Method for Monitoring the State of a Living Body

Abstract

The present invention is a method for monitoring the state of a living body, comprising: (a) receiving an image set including at least two reflected images generated at different time points and a display of at least one interval between at least two different time points, wherein the reflected images are generated while the living body is illuminated by patterned coherent electromagnetic radiation, and include at least one pattern feature, and the reflected images show at least one pattern feature formed by illuminating at least a part of the living body with the patterned coherent electromagnetic radiation, and (b) determining a feature contrast of at least two pattern features; (c) determining a state measurement value of the living body based on the feature contrast and the display of the at least one interval; (d) outputting the state measurement value. A method is provided that includes the above steps.

Description

Technical Field

[0001] The present invention relates to the field of monitoring the state of a living body. In particular, the present invention relates to a method for monitoring the state of a living body, a non-transitory computer-readable data medium storing a computer program including instructions for performing steps of the method, a system for monitoring the state of a living body, the use of signals indicating state-based actions for controlling the state monitoring system, and the use of state measurement values for operating the state monitoring system.

Background Art

[0002] As technologies for remotely monitoring the heart rate, stress, blood pressure, etc. indicating the state of a living body, generally, a photoplethysmograph (PPG) and a ballistocardiograph (BCG) are known.

[0003] PPG can be used to detect changes in blood volume. Usually, visible light is used to observe changes in intensity due to light absorption. Information regarding the cardiovascular system can be derived from these changes. PPG can be used for a wide range of medical applications such as monitoring heart rate and cardiac cycle, monitoring respiration, monitoring depth of anesthesia, monitoring low and high blood cell counts, and monitoring blood pressure. The ballistocardiograph (BCG) is a non-invasive method and is based on the measurement of body movements caused by the ejection of blood in each cardiac cycle (see Non-Patent Document 1).

Prior Art Documents

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, since these technologies usually use visible light, they need to be near the living body. Furthermore, it is necessary to illuminate the entire area uniformly. Therefore, when photographing areas other than the skin, serious drawbacks such as background due to movement and high cost may occur.

[0006] Therefore, it was an object of the present invention to overcome these drawbacks. In particular, it aimed at a method for monitoring the state of a living body that gives the living body complete mobility and does not distract the living body. This method must be fast, require inexpensive hardware, and not involve physical contact with the living body.

Means for Solving the Problems

[0007] Overview These objects have been achieved by the present invention. In one aspect, there is provided a method for monitoring the state of a living body, comprising: (a) receiving an image set including at least two reflected images generated at different times and a display of at least one interval between at least two different times, wherein the reflected images show at least a part of the living body while the living body is illuminated by coherent electromagnetic radiation and include a pattern having at least one pattern feature; and (b) determining a feature contrast of at least two pattern features; (c) determining a state measurement value of the living body based on the feature contrast and the display of the at least one interval; (d) outputting the state measurement value. The present invention relates to a method including these steps.

[0008] In another aspect, the present invention is a method for monitoring the state of a living body, comprising: (a) Receiving an image set including at least two reflected images generated at different times and a display of at least one interval between the at least two different times, wherein the reflected images are generated while a living body is illuminated by patterned coherent electromagnetic radiation, and the reflected images show at least one pattern feature formed by illuminating at least a part of the living body by the patterned coherent electromagnetic radiation, and (b) Determining a feature contrast of at least two pattern features; (c) Determining a state measurement value of the living body based on the feature contrast and the display of the at least one interval; (d) Outputting the state measurement value. Relates to a method including the above steps.

[0009] The present invention is based on the recognition that when body fluids or particles in a living body, such as blood cells, particularly red blood cells, interstitial fluid, intracellular fluid, lymph, ions, proteins, and nutrients, move, they may cause motion blur in the reflected light, while the rest of the body is stationary and does not cause motion blur. Therefore, when coherent electromagnetic radiation is reflected by moving scattering particles such as red blood cells, the pattern fluctuates and the features of the pattern blur. As a result of this blur, the feature contrast decreases. Therefore, the pattern and the feature contrast obtained from the pattern contain information regarding whether the illumination target is moving. The feature contrast is composed of at least one feature contrast value. The feature contrast value generally distributes from 0 to 1. Determining the feature contrast may include determining the feature contrast value. In particular, determining the feature contrast of at least two pattern features may refer to determining a first feature contrast in relation to a first pattern feature of at least two pattern features and determining a second feature contrast in relation to a second pattern feature of at least two pattern features. Preferably, determining the feature contrast of at least two pattern features may refer to determining a first feature contrast value in relation to a first pattern feature of at least two pattern features and determining a second feature contrast value in relation to a second pattern feature of at least two pattern features.

[0010] When illuminating an object, a value of 1 represents no movement, and a value of 0 represents the fastest movement of the particles, so the pattern features are most significantly blurred. Coherent electromagnetic radiation refers to electromagnetic radiation that can exhibit an interference effect. It may also include partial coherence, i.e., an imperfect correlation between phase values. Preferably, the coherent electromagnetic radiation is in the infrared range, most preferably in the near-infrared range. In particular, the coherent electromagnetic radiation is patterned coherent electromagnetic radiation. By illuminating at least a part of a living body with the patterned coherent electromagnetic radiation, at least one pattern feature is projected onto the living body. A reflected image generated while illuminating a living body with the patterned coherent electromagnetic radiation may show at least one pattern feature. By illuminating at least a part of a living body with the patterned coherent electromagnetic radiation, it may be possible to interact between the patterned coherent electromagnetic radiation and the living body, particularly the skin of the living body. The interaction between the patterned coherent electromagnetic radiation and the living body, particularly the skin of the living body, may result in the formation of speckles. The speckles may be contrast fluctuations, particularly local contrast fluctuations, in the region irradiated by the patterned coherent electromagnetic radiation, particularly the patterned coherent electromagnetic radiation. Subsequently, the pattern feature may be composed of a plurality of speckles and / or contrast fluctuations. Determining the feature contrast may refer to determining the contrast fluctuations regarding the pattern features related to different time points. Determining the contrast fluctuations may refer to determining at least two feature contrast values, particularly a first feature contrast value related to a first reflected image and a second feature contrast value related to a second reflected image.

[0011] The present invention provides a means for providing an efficient and robust method for monitoring the condition of a living organism. The feature contrasts of the multiple reflected images can be used to determine a condition measurement, such as heart rate, blood pressure, suction level, etc. For example, heart rate is a sensitive condition measurement that indicates the condition of the living organism, in particular the stress level, etc., indicated by the condition measurement. Thus, by monitoring the living organism, situations can be identified where the living organism is, for example, stressed, and corresponding measures can be taken based on the determined condition measurement. Identifying such situations is particularly important when critical condition measurements pose health or security risks. Examples of such situations include a driver controlling a vehicle, a user using a virtual reality headset, or a person who has to make far-reaching decisions. Identifying such situations can reduce security and health risks in such situations.

[0012] Furthermore, the invention provided herein utilizes inexpensive hardware for monitoring the living body. In addition, the invention does not require direct contact with the living body, being easy to integrate and implement while providing reliable results. Also, by irradiating the living body with light in the infrared range, the living body may not realize that monitoring is occurring. Thus, by using the methods, systems, computer readable storage media, and signals disclosed herein, the living body will not be distracted by the light or feel that it is being monitored.

[0013] A living organism is an individual form of life, preferably a human or animal. A living organism may be characterized by the fluids that flow within the organism.

[0014] In another aspect, the invention relates to a non-transitory computer readable data medium having stored thereon a computer program comprising instructions for performing the steps of any of the methods described above.

[0015] In another aspect, the present invention provides a system for monitoring a condition of a living organism, comprising: (a) An input unit for receiving an image set including at least two reflected images generated at different times and the display of at least one interval between at least two different times, wherein the reflected images show at least a part of a living body while the living body is illuminated by coherent electromagnetic radiation and include a pattern having at least one pattern feature, the input unit, and (b) A processor, - for determining the feature contrast of at least two pattern features, and - for determining a state measurement value of the living body based on the feature contrast and the display of the at least one interval, the processor, and (c) An output unit for outputting the state measurement value relating to a system.

[0016] In another aspect, the present invention relates to a method of using a state measurement value obtained by the method described in any of the foregoing in a state control system.

[0017] In another aspect, the present invention is a state control system, (a) An input unit for receiving a state measurement value obtained by the method described in any of the foregoing and a threshold value related to an important state measurement value, (b) A processor for generating a signal indicating a state-based action based on a comparison between the state measurement value and the threshold value associated with the important state measurement value, (c) An output unit for outputting a signal indicating a state-based action, relating to a system.

[0018] In another aspect, the present invention is a method for monitoring the state of a living body, (a) Receiving at least a first reflected image, a second reflected image, and a display of an interval between a time when the first reflected image is generated and a time when the second reflected image is generated, wherein the first reflected image and the second reflected image show at least a part of a living body while the living body is illuminated by coherent electromagnetic radiation including a pattern having at least one pattern feature, and (b) Determining a first feature contrast of the pattern feature in the first reflected image and a second feature contrast of the pattern feature in the second reflected image; (c) Determining a state measurement value of the living body based on the first feature contrast, the second feature contrast, and the display of the interval; (d) Outputting the state measurement value. Relates to a method including the above.

[0019] In another aspect, the present invention is a method for monitoring the state of a living body, the method comprising: (a) Receiving at least a first reflected image, a second reflected image, and a display of an interval between a time when the first reflected image is generated and a time when the second reflected image is generated, wherein the first reflected image and the second reflected image show at least a part of the living body while the living body is illuminated by patterned coherent electromagnetic radiation, and the first reflected image and the second reflected image show at least one pattern feature formed by illuminating at least a part of the living body with the patterned coherent electromagnetic radiation, and (b) Determining a first feature contrast of the pattern feature in the first reflected image and a second feature contrast of the pattern feature in the second reflected image; (c) Determining a state measurement value of the living body based on the first feature contrast, the second feature contrast, and the display of the interval; (d) Outputting the state measurement value. Relates to a method including the above.

