Detection device and detection method

Abstract

The present disclosure provides a detection device and a detection method capable of judging boarding or alighting of an occupant of a vehicle with a simple structure. In the detection device (boarding / alighting detection device (10)), an acquisition unit (second acquisition unit (14)) acquires an acceleration of the vehicle in a period determined based on a first time at which a door of the vehicle is opened and a second time at which the door is closed after the first time. A judging unit (18) judges boarding or alighting of the occupant of the vehicle based on a temporal change in the acquired acceleration.

Description

Technical Field

[0001] This invention relates to a detection device and a detection method. Background Technology

[0002] Patent Document 1 discloses an occupant detection device comprising: an acceleration sensor for detecting the acceleration of a vehicle; a light detection unit for irradiating light into the vehicle interior and detecting a target based on the reflected light; and a determination unit for determining whether the target is an occupant based on the acceleration detection result and the light detection result.

[0003] Prior art literature

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2018-179640 Summary of the Invention

[0006] The problem that the invention aims to solve

[0007] In the technology of Patent Document 1, the number of parts increases because a light detection unit needs to be installed in the vehicle, which may increase the cost.

[0008] The purpose of this invention is to provide a technology that can determine whether a vehicle occupant is getting in or getting out of the vehicle with a simple structure.

[0009] Methods for solving problems

[0010] To address the aforementioned issues, a detection device according to a certain aspect of the present invention comprises: an acquisition unit that acquires the acceleration of a vehicle during a period determined based on a first moment when a vehicle door is opened and a second moment after that first moment when the door is closed; and a determination unit that determines whether an occupant of the vehicle has boarded or alighted based on the acquired temporal change in acceleration.

[0011] Another aspect of the present invention is a detection method. This method comprises: obtaining the vehicle's acceleration during a period determined based on a first moment when a vehicle door is opened and a second moment after that moment when the door is closed; and determining whether an occupant of the vehicle has boarded or alighted based on the temporal change in the obtained acceleration.

[0012] Invention Effects

[0013] According to the present invention, it is possible to determine whether a vehicle occupant is getting on or off the vehicle with a simple structure. Attached Figure Description

[0014] Figure 1This is a diagram showing the structure of the detection system according to the first embodiment.

[0015] Figure 2 To indicate that passengers are riding in vehicles equipped with Figure 1 A side view of the vehicle's previous state as detected by the system.

[0016] Figure 3 To indicate that the passengers have boarded the vehicle Figure 2 A side view of the vehicle's condition.

[0017] Figure 4 To indicate the passenger's use before and after boarding the vehicle Figure 1 The second part is a graph of an example of time series data of acceleration in the forward and backward directions that is obtained.

[0018] Figure 5 To indicate Figure 4 A graph showing an example of a moving average and regression line for time series data of acceleration.

[0019] Figure 6 To indicate the use of the vehicle by passengers before and after disembarking. Figure 1 The second part is a graph of an example of time series data of acceleration in the forward and backward directions that is obtained.

[0020] Figure 7 To indicate Figure 6 A graph of an example moving average of time series data on acceleration.

[0021] Figure 8 To indicate Figure 1 The flowchart shows the process of the vehicle disembarkation detection device.

[0022] Figure 9 This is a diagram illustrating the period during which time-series data of acceleration in the second embodiment is acquired.

[0023] Figure 10 This is a flowchart illustrating the processing of the vehicle disembarkation detection device according to the second embodiment.

[0024] Figure 11 This is a flowchart illustrating the processing of the vehicle disembarkation detection device according to the third embodiment. Detailed Implementation

[0025] (First Implementation)

[0026] Figure 1The structure of the detection system 1 according to the first embodiment is shown. The detection system 1 is mounted on a vehicle and detects whether a passenger has boarded or alighted from the vehicle. The vehicle is not particularly limited and can be either a commercial vehicle or a private car; here, a taxi is used as an example.

