Measurement apparatus, measurement method, program, and storage medium

Abstract

To provide a measuring device capable of efficiently measuring biological information by using video data.SOLUTION: The measurement device (10) includes an acquisition unit (11) that acquires video data of a subject from an imaging device (100), a storage unit (13) that stores data table information indicating a relationship between biological information of a measurement target and a video data recording condition, a determination unit (14) that determines the video data recording condition on the basis of the data table information, and a measurement unit (15) that measures the biological information by using the video data acquired under the video data recording condition.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a measurement device, a measurement method, a program, and a storage medium. [Background technology]

[0002] In recent years, technologies for measuring biometric information without contact have been proposed. The principle of measuring biometric information such as respiratory rate and pulse rate from video data acquired by an imaging device is similar to that of photoplethysmography (PPG). The optical absorption characteristics of hemoglobin in blood are utilized to measure biometric information. Because green light is well absorbed by subcutaneous blood vessels, the signal intensity of the green component of reflected light changes depending on the increase or decrease in blood volume in the blood vessels. Therefore, measurement devices for measuring biometric information are configured to detect time-series data (PPG signals) containing biometric information using light with wavelengths that are highly absorbed by hemoglobin. In addition to information about pulse waves, PPG signals also contain information attributable to other physiological phenomena, such as respiration. For example, pulse rate can be calculated from the peak intervals of PPG signals detected over time. PPG signals not only reflect pulse rate information but also vary depending on circulatory system parameters such as blood ejection volume and vascular resistance.

[0003] Patent Document 1 discloses a method for constructing a generalized model that can estimate blood pressure from only PPG signals, and for estimating blood pressure with high accuracy and versatility. Patent Document 2 discloses a method for controlling the frame rate to measure the pulse rate. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2022-148276 [Patent Document 2] Japanese Patent Application Laid-Open No. 2010-51592 Summary of the Invention [Problem to be solved by the invention]

[0005] When measuring a subject's biological information in a non-contact manner, the minimum required conditions for the frame rate of the video data and the compression rate of the data volume of one frame of video vary depending on the type of biological information being measured, such as pulse rate, blood pressure, or oxygen saturation. In addition, when the specifications of the measurement device are insufficient or when the network bandwidth is insufficient, it is not possible to uncompress the video data used in measuring biological information, maximize the video resolution, and maximize the video frame rate. For this reason, the methods disclosed in Patent Documents 1 and 2 are unable to continuously measure the subject's biological information, and a more efficient method of measuring biological information using video data is needed.

[0006] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a measuring device that can efficiently measure biological information using video data. [Means for solving the problem]

[0007] A measurement device according to one aspect of the present invention includes an acquisition unit that acquires image data of a subject from an imaging device, a memory unit that stores data table information indicating the relationship between the biometric information of the measurement target and the image data recording conditions, a determination unit that determines the image data recording conditions based on the data table information, and a measurement unit that measures the biometric information using the image data acquired under the image data recording conditions.

[0008] Other objects and features of the present invention are illustrated in the following examples. [Effects of the Invention]

[0009] According to the present invention, it is possible to provide a measurement device that can efficiently measure biological information using video data. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram of a measurement system according to a first embodiment. [Figure 2] 10 is a diagram showing frequency information obtained by frequency analysis of a biological information signal in a face region of a subject; FIG. [Figure 3] FIG. 4 is a diagram illustrating an example of data table information according to the first embodiment. [Figure 4] 4 is a flowchart showing a process of the biological information measuring device according to the first embodiment. [Figure 5] FIG. 10 is a block diagram of a measurement system according to a second embodiment. [Figure 6] FIG. 10 is a diagram illustrating an example of data table information according to the second embodiment. [Figure 7] 10 is a flowchart showing a process of the biological information measuring device according to the second embodiment. [Figure 8] FIG. 10 is a block diagram of a measurement system according to a third embodiment. [Figure 9] FIG. 11 is a diagram illustrating an example of data table information according to the third embodiment. [Figure 10] 10 is a flowchart showing a process of the biological information measuring device according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0012] For convenience, the drawings may be drawn at a scale different from the actual scale. As shown in the drawings, the same components are designated by the same reference numerals, and redundant descriptions will be omitted. While each embodiment describes multiple features, not all of these features are necessarily essential to the invention, and multiple features may be combined in any desired manner.

[0013] It is generally known that biological information can be measured by irradiating a part of a living body (subject) with light and detecting the amount of light reflected from the body. It is also known that hemoglobin in blood effectively absorbs green visible light with wavelengths of 495 to 570 nm. The G (green) signal of the color filter of the imaging device contains many signals that transmit in the wavelength band of 495 to 570 nm, which can improve the accuracy of measuring respiratory rate and heart rate.

[0014] To explain this in more detail, capillaries flow on the skin surface, and when the blood flow in the blood vessels changes due to the heartbeat, the amount of light absorbed by the blood flow also changes in accordance with the heartbeat, and therefore the change in brightness obtained by reflection from the skin area also changes in accordance with the heartbeat. Although the amount of change in brightness is small, when the average brightness value within the region of interest is calculated, the time-series brightness data contains a signal component of biological information. Therefore, for example, the biological information signal can be detected using the time-series data of three signals, namely, the G signal, the R (red) signal, and the B (blue) signal, each of which has a different amount of light absorption by hemoglobin in the blood.

[0015] Furthermore, to detect biometric signals, it is necessary to set a region including the skin area as the region of interest. For example, it is known that the typical pulse rate at rest is in the range of 40 to 120 bpm. It is also known that the typical respiratory rate at rest is in the range of 12 to 20 breaths per minute. In other words, it can be seen that the minimum optimal condition for the video frame rate, which is one of the conditions for recording video data, differs depending on the type of biometric information being measured.

