JP2021082057A - Detection system and detection program - Google Patents

Abstract

To provide a detection system and a detection program making it possible to reliably detect an object at a high efficiency.SOLUTION: A server device 5 that detects a movable cart 1 includes: a movement unit 521 that moves the cart 1; an acquisition unit 522 that acquires images of the first and second floors which are object areas where the cart 1 imaged before and after the cart 1 is moved by the movement unit 521 may exist; and a detection unit 523 that detects the cart 1 on the basis of a difference between the images of the first and second floors, which are imaged before and after the cart 1 is moved, acquired by the acquisition unit 522. The detection unit 523 detects presence or absence of the cart 1 on the first or second floor. Further, the detection unit 523 detects a position of the cart 1. The detection unit 523 also detects an orientation of the cart 1.SELECTED DRAWING: Figure 2

Description

The present invention relates to a detection system and a detection program.

Conventionally, as a device for transporting materials at a construction site, a transport trolley pushed by a worker has been known (see, for example, Patent Document 1).

Japanese Unexamined Patent Publication No. 2016-32953

By the way, when the scale of the construction site is relatively large, a plurality of transport trolleys are used, and a large number of workers are required to move the transport trolleys when necessary (irregularly).

Therefore, from the viewpoint of improving the work efficiency of the construction site at low cost, each transport trolley is detected by attaching a marker, a lamp, or the like to each of the plurality of transport trolleys and imaging the mark with a camera. A technology for remote control has been proposed.

However, when such a technology is adopted, there is a possibility that the marker or the lamp is hidden behind the pillar or the installed material and cannot be imaged, the transport trolley cannot be detected, and it becomes difficult to operate the vehicle appropriately remotely. .. In particular, for example, when the markers and lamps are hidden by the luggage loaded on the transport trolley, or when the transport trolleys approach each other and the markers and lamps are hidden by other transport trolleys. There was a possibility that the markers and lamps could not be imaged, the transport trolley could not be detected, and proper remote operation could be difficult.

The present invention has been made in view of the above facts, and an object of the present invention is to provide a detection system and a detection program that enable highly efficient and reliable detection of an object.

In order to solve the above-mentioned problems and achieve the object, the detection system according to claim 1 is a detection system that detects a movable object, and is a moving means for moving the object and the moving means. Acquiring means for acquiring an image of a target area in which the object may exist, and the target area captured before and after moving the object acquired by the acquisition means. A detection means for detecting the object based on the difference between the images of the above.

The detection system according to claim 2 is the detection system according to claim 1, wherein the detection means detects the presence or absence of the object in the target area.

The detection system according to claim 3 is the detection system according to claim 1 or 2, wherein the detection means detects the position of the object.

The detection system according to claim 4 is the detection system according to any one of claims 1 to 3, wherein the detection means detects the orientation of the object.

The detection system according to claim 5 is the detection system according to any one of claims 1 to 4, wherein the movement operation means for operating the movement of the object based on the detection result of the detection means. Be prepared.

The detection program according to claim 6 is a detection program that detects a movable object, and images a computer with a moving means for moving the object and before and after the moving means moves the object. Based on the difference between the acquisition means for acquiring the image of the target area in which the object can exist and the images of the target area captured before and after moving the object acquired by the acquisition means. It functions as a detection means for detecting the object.

According to the detection system according to claim 1 and the detection program according to claim 6, the object is detected based on the difference between the images of the target area captured before and after moving the object. As a result, the object can be detected even when a part of the object is hidden by a shield (for example, a pillar, an installed material, etc.) and is not shown in the image. Can be reliably detected. Further, for example, it is not necessary to install a marker, a lamp, or the like for detection on the object, so that the object can be detected with high efficiency. Further, for example, it is possible to reliably detect objects that have been randomly arranged by a person without any intention or relationship in the order of use with high efficiency.

According to the detection system according to claim 2, by detecting the presence or absence of the object in each target area where the object may exist, for example, arbitrary processing related to the object (for example, considering the presence or absence of the object). , Processing to remotely control the object, etc.) can be performed.

According to the detection system according to claim 3, by detecting the position of the object, for example, arbitrary processing related to the object in consideration of the position of the object (for example, a process of remotely controlling the object). Can be done.