[0027] The detection system 1 pre-stores time-series data on the opening and closing times of taxi doors and the acceleration of taxis. At arbitrary time intervals, such as when a taxi returns to a waiting area (e.g., at a taxi company), it performs post-transfer detection based on the stored information. The taxi company's server collects the detection results of passenger boarding and alighting from multiple taxis using the detection system 1 and analyzes the collected data.

[0028] The detection system 1 includes a door sensor 2, a first storage unit 4, an acceleration sensor 6, a second storage unit 8, and a passenger / disembarkation detection device 10.

[0029] Door sensor 2 is installed on each of the multiple doors of the vehicle and detects whether each door is open or closed, and supplies the detection results to the first storage unit 4. Door sensor 2 is, for example, a door control light switch for displaying a door not closed warning light, and is an existing part of the vehicle.

[0030] The first storage unit 4 stores the times when the door changes from a closed state to an open state and the times when the door changes from an open state to a closed state, based on the detection results obtained by the door sensor 2. The information of the times stored in the first storage unit 4 can be provided to the vehicle alighting detection device 10. The first storage unit 4 is, for example, installed in a control device for controlling the display of the door not closed warning light, and is an existing part of the vehicle.

[0031] An acceleration sensor 6 is installed in the vehicle to detect the vehicle's acceleration and supply the detection results to a second storage unit 8. The acceleration sensor 6 can detect acceleration along three axes, including the vehicle's forward and backward acceleration. The acceleration sensor 6 can also detect acceleration along two axes. The acceleration sensor 6 is used, for example, in vehicle control systems and is an existing component of the vehicle.

[0032] The second storage unit 8 stores time-series data of the acceleration detected by the accelerometer 6. The acceleration data includes information about the moment of detection. The information stored in the second storage unit 8 can be provided to the vehicle disembarkation detection device 10. The second storage unit 8 is, for example, installed in a control device for controlling the vehicle and is an existing part of the vehicle.

[0033] The vehicle occupant / disembarkation detection device 10 detects whether a vehicle occupant has boarded or disembarked based on detection results obtained from the door sensor 2 and the acceleration sensor 6. The device determines the possible time period for boarding or disembarking based on the opening and closing times of the doors, and judges whether boarding or disembarking has occurred based on the temporal change in acceleration caused by changes in the vehicle's tilt during that time period. The device includes a first acquisition unit 12, a second acquisition unit 14, an export unit 16, a judgment unit 18, and an output unit 20.

[0034] The structure of the vehicle disembarkation detection device 10 can be implemented in hardware using any computer's CPU, memory, and other LSIs, and in software using a program loaded into memory. Here, functional blocks implemented through the cooperative operation of these parts are described. Therefore, those skilled in the art will understand that these functional blocks can be implemented in various forms using only hardware, only software, or a combination thereof.

[0035] The first acquisition unit 12 acquires from the first storage unit 4 the first moment when the vehicle door opened and the second moment when the door closed for the first time after the first moment, and supplies the acquired moment information to the second acquisition unit 14. When multiple combinations of first and second moments are acquired, the following processing is performed for each combination of first and second moments.

[0036] The second acquisition unit 14 acquires time-series data of the vehicle's longitudinal acceleration from the first moment to the second moment from the second storage unit 8, and supplies the acquired data to the export unit 16. The period from the first moment to the second moment is the period during which the door is open, which corresponds to the period determined based on the first moment and the second moment.

[0037] Figure 2 To indicate that passenger P1 is riding in a vehicle equipped with Figure 1 The detection system 1 shows a side view of the vehicle 50 in its previous state. The vehicle 50, acting as a taxi, is parked so that passenger P1 can board. Here, it is assumed that the ground 52 beneath the vehicle 50 is a plane perpendicular to the vertical direction, and the forward / backward direction of the vehicle 50 lies within a plane perpendicular to the vertical direction; therefore, the forward / backward acceleration of the vehicle 50 is zero. The forward / backward direction of the vehicle 50 represents the forward / backward direction in a coordinate system fixed to the vehicle 50.

