JP2011204076A - Absence detection apparatus and absence detection method - Google Patents

Abstract

An absence detection device and an absence detection method capable of improving the accuracy of absence determination are provided.
An absence detection device 10 indicates a frequency of occurrence for each sound pressure level from a sound detection unit 11 for detecting surrounding sounds and a sound pressure level of a sound detected by the sound detection unit 11 per unit time. The calculation unit 12 that calculates the detection histogram data, the storage unit 13 that stores the absence histogram data indicating the occurrence frequency for each sound pressure level in the absence environment, the detection histogram data calculated by the calculation unit 12 and the storage unit 13 And a determination unit 14 that determines the absence by comparing the absence histogram data.
[Selection] Figure 1

Description

  The present invention relates to an absence detection device and an absence detection method.

  Conventionally, an intruder detection device that detects the presence of an intruder has been proposed. This intruder detection device detects the presence of an intruder in a detection area by an optical element. In addition, the intruder detection device includes sound sensing means for preventing a malfunction that an intruder exists even though no intruder exists in the detection area. In the intruder detection device, when the output signal level of the sound sensing means becomes a predetermined value or more, the detection sensitivity of the human body by the optical element is increased to widen the detection area. On the other hand, when the output signal level of the sound sensing means is less than a predetermined value, the intruder detection device reduces the detection sensitivity of the human body by the optical element and narrows the detection area (see Patent Document 1).

JP-A-5-274562

  However, in the conventional apparatus, since the sound pressure level is compared with the predetermined value, there is a possibility that the determination of the absence is erroneously performed when a sound pressure level higher than the predetermined value is obtained in the absence environment. For example, when an object falls in the absence environment, the sound pressure level is once more than a predetermined value, and it is determined that it is not absent although it is absent.

  The present invention has been made to solve such conventional problems, and an object of the present invention is to provide an absence detection device and an absence detection method capable of improving the accuracy of absence determination. It is in.

  The absence detection device of the present invention includes sound detection means for detecting ambient sounds, and detection histogram data indicating the frequency of occurrence for each sound pressure level from the sound pressure level of the sound detected per unit time by the sound detection means. Comparing calculation means, storage means storing absence histogram data indicating the occurrence frequency for each sound pressure level in the absence environment, detection histogram data calculated by the calculation means and absence histogram data stored by the storage means And absence determination means for determining absence.

  In the absence detection device of the present invention, the absence determination means uses the sound pressure level with the highest occurrence frequency in the absence histogram data stored in the storage means as the background level, and the background level in the detected histogram data calculated by the calculation means. It is preferable to determine absence based on the ratio of the frequency sum of the following sound pressure levels and the frequency sum of the sound pressure levels exceeding the background level.

  In the absence detection device of the present invention, the absence determination means may determine the absence by comparing the variance of the detected histogram data calculated by the calculation means with the variance of the absence histogram data stored by the storage means. preferable.

  In the absence detection device of the present invention, the absence determination means uses the sound pressure level with the highest occurrence frequency in the absence histogram data stored in the storage means as the background level, and in the detected histogram data calculated by the calculation means, the background It is preferable to determine the absence by comparing with the absence histogram data after excluding the sound pressure level exceeding a predetermined frequency among the sound pressure levels exceeding the level.

  Further, the absence detection device of the present invention further includes an update unit that updates the absence histogram data stored by the storage unit, and the update unit detects the absence by the absence determination unit based on the detected histogram data calculated by the calculation unit. When it is determined, it is preferable to accumulate the detected histogram data, calculate absent histogram data from the accumulated detected histogram data, and store it in the storage means.

  In addition, the absence detection method of the present invention includes a sound detection step for detecting surrounding sounds, and a detection histogram indicating the frequency of occurrence for each sound pressure level from the sound pressure level of the sound detected per unit time in the sound detection step. Absence determination for determining absence by comparing the calculation step for calculating data, the detected histogram data calculated in the calculation step, and absence histogram data indicating the occurrence frequency for each sound pressure level in the absence environment stored in advance And a process.

  According to the present invention, it is possible to provide an absence detection device and an absence detection method capable of improving the determination accuracy.

