JP2023003702A - Information recorder and information recording method - Google Patents

Abstract

To reduce storage capacity and power consumption, mainly during monitoring while a vehicle is parked, by recording intended images without recording unintended images when an abnormality occurs in the vehicle.SOLUTION: An information recorder 10 according to an embodiment includes: a control unit 11; an image acquisition unit 12 for acquiring an image of a range including the surroundings of a vehicle; an abnormality determination unit 13 for determining a first abnormality and a second abnormality occurring in the vehicle; a storage control unit 14 for causing a storage unit 17 to store the image; a voice acquisition unit 15 for acquiring voice in a range including the surroundings of the vehicle; a voice analysis unit 16 for analyzing whether the voice is a specific voice; and the storage unit 17. The control unit 11 causes the storage control unit 14 to immediately start storing the image in the storage unit 17 if the result of the determination by the abnormality determination unit 13 is the first abnormality, and causes the storage control unit 14 to start storing the image in the storage unit 17 based on predetermined conditions for the voice analyzed by the voice analysis unit 16 if the result of the determination is the second abnormality.SELECTED DRAWING: Figure 2

Description

The present disclosure relates to an information recording device and an information recording method.

Patent Document 1 describes a drive recorder system that includes a vehicle equipped with a camera and a server that includes a storage unit and is configured to be able to communicate with the vehicle, and that collects information when an accident occurs. .

In the drive recorder system described in Patent Document 1, the vehicle includes an audio detection unit that detects sounds outside the vehicle, and image data obtained from the camera and audio data obtained from the audio detection unit are used. If at least one of them contains information indicating that an accident has occurred, the accident information including image data within a predetermined period including the time when the accident occurred is transmitted to the server. Here, the acquired voice data is analyzed, and if it includes a sudden braking sound or a collision sound, it is determined that information indicating that an accident has occurred is included. The server stores the transmitted accident information in the storage unit.

JP 2019-86895 A

As described above, in the technique described in Patent Document 1, it is determined that an accident has occurred when the sound is analyzed and the characteristics indicate a sudden braking sound or a collision sound, and the image data is stored in the server. there is However, when images are recorded with sound characteristics as a condition, there are many malfunctions such as unintended images being recorded, and there is room for improvement.

The present disclosure has been made in view of the above points. It is an object of the present invention to provide an information recording device and an information recording method capable of suppressing storage capacity and power consumption when monitoring a vehicle while it is parked.

An information recording device according to an embodiment of the present disclosure includes an image acquisition unit that acquires an image captured in a range including the surroundings of a vehicle, a sound acquisition unit that acquires sound in the range including the surroundings of the vehicle, and an audio analysis unit that analyzes whether or not the audio acquired by the audio acquisition unit is a specific audio; an abnormality determination unit that determines a first abnormality and a second abnormality occurring in the vehicle; a storage unit; a storage control unit for controlling to store the image in the storage unit; and when the determination result of the abnormality determination unit indicates the first abnormality, the storage control unit immediately instructs the storage unit to store the image. When the storage of the image is started and the second abnormality is indicated, the storage control unit instructs the storage control unit to store the a control unit for starting image storage.

An information recording device according to another embodiment of the present disclosure includes an image acquisition unit that acquires an image of a range including the surroundings of a vehicle, an audio acquisition unit that acquires audio in the range including the surroundings of the vehicle, an abnormality determination unit that determines a first abnormality and a second abnormality occurring in the vehicle; a storage unit; a storage control unit that performs control to store the image and the sound in the storage unit; and a voice analysis unit for analyzing whether or not the image is stored in the storage unit when the determination result of the abnormality determination unit indicates the first abnormality. Control to start voice analysis by the voice analysis unit for at least one of the voice acquired by the voice acquisition unit and the voice stored in the storage unit when the second abnormality is indicated and

In an information recording method according to an embodiment of the present disclosure, an information recording device having a storage unit acquires an image captured in a range including the surroundings of a vehicle, and acquires sound in the range including the surroundings of the vehicle. analyzing whether the acquired voice is a specific voice, determining whether the vehicle has a first abnormality or a second abnormality, and confirming that the result of the determination is the first abnormality. is indicated, the storage of the image in the storage unit is immediately started, and when the second abnormality is indicated, the storage is performed based on a predetermined condition for the analyzed sound It initiates the storage of the image in the unit.

