Crew detection device and crew detection method

Abstract

To highly accurately detect an occupant regardless of the seating position of the occupant.SOLUTION: An occupant detection device includes: an acquisition unit configured to acquire point cloud information that indicates, based on the intensity of reflection wave generated when a transmission wave transmitted toward a cabin of a movable body is reflected on an object in the cabin, the position of the object moving in the cabin in a three-dimentional coordinate as point cloud including a plurality of detection points; a generation unit configured to generate, based on the point cloud information for each seat row including a plurality of seating areas, a seat row map that indicates the distribution of detection points in a planar region, which corresponds to the arrangement direction of the plurality of seating areas and the height direction of the movable body; a setting unit configured to set, on the seat row map, an upper end line along an upper end portion of a planar point cloud including the plurality of detection points; and an estimation unit configured to estimate the number of occupants for each seat row based on shape characteristics of the upper end line.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] Embodiments of the present invention relate to an occupant detection device and an occupant detection method.

Background Art

[0002] In a vehicle control system or the like, a device for detecting an occupant present in the vehicle interior is used. As such a device, there is a technique for detecting the number of occupants or the like based on data obtained by an electromagnetic wave sensor installed in the vehicle interior for transmitting and receiving electromagnetic waves and a seating sensor installed on each seat.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, according to the conventional technology as described above, when an occupant is not seated at a regular seating position, the occupant may not be accurately detected.

[0005] Therefore, an object of embodiments of the present invention is to provide an occupant detection device and an occupant detection method capable of detecting an occupant with high accuracy regardless of the seating position of the occupant.

Means for Solving the Problems

[0006] An occupant detection device according to one embodiment of the present invention includes: an acquisition unit that acquires point cloud information indicating the position of an object moving in a room as a point cloud including multiple detection points, based on the intensity of reflected waves generated when transmitted waves sent toward the room of a moving object are reflected by objects present in the room; a generation unit that generates a seat row map showing the distribution of detection points in a planar region corresponding to the arrangement direction of multiple seating areas and the height direction of the moving object for each seat row including multiple seating areas, based on the point cloud information; a setting unit that sets an upper boundary line along the upper end of the planar point cloud including multiple detection points on the seat row map; and an estimation unit that estimates the number of occupants for each seat row based on the shape characteristics of the upper boundary line.

[0007] According to the above configuration, the number of occupants for each seat row is estimated based on the shape characteristics of the upper boundary line set on the seat row map generated for each seat row. This allows for highly accurate detection of occupants regardless of their seating position.

[0008] Furthermore, in the above configuration, the estimation unit may estimate the number of occupants based on the number of peaks that protrude upward from the upper limit line.

[0009] With the above configuration, the number of occupants can be estimated with high accuracy based on the number of peaks corresponding to the occupants' heads.

[0010] Furthermore, in the above configuration, the estimation unit may estimate the occupant's seating position based on the position of the peaks in the direction of arrangement.

[0011] According to the above configuration, the seating position of the occupant can be estimated with high accuracy based on the position of the peak corresponding to the occupant's head.

[0012] Furthermore, in the above configuration, the setting unit may set the upper limit line based on detection points among a plurality of detection points included in the planar point cloud that are located in a region above a first threshold that is a predetermined distance higher from the seating surface.

[0013] According to the above configuration, false detections caused by moving objects other than the occupant's head (e.g., luggage) can be suppressed, and detection accuracy can be improved.

[0014] Furthermore, in the above configuration, the estimation unit may estimate the occupant's physique based on the position in the height direction of the peak where the upper limit line protrudes upward and a second threshold set above the first threshold.

[0015] According to the above configuration, the occupant's physique can be estimated with high accuracy based on the position of the peak corresponding to the occupant's head.

[0016] Furthermore, in the above configuration, the setting unit may set the upper boundary line by smoothing the values ​​of multiple detection points located at the upper end of the planar point cloud.

[0017] With the above configuration, it is possible to suppress the appearance of peaks in parts other than the head, thereby improving detection accuracy.

