Monitoring device, method for monitoring, and monitoring program

Abstract

To avoid the possibility that a wrong determination of determining an object to be an attention target can be made.SOLUTION: The device according to the present invention has an acquisition unit and a determination unit. The acquisition unit acquires plural pieces of sensor data sequentially generated by a mobile body sensor of a vehicle. The determination unit determines whether an object is not an attention object on the basis of the distance from the average position of a mobile body determined from positional data in the acquired plural pieces of sensor data to the positional data.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a monitoring device, a monitoring method, and a monitoring program.

Background Art

[0002] Conventionally, with respect to a microwave sensor that detects an object using microwaves, a technique has been disclosed for accurately discriminating between an object to be detected, such as a human body, and an object that should not be detected (for example, plants swaying in the wind), and avoiding false alarms (for example, Patent Document 1). The means of such a technique determines that only an object whose change amount per unit time of the relative distance is equal to or greater than a predetermined amount or an object whose relative moving distance is equal to or greater than a predetermined value is an object to be detected, and determines that other objects are objects that should not be detected.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, there is a problem that when an object that should not be detected is, for example, a flag, there is a possibility of false detection with an object to be detected, and it is necessary to identify the flag as an object that should not be detected. For example, when the movement of the flag is fast or the moving distance is large, there is a risk of false detection assuming that the flag is an object to be detected. Thus, as an example of the problem to be solved by the present invention, the above-described problem is cited.

[0005] Note that the above problem is not limited to the detection of objects, and the same problem occurs even when the object not to be noted is, for example, a flag. That is, when the object not to be noted is, for example, a flag, there is a problem that misjudgment with the object to be noted may occur, and the flag needs to be specified as not being an object to be noted.

Means for Solving the Problem

[0006] In order to solve the above-described problems and achieve the object, the invention according to claim 1 includes an acquisition unit that acquires a plurality of sensor data sequentially generated by a moving body sensor provided in a vehicle, and an average position of the moving body obtained from position data included in the plurality of sensor data. And a determination unit that determines whether the moving body is an object not to be noted based on the distance from the average position to each position data.

[0007] The invention according to claim 6 is a method executed by a monitoring device, including an acquisition step of acquiring a plurality of sensor data sequentially generated by a moving body sensor provided in a vehicle, and an average position of the moving body obtained from position data included in the plurality of sensor data. And a determination step of determining whether the moving body is an object not to be noted based on the distance from the average position to each position data.

[0008] The invention according to claim 7 causes a computer to execute an acquisition step of acquiring a plurality of sensor data sequentially generated by a moving body sensor provided in a vehicle, and an average position of the moving body obtained from position data included in the plurality of sensor data. And a determination step of determining whether the moving body is an object not to be noted based on the distance from the average position to each position data.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Embodiments for Carrying Out the Invention

[0010] Hereinafter, embodiments for carrying out the present invention (hereinafter, embodiments) will be described with reference to the drawings. Note that the present invention is not limited by the embodiments described below. Furthermore, in the description of the drawings, the same parts are denoted by the same reference numerals.

[0011] [Embodiment] [1. Configuration of the Device] First, the configuration of the monitoring device according to the embodiment will be described with reference to FIG. 1. FIG. 1 is a diagram showing an example of the configuration of the monitoring device according to the embodiment. As shown in FIG. 1, the monitoring device 1 includes an in-vehicle device 100.

[0012] The monitoring device 1 may be a dedicated device built in or externally attached to the vehicle C0, or may be a device such as a recording device (drive recorder) installed in the vehicle C0 for crime prevention or countermeasures against aggressive driving.

[0013] In addition, the in-vehicle device 100 may be composed of a sensor device and a notification device. As an example, the in-vehicle device 100 may be a composite device in which a sensor device and a notification device that are independent of each other are communicably connected. Also, as another example, the in-vehicle device 100 may be a single device having a sensor function and a notification function.

[0014] In addition, the in-vehicle device 100 may be provided with various sensors. For example, the in-vehicle device 100 may be provided with various sensors such as a distance sensor, a moving body sensor such as a microwave sensor or LiDAR (light detection and ranging), a temperature sensor, a microphone, a GPS (Global Positioning System) sensor, an acceleration sensor, a gyro sensor, a camera, and a barometric pressure sensor.

[0015] Also, the moving body sensor provided in the in-vehicle device 100 sequentially generates sensor data. The sensor data referred to here is, for example, moving body position data (data indicating the position from the sensor, in other words, data indicating the position on a plane viewed from above the vehicle, such as coordinates), the distance of the moving body, and the intensity (level) of the signal, which are generated based on the information detected by the moving body sensor.

