Anomaly detection device and anomaly detection method

Abstract

The present invention comprises: a data acquisition unit (11) that acquires detection data, which relates to a mobile body existing in a target region and which is generated on the basis of sensor data acquired by a sensor (2) detecting an object existing in the target region; a selection unit (131) that selects whether to perform abandonment detection in the target region or intrusion detection for the target region; an abandonment detection unit (132) that, when the selection unit (131) has selected to perform the abandonment detection in the target region, detects the presence or absence of abandonment in the target region on the basis of the detection data acquired by the data acquisition unit (11); and an intrusion detection unit (133) that, when the selection unit (131) has selected to perform the intrusion detection for the target region, detects the presence or absence of intrusion into the target region on the basis of the detection data acquired by the data acquisition unit (11).

Description

Technical Field

[0001] The present disclosure relates to an abnormality detection device and an abnormality detection method.

Background Art

[0002] In recent years, the problem of leaving infants etc. unattended in areas to be detected for abnormalities (hereinafter referred to as "target areas"), such as inside a vehicle cabin, has become a social problem. On the other hand, technologies for preventing illegal entry into the target area have been studied. Therefore, for example, there is known a technology that attempts to detect the leaving of an object in the target area by utilizing an originally existing anti-theft function and prevent the occurrence of such leaving (for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The detection of entry into the target area and the detection of the leaving of infants etc. in the target area do not necessarily need to be performed at the same timing. In the conventional technology as disclosed in Patent Document 1, this has not been considered, and there has been a problem that the detection of entry into the target area and the detection of the leaving of infants etc. in the target area continuously operate. As a result, there has been a problem of power consumption due to the execution of unnecessary processing.

[0005] The present disclosure has been made to solve the above problems, and an object thereof is to obtain an abnormality detection device capable of achieving both the detection of the presence or absence of entry into the target area and the detection of the presence or absence of the leaving of infants etc. in the target area while suppressing the execution of unnecessary processing.

Means for Solving the Problems

[0006] The anomaly detection device related to this disclosure is: Located inside the vehicle's passenger compartment The sensor Interior and exterior of the vehicle compartment Generated based on sensor data obtained by detecting objects present in the area. Inside and outside the vehicle A data acquisition unit that acquires detection data regarding the three-dimensional spatial distribution of existing moving objects, Inside the car Abandonment detection in, or Inside the car A selection unit that selects which of the following intrusion detection methods to perform, and the selection unit Inside the car If you select to perform abandoned object detection, the data acquisition unit will use the acquired detection data to perform the following actions: Inside the car An abandoned item detection unit that detects whether or not an item has been left behind, and a selection unit Inside the car If you select to perform intrusion detection, the data acquisition unit will use the acquired detection data to perform the intrusion detection. Inside the car The system includes an intrusion detection unit that detects whether or not an intrusion has occurred, and the abandoned unit detects whether or not an intrusion has occurred, based on the information of the magnitude of relative velocity, the shape of the spatial distribution, the respiration information, or the magnitude of the spatial distribution included in the three-dimensional spatial distribution of the detection data, Inside the car By determining whether there is a person who is considered to require assistance, Inside the car Detects whether items have been left behind. The selection unit further determines whether the vehicle owner is present in the vicinity of the vehicle based on the three-dimensional spatial distribution of the interior and exterior of the vehicle compartment. If the determination is made that the vehicle owner is present in the vicinity of the vehicle, it selects to perform abandoned vehicle detection inside the vehicle compartment. If the determination is made that the vehicle owner has left the vicinity of the vehicle, it selects to perform intrusion detection into the interior of the vehicle compartment. It is characterized by the following: [Effects of the Invention]

[0007] According to this disclosure, the anomaly detection device can simultaneously detect whether or not an intrusion has occurred into the target area and whether or not an infant or other child has been left unattended in the target area, while suppressing the execution of unnecessary processes. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows an example configuration of the anomaly detection device according to Embodiment 1. [Figure 2] This figure shows an example of the configuration of the data processing unit. [Figure 3]Figures 3A and 3B show examples of three-dimensional spatial distributions generated by the three-dimensional spatial distribution generation unit in Embodiment 1. Figure 3A shows an example of a top view of the three-dimensional spatial distribution, and Figure 3B shows an example of a side view of the three-dimensional spatial distribution. [Figure 4] In Embodiment 1, Figure 4A shows an example of a three-dimensional spatial distribution when the vehicle owner moves from within the area surrounding the vehicle to outside the area surrounding the vehicle. Figure 4B shows an example of a three-dimensional spatial distribution when the vehicle owner is within the area surrounding the vehicle, and Figure 4B shows an example of a three-dimensional spatial distribution when the vehicle owner moves outside the area surrounding the vehicle and is located outside the area surrounding the vehicle. [Figure 5] Figure 5A is a diagram illustrating an example of how the abandoned vehicle detection unit in Embodiment 1 detects the presence or absence of an abandoned vehicle inside the vehicle using a three-dimensional spatial distribution, and Figure 5B is a diagram illustrating an example of how the intrusion detection unit detects the presence or absence of an intrusion into the vehicle using a three-dimensional spatial distribution. [Figure 6] This figure shows a detailed configuration example of the detection result output unit of the anomaly detection device according to Embodiment 1. [Figure 7] This is a flowchart illustrating an example of the operation of the anomaly detection device according to Embodiment 1. [Figure 8] Figures 8A, 8B, and 8C illustrate an example of the control content when the selection unit in Embodiment 1 is capable of controlling the operation of the sensor. [Figure 9] Figures 9A, 9B, and 9C are diagrams illustrating the concept in Embodiment 1 where the selection unit changes the period of anomaly detection. Figure 9B shows an example of a three-dimensional spatial distribution generated based on sensor data in which a sensor with a small number of antennas detects an object inside the vehicle. Figure 9A shows an example of a three-dimensional spatial distribution generated based on sensor data in which a sensor with a larger number of antennas than Figure 9B detects an object inside the vehicle. Figure 9C shows a three-dimensional spatial distribution in which the distribution of moving objects in the three-dimensional spatial distribution shown in Figure 9B is superimposed. [Figure 10]FIG. 10A and FIG. 10B are diagrams showing an example of the hardware configuration of the abnormality detection device according to Embodiment 1.

Mode for Carrying Out the Invention

[0009] In the present disclosure, the abnormality detection device detects an abnormality in a region to be subjected to abnormality detection (hereinafter referred to as the "target region"). In the present disclosure, the abnormality detected by the abnormality detection device includes the replacement of a person requiring assistance and the intrusion into the target region. That is, specifically, the target region is a region for detecting the presence or absence of replacement of a person requiring assistance or the presence or absence of intrusion. In the present disclosure, the "person requiring assistance" is assumed to be a living body with a physique that has difficulty getting out of the target region on its own when replaced in the target region, such as an infant. In the present disclosure, living bodies such as pets are also included in the "person requiring assistance". In the following embodiments, as an example, the "target region" is the interior of the vehicle cabin, the "person requiring assistance" is an infant, and the abnormality detection device is configured to detect both the presence or absence of replacement of the infant in the vehicle cabin and the presence or absence of intrusion of a person into the vehicle cabin. Note that the vehicle cabin is, for example, the interior of a general passenger vehicle. In the following embodiments, when simply referred to as "replacement", the "replacement" means the replacement of a person requiring assistance. Also, in the following embodiments, when simply referred to as "intrusion", the "intrusion" means the intrusion of a person. More specifically, the "intrusion" means the intrusion of a moving object regarded as a person. In the following embodiments, the detection of the presence or absence of replacement in the vehicle cabin performed by the abnormality detection device is also simply referred to as "replacement detection in the vehicle cabin", and the detection of the presence or absence of intrusion into the vehicle cabin is also simply referred to as "intrusion detection into the vehicle cabin".

[0010] Embodiment 1. FIG. 1 is a diagram showing a configuration example of the abnormality detection device 1 according to Embodiment 1. The abnormality detection device 1 is mounted on, for example, a vehicle 100 and connected to a sensor 2 and an output device 3.

[0011] The sensor 2 detects an object in the vehicle cabin. In Embodiment 1, the sensor 2 is assumed to be a radio wave sensor such as a millimeter wave radar. The sensor 2 acquires, as sensor data, a reflected wave obtained by reflecting radio waves radiated toward the interior of the vehicle by an object in the vehicle interior. The sensor 2 is provided, for example, with an antenna having a wide-angle antenna directivity in the vehicle interior so that radio waves are irradiated to passengers who may be present in the vehicle interior.

[0012] Although the sensor 2 is a general radio wave sensor that detects an object, a method for acquiring sensor data by the sensor 2 will be described with an example. There are various modulation methods for the sensing signal of the radio wave sensor. Here, as an example of the modulation method, a case where the FM-CW (Frequency Modulation - Continuous Wave) method often used in in-vehicle applications is applied will be described. A radio wave transmission / reception unit (not shown) provided in the sensor 2 periodically generates an FM signal (referred to as a chirp wave) whose frequency increases and decreases. The radio wave transmission / reception unit amplifies the signal power to obtain the power required for radio wave irradiation, and irradiates radio waves into the space in the vehicle interior via a transmission antenna (not shown). When the radio waves irradiated into the vehicle interior space reach a target object existing in the radio wave irradiation range of the radio wave transmission / reception unit, a part of them is reflected by the surface of the target object and returns to the radio wave transmission / reception unit. Here, the target object refers to an object that reflects radio waves, such as a passenger in the vehicle interior or a vehicle structure.

[0013] The radio wave transmission / reception unit receives the radio waves (reflected waves) reflected by the surface of the target object via a reception antenna (not shown). A signal similar to the FM transmission wave is input as a reception signal to the radio wave transmission / reception unit as an FM received wave. The reception signal is input to the radio wave transmission / reception unit with a time difference required for the radio wave to reach the target object from the radio wave transmission / reception unit and return. The radio wave transmission / reception unit extracts the frequency difference between the frequency of the generated FM signal and the frequency of the reception signal, and generates an intermediate frequency (IF) signal having the frequency difference. The A / D conversion unit (not shown) of sensor 2 converts the intermediate frequency signal from an analog signal to a digital signal, and outputs the digital signal as sensor data to the anomaly detection device 1.

[0014] Note that although only one sensor 2 is shown in Figure 1, this is merely an example. Multiple sensors 2 may be provided on the vehicle 100, and multiple sensors 2 may be connected to the anomaly detection device 1. For example, one sensor 2 may be installed in a location that allows a clear view of the entire interior of the vehicle, such as an overhead console, so that one sensor 2 can cover the entire area of ​​the vehicle interior. Alternatively, multiple sensors may be installed in areas corresponding to seats or in areas of the vehicle interior that have been pre-divided into multiple sections. Furthermore, the sensor 2 may control its operation independently using an internal trigger, or it may control its operation based on an external trigger.

[0015] The anomaly detection device 1 detects whether an object has been left unattended inside the vehicle and whether a person has entered the vehicle, based on the sensor data output from sensor 2. In Embodiment 1, the anomaly detection device 1 detects whether an object has been left unattended inside the vehicle and whether a person has entered the vehicle, based on the sensor data output from a common sensor 2. Details of the configuration example of the anomaly detection device 1 will be described later.

[0016] Output device 3 is, for example, a display device such as a display or an audio output device such as a speaker, which is installed on a portable terminal carried by the owner of vehicle 100, or a lamp or horn installed in vehicle 100. Alternatively, output device 3 may be a driving control device that controls the operation of vehicle 100. Alternatively, output device 3 may be a server installed in an emergency medical system. Note that in Figure 1, the output device 3 is shown as being located on the vehicle 100 as an example, but this is merely one example. As mentioned above, the output device 3 may be located outside the vehicle 100 and connected to the abnormality detection device 1 outside the vehicle 100.

[0017] Output device 3 operates based on information (hereinafter referred to as "output control information") generated by abnormality detection device 1 based on the results of abnormality detection (specifically, detection of whether an object has been left unattended inside the vehicle or detection of whether an intruder has entered the vehicle). For example, if output device 3 is a display device, the display device will display a warning indicating that an unattended vehicle has been detected inside the vehicle, or a warning indicating that an intrusion into the vehicle has been detected, based on the output control information. For example, if output device 3 is an audio output device, the audio output device will output an alarm indicating that an unattended vehicle has been detected inside the vehicle, or an alarm indicating that an intrusion into the vehicle has been detected, based on the output control information. For example, if output device 3 is a driving control device, the driving control device will control vehicle 100 based on the output control information. Control of vehicle 100 includes stopping vehicle 100, controlling the opening and closing of windows, or controlling the air conditioning. For example, if output device 3 is a server in the emergency medical system, the server will request an ambulance based on the output control information.