[0020] In another aspect, the present invention is a method for monitoring the state of a living body, comprising: (a) receiving at least a first reflection image, a second reflection image, and a display of an interval between a time when the first reflection image is generated and a time when the second reflection image is generated, wherein the first reflection image and the second reflection image are generated while at least a part of the living body is illuminated by patterned coherent electromagnetic radiation, and the first reflection image and the second reflection image show at least one pattern feature formed by illuminating at least a part of the living body with the patterned coherent electromagnetic radiation; and (b) determining a first feature contrast of a pattern feature in the first reflection image and a second feature contrast of a pattern feature in the second reflection image; (c) determining a state measurement value of the living body based on the first feature contrast, the second feature contrast, and the display of the interval; (d) outputting the state measurement value. The present invention relates to a method comprising the above steps.

[0021] The disclosures and embodiments described herein relate to the above methods, systems, uses, computer program elements, and vice versa. Advantageously, the advantages provided by any of the embodiments and examples apply equally to all other embodiments and examples, and vice versa.

[0022] Coherent electromagnetic radiation is patterned coherent electromagnetic radiation. The patterned coherent electromagnetic radiation can be composed of a plurality of light beams, for example at least one light beam, preferably at least two light beams. The pattern feature may be associated with one light beam of the patterned coherent electromagnetic radiation. In particular, one pattern feature is associated with one light beam of the patterned coherent electromagnetic radiation. Thus, the projection of the light beam of the patterned coherent electromagnetic radiation onto the surface may result in a pattern feature. The pattern feature may refer to a light spot. In particular, the pattern feature may be generated by projecting coherent electromagnetic radiation onto a living body.

[0023] The projection of the patterned coherent electromagnetic radiation onto a regular surface may result in a pattern feature that is independent of speckles projected onto the regular surface. The projection of the patterned coherent electromagnetic radiation onto a regular surface may result in a pattern feature projected onto an irregular surface consisting of at least one speckle, preferably a plurality of speckles. Subsequently, depending on the surface onto which the patterned coherent electromagnetic radiation is projected, the pattern feature may consist of zero, one or a plurality of speckles. The skin may have an irregular surface. Thus, the projection of the patterned coherent electromagnetic radiation may result in the formation of speckles within one or more pattern features. The pattern feature may be the result of the projection of a light beam associated with the patterned coherent electromagnetic radiation. The pattern feature refers to a spot of any shape of coherent electromagnetic radiation. The pattern feature may also refer to a continuous area illuminated by the coherent electromagnetic radiation. When coherent electromagnetic radiation is projected onto an irregular surface, speckles are formed. Subsequently, the pattern feature may consist of one or a plurality of speckles. The pattern feature has a diameter between 0.5 mm and 5 cm, preferably between 0.6 mm and 4 cm, more preferably between 0.7 mm and 3 cm, and most preferably between 0.4 cm and 2 cm.

[0024] For example, the patterned coherent electromagnetic radiation is generated by a plurality of light-emitting elements such as a VCSEL array. One of the plurality of light-emitting elements can emit one light beam. Thus, one of the plurality of light-emitting elements may be related to one pattern feature, the formation of one pattern feature, and / or the projection of one pattern feature. Additionally or alternatively, the patterned coherent electromagnetic radiation may be generated by one or more light-emitting elements and an optical element such as a DOE or a metasurface element. The optical element may replicate the number of light beams associated with one or more light-emitting elements and / or may be suitable for replicating the number of light beams associated with one or more light-emitting elements. For example, the light emitter may be a laser.

[0025] The reflected image shows at least a part of the living body while the living body is illuminated by the patterned coherent electromagnetic radiation. Thus, the reflected image shows the projection of the patterned electromagnetic radiation onto the living body. The projection of the patterned coherent electromagnetic radiation can show at least one pattern feature, preferably at least two pattern features. Subsequently, the reflected image shows at least one pattern feature formed by illuminating at least a part of the living body with the patterned coherent electromagnetic radiation.

[0026] A pattern refers to a regular and / or irregular arrangement of pattern features. Subsequently, a pattern may refer to a regular and / or irregular arrangement of one or more arbitrarily shaped spots of coherent electromagnetic radiation. A pattern may refer to at least one continuous region, preferably at least two, more preferably at least five, and most preferably at least ten regions illuminated by coherent electromagnetic radiation. A pattern may not mean an array of speckles. Further, the concept of a pattern may be independent of the concept of a contrast map and / or the concept of tiling an image for local contrast determination. A pattern may refer to a regular and / or irregular arrangement of one or more light beams. A pattern and / or pattern feature may be formed before and / or independently of the interaction between the patterned coherent electromagnetic radiation and the living body surface.

[0027] In one embodiment, the reflected image shows at least two pattern features. Preferably, the reflected image can show five or more pattern features.

[0028] Patterned coherent electromagnetic radiation refers to coherent electromagnetic radiation whose intensity varies spatially. In particular, the patterned coherent electromagnetic radiation can form a pattern consisting of at least one pattern feature while irradiating a living body. Further, the intensity of the patterned coherent electromagnetic radiation may vary over time, and / or the coherent electromagnetic radiation may be a continuous wave.

[0029] Using coherent electromagnetic radiation to evaluate the state of a living body is advantageous because the living body is illuminated with various intensities, for example, a light spot. In contrast to projection illumination, by using patterned coherent electromagnetic radiation, sensitive parts such as the eyes to light can be preserved. Furthermore, the characteristic contrast for specific pattern features can be determined, and the estimation accuracy of the state of the living body can be improved by the average value. Overall, the luminance of the pattern features can be further improved, and as a result, the quality of the reflected image can be improved. Finally, by improving the quality of the reflected image, it becomes possible to more accurately estimate the state of the living body.

[0030] The term "reflected image" as used in this specification is not limited to the actual visual representation of an object. Instead, the reflected image is composed of data generated based on the light reflected by the object being irradiated with light. The reflected image may be composed of at least one pattern. The reflected image is composed of at least one pattern feature. The reflected image may be included in a larger reflected image. The larger reflected image may be a reflected image composed of more pixels than the reflected image composed therein. When the reflected image is divided into at least two parts, at least two reflected images may be obtained. The at least two reflected images may be composed of different data generated based on the light reflected by the object being irradiated with light. For example, one of the at least two reflected images may represent the nose of the living body, and the other of the at least two reflected images may represent the forehead of the living body. The reflected image may be suitable for determining the characteristic contrast of at least one pattern feature. The reflected image may be composed of a plurality of pixels. The plurality of pixels may be composed of at least two pixels, preferably two or more pixels. For determining the characteristic contrast, at least one pixel related to the reflection feature and at least one pixel not related to the reflection feature may be suitable, and the reflection feature refers to the pattern feature.

[0031] In particular, the term "reflected image" as used in the present specification can refer to any data that can construct an actual visual representation of the imaging object. For example, the data can correspond to the assignment of color values or grayscale values to image positions, and each image position can correspond to a position within or on the imaged object. The reflected image or data referred to in the present specification can be two-dimensional, three-dimensional, or four-dimensional. For example, a four-dimensional image can be understood as a three-dimensional image that evolves over time. Similarly, a two-dimensional image that evolves over time may be regarded as a three-dimensional image. When the data is digital data, the reflected image can be regarded as a digital image, and in that case, the image positions can correspond to the pixels or voxels of the image and / or the image sensor. During the generation of the reflected image, the living body can be illuminated with light that is ultimately RGB light or preferably IR flood light and / or patterned light. The patterned light may include at least one pattern. The patterned light may be projected onto the living body. The patterned light may include patterned coherent electromagnetic radiation.

[0032] In this context, "generation" also includes capturing and / or recording an image.

[0033] As used herein, the term "pattern" refers to any known or predetermined arrangement consisting of at least one pattern feature of any shape, although not limited thereto. A pattern may be composed of at least one pattern feature. A pattern can consist of an array of periodic or aperiodic pattern features. A pattern is at least one quasi-random pattern; at least one Sobol pattern; at least one quasi-periodic pattern; at least one point pattern, particularly a pseudo-random point pattern; at least one line pattern; at least one stripe pattern; at least one checkered pattern; at least one triangular pattern; at least one rectangular pattern; at least one hexagonal pattern, or a pattern consisting of a further convex gradient. A pattern feature is at least a part of a pattern. A pattern feature may be at least partially composed of symbols of any shape. A symbol is any one of at least one point; at least one line; at least two lines such as parallel lines or intersecting lines; at least one point and one line; at least one array of periodic pattern features; at least one pattern of any shape.

[0034] Feature contrast may represent a measure of the contrast of the intensity distribution within the area of a pattern, particularly within the area of a pattern feature. Additionally or alternatively, feature contrast may refer to a measure of the contrast associated with a pattern feature. Feature contrast can be determined for at least two pattern features. Feature contrast may exhibit at least two feature contrast values, where a first feature contrast value among the at least two feature contrast values is associated with a first reflection image among the at least two reflection images and / or a first pattern feature among the at least two pattern features, and a second feature contrast value among the at least two feature contrast values may be associated with a second reflection image among the at least two reflection images and / or a second pattern feature among the at least two pattern features. In particular, a first pattern feature among the at least two pattern features, especially at least one first pattern feature, may be associated with a first reflection image among the at least two reflection images, especially at least one first reflection image. In particular, a second pattern feature among the at least two pattern features, especially at least one second pattern feature, may be associated with a second reflection image among the at least two reflection images, especially at least one second reflection image. Feature contrast may be determined for a first pattern feature of at least two reflection images and for a second pattern feature of at least two reflection images. Feature contrast may be determined separately for at least two pattern features of at least two reflection images.

