JP5962288B2 - Object detection program, detection apparatus, and detection method - Google Patents

Description

The present invention, the object detection program detecting device, and a detection method.

  2. Description of the Related Art Conventionally, there is a simulation system that simulates the operation of an operator who performs product assembly work in a factory and verifies the presence of useless operation or time.

  According to such a simulation system, it is possible to reduce the waste of the operator's operation and to expect improvement in work efficiency and productivity.

JP 2007-304973 A

  However, if efficiency, productivity, etc. are pursued too much, there is a risk of neglecting worker safety.

  In the factory, even if the worker is working at a fixed position, various objects such as equipment move and cross the worker's field of view. Even if such an object does not contact the worker, the worker feels danger. As a result, a worker's unexpected reaction may induce a dangerous situation such as contact with surrounding people or equipment.

  In view of this, an object of one aspect is to support the identification of an object that may cause a worker's danger.

In one proposal, an object body detection program, position information and the position information and the line-of-sight direction information indicating a direction of the line of sight indicates the operator position of each point of the predetermined interval showing the position of the object every time a predetermined distance DOO identified and the said operator of the determined object and the included in determining whether includes object field of the operator in the field of view, and the view position and the operator of the object body the relative positional relationship is smaller than a predetermined condition is allowed to execute a process for detecting an object that has changed the states included in the visual field of the operator from the state not included in the visual field of the operator to the computer.

  According to one aspect, it is possible to support identification of an object that may induce a worker's danger.

It is a 1st figure for demonstrating the detection method of the attention object in this Embodiment. It is a 2nd figure for demonstrating the detection method of the attention object in this Embodiment. It is a figure for demonstrating the determination method of the danger level of an attention required object. It is a figure for demonstrating the 1st example of the object made into the fall target of a danger level. It is a figure for demonstrating the 2nd example of the object made into the fall target of a danger level. It is a figure for demonstrating the example of the object excluded from the candidate of an attention required object. It is a figure which shows the hardware structural example of the detection apparatus in this Embodiment. It is a figure which shows the function structural example of the detection apparatus in this Embodiment. It is a figure which shows the structural example of an operator information table. 5 is a diagram illustrating a configuration example of an object information table for an object A. FIG. 6 is a diagram illustrating a configuration example of an object information table of an object B. FIG. 6 is a diagram illustrating a configuration example of an object information table of an object C. FIG. 6 is a diagram illustrating a configuration example of an object information table of an object D. FIG. It is a figure which shows the movement log | history of an operator and each object in this Embodiment. It is a figure which shows the example of the initial state of an object state table. It is a flowchart for demonstrating an example of the process sequence which a detection apparatus performs. It is a figure which shows the example of the object state table in which the result of the group specific process was reflected. It is a figure which shows the example of the object state table at the time of completion of the process regarding Time = 0 time point. It is a figure which shows the example of the object state table at the time of the completion of the process regarding Time = 1 time point. It is a flowchart for demonstrating an example of the process sequence of a risk determination process. It is a figure which shows the structural example of a result information storage part. It is a figure which shows the example of the object state table at the time of the completion of the process regarding Time = 2 time. It is a figure which shows the example of the result information storage part at the time of completion of the process regarding Time = 2 time. It is a figure which shows the example of the object state table at the time of the completion of the process regarding Time = 3 time point. It is a figure which shows the example of the object state table at the time of the completion of the process regarding Time = 4 time point. It is a flowchart for demonstrating an example of the process sequence of a group specific process.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. First, an outline of the present embodiment will be described. In the present embodiment, an object that may induce a worker's danger is referred to as an “object requiring attention”. As an example of an object that can be a sensitive object, there are equipment operating in a factory, an automatic transport vehicle, and other moving objects. Further, even if the object is not moving, an object that is moving with respect to the worker, that is, a fixed object that moves relative to the movement of the worker may be an object requiring attention.

  FIG. 1 is a first diagram for explaining a method for detecting an object requiring attention in the present embodiment.

  FIG. 1A is a view of the worker W, the objects A to G, and the like viewed from above. The boundary line bL1 and the boundary line bR1 are boundary lines of the worker's visual field (or field of view) V1. The line-of-sight direction dr1 indicates the line-of-sight direction of the operator. Therefore, among the range formed by the boundary lines bL1 and bR1, the range on the line-of-sight direction dr1 side is the worker's visual field V1.

  The arrows attached to the objects A to G are vectors (hereinafter referred to as “movement vectors”) indicating the moving direction and moving distance of each object. That is, the direction of the movement vector indicates the movement direction, and the length of the movement vector indicates the movement distance in a fixed time. The same applies to the following drawings regarding expressions relating to the worker's field of view, the position of the object, and the moving direction.

  At a certain time t0, the objects A to G are present at the positions where the rectangles are arranged. At a time point t1 after a predetermined time (for example, 1 second or 0.1 second) has elapsed from the time point t0, the objects A to G move by the directions and distances indicated by the respective movement vectors. Between the time point t0 and the time point t1, the visual line direction dr1 and the visual field V1 of the worker W are not changed.

  FIG. 1B is a diagram in which the landscape of the visual field V1 is projected onto a virtual plane (hereinafter referred to as “projection plane”) that is perpendicular to the line-of-sight direction dr1 at time t0. (C) is a diagram in which the landscape of the visual field V1 is projected on the projection plane in the line-of-sight direction dr1 at time t1. As can be seen from (B), at the time point t0, the visual field V1 includes objects A, B, and C. Further, as can be seen from (C), at the time point t1, the visual field V1 includes objects A, B, D, E, F, and G. That is, between time t0 and time t1, the object C moves out of the visual field V1, and the objects D to G enter the visual field V1.

  Under the circumstances as described above, in the present embodiment, first, the objects D to G that have entered the visual field V1 are detected as candidates for the object requiring attention. Subsequently, it is determined whether or not the relative positional relationship with the visual field V1 satisfies a predetermined condition for each object that is a candidate for the object requiring attention. An example of the predetermined condition is an angle formed by a straight line connecting the boundary line bL1 or bR1 that the object crosses last and the position of the worker W and the object after moving (at time t1) (hereinafter referred to as “inside field of view”). "Angle") exceeds a predetermined value. The in-view angle can be said to be the angle of the object after movement with respect to the boundary line bL1 or bR1 with the operator as the center. In (A), the visual field angles of the objects D, E, F, and G are indicated by ∠d, ∠e, ∠f, and ∠g.

  In FIG. 1, it is assumed that ∠e and ∠f exceed a predetermined value. Therefore, the objects E and F are detected as objects requiring attention.