According to the detection system according to claim 4, by detecting the direction of the object, for example, arbitrary processing related to the object in consideration of the direction of the object (for example, a process of remotely controlling the object). Can be done.

According to the detection system according to claim 5, by manipulating the movement of the object based on the detection result of the detection means, for example, the object can be moved, so that the convenience regarding the object is improved. It becomes possible to make it.

It is a figure which shows the warehouse to which the automatic operation system is applied to this embodiment. It is a block diagram of an automatic driving system. It is a side view of a dolly. It is a figure which illustrated the equipment information. It is a figure exemplifying the dolly information. It is a flowchart of the detection process. It is a top view of the first floor part. It is a top view of the first floor part. It is a top view of the second floor part. It is a flowchart of a trolley detection process. It is a figure which illustrated the movement route of a dolly.

Hereinafter, embodiments of the detection system and the detection program according to the present invention will be described in detail with reference to the accompanying drawings. First, the basic concept of the embodiment of [I] will be described, then the specific contents of the embodiment of [II] will be described, and finally, a modified example of the embodiment of [III] will be described. However, the present invention is not limited to the embodiments.

[I] Basic concept of the embodiment First, the basic concept of the embodiment will be described. Embodiments generally relate to detection systems and detection programs.

Here, the "detection system" is a system for detecting a movable object, for example, a dedicated system for detecting an object, or a system used for general purposes (for example, a server computer, a personal computer, a tablet). It is a concept that includes a system, etc. realized by implementing a function for detecting a movable object on a terminal, etc.). The "detection system" is a concept including, for example, a moving means, an acquiring means, and a detecting means, and optionally includes a moving operating means and the like.

The "moving means" is a means for moving an object, specifically, a means for moving the object in order to detect the object, for example, a means for moving the object by a predetermined distance. The "predetermined distance" is a predetermined distance, for example, a distance at which it is possible to recognize that the object has moved by an image captured by an imaging device (for example, a camera or the like) that images the object. As an example, it is a concept that includes a very short distance of about 10 cm to about 30 cm and the like.

Further, the "object" is a movable object, and for example, a bogie, a vehicle, a heavy machine, and a mobile landscape (a bench or an arbitrary object other than the bench) are provided with a function of being remotely controlled. It is a concept that includes a device that changes the landscape by moving it remotely.

Further, the "acquisition means" is a means for acquiring an image of a target area in which an object may exist, which is captured before and after the moving means moves the object. For example, the above-mentioned imaging device (for example, a camera or the like). ) Is a concept including means for acquiring an image captured in.

Further, the "target area" is an area in which an object may exist, specifically, an area imaged by an imaging device, for example, an area inside a building or an area outside the building. It is a concept including an area and the like, and as an example, it is a concept including an area and the like of each floor of a building.

Further, the "detection means" is a means for detecting an object based on the difference between the images of the target area captured before and after moving the object acquired by the acquisition means, for example, the object. Is a concept including means for detecting the presence or absence of an object in each target area where can exist, a concept including means for detecting the position of the object, and the like, and means for detecting the orientation of the object. It is a concept including.

Further, the "movement operation means" is a means for operating the movement of the object based on the detection result of the detection means, and is a concept including, for example, a means for remotely controlling the object.

Then, in the embodiment shown below, the case where the "object" is a trolley that can be remotely controlled and the "target area" is each floor of the warehouse which is a building will be described.

[II] Specific contents of the embodiment Next, the specific contents of the embodiment will be described.

(Constitution)
First, the configuration of the automatic driving system according to the present embodiment will be described. FIG. 1 is a diagram showing a warehouse to which the automatic operation system is applied to the present embodiment, and FIG. 2 is a block diagram of the automatic operation system. The XYZ directions shown in FIG. 1 are orthogonal to each other. Specifically, the Z direction is a vertical direction, and the X and Y directions are horizontal directions orthogonal to the vertical direction. It will be explained as a thing. Also, with respect to the center point of the warehouse, the direction of + Y is "north", the direction of -Y is "south", the direction of -X is "east", and the direction of + X is. Will be described below assuming that is "west".