[0035] Feature contrast may include determining, and / or may include determining, at least two feature contrast values associated with at least two pattern features. Determining the feature contrast of at least two pattern features may include determining a first feature contrast value associated with a first pattern feature and determining a second feature contrast value associated with a second pattern feature. The feature contrast value may be determined by determining the ratio of the standard deviation of the pattern feature intensity to the mean of the pattern feature intensity. The pattern feature intensity may include an intensity value associated with the corresponding pattern feature.

[0036] In particular, the feature contrast value K over the area of the pattern is the average pattern feature intensity The ratio of the standard deviation σ to, that is, [Chemical formula] can be expressed as. The characteristic contrast value generally distributes between 0 and 1. The characteristic contrast may be determined based on at least one pattern feature. Subsequently, at least two characteristic contrast values may be determined based on at least two pattern features.

[0037] In some embodiments, to determine the characteristic contrast, the complete pattern of the reflected image may be used. Alternatively, to determine the characteristic contrast, a part of the pattern may be used. The section of the pattern preferably represents an area smaller than the area of the pattern. The area may be of any shape. The section of the pattern can be obtained by trimming the reflected image. The characteristic contrast may be different for different parts of the living body. Different parts of the living body may correspond to different parts of the reflected image. Subsequently, the characteristic contrast may be different for different parts of the reflected image.

[0038] The image set may be composed of a set of reflected images. Preferably, the image set consists of at least two reflected images. The image set may be generated at different times.

[0039] In some embodiments, at least one or more characteristic contrast values of at least one pattern feature may be determined. The characteristic contrast value may correspond to the numerical value of the characteristic contrast.

[0040] A state measurement value is a measurement value suitable for determining the state of a living body. The state of a living body refers to the physical state and / or mental state. The physical state refers to the degree of physical stress, fatigue, excitement, suitability for performing a specific task of the living body, etc. The mental state may be related to the mental stress level, attention, concentration, excitement state, suitability for performing a specific task of the living body, etc. Such a specific task may require the concentration, attention, wakefulness, calmness, or similar characteristics of the living body. Examples of such tasks include the control of machines, vehicles, mobile devices, etc., operations on other biological species, sports-related activities, games, emergency operations, decision-making, etc. The state measurement value indicates the state of the living body. The state measurement value may be one or more of the heart rate, blood pressure, inhalation level, etc. In some embodiments, the state of the living body may be a critical state corresponding to a high value of the state measurement value, and the state of the living body may be a non-critical state corresponding to a low value of the state measurement value. Subsequently, the critical state measurement value according to these embodiments may be equal to or lower than the threshold value, and the non-critical state measurement value may be lower than the threshold value. In other embodiments, the state of the living body may be a critical state corresponding to a low value of the state measurement value, and the state of the living body may be a non-critical state corresponding to a high value of the state measurement value. Subsequently, the critical state measurement value according to these embodiments may be equal to or higher than the threshold value, and the non-critical state measurement value may be lower than the threshold value. The critical state measurement value may be related to a high stress level, low attention, low concentration level, high fatigue, high excitement, low suitability for performing a specific task of the living body, etc. The non-critical state measurement value can be associated with a low stress level, high attention, high concentration, low fatigue, low excitement, high suitability for performing a specific task of the living body, etc.

[0041] The state measurement value of a living body can be determined based on the movement of body fluid, preferably blood, and most preferably red blood cells. The movement of body fluid is not constant over time and changes due to the activity of a part of the living body, such as the heart. Such changes in movement can be judged based on changes in the characteristic contrast over time. If the difference in the values of the characteristic contrast at different time points is large, there is a possibility that the change in movement is fast. The small difference between the values of the characteristic contrast at different time points may be related to the slow change in movement. The change in the movement of body fluid, preferably blood, may be periodically associated with the corresponding movement frequency. Therefore, the characteristic contrast changes periodically with the corresponding movement frequency. The movement frequency may correspond to the length of the period associated with the periodic change of the characteristic contrast. In some embodiments, half of the period may be constituted in at least two reflection images. In other embodiments, one or several periods may be constituted in at least two reflection images. Preferably, in order to determine the state of a living body, pattern features related to the same part of the living body can be used. This is advantageous due to the fact that the perfusion of blood, and thus the characteristic contrast across different parts of the living body, changes. In some embodiments, at least one state measurement value can be determined based on the characteristic contrast.

[0042] The image set may be composed of a time series. The time series may be composed of reflection images separated by a fixed time interval or a changing time interval related to the imaging frequency. Preferably, the time series is configured such that the imaging frequency is at least twice the movement frequency. This is known as the Nyquist theorem. In the case of high resolution, more reflection images than required by the Nyquist theorem may be received.

[0043] For the determination of the state measurement value, a display of the interval between different time points at which at least two reflection images are generated is received. The display of the interval consists of measurement values suitable for determining the time between different time points at which at least two reflection images are generated.

[0044] Frequency is the reciprocal of the length of a period. The length of the period is determined by the interval between two reflected images that make up the heartbeat or the period of the cardiac cycle. The normal human heart beats 60 - 80 times per minute at rest, and the resting heart rate is 60 - 80 beats per minute (bpm). The resting heart rate may be lower, for example, when doing sports or suffering from bradycardia. When a person is active, the heart rate can increase up to 230 bpm. The heart rate of animals is 6 - 1000 bpm. The reflected images are generated according to the expected heart rate of the living body to be examined. The interval between the reflected images can be selected up to a maximum of 10 seconds. In the case of humans, the interval can be selected up to 2 seconds. Subsequently, the imaging frequency can be selected to be at least 12 reflected images per minute, or at least 60 reflected images in the case of humans. As an example, this method can be used to determine the human heart rate. For this purpose, an imaging frequency of 60 images per minute can be selected. As the characteristic contrast is determined, it can be recognized that the imaging frequency may be too low. In such a case, the imaging frequency can be increased so that the state measurement value can be determined. Alternatively, the imaging frequency for imaging a human may be selected at a high frequency such as 460 images per minute. The heart rate may be determined based on at least two reflected images and the indication of the interval between at least two different time points showing an interval of 0.13 seconds. In this example, the human heart rate is in the range of 60 - 80 bpm. Subsequently, the imaging frequency can be adjusted according to the expected and / or predetermined state measurement value.

[0045] As an example, the interval may be composed of half of one period, the whole, twice the length, etc. The interval may be between at least two reflected images. Subsequently, the at least two reflected images may be separated by a length of half a period, a full period, twice the period, etc. In an exemplary case of three reflected images, a display of one or two different intervals may be received. When two or more reflected images are received, the display of the interval may include the interval between the first reflected image and the second reflected image, and / or the interval between the first reflected image and the third reflected image (or, when three or more reflected images may be received, every other reflected image), and / or the interval between the second reflected image and the third reflected image (or, when three or more reflected images may be received, every other reflected image). This is appropriately applied to other scenarios where the amount of reflected images is different, as will be recognized by those skilled in the art. The means for displaying the interval may be at least two time points corresponding to different points in time when at least two reflected images are generated, and / or the time elapsed between different points in time, and / or the imaging frequency related to the generation of the reflected images. The at least two time points may be determined based on the timestamps of the at least two reflected images. The imaging frequency may include a selected value. The imaging frequency may be selected based on an expected state measurement value, such as an expected heart rate. Alternatively, the imaging frequency may be determined using the image frequency of the video. The expected heart rate may include the heart rate related to the living body being monitored. In some embodiments, an estimation of the state measurement value may be used to select the imaging frequency. The estimation of the state measurement value may take into account the species of the organism and its surroundings.

[0046] In one embodiment, the image dataset may include at least one first reflected image and at least one second reflected image. The at least one first reflected image and the at least one second reflected image may be generated at different times, particularly at least two different times. The at least one first reflected image and the at least one second reflected image may be generated while the living body is illuminated by patterned coherent electromagnetic radiation. The at least one first reflected image may show at least one first pattern feature, preferably at least two first pattern features, formed by illuminating at least a part of the living body with patterned coherent electromagnetic radiation. The at least one second reflected image may show at least one second pattern feature, preferably at least two second pattern features, formed by illuminating at least a part of the living body with patterned coherent electromagnetic radiation. In particular, the at least one first pattern feature and the at least one second pattern feature may be associated with the same body part of the living body.

[0047] The feature contrast can determine at least one first pattern feature and at least one second pattern feature. The feature contrast may show a first feature contrast value associated with at least one first pattern feature and a second feature contrast value associated with at least one second pattern feature. The state measurement value is determined based on the feature contrast of at least one first pattern feature and at least one second pattern feature and the display of at least one interval between the generation of at least one first reflected image and the generation of at least one second reflected image by providing them to a data-driven model, where the data-driven model is parameterized with respect to a training dataset including a historical feature contrast showing a plurality of first feature contrast values associated with a plurality of first pattern features and a plurality of second feature contrast values associated with a plurality of second pattern features, a plurality of historical displays of at least one interval, and a plurality of historical state measurement values.

[0048] In one embodiment, the biological state measurement value may be determined based on the feature contrast of at least two pattern features and the display of at least one interval during the generation of at least two pattern images by providing the feature contrast and the display of at least one interval to a data-driven model. The data-driven model is parameterized based on a training data set including past feature contrasts, past displays of at least one interval, and past state measurement values. The feature contrast can indicate at least two feature contrast values associated with at least two pattern features.

[0049] In one embodiment, the biological state measurement value based on the first feature contrast, the second feature contrast, and the display of the interval may be determined by providing the first feature contrast, the second feature contrast, and the display of the interval to a data-driven model. The data-driven model may be parameterized based on a training data set including the past first feature contrast, the past second feature contrast, the past display of at least one interval, and the past state measurement value.

