Abnormal physical condition detection device and abnormal physical condition detection method

Abstract

This physical condition abnormality detection device (TK) comprises: an imaging unit (SE) that captures an image (GZ) of an occupant (JI) getting in a vehicle; a calculation unit (SS) that calculates the heart rate (SP) of the occupant (JI) on the basis of the image (GZ); a determination unit (HT) that determines whether the heart rate (SP) is stable; a correction unit (HS) that corrects, on the basis of the determination result, a heart rate threshold value (SPS) for detecting whether the occupant (JI) has a physical condition abnormality (TI) on the basis of the heart rate (SP) of the occupant (JI); and a detection unit (KS) that detects that the occupant (JI) has a physical condition abnormality (TI) when the heart rate (SP) is larger than the corrected heart rate threshold value (SPS).

Description

[Technical Field]

[0001] The present disclosure relates to an abnormal physical condition detection device and an abnormal physical condition detection method. [Background technology]

[0002] The driver physical condition monitor described in Patent Document 1, which has in common with the abnormal physical condition detection device of the present disclosure in terms of vehicle driving safety, detects whether the driver's physical condition is good or bad while driving a vehicle, and issues an alarm to the driver when the driver's physical condition (e.g., heart rate, pulse waveform) while driving the vehicle is not within a certain range from the driver's physical condition when the vehicle is stopped. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2002-104013 Summary of the Invention [Problem to be solved by the invention]

[0004] However, depending on the type of disease (e.g., epilepsy), for most patients, as shown in Fig. 15A, the heart rate when the patient is in an abnormal physical condition is clearly higher than the heart rate when the patient is in a normal physical condition, but for some patients, the heart rate when the patient is in an abnormal physical condition is not necessarily clearly higher than the heart rate when the patient is in a normal physical condition, as shown in Fig. 15B. As a result, the driver's physical condition monitor may not be able to detect that the driver has experienced an abnormal physical condition, even if the driver driving the vehicle is a patient with the latter type of disease and has experienced an abnormal physical condition, i.e., a sudden change in physical condition that cannot be predicted in advance.

[0005] The object of the present disclosure is to provide an abnormal physical condition detection device and an abnormal physical condition detection method that can prevent situations in which it is not possible to detect the fact that an occupant of a vehicle is experiencing an abnormal physical condition. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems, the physical condition abnormality detection device according to the present disclosure includes an imaging unit that captures an image of an occupant in a vehicle, a calculation unit that calculates the heart rate of the occupant based on the image, and calculated A determination unit that determines whether the heart rate is stable or not, and a heart rate threshold that determines whether the occupant is in an abnormal physical condition or not based on the heart rate of the occupant based on the result of the determination. The heart rate threshold when it is determined that the occupant's heart rate is unstable is set to a lower value than the heart rate threshold when it is determined that the occupant's heart rate is stable. The device includes a correction unit that performs correction, and a detection unit that detects that the occupant is in abnormal physical condition when the heart rate exceeds the corrected heart rate threshold. [Effects of the Invention]

[0007] The abnormal physical condition detection device according to the present disclosure can prevent a situation in which it is not possible to detect that an occupant of a vehicle is experiencing an abnormal physical condition. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 2 is a functional block diagram of the abnormal physical condition detection device TK of the first embodiment. [Figure 2] 1 shows the hardware configuration of an abnormal physical condition detection device TK of embodiment 1. [Figure 3] 4 is a flowchart showing the operation of the abnormal physical condition detection device TK of the first embodiment. [Figure 4] FIG. 10 is a functional block diagram of an abnormal physical condition detection device TK according to a second embodiment. [Figure 5] 10 shows the relationship between the occupant JI and the heart rate SP(T) in a normal state in the second embodiment. [Figure 6] 10 shows the relationship between the heart rate SP(T) of an occupant JI in a normal state and a weighting coefficient W in the second embodiment. [Figure 7] 10 is a flowchart showing the operation of the abnormal physical condition detection device TK of the second embodiment. [Figure 8] FIG. 10 is a functional block diagram of an abnormal physical condition detection device TK according to a third embodiment. [Figure 9] 10 shows the relationship between the occupant JI and the stable heart rate SP(T) under normal circumstances in the third embodiment. [Figure 10] 11 shows the relationship between the stable heart rate SP(T) of an occupant JI under normal circumstances and the weighting coefficient W in the third embodiment. [Figure 11] 10 is a flowchart showing the operation of the abnormal physical condition detection device TK of the third embodiment. [Figure 12] FIG. 10 is a functional block diagram of an abnormal physical condition detection device TK according to a fourth embodiment. [Figure 13] 10 shows the relationship between the heart rate SP of an occupant JI and the body movement TD of the occupant JI in the fourth embodiment. [Figure 14] 10 is a flowchart showing the operation of the abnormal physical condition detection device TK of the fourth embodiment. [Figure 15] Figure 15A shows the relationship between the heart rate when the physical condition is normal and the heart rate when the physical condition is abnormal (part 1). Figure 15B shows the relationship between the heart rate when the physical condition is normal and the heart rate when the physical condition is abnormal (part 2). DETAILED DESCRIPTION OF THE INVENTION

