JP2004305239A - Dangerous state detecting method and dangerous state recording device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a dangerous state detection method and a dangerous state recording device that improve the safety of a working environment by precisely detecting a state in which a worker feel a danger. <P>SOLUTION: The method is intended to detect a dangerous state in a working environment and has a step of measuring the GSR of a worker and the heart rate or pulse rate of the worker as physiological information and the step of judging whether a dangerous state exists at the target time for judgment on the basis of a change in the time series of the physiological information. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a danger state detection method for detecting a danger state in a work environment, and a danger state recording device for recording a danger state in a work environment.
[0002]
[Prior art]
In work environments that involve dangers such as construction sites, roads, welfare facilities, etc., not only cases where an accident actually occurred, but also cases where workers felt danger even without an accident (so-called “ It has been practiced to accumulate and analyze "cool / hat" cases). Conventionally, such cases have been accumulated based on reports from workers who have actually experienced a dangerous situation.
[0003]
[Problems to be solved by the invention]
However, despite the fact that it is said that there are tens of times the actual number of accidents in the case of "Hidden / Hatto", there is often no obligation to notify workers just because they felt danger. Therefore, the number of reports required for analysis is difficult to gather at present.
[0004]
In addition, if there is no actual harm, the notification from the worker tends to be delayed, so that there is a problem that the memory of the worker fades with time and it is difficult to reproduce an accurate situation.
[0005]
The present invention has been made to solve such a problem, and a dangerous state detection method capable of improving the safety of a working environment by accurately detecting a state where a worker feels danger, and It is intended to provide a danger state recording device.
[0006]
[Means for Solving the Problems]
The object of the present invention is a method of detecting a dangerous state in a work environment, comprising: measuring a worker's GSR and a worker's heart rate or pulse rate as physiological information; This is achieved by a dangerous state detection method including a step of determining whether or not a dangerous state has occurred at a determination target time based on a series change.
[0007]
The step of determining the presence or absence of the occurrence of the dangerous state includes a step in which a GSR value after a lapse of a predetermined time t1 (sec) from the determination target time is higher than a GSR value at the determination target time by a predetermined electrical conductance c1 (μmho) or more; In addition, the minimum value of the instantaneous heart rate or the instantaneous pulse rate during the predetermined time t2 (sec) before the determination target time is the instantaneous heart rate or the instantaneous pulse during the predetermined time t3 (sec) after the determination target time. If the number is larger than the minimum value, a step of determining that a dangerous state has occurred at the determination target time may be provided.
[0008]
In this case, the predetermined time t1 is preferably 2.5 to 20 (sec), the predetermined electric conductance c1 is preferably 0.02 to 1.3 (μmho), and the predetermined time t2 is Is preferably 3 to 66 (sec), and the predetermined time t3 is preferably 6 to 66 (sec).
[0009]
In particular, to obtain a detection sensitivity of 99% or more, the predetermined time t1 is more preferably 3.5 to 17.5 (sec), and the predetermined electric conductance c1 is 0.02 to 0.14. (Μmho), the predetermined time t2 is more preferably 3 to 24 (sec), and the predetermined time t3 is more preferably 21 to 66 (sec). In determining the range of parameter values, the reason for considering the detection sensitivity as an evaluation index is that the algorithm avoids the inability to detect dangerous scenes rather than erroneously detecting non-dangerous scenes as dangerous. This is because it is considered one priority.
[0010]
The above-described dangerous state detection method includes a step of continuously capturing at least a part of a field of view of the worker, generating image information, and the time corresponding to the determination target time when it is determined that a dangerous state has occurred. The method may further include the step of specifying image information.
[0011]
Further, the object of the present invention is a device for recording a danger state in a work environment, wherein a measuring means for measuring a worker's GSR and a worker's heart rate or pulse rate as physiological information, A storage means for storing, a dangerous state determining means for determining whether or not a dangerous state has occurred at a determination target time based on a time-series change of the physiological information, and continuously capturing at least a part of a visual field of the worker, This is achieved by a danger state recording device that includes an imaging unit that generates information, and a danger state identification unit that identifies the image information corresponding to the determination target time at which the danger state is determined to have occurred by the danger state determination unit. You.