[0050] Providing a feature contrast may include providing a first feature contrast value and a second feature contrast value. A data-driven model may be parameterized based on a training data set to provide and / or output a state measurement value based on the provision of the feature contrast of at least two pattern features and the display of at least one interval between the generation of at least two pattern images. A data-driven model may be trained based on a training data set including past feature contrasts, past displays of at least one interval, and past state measurement values to provide and / or output a state measurement value based on the provision of the feature contrast of at least two pattern features and the display of at least one interval between the generation of at least two pattern images. The state measurement value of a living body may be determined based on the feature contrast and the display of at least one interval by providing the feature contrast of at least two pattern features and the display of at least one interval between the generation of at least two pattern images to a data-driven model, and the data-driven model is trained based on a training data set including past feature contrasts, past displays of at least one interval, and past state measurement values. A data-driven model may receive a feature contrast and a display of at least one interval at an input layer and / or provide a state measurement value based on receiving a feature contrast and a display of at least one interval at the input layer. A data-driven model may include at least one machine learning architecture, particularly a deep learning architecture. For example, the data-driven model may be a neural network such as a CNN, particularly a 3D CNN, or a transformer. Further, the data-driven model may be a transformer network.

[0051] In one embodiment, at least two pattern features may be associated with at least two reflected images. Preferably, a first pattern feature of the at least two pattern features may be shown in a first reflected image of the at least two reflected images, and a second pattern feature of the at least two pattern features may be shown in a second reflected image of the at least two reflected images. A feature contrast of at least two pattern features including the first pattern feature and the second pattern feature may be determined. In particular, determining a feature contrast of at least two pattern features including the first pattern feature and the second pattern feature may include determining a first feature contrast including a first feature contrast value of the first pattern feature of the first reflected image of the at least two reflected images and a second feature contrast value of the second pattern feature of the second first reflected image of the at least two reflected images. Determining a state measurement value of a living body based on the display of the feature contrast and at least one interval may include determining a state measurement value based on a first feature contrast value of the first pattern feature of the first reflected image of the at least two reflected images and a second feature contrast value of the second pattern feature of the second first reflected image of the at least two reflected images.

[0052] In some embodiments, the state measurement values are determined using an algorithm that can implement a mechanical model or a data-driven model. The mechanical model preferably reflects physical phenomena in a mathematical form, including, for example, a first-principles model. The mechanical model may be composed of a set of differential equations that describe the interaction between the object and the coherent electromagnetic radiation, thereby resulting in specific state measurement values. In particular, the fluid flow and / or the shape of the object may be represented by the mechanical model. The mechanical model may be composed of the relationship between at least two reflected images, the display at a point in time, and the state measurement values. For this purpose, the relationship may be suitable for determining the time interval between at least two reflected images and determining the motion frequency corresponding to the pulsation (heart rate) per unit time. Based on the necessary input to the mechanical model that leads to the characteristic contrast determined from the pattern of at least two reflected images, the relevant state measurement values can be determined by the mechanical model. Including pulse wave analysis in the mechanical model may be suitable for determining blood pressure as another state measurement value. For this purpose, the velocity of the pulse wave can be determined. This information is included in the display regarding at least two reflected images and the interval. The absorption and reflection behavior of a part of the living body can indicate the absorption level included in at least one pattern feature of the reflected image. Oxygen-rich blood absorbs and therefore reflects light differently from oxygen-poor blood. Other state measurement values may be determined by developing the relationship between the pattern features and the state measurement values.

[0053] Preferably, the data-driven model is a parameterized classification model. The classification model can be composed of at least one machine learning architecture and model parameters. For example, the machine learning architecture can be one or more of, or composed of, linear regression, logistic regression, random forest, discriminant linear, non-linear classifier, support vector machine, naive bayes classification, nearest neighbor classification, neural network, convolutional neural network, generative adversarial network, support vector machine, or gradient boosting algorithm, etc. In the case of a neural network, the model can be a multi-scale neural network, or a recurrent neural network (RNN) such as a gated recurrent unit (GRU) recurrent neural network or a long short-term memory (LSTM) recurrent neural network, but is not limited thereto. The term "training", also denoted as "training" as used in this specification, is a broad term and is given the ordinary and customary meaning to those skilled in the art and is not limited to a special meaning or a customized meaning. This term may refer to, but is not limited to, the process of constructing a classification model, particularly the process of determining and / or updating the parameters of the classification model. The classification model may be at least partially data-driven. For example, the classification model may be based on experimental data such as data determined by irradiating a plurality of living bodies such as humans with light and recording reflected images. For example, training consists of using at least one training data set, and the training data set consists of, for example, reflected images of a plurality of humans with known state measurements. For example, when the neural network is a feed-forward neural network such as a CNN, the backpropagation algorithm can be applied to train the neural network. In the case of an RNN, the gradient descent algorithm or the backpropagation through time algorithm can be adopted for training purposes.

[0054] In another aspect, the present invention relates to a non-transitory computer-readable data medium storing a computer program including instructions for performing the steps of the method according to any of the above.

[0055] All of the disclosures and embodiments described in this specification are related to the above method, system, and computer-readable medium, and vice versa. Advantageously, the advantages provided by any of the embodiments and examples are equally applicable to all other embodiments and examples, and vice versa. The system is suitable for implementing the steps of the method.

[0056] "Computer-readable data medium" refers to any suitable data storage device or computer-readable memory storing one or more instruction sets (e.g., software) embodying any one or more of the methodologies or functions described in this specification. The instructions may also be present, in whole or at least in part, within the main memory and / or the processing device during execution thereof by a computer, main memory, and processing device, and may constitute a computer-readable storage medium. The instructions may further be transmitted or received via a network via a network interface device. Computer-readable data media include, for example, hard drives on servers, USB storage devices, CDs, DVDs, or Blu-ray discs. The computer program may include all the functions and data necessary for the execution of the method according to the present invention, or may provide an interface for processing a part of the method on a remote system, such as a cloud system. The term "non-transitory" means that the purpose of the data storage medium is to permanently store a computer program without particularly requiring a permanent power supply.

[0057] The input section is composed of one or more of a serial or parallel interface or port, USB, Centronics port, FireWire, HDMI (registered trademark), Ethernet, Bluetooth (registered trademark), RFID, Wi-Fi, USART, or SPI, or an analog interface or port such as one or more of an ADC or DAC, or a standardized interface or port to a further device.

[0058] The "processor" is a local processor consisting of a central processing unit (CPU) and / or a graphics processing unit (GPU) and / or an application-specific integrated circuit (ASIC) and / or a tensor processing unit (TPU) and / or a field-programmable gate array (FPGA). The processor may also be an interface to a remote computer system such as a cloud service. The processor may include a secure enclave processor (SEP), or may be a secure enclave processor (SEP). The SEP may be a secure circuit configured to process reflected images. A "secure circuit" is a circuit that protects separated internal resources from direct access by an external circuit. The processor may be an image signal processor (ISP), and may include a circuit suitable for processing reflected images, particularly reflected images received by the input section or reflected images generated by a camera. In some embodiments, the processor may be configured to receive reflected images from a camera.

[0059] The output section is one or more of a serial or parallel interface or port, USB, Centronics port, FireWire, HDMI, Ethernet, Bluetooth, RFID, Wi-Fi, USART, or SPI, or an analog interface or port such as one or more of an ADC or DAC, or one or more of a standardized interface or port to a further device. In some embodiments, the output section may be configured to output a signal indicating state-based operation.

[0060] A system for monitoring the state of a living body includes an input unit, a processor, and an output unit. The system for monitoring the state of a living body is suitable for implementing the steps of the method described in this specification. The system may be a monitoring device or integrated into a monitoring device. Examples of monitoring devices include mobile devices such as mobile phones like smartphones, smartwatches, tablets, laptops, headsets, particularly virtual reality headsets, glasses, particularly smart glasses. The monitoring device can be incorporated into machines, vehicles, access points, walls, furniture, etc.

[0061] The state control system may be suitable for receiving a state measurement value obtained by any of the previous embodiments of the method described herein and a threshold value. Such a state control system can be operated without contacting the living body. Therefore, the state of the living body can be monitored without being observed by the living body and without disturbing the living body. Furthermore, the hardware required to implement the system or method described in the present application is low-cost standard hardware that is easily available without major adjustment. The state control system includes an input unit for receiving the state measurement value and the threshold value, a processor for generating a signal indicating a state-based action based on a comparison between the state measurement value and the threshold value, and an output unit for outputting the signal indicating the state-based action. The state control system may be suitable for initiating a state-based action. The state control system may be a monitoring device or integrated into a monitoring device. Examples of monitoring devices include mobile devices such as mobile phones like smartphones, smartwatches, tablets, laptops, headsets, particularly virtual reality headsets, glasses, particularly smart glasses, or any device suitable for implementing the steps of the method described herein. The monitoring device can be incorporated into machines, vehicles, access points, walls, furniture, etc. The connection can be established via a wired or wireless connection such as Ethernet, USB, LAN, WLAN, etc. Examples of control devices include mobile devices such as smartphones, smartwatches, portable computers, tablets, board computers, etc. The state control system can be deployed in scenarios where a critical state of the living body can pose security problems for the living body and / or the surroundings. Examples of such scenarios can include any of the following: a living body controlling a device such as a vehicle or a machine.

[0062] State-based actions are the result of comparing state measurement values with threshold values. The state measurement values may be determined as described in the present specification. A signal indicating a state-based action may be generated based on the comparison. The signal is received by the state control system. The state-based actions may be assisting actions and / or interfering actions. In some embodiments, the signal may indicate doing nothing. When the state measurement value of the living body is below the threshold value, the living body should not be restricted. The assisting action gives advice to the living body. In some embodiments, the assisting action may provide advice to another living body as the living body for which the reflected image is generated. In an exemplary scenario such as monitoring a child, an animal, a person with health problems, an elderly person, a person with a disability, etc., a person responsible for taking care of the living body may be notified. The person responsible for taking care may be a parent, a caregiver, a doctor, a veterinarian, etc. The assisting action can be configured in any form that provides advice in a form suitable for the living body to recognize. Such advice may include, for example, advising the living body to take a rest, to drink, and / or to eat, and advising to change the conditions and / or the surroundings of the living body, such as voice input, temperature, visual input, air circulation, etc. Examples of forms of the assisting action include visual ones by a display function, auditory ones by sound generation, such as warning signals, or tangible ones by vibration. The interfering action can be configured in any form that adjusts the outside. This is advantageous when the state of the living body is critical and can be improved by performing the interfering action. Such adjustment may include, for example, adjusting the state and / or the surroundings of the living body (such as voice input, temperature, visual input, air circulation, etc.), restricting the time during which the living body can operate and / or control a mobile device, and / or performing a specific task. Depending on the scenario, previous advisory measures may be ignored by the living body that requires interfering measures. Furthermore, countermeasures for a very critical state are highly risky and may be more appropriately handled by interfering actions. Countermeasures for a slightly critical state may be adequately addressed by assisting actions.