[0016] When measuring biometric information from video data, it is necessary to acquire a PPG signal that reflects the biometric information to be measured. In other words, when acquiring a PPG signal from an imaging device, it is necessary to appropriately set the conditions for recording the video data. The conditions for recording the video data include, for example, the video frame rate, video resolution, compression rate of the video data amount per frame, bit depth of the data amount allocated per pixel, compression encoding method when transmitting the video data, and data amount per second.

[0017] When transmitting video data, the video data may be compressed and encoded before transmission, or may be transmitted without being compressed and encoded. The compression and encoding method may be based on standards such as H.264 / MPEG-4 AVC, H.265 / MPEG-H HEVC, MJPEG, etc., or the compressed and encoded video data may be generated in any file format, including MP4 or AVI. The file format of the video data is not limited to MP4 or AVI and may be, for example, MOV or MKV. Bitrate control may be performed to set the bitrate, which is the amount of data per second of the compressed and encoded video data signal. For example, bitrate control may be performed to control the compression and encoding so that the bitrate does not exceed the bitrate set in the compression and encoding process.

[0018] In addition, the interval between independent frames (I frames) that do not require information from other video frames when decoding may be specified. In this way, determining the compression encoding method when transmitting video data is not limited to the compression encoding method, and bit rate control and the interval between independent frames (I frames) may also be specified.

[0019] Referring to Figures 2(a) and (b), we will explain the frequency characteristics of Fourier transforms performed on time-series data of the average brightness value signal of the G signal over 60 seconds when image data of a subject with a pulse rate of approximately 72 bpm was acquired and set to the skin area within the region of interest. The frequency at which the subject's pulse component's bioinformation signal peaks is approximately 1.2 Hz. The vertical axis of the graphs shown in Figures 2(a) and (b) represents the strength of the bioinformation signal (signal strength), and the horizontal axis represents frequency (Hz).

[0020] Figures 2(a) and (b) show frequency information obtained by frequency analysis of biometric signals in the subject's face area. Figure 2(a) uses video data acquired with a video frame rate of 15 fps (frames per second), a video resolution of 1920 x 1080, uncompressed video data per frame, and 8-bit data allocated per pixel. Figure 2(b) uses video data acquired with a video frame rate of 15 fps, a video resolution of 1920 x 1080, a 50% compression rate for video data per frame, and 8-bit data allocated per pixel (256 levels).

[0021] Comparing the signals near the pulse component in Figures 2(a) and 2(b), Figure 2(a) shows a frequency where the signal intensity reaches a peak of 0.1 around 1.2 Hz. Figure 2(b) shows a frequency where the signal intensity reaches a peak of 0.1 around 1.2 Hz. This indicates that the pulse component can be detected regardless of the compression rate of the image data per frame. When measuring the pulse rate as the biometric information, the compression rate of the image data per frame, which is one of the conditions for recording the image data, can be increased to reduce the data volume. Patent Document 2 discloses that, in blood pressure estimation using a PPG signal, it is effective to calculate multiple feature values ​​from the waveform of the acquired PPG signal and use them for blood pressure estimation. In other words, it is desirable to detect the signal intensity near a frequency that is twice the frequency at which the pulse component of the biometric information signal peaks.

[0022] In this study, the subject's pulse component biometric signal peaked at approximately 1.2 Hz, so a signal peak at approximately 2.4 Hz would be desirable. Comparing the signals near twice the pulse component in Figures 2(a) and 2(b), Figure 2(a) shows a peak frequency of 0.02 signal strength near 2.4 Hz. Figure 2(b) shows no clear peak near 2.4 Hz. Furthermore, peak frequencies exist not only near 2.4 Hz but also near 2.2 Hz, 2.7 Hz, and 3.2 Hz. Under the measurement conditions used, the peak frequencies excluding those near 1.2 Hz and 2.4 Hz correspond to noise components. This indicates that the compression rate of one frame of video data makes it impossible to detect the features required for blood pressure estimation. In other words, when measuring blood pressure as the biometric information, for example, the compression rate of one frame of video data, one of the video data recording conditions, must be kept low. That is, in order to continuously measure selected biological information, it is necessary to select the conditions for recording video data based on the biological information to be measured.

[0023] Each example will be described in detail below.

[0024] Example 1 First, a measurement system 1000 including a biological information measuring device (measurement device) 10 according to a first embodiment of the present invention will be described with reference to Fig. 1. Fig. 1 is a block diagram of the measurement system 1000.

[0025] The measurement system 1000 is a system that measures biological information by continuously acquiring information about reflected light from the skin surface of a subject over time from a moving image (video data) obtained by capturing an image of the skin surface of the subject with an imaging device 100. The measurement system 1000 includes the imaging device 100 and a biological information measuring device 10. The biological information measuring device 10 and the imaging device 100 are communicably connected to each other via a network. The connection method may be wired or wireless. Furthermore, the measurement system 1000 may be configured such that the biological information measuring device 10 and the imaging device 100 are integrated into one unit. That is, the measurement system of this embodiment may be configured such that the imaging device 100 is provided as an imaging unit inside the biological information measuring device 10, or such that the biological information measuring device 10 is provided as a biological information measuring unit inside the imaging device 100.