[0018] Although only one output device 3 is shown in Figure 1, this is merely an example. For example, multiple output devices 3 may be provided, and multiple output devices 3 may be connected to the abnormality detection device 1. Alternatively, multiple types of output devices 3, such as an audio output device and a driving control device, may be connected to the abnormality detection device 1, and each of the multiple types of output devices 3 may perform operations based on output control information.

[0019] An example of the configuration of the abnormality detection device 1 according to Embodiment 1 will be described. As shown in Figure 1, the anomaly detection device 1 comprises a data acquisition unit 11, an anomaly detection unit 13, and a detection result output unit 14. The data acquisition unit 11 includes a data processing unit 12. The anomaly detection unit 13 includes a selection unit 131, an abandoned item detection unit 132, and an intrusion detection unit 133. In this example, the data acquisition unit 11 is assumed to include a data processing unit 12, but this is merely one example. For instance, the data processing unit 12 may be located outside the data acquisition unit 11 in the anomaly detection device 1.

[0020] The data acquisition unit 11 acquires data related to moving objects in the vehicle interior (hereinafter referred to as "detection data"), which is generated based on sensor data acquired when the sensor 2 detects objects in the vehicle interior. Specifically, the data processing unit 12 generates detection data based on sensor data acquired from the sensor 2, and the data acquisition unit 11 acquires the detection data generated by the data processing unit 12.

[0021] The data processing unit 12 performs preprocessing on the sensor data acquired from the sensor 2, which is common to the anomaly detection device 1 for detecting whether an object is left behind inside the vehicle and whether an intrusion into the vehicle has occurred, and generates detection data.

[0022] Here, Figure 2 shows an example of the configuration of the data processing unit 12. As shown in Figure 2, the data processing unit 12 includes, for example, a motion extraction unit 121, a motion analysis unit 122, and a three-dimensional spatial distribution generation unit 123.

[0023] The motion detection unit 121 extracts motion objects based on sensor data acquired from sensor 2. In Embodiment 1, the motion extracted by the motion extraction unit 121 is an intruder into the vehicle 100 or an occupant left behind inside the vehicle. The motion extraction unit 121 extracts motion by detecting movement inside the vehicle based on sensor data. Movement inside the vehicle includes movement due to changes in the position of the intruder into the vehicle 100 or an occupant left behind inside the vehicle, as well as body movements such as chest movements associated with breathing. One method for the motion detection unit 121 to extract motion is to apply a known MTI (Moving Target Indicators) filter to the sensor data, in this case the received signal acquired by sensor 2, or more specifically, the intermediate frequency signal based on the received signal. By applying the MTI filter, signal components from completely stationary objects, such as seats in the vehicle interior, are removed, and signal components from motion are extracted. The motion extraction unit 121 outputs the sensor data, from which signal components caused by motion have been extracted, to the motion analysis unit 122.

[0024] Based on the sensor data output from the motion extraction unit 121, the motion analysis unit 122 performs frequency analysis on the received signal indicating a motion extracted by the motion extraction unit 121 to extract information such as the position, velocity, and signal strength of the motion (hereinafter referred to as "motion information"), and outputs the extracted motion information to the three-dimensional spatial distribution generation unit 123. The motion analysis unit 122 can extract motion information based on various known methods or procedures such as Fourier transform (FFT), integration, peak extraction, and beamforming.

[0025] The three-dimensional spatial distribution generation unit 123 generates a three-dimensional spatial distribution as detection data based on the motion information output from the motion analysis unit 122. The three-dimensional spatial distribution generated by the three-dimensional spatial distribution generation unit 123 represents the distribution of areas where moving objects exist within the vehicle interior in three dimensions. More specifically, the three-dimensional spatial distribution represents the minute movements of moving objects, or in other words, the minute movements of target objects that reflect radio waves emitted by sensor 2, within the vehicle interior, using multiple grids that correspond to the reflection points of radio waves in three-dimensional space. The intermediate frequency signal is generated from the reflected waves when radio waves are reflected off the surface of the target object. The motion analysis unit 122 can calculate the position of the reflection point on the surface of the target object from this intermediate frequency signal and extract motion information. Since there are multiple reflection points on the surface of the target object, the three-dimensional spatial distribution generation unit 123 can generate a three-dimensional spatial distribution for the target object based on the motion information extracted by signal processing of reflected waves from multiple reflection points.

[0026] Here, Figures 3A and 3B show an example of a three-dimensional spatial distribution generated by the three-dimensional spatial distribution generation unit 123 in Embodiment 1. Figure 3A shows an example of a top view of a three-dimensional spatial distribution, and Figure 3B shows an example of a side view of a three-dimensional spatial distribution. The three-dimensional spatial distribution shown using Figures 3A and 3B represents the distribution generated when an infant is placed in a rear-facing child seat installed in the left rear seat of a vehicle.

[0027] In a three-dimensional spatial distribution, each grid is assigned a numerical value corresponding to the velocity of the target object located at that grid. More specifically, for a given grid, the greater the velocity of the target object at that grid's location, the larger the numerical value assigned to that grid. In other words, in a three-dimensional spatial distribution, grids included in the range where a moving object with small motion exists are assigned a larger numerical value than grids where no moving object exists. In the three-dimensional spatial distribution shown in Figures 3A and 3B, grids with larger assigned values ​​are shown darker. In other words, in the three-dimensional spatial distribution shown in Figures 3A and 3B, grids that are included in the range where moving objects exist are shown darker. Furthermore, in a three-dimensional spatial distribution, components of reflected waves that are stationary, in other words, have zero velocity, do not appear.

[0028] When the three-dimensional spatial distribution generation unit 123 generates a three-dimensional spatial distribution, the data acquisition unit 11 acquires it and outputs the acquired three-dimensional spatial distribution to the anomaly detection unit 13.

[0029] The anomaly detection unit 13 selects whether to perform detection of whether an object has been left unattended inside the vehicle or detection of whether an intruder has entered the vehicle, and then executes the detection process of the selected type. In Embodiment 1, the mode in which the abnormality detection device 1 detects whether or not an object has been left behind inside the vehicle is called the "object left behind detection mode," and the mode in which the abnormality detection device 1 detects whether or not an intruder has entered the vehicle is called the "intrusion detection mode." The abnormality detection unit 13 selectively switches between the object left behind detection mode and the intrusion detection mode.

[0030] The selection unit 131 of the abnormality detection unit 13 selects whether to perform detection of whether an object has been left unattended inside the vehicle or detection of whether an intruder has entered the vehicle. In other words, the selection unit 131 selects whether to enter the unattended object detection mode or the intrusion detection mode. If the selection unit 131 selects the abandoned vehicle detection mode, it outputs an instruction to the abandoned vehicle detection unit 132 to perform detection of whether or not an abandoned vehicle is present inside the vehicle (hereinafter referred to as the "abandoned vehicle detection start instruction"). If the selection unit 131 selects the intrusion detection mode, it outputs an instruction to the intrusion detection unit 133 to perform detection of whether or not there is an intrusion into the vehicle interior (hereinafter referred to as the "intrusion detection start instruction").

[0031] Here, we will explain, with an example, the selection criteria for whether the selection unit 131 selects the abandoned object detection mode or the intrusion detection mode.

[0032] <Example Selection (1)> For example, when the operation of the anomaly detection device 1 is started, the selection unit 131 selects the abandoned object detection mode until a preset time (hereinafter referred to as the "switching time") has elapsed, and if no abandoned object is detected after the switching time has elapsed, it selects the intrusion detection mode. In other words, the selection unit 131 switches from the abandoned object detection mode to the intrusion detection mode after the switching time has elapsed following the start of operation of the anomaly detection device 1. The timing at which the abnormality detection device 1 starts operating is, for example, when the doors of the vehicle 100 are locked. In other words, the selection unit 131 selects the abandoned vehicle detection mode until a switching time has elapsed after the doors are locked, and if no abandoned vehicle is detected after the switching time has elapsed, it selects the intrusion detection mode. An example of the start and end timing of the operation of the abnormality detection device 1 will be described later. The selection unit 131 can, for example, acquire data indicating whether a door is locked or unlocked (hereinafter referred to as "door data") from a door sensor (not shown) installed in the vehicle 100 that detects whether a door is locked or unlocked.

[0033] In this case, if the selection unit 131 determines that the door is locked based on the door data, it outputs an abandoned vehicle detection start instruction to the abandoned vehicle detection unit 132. Based on the abandoned vehicle detection start instruction output from the selection unit 131, the abandoned vehicle detection unit 132 detects whether or not an abandoned vehicle is inside the vehicle. The abandoned vehicle detection unit 132 then outputs the detection result of whether or not an abandoned vehicle is inside the vehicle (hereinafter referred to as the "abandoned vehicle detection result") to the selection unit 131 and the detection result output unit 14. Details of the abandoned vehicle detection unit 132 will be described later. If the selection unit 131 does not output an abandoned vehicle detection result from the abandoned vehicle detection unit 132 indicating that an abandoned vehicle has been detected inside the vehicle after the switching time has elapsed, it selects the intrusion detection mode. The selection unit 131 then outputs an intrusion detection start instruction to the intrusion detection unit 133. At this time, the selection unit 131 outputs an instruction to the abandoned vehicle detection unit 132 to terminate the detection of whether or not an abandoned vehicle is inside the vehicle (hereinafter referred to as the "abandoned vehicle detection termination instruction"). In this case, the abandoned vehicle detection unit 132 repeatedly detects whether or not an abandoned vehicle is present inside the vehicle, for example, until the switching time has elapsed.

[0034] <Example Selection (2)> For example, the selection unit 131 selects the abandoned vehicle detection mode when the abnormality detection device 1 starts operating, and selects the intrusion detection mode when the abandoned vehicle detection unit 132 has finished detecting whether or not an abandoned vehicle is inside the vehicle. In other words, after the abnormality detection device 1 starts operating and the process of detecting whether or not an abandoned vehicle is inside the vehicle is completed, the selection unit 131 switches from the abandoned vehicle detection mode to the intrusion detection mode. In the example selection (2), if the timing at which the abnormality detection device 1 starts operating is, for example, the timing when the doors of the vehicle 100 are locked, then the selection unit 131, when it determines that the doors are locked based on the door data, outputs an abandoned vehicle detection start instruction to the abandoned vehicle detection unit 132. The abandoned vehicle detection unit 132 detects whether an abandoned vehicle is present inside the vehicle based on the abandoned vehicle detection start instruction output from the selection unit 131. When the abandoned vehicle detection unit 132 completes the process of detecting whether an abandoned vehicle is present inside the vehicle, it outputs a notification to the selection unit 131 indicating that the detection of the presence or absence of an abandoned vehicle has been completed (hereinafter referred to as the "abandoned vehicle detection completion notification"). The abandoned vehicle detection unit 132 may consider the detection of the presence or absence of an abandoned vehicle complete when it has obtained a detection result for the presence or absence of an abandoned vehicle inside the vehicle once, or it may consider the detection of the presence or absence of an abandoned vehicle complete when it has obtained a preset number of repeated detection results for the presence or absence of an abandoned vehicle inside the vehicle. When the abandoned object detection unit 132 outputs an abandoned object detection completion notification, the selection unit 131 selects the intrusion detection mode. The selection unit 131 then outputs an intrusion detection start command to the intrusion detection unit 133. At this time, the selection unit 131 outputs an abandoned object detection end command to the abandoned object detection unit 132.

[0035] The difference between the mode selection method by the selection unit 131 in the above-mentioned <Selection Example (2)> and the mode selection method by the selection unit 131 in <Selection Example (1)> is that the selection unit 131 immediately switches to intrusion detection mode when it detects that there is no unattended person inside the vehicle, without setting a predetermined period (switching time).

[0036] <Example Selection (3)> The selection unit 131 may, for example, when the operation of the abnormality detection device 1 is started, select the abandoned vehicle detection mode while the owner of the vehicle 100 is present in the vicinity of the vehicle 100, and select the intrusion detection mode when the owner of the vehicle 100 leaves the vicinity of the vehicle 100. In other words, the selection unit 131 switches from the abandoned vehicle detection mode to the intrusion detection mode when the owner of the vehicle 100 leaves the vicinity of the vehicle 100. The selection unit 131 determines whether the owner of the vehicle 100 is present in the vicinity of the vehicle 100, for example, by determining whether the owner is present in a pre-set area around the vehicle. The selection unit 131 can determine, for example, whether the owner of vehicle 100 is present in the area surrounding the vehicle, based on detection data acquired from the data acquisition unit 11, i.e., in this case, a three-dimensional spatial distribution.