[0012]
BEST MODE FOR CARRYING OUT THE INVENTION
First, a dangerous state detection method according to one embodiment of the present invention will be described. The present inventors examined effective information for detecting a dangerous state among various types of physiological information obtained from an operator, and found that the operator's GSR (galvanic skin response) and the operator's It has been found through experiments that a dangerous state can be detected with high accuracy by paying attention to the heart rate (or pulse rate).
[0013]
GSR is a change in skin electrical conductance associated with sweating when a worker receives a strong stimulus. When the GSR value before and after applying a stimulus such as a gunshot to the subject was measured, it was found that, as shown in FIG. Here, the GSR value is a skin electrical conductance and is expressed in units of μmho.
[0014]
As described above, the GSR value is considered to be effective physiological information for detecting a dangerous state such as “heat and hat”. Therefore, the present inventors have made a total of four surfaces of the front surface, the left and right surfaces, and the floor surface. The virtual construction site is reproduced using a large VR (virtual reality) device that can project stereo images onto the virtual work space. Was generated, and the subject was asked to report a scene where the subject was “cool and hit” by subjective evaluation, and the detection accuracy of the dangerous state based on the change in the GSR value of the subject was examined. The result is shown in FIG.
[0015]
FIG. 2 shows a case where it is determined that a dangerous state has occurred when an event occurs when the GSR value after a lapse of t1 (sec) from the event occurrence becomes higher than the GSR value at the time of event occurrence by c1 (μmho) or more. The (a) sensitivity (sensitivity) and (b) specificity (specificity) are shown in a bird's-eye view, where the horizontal axis is t1 (every 3 seconds) and the vertical axis is c1 (every 0.02 μmho). Here, the sensitivity is a ratio of the number of times of detection to the number of times of event occurrence, and the higher the sensitivity, the higher the detection rate at the time of event occurrence. The specificity is the ratio of the number of non-occurrence / non-detection (the number of times of non-detection when no event occurred) to the number of tests. The higher the specificity, the lower the false detection rate when no event occurs. ing.
[0016]
As shown in FIG. 2 (a), the sensitivity is almost 0 when t1 is 0, but increases as t1 is increased, and the time lag between the time when the GSR value changes and the time when the stimulus is actually received is changed. You can see what is happening. On the other hand, as c1 increases, the sensitivity decreases even if t1 is the same. As described above, from the viewpoint of improving the sensitivity, it is preferable to increase t1 and decrease c1.
[0017]
On the other hand, as shown in FIG. 2B, the specificity sharply decreases as c1 approaches 0, and the erroneous detection rate increases. Also, when t1 is increased, the specificity tends to decrease. As described above, from the viewpoint of improving the specificity, it is preferable to decrease t1 and increase c1.
[0018]
From the above, it can be seen that in order to maintain both the sensitivity and the specificity satisfactorily, it is only necessary to set t1 and c1 in the respective predetermined ranges. From the experimental results shown in FIG. 2, it is preferable to set t1 in the range of 2.5 to 20 sec in order to achieve a detection sensitivity of 70% or more, and to achieve a detection sensitivity of 80% or more. , 3 to 20 sec, and more preferably, 3.5 to 17.5 sec in order to achieve a detection sensitivity of 99% or more. Further, c1 is preferably set in the range of 0.02 to 1.3 μmho in order to achieve a detection sensitivity of 70% or more, and to 0.1% in order to achieve a detection sensitivity of 80% or more. It is more preferably set in the range of 02 to 0.7 μmho, and even more preferably in the range of 0.02 to 0.14 μmho in order to achieve a detection sensitivity of 99% or more. The reason why the detection sensitivity is considered as an evaluation index in determining the parameter value range here is that it is considered that the first priority is to avoid that the present algorithm cannot detect a dangerous scene.
Further, the present inventors measured the instantaneous heart rate before and after applying a stimulus such as a gunshot to the subject, and as shown in FIG. 3, for example, as shown in FIG. It was found to be lower than before the occurrence. The instantaneous heart rate is a value obtained for each heartbeat of the subject.
