Occupant distinguishing device, occupant distinguishing method, and program

Abstract

An occupant distinguishing device (1) comprises: a first sensor information acquisition unit (11) that acquires detection information regarding a vehicle cabin interior of a vehicle as detected by a millimeter wave sensor (2); a second sensor information acquisition unit (12) that acquires detection information from a door sensor (3) that detects the opening and closing of a vehicle door, as well as detection information from at least one of a camera (4) that captures an image of the vehicle cabin interior, a vehicle height sensor (5) that detects the height of the vehicle from the ground, a weight sensor (6) that detects the weight of the vehicle, and an air pressure sensor (7) that detects a vehicle tire air pressure; and a distinguishing unit (13) that determines whether an occupant has entered or exited the vehicle on the basis of the detection information acquired by the first sensor information acquisition unit (11) and the second sensor information acquisition unit (12) and as triggered by the detection of a vehicle door opening or closing, and further distinguishes between occupants and objects by determining at least one of the seating position of the occupant, physique information of the occupant, and whether an object other than the occupant has been loaded or unloaded.

Description

Occupant discrimination device, occupant discrimination method and program

[0001] The present disclosure relates to an occupant discrimination device, an occupant discrimination method, and a program.

[0002]

[0003] Conventionally, there have been known techniques for determining whether or not an occupant is present in a vehicle cabin. For example, the conventional technique described in Patent Literature 1 acquires a detection result of a living body detection sensor that detects a living body in the vehicle cabin and an image of the vehicle cabin captured by an imaging device, determines whether or not an occupant is present in the vehicle cabin based on the detection result of the living body detection sensor, and, if it is determined that an occupant is present in the vehicle cabin, determines the physique of the occupant based on the image captured by the imaging device.

[0003] Japanese Patent Application Laid-Open No. 2019-60608

[0004] However, there is a problem in that the detection information obtained by the living body detection sensor and the imaging device cannot accurately identify the occupant in the vehicle cabin. For example, in Patent Document 1, a seat sensor is assumed as the living body detection sensor, but there is a possibility that luggage placed on the seat will be detected. Furthermore, if the imaging device's imaging field of view is shaded by the front seat or the like, it cannot distinguish whether the object present in the seat is a occupant such as a child or luggage.

[0005] The present disclosure is intended to solve the above-mentioned problems, and has an object to provide an occupant discrimination device that can accurately discriminate occupants and objects in a vehicle cabin.

[0006] The occupant discrimination device according to the present disclosure includes a first sensor information acquisition unit that acquires detection information from the interior of the vehicle detected by a millimeter wave sensor that is a first sensor; a second sensor information acquisition unit that acquires detection information from a second sensor different from the first sensor, in addition to detection information from a door sensor that detects the opening and closing of a vehicle door, from at least one of a camera that captures images of the interior of the vehicle, a vehicle height sensor that detects the height of the vehicle from the ground, a weight sensor that detects the weight of the vehicle, or an air pressure sensor that detects the air pressure of the vehicle's tires; and a discrimination unit that determines whether an occupant has gotten in or out of the vehicle based on the detection information acquired by the first sensor information acquisition unit and the detection information acquired by the second sensor information acquisition unit, in response to the detection of the opening and closing of the vehicle door, and further discriminates occupants and objects by determining at least one of the seating position of the occupant, physical information of the occupant, or whether objects other than the occupant have been loaded or unloaded.

[0007] According to the present disclosure, an occupant discrimination device according to the present disclosure acquires detection information from the interior of a vehicle detected by a millimeter wave sensor, and acquires detection information from at least one of a camera that captures images of the interior of the vehicle, a vehicle height sensor that detects the height of the vehicle from the ground, a weight sensor that detects the weight of the vehicle, and an air pressure sensor that detects the air pressure of the vehicle's tires, in addition to detection information from a door sensor that detects the opening and closing of a vehicle door, and determines whether an occupant has gotten in or out of the vehicle based on the detection of the opening and closing of the vehicle door, and further discriminates occupants and objects by determining at least one of the seating position of the occupant, physique information of the occupant, and whether an object other than the occupant has been loaded or unloaded. This enables the occupant discrimination device according to the present disclosure to accurately discriminate occupants and objects in the vehicle interior.

[0008] 3A and 3B are block diagrams illustrating an example of the configuration of an occupant discrimination device according to Embodiment 1. FIG. 3A is a flowchart illustrating an occupant discrimination method according to Embodiment 1. FIG. 3B is a block diagram illustrating a hardware configuration that realizes the functions of the occupant discrimination device according to Embodiment 1.

[0009] Embodiment 1. When identifying an occupant or baggage in a vehicle cabin based on the detection level of a millimeter wave reflected by a millimeter wave sensor, the detection level of the reflected wave does not necessarily clearly differentiate between the types of objects present in the vehicle cabin. Therefore, the type of object detected in the vehicle cabin may not be correctly identified based on the detection information from the millimeter wave sensor alone. For example, the difference between the detection level of a millimeter wave reflected by a child, including an infant, and the detection level of a millimeter wave reflected by a baggage is generally likely to be small.

[0010] On the other hand, when an object enters or leaves the vehicle cabin, the vehicle door is inevitably opened and closed. This applies not only to occupants, including infants, but also to luggage, which is an object other than an occupant, brought into or taken out of the vehicle cabin by the occupant. Furthermore, as described above, there is a possibility that the type of object in the vehicle cabin cannot be clearly determined based on the detection information from the millimeter wave sensor alone.

[0011] In contrast, the occupant discrimination device according to the first embodiment acquires detection information from the interior of the vehicle detected by a millimeter-wave sensor as a first sensor, and acquires detection information from a second sensor different from the first sensor, a door sensor that detects the opening and closing of a vehicle door, as well as detection information from at least one of a camera that captures images of the interior of the vehicle, a vehicle height sensor that detects the height of the vehicle from the ground, a weight sensor that detects the weight of the vehicle, and an air pressure sensor that detects the air pressure of the vehicle tires. The occupant discrimination device determines whether an occupant has entered or exited the vehicle based on the detection of the opening and closing of the vehicle door, and further determines at least one of the seating position of the occupant, physical information about the occupant, and whether an object other than the occupant has been loaded or unloaded, thereby discriminating between the occupant and the object. By determining whether an occupant has entered or exited the vehicle based on the detection of the opening and closing of the door, the occupant discrimination device according to the first embodiment can discriminate between the occupant and the object at an appropriate timing when an object enters or leaves the vehicle compartment, and can suppress unnecessary determination operations that do not involve the entry or exit of an object from the vehicle compartment. Furthermore, in addition to the detection information from the millimeter wave sensor, detection information from at least one of a door sensor, a camera, a vehicle height sensor, a weight sensor, and an air pressure sensor is used, so that occupants can be identified with high accuracy.

