Attention-calling system and attention-calling device

Abstract

To provide an attention-calling system and an attention-calling device that can call a worker's attention to an object or an operation target, thereby improving accuracy of confirmation work.SOLUTION: An attention-calling system 100 for calling worker's attention to an object acquires an object image 50 of the object 4 and setting information related to image-capturing of the object image 50, determines whether or not the object image 50 includes an attention-calling object image 51, sets coordinate information for the center of the attention-calling object image 51 and instruction information 6 that is variably displayed toward the center of the coordinate information based on the setting information if the object image 50 includes the attention-calling object image 51, and emits the coordinate information and the instruction information 6 using light beams.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an attention calling system and an attention calling device that call a worker's attention to an object. [Background technology]

[0002] 2. Description of the Related Art Conventionally, an X-ray imaging apparatus as disclosed in Patent Document 1 has been proposed as a method for specifying a location by irradiating an object with a laser beam.

[0003] The X-ray imaging device disclosed in Patent Document 1 aims to improve operability when setting the X-ray irradiation field and thereby shorten the examination time, and is equipped with an X-ray imaging means capable of X-ray imaging of a subject, a surface imaging means capable of imaging the surface of the subject including the X-ray irradiation field, and a display means capable of displaying the imaged surface image. The X-ray imaging means is equipped with a stereo X-ray tube that can irradiate X-rays toward the subject from different focal positions and two sets of apertures that can each limit the irradiation range of the X-rays from the focal positions, while the surface imaging means irradiates lasers toward the subject from laser markers arranged at two positions each conjugate to the focal positions, thereby forming a laser marker frame on the surface of the subject corresponding to the aperture opening, and is capable of imaging the surface image of the subject with this laser marker frame formed. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 06-217973 Summary of the Invention [Problem to be solved by the invention]

[0005] Currently, when a worker checks a device (e.g., a medical device) or its operation, the worker visually checks the object or operation location. Therefore, the results of the check may include check errors or oversights due to the installation status of the device, as well as the worker's skills and experience, raising concerns about insufficient attention during the check and operation. In this regard, with the technology disclosed in Patent Document 1, the laser marker frame is formed on the surface of a nearby object, making it impossible for the worker to identify the device or operation location that the worker should work on from among multiple objects, or to quickly confirm which direction to focus their gaze in. Given these circumstances, there is a demand for improved accuracy in the check of the device or operation location that the worker will be working on.

[0006] Therefore, the present invention has been devised in consideration of the above-mentioned problems, and its purpose is to provide an attention-warning system and an attention-warning device that can alert workers to objects or objects to be operated, thereby improving the accuracy of confirmation work. [Means for solving the problem]

[0007] The attention drawing system according to a first aspect of the present invention is an attention drawing system for drawing an operator's attention to an object, comprising: an acquisition means for acquiring an object image of the object and setting information related to capturing the object image; a determination means for determining whether the acquired object image includes an attention drawing object image; and, if the object image includes the attention drawing object image based on the determination result of the determination means, a coordinate information of the center of the attention drawing object image and an attention drawing to be displayed at the coordinate information and pointing toward the center of the coordinate information. and when the object image includes a plurality of attention-attracting object images, setting the coordinate information and instruction information with the highest priority, or setting the coordinate information and instruction information sequentially, based on at least one of the priority of the work linked to the plurality of attention-attracting object images, the skill of the worker, and the gaze direction of the worker; and light emitting means emitting the instruction information onto the coordinate information with a light beam based on the coordinate information and instruction information set by the setting means.

[0008] The warning system according to the second invention is characterized in that, in the first invention, the instruction information set by the setting means is an image having information regarding at least one of a cross image, an X-shaped image, and a graphic image, and is an image that is displayed variably as it moves away from the center of the coordinate information.

[0009] The attention warning system according to the third invention is characterized in that, in the first and second inventions, the instruction information set by the setting means includes guidance information that is spaced apart from the instruction information and variably displayed toward the center of the coordinate information.

[0010] The warning system according to the fourth invention is characterized in that, in any one of the first to third inventions, the instruction information and the guidance information set by the setting means are information having a format related to at least one of a color related to irradiated light and an irradiated light pattern.

[0011] The warning system according to the fifth invention is characterized in that, in any one of the first to third inventions, the instruction information and guidance information set by the setting means include sound information related to at least one of voice and alert.

[0012] an acquisition unit that acquires an object image of the object and setting information related to capturing the object image; a determination unit that determines whether the acquired object image includes an object image that should be used to draw attention; a setting unit that, if the object image includes the object image based on the determination result of the determination unit, sets coordinate information of the center of the object image that should be used to draw attention based on the setting information, and instruction information for an attention-drawing object to be displayed at the coordinate information, the instruction information being variably displayed toward the center of the coordinate information; and, if the object image includes multiple object images that should be used to draw attention, sets the coordinate information and instruction information with the highest priority, or sets the coordinate information and instruction information sequentially, based on at least one of the priority of tasks linked to the multiple object images that should be used to draw attention, the skill of the worker, or the gaze direction of the worker; and a light-emitting unit that emits the instruction information onto the coordinate information with a light beam based on the coordinate information and instruction information set by the setting unit. [Effects of the Invention]

[0013] According to the first aspect of the present invention, the acquisition means acquires an object image of an object and setting information related to capturing the object image. Therefore, the determination means can determine whether the object image includes an attention-calling object image that calls attention. This can alert the worker to the object or operation target, improving the accuracy of the confirmation work.

[0014] In particular, according to the first aspect of the present invention, when the object image includes an attention-attracting object image, the setting means sets coordinate information of the center of the attention-attracting object image and instruction information that is variably displayed toward the center of the coordinate information.The light emitting means then emits the instruction information onto the coordinate information using a light beam.This allows the worker to identify the equipment or operation location that the worker should be working on from among multiple objects, and quickly confirm which direction to focus their attention in.This alerts the worker to the object or operation target, improving the accuracy of the confirmation work.