[0037] Here, Figures 4A and 4B show an example of a three-dimensional spatial distribution when the owner of vehicle 100 moves from within the area surrounding the vehicle to outside the area surrounding the vehicle in Embodiment 1. Figure 4A shows an example of the three-dimensional spatial distribution when the owner of vehicle 100 is located within the area surrounding the vehicle, and Figure 4B shows an example of the three-dimensional spatial distribution when the owner of vehicle 100 has moved outside the area surrounding the vehicle and is located outside the area surrounding the vehicle. Figures 4A and 4B show an example of a top view of the three-dimensional spatial distribution. In Figure 4A, the owner of vehicle 100 is indicated by "D". The radio waves emitted from sensor 2 also propagate outside the vehicle. Therefore, sensor 2 also detects people around vehicle 100, in other words, people outside the vehicle. As a result, in the three-dimensional spatial distribution, the minute movements of people around vehicle 100 that reflect the radio waves emitted by sensor 2 are represented by multiple grids corresponding to the reflection points of the radio waves in the three-dimensional space outside the vehicle.

[0038] The selection unit 131 stores, for example, the three-dimensional spatial distribution acquired from the data acquisition unit 11 for a predetermined time period in a storage unit (not shown). The storage unit is located in a place accessible by the anomaly detection device 1. Based on the three-dimensional spatial distribution of time series stored in the memory unit, the selection unit 131 determines that the owner of vehicle 100 has moved from inside the vehicle surrounding area to outside the vehicle surrounding area, or in other words, has moved away from the vicinity of vehicle 100, when the state changes from inside the vehicle surrounding area to outside the vehicle surrounding area and within the area surrounding the vehicle (see Figure 4A), and then to outside the area surrounding the vehicle (see Figure 4B). Note that Figure 4 omits an illustration of an example of a three-dimensional spatial distribution showing the presence of a moving object inside the vehicle.

[0039] The method for determining whether the owner of vehicle 100 has moved outside the vehicle surrounding area, as described above, is merely one example, and the selection unit 131 may determine whether the owner of vehicle 100 has moved outside the vehicle surrounding area by other means. For example, the selection unit 131 may determine whether the owner of vehicle 100 has moved outside the vehicle surrounding area by short-range wireless communication with a key sensor (not shown) provided on the key of vehicle 100.

[0040] The selection unit 131 selects the intrusion detection mode when it determines that the owner of the vehicle 100 has left the vicinity of the vehicle 100. The selection unit 131 then outputs an intrusion detection start command to the intrusion detection unit 133. At this time, the selection unit 131 outputs an abandoned vehicle detection end command to the abandoned vehicle detection unit 132. In this case, the abandoned vehicle detection unit 132 repeatedly detects whether an abandoned vehicle is present inside the vehicle until, for example, the selection unit 131 outputs an instruction to end abandoned vehicle detection.

[0041] The selection unit 131 may, for example, combine the above-mentioned <Selection Example (1)>, <Selection Example (2)>, or <Selection Example (3)> to determine whether to select the abandoned object detection mode or the intrusion detection mode. For example, the selection unit 131 may combine <Selection Example (1)> and <Selection Example (3)> to select an intrusion detection mode when either the owner of the vehicle 100 leaves the vehicle 100 or the switching time has elapsed, and output an abandoned vehicle detection termination instruction to the abandoned vehicle detection unit 132. Note that the above-mentioned <Selection Example (1)>, <Selection Example (2)>, and <Selection Example (3)> are merely examples, and the selection unit 131 may determine whether to select the abandoned vehicle detection mode or the intrusion detection mode using selection criteria other than those described above. For example, the selection unit 131 may select the abandoned vehicle detection mode or the intrusion detection mode in accordance with the laws or assessments of the area in which the vehicle 100 is used.

[0042] If the selection unit 131 selects to perform detection of whether or not an object has been left behind inside the vehicle, the abandoned object detection unit 132 of the abnormality detection unit 13 detects whether or not an object has been left behind inside the vehicle based on the detection data acquired by the data acquisition unit 11, in this case, the three-dimensional spatial distribution. Specifically, when the selection unit 131 outputs an instruction to start abandoned vehicle detection, the abandoned vehicle detection unit 132 detects whether or not an abandoned vehicle is present inside the vehicle based on a three-dimensional spatial distribution.

[0043] An example of how the abandoned vehicle detection unit 132 detects the presence or absence of an abandoned vehicle in the vehicle interior based on a three-dimensional spatial distribution will be described. For example, the abandoned vehicle detection unit 132 determines whether or not there is a moving object that is considered to be an infant inside the vehicle based on a three-dimensional spatial distribution. In Embodiment 1, the determination made by the abandoned child detection unit 132, "whether or not there is a moving body that is considered to be an infant inside the vehicle," more specifically means "whether or not there is a moving body that is considered to be an abandoned infant inside the vehicle." In other words, the abandoned child detection unit 132 determines "whether or not only a moving body that is considered to be an infant is inside the vehicle."

[0044] The abandoned vehicle detection unit 132 first determines whether there is a moving body that can be considered an occupant in the area corresponding to the interior of the vehicle in the three-dimensional spatial distribution, and if there is a moving body that can be considered an occupant, it determines which seat the moving body that can be considered an occupant is located in. Each grid in the three-dimensional spatial distribution is associated with coordinates in the real space inside the vehicle, represented by a three-dimensional coordinate system that shows the real space inside the vehicle. The abandoned vehicle detection unit 132 can identify the region corresponding to the area inside the vehicle in the three-dimensional spatial distribution. Hereinafter, the three-dimensional spatial distribution of the portion corresponding to the area inside the vehicle will be referred to as the "vehicle interior three-dimensional spatial distribution".

[0045] The abandoned vehicle detection unit 132 determines whether the spatial distribution included in the three-dimensional spatial distribution inside the vehicle is a spatial distribution corresponding to an occupant (hereinafter referred to as "occupant spatial distribution") based on the shape of the spatial distribution. Any method can be used for determination based on the shape of the spatial distribution, but for example, one possible approach is to use a model that has learned the shape of the occupant spatial distribution to determine whether or not the spatial distribution included in the three-dimensional spatial distribution inside the vehicle is the occupant spatial distribution. Furthermore, the abandoned vehicle detection unit 132 may determine that a spatial distribution is an occupant spatial distribution if the relative velocity corresponding to the spatial distribution included in the three-dimensional spatial distribution inside the vehicle is greater than, for example, a preset threshold. Each grid in the three-dimensional spatial distribution is associated with a relative velocity. An occupant, for example, an infant lying in a child seat, will still move to some extent. If the abandoned object detection unit 132 determines that the spatial distribution included in the three-dimensional spatial distribution inside the vehicle is the occupant spatial distribution, it determines that there is a moving object that is considered to be an occupant inside the vehicle.

[0046] Furthermore, the abandoned vehicle detection unit 132 determines whether the detected moving object, which is considered to be an occupant, is an adult or an infant, based on the occupant spatial distribution included in the three-dimensional spatial distribution inside the vehicle. Any method can be used for determination based on the size of the occupant space distribution. For example, one method could be used to determine whether a moving object considered to be an occupant is an adult or an infant based on the size of the occupant space distribution. Alternatively, one could use a model that has learned the sizes of the occupant space distributions for adults and infants, respectively, to determine whether a moving object considered to be an occupant is an adult or an infant. The abandoned vehicle detection unit 132 determines whether each of the multiple moving objects considered to be occupants is an adult or an infant.

[0047] The abandoned vehicle detection unit 132 then determines whether or not there is a body that has been determined to be an infant among the bodies that are considered to be occupants. The abandoned person detection unit 132, if it determines that there is an infant among the bodies considered to be occupants, determines whether there is an adult in addition to the infant. If there is no adult in addition to the infant, the abandoned person detection unit 132 detects that only an infant is present in the vehicle. In other words, the abandoned person detection unit 132 detects that an abandoned person has been found in the vehicle. On the other hand, the abandoned vehicle detection unit 132 detects that if there is an adult in addition to the vehicle it has determined to be an infant, or if there is no vehicle determined to be an infant among the vehicles considered to be occupants, that is, if all vehicles considered to be occupants are determined to be adults, then the vehicle is not in a state where only vehicles considered to be infants are present inside the vehicle. In other words, the abandoned vehicle detection unit 132 detects that there is no abandoned vehicle inside the vehicle.

[0048] The abandoned vehicle detection unit 132 performs the process of detecting whether or not an abandoned vehicle is present inside the vehicle, as described above, at a predetermined interval (hereinafter referred to as the "first interval").

[0049] The abandoned vehicle detection unit 132 outputs the abandoned vehicle detection result, indicating whether or not an abandoned vehicle is present inside the vehicle, to the detection result output unit 14. The abandoned object detection unit 132 may output the abandoned object detection result to the selection unit 131. Furthermore, if the abandoned vehicle detection unit 132 performs detection of whether an abandoned vehicle is present inside the vehicle a number of preset times (one or more), it may output an abandoned vehicle detection completion notification to the selection unit 131 when it has completed detecting whether an abandoned vehicle is present inside the vehicle.

[0050] If the detection of an unattended passenger inside the vehicle is based solely on the presence or absence of movement inside the vehicle, it may detect that an unattended passenger is an adult, or other passengers other than those requiring assistance (in this case, an infant), have been left behind. As a result, a problem of over-alerts may occur, such as issuing an alarm for an unattended passenger even when an alarm is unnecessary. The detection result output unit 14 controls the output of the alarm. Details of the detection result output unit 14 will be described later. Therefore, the abandoned child detection unit 132 detects not only whether there is a moving object inside the vehicle, but also, if there is a moving object inside the vehicle, whether that moving object is an infant that is subject to the alarm output. This prevents the abandoned passenger detection unit 132 from mistakenly detecting an abandoned passenger in the vehicle simply because there is an occupant in the vehicle who should not be considered abandoned, i.e., an occupant who does not require assistance.

[0051] In the example described above, the abandoned occupant detection unit 132 determines whether the detected occupant is an adult or an infant by determining its size based on the occupant spatial distribution. However, this is merely one example. The abandoned occupant detection unit 132 may determine whether the detected occupant is an adult or an infant by other methods. For example, the abandoned passenger detection unit 132 may determine whether the detected moving object is an adult or an infant by detecting the breathing rate based on the passenger spatial distribution. For example, the abandoned vehicle detection unit 132 may acquire images captured by a camera (not shown) connected to the anomaly detection device 1, and perform known image recognition processing on the captured images to determine whether the detected occupant is an adult or an infant. For example, the abandoned vehicle detection unit 132 may estimate the age of the occupant from the occupant's face recognized from the captured images and determine whether the detected occupant is an adult or an infant. Alternatively, for example, the abandoned vehicle detection unit 132 may determine whether the moving object considered to be a passenger is an adult or an infant by detecting crying sounds based on audio data acquired from a microphone (not shown) connected to the anomaly detection device 1. Thus, the abandoned vehicle detection unit 132 can determine whether the detected occupant is an adult or an infant using various known methods. The abandoned vehicle detection unit 132 may also determine whether the detected occupant is an adult or an infant by combining various known methods.

[0052] If the selection unit 131 selects to perform detection of whether or not there is an intrusion into the vehicle interior, the intrusion detection unit 133 of the anomaly detection unit 13 detects whether or not there is an intrusion into the vehicle interior based on the detection data acquired by the data acquisition unit 11, in this case, the three-dimensional spatial distribution. Specifically, when the selection unit 131 outputs an intrusion detection start instruction, the abandoned vehicle detection unit 132 detects whether or not an intrusion has occurred into the vehicle interior based on the three-dimensional spatial distribution.

[0053] An example of how the intrusion detection unit 133 detects whether or not an intruder has entered the vehicle interior based on a three-dimensional spatial distribution will be described. For example, the intrusion detection unit 133, based on the three-dimensional spatial distribution of time series stored in the memory unit, detects a transition from a state where no moving object is present in the vehicle interior to a state where a moving object is present in the vehicle interior. In this case, it considers the moving object to be a person, or in other words, an intruder, and detects that there has been an intrusion into the vehicle interior.

[0054] In the example described above, the intrusion detection unit 133 detects whether or not an intrusion has occurred into the vehicle interior based on the distribution of occupant space, but this is merely one example. The intrusion detection unit 133 may also detect whether or not an intrusion has occurred into the vehicle interior using other methods. For example, the intrusion detection unit 133 may perform the detection based on vibration data acquired from a vibration sensor (not shown) connected to the anomaly detection device 1. In this way, the intrusion detection unit 133 can detect whether or not there is an intrusion into the vehicle interior using various known methods. The intrusion detection unit 133 may also detect whether or not there is an intrusion into the vehicle interior by combining various known methods.