[0012] (Overview of Occupant Classification Device) Fig. 1 is a block diagram showing an example of the configuration of an occupant classification device 1 according to a first embodiment. In Fig. 1, the occupant classification device 1 determines whether an occupant has gotten in or out of the vehicle when a door sensor 3 detects the opening or closing of a vehicle door. Furthermore, the occupant classification device 1 uses detection information from a millimeter-wave sensor 2 and the door sensor 3 as well as detection information from at least one of a camera 4, a vehicle height sensor 5, a weight sensor 6, and an air pressure sensor 7 to determine at least one of the seating position of the occupant, physical information about the occupant, and whether or not an object other than the occupant has been loaded or unloaded, thereby classifying the occupant and the object. The occupant classification device 1 is also connected to a storage unit 8 and a communication unit 9 via a wired or wireless connection.

[0013] The occupant discrimination device 1 is assumed to be a device mounted on a vehicle, but is not limited thereto. For example, the occupant discrimination device 1 may be an external device capable of wireless communication with a communication device mounted on the vehicle. The communication device acquires detection information from at least one of the door sensor 3, the camera 4, the vehicle height sensor 5, the weight sensor 6, and the tire pressure sensor 7 in addition to the millimeter wave sensor 2, and transmits the acquired detection information to the occupant discrimination device 1, which is the external device, via wireless communication. The occupant discrimination device 1 uses the detection information transmitted from the communication device to discriminate occupants and objects in the vehicle. The discrimination result is transmitted from the occupant discrimination device 1 to the communication device. The communication device may output the discrimination result received from the occupant discrimination device 1 to a monitor or the like mounted on the vehicle.

[0014] An information processing application for providing the occupant classification service may be installed in the occupant classification device 1, or the information processing service may be provided in the form of so-called SaaS (Software as a Service). When the information processing service is provided in the form of SaaS, the information processing application for providing the occupant classification service is executed by a server that can be connected to by communication from the occupant classification device 1. Therefore, the occupant classification service is provided on a web browser without an information processing app being installed in the occupant classification device 1.

[0015] (Millimeter-Wave Sensor) The millimeter-wave sensor 2 is a first sensor that uses millimeter waves (frequency between 30 GHz and 300 GHz) to detect occupants or objects in the vehicle cabin. The operating principle of the millimeter-wave sensor 2 is based on detecting changes in millimeter waves when they are reflected by an object. The millimeter-wave sensor 2 emits millimeter waves and receives the millimeter waves reflected by the object. Based on the object detection information received from the millimeter waves, the millimeter-wave sensor 2 can detect the position or movement of the object. The pattern of the reflected waves received by the millimeter-wave sensor 2 varies depending on the shape, size (physique, in the case of an occupant), and movement of the occupant or object. The occupant and object can be identified based on the millimeter-wave reflection pattern. For example, the seat in the vehicle cabin in which the occupant is seated can be detected based on the irradiation range of the millimeter waves emitted from the millimeter-wave sensor 2.

[0016] (Door Sensor) The door sensor 3 is a sensor for detecting the open / closed state of a vehicle door. For example, when a door is opened, the door sensor 3 detects the operation. The door sensor 3 can detect the state of the door using magnetic, pressure, light, or other signals generated when the door is opened or closed. When the door sensor 3 detects a door opening / closing event, it can be assumed that a vehicle entry / exit event has occurred. For example, when the door sensor 3 detects that a vehicle door has been opened, it can be determined that an occupant is attempting to enter the vehicle from outside the vehicle, and when the door sensor 3 detects that the door has been closed, it can be determined that an occupant is attempting to exit the vehicle from inside the vehicle.

[0017] (Camera) The camera 4 is an imaging device that captures images of the interior of the vehicle. For example, the camera 4 captures images of the seating area in the vehicle and captures the image data in real time. The captured image can be used to detect the presence of occupants in the driver's seat or rear seats. The presence of occupants can be detected by analyzing the captured image data. The positions (seating positions) and number of occupants can be determined based on the results of analyzing image patterns that indicate the occupants' body characteristics or the shape of the seats.

[0018] (Vehicle Height Sensor) The vehicle height sensor 5 is a sensor that detects the height of the vehicle from the ground. For example, the vehicle height sensor 5 is attached to the suspension or chassis of the vehicle. Typically, a pressure sensor or a distance sensor is used as the vehicle height sensor 5. The vehicle height sensor 5 detects each change in the vehicle height. The vehicle height sensor 5 can detect the weight and position of a vehicle occupant. For example, when an occupant sits in the vehicle, the vehicle height changes due to the weight of the occupant, and the vehicle height sensor 5 detects this change. Furthermore, since the vehicle height changes depending on the seating position, the vehicle height sensor 5 can also detect the seating position of the occupant.

[0019] (Weight Sensor) The weight sensor 6 is a sensor that detects the weight of the vehicle. Generally, the weight sensor 6 is attached to a seat of the vehicle. The sensor is placed on the seat cushion or under the seat belt, etc., and detects the weight of the occupant. The weight sensor 6 can detect an occupant by measuring the pressure or displacement generated by the weight of the occupant. For example, when an occupant sits in the seat, the pressure applied to the sensor changes depending on the occupant's weight. The weight sensor 6 detects this change in pressure, and if the change in pressure corresponds to a certain weight or more, it can determine that the occupant is an occupant.

[0020] (Air Pressure Sensor) The air pressure sensor 7 is a sensor that can detect the air pressure of a vehicle tire in real time. Generally, the air pressure sensor 7 is attached directly to the wheel of the vehicle and detects the air pressure inside the tire in real time. When an object enters the vehicle compartment, the weight of the object compresses the tire, causing a change in the tire air pressure. The air pressure sensor 7 detects this change in air pressure. If the tire air pressure detected by the air pressure sensor 7 increases compared to before the vehicle got in, it can be determined that an occupant is present in the vehicle compartment.

[0021] (Storage Unit) The storage unit 8 stores information used in the arithmetic processing by the discrimination unit 13. For example, the storage unit 8 is a storage device included in a computer functioning as the occupant discrimination device 1, such as a hard disk drive (HDD) or a solid state drive (SSD). The storage unit 8 may be any storage device accessible by the occupant discrimination device 1 and may be provided external to the occupant discrimination device 1. For example, when an object is detected in the process of determining whether an occupant has gotten in or out of the vehicle, the seating position of the occupant, or the physique information of the occupant, the storage unit 8 stores object detection information including position information of the object detected by the millimeter wave sensor 2, the distance between the millimeter wave sensor 2 and the object, and the height and shape of the object.