According to the present disclosure, when an image is recorded when an abnormality occurs in the vehicle, an unintended image is not recorded, and an intended image is recorded. Also, it is possible to provide an information recording apparatus and an information recording method capable of suppressing power consumption.

1 is a schematic diagram showing how a drive recorder is installed in a vehicle; FIG. 1 is a block diagram showing a configuration example of an information recording apparatus according to Embodiment 1; FIG. 3 is a flowchart for explaining an example of an information recording method in the information recording apparatus of FIG. 2; FIG. FIG. 10 is a flowchart for explaining an example of an information recording method in an information recording apparatus according to Embodiment 2;

Hereinafter, specific embodiments to which the present invention is applied will be described in detail with reference to the drawings. However, the present disclosure is not limited to the following embodiments. Also, for clarity of explanation, the following description and drawings are simplified as appropriate.

<Embodiment 1>
An example of mounting a drive recorder as an example of the information recording apparatus according to Embodiment 1 will be described with reference to FIG. FIG. 1 is a schematic diagram showing how a drive recorder is installed in a vehicle.

As shown in FIG. 1, the drive recorder 1 includes a camera unit 2 with a camera. The camera unit 2 is installed above the windshield in the traveling direction of the vehicle 5 so as to capture an image of the surrounding environment ahead. The field of view has a diagonal spread of about 130°, as indicated by a dashed line.

The vehicle 5 can be provided with an acceleration sensor 3 that detects acceleration such as an impact received by the vehicle 5 . The acceleration sensor 3 outputs an acceleration signal, which is a detection result, to the drive recorder 1 . The acceleration sensor 3 may be built in the drive recorder 1 .

Further, the vehicle 5 has distance sensors for detecting distances to objects such as other vehicles, pedestrians, and fixed objects fixed to the road surface at a plurality of locations in the front, or in a plurality of locations such as the front, rear, and sides. 4 can be provided. The distance sensor 4 is, for example, a millimeter wave radar or an ultrasonic sensor, and outputs a distance signal, which is a detection result, to the drive recorder 1 . The distance sensor 4 may be built in the drive recorder 1 . Note that the camera unit 2 may have a compound eye, and the distance sensor 4 may be omitted by providing a configuration for calculating the distance to the object from the compound eye image.

Next, an example of the information recording apparatus according to this embodiment will be described with reference to FIG. FIG. 2 is a block diagram showing a configuration example of an information recording apparatus according to this embodiment.

As shown in FIG. 2, the information recording apparatus 10 according to the present embodiment includes an image acquisition unit 12, an abnormality determination unit 13, a memory control unit 14, a sound acquisition unit 15, a sound analysis unit 16, and a storage unit 17. . Further, the information recording device 10 can be provided with a control section 11 that controls the whole.

The control unit 11 can be implemented by, for example, a CPU (Central Processing Unit), a working memory, and a non-volatile storage device that stores a control program. Note that the control unit 11 may be implemented using a user-programmable integrated circuit such as an FPGA (field-programmable gate array) or a microcomputer.

The image acquisition unit 12 acquires an image of a range including the surroundings of the vehicle 5 . This range can also include the interior of the vehicle 5 . The image acquisition unit 12 can be an interface such as an input circuit that inputs (receives) a signal from a camera provided in the camera unit 2 . Alternatively, the image acquisition section 12 can include the camera unit 2 or a camera provided in the camera unit 2 .

The voice acquisition unit 15 acquires voice in a range including the surroundings of the vehicle 5 . This range can also include the interior of the vehicle 5 . The voice acquisition unit 15 may include a microphone, or may be an interface such as an input circuit for inputting/receiving a signal from a separately provided microphone. The voice acquisition unit 15 can also adopt a configuration that acquires voices from a plurality of microphones, thereby making it easier to capture the characteristics of sounds.