  That is, a large angle within the visual field means that the moving distance is long by entering the visual field V1 during a predetermined time, that is, the moving speed at the time of entering the visual field V1 is high. Even if the moving distance after entering the visual field V1 is short, an object close to the worker W has a large visual field angle. That is, the moving speed after entering the visual field V1 and the distance from the operator W can be evaluated by the angle in the visual field. In general, an operator is likely to be surprised by an object that has entered the field of view at high speed. Also, in general, an operator is highly likely to be surprised if something suddenly comes into view at a position close to him / her. Therefore, in the present embodiment, it is determined whether or not the object is a sensitive object based on the in-view angle.

  FIG. 2 is a second diagram for explaining a method for detecting an object requiring attention in the present embodiment. The situation setting of FIG. 2 is the same as that of FIG.

  FIG. 2 shows an example in which the gaze direction of the worker W is changed from the gaze direction dr1 to the gaze direction dr2 between time t0 and time t1 as shown in FIG. That is, an example in which the direction of the worker W is rotated to the right is shown. The visual field V2 in the line-of-sight direction dr2 is formed by the boundary line bL2 and the boundary line bR2.

  (B) is a diagram in which the landscape of the visual field V1 is projected on the projection plane in the line-of-sight direction dr1 at time t0. (C) is a diagram in which the landscape of the visual field V2 is projected on the projection plane in the line-of-sight direction dr2 at time t1.

  In the same procedure as described in FIG. 1, first, the objects E, F, and G that have entered the visual field V2 are detected as candidates for the object requiring attention. Subsequently, it is determined whether or not the in-view angle is greater than or equal to a predetermined value for each object that is a candidate for the object requiring attention. For calculation of the in-view angle, the boundary line bL2 or bR2 of the view field V2 is used. As a result, the angle α1 in the rotation direction from the visual line direction dr1 to the visual line direction dr2 is added to or subtracted from the in-field angle of each object with respect to the visual field V1. By doing so, the relative relationship between the field of view of the operator W and each object due to the rotation of the work difference W is reflected in the in-view angle. That is, due to a change in the line-of-sight direction of the worker W, the moving speed and moving amount of an object moving in the same direction as the direction decrease, and the moving speed and moving amount of an object moving in the opposite direction increase. Such a situation is reflected in the in-view angle.

  Of the in-view angles ∠e, ∠f, or ∠g of the objects E, F, and G detected as candidates for the object requiring attention, ∠f and ∠g exceed a predetermined value. Therefore, the objects F and G are detected as objects requiring attention.

  By the way, the extent to which an operator is surprised about the object detected as a sensitive object is not necessarily constant. Depending on the shape and size of the object, the extent to which the operator is surprised is considered to be different. Therefore, in this embodiment, a concept called “risk level” is introduced. The degree of danger is an integer value indicating the degree of surprise for the worker, and the greater the value, the greater the degree of surprise for the worker. In addition, it is assumed that the minimum risk level is zero. It is arbitrary how to handle the risk 0. It may be treated as having no danger or may be treated as having a danger. In the present embodiment, for example, as shown in FIG. 3, the degree of risk is determined.

  FIG. 3 is a diagram for explaining a method for determining the risk level of an object requiring attention. The situation setting in FIG. 3 is the same as in FIG. However, as shown in FIG. 1C, the shapes or sizes of the objects E, F, and G with respect to the projection plane in the viewing direction are different from those in FIG.

  In general, an object that looks large is considered to be more surprising than an object that appears small. Therefore, the risk of an object that looks large like the object E is increased.

  Moreover, since the thin object makes the worker feel sharp, it is considered that the degree of surprise of the worker is large. Therefore, the risk of thin objects such as the object G and the object F is increased. Note that the thinness may be determined based on, for example, the aspect ratio of the minimum circumscribed rectangle of the shape of the object projected on the projection plane. For example, when the horizontal / vertical value exceeds a predetermined value, it may be determined to be thin.

  Further, the risk of an object including an acute angle portion may be increased.

  On the other hand, even if an object is detected as a cautionary object, an object that is unlikely to surprise the worker is also conceivable. In this embodiment, the degree of risk is reduced for such an object.

  FIG. 4 is a diagram for explaining a first example of an object whose risk is to be lowered. In FIG. 4, the same parts as those in FIG.

  In FIG. 4, objects F1, F2, F3, and F4 are groups of objects that are moving on the same path or trajectory at regular intervals. For example, an object group moving on the belt conveyor may be assumed. Such movement of the object is highly predictable for the operator. Therefore, even if the in-view angle exceeds a predetermined value, the operator is unlikely to be surprised. Therefore, the risk level is lowered for such an object.

  In addition, for example, an object that emits a warning sound at a certain rhythm to alert the operator may be noticed by the operator even if the object is outside the operator's field of view. high. In addition, when an object that emits flashing light enters the worker's field of view, the worker can recognize the presence of the object by the light, and therefore, the possibility of surprise the worker is low. Therefore, the degree of danger is also reduced for such objects.

  FIG. 5 is a diagram for explaining a second example of an object whose risk is to be lowered. In general, even if an object moving away from the worker suddenly enters the field of view, it is considered that the degree of surprise of the worker is small compared to the approaching object. Therefore, the risk of the object moving away from the worker is reduced.

  As shown in FIG. 5, for example, as shown in FIG. 5, whether or not the worker moves away from the worker is determined by the angle formed by the vector that starts from the worker W and extends in the direction of the end point of the movement vector of the object, and the movement vector of the object. Determined by angle. That is, if the angle is larger than a predetermined value, it is assumed that the user is moving in the direction approaching the worker W, and if the angle is smaller than the predetermined value, the user is moving in a direction away from the worker W. .

  In the example of FIG. 5, the angle formed by the vector extending from the worker W in the direction of the end point of the movement vector of the object A and the movement vector of the object A is ∠βa. Further, the angle formed by the vector that extends from the worker W in the direction of the end point of the movement vector of the object B and the movement vector of the object B is ∠βb. If the predetermined value is 90 degrees, the danger level of the object B is lowered.

  Even if the object moves in the direction of approaching the worker, it is considered that there is a low possibility that the worker will be surprised if the object approaches slowly. Therefore, the risk of such an object may be lowered by changing a predetermined value that is a threshold value for ∠βa, ∠βb, and the like. Further, whether or not the worker W is approached may be determined by a method other than the method shown in FIG. For example, it may be determined by the distance between the position of the worker W and the start point and end point of the movement vector of the object. If the information on the distance between the end point of the movement vector of the object and the position of the worker W is longer than the distance between the start point of the movement vector of the object and the position of the worker W, the object is determined to move away from the worker. May be. If the report of the distance between the end point of the movement vector of the object and the position of the worker W is shorter than the distance between the start point of the movement vector of the object and the position of the worker W, the object is determined to approach the worker. May be.