[0015] According to the first to fifth aspects of the present invention, the determination means determines whether or not the object image includes an attention-attracting object image that draws attention. Therefore, if the object image includes the attention-attracting object image, information instructing attention can be set based on the setting information. This can draw the worker's attention to the object or operation target, improving the accuracy of the confirmation work.

[0016] In particular, according to the second aspect of the present invention, the instruction information is an image having information on at least one of a cross image, an X-shaped image, and a graphic image, and is an image that is displayed variably as it moves away from the center of the coordinate information. This allows the worker to identify the equipment or operation location that he or she should be working on from among multiple objects, and quickly confirm which direction he or she should focus on. This alerts the worker to the object or operation target, improving the accuracy of the confirmation work.

[0017] In particular, according to the third aspect of the present invention, the instruction information includes guidance information that is spaced apart from the instruction information and variably displayed toward the center of the coordinate information. This allows the worker to quickly confirm whether they should be gazing in the direction of the equipment or operation location they are working on. This alerts the worker to the object or operation target, improving the accuracy of the confirmation work.

[0018] In particular, according to the fourth aspect of the present invention, the instruction information and the guidance information have information in a format related to at least one of the color of the emitted light and the pattern of the emitted light, which are set so that the instruction information and the guidance information can be distinguished from each other. This allows the worker to identify the equipment or operation location that he or she should be working on from among multiple objects, and quickly confirm which direction he or she should focus on. This alerts the worker to the object or operation target, improving the accuracy of the confirmation work.

[0019] In particular, according to the fifth aspect of the present invention, the instruction information and the guidance information include sound information related to at least one of a voice and an alert, which are set so that the instruction information and the guidance information can be distinguished from each other. This allows the worker to confirm that there is a device or operation location that the worker should work on among multiple objects. This alerts the worker to the object or operation target, thereby improving the accuracy of the confirmation work.

[0020] According to a sixth aspect of the present invention, the acquisition unit acquires an object image of an object and setting information related to capturing the object image. Therefore, the determination unit can determine whether the object image includes an attention-calling object image that calls attention. This can alert the worker to the object or operation target, improving the accuracy of the confirmation work.

[0021] In particular, according to the sixth aspect of the present invention, when the object image includes an attention-attracting object image, the setting unit sets coordinate information of the center of the attention-attracting object image and instruction information that is variably displayed toward the center of the coordinate information.The light emitting unit then emits the instruction information onto the coordinate information using a light beam.This allows the worker to identify the equipment or operation location that the worker should be working on from among multiple objects, and quickly confirm which direction to focus their attention in.This alerts the worker to the object or operation target, improving the accuracy of the confirmation work. [Brief explanation of the drawings]

[0022] [Figure 1] FIG. 1 is a schematic diagram showing an example of an attention calling system according to this embodiment. [Figure 2] Fig. 2(a) is a schematic diagram showing an example of an object image captured by the attention calling device of this embodiment. Fig. 2(b) is a schematic diagram showing an example of a light emitting operation of the attention calling device of this embodiment. Fig. 2(c) is a schematic diagram showing an example of a light emitting operation of the attention calling device of this embodiment. [Figure 3] FIG. 3(a) is a schematic diagram showing an example of the configuration of an attention calling device in this embodiment, and FIG. 3(b) is a schematic diagram showing an example of the function of the attention calling device in this embodiment. [Figure 4] FIG. 4 is a schematic diagram showing an example of the reference database in this embodiment. [Figure 5] FIG. 5 is a flowchart showing an example of the operation of the attention calling system in this embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0023] Hereinafter, an example of an attention calling system and an attention calling device according to an embodiment of the present invention will be described with reference to the drawings.

[0024] An example of an attention calling system 100 and an attention calling device 1 according to this embodiment will be described with reference to FIG.

[0025] 1, the attention calling system 100 in this embodiment includes an attention calling device 1. The attention calling device 1 may be connected to another terminal 2 and a server 3 via a communication network 5, for example.

[0026] The attention warning system 100 warns a worker working at location A of an object 4. If location A is, for example, a hospital, then object 4 is a medical device, and if location A is, for example, a factory, then object 4 is a machine tool. Object 4 may be installed singly at location A, or multiple objects may be installed, such as object 4a and object 4b. Object 4b may also be equipped with a monitor 4c that displays the operating status of the equipment. Object 4 may be configured (not shown) to include, for example, levers, handles, and the like that workers use to perform their work, as well as various instruments for checking the status.

[0027] The attention-calling device 1 includes a camera 1a that captures an image of an object 4 installed in, for example, location A, and a light outlet 1b that emits a light beam that alerts an operator to the position and operation of the object 4. The camera 1a may be, for example, a known camera, or may be a device (for example, a network camera, a web camera, etc.) with a wireless function that enables communication with the terminal 2 and the server 3.

[0028] The warning system 100 may, for example, determine in advance the identity of a worker working at location A based on the identification information on an ID card held by the worker, or by facial recognition, biometric authentication, etc. (not shown) of the worker, and identify the worker working at location A based on the results of the determination.

[0029] 2(a) to 2(c), an example of an attention alert issued by the attention alert system 100 to a worker working at location A will be described. As shown in FIG. 2(a), the attention alert system 100 acquires, for example, via an attention alert device 1, an object image 50 of an object 4 installed at location A, identifies the object 4 on which the worker is working, and emits instruction information 6 to the object 4 installed at location A to alert the worker.

[0030] The attention calling device 1 installed in place A may, for example, capture images of a plurality of objects 4a and 4b in the space within place A. Furthermore, the attention calling device 1 may, for example, capture images of the situation within place A as a video (movie) in addition to images (still images). The attention calling system 100, for example, acquires a plurality of object images 50, identifies an object 4 on which a worker will work from among the plurality of object images 50, and emits instruction information 6 to the object 4 on which the worker should work from among the plurality of objects 4, thereby calling the worker's attention.