[0019]
As described above, since the instantaneous heart rate is considered to be effective physiological information for detecting a dangerous condition such as "heat and hat", the change in the heart rate of the subject is measured using the VR device in the same manner as described above. The detection accuracy of the dangerous state based on the information was investigated. The result is shown in FIG.
[0020]
FIG. 4 shows a dangerous state when an event occurs when the minimum value of the instantaneous heart rate during t2 (sec) before the event occurs is greater than the minimum value of the instantaneous heart rate during t3 (sec) after the event occurs. (A) Sensitivity and (b) Specificity (specificity) in a bird's-eye view when it is determined that is generated are shown in a bird's-eye view. The horizontal axis is t2 (every 3 seconds), and the vertical axis is t3 (every 3 seconds). I have. Note that the range in which the instantaneous heart rate is 30 or less is excluded as an artifact.
[0021]
As shown in FIG. 4A, from the viewpoint of improving the sensitivity, it is preferable to decrease t2 and increase t3. On the other hand, as shown in FIG. 4B, from the viewpoint of improving the specificity, it is preferable to increase t2 and decrease t3. Therefore, it can be seen that t2 and t3 may be set to predetermined ranges in order to maintain both the sensitivity and the specificity satisfactorily. From the experimental results shown in FIG. 4, it is preferable that t2 be set in the range of 3 to 66 seconds in order to achieve a detection sensitivity of 80% or more, and to achieve a detection sensitivity of 90% or more. More preferably, it is set in a range of 3 to 24 sec, in order to achieve a detection sensitivity of 99% or more. In addition, t3 is preferably set in a range of 6 to 66 sec in order to achieve a detection sensitivity of 90% or more, and in a range of 21 to 66 sec in order to achieve a detection sensitivity of 99% or more. It is more preferable to set. The reason why the detection sensitivity is considered as an evaluation index in determining the parameter value range here is that it is considered that the first priority is to avoid that the present algorithm cannot detect a dangerous scene.
The present inventors have confirmed by experiments that the above-described study on the instantaneous heart rate can obtain the same result as the instantaneous pulse rate. As for the instantaneous pulse rate, a value obtained for each beat can be used.
[0022]
As described above, the GSR value and the instantaneous heart rate (or instantaneous pulse rate) are both physiological information effective for detecting a dangerous state, but are highly qualitatively independent information between the two. Therefore, when both the GSR value and the instantaneous heart rate (or instantaneous pulse rate) satisfy the above-mentioned conditions for an arbitrary determination target time, it is determined that a dangerous state has occurred at the determination target time. It is possible to increase the detection accuracy of the occurrence of a dangerous state.
[0023]
Next, a danger state recording device according to one embodiment of the present invention will be described. FIG. 5 is a block diagram showing the configuration of the danger state recording device according to one embodiment of the present invention. As shown in FIG. 1, the danger state recording device 1 includes a physiological information measuring device 10, a determination processing device 20, an imaging device 30, and an image recording device 40.
[0024]
The physiological information measuring device 10 is formed in a glove shape as shown in FIG. 6, and GSR deriving electrodes 12 and 14 are respectively provided at positions corresponding to the index finger and the middle finger when worn on the left hand, and correspond to the ring finger. The pulse deriving electrode 16 is provided at a position where the pulse is derived. The physiological information measuring device 10 is connected to the determination processing device 20.
[0025]
The determination processing device 20 includes a physiological information storage unit 22 and a dangerous state determination unit 24, and is configured to be attachable to the left wrist as shown in FIG. The physiological information storage unit 22 stores the physiological information on the GSR and the pulse rate input from the physiological information measuring device 10. The danger state determination unit 24 determines whether or not a danger state has occurred at the determination target time in accordance with a preset determination condition based on a time-series change of the physiological information stored in the physiological information storage unit 22, and generates a danger state occurrence. Is output to the imaging device 30.
[0026]
The imaging device 30 includes an imaging unit 32, an image signal processing unit 34, an image information storage unit 36, and a danger state identification unit 38, and is configured in a helmet shape as shown in FIG. ing. The imaging unit 32 is, for example, a CCD camera, and captures at least a part of the visual field of the worker. The image signal processing unit 34 converts the image signal input from the imaging unit 32 into digital information, and stores the generated image information in the image information storage unit 36. The danger state specifying unit 38 extracts image information corresponding to the determination target time input from the danger state determination unit 24 from the image information storage unit 36 and outputs the extracted image information to the image recording device 40.