[0016] The monitoring device 1 is a device that determines whether a moving object is an object that does not require attention (in other words, an object other than an animal including a person) using a plurality of sensor data sequentially generated by a motion sensor. Conventionally, for the purpose of preventing a parked vehicle from being stolen or vandalized, etc., the parked vehicle has been monitored. In such a device for monitoring a parked vehicle, a person who approaches or peeks into the parked vehicle is regarded as an object that requires attention. However, when an object that does not require attention, such as a plant like a flag, grass, or tree, exists near the parked vehicle, it may be erroneously detected that an object (human body) that requires attention exists. Therefore, the monitoring device 1 needs to identify an object that does not require attention existing near the parked vehicle. For this reason, the monitoring device 1 accurately determines an object that does not require attention existing near the parked vehicle to prevent false detection. In the embodiment, the case where the object that does not require attention is a "flag" will be described.

[0017] For example, the monitoring device 1 determines whether a moving object is an object that does not require attention based on the distance from the average position (coordinates of the center of gravity) of the moving object obtained from the position data (coordinates) of the moving object included in the plurality of sensor data to each coordinate. As an example, the monitoring device 1 determines that the moving object is an object that does not require attention when the sensor data in which the distance from the average position (coordinates of the center of gravity) of the moving object to the coordinates included in each of the plurality of sensor data is within a predetermined length accounts for a predetermined ratio or more among the plurality of sensor data.

[0018] In addition, the monitoring device 1 further determines that the moving object is an object that does not require attention when at least one of the following conditions is satisfied: the standard deviation of the moving distance (amount of movement) of the plurality of sensor data is within a first range; the standard deviation of the signal intensity (level) included in each of the plurality of sensor data is less than a threshold value; and the value obtained by dividing the sum of the moving distances (amounts of movement) of the plurality of sensor data by the diagonal length obtained from the maximum value and the minimum value of the position data (coordinates) of each sensor data is within a second range.

[0019] Note that although the monitoring device 1 is described as being disposed inside the vehicle C0 and including the in-vehicle device 100, it may be disposed outside the vehicle C0 and have a configuration independent of the in-vehicle device 100. In such a case, the monitoring device 1 is communicably connected to the in-vehicle device 100 via a network, and acquires a plurality of sensor data sequentially generated by the moving body sensors of the in-vehicle device 100 provided in the vehicle C0. Then, the monitoring device 1 may determine whether the moving body is an object not to be concerned about based on the distance from the average position (center of gravity position) of the moving body obtained from the position data (coordinates) included in the acquired plurality of sensor data to each position data (coordinates).

[0020] Further, in the following embodiments, an example is shown in which the monitoring device 1 realizes the monitoring according to the embodiment by exchanging information with the in-vehicle device 100. However, the monitoring according to the embodiment may be realized only by the in-vehicle device 100. In such a case, the in-vehicle device 100 may be configured to behave like the monitoring device 1, for example, by a monitoring program according to the embodiment.

[0021] [2. Functional Configuration of Monitoring Device] Next, the monitoring device 1 according to the embodiment will be described with reference to FIG. 2. FIG. 2 is a diagram showing an example of the functional configuration of the monitoring device 1 according to the embodiment. As shown in FIG. 2, the monitoring device 1 includes a communication unit 10, a storage unit 30, and a control unit 20. Hereinafter, each unit included in the monitoring device 1 will be described.

[0022] The communication unit 10 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 10 is connected to the network by wire or wirelessly, and exchanges information with, for example, the in-vehicle device 100.

[0023] The storage unit 30 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 30 stores the position where the moving body sensor is installed, the intensity of the signal to be transmitted, the sensitivity to receive the signal, the intensity of the received signal, the angle, distance, coordinates of the moving body calculated from the received signal, and other information necessary for determining an object not to be a target of attention.

[0024] The control unit 20 is realized by using a CPU (Central Processing Unit), an NP (Network Processor), an FPGA (Field Programmable Gate Array), etc., and executes a processing program stored in a memory. As shown in FIG. 2, the control unit 20 includes an acquisition unit 21, an exclusion unit 22, a determination unit 23, and a modification unit 24. Hereinafter, each unit included in the control unit 20 will be described.

