JP2022189451A - Living body detection device - Google Patents

Abstract

To highly accurately determine a type and a state of a person existing in a cabin of a vehicle.SOLUTION: A living body detection device comprises: a sensor which transmits a laser beam whose frequency is modulated to a cabin of a vehicle as a transmission wave and receives a reflection wave generated by a reflection of the transmission wave by an object in the cabin; a first generation unit which generates three-dimensional map information in the cabin on the basis of intensity distribution of the reflection wave; a second generation unit which generates speed information about a speed of the object in the cabin on the basis of Doppler shift of the reflection wave; a first detection unit which detects a child in the cabin on the basis of the three-dimensional map information and the speed information; a second detection unit which detects a position of a seat in the cabin; and a determination unit which determines whether or not the child is seated on a child seat on the basis of a position of the child detected by the first detection unit and the position of the seat detected by the second detection unit.SELECTED DRAWING: Figure 2

Description

The present invention relates to a living body detection device.

2. Description of the Related Art Conventionally, there is a technique of irradiating a person with radio waves and calculating biological information (heart rate, etc.) by frequency-analyzing the Doppler shift of the reflected wave. There is also a technique for determining the presence or absence of a person (passenger) in a vehicle (passenger car, etc.) based on transmission and reception of radio waves of the FMCW (Frequency Modulated Continuous Wave) system. In the FMCW method, radio waves are emitted, and the position at which the reflected wave is reflected and the speed at that position can be obtained from the Doppler shift. By combining these technologies, it is possible to detect people in a room and their biometric information. There is also a technology for distinguishing between an adult in a vehicle and a child seated in a child seat based on the image characteristics of an object (such as the presence or absence of head and shoulders) acquired using a range image sensor. .

JP 2018-202921 A JP 2012-127811 A

However, if a highly penetrating radio wave is used as the radio wave to be sent and received to detect a person or the like, the transmitted wave penetrates even the metal structure of the vehicle, and the signal level of the reflected wave from the metal structure increases. In some cases, the detection accuracy of people and the like may be degraded. Also, when trying to determine the type or state of a person (whether he is a child, whether he is seated in a child seat, etc.) from the characteristics of the image, for example, when the person is covered with a blanket, etc. likely to be unidentifiable.

Therefore, the problem to be solved by the present invention is to provide a living body detection device capable of highly accurately determining the type and state of a person present in the vehicle interior.

A living body detecting device according to an embodiment of the present invention is a sensor that transmits a frequency-modulated laser beam as a transmission wave into the interior of a vehicle, and receives a reflected wave that is generated when the transmission wave is reflected by an object in the room. a first generating unit that generates three-dimensional map information in the room based on the intensity distribution of the reflected wave; a second generating unit that generates velocity information about the velocity of an object in the room based on the Doppler shift of the reflected wave; a first detector that detects the child in the room based on the three-dimensional map information and the speed information; a second detector that detects the position of the seat in the room; 2 a determination unit that determines whether or not the child is seated in the child seat based on the position of the seat detected by the detection unit.

According to the above configuration, the child in the room is detected based on the three-dimensional map information and speed information obtained by a sensor (such as a LiDAR sensor) that transmits and receives frequency-modulated laser light, and the positional relationship between the child and the seat is detected. is determined whether or not the child is seated in the child seat. As a result, the type and state of a person present in the vehicle interior can be determined with high accuracy.

Further, the determination unit may determine that the child is seated in the child seat when the position of the predetermined portion of the child deviates forward and upward from the position of the predetermined portion of the seat by a threshold value or more.

When a child is seated in a child seat, the position of the child is shifted forwards and upwards than when the child is seated in a normal seat. Therefore, by performing the determination as described above, it is possible to accurately determine whether or not the child is seated in the child seat.

Further, the position of the predetermined portion of the child may be the barycentric position of the existing region of the child in the three-dimensional map information.

This makes it possible to accurately estimate the position of the child without using an image sensor or the like, and to accurately determine whether the child is seated in the child seat.

Also, the living body detection device may further include a third generator that generates information about the heartbeat of a person in the room based on the Doppler shift of the reflected wave.

This makes it possible to generate biometric information in consideration of the type and state of a person.

Drawing 1 is a figure showing an example of composition of vehicles in an embodiment. FIG. 2 is a block diagram illustrating an example of functional configurations of a LiDAR sensor and a control device according to the embodiment; FIG. 3 is a diagram showing an outline of signal processing by the FMCW method in the embodiment. FIG. 4 is a diagram illustrating an example of a state in which an adult and a child are detected by the person detection unit according to the embodiment; FIG. 5 is a diagram showing an example of seat positions in the embodiment. FIG. 6 is a diagram showing an example of a state in which a child is directly seated on the seat in the embodiment. FIG. 7 is a diagram showing an example of a state in which a child is seated in the child seat in the embodiment. FIG. 8 is a flowchart illustrating an example of processing by the living body detection device according to the embodiment. FIG. 9 is a diagram showing an example of a vehicle in the first modified example. FIG. 10 is a diagram showing an example of how to use the LiDAR sensor in the second modified example.