[0009] An embodiment of an abnormal physical condition detection device according to the present disclosure will be described.

[0010] Embodiment 1. First Embodiment The abnormal physical condition detection device TK of the first embodiment will be described.

[0011] <Functions of the First Embodiment> 1 is a functional block diagram of the abnormal physical condition detection device TK of embodiment 1. The functions of the abnormal physical condition detection device TK of embodiment 1 will be described below with reference to FIG.

[0012] In the following, it is assumed that "heart rate" includes "pulse rate."

[0013] The abnormal physical condition detection device TK of embodiment 1 includes, as shown in FIG. 1, an imaging unit SE, a calculation unit SS, a judgment unit HT, a correction unit HS, and a detection unit KS, in order to detect whether an occupant JI (particularly, an occupant JI driving the vehicle SR) on board a vehicle SR (not shown) is experiencing an abnormal physical condition TI.

[0014] An abnormal physical condition TI refers to, for example, a state in which an occupant JI suffers from epilepsy or the like.

[0015] The imaging unit SE corresponds to the "imaging unit", the calculation unit SS corresponds to the "calculation unit", the judgment unit HT corresponds to the "judgment unit", the correction unit HS corresponds to the "correction unit", and the detection unit KS corresponds to the "detection unit".

[0016] The image capturing unit SE captures an image GZ of the occupant JI. The image capturing unit SE is configured with an optical camera that captures the image GZ under light, such as one or more visible light cameras, or one or more infrared cameras that use a near-infrared light source and a filter that transmits only the infrared region.

[0017] The calculation unit SS calculates the heart rate SP (more precisely, the pulse rate MH (not shown)) of the occupant JI based on the image GZ captured by the imaging unit SE. The calculation unit SS performs the calculation using a conventionally known method, for example, using a change in luminance on the surface of a person's face that differs depending on the person's pulse rate MH. Therefore, more specifically, the calculation unit SS detects the face of the occupant JI from the image GZ, and calculates the pulse wave number MH of the occupant JI based on the change in luminance on the detected surface of the face of the occupant JI.

[0018] The calculation unit SS performs the above detection using a classifier based on a general algorithm that combines, for example, a Haar-Like detector with Adaboost or Casecade.

[0019] The calculation unit SS may acquire and calculate the pulse wave number MH using, for example, a biosensor instead of calculating it based on the image GZ. The biosensor may be installed inside the vehicle SR (for example, at the front of the passenger compartment, inside a seat belt, or inside a seat), or may be worn by the occupant JI in wearable form.

[0020] The determination unit HT determines whether the heart rate SP of the occupant JI calculated by the calculation unit SS is stable. The determination unit HT makes the above-mentioned determination, for example, by comparing the standard deviation value, variance value, etc. of the heart rate SP over a recent fixed period with a predetermined reference standard deviation value, reference variance value, etc.

[0021] The correction unit HS corrects the heart rate threshold SPS used by the detection unit KS to detect an abnormal physical condition TI when the determination unit HT determines that the heart rate SP of the occupant JI is unstable. More specifically, the correction unit HS reduces the heart rate threshold SPS from value A to value (AB) by subtracting an initially set correction value (e.g., value B) from the initially set heart rate threshold SPS (e.g., value A).

[0022] The detection unit KS detects whether the occupant JI has an abnormal physical condition TI based on whether the heart rate SP of the occupant JI calculated by the calculation unit SS exceeds the heart rate threshold SPS. The detection unit KS uses, as the heart rate threshold SPS, (1) an initially set heart rate threshold SPS (e.g., the above-mentioned value A) when the heart rate SP of the occupant JI is stable, and (2) a heart rate threshold SPS corrected by the correction unit HS (e.g., the above-mentioned value (AB)) when the heart rate SP of the occupant JI is unstable.