It is a block diagram of the control system containing the absence detection apparatus which concerns on this embodiment. It is a block diagram which shows the example of installation of the control system shown in FIG. It is a figure which shows an example of histogram data. It is a figure which shows an example of absent histogram data. It is a figure which shows an example of detection histogram data. It is a flowchart which shows the absence detection method which concerns on this embodiment, Comprising: The determination process of presence and absence is shown. It is a flowchart which shows the absence detection method which concerns on this embodiment, Comprising: The update process of absence histogram data is shown. It is a flowchart which shows the absence detection method which concerns on 2nd Embodiment, Comprising: The determination process of presence and absence is shown.

  DESCRIPTION OF EXEMPLARY EMBODIMENTS Hereinafter, preferred embodiments of the invention will be described with reference to the drawings. FIG. 1 is a block diagram of a control system including an absence detection apparatus according to the present embodiment, and FIG. 2 is a configuration diagram illustrating an installation example of the control system illustrated in FIG.

  As shown in FIG. 1, the control system 1 controls various devices 30 installed in a home or the like, and includes an absence detection device 10, a control device 20, and various devices 30.

  The absence detection device 10 detects the presence and absence of a user at home or the like. The control device 20 controls the various devices 30 based on the detection result from the absence detection device 10. For example, the control device 20 turns off the power of the various devices 30 when the user is absent, and turns on the power of the various devices 30 when the user is present. Moreover, the 1st apparatus 31 is a television as shown, for example in FIG. 2, the 2nd apparatus 32 is an air conditioner, and the 3rd apparatus 33 is an illuminating device.

  The absence detection device 10 includes a sound detection unit (sound detection unit) 11, a calculation unit (calculation unit) 12, a storage unit (storage unit) 13, a determination unit (absence determination unit) 14, and an update unit (update unit). 15).

  The sound detection unit 11 detects ambient sounds. For example, as shown in FIG. 2, the sound detection unit 11 is configured by a microphone, and is installed on a wall surface or the like in an embedded manner. The calculation unit 12 calculates histogram data from the sound pressure level of the sound detected by the sound detection unit 11.

  FIG. 3 is a diagram illustrating an example of histogram data. As shown in FIG. 3, the histogram data represents the frequency of occurrence for each sound pressure level in frequency. In calculating such histogram data, the calculation unit 12 recognizes the sound pressure level of the sound detected by the sound detection unit 11 per unit time. Then, the calculation unit 12 determines to which group the sound pressure level belongs in units of 5 dB. The calculation unit 12 adds the frequency by “1” to the group to which it belongs. The computing unit 12 computes the histogram data by repeating the above every unit time.

  Reference is again made to FIG. The storage unit 13 stores histogram data indicating the frequency of occurrence for each sound pressure level in the absence environment. Here, the histogram data stored in the storage unit 13 is referred to as absent histogram data. The histogram data calculated by the calculation unit 12 is referred to as detection histogram data.

  The determination unit 14 determines the absence by comparing the detected histogram data and the absent histogram data. Here, the histogram data indicates the sound pressure level and the frequency of occurrence thereof, and represents the sound environment in detail. For this reason, the determination unit 14 compares the current sound environment and the sound environment in the absent environment by comparing the detected histogram data and the absent histogram data. In this way, by comparing the frequency of occurrence for each sound pressure level called histogram data, it is possible to suppress a situation in which it is determined that the sound pressure level has reached a predetermined value or more once.

  If it demonstrates in detail, the determination part 14 will obtain | require a background level. Here, the background level refers to the sound pressure level with the highest occurrence frequency in the absence histogram data stored in the storage unit 13. FIG. 4 is a diagram illustrating an example of absence histogram data. As shown in FIG. 4, the sound pressure level with the highest occurrence frequency is 40 to 45 dB. For this reason, the determination part 14 determines that 40-45 dB is a background level in the example shown in FIG.