The voice analysis unit 16 analyzes whether the voice acquired by the voice acquisition unit 15 is a specific voice. This speech analysis can be performed using speech recognition technology, for example, the specific speech may be pre-recorded as a sound or sound signature (e.g., sound frequency, etc.) of an injury, mischief, collision, etc., to the vehicle 5. It can be detected by comparison of what is stored. The damage to the vehicle 5 may occur in various situations, such as scratches caused by slight contact between cars, scratches intentionally inflicted with metal pieces by criminals, and glass breakage due to theft. .

Further, for example, the sound analysis unit 16 converts sound information that may damage the vehicle 5 into data, stores it in advance as comparison data that is determined to be a specific sound, and uses the comparison data and the sound acquisition unit 15 to An approximation coefficient can also be calculated by comparing the obtained voice data. Then, the voice analysis unit 16 can compare the approximation coefficient with a pre-stored threshold value, and determine that the approximation coefficient is positive when the coefficient is smaller (that is, determine that the coefficient is abnormal when similar to the comparison data). In addition, the voice analysis unit 16 performs voice recognition processing using a specific sound dictionary (dictionary of voices characteristic of scratches, broken glass, etc.) learned by machine learning, and determines whether or not it is a specific voice. You can also

The abnormality determination unit 13 determines abnormality occurring in the vehicle 5 . Abnormalities determined by the abnormality determination unit 13 include a first abnormality and a second abnormality. The first abnormality can refer to shaking, collision, etc. of the vehicle 5 , and the second abnormality can similarly refer to shaking, collision, etc. of the vehicle 5 .

The first anomaly and the second anomaly can be the same type of determination target data, and can have different threshold values. That is, the abnormality determination unit 13 can determine the first abnormality and the second abnormality, which are two types of abnormality having different levels. Although it is preferable that the degree of abnormality of the first abnormality is greater than that of the second abnormality, it is also possible for the degree of abnormality of the second abnormality to be greater than that of the first abnormality.

For example, the abnormality determination unit 13 receives acceleration data detected by the acceleration sensor 3, which is generated when the vehicle 5 shakes or collides with another vehicle, a person, or a fixed object (such as a building). The first abnormality and the second abnormality can be determined by comparing with . Then, for example, the first abnormality is set to have a higher determination threshold value than the second abnormality (it is not determined as an abnormality unless the shaking is larger). For example, it is preferable that the first abnormality can determine a relatively large shaking or collision of the vehicle 5, and the second abnormality can determine even a slight shaking of the vehicle 5 that occurs to such an extent that it cannot be immediately determined as an abnormality.

Also, although the acceleration sensor 3 is employed here as a sensor for detecting abnormality, other sensors may be used. The sensor that detects an abnormality may be the distance sensor 4. In this case, it is possible to detect that an object such as another vehicle, a pedestrian, or a fixed object approaches within a predetermined distance as an abnormality. In this case, for example, the first abnormality is judged to be other vehicles or pedestrians that have approached the vehicle 5 at a relatively close distance, and the second abnormality is judged to be other vehicles or pedestrians that have approached to such an extent that they cannot be immediately judged to be abnormal. judge. Further, the sensor that detects an abnormality can perform image recognition processing on the image acquired by the image acquisition unit 12 and detect detection of another vehicle, a person, a fixed object, or the like as an abnormality. Moreover, the sensor that detects an abnormality may be, for example, a strain sensor that detects deformation due to collision of an object, or a temperature sensor that detects an abnormal temperature. Of course, a combination of multiple sensors may be employed. Further, although the criteria for judging abnormalities differ depending on the sensor employed, each criterion can be determined based on known techniques. Also, various sensors such as those illustrated may be configured by being incorporated in a drive recorder.

Furthermore, for example, the abnormality determination unit 13 determines whether the sound acquired by the sound acquisition unit 15 or the sound analyzed by the sound analysis unit 16 as being a specific sound is larger than a predetermined first threshold or a second threshold, respectively. It can also be determined to be the first abnormality or the second abnormality. In that case, the criteria for determining that the loudness of the sound around the vehicle is abnormal can also be determined based on known techniques. Note that this determination can be configured so that the abnormality determination unit 13 instructs the sound analysis unit 16 to execute this determination. Description will be made on the premise that the determination unit 13 functions as a volume determination unit.