[0063] In one embodiment, a signal indicating a state-based action based on a comparison between a state measurement value and a threshold value may be generated and the signal may be output.

[0064] The threshold value is a predetermined value indicating the minimum value of the state measurement value that is critical. In some embodiments, the threshold value may be stored locally in a memory. In other embodiments, the threshold value may be provided from an external source such as a cloud server. The threshold value may be received by an input unit. Since the threshold value can be selected based on the required certainty that the state of the living body is critical, the false positive rate can be minimized. This comes at the cost of identifying too many situations as critical, that is, resulting in a high false negative rate. Therefore, the threshold value is usually a compromise point between minimizing the false positive rate and keeping the false negative rate at a reasonable level. The threshold value can be selected such that the false negative rate and the false positive rate are equal or nearly equal. The threshold value may be suitable for comparison with the state measurement value. The threshold value may be a numerical value. In some embodiments, the threshold value may be a value on a scale. Such a scale can be in the range between two arbitrary values, preferably between 0 and an arbitrary value, most preferably between 0 and 1. In other embodiments, the threshold value may be a predetermined value of the state measurement value. The threshold value may be associated with a critical state measurement value. The threshold value may constitute a critical state measurement value.

[0065] In one embodiment, the threshold value can be specific to the living body. The threshold value can be a predetermined value indicating the minimum value of the state measurement value required to trigger a state-based action. To ensure safety, it is necessary to define the threshold value correctly. Factors such as age, gender, weight, physique, and genetics may cause the heart rate, blood pressure, aspiration level, etc. to differ from the median value. Thus, the threshold value can be adjusted according to the individual factors of the living body. The threshold value may be selected from a predetermined value according to the factors. In some embodiments, the threshold value may be determined based on data generated during the monitoring of the living body. For such purposes, algorithms such as data-driven algorithms or mechanical algorithms may be introduced.

[0066] In another embodiment, at least two reflected images may be generated. The at least two reflected images may be received from a camera. In particular, an image dataset consisting of at least two reflected images may be received from a camera. An image dataset consisting of at least two reflected images may be generated by a camera. The term "camera" is not particularly limited, but may refer to a device having at least one image sensor configured to record or capture spatially resolved one-dimensional, two-dimensional, or even three-dimensional optical data or information. The camera may be a digital camera. As an example, the camera may be composed of at least one camera chip such as at least one CCD chip and / or at least one CMOS chip configured to record an image. The camera may be at least one near-infrared camera and / or RGB camera, or may be composed of these. Further, in addition to at least one camera chip or imaging chip, the camera may include one or more additional elements, such as one or more lenses and the like, as additional elements.

[0067] In another embodiment, the living body may be illuminated with coherent electromagnetic radiation consisting of a pattern having at least one pattern feature. The living body may be illuminated using an illumination light source. Illumination can be achieved by using a projector or illumination light source that irradiates a light pattern onto a part of the living body. The illumination light source can be composed of at least one light source. The illumination light source may be composed of a plurality of light sources. The illumination light source is suitable for illuminating an object. The illumination light source may be composed of an artificial illumination light source, particularly at least one laser light source and / or at least one incandescent lamp and / or at least one semiconductor light source, such as at least one light-emitting diode, particularly an organic and / or inorganic light-emitting diode. As an example, the light emitted by the illumination light source can have a wavelength of 300 to 1100 nm, particularly 500 to 1100 nm. Additionally or alternatively, light in the infrared spectral range, such as light in the range of 780 nm to 3.0 μm, may be used. Specifically, light in a part of the near-infrared region where silicon photodiodes are applicable, particularly light in the range of 700 nm to 1100 nm, may be used. By using light in the near-infrared region, the light is not detected or is weakly detected by the human eye and is still detectable by a silicon sensor, particularly a standard silicon sensor. The illumination light source can be adapted to emit light of a single wavelength. In other embodiments, the illumination can be adapted to emit light of multiple wavelengths that enable additional measurements in other wavelength channels. The light source may be at least one multi-beam light source or may be composed of a multi-beam light source. For example, the light source may be composed of at least one laser light source and one or more diffractive optical elements (DOEs). The illumination light source may be composed of at least one line laser. The line laser may be adapted to send a laser line, such as a horizontal or vertical laser line, to the object. The illumination light source may be composed of a plurality of line lasers. For example, the illumination light source may be composed of at least two line lasers arranged such that the illumination pattern is composed of at least two parallel lines or intersecting lines.The illumination source may be composed of at least one light projector adapted to generate a cloud of points such that the illumination pattern can be composed of a plurality of point patterns. The illumination source may include at least one mask adapted to generate an illumination pattern from at least one light beam generated by the illumination source.

[0068] In one embodiment, the reflected image can be generated by a camera. Preferably, the camera may include a polarizer. The polarizer may be suitable for selecting the polarization of the reflected polarized coherent electromagnetic radiation from the living body. Depending on the penetration depth, the patterned coherent electromagnetic radiation may have different polarizations. By using a polarizer, the direct reflected light from the surface that interferes with the analysis of blood flow can be removed. Therefore, using a polarizer when acquiring the reflected image makes the analysis more robust.

[0069] In one embodiment, the reflected images can be separated by a fixed time interval or a varying time interval related to the imaging frequency.

[0070] In another embodiment, the imaging frequency may be at least twice the motion frequency associated with the expected periodic motion of the body fluid. The expected periodic motion of the body fluid may be associated with the expected periodic motion of the body fluid. The motion of the body fluid can be estimated based on the living body and its surroundings.

[0071] In another embodiment, the data-driven model can be used to determine the state measurement of the living body based on the feature contrast.

[0072] In some embodiments, the living body may be moving relative to the camera, and the movement may not correspond to the movement of the blood. In such cases, the image may be motion corrected based on motion tracking data related to the movement of the living body. The motion tracking data may be received. The motion tracking data may be composed of at least two contour images generated during the generation of at least two reflected images and / or a moving image generated during the generation of at least two reflected images. The contour image may refer to an image showing at least a part of the contour of the living body. The contour image may be suitable for identifying at least a part of the living body. For example, the contour image of at least a part of the living body may show the shape of a body part such as a hand, a face, etc. Additionally or alternatively, the motion tracking data may include a display of a region related to at least a part of the living body irradiated with patterned coherent electromagnetic radiation and a display of a shift between at least two different time points of a region related to at least a part of the living body irradiated with patterned coherent electromagnetic radiation. The motion tracking data can be used to identify the movement related to the living body during the generation of at least two reflected images. The measured value of the speed of the movement of the living body may be determined based on the display of at least one interval between the generation of at least two reflected images and the distance estimation value related to the motion tracking data. For example, the distance between two eyes in the image may be estimated. Using this estimation, the distance related to the movement of the living body can be derived. The correction coefficient may be determined based on the measured value of the speed of the movement of the living body. The correction coefficient can be a numerical value indicating the contribution of the movement of the living body to the characteristic contrast of at least two reflected images. By correcting the characteristic contrast according to the correction coefficient, the corrected characteristic contrast may be determined. The state measurement value may be determined based on the corrected characteristic contrast. Correcting the characteristic contrast according to the correction coefficient to obtain the corrected characteristic contrast may include connecting the correction coefficient and the characteristic contrast by mathematical operations such as multiplication, division, addition, division, etc. Further details regarding motion correction and / or motion tracking are described in U.S. Patent Application Publication No. 2022039679A1.

[0073] Such correction aims to correct the reflected image for movements not related to blood perfusion. This can be done by tracking the movement of the living body. By tracking the movement, a correction coefficient suitable for subtraction from the characteristic contrast of the reflected image can be determined. The greater the movement of the living body not related to blood perfusion, the greater the correction coefficient for subtraction. Also, the correction coefficient may vary depending on the part of the reflected image. By doing so, the non-uniform movement on the reflected image can be taken into account with the correction coefficient. As a result, the reflected image when the living body was moving can be utilized, which has the advantage that there is no need to discard the reflected image and no need to generate many reflected images. Consequently, the data required for generation, processing, and final storage is reduced, and as a result, energy consumption can be saved.

[0074] In one embodiment, the patterned coherent electromagnetic radiation may be associated with wavelengths of 900 nm to 1000 nm, and / or 1100 nm to 1200 nm. Preferably, the patterned coherent electromagnetic radiation may have wavelengths of 920 nm to 980 nm, and / or 1110 nm to 1190 nm. More preferably, the patterned coherent electromagnetic radiation may have wavelengths between 930 nm and 950 nm, and / or 1120 nm to 1180 nm. Within this range, sunlight has a bandgap and the light is invisible to humans. Therefore, when using the selected wavelength range, human attention does not become distracted and the method and system are insensitive to sunlight. As a result, the application of the present invention described in this specification is possible even outside a closed room with ambient light present. Thus, the present invention provides a movable and versatile measurement of the state of a living body.