  Further, in the present embodiment, the object as shown in FIG. 6 is not reduced in risk level, but is excluded from the candidates for the object requiring attention in the first place.

  FIG. 6 is a diagram for explaining an example of an object that is excluded from candidates for an object requiring attention.

  FIG. 6A shows that the worker W has seen the left side immediately before the time point t1. At this time, the visual field V0 of the worker W is formed by the line-of-sight direction dr0, the boundary line bL0, and the boundary line bR0. (B) shows a diagram in which the landscape of the visual field V0 is projected on the projection plane in the line-of-sight direction dr0.

  Thereafter, at the time point t1, the worker W is rotated rightward by an angle α2 as shown in FIG. Therefore, the visual field V1 of the worker W at the time point t1 is formed by the line-of-sight direction dr1, the boundary line bL1, and the boundary line bR1. (C) shows a view in which the landscape of the visual field V1 is projected on the projection plane in the line-of-sight direction dr1.

  Furthermore, at the time point t2, the worker W is rotated leftward by an angle α3 as shown in FIG. Accordingly, the visual field V2 of the worker W at the time point t2 is formed by the line-of-sight direction dr2, the boundary line bL2, and the boundary line bR2. FIG. 4D shows a view in which the landscape of the visual field V2 is projected on the projection surface in the line-of-sight direction dr2.

  Note that the rectangle of each object indicates the position immediately before the time point t1, and the end point of the movement vector indicates the position at the time point t2.

  Here, when the visual field V1 at the time point t1 and the visual field V2 at the time point t2 are compared, the visual field V2 newly includes objects D and E. However, the objects D and E are included in the visual field V0 immediately before the time point t1. That is, the objects D and E are visually recognized by the worker W before the time t2. Then, it is considered that the worker W expects the objects D and E to be included in the field of view when changing the direction in the line-of-sight direction dr3. The occurrence of the expected situation is considered unlikely to surprise the worker W. Therefore, in the present embodiment, even if the in-view angle of the objects D and E exceeds the predetermined value, the objects D and E are excluded from the candidates for the objects requiring attention.

  Note that the object described with reference to FIG. 4 or FIG. 5 may not be reduced in risk level, but may be excluded from candidates for the object requiring attention. Alternatively, as described with reference to FIG. 6, the object may not be excluded from the candidates for the object requiring attention, but the risk level may be lowered.

  A specific example of the detection apparatus 10 that executes processing for detecting an object requiring attention by the above method will be described.

  FIG. 7 is a diagram illustrating a hardware configuration example of the detection device according to the present embodiment. The detection device 10 in FIG. 7 includes a drive device 100, an auxiliary storage device 102, a memory device 103, a CPU 104, an interface device 105, a display device 106, an input device 107, and the like that are mutually connected by a bus B.

  A program that realizes processing in the detection apparatus 10 is provided by the recording medium 101. When the recording medium 101 on which the program is recorded is set in the drive device 100, the program is installed from the recording medium 101 to the auxiliary storage device 102 via the drive device 100. However, the program need not be installed from the recording medium 101 and may be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program and also stores necessary files and data.

  The memory device 103 reads the program from the auxiliary storage device 102 and stores it when there is an instruction to start the program. The CPU 104 realizes functions related to the detection device 10 in accordance with a program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network. The display device 106 displays a GUI (Graphical User Interface) or the like by a program. The input device 107 is a keyboard, a mouse, or the like, and is used for inputting various operation instructions.

  An example of the recording medium 101 is a portable recording medium such as a CD-ROM, a DVD disk, or a USB memory. An example of the auxiliary storage device 102 is an HDD (Hard Disk Drive) or a flash memory. Both the recording medium 101 and the auxiliary storage device 102 correspond to computer-readable recording media.

  FIG. 8 is a diagram illustrating a functional configuration example of the detection device according to the present embodiment. In FIG. 8, the detection apparatus 10 includes a time progression unit 11, a group identification unit 12, a positional relationship determination unit 13, a condition determination unit 14, a risk determination unit 15, and an output unit 16. Each of these units is realized by processing executed by the CPU 104 by a program installed in the detection apparatus 10.

  The detection apparatus 10 also uses an operator information table storage unit 21, an object information table storage unit 22, an object state table storage unit 23, a result information storage unit 24, and the like. Each of these storage units can be realized by using the auxiliary storage device 102 or a storage device connected to the detection device 10 via a network.

  With the above configuration, the detection apparatus 10 performs a simulation according to the passage of time for changes in the position and line-of-sight direction of the worker W, changes in the position of the object, and the like, and for each object, for each time in the simulation space. Judgment is made as to whether or not the object needs attention. As a result, an object requiring attention is detected.

  The worker information table storage unit 21 stores a worker information table 21T. In the worker information table 21T, information indicating the time series position and the time series line-of-sight direction of the worker W is set.

  FIG. 9 is a diagram illustrating a configuration example of the worker information table. As shown in FIG. 9, each record in the worker information table 21T includes items such as time, position X, position Y, and line-of-sight direction. The time is the time in the simulation space. The time of each record is made into the fixed interval, and each record is memorize | stored in order of time. In this embodiment, the time point of 0 seconds is set as the start time (reference time point), and the unit time is set to 1 second. That is, the simulation space advances in 1 second increments. The position X and the position Y are examples of information indicating the position of the worker W at the time indicated by the time. That is, the position X and the position Y indicate the X coordinate value or the Y coordinate value in the simulation space. The coordinate value is a coordinate value in a coordinate system defined in the simulation space. In the present embodiment, the simulation space is defined as a two-dimensional space as shown in FIG. In FIG. 1A, the horizontal direction is the X axis and the vertical direction is the Y axis.

  The line-of-sight direction indicates the line-of-sight direction of the worker W at the time indicated by the time. The gaze direction is expressed by an angle. 90 degrees is parallel to the Y axis and is the positive direction of the Y axis (upward in FIG. 1A). 0 degrees is parallel to the X axis and is the direction of the positive direction of the X axis (rightward in FIG. 1A). The line-of-sight direction may be expressed by a unit vector, for example.

  The contents of the worker information table 21T are set in advance as simulation conditions. Note that the information indicating the position of the worker may be expressed by a movement vector from a position one unit time before. In this case, the worker information table 21T may store the positions X and Y of the worker at the start time and the movement vector for each time.