[0027]
The image recording device 40 is configured to be attachable to the right wrist, and stores image information input from the imaging unit 30.
[0028]
In the danger state recording device 1 having the above configuration, the GSR value and the pulse rate of the worker are constantly measured by the physiological information measuring device 10 and stored in the physiological information storage unit 22 as physiological information. The field of view of the worker is constantly imaged by the imaging device 30 and stored in the image information storage unit 36 as image information.
[0029]
The dangerous state determination unit 24 starts determining a dangerous state based on the stored physiological information after a predetermined time has elapsed since the physiological information measuring device 10 started measuring. Specifically, first, a determination target time as a determination target for determining whether or not a dangerous state has occurred is set, and a GSR value after a lapse of t1 (sec) from the determination target time is a GSR value at the determination target time. C1 (μmho) or more, and the minimum value of the instantaneous pulse rate during t2 (sec) before the determination target time is larger than the minimum value of the instantaneous pulse rate during t3 (sec) after the determination target time. In this case, it is determined that a dangerous state has occurred at the determination target time. The values of t1, c1, t2, and t3 can be appropriately determined within the above-described range. In the present embodiment, t1 = 4.5, c1 = 0.12, t2 = 9, and t3 = 66. . The danger state determination unit 24 repeatedly performs the above-described determination of the danger state while changing the determination target time by a predetermined time (for example, 3 seconds), and captures each determination target time at which the danger state is determined to occur as the imaging unit 30. Output to
[0030]
The imaging unit 30 extracts image information corresponding to each determination target time (for example, moving image information for about 3 seconds before and after the determination target time) from the image information storage unit 36 and outputs the extracted image information to the image recording device 40. Thus, the image recording device 40 stores only the image information corresponding to the state in which the worker feels danger, and by analyzing this image information, it is possible to easily identify a dangerous situation or location at the work site. And the safety of the working environment can be improved.
[0031]
As mentioned above, although one Embodiment of this invention was described in full detail, the specific aspect of this invention is not limited to the said Embodiment. For example, the danger state recording device of the present embodiment determines the danger state based on the worker's GSR value and the instantaneous pulse rate. It is also possible to determine a dangerous state in the same manner as described above.
[0032]
Further, the danger state recording device of the present embodiment is configured such that the physiological information measuring device 10 is glove-shaped and the determination processing device 20 can be mounted on the wrist, but the configuration is particularly limited as long as the workability is not impaired. Instead, for example, the physiological information measuring device 10 may be made sock-shaped, and the electrodes 12, 14, 16 may be attached to the toes, and the determination processing device 20 may be attached to the ankle.
[0033]
Further, instead of extracting the image information corresponding to the determination target time determined to be in the dangerous state as in the present embodiment, by providing a notifying means for notifying by voice or the like immediately after determining the dangerous state, the worker can The danger state may be recognized on the spot.
[0034]
In the present embodiment, the dangerous state determination unit 24 performs the determination of the dangerous state in parallel with the measurement by the physiological information measuring device 10. However, after the measurement by the physiological information measuring device 10 is completed, The determination of the state may be started.
[0035]
Further, in the present embodiment, the dangerous state specifying unit 38 extracts image information corresponding to the determination target time at which it is determined that the dangerous state has occurred, and stores the extracted image information in the image recording device 40. Other methods can be used as long as the image information corresponding to the target time can be specified. For example, the danger state specifying unit 38 determines whether the danger state of the image information stored in the image information storage unit 36 corresponds to a predetermined time before and after the determination target time at which the danger state is determined to have occurred. It can also be configured to perform processing that can be identified by voice.
[0036]
In the present embodiment, the imaging device 30 stores all image information obtained by imaging in the image information storage unit 36. However, the image information storage unit 36 It is also possible to use an image buffer or the like that can delete image information and write new image information.