[0055] The intrusion detection unit 133 performs the process of detecting whether or not there is an intrusion into the vehicle interior, as described above, at a predetermined interval (hereinafter referred to as the "second interval"). Here, we assume that the length of the first period and the length of the second period are the same.

[0056] The intrusion detection unit 133 outputs the detection result (hereinafter referred to as "intrusion detection result") of whether or not an intrusion has occurred into the vehicle interior to the detection result output unit 14. The intrusion detection unit 133 may output the intrusion detection result to the selection unit 131.

[0057] The function of detecting whether or not someone has entered the vehicle interior can be achieved if the presence or absence of a moving object inside the vehicle or around the vehicle 100 can be detected. The intrusion detection unit 133 does not necessarily have to detect the attributes of the moving object (for example, whether the moving object is an adult or an infant), unlike the abandoned object detection unit 132 which detects whether or not someone has been left behind inside the vehicle.

[0058] Here, Figure 5A is a diagram illustrating an example of how the abandoned vehicle detection unit 132 detects the presence or absence of an abandoned vehicle inside the vehicle using a three-dimensional spatial distribution in Embodiment 1, and Figure 5B is a diagram illustrating an example of how the intrusion detection unit 133 detects the presence or absence of an intrusion into the vehicle using a three-dimensional spatial distribution.

[0059] In Figure 5A, the left-hand figure shows an example of a top view of a three-dimensional spatial distribution, and the right-hand figure shows an example of a side view of a three-dimensional spatial distribution. In the example of the top view of the three-dimensional spatial distribution shown on the left, the crew member is indicated as "D4," and in the example of the side view of the three-dimensional spatial distribution shown on the right, the crew member is indicated as "D5." Note that the crew member indicated as "D4" and the crew member indicated as "D5" are the same person. The abandoned vehicle detection unit 132 can detect the number and position of moving objects, in other words, occupants, present in the vehicle interior, based on a top view of the three-dimensional spatial distribution as shown in the left-hand figure. For example, in the example shown in Figure 5A, the abandoned vehicle detection unit 132 can detect the presence of an occupant in the left rear seat of the vehicle interior, based on the top view of the three-dimensional spatial distribution on the left. However, the abandoned passenger detection unit 132 cannot detect whether an occupant is an abandoned passenger, in other words, whether it is an infant, based solely on the top view of the three-dimensional spatial distribution. Therefore, the abandoned passenger detection unit 132 also uses a side view of the three-dimensional spatial distribution, as shown in the right-hand diagram of Figure 5A, to detect whether an abandoned passenger is present in the vehicle, in other words, whether an infant is present in the vehicle. By using the side view of the three-dimensional spatial distribution, the abandoned passenger detection unit 132 can detect, for example, the occupant's height and other physical characteristics. For example, in the example of Figure 5A, the abandoned passenger detection unit 132 detects from the top view of the three-dimensional spatial distribution that an occupant is present only in the left rear seat, and from the side view of the three-dimensional spatial distribution, it detects that the occupant is an infant in a child seat. Looking at the side view of the three-dimensional spatial distribution, it can be seen that the occupant is positioned above the seat surface, and that the occupant's physical characteristics are those of an infant. Therefore, the abandoned vehicle detection unit 132 detects that an abandoned vehicle is present inside the vehicle.

[0060] In Figure 5B, the three-dimensional spatial distribution on the left, the three-dimensional spatial distribution in the middle, and the three-dimensional spatial distribution on the right show the top view of the time-series three-dimensional spatial distribution in that order. In the example of a top view of a three-dimensional spatial distribution shown on the left, the intruder is indicated as "D1". In the example of a top view of a three-dimensional spatial distribution shown in the middle, the intruder is indicated as "D2". In the example of a top view of a three-dimensional spatial distribution shown on the right, the intruder is indicated as "D3". Note that the intruder indicated as "D1", the intruder indicated as "D2", and the intruder indicated as "D3" are the same person. Based on the top view of the time-series three-dimensional spatial distribution shown in Figure 5B, the intrusion detection unit 133 detects that a moving object (intruder) approaches the vehicle 100 while there are no occupants inside the vehicle, and that the moving object has entered the vehicle. In other words, the intrusion detection unit 133 detects that there has been an intrusion into the vehicle. Furthermore, the intrusion detection unit 133 may, for example, detect an intrusion into the vehicle interior if a moving object is present around the vehicle 100 for a certain period of time, in order to prevent intrusion into the vehicle interior. In this case as well, the intrusion detection unit 133 can detect whether or not a moving object is present around the vehicle 100 for a certain period of time based on a top view of the time-series three-dimensional spatial distribution.

[0061] In this way, the abandoned vehicle detection unit 132 and the intrusion detection unit 133 can detect whether an abandoned vehicle is inside the vehicle and whether an intrusion has occurred inside the vehicle, respectively, using a three-dimensional spatial distribution acquired from a common sensor 2, in this case a radio wave sensor. However, in order to detect whether or not someone has been left behind inside the vehicle, the abandoned person detection unit 132 needs to detect attributes such as the occupant's physique, including whether the occupant is an adult or an infant. Therefore, the processing load for the abandoned person detection unit 132 to detect whether or not someone has been left behind inside the vehicle is higher than that for the intrusion detection unit 133 to detect whether or not someone has been intruded into the vehicle. On the other hand, the intrusion detection unit 133 can detect intrusion using only the information viewed from above the vehicle 100 within the three-dimensional spatial distribution. Furthermore, the intrusion detection unit 133 can detect whether or not an intrusion has occurred inside the vehicle if it knows whether or not a moving object is inside or outside the vehicle. Therefore, the intrusion detection unit 133 can, for example, limit the range in which it detects whether or not an intrusion has occurred inside the vehicle to the vicinity of the boundary between the inside and outside of the vehicle within the three-dimensional spatial distribution.

[0062] Returning to the explanation of the example configuration of the anomaly detection device 1 using Figure 1.

[0063] The detection result output unit 14 outputs to the output device 3 information based on the detection result of whether or not an unattended vehicle is present inside the vehicle by the unattended vehicle detection unit 132 (hereinafter referred to as "output control information"), or output control information based on the detection result of whether or not an intrusion into the vehicle interior is present by the intrusion detection unit 133.

[0064] Here, Figure 6 shows a detailed example of the configuration of the detection result output unit 14 of the abnormality detection device 1 according to Embodiment 1.

[0065] The detection result output unit 14 includes a detection result storage unit 141, a notification content generation unit 142, and an output control unit 143.

[0066] The detection result storage unit 141 stores the abandoned object detection result output from the abandoned object detection unit 132 of the abnormality detection unit 13, or the intrusion detection result output from the intrusion detection unit 133, for a predetermined period of time. In this example, the detection result storage unit 141 is assumed to be located within the anomaly detection device 1, as shown in Figure 6. However, this is merely one example. The detection result storage unit 141 may be located outside the anomaly detection device 1, in a location accessible to the device 1. Furthermore, the detection result storage unit 141 may be the same as the storage unit described above.

[0067] The notification content generation unit 142 generates output control information based on the abandoned object detection result output from the abandoned object detection unit 132 of the abnormality detection unit 13, or the intrusion detection result output from the intrusion detection unit 133. In Embodiment 1, the output control information is information that causes the output device 3 to perform an action in response to the presence of an object left unattended inside the vehicle or an intrusion into the vehicle. The notification content generation unit 142 determines, for example, the actions to be performed by the output device 3 based on the abandoned object detection result or the intrusion detection result, and generates output control information. For example, the action to be performed by the output device 3 is, for instance, notification that something has been left unattended inside the vehicle or that someone has entered the vehicle. The notification content generation unit 142 generates information to be performed by the output device 3 as output control information. If the notification content generation unit 142 is to be performed by the output device 3, for example, it may determine the output format and include information to instruct the determined output format in the output control information. The notification content generation unit 142 may obtain the abandoned object detection result or intrusion detection result directly from the abandoned object detection unit 132 or the intrusion detection unit 133, or it may obtain it from the detection result storage unit 141.

[0068] For example, suppose output device 3 is a display device. If the notification content generation unit 142 obtains, for example, a detection result indicating that an object has been left behind inside the vehicle, it generates output control information to output device 3 to display a message informing it that an object has been left behind. Also, if the notification content generation unit 142 obtains, for example, a detection result indicating that an intrusion has occurred into the vehicle, it generates output control information to output device 3 to display a message informing it that an intrusion has occurred into the vehicle or that there has been suspicious activity around vehicle 100. Output device 3 displays information according to the output control information.

[0069] For example, suppose output device 3 is an audio output device. If the notification content generation unit 142 obtains, for example, a detection result indicating that an object has been left behind inside the vehicle, it generates output control information to output device 3 to output an audio or alarm sound informing that an object has been left behind. Also, if the notification content generation unit 142 obtains, for example, a detection result indicating that an intrusion has occurred into the vehicle, it generates output control information to output device 3 to output an audio or alarm sound informing that an intrusion has occurred into the vehicle or that there has been suspicious activity around vehicle 100. Output device 3 outputs voice or sound according to the output control information.

[0070] For example, suppose output device 3 is a driving control device. If the notification content generation unit 142 obtains, for example, a detection result indicating that an unattended vehicle has been left inside the vehicle, it generates output control information to inform output device 3 that an unattended vehicle has been found. Also, if the notification content generation unit 142 obtains, for example, a detection result indicating that an intrusion has occurred into the vehicle, it generates output control information to inform output device 3 that an intrusion has occurred into the vehicle or that there has been suspicious activity around vehicle 100. Output device 3 performs vehicle control according to the output control information. For example, if output control information indicating that a child has been left unattended inside the vehicle is output, output device 3 will perform control such as opening the windows of vehicle 100 or turning on the air conditioning. If a child has been left unattended inside the vehicle, it is possible that the child may be suffering from heatstroke or other illnesses. On the other hand, for example, if output control information indicating that someone has entered the vehicle is output, output device 3 will perform control to lock the doors of vehicle 100.

[0071] In this way, the notification content generation unit 142 can generate output control information to cause the output device 3 to perform different actions depending on whether an abandoned object detection result or an intrusion detection result has been output.

[0072] Furthermore, the notification content generation unit 142 may include supplementary information in the output control information, such as, for example, an image of the interior of the vehicle in which an intruder is being photographed, or information indicating the location of an abandoned child. The notification content generation unit 142 can, for example, acquire images of the interior of the vehicle from a camera (not shown) mounted on the vehicle 100. Furthermore, the notification content generation unit 142 can, for example, acquire the three-dimensional spatial distribution used to detect whether or not a child has been left behind from the abandoned child detection unit 132, and then identify the location of the abandoned child from the acquired three-dimensional spatial distribution.

[0073] Furthermore, the notification content generation unit 142 may generate output control information that increases the notification level according to the elapsed time after, for example, detection of an unattended vehicle inside the vehicle or detection of intrusion into the vehicle. For example, the notification content generation unit 142 generates output control information that increases the alarm level as the elapsed time since detection of an unattended vehicle inside the vehicle or intrusion into the vehicle interior increases. The notification content generation unit 142 can also obtain past unattended vehicle detection results or intrusion detection results by referring to the detection result storage unit 141, and can determine the elapsed time since detection of an unattended vehicle inside the vehicle or intrusion into the vehicle interior. Thus, the notification content generation unit 142 can also generate output control information that changes the output format in stages.

[0074] For example, if it is detected that a vehicle has been left unattended inside the vehicle, this could be because the owner of vehicle 100 has intentionally left the vehicle temporarily. The notification content generation unit 142 generates output control information that increases the alarm level as the elapsed time since the detection of the vehicle being left unattended increases. As a result, the output device 3 issues a low-level alarm immediately after the detection of the vehicle being left unattended, and increases the alarm level as the elapsed time of the vehicle being left unattended increases.

[0075] The notification content generation unit 142 outputs the generated output control information to the output control unit 143.

[0076] The output control unit 143 outputs the output control information output from the notification content generation unit 142 to the output device 3. At this time, the output control unit 143 controls the output destination of the output control information according to the content of the output control information.

[0077] For example, if the output control information concerns an intrusion into the vehicle interior, the output control unit 143 outputs the output control information only to the output device 3 located outside the vehicle 100. Since intrusion into the vehicle interior occurs when there are no occupants inside, it is assumed that no one would notice an alert issued inside the vehicle. By outputting the output control information only to the output device 3 located outside the vehicle 100, the output control unit 143 can prevent the output of unnecessary output control information.