[0031] FIG. 2(b) shows a state in which the attention warning system 100 identifies the object 4a on which the worker is working based on, for example, the object image 50 and various setting information when the object image 50 is captured (at least one of starting point information, spatial information, difference information, position information, shooting information, shooting angle, and the worker's gaze direction), and emits a light beam that is variably displayed as the worker moves away from the center of the identified object 4a as instruction information 6.

[0032] 2(b), the instruction information 6 may be, for example, a light beam that is displayed thick at the center of the object 4a and gradually becomes thinner as it moves away from the center. In addition to the thickness of the light beam, the instruction information 6 may also be displayed such that the color of the emitted light or the type of the emitted light pattern changes continuously or gradually over a predetermined coordinate range. The various setting information may be acquired by the attention alert system 100, for example, using various sensors (not shown) provided in each device in response to capturing the target image 50.

[0033] The instruction information 6 is shown in FIG. 2(c) as guidance information projected at a distance from the instruction information 6. The guidance information 7 is displayed as, for example, a figure (such as an isosceles triangle tilted sideways). The guidance information 7 may also be a figure in which two figures overlap each other. If the guidance information 7 is, for example, an isosceles triangle, the figure may be one in which the acutest vertex indicates the direction of the center of the object 4 (the center is farther away), and if the image that is variably displayed as it moves away from the center of the coordinate information of the object 4 is an equilateral triangle, the vertex facing left or right of the equilateral triangle may be one in which the vertex indicates the direction of the center (the center is closer).

[0034] Also, Figure 2(c) shows that in the attention warning system 100, the object 4b on which the worker will be working is identified based on, for example, the object image 50 and various setting information when the object image 50 is captured (starting point information, spatial information, difference information, position information, shooting information, shooting angle, etc.), and the center point of the monitor 4c that should be checked on the identified object 4b is indicated by instruction information 6 and guidance information 7 using a light beam, as in the example shown in Figure 2(b).

[0035] In the example shown in Figure 2(c), this allows a subject at location A, for example, to accurately confirm that the device they need to work on is located to the right of location A, that this device is object 4b, and that it is monitor 4c for object 4b. This allows a subject at location A, for example, to identify the direction of object 4b, the device they need to work on, and object 4c, the device they need to work on, from among multiple devices, and enables them to quickly and accurately confirm the device they need to work on, thereby improving the accuracy of the confirmation work.

[0036] The instruction information 6 may be shaped as a line, a cross, an X, or a graphic image. The instruction information 6 may be shaped as a solid line, a broken line, or a red, green, or blue color, or may be shaped to flash. Furthermore, the instruction information 6 may include sound information such as a voice corresponding to the instruction information 6 and an alert, and may be output from a speaker (not shown) of the attention-attracting device 1 in conjunction with the emission of the light beam.

[0037] The instruction information 6 and the guidance information 7 may be emitted in various colors, such as red, green, and blue, and the type of line (e.g., solid line, dashed line), thickness, number, etc. may be set appropriately. The variable display of the guidance information 7 may be emitted in a flashing state. Furthermore, the instruction information 6 and the guidance information 7 may also include sound information such as voice and alerts, and may be output from a speaker (not shown) of the attention-attracting device 1 in conjunction with the emission of light beams indicating the distance and direction to the center.

[0038] (Attention device 1) Next, an example of the attention calling device 1 in this embodiment will be described with reference to Fig. 3. Fig. 3(a) is a schematic diagram showing an example of the configuration of the attention calling device 1 in this embodiment, and Fig. 3(b) is a schematic diagram showing an example of the function of the attention calling device 1 in this embodiment.

[0039] 3(a), the attention calling device 1 includes a housing 10, a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a storage unit 104, and I / Fs 105 to 109. The components 101 to 109 are connected to each other via an internal bus 120.

[0040] The CPU 101 controls the entire attention warning device 1. The ROM 102 stores the operation code of the CPU 101. The RAM 103 is a working area used when the CPU 101 is operating. The storage unit 104 stores various information such as evaluation target information and a reference database. As the storage unit 104, for example, a data storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive) is used.

[0041] I / F 105 is an interface for sending and receiving various information with other terminals 2, servers 3, etc., and may also be an interface for sending and receiving various information with other terminals 2, servers 3, etc. via a communication network 5 such as the Internet.

[0042] The I / F 106 is an interface for outputting light emission information as a light beam from the light emission unit 113. The light emission unit 113 may be provided, for example, in the attention calling device 1 with light emission units 113 (light emission ports 1b) that emit light in vertical and horizontal lines, each of which may be individually provided (not shown) so as to emit light in various variable indications in the direction of the center of an object.

[0043] I / F 107 is an interface for inputting captured image data and various setting information related to imaging with camera unit 112. Camera unit 112 may be attached integrally to attention warning device 1, for example, or may be a network camera installed on the ceiling of location A, or a camera (not shown) provided on a terminal held or worn by the operator or another operator.

[0044] The I / F 108 is an interface for transmitting and receiving information to and from the input unit 111. For example, a keyboard or the like is used as the input unit 111, and an evaluator or the like who uses the attention calling device 1 inputs various pieces of information or control commands for the attention calling device 1 via the input unit 111.

[0045] The I / F 109 is an interface for transmitting and receiving various types of information to and from the display unit 110. The display unit 110 outputs various types of information such as the evaluation results stored in the storage unit 104, or the processing status of the attention calling device 1. As the display unit 110, for example, a display is used, and it may be, for example, a touch panel type.

[0046] It should be noted that, for example, the same I / F may be used as I / F 105 to I / F 109, or, for example, a plurality of I / Fs may be used as each of I / F 105 to I / F 109. Also, at least one of camera unit 112, light emitting unit 113, terminal 2, server 3, communication network 5, input unit 111, and display unit 110 may be detached depending on the situation.