[0075] In one embodiment, the patterned coherent electromagnetic radiation may be emitted from an illumination source. Further, a reflected image can be generated using a camera. The distance between the living body and the camera, and / or the distance between the living body and the illumination light source may be 5 cm to 150 cm. Preferably, the distance between the living body and the camera, and / or the distance between the living body and the illumination light source may be 15 cm to 100 cm. More preferably, the distance between the living body and the camera, and / or the distance between the living body and the illumination light source is 20 cm to 80 cm. By irradiating the living body with light and / or generating an image of the living body, non-contact data generation for evaluating the state of the living body becomes possible. Further, the above distances enable the use of low-cost and easily available hardware, for example, hardware that can be easily incorporated into mobile devices such as mobile phones, laptops, watches, etc. Therefore, the present invention provides an evaluation of the state of a living body that is low-cost, mobile, and widely applicable.

[0076] In some embodiments, at least one part of the living body preferably shown in at least two reflected images may correspond to the same part of the living body. A part of the living body may be suitable for reflecting at least one pattern feature. In particular, a part of the living body may include at least a part of the skin of the living body.

[0077] In some embodiments, the image set may include at least three reflected images, and the at least three reflected images may be generated in a time series having a fixed time interval related to the imaging frequency or a changing time interval related to the average imaging frequency.

[0078] In some embodiments, the step of outputting a state measurement value is - generating a signal indicating a state-based action based on a comparison between the state measurement value and a threshold associated with the important state measurement value; - outputting the signal indicating the state-based action; replaced by.

[0079] In particular, the threshold value may be specific to the living body. Depending on the individual life form, the threshold value may vary, which is similar to the state measurement value depending on the individual life form. Individual living organisms are, for example, humans, dogs, cats, elephants, pigs, cows, fish, frogs, etc. Due to different anatomical structures, state measurement values such as heart rate may be in different ranges. Usually, a small animal like a cat may have a higher heart rate than a large organism like a human or a whale. By considering the form of the individual organism, it may be possible to improve the determination of state-based actions. Thereby, it is possible to determine more accurate and appropriate state-based actions.

[0080] In some embodiments, at least one part of the living body may be shown in at least two reflected images and may correspond to the same part of the living body.

[0081] In some embodiments, the system may further include an illumination light source.

[0082] In some embodiments, the system may further include a camera.

[0083] In one embodiment, at least two reflected images may show the same part of the living body, and at least two reflected images may be generated while the same part of the living body is illuminated with patterned coherent electromagnetic radiation.

[0084] In some embodiments, the signal indicating the state-based action may be used in a conditional control system.

[0085] Due to the advantages provided by the present invention, the use of methods, systems, computer-readable storage media, and signals can be applied in various fields. Exemplary fields for application are the automotive context, the medical context, the entertainment business, the sports context, or other fields where a critical state of a living body can pose security problems for the living body and / or the surroundings. In the automotive field, the driver can potentially be a living body. By accurately monitoring the driver, the vehicle can be reliably controlled. This can reduce the risk of accidents. In the medical field, the method is particularly suitable for living bodies that may be problematic for devices that come into direct contact with the living body, such as watches, hair clippers, etc. For example, (newborn) babies, living bodies with large wounds, sleeping living bodies, etc. By applying the present invention in the context of the entertainment business and sports, excessive tension and / or stress of a living species can be prevented. In this case, the living being can also be a human. The method, signal, state measurement, and / or system can be configured and / or used in VR technology, particularly in VR headsets.

[0086] Further possible embodiments or alternative solutions of the present invention also include combinations of features described above or below with respect to the embodiments - not explicitly mentioned in this specification. Also, those skilled in the art can add individual or isolated aspects and features to the most basic form of the present invention.

[0087] It should be understood that the preferred embodiments of the present invention can also be any combination of the dependent claims or the above embodiments and their respective independent claims. Further embodiments, features, and advantages of the present invention will become apparent from the following description and the dependent claims, considered in conjunction with the accompanying drawings.

Brief Description of the Drawings

[0088]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

[0089] Description of Embodiments FIG. 1 is a flowchart showing an example of an embodiment of a method (100) for monitoring a living body.

[0090] In a first step, at least two reflected images are received (110). The first reflected image may be generated at time point t. The second reflected image may be generated at time point t + p, where p is the length of the cardiac cycle period related to the heart rate. Further, a display of the intervals between different time points at which the reflected images can be generated is received (110). In the case of one reflected image at point t and another reflected image at point t + p, the display of the interval is suitable for determining the interval length of p. The characteristic contrast at points t and t + p may be equal, where the term equal should be understood within the limits of measurement uncertainty and / or biological variability. Since blood perfusion can deviate according to various criteria, the state measurement values are based on biological variability. To correct for uncertainty and / or biological variability, a data-driven model can be trained. A mechanical model may be suitable for correcting uncertainty and / or biological variability. To determine the state measurement values, more than two reflected images may be received. In a time series image, the temporal change in blood perfusion is periodic due to the periodic heartbeat. Sandwiching a third reflected image between two images separated by only the length of one period in time is advantageous for ensuring the change in movement during the length of one period. For example, the reflected images can be generated or received using a virtual reality headset or a vehicle. In any scenario, monitoring of the living body may be required to ensure the safe use of virtual reality (VR) technology and the safe control of the vehicle with respect to the living body. In particular, in the context of driver monitoring, the security aspect is extended around the living body. For this purpose, there is no need to directly contact the living body, and the movement of the living body (preferably a human) is not restricted either.

[0091] Feature contrast is determined (120) from at least two pattern features. At least one pattern feature may be included in one of the at least two reflected images. The feature contrast can be determined for two of the at least two pattern features by dividing the standard deviation of the intensity of one pattern feature by the average intensity of one pattern feature, thereby determining at least two feature contrast values based on the at least two pattern features. To that end, the image can be divided into several parts. These parts can be of any shape, preferably a shape that can cover the entire image without overlapping. In an exemplary scenario, the reflected image can be divided into 7×7 pixel squares. For each pixel, the feature contrast of each pixel can be determined by moving the square across the reflected image. This is known as spatial laser speckle contrast imaging (LSCI). Another way to determine the feature contrast is dynamic LSCI. In dynamic LSCI, the shape can be moved in the time axis direction by determining the standard deviation and average intensity of the intensities of at least two images from different points in time. By doing so, for example, the average intensity is determined for at least some of the pixels of the first image and at least some of the pixels of the second image.

[0092] Since the feature contrast depends on the movement of the subject, blood perfusion may be observed in a single reflected image. Fast movement means that the contrast becomes low because the pattern features reflected by the moving object are blurred. In order to detect only the movement caused by blood perfusion, it is a prerequisite that the living body from which the reflected image is generated is not moving relative to the camera. If it is not possible to avoid movement not related to body fluids, the reflected image may be corrected. Determining the feature contrast, as described, is performed for all images. In an exemplary scenario of VR technology, since the relative movement of the living body with respect to the VR headset is only related to the movement inside the body such as blood perfusion, movement correction may not be necessary. Regarding the movement of the living body involving control of the vehicle, movement correction may be developed in order to ensure that all of the generated reflected images are composed only of the feature contrast resulting from the movement of body fluids such as blood perfusion. In some embodiments, since the driver is not always moving, movement correction is not necessary. Depending on the amount of movement of the driver, since a single reflected image may be captured within a few milliseconds (for example, 1 to 5 milliseconds), a reflected image may be generated even if the driver is not moving. Therefore, only a very short time of 1 second is sufficient for determining state measurement values such as heart rate.

[0093] In the next step, a state measurement value is determined based on the feature contrast (130). By determining a regular change in the feature contrast, the length of the period referring to the heartbeat can be recognized. If a first reflected image is generated at time t and a second reflected image is generated at time t + p, the associated interval is p. The change in blood perfusion may refer to the change in blood perfusion of at least a part of the reflected image. A part of the reflected image may refer to at least a part of the body of the living body at different times. The parts of at least two reflected images may constitute the same part of the body of the living body. In some embodiments, at least one or two or more state measurement values, such as heart rate, blood pressure and / or suction level, may be determined in order to provide a more meaningful result based on the combination of all different factors related to the state of the living body. Another state measurement value can be the presence or absence of sweat, preferably the amount of sweat. When generating a reflected image of a living body that has sweated on the skin, sweat may have a higher reflectivity than normal skin and may not transmit coherent electromagnetic radiation well. Therefore, there may be more radiation reflected from the non-moving particles. As a result, the intensity of the specular reflection, which is a characteristic part of the pattern directly reflected without passing through the skin, may increase. In this way, the amount of sweat can be determined by analyzing the ratio of specular reflection to reflection by scattering with moving particles such as blood.

[0094] In the last step, the state measurement value is output (140). The state measurement value may be output so as to be provided to an external system, another part of the system for monitoring the living body, or an external device. In other embodiments, the state measurement value may be transmitted to another part of the device via an interface. The state measurement value may be transmitted to the state control system.

[0095] In some embodiments, these steps starting from reflected image generation may be executed by an external device such as a cloud infrastructure. After at least some of the steps are completed, the resulting feature contrast and / or state measurement value may be output to the device that uses it.

[0096] FIG. 2 is a block diagram of an exemplary system (200) for monitoring a living body, including an input unit (210), a processor (220), and an output unit (230).

[0097] When the system is integrated into a device, the input unit (210) and / or the output unit (230) may be connected to other devices or other components. Such connections may be wired or wireless. The connection may be established via a wired connection or a wireless connection such as one of ethernet, USB, LAN, WLAN, etc.

[0098] The processor (220) is preferably configured to execute method steps as described with reference to FIG. 1 or FIG. 4. The input unit (210) may be configured as an input unit of the processor (220) for receiving a reflected image. The output unit (230) can be configured as an output of the processor (220). The reflected image may be generated by a camera in some embodiments.