[0022] (Communication Unit) The communication unit 9 communicates between the occupant classification device 1 and an external device. For example, the communication unit 9 transmits the occupant classification result from the discrimination unit 13 to the external device. The external device may be a driving assistance device that provides driving assistance using the occupant classification result. Furthermore, when the discrimination unit 13 performs occupant classification using a trained model stored in an external storage device, the communication unit 9 may transmit detection information to the external storage device, input the detection information to the trained model, and receive the occupant classification result output by the trained model via the communication unit 9 and output it to the discrimination unit 13.

[0023] (Basic Configuration of Occupant Discrimination Device) The occupant discrimination device 1 includes a first sensor information acquisition unit 11, a second sensor information acquisition unit 12, and a discrimination unit 13. For example, the occupant discrimination device 1 is realized by a computer. A memory included in the computer stores a program constituting an information processing application for realizing each function of the first sensor information acquisition unit 11, the second sensor information acquisition unit 12, and the discrimination unit 13. A processor included in the computer executes the information processing application read from the memory, thereby realizing each function of the first sensor information acquisition unit 11, the second sensor information acquisition unit 12, and the discrimination unit 13.

[0024] (First Sensor Information Acquisition Unit) The first sensor information acquisition unit 11 acquires detection information about the interior of the vehicle detected by the millimeter-wave sensor 2. The first sensor information acquisition unit 11 is connected to the millimeter-wave sensor 2 via a wired or wireless signal line. The millimeter-wave sensor 2 receives reflected waves from an object present in the vehicle interior and generates data for obtaining information such as the distance to the object or the position of the object based on the signal of the received reflected waves. The first sensor information acquisition unit 11 acquires the data generated by the millimeter-wave sensor 2 via the signal line as detection information. This detection information is subjected to signal processing such as noise removal, filtering, data smoothing, and feature extraction by the millimeter-wave sensor 2 or the first sensor information acquisition unit 11.

[0025] For example, the first sensor information acquisition unit 11 acquires detection information from the millimeter wave sensor 2 in response to an information acquisition instruction from the second sensor information acquisition unit 12. The detection information acquired by the first sensor information acquisition unit 11 is output to the determination unit 13. Note that the first sensor information acquisition unit 11 may acquire the detection information from the millimeter wave sensor 2 at a preset cycle.

[0026] (Second Sensor Information Acquisition Unit) The second sensor information acquisition unit 12 acquires detection information from at least one of the camera 4 that captures images of the interior of the vehicle, the vehicle height sensor 5 that detects the height of the vehicle from the ground, the weight sensor 6 that detects the weight of the vehicle, and the air pressure sensor 7 that detects the air pressure of the vehicle's tires, in addition to the detection information from the door sensor 3. The second sensor information acquisition unit 12 is connected to the second sensors, namely the door sensor 3, the camera 4, the vehicle height sensor 5, the weight sensor 6, and the air pressure sensor 7, via wired or wireless signal lines.

[0027] For example, while the occupant discrimination device 1 is activated, the second sensor information acquisition unit 12 waits for detection information from the door sensor 3. Upon acquiring detection information from the door sensor 3, the second sensor information acquisition unit 12 outputs the information acquisition instruction to the first sensor information acquisition unit 11, and further acquires detection information from at least one of the camera 4, the vehicle height sensor 5, the weight sensor 6, and the tire pressure sensor 7. The sensor that acquires the detection information at this time is a sensor that has been preset in the second sensor information acquisition unit 12.

[0028] In this way, the second sensor information acquisition unit 12 acquires detection information from various sensors in response to the detection of the opening and closing of a vehicle door. The detection information acquired by the second sensor information acquisition unit 12 is output to the determination unit 13. Note that the second sensor information acquisition unit 12 may acquire detection information from at least one of the camera 4, the vehicle height sensor 5, the weight sensor 6, and the air pressure sensor 7, in addition to the detection information from the door sensor 3, as detection information used to determine whether a passenger has gotten in or out of the vehicle. In this case as well, the second sensor information acquisition unit 12 acquires detection information from the other sensors in response to the detection of the opening and closing of a vehicle door by the door sensor 3.

[0029] (Discrimination Unit) The discrimination unit 13 determines whether an occupant has gotten in or out of the vehicle, triggered by detecting the opening or closing of a vehicle door, based on the detection information acquired by the first sensor information acquisition unit 11 and the detection information acquired by the second sensor information acquisition unit 12, and further discriminates between occupants and objects by determining at least one of the seating position of the occupant, physical information of the occupant, or whether an object other than the occupant has been loaded or unloaded. For example, the discrimination unit 13 determines the seating position of the occupant, physical information of the occupant, or whether an object other than the occupant has been loaded or unloaded by mainly using the detection information acquired by the millimeter wave sensor 2 and auxiliary using the detection information of other sensors.

[0030] (Determination of getting in and out) The determination unit 13 determines whether an occupant has gotten in or out based on the detection result of the door opening and closing by the door sensor 3. For example, the determination unit 13 stores in the memory unit 8 whether the state when the door opening and closing is first detected is getting in or getting out, and each time the door opening and closing is detected thereafter, the determination unit 13 determines whether an occupant has gotten in or out based on the previous detection state. For example, if the door opening and closing is first detected and getting in is stored, and then the door opening and closing is detected again, the determination unit 13 presumes that the occupant has opened and closed the door to get out, and determines that the occupant has gotten out.

[0031] Furthermore, the determination unit 13 may determine whether an occupant has gotten in or out of the vehicle by combining the detection result of the door opening and closing by the door sensor 3 with detection information from a sensor other than the door sensor 3. For example, the determination unit 13 detects whether an occupant has gotten in or out of the vehicle by combining the detection information from the millimeter wave sensor 2 with the detection result of the door opening and closing by the door sensor 3. When the determination unit 13 detects whether a door has opened or closed, the determination unit 13 analyzes the detection information from the millimeter wave sensor 2 and determines that an occupant near the door has gotten out of the vehicle if it detects that the occupant is moving out of the vehicle compartment, and determines that an occupant near the door has gotten in the vehicle if it detects that the occupant is moving into the vehicle compartment.