[0025] The acquisition unit 21 acquires a plurality of sensor data sequentially generated by a moving body sensor provided in the vehicle C0. For example, the acquisition unit 32 acquires sensor data including the intensity of a signal received by a moving body sensor provided in the vehicle C0 and the coordinates of a moving body generated from information on the distance and angle calculated by the moving body sensor. At this time, the number of moving body sensors may be plural. For example, the acquisition unit 21 acquires sensor data including the intensity of each signal received by a plurality of moving body sensors provided in the vehicle C0 so as to include the inside of the vehicle C0 in the detection range, and the coordinates of the moving body generated based on the information detected by the plurality of moving body sensors. The sensor data includes, as an example, time, distance, angle, signal intensity, and coordinates.

[0026] Note that the installation location of the moving body sensor is not limited as long as it is inside the vehicle. For example, it may be installed near the rearview mirror or on the center pillar. That is, the moving body sensor is installed at a part inside the vehicle according to the purpose, such as a front pillar, a center pillar, a rear pillar, a rearview mirror, a ceiling, a seat, a rear glass, etc.

[0027] The excluding unit 22 excludes, from the plurality of sensor data acquired by the acquisition unit 21, sensor data in which the distance included in each sensor data is equal to or greater than a predetermined distance, or sensor data in which the distance included in each sensor data is equal to or less than the predetermined distance. As an example, the excluding unit 22 sets the parameters of the motion sensor to exclude, from the plurality of sensor data, sensor data in which the distance included in each sensor data is 4 m or more, or sensor data in which the distance included in each sensor data is 80 cm or less. The reason for excluding sensor data with a distance of 4 m or more is that a distance of 4 m or more is not in the vicinity of the parked vehicle in the first place, so there is no need to identify objects that are not of concern. Also, the reason for excluding sensor data of 80 cm or less is that since it becomes position data inside the vehicle, the possibility that it is a flagpole is low.

[0028] Furthermore, the excluding unit 22 excludes, from the plurality of sensor data acquired by the acquisition unit, sensor data corresponding to position data (coordinates) specified in the vicinity of a door attached to the vehicle. As an example, the excluding unit 22 sets the parameters of the motion sensor to exclude, from the plurality of sensor data, sensor data included in a rectangular parallelepiped region represented by a width of 150 cm in the X coordinate and a width of 250 cm in the Y coordinate in the door direction with the sensor attached to the vehicle as an end. This is because it is assumed that there is no flagpole that is not a target of attention standing in the vicinity of the door.

[0029] The determination unit 23 determines whether the moving object is an object not to be the attention target based on the distances from the average coordinates (coordinates of the center of gravity) of the moving object obtained from the coordinates of the moving object included in the plurality of sensor data acquired by the acquisition unit 21 to each coordinate. For example, the determination unit 23 calculates the average coordinates (coordinates of the center of gravity) of the moving object using a plurality of coordinates specified based on each of the plurality of sensor data. That is, the determination unit 23 calculates the coordinates of the center of gravity, which is the midpoint of the coordinates of the consecutive moving objects. Then, when the sensor data in which the distances from the coordinates of the center of gravity to the coordinates included in each are within a predetermined length includes a predetermined ratio or more among the plurality of sensor data, the determination unit 23 determines that the moving object is an object not to be the attention target.

[0030] As an example, when the sensor data in which both the X coordinate and the Y coordinate of each coordinate are within 30 cm from the coordinates of the center of gravity includes 70% or more among the plurality of sensor data, the determination unit 23 determines that the moving object is an object not to be the attention target. This is because when the object not to be the attention target is a flag, the swaying motion of the flag is assumed to stay in one place.

[0031] However, when the object to be the attention target (human body) stands at a specific location and peeks in, the determination unit 23 may also satisfy the same conditions, and there may be a case where the moving object that is a human body is determined to be an object not to be the attention target. Therefore, the determination unit 23 further determines that the moving object is an object not to be the attention target when at least one of the first condition, the second condition, and the third condition is satisfied.

[0032] The first condition here is the condition that the standard deviation of the moving distances of the plurality of sensor data is within the first range. Here, the moving distance (amount of movement) may be the moving distance of the coordinates of the moving object acquired by the acquisition unit 21, or may be the moving distance of the coordinates of the center of gravity of the moving object. Also, the standard deviation may be calculated for samples from a certain sample up to a predetermined period (for example, 2.0 seconds) ago, or may be calculated for samples from a certain sample up to a predetermined number (for example, 40) of samples ago.