  Further, the determination unit 14 determines the absence based on the ratio between the total frequency of sound pressure levels below the background level and the total frequency of sound pressure levels exceeding the background level in the detected histogram data calculated by the calculation unit 12. . Specifically, the determination unit 14 determines the presence when the total frequency of sound pressure levels below the background level is greater than the total frequency of sound pressure levels exceeding the background level in the detected histogram data, and is absent when it is not. to decide.

  Here, an example of presence / absence determination will be described. First, it is assumed that the histogram data shown in FIG. 3 is detected histogram data. In this case, the sound pressure level below the background level is only 40 to 45 dB. On the other hand, the sound pressure level exceeding the background level corresponds to 45 to 50 dB, 50 to 55 dB, and 55 to 60 dB. According to the example of FIG. 3, the power sums of 45 to 50 dB, 50 to 55 dB, and 55 to 60 dB are larger than the power sums of only 40 to 45 dB. Therefore, in the example shown in FIG. 3, the determination unit 14 determines that there is.

  Thus, since the determination part 14 determines presence and absence by a ratio, it can suppress further that it makes an incorrect determination by the raise of a sound pressure level once.

  Furthermore, the determination unit 14 excludes an inappropriate sound pressure level from the detection histogram data. An inappropriate sound pressure level is generated, for example, when a large amount of noise is generated around the building. As described above, it is possible to appropriately determine the absence determination by excluding the suddenly generated sound.

  Specifically, the determination unit 14 excludes a sound pressure level having a predetermined frequency or more from among the sound pressure levels exceeding the background level in the detected histogram data calculated by the calculation unit 12. FIG. 5 is a diagram illustrating an example of detected histogram data. In the detection histogram data shown in FIG. 5, it is assumed that the background level is 40 to 45 dB. For this reason, the determination part 14 determines whether there exists a sound pressure level more than predetermined frequency in the sound pressure level of 45 dB or more exceeding a background level. In the example illustrated in FIG. 5, the sound pressure level of 55 to 60 dB is equal to or higher than the predetermined frequency, and thus the determination unit 14 excludes the sound pressure level of 55 to 60 dB.

  Reference is again made to FIG. The update unit 15 updates absent histogram data stored in the storage unit 13. When it is determined that the update unit 15 is absent based on the detected histogram data, the update unit 15 updates the absent histogram data based on the detected histogram data. More specifically, the update unit 15 accumulates the detected histogram data when it is determined that the user is absent. Then, when the accumulated number reaches a certain value (for example, one hour), the updating unit 15 calculates the absent histogram data based on the average of the accumulated histogram data. Thereafter, the update unit 15 stores the calculated absence histogram data in the storage unit 13. The absent histogram data is not limited to being calculated by averaging, and may be calculated by other methods.

  Thus, since the update unit 15 accumulates and updates the detection histogram data in the absence, even if there is a difference in the installation environment of the apparatus 10, the absence histogram data is updated to the one that was in the installation environment. It will be followed.

  Next, the absence detection method according to the present embodiment will be described. FIG. 6 is a flowchart showing the absence detection method according to the present embodiment, and shows presence / absence determination processing. As shown in FIG. 6, first, the calculation unit 12 calculates detection histogram data from the sound pressure level of the sound detected every unit time by the sound detection unit 11 (S1).

  Next, the determination unit 14 specifies the background level from the absence histogram data, and determines whether there is a sound pressure level equal to or higher than a predetermined frequency among the sound pressure levels exceeding the background level (S2). If it is determined that there is no sound pressure level equal to or higher than the predetermined frequency (S2: NO), the process proceeds to step S4. On the other hand, when determining that there is a sound pressure level equal to or higher than the predetermined frequency (S2: YES), the determination unit 14 deletes the sound pressure level from the detection histogram data (S3). Then, the process proceeds to step S4.

  In step S4, the determination unit 14 determines whether or not the total frequency of sound pressure levels below the background level is greater than the total frequency of sound pressure levels exceeding the background level (S4). If it is determined that the total frequency of the sound pressure level exceeding the background level is greater (S4: YES), the determination unit 14 determines that it is absent (S5), and the process proceeds to step S7. On the other hand, if it is determined that it is not greater than the total frequency of the sound pressure level exceeding the background level (S4: NO), the determination unit 14 determines that it is present (S6), and the process proceeds to step S7.