[0032] The discrimination unit 13 also detects whether an occupant has gotten in or out of the vehicle by combining the detection result of the door opening / closing by the door sensor 3 with the captured image by the camera 4. When the door opening / closing is detected, the discrimination unit 13 analyzes the captured image and determines that an occupant near the door has gotten out of the vehicle if a captured image is obtained showing an occupant moving out of the vehicle compartment, and determines that an occupant has gotten in if a captured image is obtained showing an occupant near the door moving into the vehicle compartment. Furthermore, the discrimination unit 13 may determine whether an occupant has gotten in or out of the vehicle by combining the detection result of the door opening / closing by the door sensor 3 with the detection result of an increase or decrease in vehicle height by the vehicle height sensor 5. For example, the discrimination unit 13 determines that an occupant has gotten out if the vehicle height increases, and determines that an occupant has gotten in if the vehicle height decreases. Furthermore, the discrimination unit 13 may determine whether an occupant has gotten in or out of the vehicle by combining the detection result of the door opening / closing by the door sensor 3 with the detection result of an increase or decrease in weight by the weight sensor 6. For example, the discrimination unit 13 determines that an occupant has gotten out if the weight decreases, and determines that an occupant has gotten in if the weight increases. Furthermore, the determination unit 13 may determine whether a passenger has got in or out of the vehicle by combining the detection result of door opening / closing by the door sensor 3 with the detection result of an increase or decrease in tire air pressure by the air pressure sensor 7. For example, the determination unit 13 can determine that a passenger has gotten out of the vehicle if the air pressure is low, and that a passenger has gotten in if the air pressure is high.

[0033] (Seating Position Determination) The discrimination unit 13 determines the seating position of the occupant based on the detection information of the millimeter wave sensor 2. The millimeter wave sensor 2 is used to detect the position or movement of an object inside the vehicle. The discrimination unit 13 determines the shape and size of the object using the detection information of the millimeter wave sensor 2, and further determines the distance or direction to the object. When the discrimination unit 13 determines that the object is an occupant based on the shape and size of the object, it determines the position of the occupant to be the seating position.

[0034] Furthermore, the determination unit 13 may determine the seating position of the occupant by combining the detection information from the millimeter wave sensor 2 with the detection information from a sensor other than the millimeter wave sensor 2. For example, the determination unit 13 determines the seating position of the occupant by combining the detection information from the millimeter wave sensor 2 with the detection information from the door sensor 3. When the opening or closing of a door is detected, the determination unit 13 analyzes the detection information from the millimeter wave sensor 2 and determines that the position to which the occupant has moved from near the door to a certain position within the vehicle cabin is the seating position of the occupant.

[0035] The determination unit 13 may also determine the seating position of the occupant by combining the detection information from the millimeter-wave sensor 2 with the captured image from the camera 4. For example, the determination unit 13 may determine, as the seating position of the occupant, a position where the position of the occupant obtained by analyzing the detection information from the millimeter-wave sensor 2 matches the position of the occupant captured in the captured image. The determination unit 13 may also determine whether the occupant has gotten in or out of the vehicle by combining the detection information from the millimeter-wave sensor 2 with the detection result from the vehicle height sensor 5. For example, when the determination unit 13 analyzes the detection information from the millimeter-wave sensor 2 to determine the position of an object and confirms that the presence of the object has caused a change in vehicle height corresponding to the range of typical human weight, the determination unit 13 determines the position of the object as the seating position of the occupant. The determination unit 13 may also determine the seating position of the occupant by combining the detection information from the millimeter-wave sensor 2 with the detection result from the weight sensor 6. For example, when the determination unit 13 analyzes the detection information of the millimeter-wave sensor 2 to determine the position of an object and, if the presence of the object results in a change in weight within the range of a typical human weight, the determination unit 13 determines the position of the object as the seating position of the occupant. Furthermore, the determination unit 13 may determine the seating position of the occupant by combining the detection information of the millimeter-wave sensor 2 with the tire air pressure detection result of the air pressure sensor 7. For example, when the determination unit 13 analyzes the detection information of the millimeter-wave sensor 2 to determine the position of an object and, if the presence of the object results in a change in tire air pressure within the range of a typical human weight, the determination unit 13 determines the position of the object as the seating position of the occupant.

[0036] (Physique Determination) The determination unit 13 determines the physique of the occupant based on the detection information of the millimeter wave sensor 2. For example, the millimeter wave sensor 2 is used to detect the position or movement of an object inside the vehicle. The determination unit 13 determines the physique of the occupant by comparing the size of an area from which a reflected wave from the occupant is obtained, which is included in the detection information of the millimeter wave sensor 2, with a threshold value. For example, the determination unit 13 determines that the occupant has an adult physique if the size of the area is within the range of an adult physique. Alternatively, the determination unit 13 determines that the occupant has a child physique if the size of the area is within the range of a child physique.

[0037] Furthermore, the determination unit 13 may determine the physique of the occupant by combining the detection information from the millimeter wave sensor 2 with the detection information from a sensor other than the millimeter wave sensor 2. For example, the determination unit 13 determines the size of an object by combining the detection information from the millimeter wave sensor 2 with the detection information from the door sensor 3. When the opening and closing of a door is detected, the determination unit 13 analyzes the detection information from the millimeter wave sensor 2, and if the object moves from near the door to a certain position in the vehicle cabin, determines that the object is an occupant, and compares the size of the object obtained from the detection information from the millimeter wave sensor 2 with a threshold value to determine the physique of the occupant.

[0038] The determination unit 13 may also determine the seating position of the occupant by combining the detection information from the millimeter-wave sensor 2 with the captured image from the camera 4. For example, the determination unit 13 compares the size of the occupant obtained by analyzing the detection information from the millimeter-wave sensor 2 with the size of the occupant shown in the captured image obtained by analyzing the captured image, and determines the physique of the occupant based on the result of comparing both with a threshold. The determination unit 13 may also determine the physique of the occupant by combining the detection information from the millimeter-wave sensor 2 with the detection result from the vehicle height sensor 5. For example, when the determination unit 13 analyzes the detection information from the millimeter-wave sensor 2 to determine the size of an object and, due to the presence of the object, confirms a change in vehicle height that corresponds to a weight range for different human body sizes, the determination unit 13 determines the physique of the occupant based on the weight corresponding to the change in vehicle height. The determination unit 13 may also determine the physique of the occupant by combining the detection information from the millimeter-wave sensor 2 with the detection result from the weight sensor 6. For example, the discrimination unit 13 analyzes the detection information of the millimeter-wave sensor 2 to determine the size of an object, and if a change in weight within a weight range for each human body type due to the presence of the object is confirmed, the discrimination unit 13 determines the body type of the weight corresponding to the change in weight as the body type of the occupant. Furthermore, the discrimination unit 13 may determine the seating position of the occupant by combining the detection information of the millimeter-wave sensor 2 with the tire air pressure detection result of the air pressure sensor 7. For example, the discrimination unit 13 analyzes the detection information of the millimeter-wave sensor 2 to determine the size of an object, and if a change in air pressure within a weight range for each human body type due to the presence of the object is confirmed, the discrimination unit 13 determines the body type of the weight corresponding to the change in air pressure as the body type of the occupant.