[0023] Hardware Configuration of First Embodiment FIG. 2 shows the hardware configuration of the abnormal physical condition detection device TK of the first embodiment.

[0024] In order to perform the above-mentioned functions, the abnormal physical condition detection device TK of embodiment 1 includes a processor P, a memory M, and a storage medium K, as shown in Figure 2, and may further include an input unit N and an output unit S as necessary.

[0025] The processor P is the well-known core of a computer, operating hardware according to software. The memory M is composed of, for example, a dynamic random access memory (DRAM) and a static random access memory (SRAM). The storage medium K is composed of, for example, a hard disk drive (HDD), a solid state drive (SSD), and a read-only memory (ROM). The storage medium K stores a program PR. The program PR is a set of instructions that defines the content of the processing to be executed by the processor P.

[0026] The input section N and output section S are composed of, for example, an input interface and an output interface for exchanging input signals NS and output signals SS related to the operation of the processor P with the outside of the abnormal physical condition detection device TK.

[0027] Regarding the relationship between the functions (shown in Figure 1) and the hardware configuration (shown in Figure 2) of the abnormal physical condition detection device TK, on ​​the hardware side, a processor P executes a program PR stored in a storage medium K using a memory M, and, as necessary, controls the operation of the input unit N and output unit S, thereby realizing the functions of each unit from the imaging unit SE to the detection unit KS (shown in Figure 1).

[0028] Operation of the First Embodiment 3 is a flowchart showing the operation of the abnormal physical condition detection device TK of embodiment 1. The operation of the abnormal physical condition detection device TK of embodiment 1 will be described below with reference to the flowchart of FIG.

[0029] In the following, for ease of explanation and understanding, it is assumed that the heart rate SP of the occupant JI of the vehicle SR is not stable.

[0030] Step ST11: The photographing unit SE (shown in FIG. 1) photographs an image GZ (shown in FIG. 1) of the occupant JI (shown in FIG. 1) riding in the vehicle SR.

[0031] Step ST12: The calculation unit SS (shown in FIG. 1) calculates the heart rate SP of the occupant JI based on the image GZ captured by the imaging unit SE.

[0032] Step ST13: The determination unit HT (shown in FIG. 1) uses the heart rate SP of the occupant JI calculated by the calculation unit SS to determine whether the heart rate SP of the occupant JI is stable. If it is determined that the heart rate SP of the occupant JI is stable, the process proceeds to step ST15. On the other hand, if it is determined that the heart rate SP of the occupant JI is not stable, the process proceeds to step ST14. Here, under the above assumptions, it is determined that the heart rate SP of the occupant JI is not stable, so the process proceeds to step ST14.

[0033] Step ST14: The correction unit HS (shown in FIG. 1) corrects the heart rate threshold SPS (shown in FIG. 1), which was initially the above-mentioned value A, to reduce it to the above-mentioned value (AB).

[0034] Step ST15: The detection unit KS (shown in FIG. 1) determines whether the heart rate SP of the occupant JI calculated by the calculation unit SS exceeds the heart rate threshold SPS, for example, the heart rate threshold SPS after correction by the correction unit HS (for example, the above-mentioned value (AB)). If it is determined that the heart rate SP of the occupant JI exceeds the heart rate threshold SPS, the process proceeds to step ST16. On the other hand, if it is determined that the heart rate SP of the occupant JI is below the heart rate threshold SPS, the process ends.

[0035] Step ST16: When the heart rate SP of the occupant JI exceeds the heart rate threshold SPS, the detection unit KS determines that the occupant JI has an abnormal physical condition TI, that is, detects that the occupant JI has an abnormal physical condition TI.

[0036] Effects of the First Embodiment As described above, in the abnormal physical condition detection device TK of embodiment 1, when the heart rate SP of the occupant JI is unstable, the detection unit KS detects whether or not the occupant JI has an abnormal physical condition TI based on whether or not the heart rate SP of the occupant JI exceeds the heart rate threshold value SPS corrected by the correction unit HS. As a result, even if the occupant JI is ill and the heart rate SP of the occupant JI is not the heart rate SP shown in FIG. 15A but the heart rate SP shown in FIG. 15B, it is possible to detect whether or not the occupant JI has an abnormal physical condition TI (the abnormal physical condition shown in FIG. 15B).

