CN113576449A - Infrared dynamic high-resolution non-contact respiration measurement system - Google Patents
Infrared dynamic high-resolution non-contact respiration measurement system Download PDFInfo
- Publication number
- CN113576449A CN113576449A CN202010370702.4A CN202010370702A CN113576449A CN 113576449 A CN113576449 A CN 113576449A CN 202010370702 A CN202010370702 A CN 202010370702A CN 113576449 A CN113576449 A CN 113576449A
- Authority
- CN
- China
- Prior art keywords
- infrared
- resolution
- structured light
- video
- projection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000029058 respiratory gaseous exchange Effects 0.000 title claims abstract description 20
- 238000005259 measurement Methods 0.000 title claims description 22
- 210000004072 lung Anatomy 0.000 claims description 29
- 210000001015 abdomen Anatomy 0.000 claims description 21
- 241000282414 Homo sapiens Species 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 6
- 101100269850 Caenorhabditis elegans mask-1 gene Proteins 0.000 claims description 5
- 230000004199 lung function Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 210000000988 bone and bone Anatomy 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000001427 coherent effect Effects 0.000 claims description 2
- 230000001678 irradiating effect Effects 0.000 claims description 2
- 230000001788 irregular Effects 0.000 claims description 2
- 238000002360 preparation method Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 210000000038 chest Anatomy 0.000 description 14
- 230000000241 respiratory effect Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 3
- 239000007789 gas Substances 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000003187 abdominal effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000001624 hip Anatomy 0.000 description 2
- 210000004197 pelvis Anatomy 0.000 description 2
- 238000009423 ventilation Methods 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000009531 respiratory rate measurement Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/091—Measuring volume of inspired or expired gases, e.g. to determine lung capacity
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
- A61B5/1128—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique using image analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/113—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb occurring during breathing
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/113—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb occurring during breathing
- A61B5/1135—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb occurring during breathing by monitoring thoracic expansion
Abstract
The invention discloses an infrared dynamic high-resolution non-contact type respiration measuring system, which aims to solve the problems that the resolution and the frame rate are difficult to take into account and the wearing is complicated when the existing non-contact type three-dimensional measuring system is applied to respiration monitoring.
Description
Technical Field
The invention relates to a dynamic three-dimensional measurement system, in particular to an infrared high-resolution dynamic three-dimensional measurement system.
Background
Respiration is an important way for human beings to obtain oxygen and discharge carbon dioxide so as to keep the vitality of the body. By monitoring the respiratory signal, the state of the lung function of the person can be assessed. However, the measurement of the respiration signal currently adopts a contact type measurement method: i.e. the sensor is connected to the body to acquire the breathing signal. Although relatively accurate measurement parameters can be obtained, the equipment is complex, certain inconvenience is brought to clinical treatment, and besides, long-time wearing of the detection device brings obstruction to activities of patients and detection in families, and even emotional changes and physical discomfort of the patients can be caused. In addition, the existing contact measurement system can only obtain the change of the whole lung volume, and can not distinguish the change of the left lung and the right lung independently, which is very important for the rehabilitation evaluation of some hemiplegic patients. There is therefore a need for a non-contact respiratory measurement system that can distinguish between changes in left and right lung volumes.
In recent years, with the progress of sensor technology and the maturity of various image processing algorithms, the research of contactless respiration signal measurement is receiving more and more attention. In the case of lung ventilation, human respiratory motion can be viewed approximately as an activity that involves two degrees of freedom, the thoracic (rib cage, RC) and abdominal (abdomen, AB). The change in lung volume during breathing is equal to the sum of the two volume changes. According to RC, AB and two freedom degree physical system model, measuring the gas volume delta V of the entering and leaving lung and the change delta V of the gas volume of the chest cavityRCChange delta V of gas volume with abdominal cavityABThere is the following relationship between: Δ V ≈ Δ VRC+ΔVAB. The condition of respiratory ventilation can thus be measured indirectly by measuring the movements of the thoracoabdominal wall.
The structured light three-dimensional measurement system can obtain a high-resolution three-dimensional shape measurement result, and the development is rapid in recent years. However, the precision and the frame rate of the depth image measured by the existing three-dimensional measurement system are difficult to obtain, the acquisition frame rate of the high-precision structured light measurement system is very low, and the system is only suitable for static measurement, while the resolution of the high-frame-rate structured light measurement system is very low, and the system can bring large errors when being directly applied to dynamic respiration measurement.