[0018] Furthermore, another embodiment of the present invention provides a method for detecting occupants, which includes the steps of: acquiring point cloud information that indicates the position of an object moving in a room as a point cloud including multiple detection points, based on the intensity of reflected waves generated when a transmitted wave sent toward the room of a moving object is reflected by an object present in the room; generating a seat row map based on the point cloud information that shows the distribution of detection points in a planar region corresponding to the arrangement direction of the multiple seating areas and the height direction of the moving object for each seat row including multiple seating areas; setting an upper boundary line along the upper end of the planar point cloud including multiple detection points on the seat row map; and estimating the number of occupants for each seat row based on the shape characteristics of the upper boundary line. [Brief explanation of the drawing]

[0019] [Figure 1] Figure 1 is a side view showing an example of the interior configuration of a vehicle equipped with the occupant detection device of the embodiment. [Figure 2] Figure 2 is a block diagram showing an example of the hardware configuration of the occupant detection device according to the embodiment. [Figure 3] FIG. 3 is a block diagram showing an example of the functional configuration of the occupant detection device according to the embodiment. [Figure 4] FIG. 4 is a diagram showing an example of the point cloud information according to the embodiment. [Figure 5] FIG. 5 is a diagram showing an example of the seat row map and the upper end line according to the embodiment. [Figure 6] FIG. 6 is a diagram showing an example of the upper end line when the occupant is not seated at the regular seating position in the embodiment. [Figure 7] FIG. 7 is a flowchart showing an example of the processing in the occupant detection device according to the embodiment. MODE FOR CARRYING OUT THE INVENTION

[0020] Hereinafter, exemplary embodiments of the present invention will be disclosed. The configurations of the embodiments shown below, as well as 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 it is possible to obtain at least one of various effects and derivative effects based on the basic configuration.

[0021] FIG. 1 is a side view showing an example of the configuration inside the passenger compartment R of the vehicle C on which the occupant detection device 1 according to the embodiment is mounted. In the figure, the X direction corresponds to the direction from the rear part to the front part of the vehicle C, the Y direction corresponds to the direction from the left side surface to the right side surface of the vehicle C, and the Z direction corresponds to the direction from the lower part to the upper part of the vehicle C.

[0022] The vehicle C is an example of a moving body, and can be, for example, an automobile or the like having an internal combustion engine, a motor, or both (hybrid mechanism) as a drive source. The vehicle C of the present embodiment is a so-called three-row seat vehicle, and includes a first seat row SR1, a second seat row SR2, and a third seat row SR3. The first seat row SR1 includes a driver's seat and a passenger seat.

[0023] The occupant detection device 1 is a device that detects occupants present in the vehicle compartment R. In this embodiment, the occupant detection device 1 that detects occupants located behind the first seat row SR1, i.e., in the second seat row SR2 and the third seat row SR3, will be described.

[0024] The occupant detection device 1 comprises a sensor 2 and an information processing device 3. The sensor 2 is installed on the ceiling 5 of the vehicle C, transmits a wave toward the passenger compartment R, and receives reflected waves generated when the transmitted wave is reflected by objects within the passenger compartment R. In this embodiment, the sensor 2 is installed behind the backrest of the first seat row SR1, and in the example shown in Figure 1, it is located approximately above the backrest of the second seat row SR2. The information processing device 3 is installed in the dashboard and is connected to the sensor 2 via a network such as CAN (Controller Area Network). Note that the installation locations of the sensor 2 and the information processing device 3 are not limited to those described above. Also, multiple sensors 2 may be installed.

[0025] Figure 2 is a block diagram showing an example of the hardware configuration of the occupant detection device 1 of the embodiment. Sensor 2 comprises a transmitter 21, a receiver 22, an ECU (Electronic Control Unit) 23, and an input / output unit 24. Transmitter 21 is a device that transmits (irradiates) electromagnetic waves of a predetermined frequency (e.g., 60 GHz to 65 GHz, etc.) as a transmitted wave into the vehicle interior R. Receiver 22 is a device that receives reflected waves generated when the transmitted wave is reflected by an object present in the vehicle interior R, and generates an electrical signal indicating the intensity of the reflected wave. Transmitter 21 and receiver 22 can be configured using, for example, an oscillator circuit, a piezoelectric element, an AD converter, an amplifier, a filter circuit, etc. Transmitter 21 and receiver 22 may be configured as separate units or as an integrated unit. ECU 23 is a microcontroller configured using a CPU, memory, etc., and performs processing related to the control of transmitter 21 and receiver 22, and the generation of data based on the reflected wave received by receiver 22. The input / output unit 24 is an interface device that establishes communication with the information processing device 3 and other devices in accordance with a predetermined standard such as CAN.