[0038] Figure 3 To indicate that passenger P1 has boarded the vehicle Figure 2A side view of the vehicle 50 in its current state. Assume the vehicle 50 is parked. Since occupant P1 is seated in the rear seat of the vehicle 50, the vehicle 50 tilts relative to the ground 52 due to the weight of occupant P1, causing the rear side of the vehicle 50 to be lower than the front side. Let θ be the tilt angle of the vehicle 50 relative to a plane perpendicular to the vertical direction in the forward / backward direction. Furthermore, in Figure 3 In the text, the magnitude of θ is described in an exaggerated manner.

[0039] Because vehicle 50 is tilted relative to ground 52, the acceleration of vehicle 50 in the longitudinal direction increases from zero to g×sinθ. Let g be the acceleration due to gravity. Here, the rearward acceleration is set to positive, and the forward acceleration is set to negative. By detecting the change in this longitudinal acceleration, the decision of whether occupant P1 has boarded or disembarked can be made.

[0040] Figure 4 Indicates the use of passengers before and after boarding the vehicle. Figure 1 An example of time-series data of acceleration in the forward and backward directions acquired by the second acquisition unit 14. Figure 4 On the vertical axis, the acceleration in the forward and backward directions is represented by the unit G, and the horizontal axis represents the elapsed time from the first moment to. The second moment tc is set to 8 seconds. Figure 4 This example indicates that the passenger boarded the vehicle approximately within 3 to 5 seconds. Figure 4 In the middle, it is shown that... Figure 2 , 3 An example of a vehicle in a different state, where the acceleration in the forward and backward directions is negative before the occupants board the vehicle.

[0041] Figure 5 express Figure 4 An example of a moving average and regression line L1 for time series data of acceleration. Figure 5 The example shown is a 1-second moving average.

[0042] The derivation unit 16 derives an index X representing the trend of acceleration in the forward and backward directions during the period from the first time t0 to the second time tc, and supplies the derived index X to the determination unit 18. This index X indicates whether the acceleration during this period is increasing or decreasing. Alternatively, this index X can be described as representing the trend of the vehicle's pitch angle θ during this period.

[0043] The export unit 16 exports a moving average line within a predetermined interval of the time series data of acceleration from the first time point t0 to the second time point tc, performs regression analysis on the time series data of the exported moving average line, and exports a regression line L1 represented as y = ax + b. The export unit 16 sets the slope 'a' of the regression line L1 as the index X.

[0044] The determination unit 18 determines whether a vehicle occupant has boarded or alighted based on the derived index X. A threshold is set to zero; if index X is greater than the threshold, the determination unit 18 determines that a occupant has boarded the vehicle; if index X is less than the threshold, the determination unit 18 determines that a occupant has alighted. In other words, the determination unit 18 determines whether a occupant has boarded or alighted based on whether the acceleration is increasing or decreasing during the period from the first time t0 to the second time tc. This process is equivalent to the determination unit 18 determining whether a occupant has boarded or alighted based on the temporal change in acceleration obtained using the second acquisition unit 14. Figure 5 In the example, since indicator X is positive, the judgment unit 18 judges that the passenger has taken the ride.

[0045] Figure 6 Indicates the use of the vehicle by passengers before and after disembarking. Figure 1 An example of time-series data of acceleration in the forward and backward directions acquired by the second acquisition unit 14. The vertical and horizontal axes are... Figure 4 same. Figure 6 This indicates that the passenger disembarked approximately between 4 and 5 seconds.

[0046] Figure 7 express Figure 6 An example of a moving average of time series data for acceleration. Although the plot of the regression line is omitted, the judgment unit 18 determines that the passenger has disembarked because the acceleration is on a decreasing trend and the indicator X is negative.

[0047] When the judgment unit 18 detects whether someone has boarded or alighted, it supplies the detection result to the output unit 20. The detection result includes the time when the person boarded or alighted.