[0026] The imaging device 100 according to this embodiment can capture images of a subject at a frame rate of 30 fps. That is, a video can be acquired by continuously recording 30 images per second. The frame rate of the imaging device 100 is not limited to 30 fps. The imaging device 100 includes an optical system and an imaging element. The imaging element includes pixels sensitive to at least one wavelength. At least one of the pixels is sensitive to a biological information component. The imaging element may include pixels sensitive to two or more wavelengths, such as an imaging element having three RGB color filters. A photoelectric conversion element such as a CCD (Charge Coupled Device) sensor or a CMOS (Complementary Metal-Oxide-Semiconductor) sensor can be used as the imaging element.

[0027] The biological information measuring device 10 has a video data acquiring unit (acquiring unit) 11, a selecting unit 12, a storage unit 13, a deciding unit 14, and a biological information measuring unit (measuring unit) 15, and performs an examination of a subject imaged by the imaging device 100.

[0028] The video data acquisition unit 11 acquires brightness values ​​(video data) output from the imaging element of the imaging device 100 via a network. Since the imaging device 100 of this embodiment continuously images the subject over time, the video data acquisition unit 11 can also acquire brightness values ​​corresponding to the continuously imaged images over time. In this case, the video data acquisition unit 11 may acquire information related to time. The information related to time is the time from the start of imaging or the number of images (number of frames) captured from the start of imaging. By adopting such a configuration, it is possible to detect biological information of the subject at a specific timing during imaging.

[0029] The selection unit 12 selects biological information of a measurement target in accordance with a user's operation. The biological information of a measurement target (selectable biological information) is, but is not limited to, pulse rate, respiratory rate, blood pressure, oxygen saturation, or the like. Furthermore, the biological information of a measurement target is not limited to one type of biological information, and two or more types of biological information (at least two types of biological information including first biological information and second biological information), such as pulse rate and blood pressure, may be selected.

[0030] The storage unit 13 stores data table information, created in advance, indicating the relationship between the biological information of the measurement target and the conditions for recording video data (video data recording conditions). FIG. 3 is a diagram showing an example of data table information according to this embodiment. Continuous measurement of selected biological information can be achieved by using the data table information shown in FIG. 3. The biological information included in the data table information is not limited to pulse rate, blood pressure, and respiratory rate, but may also include oxygen saturation or disease detection. The video data recording conditions are not limited to the video frame rate, video resolution, compression ratio of the video data volume per frame, or compression encoding method used when transmitting the video data. For example, they may include the bit depth of the data volume allocated per pixel or the data volume per second. Note that the video frame rate, video resolution, and compression ratio of the video data volume per frame are not limited to the values ​​shown in FIG. 3.

[0031] The determination unit 14 determines the video data recording conditions based on the data table information stored in the storage unit 13. Furthermore, when the selection unit 12 selects multiple types of biometric information (at least two types of biometric information including first biometric information and second biometric information) as the biometric information to be measured, the determination unit 14 determines the video data recording conditions that satisfy all of the selected biometric information. That is, the determination unit 14 determines the third video data recording conditions that satisfy both the first video data recording condition corresponding to the first biometric information and the second video data recording condition corresponding to the second biometric information. Then, the biometric information measurement unit 15 measures the first biometric information and the second biometric information simultaneously, in parallel, or consecutively using the video data acquired under the third video data recording condition.

[0032] In this case, the data table information stored in the storage unit 13 may include information indicating the relationship between the first biometric information and the second biometric information selected as the biometric information of the measurement target and the third video data recording condition. The determination unit 14 can acquire and determine the third video data recording condition from the storage unit 13. However, this embodiment is not limited to this. For example, the determination unit 14 may acquire, from the storage unit 13, the first video data recording condition corresponding to the first biometric information and the second video data recording condition corresponding to the second biometric information. Then, the determination unit 14 can use the first video data recording condition and the second video data recording condition to determine the third video data recording condition so as to satisfy both the first video data recording condition and the second video data recording condition.

[0033] The above process allows the video data recording conditions to be changed in accordance with the biological information of the measurement subject. As a result, by determining the video data recording conditions based on the biological information of the measurement subject, the selected biological information can be measured continuously.

[0034] The biological information measurement unit 15 measures biological information. The biological information measurement device 10 acquires biological information contained in a set region of interest. The set region of interest is set to a range of any size and shape, including one body region. Furthermore, a skin region that includes facial features and that fills the skin range expressed in color space components such as the HSV color space, may be set as the region of interest.

[0035] This makes it possible to improve the accuracy of detecting biological information. The biological information of the subject is detected from the luminance value corresponding to the set skin region. The luminance value is the average luminance value extracted from the channels that pass through the color filters of the solid-state imaging element in the imaging device 100. For example, the signal of the channel that has spectral sensitivity in the red wavelength region is R, the signal of the channel that has spectral sensitivity in the green wavelength region is G, and the signal of the channel that has spectral sensitivity in the blue wavelength region is B. The average luminance value is calculated from the luminance values ​​contained in the region of interest in one frame image. By detecting the biological information using the average luminance value, the influence of noise can be reduced and the accuracy of detecting the biological information can be improved.

[0036] Finally, time-series data is obtained by extracting the luminance value for each frame image. The time-series data is not limited to the average luminance value of the G signal, but may also be the average luminance value of the R signal or the average luminance value of the B signal. For example, when generating time-series data using only the G signal, the average luminance value of the G signal is extracted in time series and a moving average process is performed. Furthermore, the time-series data is not limited to the average luminance value of a single channel signal, but may also be values ​​calculated using arithmetic operations on the luminance values ​​of multiple channels. In the following, the average luminance value corresponding to the G pixels is referred to as Gave, the average luminance value corresponding to the R pixels is referred to as Rave, and the average luminance value corresponding to the B pixels is referred to as Bave.