Meanwhile, the boundary of the measured object in the depth map of the dynamic three-dimensional measurement is difficult to define, and in order to make the volume for calculating the change of the chest and abdomen wall have a certain standard, a fixed boundary must be determined, and only the change of the volume in the boundary must be calculated. The traditional method is to paste a large number of special marking points on the clothes and select the region of interest according to the marking points, but the complicated preparation work in advance also brings much inconvenience to the measurement. Therefore, a dynamic three-dimensional measurement system which is simple, efficient and high in precision is urgently needed.
Disclosure of Invention
The invention discloses an infrared dynamic high-resolution non-contact type respiration measuring system, which aims to solve the problems that the resolution and the frame rate are difficult to be considered and the wearing is complicated when the existing non-contact type three-dimensional measuring system is applied to respiration monitoring, the high-precision three-dimensional reconstruction is carried out on the chest and abdomen part in a non-contact way by utilizing an infrared structure light and a multi-frame super-resolution algorithm under the condition of ensuring the high frame rate, the boundaries of the left chest and abdomen wall and the right chest and abdomen wall of a human body are automatically identified by utilizing a key point identification algorithm, the respiration conditions of the left lung, the right lung and the whole lung can be respectively analyzed simultaneously, and the whole measuring process is simple and efficient.
The system consists of an infrared structured light projection module M1, a data acquisition module M2, a video super resolution module M3, a three-dimensional reconstruction module M4, a key point automatic identification module M5, a vital capacity calculation module M6, a calibration module M7 and a calibration parameter memory Q; the specific technical scheme of the system is as follows:
1. the infrared structured light projection module M1 is composed of a plurality of infrared projection devices D11-D1NAnd a switching control submodule M11The device comprises an infrared projection device, a light source and a light source, wherein each infrared projection device projects a structural light pattern P1 generated in advance to a human body to be detected through an infrared light source, and the projection direction is the abdominal-back direction of the human body to be detected H; during projection, the control submodule M1 is switched by using an alternative projection mode1Responsible for switching the projection infrared projection equipment D1 in sequence and rapidly1To D1NAnd performing projection, wherein the pattern projected by each infrared projection device is the same, different infrared projection devices have a placement offset of not less than 5 centimeters, and preferably, the infrared projection devices N are 3.
2. The data acquisition module M2 is responsible for acquiring the whole breathing process of a person to be detected H and is provided with an infrared camera D21And a color camera D22Composition is carried out; wherein, D21The light video S0 is responsible for shooting an original structure light video of the chest and the abdomen of the H; d22The color RGB video S1 responsible for shooting H chest and abdomen; preferably, the infrared camera D21The collection frequency of the camera is 90Hz, and the color camera D22The acquisition frequency of (2) is 30 Hz.
3. The video super-resolution module M3 is responsible for dividing each N frames in the original structured light pattern video S0 into a group of images by using a multi-frame super-resolution algorithm, where N is the number of infrared projection devices, and performing interpolation combination on N low-resolution images in the group to generate a frame of structured light image with high resolution, and repeating the steps until the original video S0 is completely processed, so as to obtain a section of structured light video S0 with high resolution.
4. The three-dimensional reconstruction module M4 is responsible for performing local cross-correlation operation on each frame of image in the high-resolution structured light video S0 and the reference image group C1 recorded with depth information, which is obtained by actual calibration, in sequence to obtain local depth information, and finally generating a three-dimensional reconstruction video S2. Preferably, the accuracy of the reference image set calibration is 1 cm. The matching window size for the local cross-correlation operation is 7X7 pixels.
5. The key point automatic identification module M5 is responsible for extracting key points of the thoracoabdominal bone of the tested human body H through a key point identification algorithm and connecting the key points to obtain the interested areas of the irregular polygons of the left and right lungs. Preferably, the specific human skeletal key points are the neck, the left and right shoulders, the waist and the left and right pelvis, and preferably, the key point identification algorithm is OpenPose.