[0078] For example, if the output control information concerns being left behind inside the vehicle, the output control unit 143 outputs the output control information not only to the output device 3 located outside the vehicle 100, but also to the output device 3 located inside the vehicle. By outputting the output control information to the output device 3 located inside the vehicle, the output control unit 143 can inform the child who has been left behind that they are in a state of being left behind.

[0079] The output control unit 143 can combine various output devices 3 to determine the output destination of the output control information. The output control unit 143 outputs output control information from the notification content generation unit 142 to the output device 3, causing the output device 3 to perform control according to the output control information. This allows the abnormality detection device 1 to inform the owner of the vehicle 100, or more specifically, whether the vehicle has been abandoned or whether an intrusion has occurred.

[0080] Furthermore, the output control unit 143 may output information to the output device 3 for stopping alarms, etc., based on the output control information (hereinafter referred to as "stop control information"). For example, if an input device (not shown) that receives alarm deactivation instructions receives an alarm deactivation instruction, the output control unit 143 acquires the deactivation instruction and outputs deactivation control information to the output device 3. When the output device 3 receives the deactivation control information, it stops the control it was performing based on the output control information, such as an alarm.

[0081] The output control unit 143 may change the control content instructed by the stop control information depending on whether the output device 3 is outputting based on output control information generated based on the abandoned device detection result or on outputting based on output control information generated based on the intrusion detection result. For example, if the output control unit 143 receives a stop command after the output device 3 has issued an alarm based on output control information generated based on the abandoned vehicle detection result, the output control unit 143 will unconditionally stop the alarm output that the output device 3 was issuing based on the output control information. On the other hand, if the output device 3 receives a stop command after it has issued an alarm based on output control information generated based on the intrusion detection result, the output control unit 143 will not stop the alarm output that the output device 3 is issuing based on the output control information unless the vehicle key 100 is in the vicinity of the vehicle 100. This allows the output control unit 143 to prevent, for example, an intruder from stopping the alarm.

[0082] The input device for receiving stop instructions may be mounted on the vehicle 100 or located outside the vehicle. The input device may be, for example, a communication device. For example, even if a stop instruction is input via remote operation, the output control unit 143 can receive the stop instruction and stop the control that the output device 3 was performing based on the output control information, thereby further improving the convenience of the abnormality detection device 1.

[0083] The content of the output control information generated by the detection result output unit 14 described above is merely an example. The detection result output unit 14 may generate output control information with content other than that described above and control the output device 3 accordingly. For example, the detection result output unit 14 may generate output control information that conforms to the laws or assessments of the area in which the vehicle 100 is used and control the output device 3 accordingly.

[0084] The operation of the abnormality detection device 1 according to Embodiment 1 will be described below. Figure 7 is a flowchart illustrating an example of the operation of the abnormality detection device 1 according to Embodiment 1.

[0085] First, we will explain, with some examples, the timing at which the anomaly detection device 1 starts and ends its operation as shown in the flowchart of Figure 7.

[0086] <Timing example (1)> For example, the abnormality detection device 1 starts operating when the doors of the vehicle 100 are locked, and then repeats the operation shown in the flowchart of Figure 7 until the doors are unlocked. For example, the control unit (not shown) of the abnormality detection device 1 acquires door data from the door sensor, and when it detects that the door is locked, it instructs the data acquisition unit 11, abnormality detection unit 13, and detection result output unit 14 of the abnormality detection device 1 to start operation. When it detects that the door has been unlocked, it instructs the data acquisition unit 11, abnormality detection unit 13, and detection result output unit 14 to end operation.

[0087] <Timing example (2)> Since it is also conceivable that the occupants of vehicle 100 may leave vehicle 100 without locking the doors, for example, the abnormality detection device 1 may start operating when vehicle 100 stops and the doors of vehicle 100 are opened or closed, and repeat the operation shown in the flowchart of Figure 7 until the door is opened again. For example, the control unit of the abnormality detection device 1 detects that vehicle 100 has stopped from a vehicle speed sensor (not shown) or a shift position sensor (not shown) mounted on vehicle 100, and detects the opening and closing of the door from door data.

[0088] <Timing example (3)> For example, the abnormality detection device 1 may start operating when the owner of vehicle 100 leaves the vicinity of vehicle 100, and may repeat the operation shown in the flowchart of Figure 7 until the owner of vehicle 100 approaches (returns to) the vicinity of vehicle 100. The control unit can detect whether or not the owner of vehicle 100 is present in the vicinity of vehicle 100 using various known methods, such as a method using the signal of the vehicle 100's key. The control unit may, for example, use the three-dimensional spatial distribution acquired by the data acquisition unit 11 to detect whether or not the owner of vehicle 100 is present in the vicinity of vehicle 100. The control unit can determine that the owner of vehicle 100 has left vehicle 100 by using information such as whether or not the occupants of vehicle 100 are present in the vicinity of vehicle 100 immediately after disembarking, and the disappearance of biological responses after disembarking due to leaving vehicle 100.

[0089] <Timing example (4)> For example, the abnormality detection device 1 may start operating as a trigger when the vehicle 100 enters a driving state or when an occupant enters the vehicle 100, and may repeat the operation shown in the flowchart of Figure 7 until the vehicle 100 enters a driving state again after the doors of the vehicle 100 are opened and closed, or until an occupant enters the vehicle 100 again. The control unit can, for example, detect when the vehicle 100 enters a driving state from a vehicle speed sensor. The control unit can also, for example, detect when an occupant enters the vehicle 100 from a seat sensor (not shown) installed in the vehicle 100.

[0090] For example, the anomaly detection device 1 may combine the timings described in the above example for the timing of starting or ending operations as shown in the flowchart of Figure 7. For example, the abnormality detection device 1 may combine <Timing Example (1)> and <Timing Example (2)> to start operating when vehicle 100 stops and the doors of vehicle 100 are opened or closed, and then repeat the operation as shown in the flowchart of Figure 7 until the door lock is released.

[0091] Furthermore, the examples described above are merely illustrations, and the anomaly detection device 1 may start or end operations as shown in the flowchart of Figure 7 at times other than those described above. For example, the anomaly detection device 1 may set the timing for starting or ending operations as shown in the flowchart of Figure 7 in accordance with the laws or assessments of the area in which the vehicle 100 is used.

[0092] When the anomaly detection device 1 starts operating at the timing described in the example above, the anomaly detection unit 13 in the anomaly detection device 1 selectively switches between abandoned object detection mode and intrusion detection mode until the anomaly detection device 1 finishes operating.

[0093] For example, the abnormality detection device 1 starts operating when the doors of the vehicle 100 are locked (see <Timing Example (1)>). The selection unit 131 selects the abandoned vehicle detection mode until the switching time has elapsed, and the abandoned vehicle detection unit 132 performs detection of whether an abandoned vehicle is present inside the vehicle. If no abandoned vehicle is detected after the switching time has elapsed, the selection unit 131 switches from the abandoned vehicle detection mode to the intrusion detection mode. The abandoned vehicle detection unit 132 finishes detecting whether an abandoned vehicle is present inside the vehicle, and the intrusion detection unit 133 performs detection of whether an intrusion has occurred inside the vehicle (see Selection Example (1) above). Since the switching time has elapsed until the doors of vehicle 100 are released, the selection unit 131 continues to select the intrusion detection mode. When the doors of vehicle 100 are released, the abnormality detection device 1 terminates its operation. That is, both the process of detecting whether an object is left behind inside the vehicle and the process of detecting whether an intruder has entered the vehicle terminate.

[0094] Furthermore, for example, the abnormality detection device 1 starts operating when the vehicle 100 enters a driving state (see <Timing Example (4)>). Here, the selection unit 131 may instruct the abandonment detection unit 132 to detect whether or not an infant to be abandoned is present inside the vehicle. If the abandonment detection unit 132 detects that there is no infant inside the vehicle, the selection unit 131 may not select the abandonment detection mode thereafter, and may select the intrusion detection mode at the timing of the selection switch (for example, after the switching time has elapsed).

[0095] The details of the operation example of the anomaly detection device 1 shown in the flowchart of Figure 7 will be explained below.

[0096] The data processing unit 12 performs preprocessing on the sensor data acquired from the sensor 2, which is common to the detection of whether an object is left behind in the vehicle interior and whether an intrusion into the vehicle interior is performed by the anomaly detection device 1, and generates detection data, in this case a three-dimensional spatial distribution (step ST1).

[0097] The data acquisition unit 11 acquires the detection data, in this case a three-dimensional spatial distribution, generated by the data processing unit 12 in step ST1 (step ST2). The data acquisition unit 11 outputs the acquired detection data, in this case a three-dimensional spatial distribution, to the anomaly detection unit 13.

[0098] The selection unit 131 of the abnormality detection unit 13 selects whether to perform abandoned vehicle detection or intrusion detection into the vehicle interior (step ST3). In other words, the selection unit 131 selects whether to enter abandoned vehicle detection mode or intrusion detection mode. If the selection unit 131 selects the abandoned object detection mode, it outputs an abandoned object detection start command to the abandoned object detection unit 132. If the selection unit 131 selects the intrusion detection mode, it outputs an intrusion detection start command to the intrusion detection unit 133.

[0099] If the selection unit 131 selects to perform detection of an unattended object inside the vehicle in step ST3, the unattended object detection unit 132 of the anomaly detection unit 13 detects whether an object is unattended inside the vehicle based on the detection data acquired by the data acquisition unit 11 in step ST2, in this case, the three-dimensional spatial distribution. If the selection unit 131 selects to perform detection of intrusion into the vehicle in step ST3, the intrusion detection unit 133 of the anomaly detection unit 13 detects whether an intrusion into the vehicle has occurred based on the detection data acquired by the data acquisition unit 11 in step ST2, in this case, the three-dimensional spatial distribution (step ST4). When the abandoned object detection unit 132 is activated, it outputs the abandoned object detection result to the detection result output unit 14. When the intrusion detection unit 133 is activated, it outputs the intrusion detection result to the detection result output unit 14.

[0100] The detection result output unit 14 outputs to the output device 3 (step ST5) output control information based on the detection result of whether or not an object is left behind in the vehicle interior by the abandoned object detection unit 132 in step ST4, or output control information based on the detection result of whether or not an intrusion into the vehicle interior is detected by the intrusion detection unit 133. Output device 3 performs control according to the output control information.

[0101] The operation of the abnormality detection device 1 shown in the flowchart of Figure 7 may be repeatedly executed at the timing described above until the timing of operation termination, or it may not be limited to this. If the abnormality detection device 1 detects an abnormality (i.e., if it detects that an object has been left unattended in the vehicle or that an intrusion into the vehicle has occurred, and output control information is output to the output device 3), the processing of the abnormality detection device 1 may be terminated even if it is not the timing of operation termination. The anomaly detection device 1 can continue processing repeatedly even after detecting an anomaly, thereby enabling it to control the output device 3 with step-by-step alarms and other actions.

[0102] In this way, the anomaly detection device 1 acquires detection data regarding moving objects in the vehicle interior, which is generated based on the sensor data acquired when the sensor 2 detects an object in the vehicle interior, and selects whether to perform abandoned object detection in the vehicle interior or intrusion detection into the vehicle interior. If the abnormality detection device 1 selects to perform detection of an unattended vehicle inside the vehicle, it will detect whether an unattended vehicle is inside the vehicle based on the acquired detection data. If the device selects to perform detection of intrusion into the vehicle, it will detect whether an intrusion into the vehicle is occurring based on the acquired detection data.

[0103] As described above, when detecting an abandoned child inside a vehicle, the anomaly detection device 1 must detect not only the presence or absence of moving objects inside the vehicle, but also whether the moving object inside the vehicle is an infant, which is the target of the alarm, so as not to mistakenly detect the presence of adults other than infants as an abandoned child. If the anomaly detection device 1 does not determine whether the abandoned occupant is an infant that requires an alarm, the anomaly detection device 1 may, for example, mistakenly detect the presence of an adult resting inside the vehicle as an abandoned child. As a result, the anomaly detection device 1 may cause the output device 3 to issue unnecessary alarms, leading to over-alarms. On the other hand, when detecting whether or not there is an intrusion into the vehicle interior, the abnormality detection device 1 only needs to be able to detect the presence or absence of a moving object inside the vehicle interior or around the vehicle 100, and it is not necessary for it to detect whether the moving object is an adult or an infant. In other words, the process of detecting an abandoned object is more complex than the process of detecting an intrusion. Furthermore, because detecting an abandoned object may involve human life, a higher level of accuracy is required compared to intrusion detection in terms of detection performance. For this reason, the processing load for detecting an abandoned object inside a vehicle tends to be higher than that for detecting an intrusion inside a vehicle. As a result, the power consumption required to execute the process for detecting an abandoned object inside a vehicle tends to be higher than that for detecting an intrusion inside a vehicle.