  The object information table storage unit 22 stores an object information table 22T for each object. Information indicating the time-series position and the time-series movement direction of the object corresponding to the object information table 22T is set in the object information table 22T.

  10 to 13 are diagrams illustrating configuration examples of the object information table. Each record of the object information table 22T includes items such as time, position X, position Y, movement vector X, movement vector Y, and the like. The time is the time in the simulation space. The time axis regarding the time of each object information table 22T and the worker information table 21T is common.

  The position X and the position Y are examples of information indicating the position of the object at the time indicated by the time. That is, the position X and the position Y indicate the X coordinate value or the Y coordinate value in the simulation space. The movement vector X and the movement vector Y are the X component or Y component of the movement vector. The length of the movement vector indicates a movement distance per unit time (1 second in the present embodiment). 10 corresponds to the object A, the object B, the object C, and the object D, respectively. The contents of the object information table 22T are set in advance as simulation conditions.

  In the object information table 22, any one of the positions X and Y and the movement vectors X and Y may be omitted. That is, the movement vectors X and Y may be used as information indicating the position of the object. In this case, if the positions X and Y of the start time are stored, the position of the object at each time can be specified. Further, even if the movement vectors X and Y are not stored, the movement vectors having the positions X and Y as the end points and the positions X and Y after one unit time may be specified.

  FIG. 14 is a diagram showing the movement history of the worker and each object in the present embodiment. That is, FIG. 14 represents the contents of the worker information table 21T of FIG. 9 and the object information table 22T of FIGS. 10 to 13 on a two-dimensional coordinate system (simulation space).

  In FIG. 14, the position of the worker W or each object is represented by a circle. In the circle, alphabets A to D or W and numerical values are described. Circles with A to D indicate the positions of objects identified by the alphabet. That is, the circle on which A is written indicates the position of the object A. A circle on which W is written indicates the position of the worker W. The numerical value in the circle indicates the time in seconds. For example, a circle described as “D0” indicates the position of the object D at time 0. A circle described as “W0-2” indicates the position of the worker W from time 0 to time 2.

  The object state table storage unit 23 stores an object state table 23T. The object state table 23T stores the state of the object at the time (time) according to the progress of the time in the simulation space.

  FIG. 15 is a diagram illustrating an example of an initial state of the object state table. The object state table 23T stores a record for each object. Each record includes items such as a number, an object name, a field-of-view time, a group number, shape data, a movement vector X, a movement vector Y, and the presence / absence of issuing / reporting.

  The number is an identification number of the object. The object name is an identification name of the object. The in-view time is the accumulated time that the object was included in the worker W's view. As the in-view time, 0 is stored as an initial value. The group number is an effective item when the object belongs to the object group, and is an identification number of the object group to which the object belongs. An object group refers to an object group that moves on the same route or trajectory at regular intervals. The shape data is data indicating the shape of the object. In FIG. 9, the shape data is described in a format of vertical × horizontal × height, but the shape data may be, for example, a link to two-dimensional CAD data or three-dimensional CAD data. The movement vectors X and Y are the X component or Y component of the movement vector of the object at a time one unit time before. The presence / absence of light emission / report is the presence / absence of light emission / report. Luminescence means blinking at regular intervals. Alerting means issuing a warning sound or the like at a constant rhythm. The value of the presence / absence of light emission / firing is set in advance. In the example of FIG. 15, the object A related to the object name A emits light.

  The result information storage unit 24 stores, for an object determined to be a cautionary object, the time when the object becomes a cautionary object, a degree of danger, and the like.

  The time advancer 11 advances the time in the simulation space. The group specifying unit 12 specifies an object group that constitutes a group of objects from the objects whose object information table 22T is stored in the object information table storage unit 22. That is, the group specifying unit 12 specifies an object group having a relationship such as the objects F1 to F4 in FIG.

  The positional relationship determination unit 13 determines whether each object is included in the field of view of the worker W at each time based on the object information table 22T and the worker information table 21T of each object. That is, the positional relationship determination unit 13 detects a candidate for a cautionary object.

  The condition determination unit 14 determines whether or not the relative positional relationship between the object determined to be included in the field of view and the field of view of the worker W satisfies a predetermined condition for each time. Specifically, the condition determination unit 14 determines whether or not the in-view angle of each object is larger than a predetermined value when each object is included in the view for the first time. That is, the condition determination unit 14 determines whether or not the object included in the field of view is a cautionary object. In other words, the condition determining unit 14 detects an object requiring attention from among objects included in the field of view.

  The degree-of-risk determination unit 15 determines the degree of risk for an object that has been determined to be an object requiring attention. The determined risk is associated with the object identification information and stored in the result information storage unit 24. The output unit 16 outputs information stored in the result information storage unit 24.

  Hereinafter, a processing procedure executed by the detection apparatus 10 will be described. FIG. 16 is a flowchart for explaining an example of a processing procedure executed by the detection apparatus.

  In step S101, the group specifying unit 12 performs a group specifying process. In the group specifying process, as in the objects F1 to F4 in FIG. 4, an object group that moves on the same route or trajectory at regular intervals is specified as an object belonging to the same object group. The processing result of step S101 is stored in the object state table 23T.

  FIG. 17 is a diagram illustrating an example of an object state table in which a result of the group specifying process is reflected. In step S101, the same group number is stored for objects determined to belong to the same object group. In FIG. 17, group number 1 is stored in object C and object D. That is, FIG. 17 illustrates an example in which it is determined that the object C and the object D belong to the same object group. Referring to FIG. 14, it can be seen that the object D moves along the same route as the object C with a delay of 1 second from the object C. Details of the group specifying process will be described later.

  Subsequently, the time progression unit 11 assigns 0 to the variable Time (S102). That is, the time in the simulation space is set to zero. Hereinafter, the value of the variable Time is simply referred to as “Time”. Subsequently, the positional relationship determination unit 13 acquires the values of the position X, the position Y, and the line-of-sight direction of the worker W from the worker information table 21T (FIG. 9) at the time point (S103).

  Subsequently, the positional relationship determination unit 13 specifies the visual field in the simulation space of the worker W (S104). For example, a range of angles that are symmetric with respect to the worker's line-of-sight direction with the worker W's position as the center is specified as the field of view of the worker W.

  Subsequently, the positional relationship determination unit 13 assigns 1 to the object No. that is a variable (S105). That is, the object A having the number 1 stored in the object state table 23T is set as a processing target. Hereinafter, the object specified by the value of the object number is referred to as “target object”.