Illustrative embodiments of the invention are disclosed below. The configurations of the embodiments shown below and the actions, results, and effects brought about by the configurations are examples. The present invention can be realized by configurations other than those disclosed in the following embodiments, and at least one of various effects and derivative effects based on the basic configuration can be obtained.

FIG. 1 is a diagram showing an example of the configuration of a vehicle C according to the embodiment. In the interior of the vehicle C, a LiDAR sensor 2 (sensor) and a control device 3 that constitute the living body detection device 1 are arranged. The LiDAR sensor 2 is installed on the ceiling of the room. The control device 3 is installed, for example, in a dashboard provided at the front end of the room.

An occupant M (a person) sits on the seat S. Detecting the presence of the occupant M and determining the type and state of the occupant M by the living body detection device 1 will be described below.

FIG. 2 is a block diagram showing an example of functional configurations of the LiDAR sensor 2 and the control device 3 of the embodiment. The LiDAR sensor 2 includes a transmitter 21 and a receiver 22 .

The transmitter 21 transmits (irradiates) a frequency-modulated laser beam as a transmission wave into the interior of the vehicle C over a wide range. The receiving unit 22 receives reflected waves generated when the transmitted waves are reflected by objects in the room.

The control device 3 is configured by, for example, an MCU (Micro Controller Unit) having an integrated circuit on which a hardware processor, memory, and the like are mounted. The control device 3 includes an ADC (Analog-to-Digital Converter) 31 , a processing section 32 and a storage section 33 .

The ADC 31 converts the analog signal acquired from the receiver 22 of the LiDAR sensor 2 into a digital signal and outputs the digital signal to the processor 32 .

The storage unit 33 is, for example, a storage device such as a RAM (Random Access Memory), ROM (Read Only Memory), SSD (Solid State Drive), HDD (Hard Disk Drive). The storage unit 33 stores programs executed by the processing unit 32, data necessary for executing the programs, data generated by executing the programs, and the like. The storage unit 33 in this embodiment stores setting information 331, three-dimensional map information 332, speed information 333, seat position information 334, biological information 335, seating information 336, and the like.

The setting information 331 includes various thresholds for realizing the functions of the living body detection device 1 . The threshold is, for example, a threshold for detecting a person, a threshold for distinguishing between an adult and a child, a threshold for determining whether a child is seated in a child seat, or a biosignal of a person. can be a threshold value for

The three-dimensional map information 332 is information indicating the three-dimensional object arrangement state in the room, which is generated by the map information generation unit 321 based on the intensity distribution of the reflected waves. The intensity distribution is information indicating the correspondence relationship between the position of the reflection source and the intensity of the reflected wave in a three-dimensional space (inside the vehicle C).

The velocity information 333 is information indicating the velocity (movement) of an object existing in the room, which is generated by the velocity information generator 322 based on the Doppler shift of the reflected wave. Velocity information 333 may include information indicating the direction of motion of the object.

The seat position information 334 is information indicating the position of a seat (rear seat, front passenger seat, driver seat, etc.) mounted on the vehicle C detected by the seat position detection unit 423 .

The biometric information 335 is biometric information of a person (passenger M) generated by the biometric information generation unit 326 . The biological information may be, for example, a heart rate or a person's condition (physical condition, mental state, etc. estimated from the heart rate, etc.).

The seating information 336 is information indicating the seating state of the person on the seat S determined by the determination unit 325 . The seating information 336 includes information indicating whether or not the child is seated in the child seat.

Here, an outline of signal processing by the FMCW method will be described. FIG. 3 is a diagram showing an outline of signal processing by the FMCW method in the embodiment. As shown in (A), first, FMCW-modulated laser light is transmitted from the transmitter 21 of the LiDAR sensor 2 into the interior of the vehicle C. As shown in FIG. Then, the receiver 22 of the LiDAR sensor 2 receives the reflected wave.

Next, as shown in (B), indoor three-dimensional map information is created based on the intensity distribution of the reflected waves in the room. This three-dimensional map information includes a labeling area D indicating the positions and sizes of objects (passenger M, seat S, etc.) present in the cabin.

Next, as shown in (C), the occupant M is detected based on the three-dimensional map information as described above and velocity information based on the Doppler shift of the reflected wave. For example, an object having a predetermined speed (movement) can be determined as the occupant M among a plurality of objects existing in the room. Moreover, based on the Doppler shift of the reflected wave, the biological information (heart rate, etc.) of the occupant M can also be calculated.

Details of the processing of the processing unit 32 will be described below with reference to FIG.