[0104] In contrast, the anomaly detection device 1 selectively switches between detecting whether an object has been left unattended inside the vehicle or detecting whether an intruder has entered the vehicle. This allows for simultaneous detection of intrusion into the target area and detection of whether an infant or other person has been left unattended in the target area, while suppressing the execution of unnecessary processing. As a result, the anomaly detection device 1 can achieve lower power consumption compared to the conventional technology described above, where both detection of an object being left unattended inside the vehicle and detection of intrusion into the vehicle are performed continuously.

[0105] Furthermore, if, for example, as with the conventional technology described above, both abandoned vehicle detection and intrusion detection functions are implemented simultaneously based solely on the detection of moving objects considered to be living beings inside the vehicle, even if an alarm is issued, the user may not be able to determine whether the alarm is due to an abandoned vehicle or an intrusion. Thus, a problem arises in terms of usability, such as the user not knowing the cause of any notification they receive. In response to this, the anomaly detection device 1 can selectively switch between detecting an unattended vehicle inside the vehicle and detecting intrusion into the vehicle. If it detects an unattended vehicle or intrusion into the vehicle, it can cause the output device 3 to operate in a way that makes this clear. Therefore, the anomaly detection device 1 can enable the user to determine whether any notification is about an unattended vehicle inside the vehicle or an intrusion into the vehicle.

[0106] As described above, detecting whether an object has been left behind is a more complex process and requires higher accuracy than detecting whether an object has been intruded. For sensor 2, detecting whether an object has been intruded does not require the same level of detailed sensing as detecting whether an object has been left behind. Therefore, in the above embodiment 1, the selection unit 131 may control the operation of the sensor 2 according to the selection of whether to perform abandoned vehicle detection in the vehicle interior or intrusion detection into the vehicle interior.

[0107] For example, the selection unit 131 may change the number of transmitting antennas or the transmitting waveform for the sensor 2 depending on whether it is in the abandoned object detection mode or the intrusion detection mode. When the abandoned person detection unit 132 detects whether or not an abandoned person has been left behind in the vehicle, as described above, it is necessary to detect whether the moving object considered to be an occupant is an adult or an infant, based on the occupant spatial distribution included in the three-dimensional spatial distribution of the vehicle interior. For the abandoned child detection unit 132 to accurately detect the difference in body size between an adult and an infant, the difference in distance and angle from the sensor 2 (specifically the radio wave sensor) to the head of the adult and the infant is important, and therefore the sensor 2 requires high distance resolution and angular resolution. On the other hand, when the intrusion detection unit 133 detects whether or not there is an intrusion into the vehicle interior, the sensor 2 does not need to have the same resolution as when the abandoned object detection unit 132 detects whether or not something has been left behind inside the vehicle interior. It is sufficient for the sensor 2 to be able to roughly detect whether or not a biological response is inside or outside the vehicle interior. Therefore, for example, the selection unit 131 changes the number of transmitting antennas or the transmitting waveform of the sensor 2 depending on whether it is in abandoned object detection mode or intrusion detection mode.

[0108] Here, Figures 8A, 8B, and 8C are diagrams illustrating an example of the control content when the selection unit 131 is capable of controlling the operation of the sensor 2 in Embodiment 1. Figures 8A, 8B, and 8C illustrate an example of the control content when the selection unit 131 is capable of controlling the operation of the sensor 2 in Embodiment 1.

[0109] For example, if the selection unit 131 selects the abandoned object detection mode, it controls the sensor 2 to use two transmitting antennas Tx1 and Tx2 and transmit radio waves using frequency bandwidths Freq.1 to Freq.2 (see Figure 8A). On the other hand, if the selection unit 131 selects the intrusion detection mode, it controls the sensor 2 to reduce the number of transmitting antennas (see Figure 8B). As a result, in intrusion detection mode, the radio wave transmission time is shortened, and antenna operation control processing for the reduced number of transmitting antennas is unnecessary, enabling the anomaly detection device 1 to reduce the power consumption of sensor 2.

[0110] Alternatively, for example, the selection unit 131 may control the sensor 2 to limit the frequency bandwidth between Freq.1 and Freq.3 (see Figure 8C). As a result, the radio wave transmission time is shortened, enabling the anomaly detection device 1 to reduce the power consumption of the sensor 2.

[0111] The selection unit 131 may also be combined with the control of changing the transmission waveform to the sensor 2 as described above.

[0112] The selection unit 131 may change the anomaly detection cycle depending on the selection of, for example, the abandoned object detection mode or the intrusion detection mode. For example, in the above embodiment 1, the length of the period (first period) in which the abandoned vehicle detection unit 132 detects whether or not an object is left behind in the vehicle interior and the length of the period (second period) in which the intrusion detection unit 133 detects whether or not an object has entered the vehicle interior were assumed to be the same length. However, the selection unit 131 may make the lengths of the first period and the second period different. Furthermore, for example, the selection unit 131 may change the anomaly detection cycle by differentiating the cycle at which the data processing unit 12 acquires sensor data from the sensor 2, depending on whether the abandoned object detection mode or the intrusion detection mode is selected. Note that the arrow from the selection unit 131 to the data processing unit 12 is omitted in Figure 1.

[0113] Figures 9A, 9B, and 9C illustrate the concept of the selection unit 131 changing the period of anomaly detection in Embodiment 1. Figure 9B shows an example of a three-dimensional spatial distribution generated based on sensor data detected by sensor 2, which has a small number of antennas, for objects present inside the vehicle. Figure 9A shows an example of a three-dimensional spatial distribution generated based on sensor data detected by sensor 2, which has more antennas than sensor 2 in Figure 9B, for objects present inside the vehicle. Figure 9C shows a three-dimensional spatial distribution obtained by superimposing the distribution of moving objects in the three-dimensional spatial distribution shown in Figure 9B. Figures 9A, 9B, and 9C are all side views of the three-dimensional spatial distribution.

[0114] For example, suppose sensor 2 is a sensor with a small number of antennas. In this case, as shown in Figure 9B, the number of biological responses that can be detected in a single sensing is less than when using sensor 2 with a large number of antennas as shown in Figure 9A. Therefore, it is difficult for the anomaly detection device 1 to obtain a three-dimensional spatial distribution that can detect the physique of an occupant left behind in the vehicle with a single sensing by sensor 2. For example, as shown in Figure 9C, the sensor 2 continuously acquires sensor data at short intervals, and the anomaly detection device 1 generates a three-dimensional spatial distribution by superimposing the biological responses obtained in each interval, thereby clearly identifying the silhouette of the occupant and enabling detection of whether or not an occupant has been left behind in the vehicle. Therefore, when the selection unit 131 selects the abandoned occupant detection mode, it instructs the data processing unit 12 to shorten the interval for acquiring sensor data.

[0115] On the other hand, in intrusion detection mode, it is not necessary to detect the occupant's physique; it is sufficient to know whether or not there is any biological activity around vehicle 100 or inside the vehicle. Therefore, the selection unit 131 may, for example, lengthen the period for acquiring sensor data in the intrusion detection mode compared to the abandoned device detection mode.

[0116] Regarding the change in the anomaly detection cycle, as described above, the selection unit 131 is not limited to changing the length of the sensor data acquisition cycle by the data processing unit 12. For example, the acquisition cycle of sensor data by the data processing unit 12 may not be changed, but the length of the first cycle in which the abandoned vehicle detection unit 132 detects whether or not an abandoned vehicle is present in the vehicle interior and the length of the second cycle in which the intrusion detection unit 133 detects whether or not an intrusion into the vehicle interior is detected may be changed. This allows the anomaly detection device 1 to perform the detection of whether or not an abandoned vehicle is present in the vehicle interior by the abandoned vehicle detection unit 132 and the detection of whether or not an intrusion into the vehicle interior by the intrusion detection unit 133 at the necessary cycles, thereby suppressing the execution of more unnecessary processing. As a result, the anomaly detection device 1 can achieve lower power consumption. However, the selection unit 131 can change the length of the sensor data acquisition cycle by the data processing unit 12, which in turn changes, for example, the cycle of the sensor data acquisition process in sensor 2 or the cycle of the three-dimensional spatial distribution generation. This results in a greater power consumption reduction effect when the detection cycle is lengthened.

[0117] Furthermore, in the above embodiment 1, the functions of the data processing unit 12 may also be provided by the sensor 2. In this case, the data acquisition unit 11 acquires detection data, in this case a three-dimensional spatial distribution, from the sensor 2. The anomaly detection device 1 is not required to include a data processing unit 12. Furthermore, regarding the operation of the anomaly detection device 1 as explained using the flowchart in Figure 7, the anomaly detection device 1 can omit the processing of step ST1.

[0118] Furthermore, in the above embodiment 1, the abandoned vehicle detection unit 132 and the intrusion detection unit 133 each detect whether an abandoned vehicle is present in the vehicle interior or whether an intrusion has occurred in the vehicle interior, based on common detection data obtained from a common sensor 2, more specifically a radio wave sensor, and more specifically a three-dimensional spatial distribution. However, this is merely one example. For example, the abandoned object detection unit 132 may use the same three-dimensional spatial distribution of detection data used by the intrusion detection unit 133 to detect whether or not an intrusion has occurred into the vehicle interior, as well as detection data generated based on sensor data acquired by other types of sensors 2, to detect whether or not an object has been left behind inside the vehicle. For example, the abandoned vehicle detection unit 132 acquires, in addition to the three-dimensional spatial distribution, an image (hereinafter referred to as the "post-motion detection image") generated from the camera based on the image captured by the camera of the vehicle interior, which contains information about moving objects inside the vehicle, as detection data. The unit then combines the three-dimensional spatial distribution and the post-motion detection image to detect whether or not an abandoned vehicle is inside the vehicle. The intrusion detection unit 133 detects whether or not an intruder has entered the vehicle interior using only a three-dimensional spatial distribution. If the intrusion detection mode is selected by the selection unit 131, the camera may be instructed to stop operating. As a result, the anomaly detection device 1 can detect whether or not an object has been left behind inside the vehicle with high accuracy, and can also detect whether or not an object has entered the vehicle without acquiring or processing unnecessary data, thereby reducing power consumption.

[0119] In the example described above, the abandoned vehicle detection unit 132 uses the same three-dimensional spatial distribution of detection data used by the intrusion detection unit 133 to detect whether or not an intrusion has occurred into the vehicle interior, as well as detection data generated based on sensor data acquired by other types of sensors 2, to detect whether or not an abandoned vehicle has been left inside the vehicle. However, this is only one example. For example, the intrusion detection unit 133 may use the same three-dimensional spatial distribution of detection data used by the abandoned vehicle detection unit 132 to detect whether an object has been left behind inside the vehicle, as well as detection data generated based on sensor data acquired by other types of sensors 2, to detect whether an object has been left behind inside the vehicle. For example, the intrusion detection unit 133 may, in addition to the three-dimensional spatial distribution, acquire images captured after motion detection from the camera as detection data, and combine the three-dimensional spatial distribution and the images captured after motion detection to detect whether or not there is an intrusion into the vehicle interior. The abandoned object detection unit 132 detects whether an object is left behind inside the vehicle using only a three-dimensional spatial distribution. The selection unit 131 may also initiate operation for the camera when the intrusion detection mode is selected. As a result, the anomaly detection device 1 can more accurately confirm the external reaction detected by the radio wave sensor from the motion detection image when detecting whether or not there is an intrusion into the vehicle interior. For example, even if a tree near vehicle 100 shakes and triggers a reaction in the radio wave sensor, the anomaly detection device 1 can confirm from the motion detection image that the reaction was not caused by an intruder. As a result, the anomaly detection device 1 can perform detection of whether or not there is an intrusion into the vehicle interior with high accuracy, suppress false detections of intrusions, and detect whether or not something has been left behind inside the vehicle interior by omitting unnecessary data acquisition or processing, thereby reducing power consumption.