  In step S7, the determination unit 14 transmits the presence / absence determination result and detection histogram data (S7). At this time, the determination unit 14 transmits the determination result and detection histogram data to the update unit 15, and transmits the determination result to the control device 20. Thereafter, the process shown in FIG. 6 ends.

  FIG. 7 is a flowchart showing the absence detection method according to the present embodiment, and shows an update process of absence histogram data. As shown in FIG. 7, the update unit 15 first determines whether or not the determination result transmitted from the determination unit 14 is absent (S11). If it is determined that there is no absence (S11: NO), the processing shown in FIG. 7 ends.

  On the other hand, when it is determined that it is absent (S11: YES), the updating unit 15 accumulates the detection histogram data (S12), and determines whether or not one hour of detection histogram data is accumulated (S13). When it is determined that the detection histogram data for one hour has not been accumulated (S13: NO), the processing illustrated in FIG. 7 ends.

  On the other hand, when it is determined that the detected histogram data for one hour has been accumulated (S13: YES), the update unit 15 calculates the absent histogram data (S14), stores the absent histogram data in the storage unit 13, and updates the absent histogram data. (S15). Thereafter, the process shown in FIG. 7 ends.

  Thus, according to the absence detection device 10 and the absence detection method according to the present embodiment, the detection histogram data indicating the occurrence frequency for each sound pressure level is calculated from the sound pressure level of the sound detected every unit time. Therefore, the sound environment of the sound pressure level and the frequency of occurrence thereof is determined in detail. Further, the absence is determined by comparing the detected histogram data with absence histogram data indicating the occurrence frequency for each sound pressure level in the absence environment. For this reason, the clarified sound environment is compared with the sound environment in the absence environment. In this way, by comparing the frequency of occurrence for each sound pressure level called histogram data, it is possible to suppress a situation in which it is determined that the sound pressure level has reached a predetermined value or more once. Therefore, it is possible to improve the accuracy of the absence determination.

  Also, the absence is determined based on the ratio between the total frequency of sound pressure levels below the background level and the total frequency of sound pressure levels exceeding the background level in the calculated detection histogram data. As described above, by making a determination based on the ratio, it is possible to suppress erroneous determination due to a further increase in the sound pressure level. Therefore, it is possible to further improve the accuracy of the absence determination.

  In addition, the sound pressure level with the highest occurrence frequency in the stored absence histogram data is set as the background level, and the sound pressure level exceeding the predetermined frequency is excluded from the sound pressure levels exceeding the background level in the calculated detection histogram data. Then, the absence is judged. For this reason, when a large noise such as construction is generated in the surroundings, it is possible to suppress a situation where it is determined to be present despite the absence based on the sound pressure level. Therefore, it is possible to further improve the accuracy of the absence determination.

  In addition, when it is determined that it is absent, the detected histogram data is accumulated, and the absent histogram data is calculated and stored from the accumulated detected histogram data. Thus, since the detection histogram data in the absence is accumulated and updated, even if there is a difference in the installation environment of the apparatus 10, the absence histogram data will be updated to the one in the installation environment. . Therefore, it is possible to further improve the accuracy of the absence determination.

  Next, the absence detection device 10 and the absence detection method according to the second embodiment will be described. The absence detection device 10 according to the second embodiment is the same as that of the first embodiment, but the determination method of the presence and absence of the determination unit 14 is different. Only differences from the first embodiment will be described below.

  The determination unit 14 illustrated in FIG. 1 determines the absence by comparing the variance of the detected histogram data calculated by the calculation unit 12 with the variance of the absent histogram data stored by the storage unit 13. More specifically, the determination unit 14 determines that the detected histogram data is present when the variance of the detected histogram data is larger than the variance of the absent histogram data. Here, when the variance is large, it can be said that various levels of sound have been input, and there is a high possibility of being in the environment. In addition, since dispersion is employed, it is possible to further suppress erroneous determination due to a single increase in sound pressure level.

  Next, the absence detection method according to the second embodiment will be described. FIG. 8 is a flowchart showing the absence detection method according to the second embodiment, and shows presence / absence determination processing. As shown in FIG. 8, first, in steps S21 to S23, processing similar to that in steps S1 to S3 shown in FIG. 6 is executed.