6. The lung function calculation module M6 is responsible for calculating the volume changes in the regions of interest of the left and right thoraco-abdominal regions and the full thoraco-abdominal region respectively according to the high resolution depth information video S2 to obtain the left and right lung volume change curves and the full lung volume change curves respectively. And the difference of the largest change in the curve of the change in the total lung volume is recorded as the lung capacity detected this time.
The invention has the following advantages: the invention adopts the optical three-dimensional reconstruction technology, realizes the noninvasive and non-contact respiratory signal measurement by three-dimensional reconstruction of the motion of the chest and abdomen, and effectively improves the measurement experience of the measured person. The invention ensures the precision and the proper frame rate in the dynamic three-dimensional reconstruction process through the multi-frame super-resolution algorithm. The invention can simultaneously and conveniently and rapidly track and analyze the three-dimensional changes of the left and right chest and abdomen areas of the tested person through the key point automatic detection algorithm. The measured person can wear the device freely in the measuring process, so that the patient can carry out real-time respiratory monitoring in both a hospital and a home.
Drawings
FIG. 1 is a flow chart of a three-dimensional reconstruction system according to the present invention
FIG. 2 is a schematic diagram of an alternate projection and acquisition process
FIG. 3 is a schematic diagram of key point identification
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited to these examples. As shown in fig. 1, the infrared dynamic high-resolution non-contact respiration measurement system is composed of an infrared structured light projection module M1, a data acquisition module M2, and a high-performance computer D3. The method comprises the following steps:
1. n infrared projection devices D1 which are parallel to the same optical horizontal plane in the structured light projection module M11To D1NProjecting the structured light pattern P1 to a target object, wherein the projection direction is the abdominal-back direction of the human body H to be detected, and preferably, N is 3; the structured light pattern P1 is a two-dimensional coding pattern generated in advance, preferably, the pattern is a randomly distributed low-density speckle dot pattern generated by an infrared light coherent light source with the wavelength of 920-1200 nm; during projection, the control submodule M1 is switched by using an alternative projection mode1Responsible for switching the projection infrared projection equipment D1 in sequence and rapidly1To D1NAnd performing projection, wherein the pattern projected by each infrared projection device is the same, and different infrared projection devices have a placement offset of not less than x centimeters, and preferably, the placement offset x is 5 centimeters.
2. The data acquisition module M2 consists of an infrared camera D21And a color camera D22And (4) forming. As shown in fig. 2, the specific collection steps are as follows:
1) the back of the subject H is tightly attached to the fixed support, and the hands naturally droop;
2) subject H started slowly breathing deeply;
3) making the infrared projecting device D11Projecting the structured light, adjusting the rest of the infrared projection equipment to be in an off state, acquiring low-resolution structured light pattern information of a first frame through an infrared camera D21, and adjusting the low-resolution structured light pattern information of a color camera D22Begin to acquire first frame color RGB image information
4)M11Switching infrared projection device D12Projecting the structured light, adjusting other infrared projection devices to be in a closed state, and acquiring second frame low-resolution structured light pattern information through an infrared camera D21;
5)M11switching infrared projection device D13Projecting the structured light, adjusting the rest of the infrared projection equipment to be in a closed state, and passing through an infrared camera D21Acquiring the 3 rd frame low resolution structured light pattern information, color camera D22Acquiring first frame color RGB image information;
6) repeating the steps 3) to 5) until the whole breathing process is shot, preferably, the number of deep breaths is two, and outputting the original structured light pattern video S0 and the color RGB video S1 to the high-performance computer D3.
Preferably, the infrared camera D21The collection frequency of the camera is 90Hz, and the color camera D22The acquisition frequency of (2) is 30 Hz.
3. Inputting an original structured light pattern video S0 into a video super-resolution module M3 in a high-performance computer D3, dividing every N frames in the original structured light pattern video S0 into a group, wherein N is the number of infrared projection devices, performing linear interpolation combination on N low-resolution images in the group by using a multi-frame super-resolution algorithm to generate a frame of structured light image with high resolution, repeating the steps until all the groups are processed, obtaining a section of structured light video S0 with high resolution, and inputting the section of structured light video S0 into an M4 module.