[0120] Furthermore, in the above embodiment 1, the abandoned object detection unit 132 and the intrusion detection unit 133 may each use detection data generated based on sensor data acquired by separate, different types of sensors 2 to detect whether an object is left behind inside the vehicle or whether an intrusion has occurred inside the vehicle. In this case, the abandoned vehicle detection unit 132 and the intrusion detection unit 133 will no longer use common detection data. Therefore, the generation of detection data will be performed individually by the abandoned vehicle detection unit 132 and the intrusion detection unit 133 when they detect whether an abandoned vehicle is present inside the vehicle or when they detect whether an intrusion has occurred inside the vehicle. The abnormality detection device 1 can be configured without a data processing unit 12, and in the operation of the abnormality detection device 1 described using the flowchart shown in Figure 7, the processing of step ST1 can be omitted. Furthermore, in this case, regarding the operation of the anomaly detection device 1 as shown in the flowchart of Figure 7, the anomaly detection device 1 may perform the process of step ST3 before the process of step ST2. As a result, in the anomaly detection device 1, the data acquisition unit 11 only needs to acquire the detection data necessary for the mode selected by the selection unit 131 (abandonment detection mode or intrusion detection mode), and the acquisition of unnecessary detection data can be omitted.

[0121] However, the overall system configuration is simpler if the abandoned vehicle detection unit 132 and the intrusion detection unit 133 each detect whether an abandoned vehicle is left in the vehicle or whether an intrusion has occurred into the vehicle, based on detection data acquired by a common sensor 2. Therefore, it is desirable that the abandoned vehicle detection unit 132 and the intrusion detection unit 133 use detection data generated from sensor data acquired by the same sensor 2 whenever possible.

[0122] For example, as described in Embodiment 1 above, when a radio wave sensor is used as sensor 2, the radio wave sensor can penetrate fabric decorations such as seats or blankets other than metal parts, making it possible to observe the situation inside the vehicle. In addition, since radio waves from the radio wave sensor can also penetrate to the outside of the vehicle through window frames, etc., the radio wave sensor can also observe the situation around the vehicle 100. Therefore, the abnormality detection device 1 can perform both the function of detecting whether something has been left behind inside the vehicle and the function of detecting whether someone has entered the vehicle, using detection data generated based on sensor data acquired by a common radio wave sensor.

[0123] Alternatively, for example, the common sensor 2 can be a camera, and the anomaly detection device 1 can perform both the function of detecting whether something is left behind inside the vehicle and detecting whether someone has entered the vehicle, using detection data (i.e., images captured after motion detection) generated based on the sensor data (i.e., images captured) acquired by the common camera. The camera is installed inside the vehicle so as to be able to capture the area where occupants may be present. The camera can capture images inside the vehicle as well as the area around the vehicle 100 through windows, etc. For example, if the common sensor 2 is a camera, the detailed configuration example of the data processing unit 12 does not need to be the configuration example shown in Figure 2. The data processing unit 12 only needs to be configured to acquire captured images from the camera, detect moving objects in the captured images using known image recognition technology, and generate captured images after motion detection.

[0124] Furthermore, in the above embodiment 1, the sensor 2 used as the source of sensor data remained unchanged from the time the anomaly detection device 1 started operating until it stopped operating. However, this is just one example, and the anomaly detection device 1 may be able to add or change sensors 2, which are the source of sensor data, between the start and end of its operation. For example, in the anomaly detection device 1, when the intrusion detection unit 133 detects an intrusion into the vehicle interior based on detection data acquired by the radio wave sensor, i.e., based on the three-dimensional spatial distribution, it treats this as a provisional detection and switches the sensor 2 that acquires the detection data from the radio wave sensor to the camera. In other words, the intrusion detection unit 133 confirms whether it is appropriate to consider the detection of an intrusion into the vehicle interior as valid based on the post-motion detection image captured by the camera. If the intrusion detection unit 133 detects the intrusion of a moving object into the vehicle interior based on the post-motion detection image, it confirms that an intrusion into the vehicle interior has been detected and outputs an intrusion detection result indicating that an intrusion into the vehicle interior has occurred to the detection result output unit 14. For example, when the intrusion detection unit 133 detects an intrusion into the vehicle interior based on the three-dimensional spatial distribution, it notifies the control unit of the anomaly detection device 1 of this fact. The control unit activates the camera and instructs the data acquisition unit 11 to acquire the post-motion detection image. When the data acquisition unit 11 acquires the post-motion detection image, it outputs it to the intrusion detection unit 133 as detection data. The intrusion detection unit 133 performs the above verification based on the post-motion detection image acquired from the data acquisition unit 11. Furthermore, for example, in the abnormality detection device 1, if the intrusion detection unit 133 detects intrusion into the vehicle interior based on detection data acquired by the radio wave sensor, i.e., based on the three-dimensional spatial distribution, it notifies the control unit, which then activates the camera in addition to the radio wave sensor, and the notification content generation unit 142 acquires an image of the vehicle interior captured by the camera and includes the captured image as supplementary information in the output control information. Thus, the anomaly detection device 1 may be able to add or change sensors 2, which are the source of sensor data, between the start and end of its operation. This allows the anomaly detection device 1 to further improve the accuracy of detecting whether or not there is an intrusion into the vehicle interior, or whether or not something has been left behind inside the vehicle interior. In addition, the anomaly detection device 1 can provide information about whether or not there is an intrusion into the vehicle interior, or whether or not something has been left behind inside the vehicle interior, in a more easily understandable format.

[0125] Furthermore, in the explanation above that the period of anomaly detection may be changed depending on the selection of the abandoned object detection mode or the intrusion detection mode, the selection unit 131 gave an example in which the period for acquiring sensor data is made longer in the intrusion detection mode compared to the abandoned object detection mode. For example, if the common sensor 2 is a camera, the selection unit 131 may make the period for acquiring sensor data longer in the abandoned object detection mode compared to the intrusion detection mode. For example, when the anomaly detection device 1 performs abandoned vehicle detection, it can detect whether an abandoned vehicle is present inside the vehicle from the image captured after motion detection, which is based on an image of the vehicle interior captured at least once. Therefore, in the anomaly detection device 1, the selection unit 131 can extend the camera's imaging cycle or the first cycle without any problems in abandoned vehicle detection mode. On the other hand, for example, when the anomaly detection device 1 performs intrusion detection, the camera's imaging cycle or the second cycle should be shortened so as not to miss the quick movements of an intruder, such as the theft of luggage through the window of the vehicle 100. Thus, when the selection unit 131 changes the period of abnormality detection according to the selection of the abandoned object detection mode or the intrusion detection mode, the selection unit 131 only needs to decide whether to lengthen or shorten the period for the abandoned object detection mode or the intrusion detection mode, depending on the type of sensor 2.

[0126] Furthermore, in the above embodiment 1, the selection unit 131 was configured to select either the abandoned vehicle detection mode or the intrusion detection mode. However, the selection unit 131 is not limited to this configuration and may be configured to allow simultaneous selection of the abandoned vehicle detection mode and the intrusion detection mode. In other words, the selection unit 131 may be configured to allow simultaneous selection of the execution of abandoned vehicle detection within the vehicle interior and the execution of intrusion detection into the vehicle interior. The selection unit 131 can, for example, allocate the processing capacity of the anomaly detection unit 13 to processing for detecting whether an object has been left behind in the vehicle interior and processing for detecting whether an intruder has entered the vehicle interior. This allows the anomaly detection device 1 to perform both detection in parallel, rather than performing only one of these two actions. However, this will result in performance or detection limitations compared to processing each action individually. For example, when the selection unit 131 switches from the abandoned vehicle detection mode to the intrusion detection mode, it can perform detection of whether an abandoned vehicle is present inside the vehicle and detection of whether an intrusion into the vehicle is present in parallel before and after the mode switch, thereby enabling a stepwise switch between the abandoned vehicle detection mode and the intrusion detection mode. Furthermore, the anomaly detection device 1 can handle cases where the detection time and other conditions defined by regulations or assessments for detecting whether an abandoned vehicle is present inside the vehicle or whether an intrusion into the vehicle is present overlap.

[0127] Furthermore, in the above embodiment 1, the abnormality detection device 1 was described as an in-vehicle device mounted on the vehicle 100, but this is merely one example. For example, some or all of the data acquisition unit 11, data processing unit 12, anomaly detection unit 13, or detection result output unit 14 of the anomaly detection device 1 may be provided on a server (not shown), and the in-vehicle device and the server may constitute an anomaly detection system.

[0128] Furthermore, in the above embodiment 1, the target area was the interior of a typical passenger car, but this is merely one example. The target area may be the interior of a commercial vehicle such as a bus. Furthermore, the target area is not limited to the interior of a vehicle, but may also be the interior of a moving object other than a vehicle, such as the interior of an aircraft or a train. Furthermore, the target area is not limited to the interior of a moving object, but may also be the interior of a room with an entrance that can be opened and closed for entry and exit to the target area.

[0129] Figures 10A and 10B show an example of the hardware configuration of the anomaly detection device 1 according to Embodiment 1. In Embodiment 1, the functions of the data acquisition unit 11, the data processing unit 12, the anomaly detection unit 13, the detection result output unit 14, and the control unit (not shown) are realized by the processing circuit 1001. That is, the anomaly detection device 1 includes a processing circuit 1001 for controlling the detection of whether or not an object has been left unattended inside the vehicle or whether or not an object has entered the vehicle. The processing circuit 1001 may be dedicated hardware as shown in Figure 10A, or it may be a processor 1004 that executes a program stored in memory as shown in Figure 10B.

[0130] If the processing circuit 1001 is dedicated hardware, it may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof.

[0131] When the processing circuit is a processor 1004, the functions of the data acquisition unit 11, the data processing unit 12, the anomaly detection unit 13, the detection result output unit 14, and the control unit (not shown) are realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in memory 1005. The processor 1004 executes the functions of the data acquisition unit 11, the data processing unit 12, the anomaly detection unit 13, the detection result output unit 14, and the control unit (not shown) by reading and executing the program stored in memory 1005. In other words, the anomaly detection device 1 includes memory 1005 for storing a program that, when executed by the processor 1004, will result in the execution of the processes in steps ST1 to ST5 of Figure 7 described above. It can also be said that the program stored in memory 1005 causes the computer to execute the procedures or methods of the processes of the data acquisition unit 11, the data processing unit 12, the anomaly detection unit 13, the detection result output unit 14, and the control unit (not shown). Here, memory 1005 refers to non-volatile or volatile semiconductor memory such as RAM, ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), and EEPROM (Electrically Erasable Programmable Read-Only Memory), as well as magnetic disks, flexible disks, optical disks, compact disks, minidiscs, and DVDs (Digital Versatile Discs).

[0132] Furthermore, the functions of the data acquisition unit 11, the data processing unit 12, the anomaly detection unit 13, the detection result output unit 14, and the control unit (not shown) may be partially implemented by dedicated hardware and partially by software or firmware. For example, the functions of the data acquisition unit 11 and the data processing unit 12 can be implemented by a processing circuit 1001 as dedicated hardware, while the functions of the anomaly detection unit 13, the detection result output unit 14, and the control unit (not shown) can be implemented by a processor 1004 reading and executing a program stored in memory 1005. The detection result storage unit 141 and the storage unit (not shown) are composed of, for example, memory. Furthermore, the anomaly detection device 1 includes a sensor 2 or an output device 3, and an input interface device 1002 and an output interface device 1003 that perform wired or wireless communication.

[0133] As described above, according to Embodiment 1, the anomaly detection device 1 is configured to include a data acquisition unit 11 that acquires detection data relating to moving objects in the target area, which is generated based on sensor data acquired when the sensor 2 detects an object present in the target area; a selection unit 131 that selects whether to perform abandoned object detection in the target area or intrusion detection into the target area; an abandoned object detection unit 132 that detects whether an object is abandoned in the target area based on the detection data acquired by the data acquisition unit 11 when the selection unit 131 selects to perform abandoned object detection in the target area; and an intrusion detection unit 133 that detects whether an intrusion into the target area is occurring based on the detection data acquired by the data acquisition unit 11 when the selection unit 131 selects to perform intrusion detection into the target area. Therefore, the anomaly detection device 1 can simultaneously detect whether or not an intrusion has occurred into the target area and whether or not an infant or other child has been left unattended in the target area, while suppressing the execution of unnecessary processes. As a result, the anomaly detection device 1 can suppress power consumption caused by the execution of unnecessary processes.

[0134] Furthermore, any component of the embodiment can be modified, or any component of the embodiment can be omitted. [Industrial applicability]

[0135] The anomaly detection device described herein can simultaneously detect whether or not an intrusion has occurred into the target area and whether or not an infant or other child has been left unattended in the target area, while suppressing the execution of unnecessary processes. [Explanation of Symbols]

[0136] 1 Anomaly detection device, 11 Data acquisition unit, 12 Data processing unit, 121 Motion object extraction unit, 122 Motion object analysis unit, 123 Three-dimensional spatial distribution generation unit, 13 Anomaly detection unit, 131 Selection unit, 132 Left-behind detection unit, 133 Intrusion detection unit, 14 Detection result output unit, 141 Detection result storage unit, 142 Notification content generation unit, 143 Output control unit, 100 Vehicle, 1001 Processing circuit, 1002 Input interface device, 1003 Output interface device, 1004 Processor, 1005 Memory.