[0033] As an example, when the standard deviation of the movement amounts of a plurality of sensor data is within a first range that is greater than "5" and less than "9", the determination unit 23 determines that the moving object is an object not to be targeted for attention. This is because when the object not to be targeted for attention is a flag, the movement amount tends to settle at a certain value, and the characteristic standard deviation of the flag is expected to settle within such a first range.

[0034] Also, the second condition is a condition that the standard deviation of the intensities of the signals of the plurality of sensor data is less than a threshold value.

[0035] As an example, when the standard deviation of the intensities of the signals of a plurality of sensor data is less than "1.6", the determination unit 23 determines that the moving object is an object not to be targeted for attention. When the moving object is a person, the signal level changes greatly due to the movement of the person. On the other hand, when the moving object is a flag, the signal level does not change greatly. This is because the area where the motion sensor reacts as a moving object is different between a person and a flag. That is, for a person, the area where the motion sensor reacts changes depending on the moving part, but for a flag, since the entire flag moves, the change in the area where the motion sensor reacts is smaller than that of a person.

[0036] Also, the third condition is a condition that the value obtained by dividing the sum of the moving distances (movement amounts) of the plurality of sensor data by the length of the diagonal line obtained from the maximum value and the minimum value of the position data of each sensor data is within a second range. That is, the third condition is a condition that the value obtained by dividing the sum of the movement amounts of the coordinates of the moving object during a predetermined period by the square root of the sum of the square of the difference between the maximum value and the minimum value of the X coordinates of the coordinates of the moving object during the predetermined period and the square of the difference between the maximum value and the minimum value of the Y coordinates of the coordinates of the moving object during the predetermined period is within a second range. Such a value is referred to here as XYratio.

[0037] As an example, when the value calculated using Expression (1) is within a second range that is greater than "6" and less than "8", the determination unit 23 determines that the moving object is an object not to be an attention target. When a person moves back and forth within a certain range, the XY ratio becomes high, but when staying in one place, the XY ratio becomes low. Since the wind sock is in a fixed position, it corresponds to the case of staying in one place, and the XY ratio is expected to settle within such a first range.

[0038] [Number]

[0039] When the determination unit 23 determines that the moving object is an object not to be an attention target, the change unit 24 changes the setting of the moving object sensor. For example, when the determination unit 23 determines that the moving object is an object not to be an attention target, the change unit 24 changes the sensitivity at which the moving object sensor receives a signal. As an example, when the determination unit 23 determines that the moving object is an object not to be an attention target, the change unit 24 reduces the sensitivity to receive a signal reflected near the coordinates of the moving object. Also, as an example, when the determination unit 23 determines that the moving object is an object not to be an attention target, the change unit 24 reduces the sensitivity to receive a signal from the coordinate direction of the moving object.

[0040] [3. Information Stored in the Storage Unit] Next, with reference to FIG. 3, the information stored in the storage unit 30 will be described. FIG. 3 is a diagram showing an example of the information stored in the storage unit according to the embodiment. In FIG. 3, it is data specified based on the information detected by the moving object sensor in a situation where some moving object is moving near the vehicle. For example, information such as the coordinates of the X-axis and Y-axis with respect to time and the intensity (Level) of the signal is shown. Note that the information shown in FIG. 3 is an example, and the information stored in the storage unit 30 is not limited to this, and includes information necessary for determining an object not to be an attention target.

[0041] [4. Determination Process] Next, with reference to FIGS. 4 and 5, the determination process by the monitoring device 1 will be described. FIGS. 4 and 5 are diagrams showing an example of the determination process by the monitoring device according to the embodiment. FIG. 4 shows the coordinates of a moving object generated based on the information detected by the moving object sensor in a situation where the climbing flag is swaying. In FIG. 4, it is a case where the moving object sensor is installed near the rearview mirror, and the origin (0, 0) of the coordinates is a predetermined point in the moving object sensor at the position where the moving object sensor is installed.

[0042] For example, the acquisition unit 21 acquires sensor data including the intensity (Level) of the signal received by the moving object sensor provided in the vehicle, and the coordinates (X, Y) of the moving object generated from the information on the distance and angle calculated by the moving object sensor.

[0043] Then, the determination unit 23 calculates the average coordinates of the moving object using the coordinates (X, Y) of the plurality of moving objects specified based on each of the plurality of sensor data. The calculated coordinates are the coordinates G0 of the center of gravity of the moving object. Here, the coordinates G0 of the center of gravity of the moving object are calculated from each of the coordinates included in, for example, 200 pieces of sensor data.