[0037]
【Example】
A dangerous scene was generated in a virtual construction work site using the above-described VR device, and the detection accuracy of the "hi-hat" state was confirmed for 21 subjects (healthy men: 18 to 29 years old). . As the detection algorithm, by measuring the GSR and the heart rate of the subject, the GSR value after 4.5 seconds have elapsed from the determination target time is higher than the GSR value at the determination target time by 0.12 μmho or more, and When the minimum value of the instantaneous heart rate for 9 seconds before the determination target time is larger than the minimum value of the instantaneous pulse rate for 66 seconds after the determination target time, it was determined that a dangerous state occurred at the determination target time.
[0038]
As a result, in the resting (static) state, the sensitivity (sensitivity) = 1 (100%) and the specificity (specificity) = 0.90 (90%). = 1 (100%) and specificity = 0.87 (87%), and in both the static state and the dynamic state, good detection results were obtained for both sensitivity and specificity.
[0039]
【The invention's effect】
As is apparent from the above description, according to the present invention, a dangerous state detecting method and a dangerous state recording device capable of improving the safety of a working environment by accurately detecting a state where a worker feels a danger. Can be provided.
[Brief description of the drawings]
FIG. 1 is a diagram illustrating an example of a time-series change of a GSR value.
FIG. 2 is a diagram showing (a) sensitivity and (b) specificity when determining occurrence of a dangerous state based on a GSR value.
FIG. 3 is a diagram illustrating an example of a time-series change of an instantaneous heart rate.
FIG. 4 is a diagram showing (a) sensitivity and (b) specificity when determining occurrence of a dangerous state based on an instantaneous heart rate.
FIG. 5 is a block diagram illustrating a configuration of a danger state recording device according to an embodiment of the present invention.
FIG. 6 is a schematic configuration diagram of a main part of the danger state recording device.
FIG. 7 is a schematic configuration diagram of another main part of the danger state recording device.
[Explanation of symbols]
Reference Signs List 1 Danger state recording device 10 Physiological information measuring device 12, 14 GSR derivation electrode 16 Pulse derivation electrode 20 Judgment processing device 22 Physiological information storage unit 24 Danger state judgment unit 30 Imaging device 32 Imaging unit 34 Image signal processing unit 36 Image information Storage unit 38 Danger state identification unit 40 Image recording device

Claims (5)

A method for detecting a dangerous state in a work environment,
Measuring the GSR of the worker and the heart rate or pulse rate of the worker as physiological information; and
A dangerous state detection method comprising: determining whether a dangerous state has occurred at a determination target time based on a time-series change in the physiological information. The step of determining whether the dangerous state has occurred,
The GSR value after a lapse of a predetermined time t1 (sec) from the determination target time is higher than the GSR value at the determination target time by a predetermined electrical conductance c1 (μmho) or more and the predetermined time t2 ( When the minimum value of the instantaneous heart rate or the instantaneous pulse rate during the time period (sec) is larger than the minimum value of the instantaneous heart rate or the instantaneous pulse rate during the predetermined time t3 (sec) after the judgment target time, the judgment is made. The dangerous state detection method according to claim 1, further comprising a step of determining that a dangerous state has occurred at the target time. The predetermined time t1 is 2.5 to 20 (sec),
The predetermined electric conductance c1 is 0.02 to 1.3 (μmho), the predetermined time t2 is 3 to 66 (sec),
The dangerous state detection method according to claim 2, wherein the predetermined time t3 is 6 to 66 (sec). Continuously imaging at least a part of the field of view of the worker, and generating image information; and
The dangerous state detection method according to claim 1, further comprising a step of specifying the image information corresponding to the determination target time at which it is determined that a dangerous state has occurred. A device for recording a danger state in a work environment,
Measuring means for measuring the GSR of the worker and the heart rate or pulse rate of the worker as physiological information,
Storage means for storing the physiological information,
Dangerous state determination means for determining the presence or absence of a dangerous state occurrence at the determination target time based on the time-series change of the physiological information,
Imaging means for continuously imaging at least a part of the field of view of the worker and generating image information; and
A danger state recording device comprising danger state identification means for identifying the image information corresponding to the determination target time at which the danger state determination means has determined that a danger state has occurred.

Images