Claims

1. A data acquisition unit that acquires detection data relating to the three-dimensional spatial distribution of moving objects present inside and outside a vehicle's passenger compartment, which is generated based on sensor data acquired by sensors installed inside the passenger compartment of a vehicle detecting objects present inside and outside the passenger compartment, A selection unit that selects whether to perform detection of an object left behind inside the vehicle compartment or detection of intrusion into the vehicle compartment, If the selection unit selects to perform detection of an abandoned vehicle inside the vehicle compartment, the abandoned vehicle detection unit detects whether or not an abandoned vehicle is present inside the vehicle compartment based on the detection data acquired by the data acquisition unit. If the selection unit selects to perform intrusion detection into the interior of the vehicle compartment, the system includes an intrusion detection unit that detects whether or not there is an intrusion into the interior of the vehicle compartment based on the detection data acquired by the data acquisition unit. The abandoned person detection unit detects whether an abandoned person exists inside the front compartment by determining whether a moving body considered to be a person requiring assistance is present inside the front compartment, based on the information of relative velocity magnitude, spatial distribution shape, breathing information, or spatial distribution magnitude included in the three-dimensional spatial distribution of the detection data. The selection unit further determines, based on the three-dimensional spatial distribution of the interior and exterior of the vehicle compartment, whether or not the owner of the vehicle is present in the vicinity of the vehicle. If the determination results in the vehicle's owner being in the vicinity of the vehicle, the system selects to perform abandoned vehicle detection inside the vehicle compartment; if the determination results in the vehicle's owner being away from the vehicle's vicinity, the system selects to perform intrusion detection inside the vehicle compartment. An anomaly detection device characterized by the following features.

2. The system includes a data processing unit that detects the moving objects present inside and outside the vehicle compartment based on the sensor data and generates the detection data, The data acquisition unit acquires the detection data generated by the data processing unit. An anomaly detection device according to claim 1, characterized in that it is a feature of the present invention.

3. The abandoned vehicle detection unit and the intrusion detection unit each detect whether an abandoned vehicle is inside the vehicle compartment or whether an intrusion has occurred inside the vehicle compartment, based on the detection data obtained by the common sensor. An anomaly detection device according to claim 1, characterized in that it is a feature of the present invention.

4. The selection unit controls the operation of the sensor according to the selection of whether to perform detection of an object being left behind inside the vehicle compartment or detection of intrusion into the vehicle compartment. An anomaly detection device according to claim 1, characterized in that it is a feature of the present invention.

5. The abandoned vehicle detection unit detects whether an abandoned vehicle is present inside the vehicle compartment by using the detection data based on the sensor data acquired by the common sensor, as well as the detection data based on the sensor data acquired by sensors other than the common sensor. The anomaly detection device according to claim 3, characterized in that it is as described above.

6. The selection unit selects to perform detection of an unattended person inside the vehicle compartment until a switching time has elapsed after the door used for entering or exiting the vehicle compartment has been locked. If no unattended person is detected inside the vehicle compartment after the switching time has elapsed, it selects to perform detection of an intrusion into the vehicle compartment. An anomaly detection device according to claim 1, characterized in that it is a feature of the present invention.

7. The selection unit selects to perform detection of an unattended person inside the vehicle compartment when the door used for entering or exiting the vehicle compartment is locked, and when the unattended person detection unit completes the detection of whether or not an unattended person is inside the vehicle compartment based on the selection unit's choice, it selects to perform detection of intrusion into the vehicle compartment. An anomaly detection device according to claim 1, characterized in that it is a feature of the present invention.

8. The selection unit can simultaneously select to perform detection of an unattended vehicle inside the vehicle compartment and to perform detection of intrusion into the vehicle compartment. An anomaly detection device according to claim 1, characterized in that it is a feature of the present invention.

9. When the door used to enter or exit the vehicle compartment is locked, the selection unit repeatedly selects whether to perform either detection of an unattended vehicle inside the vehicle compartment or detection of intrusion into the vehicle compartment until the lock is released. An anomaly detection device according to claim 1, characterized in that it is a feature of the present invention.

10. The abandoned vehicle detection unit detects whether or not an abandoned vehicle is present inside the vehicle compartment during the first cycle. The intrusion detection unit detects whether or not there is an intrusion into the interior of the vehicle compartment in the second cycle. The lengths of the first period and the second period are different. An anomaly detection device according to claim 1, characterized in that it is a feature of the present invention.

11. A detection result output unit outputs output control information based on the detection result of the abandoned object detection unit regarding the presence or absence of an abandoned object inside the vehicle compartment, or output control information based on the detection result of the intrusion detection unit regarding the presence or absence of intrusion into the vehicle compartment. An anomaly detection device according to claim 1, comprising:

12. The output control information is information used to generate an alarm. The anomaly detection device according to claim 11, characterized in that it is a feature of the device described in claim 11.

13. The aforementioned sensor includes a radio wave sensor that acquires reflected waves as sensor data when radio waves emitted toward the interior and exterior of the vehicle compartment are reflected by objects inside and outside the vehicle compartment. An anomaly detection device according to claim 1, characterized in that it is a feature of the present invention.

14. The sensor includes a camera that takes images of the interior of the vehicle cabin. An anomaly detection device according to claim 1, characterized in that it is a feature of the present invention.

15. The output control information is information for controlling the operation of the vehicle. The anomaly detection device according to claim 11, characterized in that it is a feature of the device described in claim 11.

16. A data acquisition unit acquires detection data relating to the three-dimensional spatial distribution of moving objects inside and outside the vehicle's passenger compartment, which is generated based on sensor data acquired by sensors installed inside the vehicle's passenger compartment that detect objects inside and outside the passenger compartment. A selection unit that selects whether to perform detection of an object left behind inside the vehicle compartment or detection of intrusion into the vehicle compartment, If the selection unit selects to perform detection of an abandoned vehicle inside the vehicle compartment, the abandoned vehicle detection unit detects whether or not an abandoned vehicle is present inside the vehicle compartment based on the detection data acquired by the data acquisition unit. If the selection unit selects to perform intrusion detection into the interior of the vehicle compartment, the system includes an intrusion detection unit that detects whether or not there is an intrusion into the interior of the vehicle compartment based on the detection data acquired by the data acquisition unit. The selection unit determines whether the owner of the vehicle is present in the vicinity of the vehicle based on the three-dimensional spatial distribution of the interior and exterior of the vehicle compartment. If the determination results in the vehicle's owner being in the vicinity of the vehicle, the system selects to perform abandoned vehicle detection inside the vehicle compartment; if the determination results in the vehicle's owner being away from the vehicle's vicinity, the system selects to perform intrusion detection inside the vehicle compartment. An anomaly detection device characterized by the following features.

17. A data acquisition unit acquires detection data relating to the three-dimensional spatial distribution of moving objects inside the vehicle's interior, which is generated based on sensor data acquired when a radio wave sensor detects an object inside the vehicle's interior, and detection data relating to images of the interior of the vehicle's interior captured by a camera. A selection unit that selects whether to perform detection of an object left behind inside the vehicle compartment or detection of intrusion into the vehicle compartment, If the selection unit selects to perform detection of an abandoned vehicle inside the vehicle compartment, the abandoned vehicle detection unit detects whether or not an abandoned vehicle is present inside the vehicle compartment based on the detection data acquired by the data acquisition unit. If the selection unit selects to perform intrusion detection into the interior of the vehicle compartment, the system includes an intrusion detection unit that detects whether or not there is an intrusion into the interior of the vehicle compartment based on the detection data acquired by the data acquisition unit. If the intrusion detection unit detects an intrusion into the vehicle compartment based on the three-dimensional spatial distribution, it switches the source of the detection data from the radio wave sensor to the camera and confirms, based on the captured image, that an intrusion of a moving object into the vehicle compartment has been detected. An anomaly detection device characterized by the following features.

18. The data acquisition unit acquires detection data relating to the three-dimensional spatial distribution of moving objects inside and outside the vehicle's passenger compartment, which is generated based on sensor data acquired by sensors installed inside the vehicle's passenger compartment that detect objects inside and outside the passenger compartment. The selection unit selects whether to perform detection of an object left inside the vehicle compartment or detection of intrusion into the vehicle compartment, If the selection unit selects to perform abandoned vehicle detection inside the vehicle compartment, the abandoned vehicle detection unit detects whether an abandoned vehicle is present inside the vehicle compartment based on the detection data acquired by the data acquisition unit. The intrusion detection unit includes the step of detecting whether or not there is an intrusion into the interior of the vehicle compartment based on the detection data acquired by the data acquisition unit, when the selection unit has selected to perform intrusion detection into the interior of the vehicle compartment. The step of detecting whether or not an object is left behind inside the vehicle compartment by the abandoned object detection unit is: Based on the information on the magnitude of relative velocity, the shape of the spatial distribution, the breathing information, or the magnitude of the spatial distribution included in the three-dimensional spatial distribution of the detection data, it is determined whether the moving body considered to be a person requiring assistance is present inside the vehicle compartment. The step of the selection unit selecting whether to perform detection of an unattended vehicle inside the vehicle compartment or detection of intrusion into the vehicle compartment is as follows: The selection unit determines, based on the three-dimensional spatial distribution of the interior and exterior of the vehicle compartment, whether or not the owner of the vehicle is present in the vicinity of the vehicle. The determination includes, if it is determined that the owner of the vehicle is present in the vicinity of the vehicle, selecting to perform abandoned vehicle detection inside the vehicle compartment, and if it is determined that the owner of the vehicle has left the vicinity of the vehicle, selecting to perform intrusion detection inside the vehicle compartment. An anomaly detection method characterized by the following.

19. The data acquisition unit acquires detection data relating to the three-dimensional spatial distribution of moving objects inside and outside the vehicle's passenger compartment, which is generated based on sensor data acquired by sensors installed inside the vehicle's passenger compartment that detect objects inside and outside the passenger compartment. The selection unit selects whether to perform detection of an object left inside the vehicle compartment or detection of intrusion into the vehicle compartment, If the selection unit selects to perform detection of an abandoned vehicle inside the vehicle compartment, the abandoned vehicle detection unit detects whether or not an abandoned vehicle is present inside the vehicle compartment based on the detection data acquired by the data acquisition unit. If the selection unit selects to perform intrusion detection into the vehicle compartment, the intrusion detection unit includes the step of detecting whether or not there is an intrusion into the vehicle compartment based on the detection data acquired by the data acquisition unit. Furthermore, the selection unit determines whether the owner of the vehicle is present in the vicinity of the vehicle based on the three-dimensional spatial distribution of the interior and exterior of the vehicle compartment. The process includes the step of selecting to perform abandoned vehicle detection inside the vehicle compartment if the result of the above determination is determined to be that the owner of the vehicle is present in the vicinity of the vehicle, and selecting to perform intrusion detection inside the vehicle compartment if the result is determined to be that the owner of the vehicle has left the vicinity of the vehicle. Anomaly detection method.

20. The data acquisition unit acquires detection data relating to the three-dimensional spatial distribution of moving objects inside the vehicle's interior, which is generated based on sensor data acquired when a radio wave sensor detects an object inside the vehicle's interior, and detection data relating to images of the interior of the vehicle's interior captured by a camera. The selection unit selects whether to perform detection of an object left inside the vehicle compartment or detection of intrusion into the vehicle compartment, If the selection unit selects to perform detection of an abandoned vehicle inside the vehicle compartment, the abandoned vehicle detection unit detects whether or not an abandoned vehicle is present inside the vehicle compartment based on the detection data acquired by the data acquisition unit. If the selection unit selects to perform intrusion detection into the vehicle compartment, the intrusion detection unit includes the step of detecting whether or not there is an intrusion into the vehicle compartment based on the detection data acquired by the data acquisition unit. The step of the intrusion detection unit detecting whether or not an intrusion has occurred inside the vehicle compartment is as follows: If an intrusion into the vehicle compartment is detected based on the three-dimensional spatial distribution, the source of the detection data is switched from the radio wave sensor to the camera, and it is confirmed that an intrusion of the moving object into the vehicle compartment has been detected based on the captured image. An anomaly detection method characterized by the following.

Images