  Subsequently, the positional relationship determination unit 13 acquires the positions X and Y at the time point and the movement vectors X and Y from the object information table 22T of the target object. (S106). Subsequently, the positional relationship determination unit 13 determines whether or not the target object is included in the visual field of the worker W (S107). The determination may be made based on whether or not the visual field specified in step S104 includes a point specified by the positions X and Y of the target object acquired in step S106. Alternatively, shape data stored in the object state table 23T may be used. That is, whether or not at least part of the shape data is included in the visual field when the reference point (for example, the center of gravity) of the shape data of the target object is located at the position X and Y of the target object acquired in step S106. May be determined.

  When it is determined that at least a part of the target object is included in the field of view (Y in S107), the condition determination unit 14 calculates the in-field angle of the target object (S108). For the calculation of the in-field angle, it is only necessary to use the boundary line that the target object crosses last, out of the two boundary lines forming the field of view. That is, an angle between the boundary line and a straight line connecting the current position of the target object and the current position of the worker W may be calculated. If the target object has not crossed any boundary line in the past, that is, if it is included in the field of view from the beginning, any boundary line may be used, and the in-view angle may not be calculated Good. Note that whether or not the target object crosses the boundary line may be determined based on whether or not the movement vector of the target object up to the present intersects the boundary line.

Subsequently, the condition determination unit 14 determines whether or not all of the following three conditions (1) to (3) are satisfied (S109).
(1) Time is greater than zero.
(2) The visual field angle is larger than a predetermined value.
(3) The in-view time corresponding to the target object is 0 in the object state table 23T.

  The above conditions are conditions for determining whether the target object is a cautionary object. The condition (1) is a condition for preventing the object included in the visual field from the beginning from being included in the object requiring attention. Since an object included in the field of view from the beginning does not cause a situation in which the field of view suddenly enters the field of view, it is unlikely that the worker W will be surprised. Therefore, in step S108, the in-view angle does not have to be calculated for the object included in the view from the beginning.

  As described with reference to FIGS. 1 and 2, the condition (2) is a condition for limiting an object that is determined as an object requiring attention to an object in which the in-view angle of the target object exceeds a predetermined value. In step S107, the visual field is specified based on the visual field direction at the time point of the worker W, and in step S108, the visual field angle is calculated with respect to the visual field. As a result, the contents described in FIG. 2 are also realized.

  The condition (3) is a condition for preventing an object that has only passed for a short time since entering the visual field in the past from being included in the object requiring attention. In other words, the condition (3) is a condition for limiting an object requiring attention to an object that has entered the field of view for the first time, or an object that has been in the field of view in the past, but has passed for a long time. is there. That is, the condition (3) is a condition for realizing the contents described in FIG.

  The in-view time is a parameter indicating the accumulated time that the target object was included in the view. In this embodiment, since it is determined whether or not it is included in the field of view at each time, it can be said that the time in the field of view is the cumulative number of times that the target object is determined to be included in the field of view. However, regarding the period not included in the field of view, the time in the field of view is decremented (decreased) by that period. Also, the in-view time does not become less than zero. Therefore, when the in-view time of the target object is 0, the number of times or the period when the target object is determined to be included in the view field and the target object is not included in the view field when the in-view time is 1 or more. This is a case where the number of times or the period determined to match.

  When Step S109 is first executed for the target object, Time is 0, so at least the condition (1) is not satisfied (N in S109). Therefore, step S110 is not executed, and the process proceeds to step S111.

  In step S111, the condition determination unit 14 counts up the in-view time in the object state table 23T for the target object. That is, 1 is added to the in-view time. This is because it is determined in step S107 that the target object is included in the field of view at the time point Time. Subsequently, the condition determination unit 14 transfers the values of the movement vectors X and Y with respect to the time point in the object information table 22T of the target object to the movement vectors X and Y of the record with respect to the target object in the object state table 23T (S112). ).

  On the other hand, if it is determined in step S107 that the target object is not included in the field of view (N in S107), the condition determination unit 14 counts down the time in the field of view in the object state table 23T for the target object (S113). That is, 1 is subtracted from the in-view time. However, when the in-view time is 0, the countdown is not executed. This is because the in-view time does not become less than 0 in the present embodiment.

  For example, for an object with a field-of-view time of 1, if the field-of-view time is counted down once, the field-of-view time becomes zero. Therefore, when step S109 is executed for the object regarding the next time point, the condition of step S109 may be satisfied. On the other hand, for an object whose in-view time is 3, for example, the in-view time does not become zero unless the count-down of the in-view time is performed three times in succession.

  Due to the fact that the time in the field of view is manipulated in this way and the condition (3) in step S109, the object that has entered the field of view in the past has been in the field of view for the same period as that in the field of view. If no state continues, it can be determined that the object needs attention. Thereby, the idea that the elapsed time until the worker W forgets the existence of the object will be longer as the period when the worker W visually recognizes becomes logic. Specifically, the idea that the worker W will forget about the existence of the object seen for a moment and will remember for a long time about the existence of the object seen for a long time is logicalized. Yes.

  Subsequent to step S113, step S112 is executed.

  When the value of the object No is less than the number of the last object (here, the object D) (N in S115), the positional relationship determination unit 13 adds 1 to the object No (S114), and steps S106 and after are performed. repeat. That is, steps S106 to S115 are executed for all objects (objects A to D in the present embodiment) with respect to one time point.

  When the execution of steps S106 to S115 is completed for all objects with respect to Time = 0, the object state table 23T is in a state as shown in FIG. 18, for example.

  FIG. 18 is a diagram illustrating an example of the object state table at the time of completion of the process regarding Time = 0. In FIG. 18, the in-view time is updated for the objects A and C. This is because it is determined that the objects A and C are included in the field of view of the worker W at Time = 0. In addition, regarding the objects A to D, the movement vectors X and Y with respect to Time = 0 are transferred from the respective object information tables 22T.

  Subsequently, the time progression unit 11 adds 1 to the variable Time (S116). Subsequently, Step S106 and subsequent steps are executed for Time = 1. When execution of Steps S106 to S115 is completed for all objects with respect to Time = 1, the object state table 23T is in a state as shown in FIG. 19, for example.

  FIG. 19 is a diagram illustrating an example of the object state table at the time of completion of the process related to Time = 1 time point. In FIG. 19, the in-view time is updated for the objects A, C, and D. That is, the objects A and C are included in the field of view following Time = 0, so the in-view time is updated to 2. In addition, since the object D is included in the visual field for the first time at Time = 1, the time in the visual field is updated to 1. Further, regarding the objects A to D, movement vectors X and Y with respect to Time = 1 time point are transferred from the respective object information tables 22T.