[0037] When two types of signals, G and R, are used, they can be expressed as Gave / Rave. While the example of using two signals, G and R, has been given, any number of different signals can be selected. For example, any combination of signals that transmit light in wavelength ranges, such as G, R, B, and IR (infrared) signals, can be used, or two or more signals can be used. Because IR penetrates deeply into living organisms, it contains information about blood flow deep within. This means that biological information can be detected even in darkfield environments that are invisible to the human eye. This improves the accuracy of biological information detection at night.

[0038] The process of generating the time series data may include moving average processing and other noise removal processes, which smooth out the changes in the time series data and make it easier to detect the peak positions of the waveform.

[0039] Peaks (maximum or minimum values) are detected from the generated time-series data, and the pulse rate value is calculated and output as biometric information based on the frame rate of the imaging device 100. The frame rate represents the number of frames captured per unit time. For example, if the frame rate of the imaging device 100 is 30 fps and the interval between two adjacent peaks (the difference in frame numbers) is 30, the pulse rate is 60 × 30 ÷ 30 = 60 beats / min. Alternatively, the pulse rate may be calculated from the time average of the interval between two adjacent peaks or the average peak interval obtained from the interval between two adjacent peaks, or from the number of peaks within a specific time period. Alternatively, the respiration rate may be calculated by applying a bandpass filter to the time-series data to extract a band in which the respiration rate may exist, acquiring the peak positions, and then calculating the interval between the peaks or the number of peaks within a certain time range.

[0040] By generating a waveform that is time-series data containing biological information from which noise components, including movement components, have been removed, it is possible to accurately capture waveform feature quantities. For example, changes in the peak interval or amplitude of the generated waveform can serve as an indicator of whether or not an arrhythmia is present. The method for acquiring waveform feature quantities is not limited to the above-described method, and any method may be used. For example, biological information may be acquired from feature quantities (inflection points) that cannot be determined from the original generated waveform by taking the second derivative of the generated waveform. The acquired feature quantities may also be useful for early disease detection. In this way, by generating a waveform that is time-series data containing biological information from which noise components have been removed, it is possible to detect early-stage diseases and perform more accurate vital sign measurements.

[0041] Alternatively, the pulse rate and respiratory rate may be calculated from the peak frequency in the frequency characteristics obtained by Fourier transforming the time series data. Furthermore, peaks may be detected from the time series data, and pulse rate fluctuations may be calculated from the time fluctuations of the intervals between the peaks. Furthermore, maximum and minimum values ​​may be detected from the time series data, and oxygen saturation fluctuations may be calculated from the time fluctuations of the widths. The method for acquiring bioinformation includes, for example, calculating the moving average of the intervals between waveform peaks, performing frequency analysis, or performing principal component analysis, and the present invention does not limit the method for acquiring bioinformation. Examples of bioinformation acquired include the subject's pulse rate, respiratory rate, blood pressure, and oxygen saturation. It is also possible to select the bioinformation to be acquired from the acquired time series data.

[0042] Next, the processing (measurement method) of the biological information measuring device 10 according to this embodiment will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the measurement method according to this embodiment.

[0043] First, in step S101 (video data acquisition step), the imaging device 100 images a subject, and the video data acquisition unit 11 acquires video data output from the imaging device 100. The imaging element included in the imaging device 100 according to this embodiment is an RGB color sensor. The RGB color sensor has G pixels sensitive to G wavelengths, R pixels sensitive to R wavelengths, and B pixels sensitive to B wavelengths. The video data acquisition unit 11 acquires luminance values ​​output from the imaging element as video data. When the imaging element is an RGB sensor, the video data acquisition unit 11 acquires G luminance values, R luminance values, and B luminance values.

[0044] Since the imaging device 100 acquires images of the subject continuously over time, it is possible to acquire brightness values ​​corresponding to the images continuously over time. In this case, information regarding time may be acquired. The information regarding time is the time from the start of imaging or the number of images (number of frames) captured from the start of imaging. By adopting such a configuration, it is possible to detect biological information of the subject at a specific timing during imaging.

[0045] Next, in step S102 (selection step), the selector 12 determines whether or not to select at least one type of biological information of the measurement target. If a type of biological information of the measurement target is selected, the process proceeds to step S103. On the other hand, if a type of biological information of the measurement target is not selected, the image data recording conditions are not switched, and the acquisition of image data continues using the previous image data recording conditions, and this flow ends.

[0046] In step S103 (determination step), the determination unit 14 selects and determines the video data recording conditions using data table information indicating the relationship between the biometric information selected in step S102 and the video data recording conditions. The data table information is stored in advance in the storage unit 13.

[0047] Subsequently, in step S104 (biological information measurement step), the biological information measurement unit 15 measures biological information using the video data acquired under the video data recording conditions determined in step S103.

[0048] As described above, the bio-information measuring device 10 according to this embodiment can meet the minimum optimal conditions for recording video data corresponding to the bio-information of the measurement subject, thereby enabling continuous measurement of bio-information.

[0049] Example 2 Second Embodiment Next, a measurement system 2000 including a biological information measuring device (measurement device) 20 according to a second embodiment of the present invention will be described with reference to Fig. 5. Fig. 1 is a block diagram of the measurement system 2000. As shown in Figs.

[0050] The biological information measuring device 20 has a video data acquiring unit (acquiring unit) 21, a selecting unit 22, an identifying unit 23, a storage unit 24, a determining unit 25, and a biological information measuring unit (measuring unit) 26, and performs an examination of a subject imaged by the imaging device 200. Note that the video data acquiring unit 21, the selecting unit 22, the determining unit 25, and the biological information measuring unit 26 are similar to the video data acquiring unit 11, the selecting unit 12, the determining unit 14, and the biological information measuring unit 15 of the biological information measuring device 10 according to the first embodiment, respectively, and therefore descriptions thereof will be omitted.