[0039] (Determination of Loading and Unloading) The determination unit 13 determines whether luggage has been loaded or unloaded based on the detection information of the millimeter wave sensor 2. For example, when the determination unit 13 analyzes the detection information of the millimeter wave sensor 2 and detects that the size of the detected object is within the size range of luggage or the like other than a human, and detects that the object is moving outside the vehicle compartment, the determination unit 13 determines that luggage has been loaded or unloaded.

[0040] Furthermore, the determination unit 13 may determine whether luggage has been loaded or unloaded by combining the detection information from the millimeter wave sensor 2 with the detection information from a sensor other than the millimeter wave sensor 2. For example, the determination unit 13 determines whether luggage has been loaded or unloaded by combining the detection information from the millimeter wave sensor 2 with the detection information from the door sensor 3. When the determination unit 13 detects that a door has been opened or closed, it analyzes the detection information from the millimeter wave sensor 2, and determines that luggage has been unloaded if it detects that an object is moving from near the door to the outside of the vehicle compartment.

[0041] The determination unit 13 may also determine whether luggage is being unloaded by combining the detection information from the millimeter-wave sensor 2 with the captured image from the camera 4. For example, the determination unit 13 analyzes the detection information from the millimeter-wave sensor 2 to detect a state in which an object is moving out of the vehicle cabin from near the door, and then performs image analysis on the captured image to determine that the object shown in the captured image is luggage, and then determines that luggage is being unloaded. The determination unit 13 may also determine whether luggage is being unloaded by combining the detection information from the millimeter-wave sensor 2 with the detection result from the vehicle height sensor 5. For example, the determination unit 13 analyzes the detection information from the millimeter-wave sensor 2 to detect a state in which an object is moving out of the vehicle cabin from near the door, and then determines that a change in vehicle height corresponding to the weight range of a typical luggage due to the presence of the object is a change in vehicle height corresponding to the weight range of a typical luggage. The determination unit 13 may also determine whether luggage is being unloaded by combining the detection information from the millimeter-wave sensor 2 with the detection result from the weight sensor 6. For example, when the discrimination unit 13 analyzes the detection information from the millimeter-wave sensor 2 and detects that an object is moving out of the vehicle cabin from near the door, and when a change in weight corresponding to a range of typical luggage weight is confirmed due to the presence of the object, the discrimination unit 13 determines that the movement of the object is loading / unloading of luggage. Furthermore, the discrimination unit 13 may determine that luggage is being loaded / unloaded by combining the detection information from the millimeter-wave sensor 2 with the tire air pressure detection result from the air pressure sensor 7. For example, when the discrimination unit 13 analyzes the detection information from the millimeter-wave sensor 2 and detects that an object is moving out of the vehicle cabin from near the door, and when a change in air pressure corresponding to a range of typical luggage weight is confirmed due to the presence of the object, the discrimination unit 13 determines that the movement of the object is loading / unloading of luggage.

[0042] Next, an occupant discrimination method according to the first embodiment will be described. FIG. 2 is a flowchart showing the occupant discrimination method according to the first embodiment. The door sensor 3 detects whether a vehicle door is opened or closed. Furthermore, since opening a vehicle door is accompanied by unlocking the door and closing a vehicle door is accompanied by locking the door, the door sensor 3 may detect whether the vehicle door is unlocked or locked. The second sensor information acquisition unit 12 acquires detection information on whether the vehicle door is opened or closed from the door sensor 3 (step ST1). The second sensor information acquisition unit 12 outputs the detection information of the door sensor 3 to the discrimination unit 13, and further outputs an information acquisition instruction to the first sensor information acquisition unit 11.

[0043] In response to the information acquisition instruction, the first sensor information acquisition unit 11 acquires detection information from the millimeter wave sensor 2 (step ST2). The detection information from the millimeter wave sensor 2 acquired by the first sensor information acquisition unit 11 is output to the determination unit 13. The determination unit 13 determines whether an occupant has gotten in or out of the vehicle based on the detection information from the millimeter wave sensor 2 (step ST3). For example, the determination unit 13 may determine whether an occupant has gotten in or out of the vehicle based on object detection information stored in the storage unit 8, which will be described later in step ST8. For example, the determination unit 13 analyzes object position information, the distance between the millimeter wave sensor 2 and the object, and the height and shape of the object, which are included in the object detection information, to determine whether the object is an occupant and, if so, to identify the occupant's destination. As a result, if the object is an occupant and the occupant's destination is within or outside the vehicle, it is determined that the occupant has gotten in or out of the vehicle.

[0044] If it is determined that an occupant has got in or out of the vehicle (step ST3; YES), the discrimination unit 13 outputs an information acquisition instruction to the second sensor information acquisition unit 12. In response to the information acquisition instruction, the second sensor information acquisition unit 12 acquires detection information from at least one of the door sensor 3, the camera 4, the vehicle height sensor 5, the weight sensor 6, and the tire pressure sensor 7 (step ST4). The detection information acquired by the second sensor information acquisition unit 12 is output to the discrimination unit 13.

[0045] The determination unit 13 determines the seating position or physique of the occupant based on the detection information acquired by the first sensor information acquisition unit 11 and the detection information acquired by the second sensor information acquisition unit 12 (step ST5). By using detection information from at least one of the door sensor 3, the camera 4, the vehicle height sensor 5, the weight sensor 6, and the air pressure sensor 7 in addition to the detection information from the millimeter-wave sensor 2, the seating position or physique of the occupant can be determined more accurately than when the millimeter-wave sensor 2 is used alone. Using the determination result of the seating position or physique of the occupant can also improve the accuracy of the airbag deployment control of the vehicle.

[0046] If it is determined that no passengers have got in or out of the vehicle (step ST3; NO), the discrimination unit 13 determines whether or not an object has been loaded or unloaded (step ST6). If it is determined that an object has been loaded or unloaded (step ST6; YES), the discrimination unit 13 outputs an information acquisition instruction to the second sensor information acquisition unit 12. In response to the information acquisition instruction, the second sensor information acquisition unit 12 acquires detection information from at least one of the door sensor 3, the camera 4, the vehicle height sensor 5, the weight sensor 6, and the tire pressure sensor 7 (step ST7). The detection information acquired by the second sensor information acquisition unit 12 is output to the discrimination unit 13.