[0026] The information processing device 3 comprises a CPU (Central Processing unit) 31, a memory 32, and an input / output unit 33. The CPU 31 executes various arithmetic processes according to the program stored in the memory 32. The memory 32 may be configured using appropriate volatile and non-volatile memory. The memory 32 stores programs that cause the CPU 31 to execute various processes to realize the functions of the occupant detection device 1, setting data, data acquired from the sensor 2, data generated by the CPU 31, etc. The input / output unit 33 is an interface device that establishes communication with the sensor 2 and other devices in accordance with predetermined standards such as CAN.

[0027] Note that the hardware configuration shown in Figure 2 is an example, and the hardware configuration of the occupant detection device 1 is not limited to that shown.

[0028] Figure 3 is a block diagram showing an example of the functional configuration of the occupant detection device 1 of this embodiment. The occupant detection device 1 of this embodiment includes an acquisition unit 101, a generation unit 102, a setting unit 103, and an estimation unit 104. These functional units 101 to 104 can be configured by the cooperation of hardware and software (programs), for example, as illustrated in Figure 2. Furthermore, some or all of these functional units 101 to 104 may be configured by dedicated hardware (circuits, etc.) such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field-Programmable Gate Array).

[0029] The acquisition unit 101 acquires point cloud information that shows the position of an object moving within the vehicle interior R (moving object) as a point cloud containing multiple detection points on a three-dimensional map corresponding to the space within the vehicle interior R, based on the intensity of the reflected wave received by the sensor 2.

[0030] Figure 4 shows an example of point cloud information 201 of the embodiment. The point cloud information 201 illustrated here is information plotted as detection points P on a three-dimensional map (e.g., a voxel map) corresponding to the space inside the vehicle compartment R, with multiple points (e.g., voxels, etc.) corresponding to the position of a moving object (e.g., the area occupied by the moving part of the occupant's body 10, etc.). Which points (voxels, etc.) become detection points P is determined based on pre-set conditions related to reflected waves, etc., but for example, detection points P may be points where the amount of change per unit time of the intensity of the reflected wave is greater than a predetermined threshold.

[0031] Figure 4 illustrates a case where three seating positions S21 to S23 are set on the second seat row SR2, and two seating positions S31 and S32 are set on the third seat row SR3, with an occupant seated at the rightmost seating position S23 on the second seat row SR2. In such a case, as shown in Figure 4, a point cloud G consisting of multiple detection points P corresponding to the occupant's body (e.g., head, chest, back, shoulders, etc.) appears in the space above the seating position S23 on the three-dimensional map. The point cloud information 201 may include information about such a point cloud G, such as the position of each detection point P (plot position), the number of detection points P within a predetermined area (number of plots), and information indicating the time-series changes of the plot positions and the number of plots.

[0032] The generation unit 102 (see Figure 3) generates a seat row map for each seat row SR2, SR3 based on the point cloud information 201 acquired by the acquisition unit 101. The seat row map shows the distribution of detection points P in a planar region corresponding to the arrangement direction of multiple seating positions S21~S23, S31, S32 (Y direction in this embodiment) and the height direction of the vehicle C (Z direction in this embodiment). In other words, in this embodiment, a seat row map showing the distribution of detection points P in the planar region (YZ plane) corresponding to the second seat row SR2 and a seat row map showing the distribution of detection points P in the planar region corresponding to the third seat row SR3 are generated.

[0033] The setting unit 103 sets an upper boundary line along the upper end of the planar point cloud containing multiple detection points P on the sheet column map generated by the generation unit 102.

[0034] The estimation unit 104 estimates the number of occupants for each seat row SR2 and SR3 based on the shape characteristics of the upper edge line set by the setting unit 103. The estimation unit 104 also estimates the seating position of each occupant for each seat row SR2 and SR3 based on the shape characteristics of the upper edge line. Furthermore, the estimation unit 104 estimates the occupant's physique based on the shape characteristics of the upper edge line. The estimation unit 104 generates occupant information showing the estimated number of occupants, seating position, physique, etc. This occupant information can be used for various purposes, such as in a seat belt reminder function.

[0035] Figure 5 shows an example of a seat row map 301 and upper boundary line L of an embodiment. The seat row map 301 shown in Figure 5 shows the distribution of detection points P in a planar region Rp (YZ plane) corresponding to the second seat row SR2. The planar region Rp is set to include three seating regions R21 to R23, each corresponding to one of the three seating positions S21 to S23 included in the second seat row SR2. A planar point cloud Gp is ​​formed by multiple detection points P distributed in the planar region Rp. The planar point cloud Gp indicates the position of moving objects such as occupants present on the second seat row SR2.