4. Inputting the high-resolution structured light video S0 output by the M3 module and the reference image group C1 into a three-dimensional reconstruction module M4 in a high-performance computer D3, and performing local cross-correlation operation on each frame image in the high-resolution structured light video S0 and a reference image group C1 of depth information obtained by calibration in advance to obtain local depth information, wherein the size of a matching window of the local cross-correlation operation is preferably 7X7 pixels. Finally, a three-dimensional reconstructed video S2 is generated and input to the M6 module. The process of calibrating the reference image group C1 is as follows: arranging reference planes on the calibration board at intervals of 1cm, irradiating the calibration board by using a structured light projection module M1, and using an infrared camera D21Acquiring an image of each reference plane, and then recording the depth and the high-resolution structured light pattern of each reference plane by using a video super-resolution module M3 to obtain a reference image group C1;
5. automatic identification module for inputting color RGB video into key pointsM5, as shown in FIG. 3, extracting the key points of the bones of the chest and abdomen of the human body H to be detected from the color RGB video S1 by using a key point recognition algorithm, and respectively obtaining Mask masks of the interested areas of the left and right chest and abdomen of the human body HL0And MaskR0Then, the binocular calibration matrix stored in the Q is used for calibration matching, and left and right thoracoabdominal region-of-interest masks conforming to the visual field of the infrared camera D21 are outputL1，MaskR1And a full thoracoabdominal region of interest Mask 1-M6 module, wherein Mask1 ═ MaskL1+MaskR1；
Preferably, the specific skeletal key points of the human body are the neck, the left and right shoulders, the waist and the left and right pelvis; preferably, the key point identification algorithm is openpos.
6. The high-resolution depth information output by the M4 module, the video S2 and the region-of-interest Mask output by the M5 moduleL1，MaskR1And Mask1 are input into a lung function calculation module M6, and volume changes of the left, right, chest and abdomen regions and the whole chest and abdomen region are calculated respectively to obtain a left, right lung volume change curve and a whole lung volume change curve of each breath. And recording the maximum one-time difference value in the change curve of the total lung capacity as the total lung capacity detected at this time.
While the invention has been described in further detail with reference to specific preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. An infrared dynamic high-resolution non-contact respiration measurement system comprises an infrared structured light projection module M1, a data acquisition module M2, a video super-resolution module M3, a three-dimensional reconstruction module M4, a key point automatic identification module M5, a vital capacity calculation module M6 and a calibration parameter memory Q; it is characterized in that the preparation method is characterized in that,
m1 projector D11To D1NAnd switching control submodelBlock M11The device comprises an infrared projection device, a light source module and a light source module, wherein the infrared projection device is used for alternately projecting a structured light pattern P1 to the chest and abdomen of a human body H to be detected;
m2 is responsible for data acquisition and is composed of an infrared camera D21And a color camera D22Composition is carried out; wherein, D21The light video S0 is responsible for shooting an original structure light video of the chest and the abdomen of the H; d22The color RGB video S1 responsible for shooting H chest and abdomen;
m3 is responsible for reconstructing the original structured light video S0 into a high resolution structured light video S0 using a multi-frame super resolution algorithm;
the M4 is responsible for carrying out three-dimensional reconstruction on the object to be detected according to depth calibration parameter sets C1 and S0 stored in the calibration parameter memory Q to obtain a high-resolution depth reconstruction video S2;
m5 is responsible for automatically identifying the interested regions of the left and right chest and abdomen of the human body H in the color RGB video S1 by using a key point identification algorithm, calibrating and matching by using a binocular calibration matrix C2 stored in Q, and outputting an infrared camera D22Mask for left, right, chest and abdomen region of interest of visual field and whole chest and abdomen region of interestL1，MaskR1And Mask 1;
m6 is responsible for the data according to S2 and MaskL1，MaskR1The Mask1 respectively calculates the volume change in the region of interest to obtain a corresponding lung volume change curve, calculates the lung capacity to obtain the lung volume, and outputs the lung volume change curve and the lung volume value to a calculation result T;
the Q consists of an infrared depth calibration parameter submodule Q1 and a binocular camera calibration parameter submodule Q2; wherein, Q1 is responsible for storing the reference image group C1 recorded with the depth of each reference plane and the corresponding high-resolution structured light pattern obtained by depth calibration in advance, and Q2 is responsible for storing the color camera D2 obtained by binocular camera calibration in advance1And infrared camera D22The binocular calibration matrix C2;
the infrared dynamic high-resolution non-contact respiration measuring system sequentially projects preset infrared structured light patterns to the chest and abdomen region along the H abdomen and back direction of a human body to be measured according to a set frequency in an alternating projection mode and according to an infrared camera D21Shooting the obtained low-resolution structured light video S0, and reconstructing a high-resolution structured light video S0 by using a super-resolution method; further, according to S0, matching is carried out by utilizing an image template library C1 with the depth calibrated in advance, and high-precision three-dimensional reconstruction is completed; finally, through the color camera D22The left and right thoracoabdominal regions of the human body H to be measured are automatically tracked during breathing, and the respective dynamic vital capacities of the left and right lungs of the human body H to be measured are obtained through quantitative estimation according to the time-varying depth of the thoracoabdominal regions along the abdominal-back direction.