Alternatively, the first anomaly and the second anomaly can be determined using different types of determination target data. For example, the abnormality determination unit 13 determines that the first abnormality occurs when the acceleration detected by the acceleration sensor 3 is greater than the threshold, and the sound volume obtained by the sound acquisition unit 15 is greater than the threshold. can be determined to be the second abnormality. Although description is omitted, various other combinations of determination target data can be applied.

The storage unit 17 is a portion for storing images, and may be composed of a non-volatile storage device such as an SSD (solid-state drive), or a detachable non-volatile memory and a storage unit for accessing the non-volatile memory. interface, or both. The storage unit 17 can also be controlled by the storage control unit 14 so as to store the sound acquired by the sound acquisition unit 15 at the same time when the image is stored.

The storage control unit 14 performs control to store the image acquired by the image acquisition unit 12 in the storage unit 17 based on the instruction from the control unit 11 . The storage control unit 14 may perform control to store in the storage unit 17 the voice acquired by the voice acquisition unit 15 or the voice analyzed as a specific voice by the voice analysis unit 16 . The storage controller 14 can also be called an image storage controller. Regarding storage, for example, image data acquired by the image acquisition unit 12 and audio data acquired by the audio acquisition unit 15 can be temporarily held in a working memory provided in the control unit 11. . The storage control unit 14 can perform control to write the temporarily held data in the storage unit 17 , thereby storing image and audio data in the storage unit 17 .

For example, when the determination result of the first abnormality indicates that there is an abnormality, the control unit 11 indicates that the determination result of the second abnormality indicates that there is an abnormality, and the acquired sound is a specific sound. If there is, the storage control unit 14 is controlled to start storing the image acquired by the image acquisition unit 12 in the storage unit 17 .

Regardless of the format of the image data stored in the storage control unit 14, for example, the control unit 11 generates image data conforming to a predetermined format from the image data acquired by the image acquisition unit 12. You should keep it like that. Also, the image to be stored may be an image based on the time when the condition for storage control is established (the time when the condition is established). Therefore, a still image at the time when the condition is satisfied, a plurality of still images acquired within a predetermined time range based on the time when the condition is satisfied, a moving image during a predetermined period from the time when the condition is satisfied, or a moving image during a predetermined period including the time when the condition is satisfied and so on. Of course, when the sound is stored at the same time, the sound of the time period corresponding to the image should be stored.

Next, a processing example of the information recording device 10 will be described with reference to FIG. FIG. 3 is a flowchart for explaining an example of an information recording method in the information recording apparatus 10 of FIG.

First, the information recording device 10 acquires an image of a range including the surroundings of the vehicle 5 (step S1), acquires sound in a range including the surroundings of the vehicle 5 (step S2), and obtains a specific sound. Analysis as to whether or not it is voice is executed (step S3). Next, the information recording device 10 determines the first abnormality and the second abnormality occurring in the vehicle 5 (step S4).

However, step S1 and step S2 can be performed as parallel processing, and step S4 can also be performed as parallel processing, except for an example in which sound or image is used for determination in step S4. In step S3, speech analysis is performed on the speech acquired in step S2.

Next, the information recording device 10 causes the storage unit 17 to store the acquired image based on the analysis result and the determination result (step S5), and ends the process. Such processing is repeated in the information recording apparatus 10 . In step S5, if the determination result indicates the first abnormality, the storage of the image in the storage unit 17 is immediately started, and if the result indicates the second abnormality, the analyzed voice storage of the image in the storage unit 17 is started based on a predetermined condition for.

Next, an example of the first abnormality and the second abnormality and an example of the corresponding processing in step S5 will be described.

For example, the abnormality determination unit 13 can determine that there is a second abnormality when the volume of the sound acquired by the sound acquisition unit 15 is equal to or greater than a predetermined value. As the predetermined condition in this example, for example, it is possible to adopt that the analyzed sound is a specific sound. Here, the condition for determining the first abnormality is different from the condition for determining the second abnormality, and can be based on the detection result of the acceleration sensor 3, for example.

Similar results can also be obtained with the following configuration. That is, the abnormality determination unit 13 may determine that the sound is the second abnormality when the sound acquired by the sound acquisition unit 15 and analyzed by the sound analysis unit 16 satisfies the condition that the sound is the specific sound. As the predetermined condition in this example, it is possible to employ, for example, that the loudness of the analyzed specific sound is equal to or greater than a predetermined value.