[0047] When an object is detected during the process of determining whether an occupant has gotten in or out of the vehicle, the seating position of the occupant, or the physique of the occupant based on the detection information acquired by the first sensor information acquisition unit 11 and the detection information acquired by the second sensor information acquisition unit 12, the determination unit 13 generates object detection information including position information of the object detected by the millimeter-wave sensor 2, the distance between the millimeter-wave sensor 2 and the object, the height and shape of the object, or the orientation (direction) of the object (step ST8). The determination unit 13 stores the object detection information in the storage unit 8 (step ST9).

[0048] The determination unit 13 may determine whether an occupant has gotten in or out of the vehicle or whether an object has been loaded or unloaded, based on the object detection information stored in the storage unit 8. For example, the determination unit 13 analyzes the object's position information, the distance between the millimeter wave sensor 2 and the object, and the height and shape of the object, which are included in the object detection information, to determine whether the object is luggage and, if it is luggage, to identify its destination. As a result, if the object is luggage and the destination of the luggage is outside the vehicle cabin, it is determined that loading or unloading has occurred from the vehicle.

[0049] Next, the discrimination unit 13 determines that the state in which an object is piled at the same position is maintained and omits the detection operation until the door for which opening and closing was first detected opens and closes, or until the detection information of the second sensor for the door for which opening and closing was first detected changes (step ST10). That is, when the discrimination unit 13 detects door opening and closing or a change in weight at a position in the vehicle interior where it was determined that an object has been loaded or unloaded, the discrimination unit 13 determines that the state in which an object is piled at that position is maintained and stops detecting an occupant at that position. In this case, since no occupant is seated at the position (seat) where the object is piled, occupant detection is unnecessary, and power consumption of the occupant discrimination device 1 can be reduced.

[0050] If it is determined that no object is being loaded or unloaded (step ST6; NO), the discrimination unit 13 determines that it cannot clearly distinguish whether the object is a passenger or an object, and outputs an information acquisition instruction to the second sensor information acquisition unit 12. In response to the information acquisition instruction, the second sensor information acquisition unit 12 acquires detection information from at least one of the door sensor 3, the camera 4, the vehicle height sensor 5, the weight sensor 6, and the tire pressure sensor 7 (step ST11). The detection information acquired by the second sensor information acquisition unit 12 is output to the discrimination unit 13.

[0051] The determination unit 13 determines whether the weight has changed based on the detection information from the weight sensor 6 (step ST12). If it is determined that the weight has changed (step ST12; YES), the determination unit 13 determines whether the object can be estimated to be an occupant (step ST13). If the object can be estimated to be an occupant (step ST13; YES), the determination unit 13 determines whether the occupant has gotten in or out based on the detection information from the millimeter wave sensor 2 (step ST14).

[0052] Furthermore, if it is determined that the weight has not changed (step ST12; NO), the discrimination unit 13 determines that the door opening / closing in step ST1 does not involve passengers getting in or out of the vehicle or loading or unloading of luggage (step ST15). After this, the series of detection operations shown in FIG. 2 is stopped until a door opening / closing is detected again. That is, if the discrimination unit 13 determines that no passengers have gotten in or out of the vehicle and no objects have been loaded or unloaded, and if there is no change in weight, it finally determines that no passengers have gotten in or out of the vehicle and no objects have been loaded or unloaded. This suppresses unnecessary detection operations, thereby reducing the power consumption of the occupant discrimination device 1.

[0053] On the other hand, if the object cannot be estimated to be an occupant (step ST13; NO), the discrimination unit 13 determines that the object is an object (step ST16). Next, when an object is detected during the process of determining whether an occupant has gotten in or out of the vehicle, the seating position of the occupant, or the physique of the occupant based on the detection information acquired by the first sensor information acquisition unit 11 and the detection information acquired by the second sensor information acquisition unit 12, the discrimination unit 13 generates object detection information including position information of the object detected by the millimeter-wave sensor 2, the distance between the millimeter-wave sensor 2 and the object, the height and shape of the object, or the orientation (direction) of the object (step ST17). The discrimination unit 13 stores the object detection information in the storage unit 8 (step ST18).

[0054] The discrimination unit 13 determines that the state in which an object is piled at the same position is maintained and omits the detection operation until the door for which opening and closing was first detected opens and closes, or until the detection information of the second sensor for the door for which opening and closing was first detected changes (step ST19). That is, when the discrimination unit 13 detects door opening and closing or a change in weight at a position in the vehicle interior where it was determined that an object has been loaded or unloaded, the discrimination unit 13 determines that the state in which an object is piled at that position is maintained and stops detecting an occupant at that position. In this case, since no occupant is seated at the position (seat) where the object is piled, occupant detection is not necessary, and power consumption of the occupant discrimination device 1 can be reduced.

[0055] When the detection information acquired by the first sensor information acquisition unit 11 and the detection information acquired by the second sensor information acquisition unit 12 are input, the discrimination unit 13 discriminates occupants and objects using a machine learning model that outputs a discrimination result of whether an occupant has gotten in or out of the vehicle, as well as at least one of the following: the seating position of the occupant, physique information of the occupant, or the loading or unloading of an object other than the occupant. The machine learning model may be, for example, a Transformer, BERT, or GPT-3 model, and is trained by machine learning to accept the detection information as input and output information indicating the discrimination result. The machine learning model is stored, for example, in the storage unit 8. Alternatively, the machine learning model may be stored in an external storage device that is provided separately from the occupant discrimination device 1 and is communicatively connectable. In this case, the discrimination unit 13 controls the communication unit 9 to communicate with the external storage device. The machine learning model stored in the external storage device receives the detection information transmitted from the discrimination unit 13 via the communication unit 9, and the discrimination result information output from the machine learning model is received by the communication unit 9 and acquired by the discrimination unit 13.

[0056] Next, a description will be given of the hardware configuration that realizes the functions of the occupant classification device 1. The functions of the first sensor information acquisition unit 11, the second sensor information acquisition unit 12, and the discrimination unit 13 provided in the occupant classification device 1 are realized by processing circuits. That is, the occupant classification device 1 includes a processing circuit for executing the processes of steps ST1 to ST19 shown in Fig. 2. The processing circuit may be dedicated hardware, or may be a CPU (Central Processing Unit) that executes a program stored in a memory.