[0037] Embodiment 2. Second Embodiment The abnormal physical condition detection device TK of the second embodiment will be described.

[0038] The abnormal physical condition detection device TK of the second embodiment differs from the abnormal physical condition detection device TK of the first embodiment (shown in FIG. 1) in that it uses multiple individual heart rate thresholds SPS(K) instead of a single heart rate threshold SPS. More specifically, the abnormal physical condition detection device TK of the second embodiment focuses on the fact that the heart rates SPa, SPb, and SPc (not shown) of multiple occupants JIa, JIb, and JIc (not shown) are inherently different from one another, and more specifically, it focuses on the fact that, for example, some people have relatively high heart rates SP under normal circumstances, while others have relatively low heart rates SP under normal circumstances. Based on this focus, the abnormal physical condition detection device TK of the second embodiment uses individual heart rate thresholds SPS(K), i.e., individual heart rate thresholds SPS(Ka), SPS(Kb), and SPS(Kc), which are the heart rate thresholds SPS for each of the multiple occupants JIa, JIb, and JIc.

[0039] Here, "normal times" refers to, for example, (1) when occupant JI is not in the vehicle SR, (2) when occupant JI is not driving the vehicle SR, (3) when occupant JI is in the vehicle SR but is not experiencing any abnormalities in the occupant's health, or (4) when occupant JI is driving the vehicle SR but is not experiencing any abnormalities in the occupant's health.

[0040] The individual heart rate threshold SPS(Ka) is used as a criterion for detecting whether or not an abnormal physical condition TI has occurred in occupant JIa, the individual heart rate threshold SPS(Kb) is used as a criterion for detecting whether or not an abnormal physical condition TI has occurred in occupant JIb, and the individual heart rate threshold SPS(Kc) is used as a criterion for detecting whether or not an abnormal physical condition TI has occurred in occupant JIc.

[0041] <Functions of the Second Embodiment> 4 is a functional block diagram of the abnormal physical condition detection device TK of embodiment 2. The functions of the abnormal physical condition detection device TK of embodiment 2 will be described below with reference to FIG.

[0042] As shown in Figure 4, the abnormal physical condition detection device TK of embodiment 2 includes an imaging unit SE, a calculation unit SS, a judgment unit HT, a correction unit HS, and a detection unit KS, similar to the abnormal physical condition detection device TK of embodiment 1 (shown in Figure 1).

[0043] The functions of the imaging unit SE, calculation unit SS, determination unit HT, and detection unit KS of the second embodiment are basically the same as the functions of the imaging unit SE, calculation unit SS, determination unit HT, and detection unit KS of the first embodiment.

[0044] The correction unit HS of the second embodiment performs calculations by the correction unit HS of the first embodiment, for example, calculation of the value (AB) instead of calculation of the value (AB) by the correction unit HS of the first embodiment.

[0045] FIG. 5 shows the relationship between the occupant JI and the heart rate SP(T) in a normal state in the second embodiment.

[0046] FIG. 6 shows the relationship between the normal heart rate SP(T) of the occupant JI in Embodiment 2 and the weighting factor W.

[0047] The correction unit HS corrects the individual heart rate thresholds SPS(K) of the occupants JIa, JIb, and JIc in accordance with the magnitudes of the normal heart rates SP(T) of the occupants JIa, JIb, and JIc, respectively. More specifically, the correction unit HS sets the individual heart rate threshold SPS(K) such that the higher the normal heart rate SP(T) of the occupants JIa, JIb, and JIc, the higher the individual heart rate threshold SPS(K).

[0048] For example, as shown in FIG. 5, when the normal heart rate SP(T) of the occupant JIa is the value S1 and, as shown in FIG. 6, the weighting factor corresponding to the value S1 is 0.9, the correction unit HS corrects the individual heart rate threshold SPS(Ka) of the occupant JIa to be SPS(Ka)=A - B * 0.9.

[0049] For example, as shown in FIG. 5, when the normal heart rate SP(T) of the occupant JIb is the value U1 (U1 < S1) and, as shown in FIG. 6, the weighting factor corresponding to the value U1 is 1.1, the correction unit HS corrects the individual heart rate threshold SPS(Kb) of the occupant JIb to be SPS(Kb)=A - B * 1.1.