The processing unit 32 is configured by, for example, a hardware processor such as a CPU (Central Processing Unit). The processing unit 32 reads a program stored in the storage unit 33 and executes arithmetic processing. The processing unit 32 includes, as functional units, a map information generation unit 321 (first generation unit), a speed information generation unit 322 (second generation unit), a person detection unit 323 (first detection unit), and a seat position detection unit 324 ( second detection unit), a determination unit 325, and a biological information generation unit 326 (third generation unit). Some or all of the units 321 to 326 may be configured by hardware such as circuits including ASICs (Application Specific Integrated Circuits) and FPGAs (Field-Programmable Gate Arrays).

The map information generation unit 321 generates indoor three-dimensional map information 332 based on the reflected wave information acquired from the ADC 31 and stores it in the storage unit 33 .

The speed information generation unit 322 generates speed information 333 indicating the speed of an object existing in the room based on the reflected wave information acquired from the ADC 31 and stores the speed information 333 in the storage unit 33 .

The human detection unit 323 detects the occupant M present inside the vehicle C based on the setting information 331, the three-dimensional map information 332, the speed information 333, and the like. Also, the person detection unit 323 detects whether or not the passenger M is a child. Whether the occupant M is a child can be detected, for example, by comparing the setting information 331 and information indicating the size of the labeling area D included in the three-dimensional map information 332 .

A sheet position detection unit 324 detects the position of the sheet S. FIG. Although the method of detecting the position of the seat S should not be particularly limited, for example, the position can be detected based on the detection signal of a sensor installed in the slide mechanism of the seat S, the three-dimensional map information 332, or the like. Sheet position information 334 indicating the position of the sheet S is stored in the storage unit 33 .

The determination unit 325 determines whether the child is seated in the child seat based on the position of the child detected by the person detection unit 323 and the seat position information 334 . A specific determination method by the determination unit 325 will be described later.

Based on the reflected wave information acquired from the ADC 31 , the biological information generation unit 326 generates biological information (heart rate, etc.) of the occupant M detected by the person detection unit 323 . The generated biometric information is stored in the storage unit 33 .

FIG. 4 is a diagram illustrating an example of a state in which an adult Ma and a child Mc are detected by the person detection unit 323 in the embodiment. For example, based on the size of the labeling area D (see FIG. 2) corresponding to the person, the physique of the person can be estimated, and if the physique is equal to or less than a threshold, the person can be estimated to be the child Mc.

FIG. 5 is a diagram showing an example of the seat position Ps in the embodiment. FIG. 5 illustrates the seat S in the default position and the seat S slid forward. The seat position Ps is the position of a predetermined portion of the seat S, here, the position of the central portion of the seating portion of the seat S (excluding the backrest portion). The seat position Ps is not limited to this, and may be a position of another portion of the seat S. FIG. The seat position Ps is displaced as the seat S moves. The movement of the seat S may be not only horizontal sliding but also vertical or oblique movement.

FIG. 6 is a diagram showing an example of a state in which the child Mc is directly seated on the seat S in the embodiment. FIG. 7 is a diagram showing an example of a state in which the child Mc is seated in the child seat Sc in the embodiment.

6 and 7 illustrate the seat position Ps and the child position Pm. The child position Pm is the position of a predetermined portion of the child Mc, and may be, for example, the position of the center of gravity of the existing area (labeling area D) of the child Mc in the 3D map information 332 . By adopting such a child position Pm, the position of the child Mc can be estimated without using image analysis or the like. Note that the child position Pm may be the position of the head of the child Mc. 6 and 7 also illustrate the amount of forward deviation Df of the child position Pm with respect to the seat position Ps and the amount of upward deviation Du of the child position Pm with respect to the seat position Ps.

The shift amounts Df and Du shown in FIG. 7 are larger than the shift amounts Df and Du shown in FIG. That is, when the child Mc is seated on the child seat Sc, the displacement amounts Df and Du are becomes larger than the amount of deviation Df, Du. Therefore, when each of the deviation amounts Df and Du is equal to or greater than the threshold value, it can be determined that the child Mc is seated in the child seat Sc.

FIG. 8 is a flowchart showing an example of processing by the living body detection device 1 according to the embodiment. When the reflected wave information in the interior of the vehicle C is acquired by driving the LiDAR sensor 2 (S101), the map information generation unit 321 generates the three-dimensional map information 332 based on the intensity distribution of the reflected wave (S102), and the speed The information generator 322 generates velocity information 333 based on the Doppler shift of the reflected wave (S103).

The human detection unit 323 detects whether or not the child Mc is present in the vehicle C based on the three-dimensional map information 332 and the speed information 333 (S104). When the child Mc does not exist (S104: No), the person detection unit 323 determines whether or not a person (adult Ma) exists (S105). If the person does not exist (S105: No), this routine ends. biometric information is generated (S111), and this routine ends.