[0036] The upper boundary line L is set along the upper end of the planar point cloud Gp. The upper boundary line L can be set by applying an appropriate smoothing process to the values ​​(height values) of multiple detection points P located at the upper end of the planar point cloud Gp. The smoothing process is not particularly limited, but it may involve processes such as exponential moving averages or simple moving averages.

[0037] In Figure 5, the upper boundary line L shows three peaks PK1, PK2, and PK3 projecting upward (towards the positive side in the height direction). Each peak PK1, PK2, and PK3 can be estimated to correspond to the upper end of a moving object within the vehicle compartment R, i.e., the heads of the occupants. In other words, from the upper boundary line L shown in Figure 5, it can be estimated that three occupants are seated on the second seat row SR2. Thus, the number of occupants can be estimated for each seat row SR2 and SR3 based on the number of peaks appearing on the upper boundary line L.

[0038] Furthermore, the seating position of each occupant can be estimated based on the position of each peak PK1, PK2, and PK3 in the Y direction (the direction of the arrangement of the multiple seating positions S21 to S23). In the upper boundary line L shown in Figure 5, the three peaks PK1, PK2, and PK3 are located in the respective three seating regions R21 to R23, so it can be estimated that the three occupants are each seated in the normal seating positions S21 to S23. In this way, the seating position of each occupant can be estimated for each seat row SR2 and SR3 based on the position of the peaks appearing on the upper boundary line L.

[0039] In this embodiment, the condition for the establishment of peaks PK1, PK2, and PK3 is that the peak interval D formed between two adjacent peaks is secured to be a predetermined distance (e.g., 20 cm) or more. This allows for high-precision detection of peaks PK1, PK2, and PK3 corresponding to the occupant's head. Furthermore, the upper limit line L in this embodiment is set based on detection points P located in a region above a first threshold H1 that is a predetermined distance higher than the seating surface, among a plurality of detection points P included in the planar point cloud Gp. The first threshold H1 is set to exclude low regions from the detection range where there is almost no possibility of an occupant's head being present. Note that the first threshold H1 may be set based on the installation position of the sensor 2 (inner surface of the ceiling 5), etc. In this case, the first threshold H1 will vary depending on the vehicle height (distance from the seat surface to the ceiling 5), etc., but can be set, for example, at a position about 60 cm below the sensor 2. By setting such a first threshold H1, false detections due to the influence of moving objects other than the occupant's head (e.g., luggage placed on the seat surface) can be suppressed.

[0040] Furthermore, the occupant's physique (e.g., adult or child) is estimated based on the height positions of peaks PK1, PK2, and PK3, and a second threshold H2 set higher than the first threshold H1. In the example shown in Figure 5, peaks PK1 and PK2 are higher than the second threshold H2, while peak PK3 is lower than the second threshold H2. In such a case, for example, it can be estimated that the occupant corresponding to peaks PK1 and PK2 is an adult, and the occupant corresponding to peak PK3 is a child. The second threshold H2 should be set appropriately according to the physique to be estimated, but for example, it can be set based on the position of the head of an average-sized child sitting in a child seat. Alternatively, the second threshold H2 may be set based on the installation position of sensor 2, similar to the first threshold H1. In this case, the second threshold H2 will vary depending on the vehicle height, but for example, it can be set at a position approximately 36 cm below sensor 2. By setting such a second threshold H2, the occupant's physique can be estimated.

[0041] Figure 6 shows an example of the upper boundary line L in an embodiment where the occupants are not seated in the regular seating positions. Two peaks, PK4 and PK5, appear on the upper boundary line L shown in Figure 6. One peak, PK4, is located between the leftmost seating area R21 and the central seating area R22, and the other peak, PK5, is located in the rightmost seating area R23. Based on this upper boundary line L, it can be estimated that there are two occupants on the second seat row SR2, with one occupant seated between the leftmost seating position S21 and the central seating position S22, and the other occupant seated in the rightmost seating position S23.

[0042] Figure 7 is a flowchart showing an example of processing in the occupant detection device 1 of the embodiment. When the occupant detection process is started, the acquisition unit 101 acquires point cloud information 201 based on the intensity of the reflected wave received by the sensor 2 (S101). The generation unit 102 generates a sheet column map 301 for each sheet column SR2, SR3 based on the point cloud information 201 (S102). The setting unit 103 sets the upper limit line L in each sheet column map 301 (S103).