  By the way, when Time = 1, the condition (1) is satisfied in step S109. There may also be an object that satisfies the conditions (2) and (3). When all of the conditions (1) to (3) are satisfied for the target object (Y in S109), the risk determination process is executed in step S110.

  FIG. 20 is a flowchart for explaining an example of a processing procedure of the risk determination processing.

  In step S201, the risk determination unit 15 acquires shape data corresponding to the target object from the object state table 23T. Note that the target object refers to an object specified by the object No when step S110 of FIG. 16 is executed.

  Subsequently, the risk determination unit 15 generates a two-dimensional projection figure when the shape data of the target object is projected on the projection plane in the sight line direction of the worker W at the time of time (S202). That is, a graphic indicating the shape of the target object that can be seen by the worker W is generated. For generating such a two-dimensional figure, for example, a known technique used in a three-dimensional CAD system or the like may be used.

  Subsequently, the risk determination unit 15 calculates an aspect ratio (horizontal / vertical) for the minimum circumscribed rectangle of the generated two-dimensional figure (S203). Subsequently, the risk determination unit 15 determines whether the area of the two-dimensional graphic is larger than a predetermined value, whether the aspect ratio is larger than a predetermined value, or whether the two-dimensional graphic has an acute angle portion (S204). If any one of the conditions is satisfied (Y in S204), the risk determination unit 15 increases the risk for the target object (S205). That is, the contents described in FIG. 3 are realized. In the present embodiment, it is assumed that the initial value of the risk is 1. This is because the probability of being an object requiring attention is recognized at the time when the risk is determined. The degree of increase in the degree of risk in step S205 may be increased as the number of satisfied conditions increases, or may be uniform regardless of the number of satisfied conditions. Further, even in a uniform case, the increase width may not be 1.

  In the case of N in step S208 or subsequent to step S209, the risk determination unit 15 acquires the movement vectors X and Y stored for the target object in the object state table 23T (S206). The movement vector is a movement vector for a time point one unit time before the Time point (Time-1 point). Hereinafter, the movement vector is referred to as a “previous movement vector” in order to distinguish it from the movement vector corresponding to the Time point.

  Subsequently, the risk determination unit 15 calculates an angle formed by the previous movement vector and a vector related to an angle direction indicating the line-of-sight direction at the time point of the worker W (S207). Subsequently, the risk determination unit 15 determines whether or not the angle is larger than a predetermined value (S208). When the angle is larger than the predetermined value (Y in S208), the risk determination unit 15 increases the risk (S209). That is, the contents described in FIG. 5 are realized. Note that the degree of increase in the degree of danger may vary depending on the size of the angle. For example, the degree of increase may be increased as the angle increases.

  In the case of N in Step S208 or following Step S209, the risk determination unit 15 determines whether or not light emission or notification is stored for the target object in the object state table 23T (S210). When the light emission or the notification is stored, the risk determination unit 15 decreases the risk (S211). The decrease may be 1 or greater than 1.

  In the case of N in step S210 or following step S211, the risk determination unit 15 determines whether or not a group number is stored for the target object in the object state table 23T (S212). When the group number is stored (Y in S212), the risk determination unit 15 decreases the risk (S213). The decrease may be 1 or greater than 1. Alternatively, any value of the current risk level may be reduced to zero. When the degree of risk is reduced to 0, the object group that moves at regular intervals is substantially excluded from the detection target of the object requiring attention.

  In the case of N in Step S212 or following Step S213, the risk determination unit 15 stores the risk in the result information storage unit 24 in association with the object name and Time of the target object (S212).

  FIG. 21 is a diagram illustrating a configuration example of the result information storage unit. As shown in FIG. 21, the result information storage unit 24 stores an object name, an occurrence time, and a risk level for each object determined to satisfy the conditions (1) to (3) in step S109 of FIG. To do. That is, information indicating when and how dangerous an object is generated is stored. Note that Time is stored as the occurrence time.

  FIG. 21 shows a state at the completion of the process related to Time = 1. That is, at Time = 1, it is determined that the object D is a cautionary object. However, the group number is stored in the object D in the object state table 23T. Therefore, the risk is set to 0.

  Subsequently, when the execution of Steps S106 to S115 is completed for all objects with respect to Time = 2, the object state table 23T is in a state as shown in FIG. 22, for example.

  FIG. 22 is a diagram illustrating an example of the object state table at the time of completion of the process regarding the time = 2. In FIG. 22, the in-view time is updated for the objects A to D. That is, since the objects A and C are continuously included in the field of view from Time = 0, the in-field time is updated to 3. In addition, since the object D is included in the field of view following Time = 1, the in-field time is updated to 2. In addition, since the object B is included in the visual field for the first time at Time = 2, the time in the visual field is updated to 1. Further, regarding the objects A to D, the movement vectors X and Y with respect to Time = 2 are transferred from the respective object information tables 22T.

  Further, with respect to Time = 2, the result information storage unit 24 at the time when execution of Steps S106 to S115 is completed for all objects is in a state as shown in FIG. 23, for example.

  FIG. 23 is a diagram illustrating an example of the result information storage unit at the time of completion of the process regarding Time = 2. At Time = 2, the object B is newly detected as an object requiring attention. Therefore, a record including the object name and the danger level of the object B is newly added with Time = 2 as the occurrence time.

  Subsequently, when execution of steps S106 to S115 is completed for all objects at the time point of Time = 3, the object state table 23T is in a state as shown in FIG. 23, for example.

  FIG. 24 is a diagram illustrating an example of the object state table at the time of completion of the processing related to Time = 3. In FIG. 24, the in-view time is updated for the objects A to D. That is, since the objects A and C are continuously included in the field of view from Time = 0, the in-view time is updated to 4. Since the object B is included in the field of view subsequent to Time = 2, the time in the field of view is updated to 4. Since the object D is no longer included in the field of view, the time in the field of view is reduced to 1.

  In the object state table 23T at Time = 2, there is no object whose in-view time is zero. Therefore, an object requiring attention is not detected in the processing related to Time = 3.

  Subsequently, when the execution of Steps S106 to S115 is completed for all the objects at Time = 4, the object state table 23T is in a state as shown in FIG. 25, for example.

  FIG. 25 is a diagram illustrating an example of the object state table at the time of completion of the process relating to Time = 4. In FIG. 25, the in-view time is updated for the objects A to D. That is, since the objects A and C are continuously included in the field of view from Time = 0, the in-view time is updated to 5. Since the object B is continuously included in the field of view from Time = 2, the time in the field of view is updated to 3. Since the object D is included in the field of view again, the time in the field of view is updated to 2.