2. The system of claim 1, wherein the structured light projection module M1 comprises N infrared projection devices D1 parallel to the same optical horizontal plane1-D1N(N ═ 2), each infrared projection device projects the structured light pattern P1 to the target object through an infrared light source, the projection direction being the ventral-dorsal direction of the human body H to be measured; the structured light pattern P1 is a two-dimensional coding pattern generated in advance, including but not limited to a randomly distributed low-density speckle dot pattern generated by using an infrared light coherent light source with wavelength of 920-1200 nm; during projection, the control submodule M1 is switched by using an alternative projection mode1Responsible for switching the projection infrared projection equipment D1 in sequence and rapidly1To D1NAnd performing projection, wherein the pattern projected by each infrared projection device is the same, and different infrared projection devices have a placement offset of not less than 5 centimeters.
3. The data acquisition module M2 of claim 1, wherein: infrared camera D21The collection range should include the wavelength of 920-; color camera D22An infrared cut-off filter is included, and the cut-off frequency is 780 nm; the specific collection steps are as follows:
1) making the infrared projecting device D11Projecting the structured light, adjusting the rest of the infrared projection equipment to be in a closed state, and adjusting the rest of the infrared projection equipment to be in a closed state through an infrared camera D21Acquiring low resolution structured light pattern information for a first frame, color camera D22Starting to acquire first frame color RGB pattern information;
2) switching infrared projection device D12Projecting the structured light, adjusting the rest of the infrared projection equipment to be in a closed state, and adjusting the rest of the infrared projection equipment to be in a closed state through an infrared camera D21Acquiring second frame low-resolution structured light pattern information;
3)D13to D1N-1The steps of (1) are omitted;
4) switching infrared projection device D1NProjecting the structured light, adjusting the rest of the infrared projection equipment to be in a closed state, and adjusting the rest of the infrared projection equipment to be in a closed state through an infrared camera D21Obtaining the N-th frame of low resolution structured light pattern information, color camera D22Acquiring first frame color RGB pattern information;
5) and repeating the steps 1) to 4) until the acquisition is finished, and outputting the original structured light pattern video S0 and the color RGB video S1.
4. The video super resolution module M3 of claim 1, wherein: the super-resolution method is a multi-frame image super-resolution algorithm and comprises the following specific steps:
1) divide every N frames in the original structured-light pattern video S0 into a group of images, where N is the number of infrared projection devices, and totally divide into M groups (M N equals the total number of frames of S0)
2) Using multi-frame super-resolution algorithm to make interpolation combination of N low-resolution images in a group to generate a frame of structured light image with high resolution,
3) repeating until all M groups are processed, and obtaining a high-resolution structured light video S0.
5. The three-dimensional reconstruction module M4 of claim 1, wherein the three-dimensional reconstruction method comprises performing a local cross-correlation operation on each frame of image in the high resolution structured light video S0 sequentially with a pre-marked reference image group C1 recorded with depth information, and outputting a three-dimensional reconstructed video S2 according to the matching result.
6. The module M5 for automatically identifying key points according to claim 1, wherein the interest area of the thoracoabdominal region is an irregular polygon obtained by connecting key points of specific human bones.
7. The lung function calculation module M6 of claim 1, wherein the high resolution depth information video S2 and the Mask obtained from M4L1，MaskR1And Mask1, respectively calculating the volume change in the region of interest to obtain a left and right lung volume change curve and a full lung volume change curve of each breath. And recording the maximum volume change value in the full lung capacity change curve as the maximum lung capacity detected at this time.