(Composition-Warehouse)
The warehouse 900 of FIG. 1 is a building to which the automatic operation system 100 of FIG. 2 is applied. For example, the first floor portion 901 (target area) and the second floor portion 902 (target portion) are connected to each other via an elevator 903. It is movable. Regarding this warehouse 900, only an outline is shown in FIG. 1 for convenience of explanation.

(Configuration-Automated driving system)
The automatic driving system 100 of FIG. 2 includes, for example, a dolly 1, a camera 2, a communication device 3, a terminal device 4, and a server device 5.

(Configuration-Automated driving system-Bogie)
FIG. 3 is a side view of the dolly. The trolley 1 in FIG. 2 is an object, for example, a trolley that can be operated separately (that is, a trolley that can be automatically driven), and is loaded with luggage 8 as shown in FIG. 3, for example. 2. The communication unit 11, the traveling unit 12, the steering unit 13, the recording unit 14, and the control unit 15 are provided. It should be noted that the trolley 1 here is a generic term for trolleys 101 to 104 having similar appearances in FIG. 1, and when it is not necessary to distinguish each of these trolleys 101 to 104 from each other, this generic term is used. It will be described using (the same applies to the camera 2).

(Configuration-Automated driving system-Bogie-Communication unit)
The communication unit 11 is a means of communicating communication with an external device. The specific type and configuration of the communication unit 11 is arbitrary, but for example, it is configured by using a known wireless communication circuit or the like so as to perform wireless communication with the server device 5 via the communication device 3. Can be done.

(Configuration-Automated driving system-Bogie-Running unit)
The traveling unit 12 is a traveling means for traveling the carriage 1. The specific type and configuration of the traveling unit 12 are arbitrary, but for example, the wheels 121 shown in FIG. 3, a battery (not shown) mounted on the carriage 1, and a wheel driven by a power source from the battery. It can be configured by using a motor (not shown) mounted on the carriage 1 for rotating 121.

(Configuration-Automated driving system-Bogie-Steering unit)
The steering unit 13 is a steering means for steering to change the traveling direction of the carriage 1. The specific type and configuration of the steering unit 13 are arbitrary, but can be configured by using, for example, a known direction changing mechanism or the like.

(Configuration-Automated driving system-Bogie-Recording unit)
The recording unit 14 is a recording means for recording a program and various data necessary for the operation of the carriage 1. The specific type and configuration of the recording unit 14 are arbitrary, but are configured by using, for example, EEPROM, Flash memory, or the like. However, instead of EEPROM or Flash memory, or together with EEPROM or Flash memory, an external recording device such as a hard disk, a magnetic recording medium such as a magnetic disk, an optical recording medium such as a DVD or Blu-ray disk, or a ROM, USB memory, SD. Any other recording medium, including an electrical recording medium such as a card, can be used (as well as the recording section of other devices).

For example, the trolley identification information (hereinafter, the identification information is referred to as "ID") is stored in the recording unit 14. The "trolley ID" is, for example, information for uniquely identifying the trolley 1. Here, for example, it will be described below assuming that "ID101", "ID102", "ID103", and "ID104" are recorded as trolley IDs in the recording units 14 of the trolleys 101, 102, 103, and 104 of FIG. To do.

(Configuration-Automated driving system-Bogie-Control unit)
The control unit 15 is a control means for controlling the trolley 1, and specifically, a CPU, various programs interpreted and executed on the CPU (basic control programs such as an OS, and specific functions started on the OS). It is a computer configured to include an application program to be realized) and an internal memory such as a RAM for storing the program and various data (the same applies to the control unit of other devices). The processing performed by each unit of the control unit 15 will be described later.

(Configuration-Automated driving system-Camera)
The camera 2 in FIG. 2 is an imaging means that captures an imaging range that is a target range for imaging. The specific type and configuration of the camera 2 are arbitrary, but for example, they are connected to the server device 5 so as to be communicable, and as an example, the cameras 21 and 22 of FIG. 1 are provided. The camera 21 is a camera that captures the first-floor portion 901 that is the self-imaging range, and for example, "ID 21" is set and recorded as a camera ID that identifies the self. The camera 22 is a camera that captures the second floor portion 902, which is the self-imaging range, and for example, "ID 22" is set and recorded as a camera ID that identifies the self.