[0047] <Database> Next, an example of a database in this embodiment will be described with reference to Fig. 4. The database is stored in, for example, the server 3, and also in, for example, the storage unit 104, and various information stored in the database, data table, etc. is extracted as needed.

[0048] The database is composed of various data tables including at least a "user data table," an "object data table," a "warning object data table," and a "instruction information / guidance information data table," as shown in Figure 4. The various data tables that make up the database are configured by linking each piece of data.

[0049] <<User Data Table>> The user data table stores, for example, a "user ID" that indicates data for identifying the worker performing the work, a "user name" that indicates the name of the worker in association with the user ID, "user information" that indicates detailed information about the worker, and an "object ID" that identifies the object that is the target of a warning.

[0050] <<Object Data Table>> The object data table stores, for example, an "object ID" that indicates data for identifying the object that is the target of the warning, an "object name" that corresponds to the object ID and indicates the name and model number of the object installed in each location, an "object image" that is an image of the object such as equipment that is the target of the warning, "coordinate information (starting point, space, difference)" that indicates various coordinate information such as the position that will be the starting point of the warning within the location where the object is installed, the spatial position within the location, and the differential distance from the position of the camera installed within the location, and an "alert target ID" that identifies the object or state that is the target of the warning.

[0051] <<Caution Object Data Table>> The attention-warning object data table stores, in association with each other, for example, an "attention-warning object ID" indicating data for identifying the object to be alerted, a "attention-warning object name" which corresponds to the attention-warning object ID and indicates the name, model number, etc. of the object to be alerted for each object, an "object image" which is an image of the object and state of the device or other object to be alerted, "coordinate information (center, space, difference)" which indicates various coordinate information such as the center position of the attention-warning object 4a to 4c, its spatial position within the location, and the difference between the angle of the camera 1a of the attention-warning device 1 at which the object was photographed and the center position of the attention-warning object, an "instruction ID" which identifies instruction information 6 which changes its display as it moves away from the coordinate information of the center of the object and instructs attention, and an "identification ID" which identifies guidance information 7 which changes its display as it moves away from the instruction information 6 and moves away from the coordinate information of the center of the object.

[0052] <<Instruction and Guidance Information Data Table>> The instruction information / guidance information data table stores, for example, an "instruction ID" indicating data for identifying the instruction information 6 and a "guidance ID" indicating data for identifying the guidance information 7, a "display format" corresponding to each of the instruction IDs and guidance IDs and indicating the display format for emitting light to the object, various setting information for the emitting instruction information 6 or guidance information 7, such as the display type of the emitting instruction information 6 and guidance information 7, the color of the emitting light, the emitting light pattern, various positions related to the display, the spatial position within location A, the difference between the angle of the camera 1a of the attention-calling device 1 at which the object was photographed and the center position of the attention-calling object, the coordinates and distance information for variably displaying the instruction information 6 and guidance information 7, various information such as voice and alert, the voice, and the alert, the time for displaying or issuing a call, and "instruction format / guidance format" indicating various positions of the emitting light of the instruction information 6 and guidance information 7 set in the "instruction format / guidance format", and "coordinate information (center, space, difference)" indicating the coordinate positions related to the position and range for variably displaying the instruction information 6 and guidance information 7, etc.

[0053] The database may also store associations between, for example, previously acquired past object images 50 and attention-calling object images 51 (not shown) and reference information linked to the past object images 50 and attention-calling object images 51, and may store, for example, a learning model having the associations. The database may store, for example, past object images 50, attention-calling object images 51, setting information, discrimination results, coordinate information, evaluation target information such as instruction information 6 and guidance information 7, and reference information. The associations may be constructed by machine learning using multiple learning data, for example, with the past object images, attention-calling object images 51, and reference information as a set of learning data. As a learning method, for example, deep learning such as a convolutional neural network may be used.

[0054] The past evaluation target information may include, for example, composite data and a similarity. The composite data is represented by three or more levels of similarity between the composite data and the past image data or the past discrimination information. The composite data may be stored in the database in the form of a numerical value, a matrix, a histogram, or the like, or may be stored in the form of an image, a character string, or the like.

[0055] Fig. 3(b) is a schematic diagram showing an example of the functions of the attention calling device 1. The attention calling device 1 includes an acquisition unit 11, a discrimination unit 12, a setting unit 13, and a light emitting unit 14, and may also include, for example, a storage unit 15. Note that each function shown in Fig. 3(b) is realized by the CPU 101 using the RAM 103 as a working area to execute a program stored in the storage unit 104 or the like, and may be controlled by, for example, artificial intelligence.

[0056] <Acquisition part 11> The acquisition unit 11 acquires an object image 50 of the object and setting information when the object image 50 was captured. The acquisition unit 11 acquires the object image 50 of the object 4 in place A, for example, by the camera 1a of the attention warning device 1. For example, if the attention warning device 1 is fixedly installed in place A, the acquisition unit 11 captures an image of the object from the fixed installation position. Note that the attention warning device 1 may be remotely operated, for example, from the terminal 2 via the communication network 5, and may remotely capture an image of the object 4 in place A. Furthermore, for example, the camera 1a may be worn by a worker, and the object image 50 of the object 4 from the worker's point of view may be acquired.

[0057] For example, when acquiring an object image 50 of an object 4 in location A, the acquisition unit 11 also acquires various types of information from which the object image 50 was acquired, and stores the acquired various types of information in the storage unit 104. For example, the acquisition unit 11 may store the acquired object image 50 and various types of setting information in a database of the server 3 via the communication network 5.