8. A calibration parameter memory Q as defined in claim 1, wherein: the calibration method of the depth calibration comprises the following steps: arranging reference planes on the calibration board at intervals of 1cm, irradiating the calibration board by using a structured light projection module M1, and using an infrared camera D21Acquiring an image of each reference plane, and then recording the depth and the high-resolution structured light pattern of each reference plane by using a video super-resolution module M3 to obtain a reference image group C1; the infrared binocular color calibration method comprises the steps of using a chessboard calibration method to calibrate the color camera D22The characteristic points in the shot images are in a world coordinate system with the infrared camera D21And corresponding the acquired coordinates to obtain a binocular calibration parameter matrix C2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010370702.4A CN113576449A (en) | 2020-04-30 | 2020-04-30 | Infrared dynamic high-resolution non-contact respiration measurement system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010370702.4A CN113576449A (en) | 2020-04-30 | 2020-04-30 | Infrared dynamic high-resolution non-contact respiration measurement system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113576449A true CN113576449A (en) | 2021-11-02 |
Family
ID=78237792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010370702.4A Pending CN113576449A (en) | 2020-04-30 | 2020-04-30 | Infrared dynamic high-resolution non-contact respiration measurement system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113576449A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114587347A (en) * | 2022-03-25 | 2022-06-07 | 深圳市华屹医疗科技有限公司 | Lung function detection method, system, device, computer equipment and storage medium |
-
2020
- 2020-04-30 CN CN202010370702.4A patent/CN113576449A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114587347A (en) * | 2022-03-25 | 2022-06-07 | 深圳市华屹医疗科技有限公司 | Lung function detection method, system, device, computer equipment and storage medium |
| CN114587347B (en) * | 2022-03-25 | 2023-04-28 | 深圳市华屹医疗科技有限公司 | Lung function detection method, system, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11089974B2 (en) | Monitoring the location of a probe during patient breathing | |
| Camison et al. | Validation of the Vectra H1 portable three-dimensional photogrammetry system for facial imaging | |
| Adler et al. | GREIT: a unified approach to 2D linear EIT reconstruction of lung images | |
| CN102301202B (en) | Method And Apparatus For Monitoring An Object | |
| US9226691B2 (en) | Processing a video for tidal chest volume estimation | |
| EP1718206B1 (en) | Time-dependent three-dimensional musculo-skeletal modeling based on dynamic surface measurements | |
| CN104739418A (en) | Respiratory gating system and control method based on three-dimensional vision | |
| Rehouma et al. | Quantitative assessment of spontaneous breathing in children: evaluation of a depth camera system | |
| CN114787869A (en) | Apparatus, method and computer program for monitoring an object during a medical imaging procedure | |
| Mitchell | Applications of digital photogrammetry to medical investigations | |
| CN113576449A (en) | Infrared dynamic high-resolution non-contact respiration measurement system | |
| Rehouma et al. | A computer vision method for respiratory monitoring in intensive care environment using RGB-D cameras | |
| Enciso et al. | Three-dimensional head anthropometric analysis | |
| Deacon et al. | Evaluation of a CCD-based facial measurement system | |
| KR101309013B1 (en) | Diagnosis Device For Face Form Using Facial Image and Cephalometric Image | |
| CN116128838A (en) | Binocular vision-based respiratory detection system, 4D-CT image reconstruction system and method | |
| CN115187608B (en) | Respiration characteristic extraction method based on body surface significance analysis | |
| Mündermann et al. | Measuring human movement for biomechanical applications using markerless motion capture | |
| Wang et al. | An improved correlation model for respiration tracking in robotic radiosurgery using essential skin surface motion | |
| Elad et al. | Three-dimensional measurement of biological surfaces | |
| US20220378321A1 (en) | Methods and systems for assessing severity of respiratory distress of a patient | |
| CN111466933A (en) | Spine mobility measuring method and system | |
| Jawaid et al. | Advancements in medical imaging through Kinect: A review | |
| Rehouma et al. | Visualizing and quantifying thoraco-abdominal asynchrony in children from motion point clouds: A pilot study | |
| Katashev et al. | Application of 3D Scanner for Estimation of Chest Movement in Scoliotic Patients |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211102 |