[0051] The imaging device 200 according to this embodiment has a communication unit capable of communication compliant with standards such as TCP / IP and UDP / IP, and a control unit that controls the transmission of video data, and is capable of transmitting video data to a network. The communication unit of the imaging device 200 is connected to a network such as a LAN or the Internet via network wiring. The control unit can be configured with a dedicated control circuit or a CPU and peripheral circuits. Note that, for the sake of simplicity, only one imaging device 200 is shown in FIG. 5 , but an actual configuration may include multiple imaging devices. In this case, video data can be transmitted from one imaging device (camera) to multiple locations, and one display device (monitor) can receive and display video data from multiple imaging devices.

[0052] The identification unit 23 identifies the network communication status by determining whether the specifications of the biometric measuring device 20 that performs biometric measurement, the network bandwidth, etc., are sufficient for transmitting and receiving video data used in biometric measurement. In other words, it identifies changes in the network. For example, the determination may be made using the specifications of the measurement system 2000. For example, a method may be used in which the current link speed of the network adapter is checked to determine whether the network adapter is operating according to specifications. For example, if the transmission and reception link speed is 100 Mbps, the biometric measuring device 20 compares the amount of video data calculated based on the conditions for recording video data in the imaging device 200. If the link speed of the network adapter is higher, the biometric measuring device 20 determines that the network communication status is good. On the other hand, if the link speed of the network adapter is lower, the biometric measuring device 20 determines that the network communication status is not good.

[0053] The amount of video data can be calculated from the video frame rate, video resolution, compression rate of the amount of video data per frame, bit depth of the amount of data allocated per pixel, compression encoding method used when transmitting the video data, and the amount of data per second. Alternatively, the identification unit 23 may acquire the amount of data actually transmitted and received in real time and compare it with the amount of data calculated based on the conditions for recording the video data. The amount of data is not limited to only the video data generated by the imaging device 200. The amount of data actually transmitted and received via the connected network may also include, for example, document data and video data from a system other than the measurement system 2000. Note that in this embodiment, the method for identifying the network communication status by determining whether or not there are any problems with transmitting and receiving video data used for biometric information measurement is not limited.

[0054] The storage unit 24 stores data table information, which has been created in advance, that indicates the relationship between the biological information of the measurement target and the video data recording conditions. Figures 6(a) and 6(b) are diagrams showing an example of the data table information according to this embodiment. By using the data table information shown in Figures 6(a) and 6(b), it is possible to continuously measure selected biological information.

[0055] The biological information included in the data table information is not limited to pulse rate and blood pressure, but may also include oxygen saturation, respiratory rate, etc. The video data recording conditions included in the data table information are not limited to the video frame rate, the compression rate of the video data amount per frame, and the bit depth of the data amount allocated per pixel. For example, the video resolution, the compression encoding method used when transmitting the video data, or the data amount per second may be included. Note that the video frame rate, the compression rate of the video data amount per frame, and the bit depth of the data amount allocated per pixel are not limited to the values ​​shown in Figures 6(a) and 6(b).

[0056] The storage unit 24 updates the video data recording conditions (information stored in the storage unit 24) of the data table information based on the network communication state identified by the identification unit 23 as being in a state where there is no problem in transmitting and receiving video data used for measuring biological information. FIG. 6(a) shows data table information indicating the relationship between pre-stored biometric information of the measurement target and the video data recording conditions. When the identification unit 23 identifies that the network communication state is good, the data table information of FIG. 6(a) is used. FIG. 6(b) shows data table information updated after the identification unit 23 identifies that the network communication state is not good. When the network communication state is not good, the video frame rate is reduced while the compression rate of the video data amount per frame is increased, thereby enabling recording under the minimum optimal conditions required for measuring biological information.

[0057] In this embodiment, instead of updating the data table information stored in the storage unit 24, the storage unit 24 may store data table information for each communication state. That is, the storage unit 24 may store the data table information of both Figures 6(a) and 6(b). In this case, the determination unit 25 can select (determine) the video data recording conditions using the data table information according to the communication state.

[0058] The video data recording conditions are not limited to the minimum conditions necessary for measuring biological information, but may be conditions that exceed the minimum conditions necessary for continuous measurement of biological information. For example, when measuring pulse rate, in order to extract only the peak interval, the data volume can be reduced by significantly increasing the compression rate of the video data volume per frame while slightly decreasing the video frame rate, thereby enabling continuous measurement of biological information. On the other hand, when measuring blood pressure, in order to extract minute changes (multiple feature quantities), the data volume can be reduced by significantly decreasing the video frame rate without changing the compression rate of the video data volume per frame, thereby enabling continuous measurement of biological information. Furthermore, values ​​such as the bit depth of the data volume allocated per pixel do not need to be changed before and after an update. By updating the data table information, biological information can be continuously measured.

[0059] The updated values ​​of the video data recording conditions are the values ​​of the conditions for recording video data when biometric information was measured in the past under similar network communication conditions. Similar network communication conditions are not limited to network communication conditions under which the measurement system 2000 had the same configuration as the measurement system 2000 that was able to measure biometric information in the past. For example, it may be a network communication condition in which the network includes a system other than the measurement system 2000.

[0060] Furthermore, values ​​of the video data recording conditions to be updated may be calculated from the communication state of the network identified by the identification unit 23. For example, the video frame rate, video resolution, compression rate of the video data amount per frame, and bit depth of the data amount allocated per pixel may be calculated so that the video data amount is smaller than the link speed of the network adapter. Note that in this embodiment, the method for calculating the values ​​of the video data recording conditions is not limited.