[0043] The estimation unit 104 estimates the number of occupants for each seat row SR2, SR3 based on the number of peaks appearing at each upper line L (for example, peaks PK1 to PK5 as described above) (S104), estimates the seating position of each occupant for each seat row SR2, SR3 based on the position of the peaks (S105), and estimates the occupant's physique based on the position of the peaks in the height direction (S106). Subsequently, the estimation unit 104 generates occupant information indicating the estimated number of occupants, seating position, and occupant's physique, and outputs it to a predetermined system (for example, a seat belt reminder) (S107).

[0044] In the above embodiment, occupant detection was described for the second seat row SR2 and the third seat row SR3 in a three-row seat vehicle, but the embodiment is not limited to this. For example, the rear seat row in a two-row seat vehicle may be targeted, or the first seat row SR1 may be targeted.

[0045] As described above, according to this embodiment, the number of occupants, etc., for each seat row SR2, SR3 is estimated based on the shape characteristics of the upper line L set on the seat row map 301 generated for each seat row SR2, SR3. This makes it possible to detect occupants with high accuracy regardless of their seating position.

[0046] The program that causes a computer (information processing device 3) to execute the processing necessary to realize the functions of the occupant detection device 1 as described above may be provided as a computer program product by being stored in an installable or executable file format on a computer-readable storage medium such as a CD-ROM, CD-R, memory card, DVD (Digital Versatile Disk), or flexible disk (FD). 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. Furthermore, the program may be provided or distributed via a network such as the Internet.

[0047] Although embodiments of the present invention have been described above, these embodiments are presented as examples only and are not intended to limit the scope of the invention. This novel embodiment can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. This embodiment and its variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. [Explanation of symbols]

[0048] 1... Occupant detection device, 2... Sensor, 3... Information processing device, 5... Ceiling, 21... Transmitter, 22... Receiver, 23... ECU, 24... Input / Output unit, 31... CPU, 32... Memory, 33... Input / Output unit, 101... Acquisition unit, 102... Generation unit, 103... Setting unit, 104... Estimation unit, 201... Point cloud information, 301... Seat row map, C... Vehicle, D... Peak interval, G... Point cloud, Gp... Planar point cloud, H1... First threshold, H2... Second threshold, L... Upper limit line, P... Detection point, PK1~PK5... Peak, R... Passenger compartment, R21~R23... Seating area, Rp... Planar area, S21~S23, S31, S32... Seating position, SR1... First seat row, SR2... Second seat row, SR3... Third seat row

Claims

1. An acquisition unit acquires point cloud information that indicates the position of an object moving in a room as a point cloud including multiple detection points, based on the intensity of the reflected wave generated when a transmitted wave sent toward a room of a moving object is reflected by an object present in the room, and A generation unit generates a seat row map that shows the distribution of the detection points in a planar region corresponding to the arrangement direction of the multiple seating regions and the height direction of the moving body for each seat row containing multiple seating regions, based on the point cloud information. A setting unit that sets an upper boundary line along the upper end of a planar point cloud containing multiple detection points on the sheet column map, An estimation unit that estimates the number of occupants for each seat row based on the number of peaks that protrude upward from the upper end line, A crew detection device equipped with the following features.

2. The estimation unit estimates the seating position of the occupant based on the position of the peaks in the arrangement direction. The occupant detection device according to claim 1.

3. The setting unit sets the upper limit line based on the detection points among the plurality of detection points included in the planar point cloud that are located in a region above a first threshold that is a predetermined distance higher from the seat surface. The occupant detection device according to claim 1 or 2.

4. The estimation unit estimates the occupant's physique based on the position in the height direction of the peak that the upper limit line protrudes upward and a second threshold set above the first threshold. The occupant detection device according to claim 3.

5. The setting unit sets the upper limit line by smoothing the values ​​of the multiple detection points located at the upper end of the planar point cloud. The occupant detection device according to claim 1 or 2.

6. A step of acquiring point cloud information that indicates the position of an object moving in a room as a point cloud including multiple detection points, based on the intensity of the reflected wave generated when a transmitted wave sent toward a room of a moving object is reflected by an object present in the room, and Based on the point cloud information, a step is to generate a seat row map showing the distribution of the detection points in a planar region corresponding to the arrangement direction of the multiple seating areas and the height direction of the moving body for each seat row containing multiple seating areas, The steps include setting an upper boundary line along the upper end of a planar point cloud containing a plurality of detection points on the sheet column map, A step of estimating the number of occupants for each seat row based on the number of peaks that protrude upward from the upper end line, Crew detection method including

Images