[0044] Then, as shown in FIG. 4, when more than 70% of the coordinates included in the sensor data in which the distance from the coordinates G0 of the center of gravity of the moving object to each coordinate is within 30 cm are included in the plurality of sensor data, the determination unit 23 determines that the moving object is an object (climbing flag) that is not a target of attention.

[0045] Thereby, the monitoring device 1 can avoid the possibility of misjudgment with an object (human body) that is a target of attention by using the distance from the center of gravity of the moving object obtained by the plurality of coordinates to each coordinate. That is, the monitoring device 1 can determine that the moving object is an object (climbing flag) that is not a target of attention.

[0046] Next, since there may be a case where the object (human body) to be monitored is erroneously determined as a flag that is not an object to be monitored according to the conditions by the determination unit 23, an addition to the determination conditions by the determination unit 23 will be described. Here, an example of determining an object (flag) that is not an object to be monitored based on the third condition will be described with reference to FIG. 5. FIG. 5 is a diagram showing an example of a determination process by the monitoring device according to the embodiment. FIG. 5(1) shows the movement of coordinates when the flag is swayed by the wind. For example, when the flag is swayed by the wind, the flag moves at a fixed position. That is, the total amount of movement within a predetermined position coordinate area tends to be small. Here, the predetermined position coordinate area is an area determined by the maximum and minimum values of the X coordinate and the maximum and minimum values of the Y coordinate during a predetermined period, as shown by the diagonal line (La) of the rectangle in FIG. 5(1).

[0047] La is represented by the square root of the sum of the square of the difference between the maximum and minimum values of the X coordinate during a predetermined period of the coordinates of the moving object and the square of the difference between the maximum and minimum values of the Y coordinate during a predetermined period of the coordinates of the moving object. Note that the predetermined period may be indicated by the number of data.

[0048] For example, the determination unit 23 performs a threshold determination on the movement amount / La in a predetermined position coordinate area according to the conditions shown in FIG. 5(2). As an example, when the total number of data is 400 samples, the determination unit 23 calculates the sum of the moving distances of 400 samples divided by the square root La of the sum of the square of the difference between the maximum and minimum values of the X coordinate and the square of the difference between the maximum and minimum values of the Y coordinate during a predetermined period of the coordinates of the moving object as XYratio. Then, when the calculated XYratio is, for example, greater than 6 and less than 8, the determination unit 23 determines that the moving object is an object (flag) that is not an object to be monitored.

[0049] Thereby, the monitoring device 1 can evaluate the moving distance of each point without separating the X coordinate and the Y coordinate by performing a threshold determination on the value obtained by dividing the total movement amount by the length of the diagonal line obtained from the maximum and minimum values for each coordinate axis, and can accurately determine an object (flag) that is not an object to be monitored.

[0050] [5. Exclusion Process] Next, with reference to FIGS. 6 and 7, an example of excluding sensor data that becomes noise from the plurality of sensor data acquired by the acquisition unit 21 will be described. FIGS. 6 and 7 are diagrams showing an example of the exclusion process by the monitoring device according to the embodiment.

[0051] As shown in FIG. 6, the diagram indicated by reference sign a0 shows the coordinates of the moving object when the moving object is detected by the motion sensor. The diagram indicated by reference sign a0 is the data of the original coordinates without excluding noise. The diagrams indicated by reference signs a1, a2, and a3 are cases where the sensor data is filtered (excluded) with different distances. In the diagram indicated by reference sign a1, the sensor data within a distance of 80 cm and more than 4 m is filtered (excluded). In the diagram indicated by reference sign a2, the sensor data within a distance of 80 cm and more than 4.5 m is filtered (excluded). In the diagram indicated by reference sign a3, the sensor data within a distance of 80 cm and more than 5 m is filtered (excluded). Note that the portion surrounded by the dotted circle is the centroid of 200 coordinates.

[0052] In the diagrams indicated by reference signs a2 and a3, the motion sensor reacts to various objects according to the distance at which the motion sensor filters (excludes) the sensor data, and the 200 centroids are elongated. Therefore, as shown in the diagram indicated by reference sign a1, for the purpose of the motion sensor detecting an object (a flag) that is not a target of attention existing near a parked vehicle, the motion sensor may filter (exclude) the sensor data within a distance of 80 cm and more than 4 m.

[0053] For example, the exclusion unit 22 sets the parameters of the motion sensor so as to exclude, from the plurality of sensor data, the sensor data having a distance of 4 m or more included in each sensor data or the sensor data having a distance of 80 cm or less included in each sensor data.