[0061] The update frequency of the data table information may be, for example, after the selection unit 22 selects the biological information to be measured. Alternatively, the data table information may be updated at specified time intervals. However, there are no limitations on the update frequency of the data table information. Through the above process, in addition to the biological information to be measured, it is possible to change the conditions for recording video data based on the communication state of the network to determine whether there are any problems in transmitting and receiving the video data used for measuring the biological information. In other words, since the conditions for recording video data can be selected depending on the communication state of the network, it is possible to continuously measure biological information.

[0062] Next, the processing (measurement method) of the biological information measuring device 20 according to this embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the measurement method according to this embodiment. Note that steps S201, S202, S206, and S207 in Fig. 7 are the same as steps S101, S102, S103, and S104 in Fig. 4 described in the first embodiment, respectively, and therefore their description will be omitted.

[0063] In step S203 (identification step), the identification unit 23 identifies the network state (communication state) to determine whether or not there is a problem in transmitting and receiving video data used for measuring biological information. This process may be executed in parallel with step S202 (selection step) and step S204 (determination step). By performing parallel processing, it is possible to reduce the time required to select biological information to be measured and to determine conditions for recording video data.

[0064] Subsequently, in step S204 (determination step), the identification unit 23 determines whether the network state has changed. If it is determined that the network state has not changed, the process proceeds to step S206 (decision step). In step S206, the decision unit 25 decides the video data recording conditions using data table information that is stored in advance in the storage unit 24 and indicates the relationship between the biometric information of the measurement target and the video data recording conditions.

[0065] On the other hand, if it is determined that the network status has changed, the process proceeds to step S205 (update step). In step S205, the storage unit 24 updates the video data recording conditions in the data table information based on the network status. If the network status changes from good to bad, the video data recording conditions can be updated to reduce the amount of data. When the network communication status improves, the conditions for recording video data can be updated to increase the amount of data in order to improve the accuracy of the measured biological information. The video data recording conditions may also be updated to recover the reduced amount of data.

[0066] As described above, the biological information measuring device 20 according to this embodiment can select conditions that meet or exceed the minimum optimal conditions for recording video data corresponding to the biological information to be measured, even if the specifications of the biological information measuring device being used are insufficient or the network bandwidth is insufficient. Therefore, biological information can be measured continuously.

[0067] Example 3 Third Embodiment Next, a measurement system 3000 including a biological information measuring device (measurement device) 30 according to a third embodiment of the present invention will be described with reference to Fig. 8. Fig. 1 is a block diagram of the measurement system 3000.

[0068] The biological information measuring device 30 has a video data acquiring unit (acquiring unit) 31, a selecting unit 32, a detecting unit 33, a discriminating unit 34, a storage unit 35, a determining unit 36, and a biological information measuring unit (measuring unit) 37, and performs an examination of a subject imaged by the imaging device 300. Note that the video data acquiring unit 31, the selecting unit 32, the discriminating unit 34, the determining unit 36, and the biological information measuring unit 37 are similar to the video data acquiring unit 21, the selecting unit 22, the discriminating unit 23, the determining unit 25, and the biological information measuring unit 26 according to the second embodiment, respectively, and therefore description thereof will be omitted.

[0069] The detection unit 33 detects the subject from the video data acquired by the video data acquisition unit 31. The detection unit 33 may detect facial information of the subject from the video data based on feature points of facial areas such as the eyes, nose, mouth, and facial contours. The detection unit 33 may perform facial authentication by determining whether the detected facial information is identical to any person registered in a database in which feature amounts of facial information of multiple people are stored in advance.

[0070] The detection unit 33 calculates features from an image containing the detected face using a model, and calculates the similarity between the calculated features and the features in the database. If the similarity is greater than a threshold, it determines that the detected subject is the same person as the person registered in the database. By detecting the face of the subject whose biometric information is to be measured, it is possible to record video data corresponding to the measured biometric information at the appropriate time.

[0071] The detection unit 33 also detects the positions of the feature points of each joint of the subject from the video data using machine learning or the like. The detected coordinates and likelihood may then be output as the results of posture detection of the subject. For example, when it is detected that the subject has been in the same posture for more than five minutes, it may determine that the subject's physical condition is not good, and record the video data corresponding to the measured biometric information. Note that in this embodiment, the method for detecting the subject from the video data used for measuring biometric information is not limited.

[0072] The detection unit 33 can change the processing conditions for detecting the subject (e.g., an algorithm for acquiring facial feature points when detecting the subject) based on the video data recording conditions determined by the determination unit 36. For example, when performing facial recognition of the subject, the amount of data required to detect multiple feature points of the subject from one frame of video data increases, and the amount of calculation required to calculate similarity increases. The detection unit 33 compares the amount of data calculated from the video data recording conditions determined by the determination unit 36 ​​with the amount of data required for facial recognition and the amount of data that can actually be transmitted and received, and changes the processing conditions for facial recognition, thereby reducing the amount of data required for facial recognition.

[0073] By changing the processing conditions based on the video data recording conditions, it is possible to continuously measure biological information. The processing conditions are detected from the video data and are, for example, the number of feature points and the detection frequency (the interval between frames in which feature points are detected). The processing conditions may be stored in a database, for example, or may be stored in association with data table information stored in the storage unit 35. By changing the processing conditions for detecting the subject based on the video data recording conditions, it is possible to continuously measure biological information while detecting the subject, even when the specifications of the biological information measuring device being used are insufficient or the network bandwidth is insufficient. Furthermore, it is possible to perform a comprehensive analysis of the subject while continuously measuring biological information.