[0050] For example, as shown in FIG. 5, when the normal heart rate SP(T) of the occupant JIc is the value T1 (T1 < S1 and T1 > U1) and, as shown in FIG. 6, the weighting factor corresponding to the value T1 is 1.0, the correction unit HS corrects the individual heart rate threshold SPS(Kc) to be SPS(Kc)=A - B * 1.0.

[0051] The normal SP(T) of the occupants JIa, JIb, and JIc is, for example, the average value or the median value of the heart rates SP of the occupants JIa, JIb, and JIc.

[0052] The correction unit HS determines which of the occupants JIa, JIb, and JIc the occupant JI riding in the vehicle SR is, for example, by analyzing the face image of the occupant JI captured in the image GZ.

[0053] Hardware Configuration of Second Embodiment The abnormal physical condition detection device TK of the second embodiment has the same hardware configuration (shown in FIG. 2) as the abnormal physical condition detection device TK of the first embodiment.

[0054] <Operation of the Second Embodiment> 7 is a flowchart showing the operation of the abnormal physical condition detection device TK of embodiment 2. The operation of the abnormal physical condition detection device TK of embodiment 2 will be described below with reference to the flowchart of FIG.

[0055] In the following, for ease of explanation and understanding, it is assumed that the occupant JI aboard the vehicle SR is an occupant JIa.

[0056] Steps ST21 to ST23: Similar to steps ST11 to ST13 in embodiment 1, the photographing unit SE (shown in Figure 4) photographs an image GZ, the calculation unit SS (shown in Figure 4) calculates the heart rate SP of the occupant JI, and the judgment unit HT (shown in Figure 4) judges the stability of the heart rate SP of the occupant JI.

[0057] Step ST24: The correction unit HS (shown in FIG. 4) of the second embodiment differs from the correction unit HS (shown in FIG. 1) of the first embodiment in that, instead of using the heart rate threshold SPS of the first embodiment, the correction unit HS analyzes the image GZ of the occupant JI to recognize that the occupant JI is the occupant JIa. Based on the above recognition, the correction unit HS calculates the individual heart rate threshold SPS(Ka) of the occupant JIa by the correction described above with reference to FIGS. 5 and 6.

[0058] Step ST25: The detection unit KS (shown in FIG. 4) determines whether the heart rate SP of the occupant JI calculated by the calculation unit SS, i.e., the heart rate SP of the occupant JIa, exceeds the individual heart rate threshold SPS(Ka) of the occupant JIa after correction by the correction unit HS. If it is determined that the heart rate SP of the occupant JIa exceeds the individual heart rate threshold SPS(Ka) of the occupant JIa, the process proceeds to step ST26. On the other hand, if it is determined that the heart rate SP of the occupant JIa is below the heart rate threshold SPS(Ka) of the occupant JIa, the process ends.

[0059] Step ST26: When the heart rate SP of the occupant JIa exceeds the heart rate threshold SPS(Ka) of the occupant JIa, the detection unit KS determines that the occupant JIa has an abnormal physical condition TI, that is, detects that the occupant JIa has an abnormal physical condition TI.

[0060] Effects of the Second Embodiment As described above, in the abnormal physical condition detection device TK of the second embodiment, the correction unit HS corrects the individual heart rate thresholds SPS(K) of each of the occupants JIa, JIb, and JIc, i.e., the individual heart rate thresholds SPS(Ka), SPS(Kb), and SPS(Kc), in accordance with the magnitude of the normal heart rate SP(T) of each of the occupants JIa, JIb, and JIc. This makes it possible to detect whether an abnormal physical condition TI has occurred in the occupant JI, taking into consideration individual differences in whether the normal heart rate SP(T) of each of the occupants JIa, JIb, and JIc is high or low.

[0061] Embodiment 3. Third Embodiment The abnormal physical condition detection device TK of the third embodiment will be described.

[0062] The abnormal physical condition detection device TK of embodiment 3 differs from the abnormal physical condition detection device TK of embodiment 2 (shown in Figure 4) in that instead of using the normal heart rate SP(T), it uses the normal stable heart rate SP(T) to calculate the individual heart rate thresholds SPS(Ka), SPS(Kb), SPS(Kc) of occupants JIa, JIb, JIc.

[0063] Here, "stable" means that the heart rate SP, for example, changes relatively little over time.

[0064] <Functions of the Third Embodiment> 8 is a functional block diagram of the abnormal physical condition detection device TK of embodiment 3. The functions of the abnormal physical condition detection device TK of embodiment 3 will be described below with reference to FIG.

[0065] As shown in FIG. 8, the physical condition abnormality detection device TK of Embodiment 3 includes a photographing unit SE, a calculation unit SS, a determination unit HT, a correction unit HS, and a detection unit KS, similar to the physical condition abnormality detection device TK (illustrated in FIG. 4) of Embodiment 2.

[0066] The functions of the photographing unit SE, calculation unit SS, determination unit HT, and detection unit KS of Embodiment 3 are basically the same as those of the photographing unit SE, calculation unit SS, determination unit HT, and detection unit KS of Embodiment 2.

[0067] The correction unit HS of Embodiment 3 calculates the value (A - B*W) through the calculation by the correction unit HS of Embodiment 2, and performs the calculation based on the stable heart rate SP(T) in the normal state described above.

[0068] FIG. 9 shows the relationship between the occupant JI of Embodiment 3 and the stable heart rate SP(T) in the normal state.

[0069] FIG. 10 shows the relationship between the stable heart rate SP(T) in the normal state of the occupant JI of Embodiment 3 and the weighting coefficient W.

[0070] As shown in FIGS. 9 and 10, the correction unit HS of Embodiment 3 is different from the correction unit HS of Embodiment 2, and calculates the individual heart rate threshold SPS(K) based on the stable heart rate SP(T) in the normal state.

[0071] For example, as shown in FIG. 9, when the stable heart rate SP(T) of the occupant JIa in the normal state is the value S2, and as shown in FIG. 10, when the weighting coefficient corresponding to the value S2 is 0.9, the correction unit HS corrects the individual heart rate threshold SPS(Ka) of the occupant JIa to be A - B*0.9.

[0072] For example, as shown in FIG. 9, when the stable heart rate SP(T) of the occupant JIb in the normal state is the value U2 (U2 < S2), and as shown in FIG. 10, when the weighting coefficient corresponding to the value U2 is 1.1, the correction unit HS corrects the individual heart rate threshold SPS(Kb) of the occupant JIb to be A - B*1.1.

[0073] For example, as shown in FIG. 9, when the normal stable heart rate SP(T) of the occupant JIc is equal to the value T2 (T2<S2かつT2> U2), and as shown in FIG. 10, when the weighting coefficient corresponding to the value T2 is 1.0, the correction unit HS corrects the individual heart rate threshold value SPS(Kc) of the occupant JIc to be AB*1.0.

[0074] The correction unit HS determines whether the normal heart rate SP(T) is stable, for example, by comparing the standard deviation value, variance, etc. of the normal heart rate SP(T) of the occupant JI riding in the vehicle SR with predetermined reference standard deviation values, reference variance values, etc.

[0075] Hardware Configuration of Third Embodiment The abnormal physical condition detection device TK of the third embodiment has the same hardware configuration (shown in FIG. 2) as the abnormal physical condition detection device TK of the first embodiment.

[0076] <Operation of the Third Embodiment> 11 is a flowchart showing the operation of the abnormal physical condition detection device TK of embodiment 3. The operation of the abnormal physical condition detection device TK of embodiment 3 will be described below with reference to the flowchart of FIG.

[0077] In the following, for ease of explanation and understanding, it is assumed that the occupant JI aboard the vehicle SR is an occupant JIa.

[0078] Steps ST31 to ST33: Similar to steps ST21 to ST23 in embodiment 2, the photographing unit SE (shown in FIG. 8) photographs an image GZ, the calculation unit SS (shown in FIG. 8) calculates the heart rate SP of the occupant JI, and the judgment unit HT (shown in FIG. 8) judges the stability of the heart rate SP of the occupant JI.

[0079] Step ST34: The correction unit HS (shown in FIG. 8) of the third embodiment, like the correction unit HS (shown in FIG. 4) of the second embodiment, analyzes the image GZ of the occupant JI to recognize that the occupant JI is the occupant JIa. Based on the above recognition, the correction unit HS calculates the individual heart rate threshold SPS(Ka) of the occupant JIa by the correction described above with reference to FIGS. 9 and 10, instead of the correction described with reference to FIGS. 5 and 6 in the second embodiment.

[0080] Step ST35: The detection unit KS (shown in FIG. 8) determines whether the heart rate SP of the occupant JIa calculated by the calculation unit SS, i.e., the heart rate SP of the occupant JIa, exceeds the individual heart rate threshold SPS(Ka) of the occupant JIa after correction by the correction unit HS, similar to the detection unit KS in embodiment 2. If it is determined that the heart rate SP of the occupant JIa exceeds the individual heart rate threshold SPS(Ka) of the occupant JIa, the process proceeds to step ST36. On the other hand, if it is determined that the heart rate SP of the occupant JIa is below the heart rate threshold SPS(Ka) of the occupant JIa, the process ends.

[0081] Step ST36: Similar to the detection unit KS of embodiment 2, when the heart rate SP of the occupant JIa exceeds the individual heart rate threshold SPS(Ka) of the occupant JIa, the detection unit KS determines that the occupant JIa has an abnormal physical condition TI, i.e., detects that the occupant JIa has an abnormal physical condition TI.

[0082] Effects of the Third Embodiment As described above, in the abnormal physical condition detection device TK of embodiment 3, the correction unit HS calculates the individual heart rate thresholds SPS(K) of occupants JIa, JIb, and JIc, i.e., calculates the individual heart rate thresholds SPS(Ka), SPS(Kb), and SPS(Kc), based on the normal, stable heart rate SP(T) instead of the normal heart rate SP(T) as in embodiment 2. This makes it possible to set the individual heart rate thresholds SPS(Ka), SPS(Kb), and SPS(Kc) of occupants JIa, JIb, and JIc with higher accuracy.

[0083] Embodiment 4. Fourth Embodiment The abnormal physical condition detection device TK of the fourth embodiment will be described.

[0084] The abnormal physical condition detection device TK of embodiment 4 differs from the abnormal physical condition detection devices TK of embodiments 1 to 3 (shown in Figures 1, 4, and 8) in that the correction unit HS corrects the heart rate threshold SPS (step ST14 in embodiment 1, step ST24 in embodiment 2, and step ST34 in embodiment 3) taking into account whether or not a body movement TD is occurring in the occupant JI aboard the vehicle SR (particularly, the occupant JI driving the vehicle SR).

[0085] <Functions and Hardware Configuration of Fourth Embodiment> 12 is a functional block diagram of the abnormal physical condition detection device TK of embodiment 4. The functions of the abnormal physical condition detection device TK of embodiment 4 will be described below with reference to FIG.

[0086] As shown in Figure 12, the abnormal physical condition detection device TK of embodiment 4 includes an imaging unit SE, a calculation unit SS, a judgment unit HT, a correction unit HS, and a detection unit KS, similar to the abnormal physical condition detection device TK of embodiment 1 (shown in Figure 1).

[0087] As shown in FIG. 12, the abnormal physical condition detection device TK of the fourth embodiment differs from the abnormal physical condition detection device TK of the first embodiment in that it further includes a detection unit KC.

[0088] The detection unit KC corresponds to the "detection unit."

[0089] The detection unit KC detects whether or not a body movement TD is occurring in an occupant JI who is riding in or driving the vehicle SR, and whether or not the body movement TD of the occupant JI is below a predetermined reference body movement. The detection unit KC performs the detection by, for example, using a conventionally known general algorithm (e.g., OpenPose) to calculate the amount of movement of the occupant JI based on the skeleton of the occupant JI.

[0090] FIG. 13 shows the relationship between the heart rate SP of the occupant JI and the body movement TD of the occupant JI in the fourth embodiment.

[0091] As shown in Figure 13, when the occupant JI is in a vehicle SR and is experiencing body movements TD, i.e., when the occupant JI is swaying, for example, due to the vehicle SR traveling on a rough road, the heart rate SP of the occupant JI differs from when the occupant JI is not swaying and becomes disturbed.

[0092] The abnormal physical condition detection device TK of the fourth embodiment has the same hardware configuration (shown in FIG. 2) as the abnormal physical condition detection device TK of the first embodiment.

[0093] <Operation of the Fourth Embodiment> 14 is a flowchart showing the operation of the abnormal physical condition detection device TK of embodiment 4. The operation of the abnormal physical condition detection device TK of embodiment 4 will be described below with reference to the flowchart of FIG.

[0094] Steps ST41 to ST46: Similar to steps ST11 to ST16 in embodiment 1, steps ST21 to ST26 in embodiment 2, and steps ST31 to ST36 in embodiment 3, the image GZ of the occupant JI is captured by the capturing unit SE (shown in FIG. 12) and an abnormal physical condition TI is detected by the detecting unit KS (shown in FIG. 12).