In any of the two examples described above, when the control unit 11 indicates to the storage control unit 14 that the first abnormality has occurred, the image acquired by the image acquisition unit 12 is immediately stored in the storage unit 17. If the analyzed sound is a specific sound and the volume of the specific sound is greater than or equal to a predetermined value, control is performed to store the image in the storage unit 17 . In these examples, as described above, the result of voice analysis is used as a condition for image storage only in the case of the determination of the second abnormality, which is determined under different conditions from the determination of the first abnormality.

Further, for example, there is a situation where a dent or scratch on the vehicle 5 occurs even if the detection value of the acceleration sensor 3 is small. As an example that can deal with such a situation, it is adopted as the predetermined condition that the analyzed sound is a specific sound, and if the detected value of the acceleration sensor 3 is equal to or greater than the first threshold value, the first 1 abnormality, and if the value is equal to or greater than a second threshold value (a value that is smaller than the first threshold value and cannot be immediately determined to be abnormal), it may be determined to be the second abnormality. With such a configuration, the storage control unit 14 stores the image when the specific sound is detected as long as the second threshold is not exceeded, so the image can be stored even in the situation described above. Of course, by lowering the first threshold for determining the first abnormality, it is possible to store an image even with such a small detection value. is stored, the image recording frequency increases and the storage capacity is compressed. It can be said that the configuration described above is useful in order to reduce the frequency of occurrence of such a problem of frequent malfunctions. Further, although it is difficult to obtain a correlation between the size of the scratch and the detection value of the acceleration sensor 3, by adopting the above-described configuration, it is possible to prevent an event in which an image is not recorded despite a large amount of damage. . It should be noted that this example can be used together with the example relating to identification of the sound source, which will be described below.

Further, the information recording apparatus 10 can further include a sound source specifying unit (not shown) that specifies the position of the sound source of the sound acquired by the sound acquiring unit 15 . This sound source specifying unit can also be provided inside the voice analysis unit 16 . Sound source identification is based on the ratio of reverberant sound contained in the speech, using known techniques such as identifying the position of the sound source far when there is a lot of reverberation and the position of the sound source close when there is little reverberation. Then, the distance between the vehicle 5 and the sound source position can be calculated. For example, the voice acquisition unit 15 adopts a configuration that acquires voices from a plurality of microphones, and determines the sound source (that is, the location of the damage) from the difference in volume and delay amount of each voice collected by each microphone. Direction can be specified. By specifying the direction of the sound source from a plurality of positions of the vehicle 5 using a plurality of microphones, the position at which the straight line from the predetermined position of the vehicle 5 to the specified sound source direction intersects is specified, and the vehicle 5 and the sound source position are specified. can be calculated. The sound source identifying unit can also identify the sound source by estimating the sound source using a model learned by machine learning.

In a configuration example capable of specifying such a sound source, the following processing can be adopted. That is, the abnormality determination unit 13 determines that the sound acquired by the sound acquisition unit 15 has the second abnormality when the distance between the sound source identified by the sound source identification unit and the vehicle 5 is equal to or less than a predetermined value. Here, the condition for determining the first abnormality is different from the condition for determining the second abnormality, and can be based on the detection result of the acceleration sensor 3, for example.

In this case, the memory control unit 14 indicates that the determination result of the abnormality determination unit 13 is the second abnormality, and the voice acquired by the voice acquisition unit 15 and analyzed by the voice analysis unit 16 as the predetermined condition is the specific sound, control is performed to store the image acquired by the image acquisition unit 12 in the storage unit 17 . In this example, as described above, the result of voice analysis is used as a condition for image storage only in the case of the determination of the second abnormality, which is determined under different conditions from the determination of the first abnormality. In a similar way of thinking, the abnormality determination unit 13 can also determine that there is a second abnormality when the distance detected by the distance sensor 4 is equal to or less than a predetermined value.

As described above, in the information recording apparatus 10 according to the present embodiment, not only the analysis result of whether or not the acquired sound is the specific sound, but also other information (for example, volume, sound generation position, acceleration sensor Any one or more of the acceleration detected in step 3 and the distance detected by the distance sensor 4) is also combined to determine an abnormality that serves as a trigger for starting image recording.