[0074] The storage unit 35 stores data table information indicating the relationship between the biometric information of the measurement target and the video data recording conditions, which has been created in advance. The storage unit 35 also stores information indicating the priority of the video data recording conditions in association with the type of biometric information of the measurement target. FIGS. 9(a) and 9(b) are diagrams showing an example of data table information according to this embodiment. FIG. 9(a) shows data table information indicating the relationship between the biometric information to be measured and the video data recording conditions, which has been stored in advance. When the identification unit 34 determines that the network communication state is good, the data table information of FIG. 9(a) is used. FIG. 9(b) shows data table information updated after the identification unit 34 determines that the network communication state is not good. When the identification unit 34 determines that the network communication state is not good, the data table information is updated, allowing the biometric information to be measured continuously.

[0075] When updating data table information, the data table information is updated based on information indicating priority. For example, consider a case where the video frame rate and the compression ratio of the video data amount per frame are updated so that the video data amount is smaller than the link speed of the network adapter. In this case, in order to reduce the data amount, it is not desirable to update the video frame rate and the video data amount per frame at the same rate.

[0076] For example, when measuring pulse rate, in order to extract only the peak interval, priority is given to the image frame rate rather than the compression rate of the image data for one frame, and the data is stored in association with the image. In other words, the compression rate of the image data for one frame is updated to increase. On the other hand, when measuring blood pressure, priority is given to the compression rate of the image data for one frame, in order to extract minute changes (multiple feature amounts). On the other hand, when measuring oxygen saturation, priority is given to the image frame rate, in order to extract temporal fluctuations in width, and the compression rate of the image data for one frame and the image frame rate are changed to reduce the data volume. By associating information indicating priority, the selected biological information can be measured continuously regardless of the network communication status.

[0077] In addition, the information indicating the priority is not limited to the frame rate of the video or the compression rate of the data amount of one frame of video, but may also be the video resolution, the bit depth of the data amount allocated per pixel, the compression encoding method used when transmitting the video data, or the data amount per second.

[0078] Next, the processing (measurement method) of the biological information measuring device 30 according to this embodiment will be described with reference to Fig. 10. Fig. 10 is a flowchart showing the measurement method according to this embodiment. Note that steps S301 to S304, S306, and S308 in Fig. 10 are the same as steps S201 to S204, S206, and S207 in Fig. 7 described in the second embodiment, respectively, and therefore their description will be omitted.

[0079] In step S305 (updating step), the storage unit 35 updates the data table information based on the communication state of the network as well as information indicating the pre-stored priority.

[0080] In step S307 (detection step), the detection unit 33 determines whether or not a subject has been detected from the video data. For example, if the subject's face has been detected, the process proceeds to step S308 (biometric information measurement step). In step S308, the biometric information measurement unit 37 measures biometric information. In the previous step S306 (determination step), the determination unit 36 ​​previously determined the conditions for recording video data. Therefore, immediately after detecting the subject's face, biometric information can be measured under the minimum optimal conditions. By measuring biometric information immediately after face detection, biometric information can be measured even if the subject immediately moves off-screen. On the other hand, if the subject's face has not been detected, the video data recording conditions are not switched, and the acquisition of video data continues under the previous video data recording conditions. Note that this embodiment is not limited to detecting the subject's face, but can also be applied to subject face authentication or subject posture detection.

[0081] As described above, the biological information measuring device 30 according to this embodiment can select the conditions for recording video data under the minimum optimal conditions based on the biological information to be measured, even when the specifications of the biological information measuring device being used are insufficient or the network bandwidth is insufficient, etc. Therefore, the biological information can be measured continuously.

[0082] (Other Examples) The present invention can also be realized by supplying a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and having one or more processors in the computer of the system or device read and execute the program. It can also be realized by a circuit (e.g., ASIC) that realizes one or more functions.

[0083] In each embodiment, in order to continuously measure biological information, conditions for recording video data are selected based on the biological information to be measured. Therefore, according to each embodiment, it is possible to provide a measurement device, a measurement method, a program, and a storage medium that can measure biological information efficiently (for example, with a small storage capacity) using video data.