If the child Mc exists (S104: Yes), the seat position detection unit 324 detects the seat position Ps of the seat S corresponding to the position of the child Mc (S106), and the determination unit 325 detects the child position Pm and the seat position Ps. It is determined whether or not the amount of deviation Df, Du between is equal to or greater than a threshold value (S107). When both the deviation amounts Df and Du are equal to or larger than the threshold (S107: Yes), the determination unit 325 determines that the child Mc is seated in the child seat Sc (S108), and the child Mc is seated in the child seat Sc. Seating information indicating that is generated (S110). On the other hand, if both or one of the deviation amounts Df and Du is not equal to or greater than the threshold value (S107: No), the determination unit 325 determines that the child Mc is seated on the normal seat S (S109). Seating information indicating that the seat S is seated is generated (S110). After the seating information is generated, the biometric information generator 326 generates the biometric information of the person based on the Doppler shift of the reflected wave (S111), and this routine ends. The biological information and the seating information generated as described above can be output to a predetermined system (for example, a driving support system of the vehicle C, etc.) and used.

According to the above embodiment, the child Mc in the room is detected based on the three-dimensional map information 332 and the speed information 333 acquired by the LiDAR sensor 2, and the child Mc is detected based on the positional relationship between the child Mc and the seat S. It is determined whether or not the child is seated in the child seat Sc. As a result, the types and states of persons present in the interior of the vehicle C can be determined with high accuracy.

(Modification)
FIG. 9 is a diagram showing an example of a vehicle C in the first modified example. As shown in FIG. 9, in the interior of the vehicle C, the LiDAR sensor 2 may be installed in the front portion instead of the ceiling, and processing for detecting the type and state of the occupant M may be performed.

FIG. 10 is a diagram showing an example of how to use the LiDAR sensor 2 in the second modified example. The LiDAR sensor 2 may be installed on the ceiling above the bathtub B of the bathroom to perform processing for detecting the type and state of the bather M. As a result, for example, when an elderly person suddenly becomes ill while taking a bath, the sudden illness can be detected with high accuracy when there is a predetermined change in the pulse wave, respiration, body movement, or the like of the old person.

The program executed by the control device 3 is a file in an installable format or an executable format, and can be stored in a computer such as a CD-ROM, a CD-R, a memory card, a DVD (Digital Versatile Disk), a flexible disk (FD), or the like. may be stored in a readable storage medium and provided as a computer program product. Alternatively, the program may be stored on a computer connected to a network such as the Internet, and provided by being downloaded via the network. Also, the program may be provided or distributed via a network such as the Internet.

Although the embodiment of the present invention has been described above, the above embodiment is presented as an example and is not intended to limit the scope of the invention. This novel embodiment can be embodied in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. This embodiment and its modifications are included in the scope and gist of the invention, and are included in the scope of the invention described in the claims and its equivalents.

DESCRIPTION OF SYMBOLS 1... Living body detection apparatus, 2... LiDAR sensor, 3... Control apparatus, 21... Transmission part, 22... Reception part, 31... ADC, 32... Processing part, 33... Storage part, 321... Map information generation part, 322... Velocity Information generation unit 323 Person detection unit 324 Seat position detection unit 325 Determination unit 326 Biological information generation unit 331 Setting information 332 Three-dimensional map information 333 Speed information 334 Seat position Information 335...Biological information 336...Seating information C...Vehicle D...Labeling area Df, Du...Displacement amount M...Occupant (bather) Ma...Adult Mc...Child Pm...Child position Ps …Seat position, S…Seat, Sc…Child seat

Claims (4)

a sensor that transmits a frequency-modulated laser beam as a transmission wave into the interior of the vehicle and receives a reflected wave that is generated when the transmission wave is reflected by an object in the room;
a first generating unit that generates three-dimensional map information of the interior of the room based on the intensity distribution of the reflected waves;
a second generator that generates velocity information about the velocity of an object in the room based on the Doppler shift of the reflected wave;
a first detection unit that detects a child in the room based on the three-dimensional map information and the speed information;
a second detection unit that detects the position of the seat in the room;
a determination unit that determines whether the child is seated in a child seat based on the position of the child detected by the first detection unit and the position of the seat detected by the second detection unit;
A living body detection device comprising: The determination unit determines that the child is seated in the child seat when the position of the predetermined portion of the child is shifted forward and upward from the position of the predetermined portion of the seat by a threshold value or more.
The living body detection device according to claim 1. the position of the predetermined part of the child is the center of gravity of the existing area of the child in the three-dimensional map information;
The living body detection device according to claim 1 or 2. a third generator that generates information about the heartbeat of a person in the room based on the Doppler shift of the reflected wave;
The living body detection device according to any one of claims 1 to 3, further comprising:

Images