Therefore, according to the information recording apparatus 10 according to the present embodiment, when an image is recorded when an abnormality occurs in the vehicle 5, the conditions determined simply by the characteristics of the sound (such as the type of sound and the occupant of the vehicle 5) are used. Compared to processing that only executes image recording when conditions are satisfied (e.g., whether the voice is an unintended voice), the intended image can be recorded without recording an unintended image, and the storage capacity can be reduced. Also, the power consumption of the information recording apparatus 10 can be reduced.

The information recording apparatus 10 can also be configured so that conditions for determining abnormality (determination conditions for the first abnormality and determination conditions for the second abnormality) can be designated by an operation unit (not shown) or the like. As a result, appropriate recording that matches the user's intention can be performed. The conditions that can be specified can include thresholds for determination.

In addition, the information recording device 10 can have a running mode and a parking monitoring mode as its operation modes. can be set to run. This is because the image recording process described above is beneficial during parking. On the other hand, in the running mode, it is possible to record images and sounds all the time, or to perform loop recording in which such recording is performed while erasing it for a certain period of time. A configuration including such a parking monitoring mode makes it possible to record an intended image while suppressing storage capacity and power consumption during monitoring while the vehicle is parked.

In the above configuration example, an example in which one camera unit 2 is basically provided for shooting from the front has been given. A plurality of units can be provided for directional photography or the like. Some or all of the camera units can be arranged at a position separated from the main body of the drive recorder 1, and can be configured to transmit images to the main body by wired or wireless communication. Even when another camera unit is provided, the same processing as described above can be applied.

Also, when a plurality of camera units are provided, the images to be stored can be images captured by all the camera units, for example. In other words, in this case, the image acquisition unit 12 can be configured to acquire images from a plurality of cameras and transfer them to the storage control unit 14 as storage targets. Also, in this case, a plurality of storage devices or storage media may be provided as the storage unit 17, and the storage control unit 14 may store images from each camera in separate storage devices or storage media.

Further, when a plurality of camera units are provided, the storage control section 14 can also select and store images to be stored. For example, by adopting a configuration in which the memory control unit 14 also acquires the direction of the acceleration detected by the acceleration sensor 3, the direction in which the abnormality occurred (for example, the direction in which the object collided with the vehicle 5) ) can be determined, and an image acquired by one or a plurality of camera units arranged corresponding to the orientation can be selected as an object to be stored. As a result, the object causing the abnormality can be recorded more accurately, and the storage capacity can be reduced.

In addition, the storage control unit 14 can cause the storage unit 17 to store at least one of the time information and the position information in association with each other when performing image storage control. Time information can be acquired by providing a timer (not shown) or the like in the information recording apparatus 10 . Also, the position information can be obtained by providing the information recording apparatus 10 with a position information obtaining unit (not shown). The position information acquisition unit can be configured to acquire position information by, for example, a GNSS (Global Navigation Satellite System) or the like. GNSS is a general term for satellite positioning systems such as GPS (Global Positioning System), GLONASS, Galileo, and Quasi-Zenith Satellite (QZSS).

The information recording apparatus 10 may also include a display device (not shown) for displaying image data obtained by the image acquisition unit 12, or may be connected to such a display device. can. In the former case, the display device can be, for example, a dedicated display panel provided integrally with the drive recorder 1, and in the latter case, the display device can be, for example, a display panel of a car navigation system.

<Embodiment 2>
The information recording apparatus according to Embodiment 2 differs from the information recording apparatus according to Embodiment 1 in the procedure of processing, and the other points are the same as those of Embodiment 1 including its application example. The configuration of the information recording apparatus according to the present embodiment will be described with reference to FIGS. 1 and 2, and the processing example thereof will be described with reference to FIG. 4, focusing on differences from the first embodiment. FIG. 4 is a flowchart for explaining an example of an information recording method in the information recording apparatus according to this embodiment.

As in Embodiment 1, the information recording apparatus 10 according to the present embodiment includes a control unit 11, an image acquisition unit 12, an abnormality determination unit 13, a storage control unit 14, an audio acquisition unit 15, an audio analysis unit 16, and A storage unit 17 can be provided.