(Configuration-Automated driving system-Communication device)
The communication device 3 of FIG. 2 is a communication means that enables wireless communication between the server device 5 and the carriage 1 and the terminal device 4. The specific type and configuration of the communication device 3 is arbitrary, but for example, it can be configured by using a known wireless communication circuit or the like.

(Configuration-Automated driving system-Terminal device)
The terminal device 4 of FIG. 2 is a display input means that functions as a user interface of the server device 5. The specific type and configuration of the terminal device 4 is arbitrary, but for example, it has at least a function as a display means for displaying information and an input means for inputting an operation from a user. As an example, a display A smartphone, tablet terminal, or the like provided with a touch screen or the like configured by stacking a touch pad on the device can be used.

(Configuration-Automated driving system-Server device)
The server device 5 of FIG. 2 is a detection system, and is, for example, communicably connected to the camera 2 and wirelessly connected to the carriage 1 and the terminal device 4 via the communication device 3. As an example, a recording unit 51 and a control unit 52 are provided.

(Configuration-Automated driving system-Server device-Recording unit)
For example, drawing information, equipment information, and trolley information are stored in the recording unit 51.

(Configuration-Automated driving system-Server device-Recording unit-Drawing information)
"Drawing information" is drawing information that specifies a drawing indicating a target area. Although this drawing information is arbitrary, for example, a case where information showing a plan view of the first floor portion 901 and the second floor portion 902 of FIG. 1 is used will be described. Further, in the drawing specified by this drawing information, it will be described below assuming that the position and direction can be specified with reference to an arbitrary reference object (for example, a grid core or the like). The specific storage method of such drawing information is arbitrary, but it is stored in, for example, when the administrator inputs the information via an input means (not shown) of the server device 5 or the terminal device 4. (The same applies to the equipment information shown below).

(Configuration-Automated driving system-Server device-Recording unit-Equipment information)
The "equipment information" is information that identifies the equipment of the automatic operation system 100, and is, for example, information that identifies the camera 2. FIG. 4 is a diagram illustrating equipment information. In the "equipment information", for example, the item "camera ID" and the item "installation position information" are associated with the information corresponding to each item. The information corresponding to the item "camera ID" is the above-mentioned camera ID ("ID21", "ID22", etc. in FIG. 4). The information corresponding to the item "installation position information" is the installation position information that specifies the position where the camera 2 is installed (in FIG. 4, it is the information that specifies the number of floors on which the camera 2 is installed, and is "the first floor". , Or "second floor"). Here, for example, the specific installation position, imaging direction, angle of view, etc. of the camera 2 on each floor are predetermined, and the image captured by the camera 2 is reflected in the image by recognizing the image. The position of the object will be described as being identifiable on the drawing specified by the above-mentioned drawing information.

(Configuration-Automated driving system-Server device-Recording unit-Bogie information)
The "trolley information" is trolley information that identifies the trolley 1. FIG. 5 is a diagram illustrating dolly information. In the "trolley information", for example, the item "trolley name information", the item "trolley ID", the item "trolley position information", and the item "trolley direction information" are associated with each other. There is. The information corresponding to the item "Bogie name information" is the bogie name information for specifying the name of the bogie (in FIG. 5, "Unit 1" for specifying the name of the bogie 101 in FIG. 1 and the name of the bogie 102 are specified. "Unit 2", "Unit 3" that specifies the name of the trolley 103, and "Unit 4" that specifies the name of the trolley 104). The information corresponding to the item "trolley ID" is the above-mentioned trolley ID (in FIG. 5, the above-mentioned "ID101" and the like). The information corresponding to the item "trolley position information" is the trolley position information that specifies the position where the trolley 1 is provided. The trolley position information is arbitrary, but in FIG. 5, for example, in FIG. 5, the number of floors on which the trolley is provided and a predetermined arbitrary position on the drawing specified by the above-mentioned drawing information on the floor are used as a reference. The following will be described by using the above-mentioned coordinates and using "1st floor, (x11, y11)" or the like that specifies that the number of floors is the 1st floor and the coordinates are (x11, y11). It should be noted that the coordinates “(x11, y11)” and the like specifically described here are described for convenience of explanation.