[0048] The output unit 20 outputs the detection results to a pre-defined server device via a network such as the Internet and through wireless communication. The detection results can also be retrieved using a storage medium such as flash memory.

[0049] Alternatively, the index X can also be the change in acceleration in the forward and backward directions during the period from the first time to to the second time tc.

[0050] Furthermore, the regression formula in the regression analysis can be of any form, as long as it can show the increasing or decreasing trend of acceleration. The regression formula can also be set to show the change in acceleration. Nonlinear regression formulas can be used, and the number of indicators X can be multiple. The derivation unit 16 can also perform regression analysis on the time series data of acceleration without deriving moving averages.

[0051] Furthermore, depending on the direction in which the acceleration sensor 6 is mounted on the vehicle, there are also cases where the sign of the acceleration detected by the acceleration sensor 6 is opposite to that described above, resulting in a negative backward acceleration. In this case, if the index X is less than the threshold, the determination unit 18 determines that the occupant has boarded the vehicle; if the index X is greater than the threshold, the determination unit 18 determines that the occupant has disembarked.

[0052] Furthermore, the threshold can also include positive and negative thresholds. In this case, if the index X is greater than the positive threshold, the determination unit 18 determines that the passenger has boarded the vehicle; if the index X is less than the negative threshold, the determination unit 18 determines that the passenger has alighted; and if the index X is above the negative threshold and below the positive threshold, it is determined that neither boarding nor alighting has occurred. The positive and negative thresholds can be appropriately determined through experiments or simulations. Thus, even if neither boarding nor alighting has occurred, the possibility of misjudging whether boarding or alighting has occurred due to acceleration detection errors or noise can be reduced.

[0053] Figure 8 To indicate Figure 1 The flowchart illustrates the processing of the boarding and disembarking detection device 10. This processing begins when the boarding and disembarking detection device 10 receives an instruction to start processing, and is implemented for each combination of a first time and a second time.

[0054] The first acquisition unit 1 acquires the first moment to when the door opens (S10), and the second moment tc when the door closes for the first time after the first moment to (S12). The second acquisition unit 14 acquires the time series data of acceleration in the forward and backward directions from the first moment to to the second moment tc (S14), and the derivation unit 16 derives an index X representing the trend of acceleration change from the first moment to to the second moment tc (S16).

[0055] The judgment unit 18 compares the indicator X with the threshold (S18). If the indicator X is greater than the threshold, boarding is detected (S20), and the process ends. If the indicator X is less than the threshold, the judgment unit 18 detects alighting (S22), and the process ends. If the indicator X is equal to the threshold, the judgment unit 18 ends the process.

[0056] According to the implementation method, since the determination of whether a passenger is boarding or alighting is based on the time-varying change in the vehicle's acceleration between the first moment when the door is opened and the second moment when the door is closed, it is possible to detect boarding or alighting with good accuracy.

[0057] Since the door sensor 2 and the acceleration sensor 6 are existing parts of the vehicle, the detection system 1 can be constructed by installing the passenger / alighting detection device 10 on the vehicle without adding new sensors. Therefore, the detection system 1 can be constructed with a relatively small number of parts and at a low cost. Thus, the detection of passengers boarding or alighting can be performed with a simple structure. Furthermore, since information about the interior of the vehicle, such as the movement of passengers, is not utilized, accurate judgments can be made regardless of the conditions inside the vehicle.

[0058] (Second Implementation)

[0059] In the second embodiment, the method of determining whether to board or alight based on the acceleration a few seconds before and after the first moment and a few seconds before and after the second moment differs from that in the first embodiment. The following description will focus on the differences from the first embodiment.

[0060] Figure 9 This diagram illustrates the period for acquiring time-series acceleration data in the second embodiment. The second acquisition unit 14 acquires time-series acceleration data in the forward and backward directions during a first period and a second period. The first period is determined based on a first time *to*, from *to-ε1* to *to+ε2*, and the second period is determined based on a second time *tc*, from *tc-ε3* to *tc+ε4*. The first and second periods do not overlap.