However, the storage control unit 14 in the present embodiment may be configured to perform control to store the image acquired by the image acquisition unit 12 and the sound acquired by the audio acquisition unit 15 in the storage unit 17. . Alternatively, as in the first embodiment, the image obtained by the image obtaining unit 12 and the sound obtained by the sound obtaining unit 15 may be temporarily stored in the working memory provided in the control unit 11 . Therefore, the control unit 11 according to the present embodiment can be configured not to perform control using a predetermined condition as described in the first embodiment.

Further, although the control unit 11 in the present embodiment can function as a control unit that controls the entire system, at least the following control shall be performed.

That is, when the determination result of the abnormality determination unit 13 indicates the first abnormality, the control unit 11 in the present embodiment causes the storage control unit 14 to start storing an image in the storage unit 17, If the second abnormality is indicated, the voice analysis is performed on at least one of the voice acquired by the voice acquisition unit 15 and stored in the storage unit 17 and the voice stored in the working memory provided in the control unit 11. Start speech analysis in unit 16 . In this way, the speech to be analyzed by the speech analysis unit 16 is acquired by the speech acquisition unit 15 (for example, when it is determined that storage is necessary or is always stored) and stored in the storage unit 17. and at least one of the immediately preceding voice and the voice on the working memory that is not stored in the storage unit 17 . In other words, in the first embodiment, voice analysis is performed on the voice acquired by the voice acquisition unit 15, but in the present embodiment, voice analysis is also performed on the voice stored in the storage unit 17. Can be configured. When the determination result of the abnormality determination unit 13 indicates the second abnormality, the control unit 11 causes the storage control unit 14 to start storing an image in the storage unit 17, or causes the sound analysis unit 16 to start storing a sound. An activation function selection unit is provided for selecting a function to activate whether analysis is to be performed.

In addition, in order to enable the start of such voice analysis, the voice data acquired by the voice acquisition unit 15 is stored in the working memory provided in the storage unit 17 or the control unit 11. However, the storage period should be at least a fixed period. Here, the certain period of time refers to a period in which, when the second abnormality is determined, a sound that enables analysis of the specific sound that is the target of the abnormality (for example, the sound at the time of occurrence of injury) can be secured. can be done. In this case, if the voice is stored in the working memory provided in the control unit 11, it is preferable to move the image including the voice to the storage unit 17 when finally storing the image.

As described above, in the first embodiment, the condition for storing an image is defined by abnormality detection (for example, sound volume, sound generation position, acceleration detected by the acceleration sensor 3, distance detected by the distance sensor 4, etc.). On the other hand, in the present embodiment, the function to be activated (either the image recording function or the sound analysis function) is selected depending on the detection of an abnormality.

Next, a processing example of the information recording apparatus 10 according to this embodiment will be described with reference to FIG.

First, the information recording device 10 acquires an image captured in a range including the surroundings of the vehicle 5 (step S11), acquires sound in a range including the surroundings of the vehicle 5 (step S12), Determination of the first abnormality and the second abnormality is performed (step S13). However, step S11 and step S12 can be performed as parallel processes, and step S13 can also be performed as parallel processes, except for an example in which sound or image is used for determination in step S13.

Next, when the second abnormality is determined in step S13 (YES in step S14), the information recording device 10 analyzes whether or not the sound acquired in step S12 is a specific sound (specific sound). Execute (step S15). If the sound is not the specific sound (NO in step S16), the information recording device 10 ends the process, and if the sound is the specific sound (YES in step S16), the acquired image is stored in the storage unit 17 ( Step S17), the process ends.

On the other hand, in the case of NO in step S14, if the first abnormality is determined in step S13 (YES in step S18), the information recording device 10 stores the acquired image in the storage unit without performing the voice analysis. 17 (step S17), and the process ends. If NO in step S18, that is, if neither the first nor the second abnormality occurs, the information recording device 10 terminates the process. Such processing is repeated in the information recording apparatus 10 .

According to the present embodiment, in addition to the effect of the first embodiment, the power consumption can be reduced because the voice analysis is not started until the determination of the second abnormality becomes abnormal.