[0054] Accordingly, the monitoring device 1 can surely determine an object (a flag) that is not a target of attention and exists near the parked vehicle by excluding sensor data at positions where it is predicted that the monitoring device 1 will not detect the object (flag) that is not a target of attention.

[0055] FIG. 7 shows the coordinates of a moving object when some moving object is detected by the motion sensor. There is no flag erected near the door of the vehicle. In other words, the vehicle is not parked such that there is a flag near the door. Therefore, the exclusion unit 22 sets the parameters of the motion sensor to exclude sensor data included in a rectangular parallelepiped region represented by a width of 150 cm in the X coordinate and a width of 250 cm in the Y coordinate in the door direction with the sensor attached to the vehicle as an end point from the plurality of sensor data.

[0056] Accordingly, the monitoring device 1 can surely determine an object (a flag) that is not a target of attention and exists near the parked vehicle by excluding sensor data at positions where it is predicted that the monitoring device 1 will not detect the object (flag) that is not a target of attention.

[0057] [6. Flowchart] Next, the processing by the monitoring device 1 having the above-described configuration will be described with reference to the flowchart of FIG. 8. FIG. 8 is a flowchart showing an example of the flow of processing by the monitoring device according to the embodiment. In FIG. 8, it is assumed that the determination unit 23 determines that the moving object is an object that is not a target of attention when any one of the first condition, the second condition, and the third condition is satisfied. The flowchart of FIG. 8 is mainly executed by the control unit 20. Further, this flowchart can be configured as a program executed by the CPU included in the control unit 20 to obtain a monitoring program. Note that the following steps can also be executed in a different order, and there may be some processes that are omitted.

[0058] First, the acquisition unit 21 acquires a plurality of sensor data (coordinates of a moving object, signal strength, distance of the moving object) sequentially generated by a moving object sensor provided in the vehicle (step S11). For example, the acquisition unit 21 acquires sensor data including the signal strength received by the moving object sensor provided in the vehicle, the coordinates of the moving object generated from the information on the distance and angle calculated by the moving object sensor, and the distance detected by the moving object sensor.

[0059] Then, the determination unit 23 calculates the coordinates of the center of gravity from the coordinates of each moving object included in the plurality of sensor data (step S12).

[0060] Subsequently, the determination unit 23 determines whether or not X% or more of the coordinates of the sensor data whose distance from the coordinates of the center of gravity is within the first threshold exists (step S13). That is, the determination unit 23 determines whether or not X% or more of the sensor data in which the distance from the coordinates of the center of gravity to the included coordinates is within the first threshold is included in the plurality of sensor data. Here, when it is determined by the determination unit 23 that less than X% of the coordinates whose distance from the coordinates of the center of gravity is within the first threshold are included (step S13; No), the determination unit 23 returns to step S11 again.

[0061] On the other hand, when it is determined by the determination unit 23 that X% or more of the coordinates whose distance from the coordinates of the center of gravity is within the first threshold are included (step S13; Yes), the determination unit 23 determines whether or not the standard deviation of the moving distance (amount of movement) is greater than the second threshold and less than the third threshold (step S14). The second threshold here is set to be smaller than the third threshold. That is, the determination unit 23 determines whether or not the first condition is satisfied. Here, when it is determined by the determination unit 23 that the standard deviation of the moving distance (amount of movement) is less than or equal to the second threshold or greater than or equal to the third threshold (step S14; No), the determination unit 23 returns to step S11 again.

[0062] On the other hand, when the determination unit 23 determines that the standard deviation of the movement distance (movement amount) is greater than the second threshold and less than the third threshold (step S14; Yes), the determination unit 23 determines whether the standard deviation of the signal strength is less than the fourth threshold (step S15). That is, the determination unit 23 determines whether the second condition is satisfied. Here, when the determination unit 23 determines that the standard deviation of the signal strength is greater than or equal to the fourth threshold (step S15; No), the determination unit 23 returns to step S11 again.

[0063] On the other hand, when the determination unit 23 determines that the standard deviation of the signal strength is less than the fourth threshold (step S15; Yes), the determination unit 23 determines whether the value obtained by dividing the total movement amount in a predetermined period by the square root of the sum of the square of the difference between the maximum and minimum values of the X coordinate and the square of the difference between the maximum and minimum values of the Y coordinate is within a predetermined range (step S16). That is, the determination unit 23 determines whether the third condition is satisfied. Here, when the determination unit 23 determines that the value obtained by dividing the total movement amount in a predetermined period by the square root of the sum of the square of the difference between the maximum and minimum values of the X coordinate and the square of the difference between the maximum and minimum values of the Y coordinate is not within the predetermined range (step S16; No), the determination unit 23 returns to step S11 again.