  Next, the determination unit 14 determines whether or not the variance of the detected histogram data is larger than the variance of the absent histogram data (S24). If it is determined that the variance of the detected histogram data is greater than the variance of the absent histogram data (S24: YES), the determination unit 14 determines that it is present (S25), and the process proceeds to step S27. On the other hand, if it is determined that the variance of the detected histogram data is not greater than the variance of the absent histogram data (S24: NO), the determination unit 14 determines that it is absent (S26), and the process proceeds to step S27. In step S27, the determination unit 14 transmits the presence / absence determination result and detection histogram data (S27). Thereafter, the process shown in FIG. 8 ends.

  Thus, according to the absence detection device 10 and the absence detection method according to the present embodiment, the accuracy of the absence determination can be improved as in the first embodiment.

  Further, according to the second embodiment, the absence of the presence is determined by comparing the calculated variance of the detected histogram data with the variance of the stored absent histogram data. Here, if the variance is large, it can be said that various levels of sound have been input, and there is a high possibility of being in the environment. In addition, since dispersion is employed, it is possible to further suppress erroneous determination due to a single increase in sound pressure level. Therefore, it is possible to further improve the accuracy of the absence determination.

  As mentioned above, although this invention was demonstrated based on embodiment, this invention is not limited to the said embodiment, You may add a change in the range which does not deviate from the meaning of this invention, and combines each embodiment. Also good.

  For example, in the embodiment described above, the absence detection device 10 is used as a part of the control system 1 that controls the various devices 30, but the present invention is not limited to this, and may be used in a security system or the like.

DESCRIPTION OF SYMBOLS 1 ... Control system 10 ... Absence detection apparatus 11 ... Sound detection part (sound detection means)
12 ... Calculation unit (calculation means)
13. Storage unit (storage means)
14: Determination unit (absence determination means)
15. Update unit (update means)
20 ... Control device 30 ... Various devices

Claims (6)

Sound detection means for detecting ambient sounds;
Calculation means for calculating detection histogram data indicating the frequency of occurrence for each sound pressure level from the sound pressure level of the sound detected per unit time by the sound detection means;
Storage means for storing absence histogram data indicating the occurrence frequency for each sound pressure level in the absence environment;
Absence judging means for judging absence by comparing the detected histogram data computed by the computing means with the absent histogram data stored by the storage means,
An absence detection device comprising: The absence determination means sets the sound pressure level with the highest occurrence frequency in the absence histogram data stored by the storage means as a background level, and the detected histogram data calculated by the calculation means has a sound pressure level equal to or lower than the background level. The absence detection device according to claim 1, wherein absence is determined based on a ratio between a total frequency and a total frequency of sound pressure levels exceeding the background level. The absence determination unit compares the detection histogram data calculated by the calculation unit with the absence histogram data stored by the storage unit to determine the absence. The absence detector described. The absence determination means sets the sound pressure level having the highest occurrence frequency in the absence histogram data stored by the storage means as a background level, and the detected histogram data calculated by the calculation means has a sound pressure level exceeding the background level. The absence detection according to any one of claims 1 to 3, wherein sound pressure levels having a predetermined frequency or more are excluded and the absence histogram is compared with the absence histogram data. apparatus. Update means for updating absence histogram data stored by the storage means;
The update means accumulates the detected histogram data when the absence determination means determines that the absence is based on the detected histogram data calculated by the calculation means, and the absence histogram data is stored from the accumulated detection histogram data. The absence detecting device according to any one of claims 1 to 4, wherein the absence is calculated and stored in the storage unit. A sound detection process for detecting ambient sounds;
A calculation step of calculating detection histogram data indicating the occurrence frequency for each sound pressure level from the sound pressure level of the sound detected every unit time in the sound detection step;
The absence determination step of comparing the detected histogram data calculated in the calculation step with the absence histogram data indicating the occurrence frequency for each sound pressure level in the absence environment stored in advance, and determining the absence,
The absence detection method characterized by having.

Images