[0099] Preferably, the processor (220) includes a logic circuit for processing the reflected image or a signal related to the reflected image. The processor (220) is configured to determine the characteristic contrast of the pattern shown in the reflected image. To determine the characteristic contrast of the pattern, the processor (220) is configured to calculate the standard deviation of the illumination divided by the average intensity. The resulting characteristic contrast value is generally in the range of 0 to 1. A characteristic contrast value of 1 indicates that there is no blur in the characteristics of the pattern, that is, there is no movement in the illuminated interior of the object. A characteristic contrast value of 0 indicates that the blur of the characteristics of the pattern due to the detected movement of the particles in the illuminated interior of the object, for example, red blood cells, is maximum. The processor (220) is further configured to determine a state measurement value based on the determined characteristic contrast. The processor (220) may provide the state measurement value to the providing unit (230).

[0100] For this purpose, the processor (220) has a neural network module consisting of a trained neural network. The neural network is trained to predict the state measurement value of the reflection image based on the determined feature contrast. Therefore, the neural network is trained to use the feature contrast determined by the processor as an input and provide the state measurement value as an output. The trained neural network may be, for example, a multi-scale neural network, or a recurrent neural network (RNN) such as a gated recurrent unit (GRU) recurrent neural network or a long short-term memory (LSTM) recurrent neural network. Alternatively, the neural network may be a convolutional neural network (CNN).

[0101] As an alternative or in addition to the trained neural network, the processor (220) may configure an algorithm that implements a mechanical model. The mechanical model is configured to determine the state measurement value based on the first principle assumption.

[0102] In some embodiments, the system may further include an illumination light source for illuminating the object. The object may be illuminated with light, preferably patterned IR light, while a plurality of reflection images are generated.

[0103] In some embodiments, the system can further include a memory for storing at least one threshold value.

[0104] Figure 3 shows a depiction (300) of the characteristic contrast determined from reflection images at different times. In particular, it is possible to represent a plurality of characteristic contrast values related to the living body's hand at different times. This depiction may be suitable for expressing blood perfusion at different times. This representation corresponds to a contrast map. As described in the context of FIG. 1, a single image can be evaluated to obtain a measurement value of blood perfusion by contrast. This can be represented by a blood perfusion map (300) as shown in FIG. 3. This map (300) can be colored according to the characteristic contrast, with high characteristic contrast values represented by dark colors and low characteristic contrast values represented by light colors. The spatial orientation of each pixel of the image corresponds to the spatial orientation of the pixel of the reflection image having the determined corresponding characteristic contrast.

[0105] As an example, in FIG. 3, the temporal change in blood perfusion of the hand (300) can be seen. By generating a plurality of reflection images at different time points, blood flow and heart rate can be visualized. (310) in FIG. 3 is a depiction of a contrast map at time point t showing a hand with reduced blood perfusion. Due to the activity of the heart that pumps blood into the blood vessels, blood perfusion increases to a maximum in the hand at time point t + p / 2 (320) when half of the cardiac cycle has elapsed. After reaching the maximum, blood perfusion decreases until it reaches the initial blood perfusion (330). The change in blood perfusion is visualized by a change in color, where a large amount of bright color corresponds to a large amount of blood perfusion with a low characteristic contrast value, and a large amount of dark color corresponds to a small amount of blood perfusion with a high characteristic contrast value. The elapsed time (340) between t and t + p / 2 is equal to the elapsed time (350) between t + p / 2 and t + p, where p corresponds to the length of the cycle. Both intervals have a length of p / 2. This is represented in FIG. 3 by arrows between points within the time. Another interval that sufficiently shows the time elapsed between at least two reflection images is the interval (360) of length p between the first reflection image (310) and the last reflection image (330). By recognizing the contrast change from the minimum blood perfusion to the maximum blood perfusion, the frequency of the heart rate can be determined using an interval of length p / 2. Alternatively, the interval of the entire cycle of length p can also be used to determine the frequency of the heart rate, which is also called the exercise frequency.

[0106] FIG. 4 is a flowchart of an exemplary embodiment of a method for monitoring a living body, further including the generation of a signal indicative of state-based behavior.

[0107] In a first step, at least two reflection images are received as described in the context of FIG. 1.

[0108] In the next step, the characteristic contrast of at least one pattern feature is determined as described in the context of FIG. 1.

[0109] In the next step, a state measurement value is determined based on the characteristic contrast as described in the context of FIG. 1.

[0110] In some embodiments, the state measurement value may not be output. Instead, the state measurement value may be used for comparison with a threshold value. In other embodiments, the state measurement value may be output to an external system such as a cloud infrastructure. In such an infrastructure, the following steps may be performed.

[0111] In the next step, a signal indicating state-based behavior based on the comparison between the state measurement value and the threshold value is generated. Such state-based behavior can be used to ensure safe applications and controls of devices such as VR headsets or vehicles. In the case of VR, not only advice to take a break or drink something is presented, but also ending the current application after a limited time, changing (or advising to change) the application used on the VR headset can be done. Similarly, in the vehicle scenario, advice such as taking a break, drinking something, changing the driver or route to be less burdensome is presented, and in addition, speed limits, turning lights and music on / off, adjusting the temperature, etc. may also be performed.

[0112] In the last step, a signal indicating state-based behavior based on the comparison between the state measurement value and the threshold value is output. This signal may be an input part of the state control system. The signal may be transmitted to the reflection image generation device. There, the signal may be used to operate the state control system.

[0113] Figure 5 shows an example of an embodiment of the aspect of the present invention in a vehicle (500). For this purpose, an embodiment of the system may be integrated into a vehicle such as an automobile and is suitable for implementing the steps of the method as described above. In the specific example shown in Figure 5, a human (510), specifically a driver, can control the vehicle by stepping on the accelerator to achieve, for example, a speed increase as displayed on the speedometer (520), or by operating the steering wheel (530). To ensure safe driving, the vehicle can be equipped with a system for monitoring the state of the living body as described in the context of Figure 2. The system for monitoring the state of the living body includes an input unit, a processor, and an output unit. The input unit and the output unit may be connected to the processor via a wired or wireless connection. The input unit may be an interface to, for example, a camera used to generate at least two reflected images. The output unit may be an interface to, for example, another processor for further processing the state measurement values. The state measurement values can be used in the state control system. In some embodiments, the state measurement values may be generated in the state control system. The system for monitoring the state of the living body may be configured in the state control system. Based on the comparison between the state measurement values and the threshold values, a signal indicating state-based behavior is generated. For this purpose, the state control system includes an input unit, a processor (570), and an output unit. The processor (570) of the state control system is suitable for generating a signal indicating state-based behavior. The processor may further be suitable for determining the state measurement values based on the feature contrast. The signal indicating state-based behavior may be suitable for operating a device unit such as a device, a device component, or a speaker to generate a warning signal in some cases. In some embodiments, the state control system may be integrated into the dashboard (540) and may be composed of a device, a device part, or a unit suitable for performing state-based behavior in the form of generating a warning signal using an illumination source (550), a camera (560), a processor (570), and a device for limiting the maximum speed (580a) and / or a speaker (580b) (580b).To determine the driver's fitness, the system can monitor state measurement values such as heart rate that indicate the state of the living body. To determine the heart rate, it may receive at least two reflected images and an indication of the interval. The reflected images can be generated using a camera (560) while the driver is illuminated with NIR light from an illumination light source (550). In an exemplary scenario, the driver may be illuminated for several seconds to generate a time series of reflected images and obtain at least one indication regarding the interval between different points in time at which the reflected images are generated. The time series can be generated, for example, at a specific imaging frequency of 5 frames per second. This frequency is large enough to meet the requirements of the Nyquist theorem. The driver may be illuminated with patterned coherent light such as a point cloud in the face region or another illuminable part of the bare skin. For this purpose, the illumination light source (550) may be arranged at a distance of 10 to 200 cm from the driver. For example, the illumination light source (550) may be built into the speedometer, steering wheel, or dashboard. The illuminated light is reflected by the driver's skin and recorded as a feature of the pattern of the reflected image. For this purpose, a camera (560) that can be built into the speedometer, steering wheel, or dashboard can also be used. The camera (560) can be equipped with an image sensor sensitive to infrared or near-infrared light. The image sensor can sense the reflected light and thereby generate a reflected image showing at least one pattern feature. Such a reflected image is received by the input unit and transmitted to the processor (570). The processor (570) takes the standard deviation σ of the average intensity as the average pattern feature intensity. It may be suitable for determining the characteristic contrast by dividing by. The characteristic contrast determined in this way includes information regarding the movement of the illuminated object. In the case of the skin, movement may occur due to blood perfusion. A low contrast corresponds to fast movement. Depending on the scenario, the driver may turn their head or make other movements while driving. Therefore, motion correction may be used to correct movements not related to blood perfusion. For this purpose, methods and devices are known in the art. By determining the characteristic contrast of at least two reflected images, the temporal change in blood perfusion can be tracked. By displaying at least one interval between at least two time points at which the reflected images are generated, the frequency of the pumping cycle of the heart can be determined by displaying at least two reflected images and at least one of the intervals, so the frequency of the heart rate can be determined. Further state measurements such as blood pressure and suction level can be associated with information on how the coherent electromagnetic radiation included in the reflected image and at least one interval interacts with the skin. To obtain better results, in the case of blood pressure, a reference measurement value or reference value can be used to adjust the value and improve the accuracy. To determine blood pressure and suction level, a data-driven model or a mechanical model can be introduced. Mechanical models are known in the art. Data-driven models may be trained according to a training data set. Such a training data set may be composed of a historical data set including reflected images and / or characteristic contrast values, the display of at least one interval corresponding to the reflected image, and state measurement values. Such a model is available to the processor and (570) can be used to determine the state measurement values. Since the state measurement values indicate the state of the living body, the state measurement values may be suitable for monitoring the driver. If the state measurement value exceeds a threshold value regarded as the critical value of the state measurement value, the risk of an unsafe drive may increase. As an example, a stressed driver (510) may be identified by a high heart rate and / or high blood pressure. This can be particularly dangerous during driving at high vehicle speeds.In one example, the threshold is selected as 110 as the critical value of the driver's heart rate. When the driver's state measurement value reaches 120 beats per minute, state-based actions may be triggered. In this example, the driver (510) may be driving at a speed of 180 km / h. The state control system can generate signals indicating state-based actions such as limiting the maximum speed to 130 km / h (580a) or generating a warning signal by a speaker (580b). Thus, as long as the state measurement value, especially the heart rate, exceeds the threshold selected for the driver's (510) heart rate, the driver (510) cannot increase the speed to a value greater than 130 km / h. For this purpose, the vehicle can apply the brakes until the speed becomes equal to or less than 130 km / h and disable acceleration to a speed greater than 130 km / h. The threshold is selected so that the driver (510) can reduce the influence of stress due to high speed and calm down.