The information corresponding to the item "trolley direction information" is the trolley direction information that specifies the direction in which the front side of the trolley 1 is directed as the direction of the trolley 1. The definition of "front side of the carriage 1" is arbitrary, and is, for example, either the −Y side or the + Y side in the carriage 1 of FIG. 3, for example, when the above-mentioned motor is rotated clockwise. The direction in which the trolley 1 advances is the front side of the trolley 1, and the direction in which the trolley 1 advances when the motor is rotated counterclockwise is the back side of the trolley 1 (that is, the front side of the trolley 1). The other side). Further, the trolley direction information is arbitrary, but for example, in FIG. 5, the direction of "north" (+ Y direction) is set to 0 degrees with reference to the center of each trolley 1 in FIG. 1, and the clockwise direction is 360 degrees. The information shown is used, that is, as an example, "90" indicating 90 degrees corresponding to "east" not shown in FIG. 5 and 180 degrees corresponding to south shown in FIG. 5 are shown. This will be described below with reference to "180" and the like. The specific storage method of such trolley information is arbitrary, but for example, the trolley name information and the trolley ID are stored in the same manner as the above-mentioned drawing information, and the trolley position information and the trolley direction are stored. The information is stored in the detection process described later.

(Configuration-Automated driving system-Server device-Control unit)
The control unit 52 is a control means for controlling the server device 5. The control unit 52 includes, for example, a movement unit 521, an acquisition unit 522, a detection unit 523, and a movement operation unit 524 in terms of functional concept. The moving unit 521 is a moving means for moving the carriage 1. The acquisition unit 522 is an acquisition means for acquiring images of the first floor portion 901 and the second floor portion 902, which are target areas in which the trolley 1 may exist, which is captured before and after the moving unit 521 moves the trolley 1. The detection unit 523 is a difference between the images of the first floor portion 901 and the second floor portion 902 captured before and after moving the trolley 1 acquired by the acquisition unit 522 (specifically, before and after moving the trolley 1). A detection means for detecting the trolley 1 based on the difference between the images of the first floor portion 901 captured and the difference between the images of the second floor portion 902 captured before and after moving the trolley 1. is there. The movement operation unit 524 is a movement operation means for operating the movement of an object based on the detection result of the detection means. Each process performed by the control unit 52 will be described later.

Next, the detection process and the movement process executed by the automatic operation system 100 configured in this way will be described.

(Processing-Detection processing)
First, the detection process will be described. FIG. 6 is a flowchart of the detection process (steps are abbreviated as “S” in the following description of each process). The "detection process" is generally a process executed by the server device 5, and is, for example, a process for detecting a dolly 1. The timing at which this detection process is executed is arbitrary, but for example, when the user selects the dolly name of the dolly 1 of FIG. 1 via a touch panel (not shown) of the terminal device 4, the dolly corresponding to the dolly name is selected. The terminal device 4 transmits an operation signal including an ID to the server device 5, and the control unit 52 of the server device 5 is activated when the operation signal is received via the communication device 3, and the detection process is performed. I will explain from the place where it started. Here, for example, when the user selects the dolly names "Unit 1" to "Unit 4" of the trolleys 101 to 104 in FIG. 1 via the terminal device 4, the terminal device 4 has "ID 101" to "ID 101" to ". The case where the operation signal including "ID 104" is transmitted to the server device 5 and the server device 5 receives the operation signal and the detection process is started will be described as an example.

In SA1 of FIG. 6, the moving unit 521 selects a dolly ID that has not yet been selected. Specifically, although it is arbitrary, for example, one trolley ID that has not yet been selected is selected from the trolley ID included in the operation signal received at the start of the detection process. Here, for example, "ID101" is selected from "ID101" to "ID104".

In SA2 of FIG. 6, the moving unit 521 moves the carriage 1. Specifically, although it is arbitrary, for example, the trolley ID selected in SA1 is acquired, a forward tremor signal including the acquired trolley ID and a forward tremor command is generated, and the generated forward tremor signal is used in the communication device 3. It is transmitted to the trolley 1 via. Then, the transmitted forward fine movement signal reaches all the carriages 1 and is received by each carriage 1. The "forward fine movement command" is a command for advancing the carriage 1 by a predetermined distance (for example, about 10 cm to 30 cm). For example, a motor (not shown) of the traveling portion 12 of the carriage 1 is specified clockwise. It is a command to rotate by the amount corresponding to the distance. Here, for example, by acquiring the trolley ID "ID101" selected in SA1 and generating and transmitting a forward tremor signal including the acquired trolley ID "ID101" and a forward tremor command, "ID101" The forward tremor signal including "" will be received by the carriages 101 to 104 of FIG.