[0057] Fig. 3A is a block diagram showing a hardware configuration that realizes the functions of the occupant classification device 1. Fig. 3B is a block diagram showing a hardware configuration that executes software that realizes the functions of the occupant classification device 1. In Figs. 3A and 3B, the first sensor information acquisition unit 11 and the second sensor information acquisition unit 12 acquire detection information from each sensor via an input interface 100. The discrimination unit 13 outputs the discrimination result to the storage unit 8 via an output interface 101. The discrimination unit 13 may also transmit the discrimination result to an external device via the output interface 101 through the communication unit 9.

[0058] 3A , the processing circuit 102 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof. The functions of the first sensor information acquisition unit 11, the second sensor information acquisition unit 12, and the discrimination unit 13 provided in the occupant discrimination device 1 may be realized by separate processing circuits, or these functions may be realized together by a single processing circuit.

[0059] 3B , the functions of the first sensor information acquisition unit 11, the second sensor information acquisition unit 12, and the determination unit 13 included in the occupant classification device 1 are realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in the memory 104.

[0060] The processor 103 reads and executes programs stored in the memory 104 to realize the functions of the first sensor information acquisition unit 11, the second sensor information acquisition unit 12, and the discrimination unit 13 included in the occupant classification device 1. For example, the occupant classification device 1 includes the memory 104 for storing programs that, when executed by the processor 103, result in the execution of the processes from step ST1 to step ST19 shown in FIG. 2 . These programs cause a computer to execute the procedures or methods of the processes performed by the first sensor information acquisition unit 11, the second sensor information acquisition unit 12, and the discrimination unit 13. The memory 104 may be a computer-readable storage medium that stores programs for causing a computer to function as the first sensor information acquisition unit 11, the second sensor information acquisition unit 12, and the discrimination unit 13.

[0061] The memory 104 may be, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), or an EEPROM (Electrically-EPROM) (registered trademark), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD.

[0062] Some of the functions of the first sensor information acquisition unit 11, the second sensor information acquisition unit 12, and the discrimination unit 13 included in the occupant discrimination device 1 may be realized by dedicated hardware, and other functions may be realized by software or firmware. For example, the functions of the first sensor information acquisition unit 11 and the second sensor information acquisition unit 12 may be realized by a processing circuit 102 that is dedicated hardware, and the function of the discrimination unit 13 may be realized by the processor 103 reading and executing a program stored in the memory 104. In this way, the processing circuit can realize the above functions by hardware, software, firmware, or a combination of these.

[0063] As described above, the occupant discrimination device 1 according to the first embodiment includes the first sensor information acquisition unit 11 that acquires detection information about the interior of the vehicle detected by the millimeter-wave sensor 2, the second sensor information acquisition unit 12 that acquires detection information from at least one of the camera 4 that captures images of the interior of the vehicle, the vehicle height sensor 5 that detects the height of the vehicle from the ground, the weight sensor 6 that detects the weight of the vehicle, and the air pressure sensor 7 that detects the air pressure of the vehicle tires, in addition to detection information from the door sensor 3 that detects whether the vehicle doors are opened or closed, and the discrimination unit 13 that determines whether an occupant has gotten in or out of the vehicle based on the detection information acquired by the first sensor information acquisition unit 11 and the detection information acquired by the second sensor information acquisition unit 12, in response to detection of the opening or closing of the vehicle door, and further discriminates occupants and objects by determining at least one of the seating position of the occupant, physical information about the occupant, and whether any object other than the occupant has been loaded or unloaded. This enables the occupant discrimination device 1 to accurately discriminate occupants and objects in the vehicle interior.

[0064] The occupant classification device 1 according to the first embodiment includes a storage unit 8. When an object is detected during the process of determining whether an occupant has gotten in or out of the vehicle, the seating position of the occupant, or the physical build information of the occupant, the classification unit 13 stores object detection information including position information of the object detected by the millimeter-wave sensor 2, the distance between the millimeter-wave sensor 2 and the object, and the height and shape of the object in the storage unit 8. By using the object detection information stored in the storage unit 8, it is no longer necessary to detect a new occupant, and power consumption of the occupant classification device 1 can be reduced.

[0065] In the occupant discrimination device 1 according to the first embodiment, the discrimination unit 13 determines whether an occupant has gotten in or out of the vehicle or whether an object has been loaded or unloaded, based on the object detection information stored in the storage unit 8. This makes it possible to accurately determine whether an occupant has gotten in or out of the vehicle or whether an object has been loaded or unloaded.

[0066] In the occupant discrimination device 1 according to the first embodiment, when the detection information acquired by the first sensor information acquisition unit 11 and the detection information acquired by the second sensor information acquisition unit 12 are input, the discrimination unit 13 discriminates occupants and objects using a machine learning model that outputs, in addition to a discrimination result as to whether an occupant has gotten in or out of the vehicle, at least one of a seating position of the occupant, physical information of the occupant, or a discrimination result as to whether an object other than the occupant has been loaded or unloaded. By using the machine learning model, in addition to a discrimination result as to whether an occupant has gotten in or out of the vehicle, it is possible to discriminate the seating position of the occupant, physical information of the occupant, or whether an object other than the occupant has been loaded or unloaded.

[0067] In the occupant discrimination device 1 according to the first embodiment, when a door opening / closing is detected or a weight change occurs at a position in the vehicle interior where it has been determined that an object has been loaded or unloaded, the discrimination unit 13 determines that the state in which an object is loaded at that position is maintained and stops detecting an occupant at that position. This eliminates the need to detect an occupant, thereby enabling a reduction in power consumption of the occupant discrimination device 1.

[0068] In the occupant discrimination device 1 according to the first embodiment, when it is determined that no occupants have gotten in or out of the vehicle and no objects have been loaded or unloaded, and there is no change in weight, the discrimination unit 13 finally determines that no occupants have gotten in or out of the vehicle and no objects have been loaded or unloaded. This suppresses unnecessary detection operations, thereby reducing the power consumption of the occupant discrimination device 1.

[0069] The occupant discrimination method according to the first embodiment includes the steps of: a first sensor information acquisition unit 11 acquiring detection information about the interior of the vehicle detected by the millimeter-wave sensor 2; a second sensor information acquisition unit 12 acquiring detection information from at least one of a camera 4 capturing an image of the interior of the vehicle, a vehicle height sensor 5 detecting the height of the vehicle from the ground, a weight sensor 6 detecting the weight of the vehicle, and an air pressure sensor 7 detecting the air pressure of tires of the vehicle, in addition to the detection information from the door sensor 3; and a discrimination unit 13 determining whether an occupant has entered or exited the vehicle based on the detection information acquired by the first sensor information acquisition unit 11 and the detection information acquired by the second sensor information acquisition unit, in response to detection of the opening or closing of a vehicle door, and further discriminating between an occupant and an object by determining at least one of the seating position of the occupant, physical information about the occupant, and whether an object other than the occupant has been loaded or unloaded. By executing the above method, the occupant discrimination device 1 can accurately discriminate between an occupant and an object in the vehicle interior.