  In the object state table 23T at Time = 3, there is no object whose in-view time is zero. Therefore, an object requiring attention is not detected in the processing related to Time = 4.

  When Time exceeds the end time (Y in S117), the output unit 16 outputs information stored in the result information storage unit 24 (S118). The end time is the last time among the times stored in the work information table or the object information table 22T of each object. The user can refer to the output information and confirm which object is the object requiring attention at which timing. The output form is not limited to a predetermined one such as storage in the display device 106, the auxiliary storage device 102, or printing on a printer (not shown).

  Next, details of step S101 in FIG. 16 will be described. FIG. 26 is a flowchart for explaining an example of the process procedure of the group specifying process.

  In step S301, the group identification unit 12 substitutes 0 for the variable Time. Hereinafter, the value of the variable Time is simply referred to as “Time”. Subsequently, the group specifying unit 12 substitutes 1 for the object No (S302). Hereinafter, the object specified by the value of the object number is referred to as “target object”.

  Subsequently, the group specifying unit 12 acquires the positions X and Y at the time point and the movement vectors X and Y from the object information table 22T of the target object. (S303). Subsequently, the group specifying unit 12 searches the object information table 22T of each object other than the target object for records in which the positions X and Y and the movement vector match the positions X and Y and the movement vector acquired in step S303. (S304). The corresponding record may be searched from a plurality of object information tables 22T.

  If the corresponding record is not searched (N in S305), the process proceeds to step S310. When the corresponding record is searched (Y in S305), the group specifying unit 12 calculates the time difference between the time of the searched record and Time (S306). Subsequently, the group specifying unit 12 reads the data of each record in the object information table 22T to which the searched record belongs, and shifts the time of each read data by the time difference (S307). That is, when the time difference indicates that it is behind Time, the time difference is subtracted from the time of each data. On the other hand, when the time difference indicates that it is ahead of Time, the time difference is added to the time of each data. The searched object related to the object information table 22T belonging to the record card is hereinafter referred to as “candidate object”.

  Subsequently, the group specifying unit 12 matches the position X and Y and the movement vectors X and Y with the record related to the same time in the object information table 22T of the target object for each candidate object data after the time is shifted. It is determined whether or not to perform (S308).

  When all the data of the candidate object and the record of the object information table 22T of the target object match with respect to the positions X and Y and the movement vectors X and Y (Y in S308), the group specifying unit 12 determines that the target object and the candidate object Is set to the same group number in the object state table 23T (S309). That is, it is determined that the target object and the candidate object are object groups belonging to the same group.

  Steps S306 to S309 are executed for each object other than the target object for which the corresponding record is searched in step S304.

  When the value of the object No is less than the number of the last object (here, object D) (N in S310), the group specifying unit 12 adds 1 to the object No (S311), and repeats step S303 and subsequent steps. . That is, steps S303 to S310 are executed for all objects (in the present embodiment, objects A to D) with respect to one time point.

  When execution of Steps S303 to S310 is completed for all objects at the Time point (Y in S310), the group specifying unit 12 adds 1 to the variable Time (S312). If Time is less than or equal to the end time (N in S313), Step S302 and subsequent steps are repeated. If Time exceeds the end time (Y in S313), the process in FIG. 26 ends.

  As described above, according to the present embodiment, it is possible to support identification of an object that may induce a worker's danger.

  In the present embodiment, the in-view angle is used to determine whether or not the object is a cautionary object. Instead of the in-view angle, for example, the boundary line of the view that the object crosses last and the object (Hereinafter referred to as “in-view distance”) may be used. In this case, the threshold for the in-view distance may be changed according to the distance between the worker W and the object. That is, the threshold may be reduced for an object close to the worker W.

  Further, even when the in-view angle is used, the threshold for the in-view angle may be changed according to the distance between the worker W and the object. That is, the threshold may be reduced for an object close to the worker W.

  Further, the threshold for the in-view angle or the in-view distance may be changed depending on a factor that increases or decreases the degree of risk. That is, the threshold value may be decreased for an object with a high degree of danger, and the threshold value may be increased with respect to an object with a low degree of risk. In this case, the process of FIG. 26 may be executed before the condition determination in step S109 of FIG. The threshold value (predetermined value) to be compared with the in-field angle or the in-field distance may be changed in step S109 according to the risk level output by the processing of FIG.

  In addition, for example, attribute information such as experience level, skill level, or age is stored in the auxiliary storage device 102 or the like for each worker W, and a threshold value for an in-view angle or an in-view distance is determined based on the attribute information. May be changed. For example, the threshold value may be increased for the worker W having a high experience level or skill level. Moreover, an elderly person may make a threshold value small.

  In the present embodiment, for convenience, the description has been given using the two-dimensional simulation space, but a three-dimensional simulation space may be used. In this case, the position information and the line-of-sight direction information in the worker information table 21T, the position information in the object information table 22T, the movement vector information, and the like may be three-dimensional information. The field of view of the worker W may be defined by, for example, a cone, an elliptical cone, or a pyramid having the worker W as the apex and having a height in the viewing direction.

  In the present embodiment, the positional relationship determination unit 13 is an example of a determination unit. The condition determination unit 14 is an example of a detection unit.

  As mentioned above, although the Example of this invention was explained in full detail, this invention is not limited to such specific embodiment, In the range of the summary of this invention described in the claim, various deformation | transformation・ Change is possible.