On the other hand, the control unit 15 of the trolley 1 that has received the forward tremor signal acquires the trolley ID included in the received forward tremor signal, and the trolley ID stored in its own recording unit 14 and the acquired trolley ID. If each of these trolley IDs does not match each other, it is judged that it is not a forward tremor signal for itself and is not controlled. If each trolley ID matches each other, it is determined that it is not a forward tremor signal for itself. Determining that it is a signal, the motor (not shown) of the traveling unit 12 is rotated clockwise to advance the carriage 1 by a predetermined distance.

7 and 8 are plan views of the first floor portion, and FIG. 9 is a plan view of the second floor portion. Here, for example, since the control unit 15 of the carriages 101 to 104 in FIG. 1 receives the forward fine movement signal including the “ID 101”, the control units 15 of the carriages 102 to 104 are included in the forward fine movement signal. Since the ID "101" and the own bogie IDs "ID102" to "ID104" do not match each other, it is determined that the signal is not a forward fine movement signal for the self and is not controlled. On the other hand, the control unit 15 of the trolley 101 uses the forward tremor signal for itself because the trolley ID "101" included in the forward fine movement signal and the own trolley ID "ID101" match each other. Determining that there is, the motor (not shown) of the traveling unit 12 is rotated clockwise to advance the carriage 101 by a predetermined distance. In this case, the carriage 101 moves from the position shown in FIG. 7 toward the position shown in FIG. 8 toward the south side (−Y direction) by a predetermined distance.

In SA3 of FIG. 6, the acquisition unit 522 acquires images of the target area captured before and after the moving unit 521 moves the carriage 1. Specifically, although it is arbitrary, for example, the camera 2 in FIG. 2 captures an image of its own imaging range at predetermined time intervals (for example, every 0.5 seconds to 1.0 seconds, etc.). The captured imaging time is specified by an arbitrary method (for example, a method in which the camera 2 is provided with a timing means such as a timer and is specified by using the timing result of the timing means), and the captured image and the specified imaging are specified. The time and its own camera ID are associated with each other and transmitted to the server device 5, and the control unit 52 of the server device 5 associates the information (image, imaging time, and camera ID) from the camera 2 side with each other. A case where the recording unit 51 is configured to store the information) will be described. That is, the process of accumulating the above-mentioned "information in which the image, the imaging time, and the camera ID are associated with each other" in the recording unit 51 is executed in parallel with the detection process described here. It will be described as being configured so that "information in which the image, the imaging time, and the camera ID are associated with each other" before and after moving the carriage 1 is accumulated in the recording unit 51. The "information in which the image, the imaging time, and the camera ID are associated with each other" will be referred to as "imaging-related information" and will be described below. That is, a case where "imaging-related information" including images captured by the camera 2 at predetermined time intervals is stored in the recording unit 51 of the server device 5 will be described.

For details on the processing of SA3 in FIG. 6, for example, among the "imaging-related information" recorded in the recording unit 51, the information before moving the carriage 1 by SA2 (hereinafter, "pre-movement imaging-related information"". ), And the information after the trolley 1 is moved by SA2 (hereinafter, "post-movement imaging-related information") is recorded in the equipment information of FIG. 5 for each camera ID included in the "imaging-related information". Identify all IDs and acquire the identified information.