[0058] The object image 50 acquired by the acquisition unit 11 may be, for example, a still image or a video. The acquisition unit 11 may acquire the still image or video by, for example, referring to the "user data table" shown in FIG. 4, or may automatically acquire the image based on the worker's behavior, posture, speech, etc. Furthermore, the acquisition unit 11 may acquire the user ID of a worker who has been detected by an entry / exit management device (not shown) as a person to be alerted entering place A, and may capture an image of the object 4 in the space within place A.

[0059] 4, and includes at least various setting information such as location information where the attention alert device 1 is installed, the space within place A based on the location information, the direction and imaging angle (pan, tilt, zoom) at which the camera 1a captured the image of the object 4, and the distance to the object 4. This makes it possible to accurately acquire an object image 50 including the object 4, draw the worker's attention to the object or operation target, and improve the accuracy of the confirmation work.

[0060] The acquisition unit 11 acquires, for example, various shooting conditions as setting information together with the object image 50. Note that the acquisition unit 11 may acquire the object image 50 and the setting information based on, for example, the work content and skills of the worker, the shape, specifications (performance, function, interface, design, etc.) of the object installed at location A, the number of installed units, etc., and the frequency and cycle are arbitrary.

[0061] The acquisition unit 11 also receives various types of information transmitted to the attention-calling device 1. The acquisition unit 11 receives various types of information, such as coordinate information, instruction information 6, and guidance information 7, transmitted from an external terminal such as another terminal 2, via the communication network 5 and the I / F 105, for example.

[0062] <Discrimination part 12> The determination unit 12 determines whether or not an attention-attracting object image 51 for attracting attention is included in the object image 50 acquired by the acquisition unit 11. The determination unit 12 determines whether or not an image of an attention-attracting object 4a to 4c is included in the object image 50 acquired by the acquisition unit 11, by referring to, for example, the "object data table" and the "attention-attracting object data table" shown in FIG.

[0063] The determination unit 12 may determine whether or not the object image 50 includes attention-attracting objects 4a to 4c that require attention, based on, for example, the object image 50 acquired by the acquisition unit 11 and various setting information at the time of capturing the object image 50. The determination unit 12 refers to, for example, a database in the server 3, and determines whether or not the acquired object image 50 includes images of the attention-attracting objects 4a to 4c by AI determination processing using known similar image comparison technology, similar image search technology, artificial intelligence, machine learning, or the like.

[0064] The discrimination unit 12 refers to, for example, a database of the server 3 and selects an image that is identical to or similar to the image of the attention-attracting object 4a-4c included in the captured object image 50. For example, the discrimination unit 12 may select, as the first data, data that partially or completely matches the attention-attracting object, or may select data that is similar to the first data. When the selected data is represented by numerical values ​​such as a matrix, the discrimination unit 12 may set a numerical range to be selected in advance.

[0065] For example, when the discrimination unit 12 discriminates the object image 50 of object 4 acquired by the worker "user ID=002", it refers to the "user data table" in the database and discriminates that the object on which "user ID=002" is working (the object to be focused on) is "object ID=B001 (for example, object 4)".

[0066] Next, the discrimination unit 12 acquires, for example, an image of the object image 50 linked to "object ID=B001" (object image=B001), and through processing such as well-known image discrimination, discriminates the similarity, degree of agreement, etc. between the object image 50 and the "object image=B001" linked to "object ID=B001" using well-known image comparison techniques, etc.

[0067] Next, when the discrimination unit 12 determines that the object 4 is object image "B001" based on the discrimination result of the object image 50 and "object image=B001" linked to "object ID=B001," it determines whether or not there is an attention-calling object linked to the object image "B001" by referring to the data record of the "attention-calling object ID." If, for example, object image "B001" is included in object image "B001," the discrimination unit 12 determines that there is an attention-calling object linked to the object image "B001," and acquires "attention-calling object ID=BB01." Here, the attention-calling object corresponding to "attention-calling object ID=BB01" will be described below as attention-calling object 4c shown in FIG. 2.

[0068] <Settings section 13> The setting unit 13 sets coordinate information of the center of the attention-attention object (attention-attention object image), the instruction information 6 to be displayed, and the guidance information 7. The setting unit 13 refers to the "attention-attention object data table" shown in Fig. 4, for example, to identify the attention-attention object ID (e.g., "attention-attention object ID=BB01") included in the object image 50, and acquires an instruction ID (e.g., "instruction ID=BBB1") and a guidance ID (e.g., "guidance ID=CCC1") to be instructed to the attention-attention objects 4a to 4c.

[0069] The instruction ID is an ID for identifying the content of an instruction given to, for example, attention-drawing objects 4a to 4c to draw the attention of a worker. As information corresponding to the instruction ID, various setting information such as what instruction information 6 should be emitted to the attention-drawing objects 4a to 4c is stored in the "instruction information / guidance information data table."

[0070] The guidance ID is an ID for identifying the content of an instruction to point the direction of the center of the attention-drawing location of the attention-drawing object 4a to 4c to draw the worker's attention. As information corresponding to the guidance ID, various setting information such as what kind of guidance information 7 should be emitted in the direction of the center of the attention-drawing object 4a to 4c is stored in the "instruction information / guidance information data table."

[0071] The setting unit 13 refers to the "Instruction Information / Guidance Information Data Table" shown in Fig. 4 based on the instruction ID and guidance ID. The setting unit 13 acquires, for example, instruction information 6 and guidance information 7 corresponding to "Instruction ID = BBB1" and "Guidance ID = CCC1", and sets them as information to be transmitted to the light projection unit 14. The setting unit 13 refers to the "Attention-calling Object Data Table" and acquires an image of "Attention-calling Object Image = BB01 (Attention-calling Object 4c)" linked to "Attention-calling Object ID = BB01" and "Coordinate Information (Center, Space, Difference) = ***, ***, ***".