[0064] On the other hand, when the determination unit 23 determines that the value obtained by dividing the total movement amount in a predetermined period by the square root of the sum of the square of the difference between the maximum and minimum values of the X coordinate and the square of the difference between the maximum and minimum values of the Y coordinate is within the predetermined range (step S16; Yes), the determination unit 23 determines that the moving object is an object not to be an attention target (step S17). Subsequently, the change unit 24 changes the setting of the moving object sensor (step S18). For example, the change unit 24 reduces the reception sensitivity for the signal from the coordinate direction of the moving object determined to be an object not to be an attention target.

[0065] Note that it has been described that the determination unit 23 determines that the moving object is an object (a flag) not to be the attention target when a predetermined ratio or more of the sensor data, in which the distance from the coordinates of the center of gravity to the coordinates included in each is within a predetermined length (for example, 30 cm), is included in the plurality of sensor data. The predetermined ratio has been described as, for example, 70%. However, the ratio of the sensor data falling within the range of the predetermined length (for example, 30 cm) from the center of gravity varies depending on the size of the flag. For example, in the case of a 45-cm flag, the ratio of the sensor data falling within the range of the predetermined length (for example, 30 cm) from the center of gravity may be, for example, 80%. In the case of a 60-cm flag, the ratio of the sensor data falling within the range of the predetermined length (for example, 30 cm) from the center of gravity may be, for example, 65%. In the case of a 70-cm flag, the ratio of the sensor data falling within the range of the predetermined length (for example, 30 cm) from the center of gravity may be, for example, 55%. Therefore, the determination unit 23 may simultaneously run algorithms with different predetermined ratios for each flag size. Then, when any of the algorithms matches, the determination unit 23 determines that the moving object is an object (a flag) not to be the attention target. In addition, the determination unit 23 specifies the flag size corresponding to the matching algorithm. Further, when none of the algorithms match, the determination unit 23 determines that the moving object is not an object (a flag) not to be the attention target. Thereby, the monitoring device 1 can determine that the moving object is an object (a flag) not to be the attention target regardless of the size of the flag.

[0066] 〔7. Effect〕 The monitoring device 1 according to the embodiment includes an acquisition unit 21 that acquires a plurality of sensor data sequentially generated by a moving object sensor provided in a vehicle, and a determination unit 23 that determines whether a moving object is an object not to be the attention target based on the distance from the average position of the moving object obtained from the position data included in the plurality of sensor data to each position data.

[0067] As a result, the monitoring device 1 can avoid the possibility of misjudgment with the object that is the target of attention by using the distances from the average position of the moving object obtained from the plurality of position data to each position data. That is, the monitoring device 1 can determine that the moving object is an object that is not the target of attention.

[0068] In addition, the determination unit 23 of the monitoring device 1 according to the embodiment calculates the average position of the moving object using a plurality of position data specified based on each of the plurality of sensor data, and when sensor data in which the distances from the average position of the moving object to each position data are within a predetermined length are included in the plurality of sensor data at a predetermined ratio or more, it determines that the moving object is an object that is not the target of attention. As a result, the monitoring device 1 can determine that the moving object is an object that is not the target of attention by determining whether sensor data in which the distances from the average position of the moving object to each position data are within a predetermined length are included in the plurality of sensor data at a predetermined ratio or more.

[0069] In addition, the determination unit 23 of the monitoring device 1 according to the embodiment further satisfies at least one of the conditions that the standard deviation of the moving distances of the plurality of sensor data is within a first range, the standard deviation of the intensities of the signals included in each of the plurality of sensor data is less than a threshold value, and the value obtained by dividing the sum of the moving distances of the plurality of sensor data by the diagonal length obtained from the maximum value and the minimum value of the position data of each sensor data is within a second range. When this is the case, it determines that the moving object is an object that is not the target of attention. As a result, the monitoring device 1 can accurately determine that the moving object is an object that is not the target of attention by using the condition using the standard deviation of the moving distance, the condition using the standard deviation of the signal intensity, and the condition using the position data.