[0114] Figure 6 shows an exemplary embodiment of a reflection image related to the contour of a living body (620, 640, 660, 680). The reflection image shows at least a part of the living body under illumination by patterned coherent electromagnetic radiation. For this purpose, the living body may be illuminated with patterned coherent electromagnetic radiation. The patterned coherent electromagnetic radiation may include at least one light beam. The at least one light beam may be projected onto the living body. The projection of the at least one light beam onto the living body may result in illuminating at least one continuous region with the coherent electromagnetic radiation. A reflection image may be generated from the light reflected from the living body illuminated by the at least one light beam. The at least one continuous region of the coherent electromagnetic radiation can be seen, for example, in the form of light spots in the reflection image. The light spots in the reflection image may be called pattern features. Figure 6 shows four examples of reflection images related to the contour of the living body (620, 640, 660, 680). 620 may refer to a reflection image generated while the hand of the living body is illuminated by patterned coherent electromagnetic radiation. In example 620, the pattern feature may be star-shaped and may be irregularly arranged. Also, the hand in 620 may be sketched to schematically show that a reflection image can be generated while the hand of the living body is illuminated by the patterned electromagnetic radiation. The reflection image may be independent of the contour of the hand of the living body. Similarly, 640 shows six circular light spots reflected by the hand of the living body. Subsequently, the pattern related to the patterned electromagnetic radiation may be a regular dot pattern having rectangular symmetry. In 660, the face of the living body is irradiated with patterned coherent electromagnetic radiation. The projection of the patterned coherent electromagnetic radiation may result in a regular arrangement of the pattern features, for example, a hexagonal arrangement. The pattern related to the patterned coherent electromagnetic radiation may be a hexagonal pattern. In 680, the face of the living body is illuminated with patterned coherent electromagnetic radiation. The projection of the patterned coherent electromagnetic radiation may result in an irregular arrangement of the pattern features.This can be achieved by randomly arranging the light beam emitters within the illumination source and / or by using different optical elements for the light beams associated with the patterned coherent electromagnetic radiation.

[0115] Figure 7 shows an application example of the method and system described in the present specification. The system as described in the context of FIG. 2 and the method as described in the context of FIG. 1 may be used for patient monitoring. In such an embodiment, patient 720 is illuminated by patterned coherent electromagnetic radiation emitted from illumination source 740. Preferably, the patient is kept quiet, such as being laid in a bed. The illumination light source may be composed of a VCSEL array and a DOE for replicating the light beam emitted by the VCSEL array. Thus, the illumination light source can emit a plurality of coherent light beams. The plurality of coherent light beams, also referred to as patterned coherent electromagnetic radiation, may be projected onto patient 720. Subsequently, patient 720 may be illuminated with a light pattern. The light may interact with the skin of patient 720. Speckles may be formed by the interaction between the coherent light and the skin of a living body such as patient 720. Two reflected images showing the patient under illumination by coherent electromagnetic radiation may be generated using camera 760 at two different points in time. The reflected images can show the projection of a plurality of light beams onto the skin of patient 720, resulting in a plurality of pattern features. Preferably, the number of pattern features may be equal to the number of light beams associated with the patterned coherent electromagnetic radiation. The reflected images may be associated with a timestamp. From the timestamp associated with the reflected images, a display of at least one interval between at least two different points in time may be derived. The display of the interval and the reflected images may be provided to processor 780 via an input section. The processor and the input section may refer to the processor and the input section as described in the context of FIG. 2. The processor may execute the method as described in the context of FIG. 1. The state measurement value may be output, as described in the context of FIG. 1, for example, via the output section of the system as described in the context of FIG. 2. In one example, the state measurement value may be provided to display 790. Display 790 may be suitable for displaying the state measurement value, particularly the value and / or unit associated with the state measurement value. Display 790 may be used for visual tracking of the state of patient 720.

[0116] As used in this specification, "determine" includes "initiate a determination, or cause a determination to be made", "generate" includes "initiate a generation, or cause a generation to be made", and "provide" includes "initiate a determination, generation, selection, transmission, or reception, or cause any of them to be initiated". "Initiate an action, or cause an action to be performed" includes any processing signal that triggers a computing device to perform each respective action.

[0117] The disclosures and aspects described in this specification relate to the above methods, systems, devices, and computer program elements, and vice versa. Advantageously, the advantages provided by any of the aspects and examples apply equally to all other aspects and examples, and vice versa.

[0118] In the claims and the specification, the term "consisting of" does not exclude other elements or steps. The indefinite articles "a" or "an" and the definite article "the" do not exclude a plurality. In particular, the indefinite article "a" or "an" may be replaced by "one or more", and the definite article "the" may be replaced by "one or more". A single element or other unit may perform the functions of a plurality of entities or items recited in the claims. The mere fact that certain means are recited in mutually different dependent claims does not indicate that a combination of these means cannot be used in advantageous embodiments.

Description of Reference Numerals

[0119] 100 Method for monitoring a living body 110 Receiving at least two reflected images 120 Determining a feature contrast 130 Determining a state measurement value 140 Outputting the state measurement value 210 Input unit 220 Processor 230 Output unit 300 Blood perfusion map 310 Contrast map at time t 320 Time t + p / 2 when half of the cardiac cycle has elapsed 330 Decrease in blood perfusion 340 Elapsed time between t and t + p / 2 350 Elapsed time between t + p / 2 and t + p 360 Interval of length p between the first and last reflected images 500 Vehicle 510 Human 520 Speedometer 530 Steering wheel 540 Dashboard 550 Lighting source 560 Camera 570 Processor 580a Form for limiting the maximum speed 580b Form for generating a warning signal using a speaker 620, 640, 660, 680 Outline of a living body 720 Patient 740 Lighting source 760 Camera 780 Processor 790 Display

Claims

**Claim 1** A method for monitoring the state of a living body, comprising: (a) receiving an image set including at least two reflected images generated at different times and a display of at least one interval between at least two different times, wherein the reflected images are generated while the living body is illuminated by patterned coherent electromagnetic radiation, and the reflected images show at least one pattern feature formed by illuminating at least a part of the living body with the patterned coherent electromagnetic radiation; and (b) determining a feature contrast of at least two pattern features; (c) determining a state measurement value of the living body based on the feature contrast and the display of the at least one interval; (d) outputting the state measurement value. A method comprising the above steps. **Claim 2** The method according to claim 1, wherein the image set includes at least three reflected images, and the at least three reflected images are generated in time series at a constant time interval related to the imaging frequency or a changing time interval related to the average imaging frequency. **Claim 3** The method according to claim 2, wherein the imaging frequency is at least twice the movement frequency related to the expected periodic movement of the body fluid. **Claim 4** The state measurement value of the living body based on the feature contrast and the display of the at least one interval is determined by providing the feature contrast of at least two pattern features and the display of at least one interval between the generation of at least two pattern images to a data-driven model, and the data-driven model is parameterized based on a training data set including historical feature contrasts, historical displays of at least one interval, and historical state measurement values. The method according to claim 1 or 2. **Claim 5** The method according to claim 1 or 2, wherein the reflected images are motion-corrected based on motion tracking data related to the movement of the living body. **Claim 6** The method according to claim 1 or 2, wherein the coherent electromagnetic radiation has a wavelength of 900 nm to 1000 nm. **Claim 7** The method according to claim 1 or 2, wherein the patterned coherent electromagnetic radiation is emitted from an illumination source, an image set including at least two reflected images is received from a camera, and the distance between the living body and the camera and / or the distance between the living body and the illumination source is 5 cm to 150 cm. **Claim 8** The method according to claim 1 or 2, wherein the state measurement value includes at least one of a heart rate, blood pressure, and / or a suction level.

9. The output of the state measurement value is - generating a signal indicating a state-based action based on a comparison between the state measurement value and a threshold value associated with an important state measurement value; - outputting a signal indicating the state-based action, The method according to claim 1 or 2, which is replaced by.

10. The method according to claim 9, wherein the threshold value is specific to the living body.

11. A non-transitory computer-readable data medium storing a computer program including instructions for executing the steps of the method according to any one of claims 1 to 3.

12. A system for monitoring the state of a living body, comprising (a) an input unit for receiving an image set including at least two reflected images generated at different times and a display of at least one interval between at least two different times, wherein the reflected images are generated while the living body is illuminated by patterned coherent electromagnetic radiation, and the reflected images show at least one pattern feature formed by illuminating at least a part of the living body with the patterned coherent electromagnetic radiation; (b) a processor, - for determining the feature contrast of at least two pattern features, and - for determining the state measurement value of the living body based on the feature contrast and the display of the at least one interval, a processor, and (c) an output unit for outputting the state measurement value A system comprising.

13. The system according to claim 12, further comprising a camera for generating at least two reflected images and / or an illumination source for illuminating the living body with the patterned coherent electromagnetic radiation.

14. A method of using a state measurement value obtained by the method according to any one of claims 1 to 3 in a state control system.

15. A state control system, comprising (a) an input unit for receiving a state measurement value obtained by the method according to any one of claims 1 to 3 and a threshold value associated with an important state measurement value; (b) a processor for generating a signal indicating a state-based action based on a comparison between the state measurement value and a threshold value associated with an important state measurement value; (c) an output unit for outputting a signal indicating the state-based action; A system including the same.

Images