[0072] The setting unit 13 compares the position information (coordinate information) included in the setting information of the object 4 acquired by the acquisition unit 11 together with the object image 50 with the "coordinate information (center, space, difference) = ***, ***, ***" of the attention-attracting object 4c, obtains coordinates (for example, from the positive area toward the center, or from the negative area toward the center, etc.) adjusted so that the instruction information 6 is located at the center of the attention-attracting object 4c, and stores these in "coordinate information (center, space, difference) = ***, ***, ***" linked to "instruction ID = BBB1". The setting unit 13 obtains coordinate information (such as a coordinate range that is continuous or stepped with respect to a predetermined coordinate range) of the instruction information 6 that is variably displayed toward the center of the obtained coordinate information, and sets it as the coordinate information from which the instruction information 6 is irradiated.

[0073] The setting unit 13 further obtains coordinates (for example, from the positive area to the center, from the negative area to the center, etc.) on each axis adjusted so that the guidance information 7 indicates the direction of the center of the attention-attracting object 4c, and stores the coordinates in "coordinate information (center, space, difference) = ***, ***, ***" associated with "guidance ID = CCC1". Note that the coordinates may be set so that multiple pieces of guidance information 7 are displayed, and furthermore, multiple coordinates may be set that are located in the vicinity of but spaced from the coordinates on the instruction information 6.

[0074] The setting unit 13 sets, for example, "red, cross, solid line (variable display: yes), direction A (front), sound A, time, ..." and "coordinate information (center, space, difference) = ***, ***, ***" linked to "instruction ID = BBB1", and "red, guidance display (three arrows), horizontal (front), alert A, time, ..." and "coordinate information (center, space, difference) = ***, ***, ***" linked to "guidance ID = CCC1".

[0075] The setting unit 13 sets various pieces of instruction information 6 and guidance information 7, for example, by referring to an "instruction information / guidance information data table." The instruction information 6 set by the setting unit 13 may be an image having information on at least one of a cross image, an X image, and a graphic image. The graphic image may be, for example, a circle, a rectangle, or an icon indicating a position. The guidance information 7 set by the setting unit 13 may be an image whose display (for example, the shape, number, color, gradation, etc. of the graphic) changes with distance from the coordinate information of the center of the attention-attention objects 4a to 4c. The image whose display changes may be, for example, an arrow, a rectangle, or an icon indicating a direction, or a line type.

[0076] The parameters of the irradiated light pattern may include, for example, color, blinking as an irradiated light pattern, and the roll rotation angle of the cross image, X image, and graphic image. The setting unit 13 may set, as a pattern parameter, for example, the rotation speed of the roll angle of the cross image, X image, and graphic image. The setting unit 13 may set, for example, a parameter for displaying the cross image, X image, and graphic image in a fixed state, as well as a parameter for rotating the cross image clockwise, counterclockwise, alternately rotating clockwise and counterclockwise, rotating quickly, rotating slowly, etc.

[0077] The instruction information 6 and the guidance information 7 set by the setting unit 13 may be, for example, sound information relating to at least one of a sound and an alert corresponding to the instruction information 6 and the guidance information 7. The format of the instruction information 6 and the guidance information 7, the sound, and the alert set by the setting unit 13 may be different for each axis (e.g., X-axis, Y-axis, etc.).

[0078] Furthermore, for example, when a plurality of attention-attracting object images 4a to 4c are included in the discrimination result of the discrimination unit 12, the setting unit 13 may set the coordinate information, instruction information 6, and guidance information 7 with the highest priority based on the priorities of the tasks associated with the plurality of attention-attracting object images 4a to 4c or the skills of the worker. Alternatively, the setting unit 13 may set the coordinate information, instruction information 6, and guidance information 7 sequentially.

[0079] Because the determination result by the determination unit 12 indicates that the attention-attracting object image 4c is included in the object image 50, the setting unit 13 may output the setting result, in which the coordinate information of the center of the attention-attracting object image 4c, the instruction information 6, and the guidance information 7 are set based on the setting information, to the light-emitting unit, for example, via the I / F 106. The determination result may be sent to the display unit 110, for example, via the I / F 107, or may be sent to another terminal 2, for example, via the I / F 105.

[0080] <Light emitting part 14> The light emitting unit 14 refers to the "instruction information / guidance information data table" and variably displays the instruction information 6 toward the center of the coordinate information based on the coordinate information and instruction information 6 set by the setting unit 13. Furthermore, the light emitting unit 14 emits guidance information 7, which is spaced apart from the instruction information 6 and indicates the direction of the center of the coordinate information, by a light beam based on the coordinate information and instruction information 6 set by the setting unit 13. Note that the guidance information 7 may not be emitted when, for example, the determination result by the determination unit 12 indicates that only the instruction information 6 is set (for example, the location A is a large area, the attention-calling object 4c is in an easy-to-find position, the work content is an overall instruction, the worker's work skills are skilled, etc.), and only the instruction information 6 may be variably displayed and emitted toward the center of the coordinate information.

[0081] For example, when there are multiple pieces of coordinate information, instruction information 6, and guidance information 7 set by the setting unit 13, the light emitting unit 14 may emit light sequentially based on at least one of the priority of the task linked to the image of the object to be warned, the skill of the worker, or the direction of the worker's gaze.

[0082] <Memory unit 15, database> The storage unit 15 retrieves, as necessary, various types of information such as databases stored in the storage unit 104. The storage unit 15 stores in the storage unit 104 various types of information acquired or generated by each of the components 11 to 14.

[0083] <Camera 1a (camera unit 112)> The camera unit 112 is, for example, a known camera that captures an image of the object 4 and generates image data. For example, a network camera, a web camera, or the like is used as the camera unit 112, and multiple units may be used remotely. The camera unit 112 may be, for example, built into the attention calling device 1, or may be separate from the attention calling device 1, or may even be configured to be held by the worker.

