real-time face tracking method and device |
| CN105930808A (en) * | 2016-04-26 | 2016-09-07 | 南京信息工程大学 | Moving object tracking method based on vector boosting template updating |
Non-Patent Citations (1)
| Title |
|---|
| "Fast Compressive Tracking";Kaihua Zhang et.al;《IEEE》;20141031;期刊第3-4节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106778695A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778695B (en) | Multi-person rapid heart rate detection method based on video | |
| Hsu et al. | Deep learning with time-frequency representation for pulse estimation from facial videos | |
| JP6521845B2 (en) | Device and method for measuring periodic fluctuation linked to heart beat | |
| Tang et al. | Non-contact heart rate monitoring by combining convolutional neural network skin detection and remote photoplethysmography via a low-cost camera | |
| WO2013165550A1 (en) | Methods and systems for measuring dynamic changes in the physiological parameters of a subject | |
| KR101738278B1 (en) | Emotion recognition method based on image | |
| KR102215557B1 (en) | Heart rate estimation based on facial color variance and micro-movement | |
| JP6098304B2 (en) | Pulse wave detection device, pulse wave detection method, and pulse wave detection program | |
| CN109820499A (en) | The anti-interference heart rate detection method of height, electronic equipment and storage medium based on video | |
| CN110866498B (en) | Heart rate monitoring method | |
| Huang et al. | A motion-robust contactless photoplethysmography using chrominance and adaptive filtering | |
| CN111938622B (en) | Heart rate detection method, device and system and readable storage medium | |
| CN111839492B (en) | Heart rate non-contact type measuring method based on face video sequence | |
| Yin et al. | Heart rate estimation based on face video under unstable illumination | |
| Hernandez-Ortega et al. | A comparative evaluation of heart rate estimation methods using face videos | |
| CN111275018A (en) | Non-contact heart rate signal extraction method based on annular region of interest weighting | |
| Gupta et al. | Accurate heart-rate estimation from face videos using quality-based fusion | |
| KR102150635B1 (en) | Method for measuring heart rate based on Vision System | |
| CN108937905B (en) | Non-contact heart rate detection method based on signal fitting | |
| Panigrahi et al. | Non-contact HR extraction from different color spaces using RGB camera | |
| Tao et al. | Multi-feature fusion prediction of fatigue driving based on improved optical flow algorithm | |
| US20200311388A1 (en) | Human body physiological parameter monitoring method based on face recognition for workstation | |
| Rafiqi et al. | Work-in-progress, PupilWare-M: Cognitive load estimation using unmodified smartphone cameras | |
| CN113693573B (en) | Video-based non-contact multi-physiological-parameter monitoring system and method | |
| Kopeliovich et al. | Color signal processing methods for webcam-based heart rate evaluation |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170531 |
|
| RA01 | Restoration of patent right | ||
| RA01 | Restoration of patent right |
Former decision: The withdrawal of the patent application shall be deemed to be withdrawn Former decision publication date: 20200717 |
|
| RA01 | Restoration of patent right | ||
| RA01 | Restoration of patent right |
Former decision: After the publication of the patent application, it shall be deemed to have been withdrawn Former decision publication date: 20200717 |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |