Occupant detector

Abstract

To accurately detect if an infant is left in a cabin by discriminating various situations.SOLUTION: An occupant detector comprises: an acquisition unit that, on the basis of a reflected wave that is reflected by an occupant in the cabin from a transmitted wave transmitted toward the inside of a cabin of a vehicle, acquires point group information indicating, as a point group, one or more detection points representing the position of the occupant present in the cabin; an operation unit that counts the number of point groups that are set to a seating area in the cabin and appear in a first area of interest including seating faces of the seating area; and a determination unit that, when the number of point groups in the first area of interest is equal to or more than a first threshold, determines that the seating area includes an occupant who takes a posture lower than a seating posture in which the occupant sits up straight.SELECTED DRAWING: Figure 13

Description

[Technical Field]

[0001] FIELD An embodiment of the present invention relates to an occupant detection device. [Background technology]

[0002] In vehicle control systems and the like, there are technologies that detect whether an occupant has been left behind in the vehicle cabin based on data acquired by a radio wave sensor or the like installed in the vehicle cabin. For example, in the technology of Patent Document 1, when an occupant in the rear seat is detected by a radio wave sensor and the driver's seat belt is fastened or unfastened or a side door is opened or closed, it is determined that an occupant has been left behind in the vehicle after the driver has exited, and an alert is sent to those around. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-101415 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology of Patent Document 1 described above sets a detection area for detecting rear seat occupants in a uniform manner, and only determines whether what is detected in the rear seat is a person or an object such as luggage. If the person remaining in the vehicle after the driver has exited is an adult, it is not necessarily necessary to notify the surrounding area. In addition, the technology of Patent Document 1 described above has difficulty in correctly detecting, for example, an adult or a child who is lying down.

[0005] The present invention has been made in view of the above, and an object of the present invention is to provide an occupant detection device that can distinguish between various situations and detect with high accuracy whether a child has been left behind. [Means for solving the problem]

[0006] The occupant detection device of the embodiment includes an acquisition unit that acquires point cloud information that shows one or more detection points representing the positions of occupants present in the vehicle cabin as a point cloud based on a transmission wave transmitted toward the vehicle cabin and reflected by an occupant in the cabin; a calculation unit that counts the number of point clouds that appear in a first region of interest that is set for a seating area in the vehicle cabin and includes the seat surface of the seating area; and a determination unit that determines that an occupant who is sitting in a posture lower than a straight seated posture is present in the seating area if the number of point clouds in the first region of interest is equal to or greater than a first threshold.

[0007] The occupant detection device of the embodiment can distinguish between various situations and detect with high accuracy whether a child has been left behind. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a perspective side view showing an example of the configuration of the interior of a vehicle in which an occupant detection system according to an embodiment is installed. [Figure 2] FIG. 2 is a perspective top view showing an example of the configuration of the interior of a vehicle in which an occupant detection system according to an embodiment is installed. [Figure 3] FIG. 3 is a block diagram illustrating an example of a hardware configuration of the occupant detection system according to the embodiment. [Figure 4] FIG. 4 is a block diagram illustrating an example of a functional configuration of the occupant detection system according to the embodiment. [Figure 5] FIG. 5 is a schematic diagram showing the state of an occupant to be detected by the occupant detection system according to the embodiment. [Figure 6] FIG. 6 is a schematic diagram showing the state of an occupant to be detected by the occupant detection system according to the embodiment. [Figure 7] FIG. 7 is a schematic diagram showing the state of an occupant to be detected by the occupant detection system according to the embodiment. [Figure 8] FIG. 8 is a schematic diagram showing some examples of analysis results for a seat row by the occupant detection system according to the embodiment. [Figure 9]FIG. 9 is a schematic diagram showing some examples of analysis results for a seat row by the occupant detection system according to the embodiment. [Figure 10] FIG. 10 is a schematic diagram showing some examples of analysis results for a seat row by the occupant detection system according to the embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of various detection areas set in the occupant detection system according to the embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of various detection areas set in the occupant detection system according to the embodiment. [Figure 13] FIG. 13 is a diagram illustrating an example of various detection areas set in the occupant detection system according to the embodiment. [Figure 14] FIG. 14 is a diagram illustrating an example of various detection areas set in the occupant detection system according to the embodiment. [Figure 15] FIG. 15 is a flowchart illustrating an example of a procedure of an occupant detection process performed by the occupant detection device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Exemplary embodiments of the present invention are disclosed below. The configurations of the embodiments described below, as well as the actions, results, and advantages brought about by the configurations, are merely examples. The present invention can be realized using configurations other than those disclosed in the following embodiments, and it is possible to obtain at least one of the various advantages and derivative advantages based on the basic configurations.

[0010] (Configuration example of an occupant detection system) Fig. 1 is a perspective side view showing an example of the configuration inside a passenger compartment R of a vehicle C in which an occupant detection system 1 according to an embodiment is installed. Fig. 2 is a perspective top view showing an example of the configuration inside a rear part of the passenger compartment R of a vehicle C in which an occupant detection system 1 according to an embodiment is installed.

[0011] In the figure, the +X direction is the direction from the center of the left-right direction of vehicle C toward the right, and the -X direction is the direction from the center of the left-right direction of vehicle C toward the left. The left-right direction of vehicle C is the direction as seen from the driver's seat. The +Y direction is the direction from the center of the front-rear direction of vehicle C toward the rear, and the -Y direction is the direction from the center of the front-rear direction of vehicle C toward the front. The +Z direction is the direction downward from the ceiling 5 of vehicle C.

[0012] The vehicle C may be, for example, an automobile powered by an internal combustion engine or a motor, or a hybrid vehicle powered by both of these.

[0013] As shown in FIGS. 1 and 2, the vehicle C of this embodiment is a so-called three-row seat vehicle, and is provided with, from the front of the vehicle C, seat rows SR1, SR2, and SR3 in that order.

[0014] Seat row SR1 includes a driver's seat and a passenger seat. Seat rows SR2 and SR3 include multiple seats adjacent to each other. In the example of FIG. 2, seat row SR2 includes three seats adjacent to each other, with an occupant P seated in each seat on either side of the center seat. Seat row SR3 includes two seats adjacent to each other, with an occupant P seated in the seat on the right side of vehicle C.

[0015] The occupant detection system 1 has a function of detecting an occupant P present in the vehicle compartment R and the position of the occupant P. The detection result of the occupant P by the occupant detection system 1 is used, for example, to detect a child left behind in the vehicle compartment R, or as a seat belt reminder in a moving vehicle C.

[0016] The occupant detection system 1 includes a sensor device 2 and an occupant detection device 3.

[0017] The sensor device 2 is installed, for example, on the ceiling 5 near the center of the vehicle C in the ±X directions, transmits a transmission wave toward the interior of the vehicle compartment R, and receives a reflected wave generated when the transmission wave is reflected by an object present in the vehicle compartment R. The sensor device 2 of the embodiment is installed behind the seat backs of the seat row SR1 when viewed from the ceiling 5. The occupant detection device 3 is installed, for example, in the dashboard, and is connected to the sensor device 2 via a network such as a CAN (Controller Area Network).

[0018] The installation positions of the sensor device 2 and the occupant detection device 3 are not limited to those described above. Also, the number of sensor devices 2 installed in the vehicle interior R is not limited to the example shown in FIG.

[0019] FIG. 3 is a block diagram showing an example of a hardware configuration of the occupant detection system 1 according to the embodiment.

[0020] As shown in FIG. 3, the sensor device 2 included in the occupant detection system 1 includes a transmitter 21, a receiver 22, a sensor ECU (Electronic Control Unit) 23, and an input / output unit 24.

[0021] The transmitter 21 transmits (irradiates) an electromagnetic wave of a predetermined frequency, such as 60 GHz to 65 GHz, as a transmission wave into the vehicle interior R. The receiver 22 receives a reflected wave generated when the transmission wave is reflected by an object present in the vehicle interior R, and generates an electrical signal indicating the intensity of the reflected wave. The transmitter 21 and the receiver 22 may be configured using, for example, an oscillator circuit, a piezoelectric element, an AD converter, an amplifier, a filter circuit, etc. The transmitter 21 and the receiver 22 may be configured separately from each other, or may be configured integrally.

[0022] The sensor ECU 23 is a microcontroller configured using a CPU (Central Processing unit), memory, etc., and performs processes related to control of the transmitter 21 and receiver 22, generation of data based on the reflected waves received by the receiver 22, etc.

[0023] The input / output unit 24 is an interface device that establishes communication between the occupant detection device 3 and other devices in accordance with a predetermined standard such as CAN.

[0024] As described above, the sensor device 2 has a configuration in which a radio wave sensor including, for example, the transmitter 21 and the receiver 22 is integrated with the sensor ECU 23 that generates data based on transmitted and received waves obtained from the radio wave sensor.

[0025] The occupant detection device 3 included in the occupant detection system 1 is an ECU or the like including a CPU 31, a memory 32, and an input / output unit 33.

[0026] The CPU 31 executes various arithmetic processes in accordance with programs stored in, for example, the memory 32. The memory 32 may be configured using a volatile memory and a non-volatile memory. The memory 32 stores programs that cause the CPU 31 to execute various processes for realizing the functions of the occupant detection device 3, setting data, data acquired from the sensor device 2, data generated by the CPU 31, and the like.

[0027] The input / output unit 33 is an interface device that establishes communication between the sensor device 2 and other devices in accordance with a predetermined standard such as CAN.

[0028] It should be noted that the hardware configuration shown in FIG. 3 is an example, and the hardware configuration of the occupant detection system 1 is not limited to the above.

[0029] FIG. 4 is a block diagram showing an example of a functional configuration of the occupant detection system 1 according to the embodiment.

[0030] As shown in FIG. 4, the sensor device 2 included in the occupant detection system 1 includes a wave transmitting / receiving unit 201 and a generating unit 202 as functional units.

[0031] The wave transmitting / receiving unit 201 transmits a transmission wave such as an electromagnetic wave into the vehicle interior R, receives a reflected wave of the transmission wave reflected by an object present in the vehicle interior R, and generates an electrical signal indicating the intensity of the reflected wave.

[0032] The generation unit 202 generates point cloud information based on the electrical signal generated by the wave transmitting and receiving unit 201. The point cloud information is a point cloud showing one or more detection points representing the position of the occupant P present in the vehicle cabin R on a three-dimensional map corresponding to the space within the vehicle cabin R. The three-dimensional map corresponding to the space within the vehicle cabin R may be, for example, a voxel map. In this case, the detection points representing the occupant P may be voxels within the voxel map.

[0033] Here, the electrical signal generated by the wave transmitting / receiving unit 201 includes not only the occupant P in the vehicle compartment R, but also waves reflected by components of the vehicle C such as the vehicle body and seats, and luggage placed on the seats, etc. Among these, the components and luggage, etc. of the vehicle C maintain a substantially stationary state, or fluctuate in a manner highly correlated with the movement of the vehicle body as the vehicle body sways. Therefore, the components and luggage, etc. of the vehicle C also fluctuate in a manner highly correlated with the sensor device 2 installed, for example, on the ceiling 5 of the vehicle C. On the other hand, the occupant P in the vehicle compartment R is usually seated and making some kind of spontaneous movement.

[0034] Therefore, the point cloud information can be obtained by extracting, from the electrical signals generated by the wave transmitting and receiving unit 201, reflecting objects whose movements are not synchronized with the movement of the vehicle body as detection points representing the occupant P. As an example, the detection points representing the occupant P can be points where the amount of change in the intensity of the reflected waves per unit time caused by movements not synchronized with the movement of the vehicle body is greater than a predetermined threshold. However, the type of points to be set as detection points representing the occupant P can be determined appropriately depending on the function of the sensor device 2 to be used, etc.

[0035] The occupant detection device 3 included in the occupant detection system 1 includes, as functional units, an acquisition unit 301, a calculation unit 302, a determination unit 303, an output unit 304, and a storage unit 305. These functional units may be configured, for example, by cooperation between hardware and a program as illustrated in Fig. 3. Furthermore, some or all of these functional units may be configured by dedicated hardware (circuits, etc.) such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array).

[0036] The acquisition unit 301 acquires point cloud information generated by the sensor device 2.

[0037] The calculation unit 302 counts the number of each point cloud included in the point cloud information for each appearance area. In the 3D map in which the point clouds are arranged, corresponding to the space within the vehicle cabin R, multiple detection areas are set corresponding to seating areas, which are spaces above multiple seats within the vehicle cabin R. The multiple detection areas include, for example, various detection areas used to detect occupants who are seated or lying down on a specific seat, various detection areas used to determine the physique of a detected occupant to determine whether they are an adult or a child, etc. The calculation unit 302 counts the number of point clouds in these detection areas and calculates the ratio of the number of counted point clouds.

[0038] Based on the calculation result of the calculation unit 302, the determination unit 303 determines whether or not there is an occupant in a seated or lying position in a predetermined seat, and whether the detected occupant is an adult or a child.

[0039] More specifically, the determination unit 303 makes the determination based on thresholds set for various detection areas used to detect an occupant in a predetermined posture on a predetermined seat and various detection areas used to determine the physique of the detected occupant. In other words, if the number of point clouds or the ratio counted by the calculation unit 302 is equal to or greater than the corresponding threshold, the determination unit 303 determines that an adult or child is seated or lying down on the predetermined seat.

[0040] When the determination unit 303 determines that a child has been left behind in the vehicle compartment R, the output unit 304 outputs an alarm to, for example, the alarm device 4. The alarm device 4 is, for example, a buzzer or the like provided in the vehicle C, and issues the alarm when the alarm is output from the output unit 304. The alarm issued by the alarm device 4 may be, for example, an alarm sound or an announcement such as a warning.

[0041] The storage unit 305 stores, for example, programs and control parameters that realize various functions of the occupant detection device 3. The storage unit 305 also stores point cloud information acquired by the occupant detection device 3 from the sensor device 2, as well as the number of point clouds in each detection area and determination results such as the presence or absence of an occupant P. The storage unit 305 also stores a three-dimensional map corresponding to the space within the vehicle interior R, and information such as the sizes and arrangements of various detection areas within the three-dimensional map.

[0042] (Determination method for occupant detection system) Next, a determination method by the occupant detection system 1 of the embodiment will be described with reference to Figures 5 to 14. In the following example, a case will be described in which the presence or absence of an occupant P present mainly in seat row SR2 among seat rows SR1 to SR3 is determined.

[0043] 5 to 7 show examples in which occupants P, Pc are in various positions in seat row SR2. Figures 5 to 7 are schematic diagrams showing the states of occupants P, Pc to be detected by occupant detection system 1 according to the embodiment.

[0044] As shown in Figure 5, when an adult occupant P and a child occupant Pc are seated in seat row SR2, there is a difference between the occupants P and Pc in terms of the height of their heads, overall physique, etc. In other words, the adult occupant P has a higher head position and a larger physique than the child occupant Pc.

[0045] 6 and 7, when an adult occupant P and a child occupant Pc are lying down in seat row SR2, there is also a difference between the height positions of the upward-facing body parts and the overall physiques of these occupants P, Pc. That is, in the example of Figures 6 and 7, the position of the left arm of the adult occupant P facing upward is higher than that of the child occupant Pc, and because the occupant P is larger in physique, the area of ​​his or her entire body on seat row SR2 is also larger.

[0046] Next, Fig. 8 to Fig. 10 show how the occupants P, Pc shown in Fig. 5 to Fig. 7 can be detected by the occupant detection system 1. Fig. 8 to Fig. 10 are schematic diagrams showing some examples of analysis results in seat row SR2 by the occupant detection system 1 according to the embodiment.

[0047] 8 to 10(a) are overhead views of three-dimensional maps corresponding to the space inside the vehicle compartment R, with the horizontal axis representing the left-right direction (±X direction) of the vehicle C and the vertical axis representing the front-to-rear direction (±Y direction) of the vehicle C. Also, in FIGS. 8 to 10(a), the positions corresponding to the seats in the seat rows SR1 to SR3 are shown by rectangular frames.

[0048] 8 to 10(b) are rear views of the 3D maps corresponding to the space within the vehicle compartment R, showing the seat row SR2 as viewed from behind. The horizontal axis of FIGS. 8 to 10(b) indicates the left-right direction (±X direction) of the vehicle C, and the vertical axis indicates the position in the height direction (±Z direction). In addition, in FIGS. 8 to 10(b), the positions corresponding to the left and right seats SR(L) and SR(R) of the seat row SR2 and the center seat SR2(C) are indicated by rectangular frames.

[0049] 8 shows an example of the analysis results of the occupant detection system 1 when an adult occupant P is seated in the rightmost seat SR2(R) of the seat row SR2. As shown in FIG. 8, in this case, a point cloud PP representing the occupant P appears in a predetermined area above the seat SR2(R), for example.

[0050] Fig. 9 shows an example of the analysis results by the occupant detection system 1 when an infant occupant Pc is seated in the rightmost seat SR2(R) of the seat row SR2. In the example shown in Fig. 9, the point cloud PP representing the occupant Pc appears in a predetermined area above the seat SR2(R), just like in Fig. 8 described above. However, the range in which the point cloud PP appears due to an infant who is smaller than an adult is smaller than the range in which the point cloud PP appears in Fig. 8 described above, and the height position of the point cloud PP appearing at the highest position is also lower than the position of the highest point cloud PP in Fig. 8.

[0051] 10 shows an example of the analysis results of the occupant detection system 1 when an adult occupant P is lying down and straddling multiple seats SR2(L), SR2(C), and SR2(R) in the seat row SR2. As shown in FIG. 10, in this case, a point cloud PP representing the occupant P appears in the area on the seat surface that covers the entirety of the seats SR2(L), SR2(C), and SR2(R).

[0052] Comparing the appearance region of the point cloud PP in Fig. 10 with the appearance region of the point cloud PP in Fig. 8 described above, in the example of Fig. 10, the occupant P is lying down, so the appearance region of the point cloud PP in the left-right direction (±X direction) is wider than in Fig. 8. On the other hand, the appearance region of the point cloud PP in the up-down direction (±Z direction) is narrower than in Fig. 8, and the height position of the point cloud PP appearing at the highest position is also lower than the height position of the point cloud PP at the highest position in Fig. 8. Furthermore, while the point cloud PP in Fig. 8 was located above the seat surface of seat row SR2, some of the point cloud PP in Fig. 10 appear in contact with the seat surface of seat row SR2.

[0053] As described above, in the occupant detection system 1 of the embodiment, multiple detection areas are set to detect occupants P and Pc in these various states, based on the differences in the appearance area of ​​the point cloud PP that arise due to the posture of the occupant P, etc., and the differences in physique between adult and child occupants P and Pc.

[0054] 11 to 14 are diagrams showing examples of various detection regions RSs, RSa, RSc, RRs, RRa, and RRc set in the occupant detection system 1 according to the embodiment.

[0055] 11 to 14, like (b) of FIGS. 8 to 10 described above, are rear views of three-dimensional maps corresponding to the space within vehicle compartment R, showing seat row SR2 as viewed from behind. The horizontal axis of FIGS. 11 to 14 indicates the position in the left-right direction (±X direction) of vehicle C, and the vertical axis indicates the position in the height direction (±Z direction). In addition, in FIGS. 11 to 14, the positions corresponding to each seat in seat rows SR1 to SR3 are indicated by rectangular frames.

[0056] Fig. 11 shows an example of a detection area RSs that is set in the occupant detection system 1 of the embodiment and is used to detect seated occupants P, Pc. As shown in Fig. 11, the detection area RSs is set in a predetermined area above the seat surfaces of the multiple seats SR2(L), SR2(C), and SR2(R) in the seat row SR2, assuming that the heads of the occupants P, Pc will reach a certain height.

[0057] When determining whether or not an occupant P, Pc in a seated position is in, for example, one of seats SR2(L), SR2(C), or SR2(R) in seat row SR2, the calculation unit 302 of the occupant detection device 3 counts the number of point clouds that appear in the detection area RSs among the point clouds included in the point cloud information acquired by the acquisition unit 301 from the sensor device 2.

[0058] The determination unit 303 of the occupant detection device 3 determines whether the number of point clouds in the detection area RSs counted by the calculation unit 302 is equal to or greater than a predetermined threshold. Hereinafter, this threshold will be referred to as the third threshold. If the number of point clouds in the detection area RSs is equal to or greater than the third threshold, the determination unit 303 determines that an adult or child occupant P, Pc is seated in any of the seats SR2(L), SR2(C), and SR2(R) corresponding to the appearance positions of those point clouds. On the other hand, if the number of point clouds in the detection area RSs is less than the third threshold, the determination unit 303 determines that an occupant P, Pc is not seated in any of the seats SR2(L), SR2(C), and SR2(R).

[0059] Fig. 12 shows an example of detection areas RSa, RSc set in the occupant detection system 1 of the embodiment and used to determine the physical constitution of occupants P, Pc who are seated. The physical constitution of the occupants P, Pc is determined to be present in any of the seats SR2(L), SR2(C), and SR2(R) in which the occupants P, Pc are seated, for example, based on the determination result of Fig. 11. Fig. 12 shows detection areas RSa, RSc used to determine the physical constitution of occupants P, Pc seated in seat SR2(R).

[0060] As shown in Fig. 12, the detection areas RSa and RSc are set so that almost the entire area is included in the detection area RSs shown in Fig. 11. The widths of the detection areas RSa and RSc in the left-right direction (±X directions) are smaller than the above-mentioned detection area RSs, for example, to match the width of the corresponding seat SR2(R). The widths of the detection area RSa in the up-down direction (±Z directions) are smaller in the upward direction than the above-mentioned detection area RSs. The widths of the detection area RSc in the up-down direction (±Z directions) are smaller in the downward direction than the above-mentioned detection area RSs, for example.

[0061] Of the detection areas RSa and RSc, the detection area RSa is set to correspond to an adult occupant P. As an area where a point cloud representing the adult occupant P may appear, the detection area RSa is set to be at a position corresponding to the seat SR2(R), with its lower end above the seat surface of the seat SR2(R) and its upper end at a height position close to the ceiling 5 of the vehicle C.

[0062] Of the detection areas RSa and RSc, the detection area RSc is smaller than the above-mentioned detection area RSa and is set to correspond to the child occupant Pc. As an area where a point cloud indicating the child occupant Pc may appear, the detection area RSc is set to be in a position corresponding to the seat SR2(R), with its lower end above the seat surface of the seat SR2(R) at a position lower than the lower end of the detection area RSa and its upper end lower than the upper end of the detection area RSa near the ceiling 5. Furthermore, the width of the detection area RSc in the left-right direction (±X direction) is narrower than the above-mentioned detection area RSa toward the center of the left-right width of the detection area RSa.

[0063] When determining the physical build of seated occupants P and Pc, the calculation unit 302 of the occupant detection device 3 counts the number of point clouds appearing in the detection areas RSa and RSc among the point clouds included in the point cloud information acquired by the acquisition unit 301 from the sensor device 2. Since the detection areas RSa and RSc partially overlap, some point clouds are counted in both the detection areas RSa and RSc. In addition, the calculation unit 302 calculates the ratio of the number of point clouds in the detection area RSa to the number of point clouds in the detection area RSc.

[0064] Ratio = (number of points in detection area RSa) / (number of points in detection area RSc)

[0065] The determination unit 303 of the occupant detection device 3 determines whether the ratio of the number of point clouds calculated by the calculation unit 302 is equal to or greater than a predetermined threshold. Hereinafter, this threshold will be referred to as a fourth threshold. If the ratio of the number of point clouds in the detection areas RSa and RSc is equal to or greater than the fourth threshold, the determination unit 303 determines that the person sitting in the seat SR2(R) is an adult occupant P. On the other hand, if the ratio is less than the fourth threshold, the determination unit 303 determines that the person sitting in the seat SR2(R) is an infant occupant Pc.

[0066] The detection areas used to determine the physical build of seated occupants P and Pc are not only the detection areas RSa and RSc set corresponding to seat SR2(R), but also areas corresponding to seats SE2(C) and SR2(R). The occupant detection device 3 performs the above-mentioned physical build determination using the corresponding detection areas for all seats in the seat row SR2(L), SR2(C), and SR2(R) where it is determined that occupants P and Pc are present.

[0067] The occupant detection system 1 may simultaneously determine the presence or absence of seated occupants P, Pc and the physical builds of these occupants P, Pc. In this case, the occupant detection system 1 can determine the presence or absence of seated occupants P, Pc and the physical builds of these occupants P, Pc by sequentially using detection areas including detection areas RSa and RSc that are set for each of the seats SR2(L), SR2(C), and SR2(R) without using the detection area RSs shown in Fig. 11 above, for example.

[0068] More specifically, in the case of a judgment regarding seat SR2(R), if at least one of the point cloud counts in the detection areas RSa and RSc is equal to or greater than a predetermined threshold, it is determined that there is an occupant P or Pc seated in seat SR2(R), and if the ratio of these point cloud counts is equal to or greater than, for example, the fourth threshold mentioned above, it can be determined that an adult occupant P is seated in seat SR2(R).

[0069] Fig. 13 shows an example of a detection area RRs that is set in the occupant detection system 1 of the embodiment and is used to detect recumbent occupants P, Pc. As shown in Fig. 13, the detection area RRs is set to an area that includes the seat surfaces of the multiple seats SR2(L), SR2(C), and SR2(R) in the seat row SR2, assuming that the bodies of the occupants P, Pc, which are located on the upper side, will be lower than the heads, etc., of the occupants P, Pc when they are seated.

[0070] More specifically, the detection area RRs is set to have a lower end lower than the lower end of the detection area RSs shown in Fig. 11, on or slightly below the seat surfaces of the seats SR2(L), SR2(C), and SR2(R), and an upper end lower than the upper end of the detection area RSs. As a result, the detection area RRs is set at a position generally lower than the detection area RSs. The detection area RRs may be set at a position where a portion of the upper end of the detection area RRs overlaps with a portion of the lower end of the detection area RSs.

[0071] When detecting whether or not an occupant P, Pc in a lying position is present, for example, in seat row SR2, the calculation unit 302 of the occupant detection device 3 counts the number of point clouds that appear in the detection area RRs among the point clouds contained in the point cloud information acquired by the acquisition unit 301 from the sensor device 2.

[0072] The determination unit 303 of the occupant detection device 3 determines whether the number of point clouds in the detection area RRs counted by the calculation unit 302 is equal to or greater than a predetermined threshold. Hereinafter, this threshold will be referred to as the first threshold. If the number of point clouds in the detection area RRs is equal to or greater than the first threshold, the determination unit 303 determines that there is an adult or child occupant P, Pc lying down in seat row SR2. On the other hand, if the number of point clouds in the detection area RRs is less than the first threshold, the determination unit 303 determines that there is no occupant P, Pc lying down in seat row SR2.

[0073] Note that by using the detection area RRs, it may be possible to detect, for example, occupants P, Pc who are in a posture other than a lying position. As an example, it may be possible to use the detection area RRs to detect occupants P, Pc who are in a posture that is out of the normal seating position, such as leaning against an adjacent seat or the door of the vehicle C. In this way, by using the detection area RRs, it may be possible to detect, for example, occupants P, Pc who are in a lower position than when seated upright.

[0074] Hereinafter, the lying posture will include all postures lower than the normal sitting posture, such as leaning on the seat next to you, etc. Also, hereinafter, the posture of occupants P, Pc who sit upright will also be called the normal sitting posture, and the posture of occupants P, Pc who have fallen off their feet and are lower than the normal sitting posture will also be called the irregular sitting posture.

[0075] 14 shows an example of detection areas RRa, RRc that are set in the occupant detection system 1 according to the embodiment and are used to determine the physiques of occupants P, Pc who are in a lying position. The physiques of the occupants P, Pc are determined collectively for the entire seat row SR2, for example.

[0076] As shown in Fig. 14, the detection areas RRa and RRc are set so that almost the entire area is included in the detection area RRs shown in Fig. 13. The widths of the detection areas RRa and RRc in the left-right direction (±X directions) are narrower than the above-mentioned detection area RSs, for example, toward the left-right center of the seat row SR2. The widths of the detection areas RRa and RRc in the up-down direction (±Z directions) are narrower than the above-mentioned detection area RRs, for example, downward.

[0077] Of the detection areas RRa and RRc, the detection area RRa is set to correspond to an adult occupant P. As an area where a point cloud representing an adult occupant P may appear, the detection area RRa is set to have its lower end on or slightly below the seat surface of the seat row SR2 and its upper end above the seat surface of the seat row SR2.

[0078] Furthermore, of the detection areas RRa and RRc, the detection area RRc is smaller than the above-mentioned detection area RRa and is set to correspond to the child occupant Pc. As an area where a point cloud indicating the child occupant Pc may appear, the detection area RRc has a lower end on or slightly below the seat surface of the seat row SR2, similar to the detection area RRa, and the width of the detection area RRc in the up-down direction (±Z direction) is, for example, reduced downward compared to the above-mentioned detection area RRa. Furthermore, the width of the detection area RRc in the left-right direction (±X direction) is reduced toward the center of the left-right width of the detection area RRa compared to the above-mentioned detection area RRa.

[0079] When determining the physique of occupants P and Pc who are lying down, the calculation unit 302 of the occupant detection device 3 counts the number of point clouds appearing in the detection areas RRa and RRc among the point clouds included in the point cloud information acquired by the acquisition unit 301 from the sensor device 2. For example, since the detection area RRc entirely overlaps with the detection area RRa, some point clouds are counted in both the detection areas RRa and RRc. In addition, the calculation unit 302 calculates the ratio of the number of point clouds in the detection area RRa to the number of point clouds in the detection area RRc.

[0080] Ratio = (number of points in detection area RRa) / (number of points in detection area RRc)

[0081] The determination unit 303 of the occupant detection device 3 determines whether the ratio of the number of point clouds calculated by the calculation unit 302 is equal to or greater than a predetermined threshold. Hereinafter, this threshold will be referred to as the second threshold. If the ratio of the number of point clouds in the detection areas RRa and RRc is equal to or greater than the second threshold, the determination unit 303 determines that the person lying down in seat row SR2 is an adult occupant P. On the other hand, if the ratio is less than the second threshold, the determination unit 303 determines that the person lying down in seat row SR2 is an infant occupant Pc.

[0082] 11 to 14 are also called regions of interest (ROI). Of these, the detection region RSs is an example of a fourth region of interest, the detection region RRs is an example of a first region of interest, the detection region RRa is an example of a second region of interest, and the detection region RRc is an example of a third region of interest.

[0083] After going through the above procedure, the determination unit 303 further determines whether or not there is only an infant occupant Pc in the vehicle C. If there is only an infant occupant Pc in the vehicle C, the output unit 304 outputs an alarm to the alarm device 4, and the alarm device 4 issues an alarm sound or the like.

[0084] If there is only an adult occupant P in the vehicle C, or if there are an adult and a child occupant P, Pc, the output unit 304 does not output an alarm to the alarm device 4, and no alarm sound or the like is issued from the alarm device 4.

[0085] (Processing example of occupant detection device) Next, an example of the occupant detection process of the occupant detection device 3 according to the embodiment will be described with reference to Fig. 15. Fig. 15 is a flow chart showing an example of the procedure of the occupant detection process by the occupant detection device 3 according to the embodiment. Fig. 15 shows a determination process per one time for the seat row SR2.

[0086] As shown in Figure 15, the acquisition unit 301 acquires point cloud information that shows point clouds of occupants P and Pc on a three-dimensional map of the vehicle interior R, detected by the transmitting and receiving unit 201 of the sensor device 2 and generated by the generation unit 202 (step S101).

[0087] The calculation unit 302 counts the number of points in the detection area RSs set for the seat row SR2 to be used for detecting the seated occupants P and Pc (step S102). The determination unit 303 determines whether or not there are adult or child occupants P and Pc seated in any of the seats SR2(L), SR2(C), and SR2(R) in the seat row SR2, based on whether or not the number of points in the detection area RSs is equal to or greater than a third threshold (step S103).

[0088] If the number of points in the detection area RSs is equal to or greater than the third threshold and the judgment unit 303 determines that there is an adult or child occupant P, Pc seated in one of the seat rows SR2 (step S103: Yes), a physical assessment is performed for the occupant P, Pc (step S104).

[0089] That is, the calculation unit 302 counts the number of point clouds in each of the detection areas RSa and RSc used to determine the physique of the seated occupants P and Pc, and calculates the ratio between the number of point clouds in each of the detection areas RSa and RSc. The determination unit 303 determines whether the seat occupant sitting in the corresponding seat SR2(L), SR2(C), or SR2(R) is an adult occupant P or an infant occupant Pc, based on whether the ratio between the number of point clouds is equal to or greater than a fourth threshold.

[0090] The calculation unit 302 and the determination unit 303 also check whether the physical build determination process has been completed for all seats in which occupants P and Pc have been detected among the seats SR2(L), SR2(C), and SR2(R) in the seat row SR2 (step S105). If there are any seats for which the physical build determination process has not been completed (step S105: No), the process of step S104 is repeated. When the physical build determination process has been completed for all seats in which occupants P and Pc have been detected (step S105: Yes), the process proceeds to the next step.

[0091] On the other hand, if the number of point clouds in the detection area RSs is less than the third threshold and the judgment unit 303 determines that there are no occupants P, Pc seated in any of the seat rows SR2 (step S103: No), the processing of steps S104 and S105 is skipped.

[0092] The calculation unit 302 counts the number of points in the detection area RRs used to detect lying occupants P, Pc set for the seat row SR2 (step S106). The determination unit 303 determines whether lying adult or child occupants P, Pc are present in the seat row SR2 based on whether the number of points in the detection area RRs is equal to or greater than a first threshold (step S107).

[0093] If the number of points in the detection area RRs is greater than or equal to the first threshold value and the judgment unit 303 determines that there is an adult or child occupant P, Pc in a lying position in seat row SR2 (step S107: Yes), a physical assessment is performed for the occupant P, Pc (step S108).

[0094] That is, the calculation unit 302 counts the number of point clouds in each of the detection areas RRa and RRc used to determine the physique of the lying occupants P and Pc, and calculates the ratio between the number of point clouds in each of the detection areas RRa and RRc. The determination unit 303 determines whether the lying occupant in seat row SR2 is an adult occupant P or an infant occupant Pc, based on whether the ratio between the number of point clouds is equal to or greater than a second threshold.

[0095] On the other hand, if the number of points in the detection region RRs is less than the first threshold and the determination unit 303 determines that there are no recumbent occupants P, Pc in the seat row SR2 (step S107: No), the process of step S108 is skipped.

[0096] The determination unit 303 determines whether or not a child has been left behind in the vehicle compartment R based on the processing results of steps S102 to S108 (step S109).

[0097] That is, the determination unit 303 determines that an infant has been left behind if the processing results of steps S102 to S108 show that only an infant occupant Pc in a seated or lying position is present in the vehicle compartment R, and no adult occupant P in a seated or lying position is present in the vehicle compartment R. On the other hand, even if an infant occupant Pc in a seated or lying position is present in the vehicle compartment R, if an adult occupant P in a seated or lying position is present in the vehicle compartment R, the determination unit 303 determines that an infant has not been left behind.

[0098] If the determination unit 303 determines that an infant has been left behind (step S109: Yes), the output unit 304 outputs an alarm to the alarm device 4 (step S110). If the determination unit 303 determines that an infant has not been left behind (step S109: No), the process of step S110 is skipped.

[0099] With the above, one cycle of the occupant detection process of the occupant detection device 3 of the embodiment is completed.

[0100] The occupant detection device 3 starts the process shown in Fig. 15 at a predetermined timing and repeats it until the predetermined timing is reached. For example, when determining whether an infant is left behind in the vehicle compartment R, the above process is repeated from when the engine of the vehicle C is turned off until it is turned on.

[0101] 15, the order of the various processes can be changed as appropriate. For example, the processes of steps S106 to S108 may be executed before the processes of steps S102 to S105. Furthermore, the processes of steps S102 to S105 and the processes of steps S106 to S108 may be executed in parallel. Furthermore, the detection of seated occupants P and Pc using the detection areas RSa and RSc (step S103) and the physique determination (step S104) may be performed simultaneously or consecutively, without performing the process of step S102.

[0102] (Overview) There is a technology for detecting occupants in a vehicle cabin using a radio wave sensor or the like. In recent years, attempts to use such technology to detect whether a child has been left behind in the vehicle cabin have been considered. In this case, it is preferable to build a system that can accurately obtain information such as whether a child is in the vehicle cabin and whether an adult is also in the cabin, and then take appropriate action.

[0103] However, the detection area for detecting a passenger seated in a normal position is set relatively high on the seat to match the head position of an adult passenger, for example. In this case, there is a possibility that a short child will not be detected. On the other hand, if the detection area is simply set at a lower position, there is a possibility that an adult in a lying position will be mistakenly detected as a child left behind.

[0104] According to the embodiment of the occupant detection device 3, the number of point clouds that appear in a detection area RRs that is set for a seat row SR2 in the vehicle compartment R and includes the seat surface of the seat row SR2 is counted, and if the number of point clouds in the detection area RRs is equal to or greater than a first threshold value, it is determined that an adult or child occupant P, Pc who is in a posture lower than a normal seated posture is present in the seat row SR2.

[0105] In this way, first, the posture of the occupants P, Pc in the vehicle compartment R is determined, so it is possible to prevent omission of detection of occupants P, Pc in a low posture, such as lying down. This makes it possible to distinguish between various situations and detect whether an infant has been left behind with high accuracy.

[0106] According to the occupant detection device 3 of the embodiment, if the number of point clouds in the detection area RRs is equal to or greater than a first threshold value, the number of point clouds that appear in the detection area RRa, which is set for the seat row SR2 in the vehicle compartment R and includes the seat surface of the seat row SR2, is counted, the number of point clouds that appear in the detection area RRc, which is set in an area overlapping with the detection area RRa and is narrower than the detection area RRa, is counted, the ratio of the number of point clouds in the detection area RRa to the number of point clouds in the detection area RRc is calculated, and if the above ratio is equal to or greater than a second threshold value, it is determined that there is an adult occupant P in a low posture.

[0107] In this way, the posture of the occupants P, Pc is first identified, and then the physical constitution of the occupants P, Pc is determined using the detection areas RRa, RRc, etc. set according to the identified posture of the occupants P, Pc. This makes it possible to prevent an adult in a low posture, such as a lying position, from being mistakenly detected as a child being left behind.

[0108] According to the occupant detection device 3 of the embodiment, the detection areas RRa and RRc are set by defining a seat row SR2 having a plurality of adjacent seats as a seating area. In a vehicle having a plurality of adjacent seats, such as a rear seat, it is conceivable that an occupant may lie across the plurality of adjacent seats. Therefore, by setting the detection areas RRa and RRc to include the plurality of adjacent seats, it becomes easier to detect occupants P and Pc who lie across the plurality of adjacent seats.

[0109] According to the embodiment of the occupant detection device 3, the number of point clouds that appear in the detection area RSs, which is set above the seat surface of the seat row SR2 and has an upper end at a higher height position than the detection area RRs, is counted, and if the number of point clouds in the detection area RSs is equal to or greater than a third threshold, it is determined that there is an adult or child occupant P, Pc seated in the seat row SR2.

[0110] In this way, since occupant detection is performed using the detection area RSs used to detect seated occupants P, Pc, separate from the detection area RRs used to detect occupants P, Pc in a low posture such as lying down, adult or child occupants P, Pc can be correctly detected regardless of their posture. Also, it is possible to prevent a false alarm from being issued when an adult is riding in the vehicle and a child is mistakenly detected as being left behind.

[0111] In the above-described embodiment, the physical build of the occupants P, Pc who are sitting low is determined based on the ratio (RRa / RRc) of the number of point clouds in the detection area RRa to the number of point clouds in the detection area RRc. However, the occupant detection system may also determine the physical build of the occupants P, Pc who are sitting low based on the ratio (RRc / RRa) of the number of points in the detection area RRc to the number of points in the detection area RRa. In this case, if the ratio (RRc / RRa) is equal to or greater than a predetermined threshold, it indicates that a low-slung child occupant Pc is present in the vehicle compartment R, and if the ratio (RRc / RRa) is less than the predetermined threshold, it indicates that a low-slung adult occupant P is present in the vehicle compartment R.

[0112] Similarly, in the above-described embodiment, the physical build of the seated occupants P, Pc is determined based on the ratio (RSa / RSc) of the number of point clouds in the detection area RSa to the number of point clouds in the detection area RSc. However, the occupant detection system may also determine the physical build of the seated occupants P, Pc based on the ratio (RSc / RSa) of the number of points in the detection area RSc to the number of points in the detection area RSa. In this case, if the ratio (RSc / RSa) is equal to or greater than a predetermined threshold, it indicates that a seated child occupant Pc is present in the vehicle compartment R, and if the ratio (RSc / RSa) is less than the predetermined threshold, it indicates that a seated adult occupant P is present in the vehicle compartment R.

[0113] In the above-described embodiment, for example, in a seat row SR2 in which multiple seats are adjacent to each other, detection areas RSs and RRs extending in the ±X direction are set to correspond to all the seats, and the postures of the occupants P and Pc are determined. However, the method of the above-described embodiment can also be applied to seating areas in which seats are individually and independently arranged, such as the driver's seat and passenger seat included in the seat row SR1.

[0114] Furthermore, in the above-described embodiment, when it is determined that a child has been left behind, the occupant detection system 1 outputs an alarm to the alarm device 4, and the alarm device 4 issues an alarm. However, when a child has been left behind, instead of or in addition to issuing an alarm by the alarm device 4, the occupant detection system may be able to send a notification to a mobile device or the like of a user of the vehicle C, such as a driver.

[0115] Although the embodiments of the present invention have been described above, the above embodiments are presented as examples and are not intended to limit the scope of the invention. This novel embodiment can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. This embodiment and its modifications are included within the scope and spirit of the invention, and are also included in the inventions and their equivalents as set forth in the claims. [Explanation of symbols]

[0116] 1...occupant detection system, 2...sensor device, 3...occupant detection device, 5...ceiling, 21...transmitter, 22...receiver, 23...sensor ECU, 24...input / output unit, 31...CPU, 32...memory, 33...input / output unit, 201...transmitter / receiver unit, 202...generation unit, 301...acquisition unit, 302...calculation unit, 303...determination unit, 304...output unit, 305...storage unit, RRa, RRc, RRs, RSa, RSc, RSs...detection area, C...vehicle, P, Pc...occupant, PP...point cloud, R...vehicle compartment, SR1, SR2, SR3...seat rows.

Claims

1. an acquisition unit that acquires point cloud information that indicates, as a point cloud, one or more detection points that represent the positions of occupants present in the vehicle cabin, based on a transmission wave that is transmitted toward the vehicle cabin and reflected by the occupants in the vehicle cabin; a calculation unit that counts the number of points that appear in a first region of interest that is set for a seating area in the vehicle cabin and includes a seat surface of the seating area; a determination unit that determines that an occupant in a posture lower than a normal seating posture is present in the seating area when the number of points in the first region of interest is equal to or greater than a first threshold value, Occupant detection device.

2. The calculation unit If the number of points in the first region of interest is equal to or greater than a first threshold, counting the number of points that appear in a second region of interest that is set for a seating area in the vehicle interior and includes a seat surface of the seating area; counting the number of points that appear in a third region of interest that is set in an area overlapping the second region of interest and is narrower than the second region of interest; calculating a ratio of the number of point clouds in the second region of interest to the number of point clouds in the third region of interest; The determination unit If the ratio is equal to or greater than a second threshold, it is determined that an adult occupant is in the low posture. The occupant detection device according to claim 1 .

3. The seating area is an area corresponding to a plurality of adjacent seats. The occupant detection device according to claim 1 or 2.

4. The calculation unit counting the number of points that appear in a fourth region of interest that is set above the seat surface of the seating area and has an upper end that is higher in height than the first region of interest; The determination unit If the number of points in the fourth region of interest is equal to or greater than a third threshold, it is determined that an occupant is seated in the seating region. The occupant detection device according to claim 1 .

Images