[0070] The computer that executes the program according to the first embodiment functions as a first sensor information acquisition unit 11 that acquires detection information in the vehicle interior detected by the millimeter wave sensor 2, a second sensor information acquisition unit 12 that acquires detection information from at least one of the following: a camera 4 that captures images of the vehicle interior, a vehicle height sensor 5 that detects the height of the vehicle from the ground, a weight sensor 6 that detects the weight of the vehicle, and an air pressure sensor 7 that detects the air pressure of the vehicle's tires, in addition to the detection information from the door sensor 3, and a discrimination unit 13 that determines whether an occupant has gotten in or out of the vehicle based on the detection information acquired by the first sensor information acquisition unit 11 and the detection information acquired by the second sensor information acquisition unit 12, in response to detection of the opening or closing of a vehicle door, and further determines at least one of the seating position of the occupant, physical information of the occupant, and whether an object other than the occupant has been loaded or unloaded, thereby discriminating between the occupant and the object. Execution of the program by the computer enables accurate discrimination of the occupant and the object in the vehicle interior.

[0071] Any of the components of the embodiments may be modified or omitted.

[0072] The occupant discrimination device according to the present disclosure can be used, for example, to control the deployment of an airbag.

[0073] 1 Occupant discrimination device, 2 Millimeter wave sensor, 3 Door sensor, 4 Camera, 5 Vehicle height sensor, 6 Weight sensor, 7 Air pressure sensor, 8 Memory unit, 9 Communication unit, 11 First sensor information acquisition unit, 12 Second sensor information acquisition unit, 13 Discrimination unit, 100 Input interface, 101 Output interface, 102 Processing circuit, 103 Processor, 104 Memory.

Claims

1. An occupant discrimination device comprising: a first sensor information acquisition unit that acquires detection information from a first sensor, a millimeter wave sensor, inside the vehicle cabin; a second sensor information acquisition unit that acquires detection information from a second sensor, different from the first sensor, including a door sensor that detects whether a door of the vehicle is opened or closed, as well as detection information from at least one of a camera that captures images of the inside of the vehicle cabin, a vehicle height sensor that detects the height of the vehicle from the ground, a weight sensor that detects the weight of the vehicle, or an air pressure sensor that detects the air pressure of tires of the vehicle; and a discrimination unit that determines whether an occupant has gotten in or out of the vehicle based on the detection information acquired by the first sensor information acquisition unit and the detection information acquired by the second sensor information acquisition unit, in response to detection of the door being opened or closed, and further discriminates the occupant and the object by determining at least one of the seating position of the occupant, physical information of the occupant, or whether an object other than the occupant has been loaded or unloaded.

2. An occupant discrimination device as described in claim 1, characterized in that it is equipped with a memory unit, and when the object is detected in the process of discriminating whether the occupant has got in or out, the seating position of the occupant, or the physique information of the occupant, the discrimination unit stores object detection information in the memory unit, including position information of the object detected by the first sensor, the distance between the first sensor and the object, and the height and shape of the object.

3. The occupant discrimination device according to claim 2, characterized in that the discrimination unit determines whether the occupant is getting on or off or whether the object is being loaded or unloaded based on the object detection information stored in the memory unit.

4. The occupant discrimination device of claim 1, characterized in that, when the detection information acquired by the first sensor information acquisition unit and the detection information acquired by the second sensor information acquisition unit are input, the discrimination unit discriminates the occupant and the object using a machine learning model that outputs, in addition to the discrimination result of whether the occupant has boarded or disembarked, at least one of the following discrimination results: the seating position of the occupant, the physique information of the occupant, or whether the object has been loaded or unloaded.

5. An occupant discrimination device as described in any one of claims 1 to 4, characterized in that, when a door opening or closing is detected or a change in weight occurs at a position within the vehicle interior where it has been determined that the object has been loaded or unloaded, the discrimination unit determines that the object remains loaded at that position and stops detecting the occupant at that position.

6. An occupant discrimination device as described in any one of claims 1 to 4, characterized in that if it is determined that the occupant has not gotten on or off the vehicle and that the object has not been loaded or unloaded, and there is no change in weight, the discrimination unit finally determines that the occupant has not gotten on or off the vehicle and that the object has not been loaded or unloaded.

7. An occupant discrimination method using an occupant discrimination device, comprising: a step in which a first sensor information acquisition unit acquires detection information from the interior of the vehicle detected by a millimeter wave sensor which is a first sensor; a step in which a second sensor information acquisition unit acquires detection information from at least one of a camera which captures images of the interior of the vehicle, a vehicle height sensor which detects the height of the vehicle from the ground, a weight sensor which detects the weight of the vehicle, or an air pressure sensor which detects the air pressure of the tires of the vehicle, in addition to detection information from a door sensor which detects the opening and closing of the door of the vehicle, as a second sensor different from the first sensor; and a step in which a discrimination unit determines whether an occupant has gotten in or out of the vehicle based on the detection information acquired by the first sensor information acquisition unit and the detection information acquired by the second sensor information acquisition unit, in response to the detection of the opening and closing of the door of the vehicle, and further discriminates the occupant and the object by determining at least one of the seating position of the occupant, physical information of the occupant, or whether an object other than the occupant has been loaded or unloaded.

8. A program for causing a computer to function as a discrimination unit that includes: a first sensor information acquisition unit that acquires detection information from the interior of the vehicle detected by a millimeter wave sensor that is a first sensor; a second sensor information acquisition unit that acquires detection information from a second sensor different from the first sensor, in addition to detection information from a door sensor that detects the opening and closing of the vehicle door, from at least one of a camera that captures images of the interior of the vehicle, a vehicle height sensor that detects the height of the vehicle from the ground, a weight sensor that detects the weight of the vehicle, or an air pressure sensor that detects the air pressure of the vehicle's tires; and a discrimination unit that determines whether an occupant has gotten in or out of the vehicle based on the detection information acquired by the first sensor information acquisition unit and the detection information acquired by the second sensor information acquisition unit, in response to the detection of the opening and closing of the vehicle door, and further determines at least one of the seating position of the occupant, physical information of the occupant, or whether an object other than the occupant has been loaded or unloaded, thereby discriminating between the occupant and the object.