[0061] ε1, ε2, ε3, and ε4 are each predetermined real values ​​within a range of zero seconds to a few seconds, and can be appropriately determined through experimentation or simulation. ε2 and ε3 are preferably set in a way that excludes the period during which acceleration changes due to occupants getting in and out of the vehicle. Alternatively, ε2 and ε3 can be set to zero, the first period can be set to the period immediately preceding the first time *to*, and the second period can be set to the period immediately following the second time *tc*. ε1 and ε4 are preferably set in a way that excludes the period during which acceleration occurs due to vehicle braking or driving. Alternatively, ε1 and ε4 can be set to zero, the first period can be set to the period immediately following the first time *to*, and the second period can be set to the period immediately preceding the second time *tc*.

[0062] The derivation unit 16 derives the difference between the statistical values ​​of the time-series acceleration data during the first period and the statistical values ​​of the time-series acceleration data during the second period as an index X. The statistical value can be the average or the median, etc. Alternatively, a moving average line may not be derived. Index X corresponds to the change in acceleration in the forward and backward directions during the period from the first time point to to the second time point tc.

[0063] Figure 10 This is a flowchart illustrating the processing of the vehicle disembarkation detection device 10 according to the second embodiment. The processing in S10 and S12 is... Figure 8 Same as above. Following S12, the second acquisition unit 14 acquires time-series data of acceleration in the forward and backward directions for the first period from to-ε1 to to+ε2 and the second period from tc-ε3 to tc+ε4 (S30). The derivation unit 16 derives the average acceleration Ato during the first period and the average acceleration Atc during the second period (S32), and derives the index X = Atc - Ato (S34), then transfers the process to S18. The processing after S18 is the same as above. Figure 8 same.

[0064] According to this embodiment, even if a passenger gets on the vehicle, gets off, and then gets on again during the period from when the door opens until it closes, the system can easily and accurately detect boarding without utilizing the significant increase or decrease in acceleration caused by boarding and alighting. Furthermore, even if a passenger gets off the vehicle, forgets something, and then gets on and off again during the period from when the door opens until it closes, the system can similarly easily and accurately detect alighting.

[0065] (Third Implementation)

[0066] In the third embodiment, the method of acquiring acceleration from the moment the door opens to the moment the door closes differs from that in the first embodiment. The following description will focus on the differences from the first embodiment.

[0067] The first acquisition unit 12 acquires information from the door sensor 2 indicating whether the door is open or closed, and supplies the acquired information to the second acquisition unit 14.

[0068] The second acquisition unit 14 acquires acceleration data from the acceleration sensor 6 when a closed door is opened based on information supplied from the first acquisition unit 12, and stops acquiring acceleration data when the open door is closed. The acquired acceleration data is the latest data at the acquisition time. That is, the second acquisition unit 14 acquires time-series data of acceleration from the first moment the door is opened to the second moment the door is closed. The second acquisition unit 14 supplies the acquired time-series acceleration data to the output unit 16.

[0069] The derivation unit 16 and the determination unit 18 perform the processing of the first embodiment. The derivation unit 16 may also be set to ε1=ε4=0 and perform the processing of the second embodiment.

[0070] Figure 11 This is a flowchart illustrating the processing of the vehicle disembarkation detection device 10 according to the third embodiment. This processing is repeatedly executed. If the door is not open (S40: No), the process returns to S40. If the door is open (S40: Yes), the second acquisition unit 14 sets i = 1 (S42) and acquires the acceleration Ai in the forward / backward direction (S44). If the door is not closed (S46: No), the current i is incremented by 1 (S48), and the process returns to S44. If the door is closed (S46: Yes), the derivation unit 16 derives an index X representing the trend of acceleration Ai from i = 1 to i = N (S50) and proceeds to the processing in S18. Additionally, the value of i at the moment the door is closed is set to N. The processing after S18 is the same as... Figure 8 same.

[0071] According to this embodiment, it can be detected immediately when boarding or alighting from a vehicle.