Regarding the above description, the following items are further disclosed.
(Appendix 1)
The position information indicating the position of the object at each predetermined time point, the position information indicating the worker's position at each predetermined time point, and the gaze direction information indicating the direction of the line of sight are specified, and the visual field of the worker Whether or not the object is included in
A cautionary object detection program that causes a computer to execute processing for detecting an object that satisfies a predetermined positional relationship between a position of the object and the visual field among objects determined to be included in the visual field.
(Appendix 2)
The non-requiring object detection program according to appendix 1, wherein the predetermined condition is that an angle of the position of the object with respect to a boundary line of the visual field of the worker when the position of the worker is set as a center exceeds a predetermined value.
(Appendix 3)
The detection process includes a first cumulative number of times that the object is determined to be included in the visual field, and the first cumulative number of times that is determined to be included in the visual field. In this case, the second cumulative number of times that the object is determined not to be included in the field of view coincides, and the relative positional relationship between the position of the object and the field of view detects an object that satisfies a predetermined condition. The program for detecting a cautionary object described in 1 or 2.
(Appendix 4)
The non-cautionary object detection program according to any one of supplementary notes 1 to 3, wherein the predetermined condition is changed according to a distance between the position of the worker and the position of the object.
(Appendix 5)
The non-cautionary object detection program according to any one of supplementary notes 1 to 4, wherein the predetermined condition is changed according to a shape or a size of the object.
(Appendix 6)
The non-cautionary object detection program according to any one of supplementary notes 1 to 5, wherein the predetermined condition is changed according to the attribute information of the worker.
(Appendix 7)
The position information indicating the position of the object at each predetermined time point, the position information indicating the worker's position at each predetermined time point, and the gaze direction information indicating the direction of the line of sight are specified, and the visual field of the worker A determination unit for determining whether the object is included in
A detection device that includes a detection unit that detects an object that is determined to be included in the field of view and that satisfies a predetermined condition of a relative positional relationship between the position of the object and the field of view.
(Appendix 8)
The detection apparatus according to claim 7, wherein the predetermined condition is that an angle of the position of the object with respect to a boundary line of the visual field of the worker when the position of the worker is set as a center exceeds a predetermined value.
(Appendix 9)
The detection unit includes a first cumulative number of times that the object is determined to be included in the visual field, and a first cumulative number that is determined to be included in the visual field, and the first cumulative number is 1 or more. Note 7 is that the second cumulative number of times that the object is determined not to be included in the field of view matches the object, and the relative positional relationship between the position of the object and the field of view satisfies a predetermined condition. Or the detection apparatus of 8.
(Appendix 10)
The detection apparatus according to any one of appendices 7 to 9, wherein the predetermined condition is changed according to a distance between the position of the worker and the position of the object.
(Appendix 11)
The detection device according to any one of appendices 7 to 10, wherein the predetermined condition is changed according to a shape or a size of the object.
(Appendix 12)
The detection device according to any one of appendices 7 to 11, wherein the predetermined condition is changed according to the attribute information of the worker.
(Appendix 13)
The position information indicating the position of the object at each predetermined time point, the position information indicating the worker's position at each predetermined time point, and the gaze direction information indicating the direction of the line of sight are specified, and the visual field of the worker Whether or not the object is included in
A detection method in which a computer executes a process of detecting an object in which a relative positional relationship between the position of the object and the visual field satisfies a predetermined condition among objects determined to be included in the visual field.
(Appendix 14)
The detection method according to appendix 13, wherein the predetermined condition is that an angle of the position of the object with respect to a boundary line of the visual field of the worker when the position of the worker is set as a center exceeds a predetermined value.
(Appendix 15)
The detection process includes a first cumulative number of times that the object is determined to be included in the visual field, and the first cumulative number of times that is determined to be included in the visual field. In this case, the second cumulative number of times that the object is determined not to be included in the field of view coincides, and the relative positional relationship between the position of the object and the field of view detects an object that satisfies a predetermined condition. The detection method according to 13 or 14.
(Appendix 16)
The detection method according to any one of supplementary notes 13 to 15, wherein the predetermined condition is changed according to a distance between the position of the worker and the position of the object.
(Appendix 17)
The detection method according to any one of supplementary notes 13 to 16, wherein the predetermined condition is changed according to a shape or a size of the object.
(Appendix 18)
The detection method according to any one of supplementary notes 13 to 17, wherein the predetermined condition is changed according to the attribute information of the worker.

DESCRIPTION OF SYMBOLS 10 Detection apparatus 11 Time progress part 12 Group specific | specification part 13 Positional relationship determination part 14 Condition determination part 15 Risk degree determination part 16 Output part 21 Worker information table storage part 22 Object information table storage part 23 Object state table storage part 24 Result information Storage unit 100 Drive device 101 Recording medium 102 Auxiliary storage device 103 Memory device 104 CPU
105 interface device 106 display device 107 input device B bus

Claims (8)

The position information indicating the position of the object at each predetermined time point, the position information indicating the worker's position at each predetermined time point, and the gaze direction information indicating the direction of the line of sight are specified, and the visual field of the worker Whether or not the object is included in
Among the is determined to be included in the operator's field of view the object, the relative positional relationship between the position and the operator's visual field of the object body meets a predetermined condition, not included in the visual field of the operator Detecting an object that has changed from a state to a state included in the field of view of the operator ;
Body detection program those for executing the process to the computer. The position information indicating the position of the object at each predetermined time point, the position information indicating the worker's position at each predetermined time point, and the gaze direction information indicating the direction of the line of sight are specified, and the visual field of the worker Whether or not the object is included in
Among the objects determined to be included in the field of view, the computer executes processing for detecting an object in which the relative positional relationship between the position of the object and the field of view satisfies a predetermined condition,
The predetermined condition is that the worker said object by angular position exceeds the predetermined value is those body detecting program of relative to the operator's field of view border when the position around the. The position information indicating the position of the object at each predetermined time point, the position information indicating the worker's position at each predetermined time point, and the gaze direction information indicating the direction of the line of sight are specified, and the visual field of the worker Whether or not the object is included in
Among the objects determined to be included in the field of view, the computer executes processing for detecting an object in which the relative positional relationship between the position of the object and the field of view satisfies a predetermined condition,
The detection process includes a first cumulative number of times that the object is determined to be included in the visual field, and the first cumulative number of times that is determined to be included in the visual field. a second cumulative number of times the object is determined to not be included in the field of view matches if, those relative positional relationship between said the position of the object field to detect a predetermined condition is satisfied object Body detection program. Depending on the distance between the position of the position and the object of the worker claims 1 to 3 object body detection program according to any one claim changing the predetermined condition. According to the shape or size of the object, claim 1 to 4 object body detection program according to any one claim changing the predetermined condition. Depending on the attribute information of the operator, according to claim 1 to 5 to any one claim monoester detecting program changes the predetermined condition. The position information indicating the position of the object at each predetermined time point, the position information indicating the worker's position at each predetermined time point, and the gaze direction information indicating the direction of the line of sight are specified, and the visual field of the worker A determination unit for determining whether the object is included in
Among the is determined to be included in the operator's field of view the object, the relative positional relationship between the position and the operator's visual field of the object body meets a predetermined condition, not included in the visual field of the operator A detection unit that detects an object that has changed from a state to a state included in the field of view of the operator . The position information indicating the position of the object at each predetermined time point, the position information indicating the worker's position at each predetermined time point, and the gaze direction information indicating the direction of the line of sight are specified, and the visual field of the worker Whether or not the object is included in
Among the is determined to be included in the operator's field of view the object, the relative positional relationship between the position and the operator's visual field of the object body meets a predetermined condition, not included in the visual field of the operator A detection method in which a computer executes a process of detecting an object that has changed from a state to a state included in the field of view of the worker .

Images