[0084] The disclosure of each embodiment includes the following configurations and methods. (Configuration 1) an acquisition unit that acquires image data of the subject from an imaging device; a storage unit that stores data table information indicating the relationship between biological information of the measurement subject and video data recording conditions; a determination unit that determines the video data recording conditions based on the data table information; a measurement unit that measures the biological information using the video data acquired under the video data recording conditions. (Configuration 2) 2. The measurement device according to configuration 1, further comprising a selection unit that selects the biological information of the measurement target from a plurality of types of biological information. (Configuration 3) The measurement device according to configuration 2, wherein the video data recording conditions vary depending on the biological information of the measurement object, and are conditions necessary for measuring the biological information of the measurement object. (Configuration 4) When the biological information of the measurement target selected by the selection unit is first biological information and second biological information, the determination unit determines a third video data recording condition that satisfies both a first video data recording condition corresponding to the first biometric information and a second video data recording condition corresponding to the second biometric information; The measuring device according to configuration 2 or 3, wherein the measurement unit measures the first biological information and the second biological information using the video data acquired under the third video data recording condition. (Configuration 5) the data table information includes information indicating a relationship between the first biological information and the second biological information selected as the biological information of the measurement target and the third video data recording condition, 5. The measuring device according to configuration 4, wherein the determining unit acquires the third video data recording condition from the storage unit. (Configuration 6) The determination unit acquiring, from the storage unit, the first video data recording condition corresponding to the first biometric information and the second video data recording condition corresponding to the second biometric information; 5. The measuring device according to configuration 4, wherein the third video data recording condition is determined using the first video data recording condition and the second video data recording condition. (Configuration 7) 7. The measuring device according to any one of configurations 1 to 6, wherein the acquisition unit acquires the video data from the imaging device via a network. (Configuration 8) further comprising an identification unit that identifies a communication state of the network; The measuring device according to configuration 7, wherein the storage unit updates the video data recording conditions of the data table information stored in the storage unit based on the communication state of the network identified by the identification unit. (Configuration 9) further comprising an identification unit that identifies a communication state of the network; the storage unit stores the data table information indicating a relationship between the biological information of the measurement object and the video data recording condition for each of the communication states; The measuring device according to configuration 7, wherein the determining unit determines the video data recording conditions using the data table information according to the communication state. (Configuration 10) 10. The measurement device according to any one of configurations 7 to 9, wherein the storage unit stores information indicating a priority in association with the video data recording conditions according to the biological information of the measurement subject. (Configuration 11) a detection unit that detects the subject from the video data; 11. The measuring device according to any one of configurations 1 to 10, wherein the detection unit changes processing conditions for detecting the subject based on the video data recording conditions. (Configuration 12) The measuring device according to any one of configurations 1 to 11, wherein the video data recording conditions include conditions related to at least one of the frame rate of the video, the compression rate of the amount of video data per frame, the resolution of the video, the bit depth of the amount of data allocated per pixel, the compression encoding method used when transmitting the video data, or the amount of data per second. (Configuration 13) 13. The measuring device according to any one of configurations 1 to 12, wherein the biological information includes information on at least one of pulse rate, respiratory rate, blood pressure, and oxygen saturation. (Method 1) acquiring image data of the subject from an imaging device; determining the video data recording conditions based on data table information stored in a storage unit, the data table information indicating the relationship between the biological information of the measurement subject and the video data recording conditions; and measuring the biological information using the video data acquired under the video data recording conditions. (Configuration 14) A program that causes a computer to execute the measurement method described in Method 1. (Configuration 15) A computer-readable storage medium storing the program according to configuration 14.

[0085] Although the preferred embodiments of the present invention have been described above, the present invention is not limited to these embodiments, and various modifications and changes are possible within the scope of the gist of the present invention. [Explanation of symbols]

[0086] 10. Biological information measuring device 11 Video data acquisition unit (acquisition unit) 12 Selection section 13 Storage section 14 Decision Section 15 Biological Information Measurement Unit (Measurement Unit) 100 Imaging device

Claims

1. an acquisition unit that acquires image data of the subject from an imaging device; a storage unit that stores data table information indicating the relationship between biological information of the measurement subject and video data recording conditions; a determination unit that determines the video data recording conditions based on the data table information; a measurement unit that measures the biological information using the video data acquired under the video data recording conditions.

2. 2. The measurement device according to claim 1, further comprising a selection unit that selects the biological information of the measurement target from a plurality of types of biological information.

3. 3. The measurement device according to claim 2, wherein the video data recording conditions vary depending on biological information of the measurement subject, and are conditions necessary for measuring the biological information of the measurement subject.

4. When the biological information of the measurement target selected by the selection unit is first biological information and second biological information, the determination unit determines a third image data recording condition that satisfies both a first image data recording condition corresponding to the first biometric information and a second image data recording condition corresponding to the second biometric information; The measuring device according to claim 2 , wherein the measuring unit measures the first biological information and the second biological information using the video data acquired under the third video data recording condition.

5. the data table information includes information indicating a relationship between the first biological information and the second biological information selected as the biological information of the measurement target and the third video data recording condition, The measuring device according to claim 4 , wherein the determining unit acquires the third video data recording condition from the storage unit.

6. The determination unit acquiring, from the storage unit, the first video data recording condition corresponding to the first biometric information and the second video data recording condition corresponding to the second biometric information; 5. The measuring device according to claim 4, wherein the third video data recording condition is determined using the first video data recording condition and the second video data recording condition.

7. The measuring device according to claim 1 , wherein the acquisition unit acquires the video data from the imaging device via a network.

8. further comprising an identification unit that identifies a communication state of the network; The measuring device according to claim 7, characterized in that the storage unit updates the video data recording conditions of the data table information stored in the storage unit based on the communication status of the network identified by the identification unit.

9. further comprising an identification unit that identifies a communication state of the network; the storage unit stores the data table information indicating a relationship between the biological information of the measurement object and the video data recording condition for each of the communication states; 8. The measuring device according to claim 7, wherein the determining unit determines the video data recording conditions using the data table information according to the communication state.

10. 8. The measuring device according to claim 7, wherein the storage unit stores information indicating a priority in association with the video data recording conditions in accordance with the biological information of the measurement subject.

11. a detection unit that detects the subject from the video data; 11. The measuring apparatus according to claim 1, wherein the detection unit changes a processing condition for detecting the subject based on the video data recording condition.

12. The measuring device according to any one of claims 1 to 10, characterized in that the video data recording conditions include conditions relating to at least one of the frame rate of the video, the compression rate of the amount of video data per frame, the resolution of the video, the bit depth of the amount of data allocated per pixel, the compression encoding method used when transmitting the video data, or the amount of data per second.

13. 11. The measurement device according to claim 1, wherein the biological information includes information on at least one of pulse rate, respiratory rate, blood pressure, and oxygen saturation.

14. acquiring image data of the subject from an imaging device; determining the video data recording conditions based on data table information stored in a storage unit, the data table information indicating the relationship between the biological information of the measurement subject and the video data recording conditions; and measuring the biological information using the video data acquired under the video data recording conditions.

15. A program causing a computer to execute the measurement method according to claim 14.

16. A computer-readable storage medium storing the program according to claim 15.

Images