[0072] The present invention has been described above based on embodiments. Those skilled in the art will understand that the embodiments are merely examples, and various modifications can be made to the combination of structural elements and processing flows, and such modifications are also within the scope of the present invention.

[0073] For example, although the embodiment describes the example of determining whether someone is getting on or off the vehicle from the rear seats, the determination unit 18 may also determine whether someone is getting on or off the vehicle from the driver's seat or the front passenger seat in addition to the rear seats, or it may determine whether someone is getting on or off the vehicle from the driver's seat or the front passenger seat instead of the rear seats. If the vehicle's lateral acceleration changes due to someone getting on or off the vehicle from the driver's seat or the front passenger seat, the determination unit 18 may also determine whether someone is getting on or off the vehicle based on the change in lateral acceleration.

[0074] In both the first and second embodiments, the first storage unit 4 and the second storage unit 8 may also be provided in the vehicle disembarkation detection device 10.

[0075] Although the embodiment described an example of the passenger / disembarkation detection device 10 being mounted on a vehicle, the passenger / disembarkation detection device 10 can also be included in a cloud server. In this case, a wireless communication device (not shown) mounted on the vehicle sends time-series data of information related to the opening and closing of the vehicle doors and acceleration to the passenger / disembarkation detection device 10 on the server, and the passenger / disembarkation detection device 10 sends the detection results of boarding and disembarking to a terminal device of a taxi company or an onboard device of the vehicle, etc.

[0076] Although the implementation example illustrates a taxi, the vehicle could also be a bus such as a kindergarten.

[0077] The vehicle may also be a truck or similar vehicle with doors on the cargo box and capable of carrying loads. In this case, the determination unit 18 determines whether the vehicle is being loaded or unloaded, instead of determining whether passengers are boarding or alighting. That is, the determination unit 18 detects whether the cargo has been loaded or unloaded based on whether the acceleration is increasing or decreasing while the door is open.

[0078] Symbol Explanation

[0079] 1…Detection system; 2…Door sensor; 4…First storage unit; 6…Acceleration sensor; 8…Second storage unit; 10…Passenger / disembarkation detection device; 12…First acquisition unit; 14…Second acquisition unit; 16…Export unit; 18…Judgment unit; 20…Output unit; 50…Vehicle.

Claims

1. A detection device, characterized in that, have: The acquisition unit acquires the vehicle's acceleration during the period determined based on the first moment when the vehicle door opens and the second moment after that moment when the door closes; The derivation section derives an index representing the trend of change of the acceleration during the period from the first moment to the second moment; The judgment unit determines whether the occupants of the vehicle are boarding or alighting based on the derived indicators. The acquisition unit acquires the acceleration during the period from the first moment to the second moment. The determination unit determines whether a passenger should board or alight the vehicle based on whether the acceleration has increased or decreased during the period from the first moment to the second moment.

2. The detection device as described in claim 1, characterized in that, The acquiring unit acquires the acceleration during a first period and a second period, wherein the first period is a period determined based on the first moment, and the second period is a period determined based on the second moment and does not overlap with the first period. The judgment unit determines whether a passenger is boarding or alighting based on the difference between the statistical value of acceleration during the first period and the statistical value of acceleration during the second period.

3. The detection device as described in claim 1 or 2, characterized in that, The judgment unit determines whether the vehicle is loaded or unloaded, instead of determining whether the occupants of the vehicle are boarding or alighting.

4. A detection method, characterized in that, have: The steps to obtain the vehicle's acceleration during the period determined by the first moment when the vehicle door opens and the second moment after that moment when the door closes; Derive an index representing the trend of change in the acceleration during the period from the first moment to the second moment; The step of determining whether the occupants of the vehicle boarded or disembarked based on the derived indicators. Obtain the acceleration during the period from the first moment to the second moment. The decision to allow passengers to board or disembark is made based on whether the acceleration has increased or decreased during the period from the first moment to the second moment.

Images