[0095] Step ST47: The detection unit KC (shown in FIG. 12) detects whether or not the occupant JI who is riding in or driving the vehicle SR is experiencing a body movement TD, and whether or not the body movement TD of the occupant JI is below the above-mentioned reference body movement.

[0096] When it is detected that the occupant JI has a body movement TD and that the detected body movement TD of the occupant JI is not below the reference body movement, the process proceeds to end. On the other hand, when it is detected that the occupant JI has no body movement TD, or when it is detected that the occupant JI has a body movement TD and that the detected body movement TD of the occupant JI is below the reference body movement, the process proceeds to step ST42, and the operations of steps ST42 to ST46 are subsequently performed as in the first to third embodiments.

[0097] Effects of the Fourth Embodiment As described above, in the abnormal physical condition detection device TK of the fourth embodiment, the detection unit KC detects whether or not the occupant JI in the vehicle SR is experiencing a body movement TD and whether or not the body movement TD of the occupant JI is below the reference body movement. Only when it is detected that the body movement TD of the occupant JI is below the reference body movement is the subsequent process (the process of steps ST42 to ST46) performed. This allows the detection unit KS to detect whether or not the occupant JI is experiencing an abnormal physical condition TI based on the heart rate SP of the occupant JI, which is not affected by the body movement TD of the occupant JI, unlike the heart rate SP of the first to third embodiments.

[0098] The above-described embodiments may be combined with each other without departing from the spirit of the present disclosure, and components in each embodiment may be deleted or modified, or other components may be added, as appropriate. [Industrial Applicability]

[0099] The abnormal physical condition detection device according to the present disclosure can be used to prevent a situation in which it is not possible to detect that an occupant of a vehicle is experiencing an abnormal physical condition. [Explanation of symbols]

[0100] GZ image, HS correction unit, HT judgment unit, JI occupant, K storage medium, KC detection unit, KS detection unit, SE photography unit, SP heart rate, SPS heart rate threshold, SS calculation unit, TD body movement, TI physical condition abnormality, TK physical condition abnormality detection device.

Claims

1. an image capturing unit that captures images of occupants in the vehicle; a calculation unit that calculates a heart rate of the occupant based on the image; a determination unit that determines whether the calculated heart rate is stable; a correction unit that corrects a heart rate threshold for detecting whether the occupant is in an abnormal physical condition based on the heart rate of the occupant based on the result of the determination so that the heart rate threshold when it is determined that the occupant's heart rate is unstable becomes a lower value than the heart rate threshold when it is determined that the occupant's heart rate is stable; a detection unit that detects that the occupant is in an abnormal physical condition when the heart rate exceeds the corrected heart rate threshold; A physical condition abnormality detection device including:

2. The abnormal physical condition is epilepsy. The abnormal physical condition detection device according to claim 1.

3. The image is acquired by light. The abnormal physical condition detection device according to claim 1.

4. the determination unit determines whether the heart rate of the occupant is stable by comparing a variance value of the heart rate calculated by the calculation unit with a predetermined reference variance value. The abnormal physical condition detection device according to claim 1.

5. the correction unit corrects the heart rate threshold value in accordance with a normal heart rate of each occupant. The abnormal physical condition detection device according to claim 1.

6. the correction unit corrects the heart rate threshold value in accordance with a normal, stable heart rate for each occupant. The abnormal physical condition detection device according to claim 1.

7. The vehicle seat further includes a detection unit that detects whether or not the occupant is moving, the calculation unit calculates the heart rate of the occupant when the detection unit detects that the body movement is lower than a predetermined reference body movement. The abnormal physical condition detection device according to claim 1.

8. The photographing unit photographs images of the occupants of the vehicle, a calculation unit that calculates a heart rate of the occupant based on the image; a determination unit determining whether the calculated heart rate is stable; a correction unit corrects a heart rate threshold for detecting whether the occupant is in an abnormal physical condition based on the heart rate of the occupant based on the result of the determination so that the heart rate threshold when it is determined that the occupant's heart rate is unstable is lower than the heart rate threshold when it is determined that the occupant's heart rate is stable, a detection unit that detects that the occupant is in abnormal physical condition when the heart rate exceeds the corrected heart rate threshold; A method for detecting abnormal physical condition.

Images