<Other embodiments, etc.>
In Embodiments 1 and 2, the function of each part of the information recording device 10 has been described, but it is sufficient that the information recording device can realize these functions. Moreover, the information recording apparatus 10 according to Embodiments 1 and 2 can be mounted not only on the automobile exemplified as the vehicle 5 but also on other types of vehicles such as bicycles and motorcycles.

The programs described above also include instructions (or software code) that, when read into a computer, cause the computer to perform one or more of the functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or tangible storage medium. By way of example, and not limitation, computer readable media or tangible storage media may include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drives (SSD) or other memory technology, CDs -ROM, digital versatile disc (DVD), Blu-ray disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disc storage or other magnetic storage device. The program may be transmitted on a transitory computer-readable medium or communication medium. By way of example, and not limitation, transitory computer readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

The invention made by the present inventor has been specifically described above based on the embodiments, but the present invention is not limited to the above embodiments, and various modifications can be made without departing from the scope of the invention. Needless to say. Moreover, the present invention may be carried out by appropriately combining each embodiment.

1 drive recorder 2 camera unit 3 acceleration sensor 4 distance sensor 5 vehicle 10 information recording device 11 control unit 12 image acquisition unit 13 abnormality determination unit 14 storage control unit 15 voice acquisition unit 16 voice analysis unit 17 storage unit

Claims (5)

an image acquisition unit that acquires an image of a range including the surroundings of the vehicle;
a sound acquisition unit that acquires sound in a range including the surroundings of the vehicle;
a voice analysis unit that analyzes whether the voice acquired by the voice acquisition unit is a specific voice;
an abnormality determination unit that determines a first abnormality and a second abnormality occurring in the vehicle;
a storage unit;
a storage control unit that controls to store the image in the storage unit;
When the judgment result of the abnormality judging section indicates the first abnormality, the storage control section immediately starts storing the image in the storage section to indicate the second abnormality. a control unit for causing the storage control unit to start storing the image in the storage unit, based on a predetermined condition regarding the sound analyzed by the sound analysis unit, if the
Information recording device with an image acquisition unit that acquires an image of a range including the surroundings of the vehicle;
a sound acquisition unit that acquires sound in a range including the surroundings of the vehicle;
an abnormality determination unit that determines a first abnormality and a second abnormality occurring in the vehicle;
a storage unit;
a storage control unit that performs control to store the image and the sound in the storage unit;
a speech analysis unit that analyzes whether the speech is a specific speech;
When the determination result of the abnormality determining unit indicates the first abnormality, causing the storage control unit to start storing the image in the storage unit and indicating the second abnormality. if there is, a control unit for starting voice analysis by the voice analysis unit for at least one of the voice acquired by the voice acquisition unit and the voice stored in the storage unit;
Information recording device with The abnormality determination unit determines that the second abnormality occurs when the volume of the voice acquired by the voice acquisition unit is equal to or greater than a predetermined value, which is a condition different from the condition for determining the first abnormality. death,
When the determination result of the abnormality determination unit indicates that the second abnormality is present and the sound analyzed by the sound analysis unit is a specific sound, the control unit causes the memory control unit to starting to store the image in the storage unit;
3. The information recording apparatus according to claim 1 or 2. further comprising a sound source identification unit that identifies a sound source of the sound acquired by the sound acquisition unit;
The abnormality determination unit determines that the distance between the vehicle and the sound source identified by the sound source identification unit for the sound acquired by the sound acquisition unit is a predetermined value or less, which is a condition different from the condition for determining the first abnormality. is determined to be the second abnormality,
When the determination result of the abnormality determination unit indicates that the second abnormality is present and the sound analyzed by the sound analysis unit is a specific sound, the control unit causes the memory control unit to starting to store the image in the storage unit;
The information recording apparatus according to any one of claims 1 to 3. An information recording device having a storage unit,
Acquire an image that captures the range including the surroundings of the vehicle,
Acquiring sound in a range including the surroundings of the vehicle;
Analyze whether the acquired voice is a specific voice,
determining a first abnormality and a second abnormality occurring in the vehicle;
When the determination result indicates the first abnormality, the storage of the image in the storage unit is immediately started, and when the result indicates the second abnormality, the analysis is performed. starting to store the image in the storage unit based on a predetermined condition regarding sound;
Information recording method.

Images