[0084] <Light emission port 1b (light emission unit 113)> The light emission unit 113 acquires coordinate information for emitting the instruction information 6 and the guidance information 7, as well as the display format and instruction format for the light beam of the emitted instruction information 6 and the guidance information 7, and emits the light beam from the light emission port 1b of the attention alert device 1 in a variable display toward the center of the attention alert object 4a to 4c.

[0085] The light beam may be emitted using, for example, a known technology related to a laser marking device. For example, a plurality of light emission ports 1b may be used in the attention warning device 1. The light emission port 1b may be built into the attention warning device 1, or may be configured to be separate, for example.

[0086] <Communication Network 5> The communication network 5 is, for example, the Internet or the like to which the attention warning device 1 and the like are connected via a communication circuit. The communication network 5 may be configured as a so-called optical fiber communication network. Furthermore, the communication network 5 may be realized by a known communication network such as a wired communication network or a wireless communication network.

[0087] <Other device 2> The other terminal 2 may be, for example, an electronic device embodied in the same way as the attention-calling device 1. The other terminal 2 may, for example, be a central control device or the like that can communicate with a plurality of attention-calling devices 1. The other terminal 2 may, for example, be connectable to a plurality of attention-calling devices 1, and may acquire object images 50 captured by each of the attention-calling devices 1. This allows, for example, determining whether or not object images 50 captured at a plurality of locations contain attention-calling object images 51 that call attention, and if the result of this determination indicates that the object images 50 contain attention-calling object images 51, it is possible to set instruction information and guidance information 7 based on the setting information, thereby calling the worker's attention to the object or operation target, and improving the accuracy of the confirmation work.

[0088] <Server 3> The server 3 stores, for example, the various types of information described above. The server 3 accumulates, for example, various types of information sent via the communication network 5. The server 3 may store, for example, information similar to that stored in the storage unit 104, and may transmit and receive various types of information to and from one or more attention calling devices 1 via the communication network 5. That is, the attention calling device 1 may use the server 3 instead of the storage unit 104.

[0089] (An example of the operation of the alert system 100) Next, a description will be given of an example of the operation of the attention calling system 100 in this embodiment. Fig. 5 is a flowchart showing an example of the operation of the attention calling system 100 in this embodiment.

[0090] <Acquisition means S110> 5, the acquisition unit 11 acquires an object image 50 of the object 4 and setting information related to capturing the object image 50 (acquisition means S110). The acquisition unit 11 acquires, for example, the object image 50 of the object and various setting information when the object image 50 was captured. The acquisition unit 11 stores the acquired object image 50 of the object 4 and various setting information in the storage unit 104 via the storage unit 15, for example.

[0091] <Discrimination means S120> Next, the determination unit 12 determines whether or not the image of the attention-calling objects 4a to 4c is included (determination means S120). The determination unit 12 determines whether or not the image of the object 50 includes the attention-calling objects 4a to 4c that call attention, based on the object image 50 acquired by the acquisition unit 11 and various setting information at the time of capturing the object image 50. The determination unit 12 may determine whether or not the acquired object image 50 includes the images of the attention-calling objects 4a to 4c by, for example, referring to a database and performing image processing using known similar image search, artificial intelligence, machine learning, or the like.

[0092] Furthermore, the discrimination unit 12 generates a discrimination result using format data such as an output format stored in the storage unit 104. The discrimination unit 12 may store the discrimination result in the storage unit 104 via the memory unit 15, for example.

[0093] <Setting Means S130> Next, the setting unit 13 sets the coordinate information of the center and the instruction information 6 that is variably displayed toward the center of the coordinate information (setting means S130). The setting unit 13 may, for example, output the determination result to the display unit 110 or the like. The setting unit 13 may also output the determination result to another terminal 2 or the server 3 via the communication network 5, for example.

[0094] For example, when the object image 50 includes an attention-calling object image, the setting unit 13 sets coordinate information of the center of the attention-calling object image and instruction information 6, which is an attention-call to be displayed at the coordinate information and is variably displayed toward the center of the coordinate information, based on the setting information. The setting unit 13 references a database based on the determination result of the determination unit 12, for example, to acquire various pieces of corresponding coordinate information and various pieces of information related to the instruction information 6, and generates setting information for the instruction information 6, which is variably displayed toward the center of the coordinate information of the centers of the attention-calling objects 4a to 4c.

[0095] Furthermore, the setting unit 13 sets, for example, guidance information 7 that is spaced apart from the instruction information 6 and variably displayed toward the center of the coordinate information. The setting unit 13 may refer to a database based on the determination result of the determination unit 12, for example, to acquire various pieces of corresponding coordinate information and various pieces of information related to the guidance information 7, and generate setting information for guidance information 7 that is spaced apart from the instruction information 6 and variably displayed toward the center of the coordinate information of the centers of the attention-attention objects 4a to 4c.

[0096] <Light emitting means S140> The light emitting unit 14 emits the instruction information 6 by a light beam so as to variably display the instruction information 6 toward the center of the attention monitoring objects 4a to 4c and the center of the coordinate information of the attention monitoring objects 4a to 4c according to the coordinate information and instruction information 6 set by the setting unit 13 (light emitting means S140). The light emitting unit 14 is installed, for example, at location A as the attention calling target device 1, but for example, a plurality of light emitting units 14 (light emitting units 113) may be installed. In this case, for example, the setting unit 13 sets the coordinate information, instruction information 6, and guidance information 7 for each of the attention calling objects 4a to 4c, and the light is emitted from each light emitting unit 14 (light emitting port 1b).

[0097] Furthermore, when the guidance information 7 is set by the setting unit 13, the light emitting unit 14 may emit the guidance information 7 by a light beam so that the set coordinate information and guidance information 7 are spaced apart from the instruction information 6 and are variably displayed toward the center of the coordinate information of the objects 4a to 4c to be monitored.