[0070] Further, the monitoring device 1 according to the embodiment further includes an exclusion unit 22 that excludes sensor data corresponding to position data specified near a door attached to the vehicle from a plurality of sensor data acquired by the acquisition unit 21. Thereby, the monitoring device 1 can surely cause the moving object sensor to detect an object not to be a target of attention by excluding sensor data at positions where an object not to be a target of attention is not detected.

[0071] Further, the exclusion unit 22 of the monitoring device 1 according to the embodiment excludes, from a plurality of sensor data acquired by the acquisition unit 21, sensor data in which the distance included in each sensor data is equal to or greater than a predetermined distance, or sensor data in which the distance included in each sensor data is equal to or less than a predetermined height. Thereby, the monitoring device 1 can surely cause the moving object sensor to detect an object not to be a target of attention by excluding sensor data at positions where an object not to be a target of attention is not detected.

[0072] [Others] [8. Hardware Configuration] Further, the monitoring device 1 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. 9. FIG. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the monitoring device. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0073] The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

[0074] The HDD 1400 stores programs executed by the CPU 1100 and data and the like used by such programs. The communication interface 1500 receives data from other devices via a predetermined communication network and sends it to the CPU 1100, and sends the data generated by the CPU 1100 to other devices via a predetermined communication network.

[0075] The CPU 1100 controls output devices such as displays and printers and input devices such as keyboards and mice via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Also, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

[0076] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory or the like.

[0077] For example, when the computer 1000 functions as the monitoring device 1 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 20 by executing the program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from other devices via a predetermined communication network.

[0078] 〔9. Others〕 So far, an example of an embodiment according to the present invention has been described, but the present invention is not limited to the above-described embodiments. That is, those skilled in the art can implement various modifications without departing from the gist of the present invention in accordance with conventionally known knowledge. As long as the monitoring device of the present invention is still provided even by such modifications, of course, it is included in the scope of the present invention.

Explanation of Reference Numerals

[0079] 1 Monitoring device 10 Communication unit 20 Control unit 21 Acquisition unit 22 Removal unit 23 Determination unit 24 Change unit 30 Storage unit 100 Vehicle-mounted device

Claims

1. An acquisition unit that acquires a plurality of sensor data sequentially generated by a moving body sensor provided in a vehicle; A determination unit that determines whether the moving body is an object not to be concerned about, based on the distances from the average position of the moving body obtained from the position data included in the plurality of sensor data to the respective position data; A monitoring device, characterized by comprising the above.

2. The determination unit: Calculates the average position of the moving body using a plurality of position data specified based on each of the plurality of sensor data; Determines that the moving body is an object not to be concerned about when sensor data in which the distances from the average position of the moving body to the respective position data are within a predetermined length is included in the plurality of sensor data at a predetermined ratio or more. The monitoring device according to claim 1, characterized by the above.

3. The determination unit: Further, when at least one of the conditions is satisfied, including the condition that the standard deviation of the moving distances of the plurality of sensor data is within a first range, the condition that the standard deviation of the signal intensities included in each of the plurality of sensor data is less than a threshold value, and the condition that the value obtained by dividing the sum of the moving distances of the plurality of sensor data by the length of the diagonal line obtained from the maximum value and the minimum value of the position data of each sensor data is within a second range, determines that the moving body is an object not to be concerned about. The monitoring device according to claim 2, characterized by the above.

4. An exclusion unit that excludes sensor data corresponding to position data specified in the vicinity of a door attached to the vehicle from the plurality of sensor data acquired by the acquisition unit; The monitoring device according to claim 2, further characterized by comprising the above.

5. The exclusion unit: Excludes sensor data in which the distance included in each sensor data is equal to or greater than a predetermined distance, or sensor data in which the distance included in each sensor data is equal to or less than a predetermined height, from the plurality of sensor data acquired by the acquisition unit. The monitoring device according to claim 4, characterized by the above.

6. A method executed by a monitoring device, comprising: An acquisition step of acquiring a plurality of sensor data sequentially generated by a moving body sensor provided in a vehicle; A determination step of determining whether the moving body is an object not to be concerned about, based on the distances from the average position of the moving body obtained from the position data included in the plurality of sensor data to the respective position data. A monitoring method, characterized by including the above.

7. An acquisition step of acquiring a plurality of sensor data sequentially generated by a moving body sensor provided in a vehicle; A determination step of determining whether or not the moving body is an object not to be noted based on the distance from the average position of the moving body obtained from the position data included in the plurality of sensor data to each position data; A monitoring program characterized by causing a computer to execute the above.

Images