[0098] The light emitting unit 14 may emit the instruction information 6 and the guidance information 7 set by the setting unit 13 onto the attention-calling objects 4a to 4c using, for example, a light emitting technique related to a known laser marking device or the like. The attention-calling device 1 may have, for example, a plurality of light emitting ports 1b, and the light emitting ports 1b may be built into the attention-calling device 1 or may be configured to be separate, for example.

[0099] For example, when there are multiple pieces of coordinate information, instruction information 6, and guidance information 7 set by the setting unit 13, the light emitting unit 14 may be configured to sequentially emit light to the worker. In this case, the setting unit 13 may be configured to sequentially display the pieces of coordinate information, instruction information 6, and guidance information 7 based on at least one of the setting information related to the worker, the priority of the work being performed by the worker, and the gaze direction of the worker.

[0100] This completes the operation of the attention calling system 100 in this embodiment.

[0101] According to this embodiment, the acquisition unit 11 acquires an object image 50 of the object and various setting information related to capturing the object image 50. The installation information may include various information about the worker and authentication information identifying the worker, which are acquired at location A. Alternatively, the installation information may refer to a "user data table" or the like to acquire various information linked to the worker's user ID, and the information may be included in the setting information. This allows the worker to quickly identify the equipment or operation location that the worker should be working on among multiple objects, and further to quickly identify the direction in which the worker should be gazing. This alerts the worker to the object or operation target, improving the accuracy of the confirmation work.

[0102] Furthermore, according to this embodiment, the user information includes various information for evaluating the worker's attention, such as information about the department, information about the work, the worker's posture and line of sight, information about the role, skills (expert to beginner, etc.), and employment history. This allows accurate instructions to be given to the worker regarding their work and work response, even if they have overlooked something. This allows the worker to be alerted to the object or operation target, improving the accuracy of the confirmation work.

[0103] Furthermore, according to this embodiment, the setting information includes instruction information 6 and guidance information 7. The instruction information 6 and guidance information 7 include, for example, the size of place A, brightness, and the number of devices to be installed. Therefore, it is possible to give instructions that are adapted to the space of the place, the devices (objects) installed in the space, the work and work responses of the worker, etc. This makes it possible to draw the worker's attention to the objects and the objects to be operated, thereby improving the accuracy of the confirmation work.

[0104] Furthermore, according to this embodiment, the display format includes a pattern. The pattern may be, for example, an animation, text, or a message. Therefore, it is possible to convey instructions or actions by message to the space (wall, etc.) in place A. This makes it possible to inform the worker of actions regarding the object or operation target. This can draw the worker's attention to the object or operation target, improving the accuracy of the confirmation work.

[0105] Although the embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, and are also included in the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0106] 1: Alert device 1a: Camera 1b: Light aperture 2: Terminal 3: Server 4: Object 4a: Caution object 4b: Caution object 4c: Monitor 5: Communication network 6 :Instruction information 7: Guidance information 10: Housing 11: Acquisition part 12:Discrimination part 13: Setting section 14: Light emitting part 15: Storage section 50: Object image 51: Image of object to be warned 100: Warning system 101: CPU 102:ROM 103:RAM 104: Preservation Department 105: Interface 106: Interface 107: Interface 108: Interface 109: Interface 110: Display section 111: Input section 112: Camera unit 113: Light Unit A: Location S110: Acquisition means S120: Discrimination means S130: Setting means S140: Light emitting means

Claims

1. An attention alert system that alerts a worker to an object, an acquisition means for acquiring an object image of the object and setting information related to capturing the object image; a determination means for determining whether or not the acquired object image includes an attention-attracting object image for attracting attention; a setting means for setting, based on the setting information, coordinate information of the center of the attention-calling object image and instruction information for the attention to be displayed at the coordinate information and variably displayed toward the center of the coordinate information, if the object image includes the attention-calling object image as a result of the determination by the determination means, and, if the object image includes a plurality of attention-calling object images, setting the coordinate information and instruction information with the highest priority, or setting the coordinate information and instruction information sequentially, based on at least one of the priority of tasks linked to the plurality of attention-calling object images, the skill of the worker, or the gaze direction of the worker; a light emitting means for emitting the instruction information onto the coordinate information by a light beam based on the coordinate information and the instruction information set by the setting means; To be prepared A warning system characterized by:

2. The instruction information set by the setting means is an image having information on at least one of a cross image, an X-shaped image, and a graphic image, and is an image that is displayed variably as it moves away from the center of the coordinate information.

2. The attention calling system according to claim 1,

3. The instruction information set by the setting means includes guidance information that is spaced apart from the instruction information and variably displayed toward the center of the coordinate information.

3. The attention calling system according to claim 1 or 2, characterized in that:

4. The instruction information and the guidance information set by the setting means have a format related to at least one of a color of irradiated light and an irradiated light pattern. The attention calling system according to any one of claims 1 to 3, characterized in that:

5. The instruction information and guidance information set by the setting means include sound information related to at least one of voice and alert. The attention calling system according to any one of claims 1 to 3, characterized in that:

6. An attention-attracting device that alerts a worker to an object, an acquisition unit that acquires an object image of the object and setting information related to capturing the object image; a determination unit that determines whether or not the acquired object image includes an attention-attracting object image that draws attention; a setting unit that, when the determination result of the determination unit indicates that the object image includes the attention-calling object image, sets coordinate information of the center of the attention-calling object image based on the setting information and instruction information for the attention to be displayed at the coordinate information and variably displayed toward the center of the coordinate information, and when the object image includes a plurality of the attention-calling object images, sets the coordinate information and instruction information with the highest priority, or sets the coordinate information and instruction information sequentially, based on at least one of the priority of tasks linked to the plurality of attention-calling object images, the skill of the worker, or the gaze direction of the worker; a light emitting unit that emits the instruction information onto the coordinate information by a light beam based on the coordinate information and the instruction information set by the setting unit; To be prepared An attention-calling device characterized by the above.

Images