More specifically, for example, it is assumed that the server device 5 is provided with a time measuring means (not shown) such as a timer (a time measuring means for measuring the time corresponding to the time measuring means of the camera 2). The time when the forward fine movement signal is transmitted by SA2 is specified based on the time measurement result of (more specifically, it is assumed that the time measurement result of the time measuring means when the forward fine movement signal is transmitted by SA2 is recorded in the recording unit 51. , Based on this timekeeping result, specify the time when the forward tremor signal was transmitted by SA2). Next, in the "imaging-related information" recorded in the recording unit 51, the "imaging-related information" in which the time immediately before the time when the specified forward tremor signal is transmitted is the imaging time is shown for each camera ID. All the camera IDs recorded in the equipment information of No. 5 are specified, and the specified "imaging-related information" is acquired as "pre-movement imaging-related information". Next, in the "imaging-related information" recorded in the recording unit 51, the "imaging-related information" in which the time after the time when the specified forward tremor signal is transmitted is the imaging time is shown for each camera ID. All the camera IDs recorded in the equipment information of No. 5 are specified, and the specified "imaging-related information" is acquired as "post-movement imaging-related information". Regarding the time after this, the trolley 1 is set to a predetermined waiting time (for example, the processing distance included in the forward tremor command of the SA2) in consideration of the time for the trolley 1 to move after transmitting the forward tremor signal. The time is sufficiently longer than the time when the vehicle finishes moving (4 seconds or more longer, etc.), and the time after 5 seconds to 8 seconds, which is a predetermined time in consideration of the vehicle speed of the trolley 1, etc.) It may be adopted. Next, the image included in the "pre-movement imaging-related information" is acquired as an image of the target area captured before the moving unit 521 moves the carriage 1, and is also included in the "post-movement imaging-related information". The image is acquired as an image of the target area captured after the moving unit 521 moves the carriage 1.

Here, for example, as an image of the target area captured before moving the trolley 1 associated with the camera ID 21 (that is, an image of the first floor portion 901 captured by the camera 21 before moving the trolley 1). , An image of the first floor portion 901 illustrated in FIG. 7 is acquired, and an image of the target area (that is, the trolley 1) captured after moving the trolley 1 associated with the camera ID 21 is obtained. As an image of the first floor portion 901 captured by the camera 21 after being moved), an image of the first floor portion 901 shown in FIG. 8 is acquired. Further, as an image of the target area captured before and after moving the carriage 1 associated with the camera ID 22 (that is, an image of the second floor portion 902 captured by the camera 22 before and after moving the carriage 1), FIG. The second-floor portion 902 illustrated in the above is imaged to obtain images similar to each other.

In SA4 of FIG. 6, the detection unit 523 executes the trolley detection process. FIG. 10 is a flowchart of the trolley detection process. The "trolley detection process" is, for example, a process of detecting a trolley based on an image acquired by SA3.

In SB1 of FIG. 10, the detection unit 523 captured the image acquired by the SA3 with reference to the camera ID of the “imaging-related information” before moving the trolley 1, which was imaged by the same camera 2 to each other. It is divided into a combination of an image of the target area (hereinafter, "target area image before movement") and an image of the target area captured after moving the trolley 1 (hereinafter, "target area image after movement"). Here, for example, a combination of images obtained by capturing the first floor portion 901 of FIGS. 7 and 8 based on the camera ID “ID21”, and the second floor of FIG. 9 based on the camera ID “ID22”. Part 902 is divided into a combination of captured images.

In SB2 of FIG. 10, the detection unit 523 selects an image of an unselected combination from the images of the combination divided by SB1. Here, for example, a combination of the image of the first floor portion 901 of FIG. 7 which is the “pre-movement target area image” and the image of the first floor portion 901 of FIG. 8 which is the “post-movement target area image” is selected.

In SB3 of FIG. 10, the detection unit 523 may or may not have the dolly 1 to be detected corresponding to the dolly ID selected in SA1 of FIG. 6 in the target area corresponding to the image selected in SB2. To judge. Specifically, although it is arbitrary, for example, it is determined whether or not the trolley 1 exists by performing image recognition on the "pre-movement target area image" and the "post-movement target area image" selected in SB2. Then, if no trolley 1 can be recognized by image recognition in at least one of the "target area image before movement" or the "target area image after movement", there is no possibility that the trolley 1 to be detected exists. It is determined that it is (NO of SB3), and the process proceeds to SB6. Further, if one or more trolleys 1 can be recognized by image recognition in both the "target area image before movement" and the "target area image after movement", there is a possibility that the trolley 1 to be detected exists. Judgment (YES of SB3), and shift to SB4. Here, for example, four trolleys 1 can be recognized in image recognition for the image of the first floor portion 901 of FIG. 7 and the image of the first floor portion 901 of FIG. 8, so that the trolley 1 to be detected may exist in this case. Judge as having sex. In the image recognition here, since the four carriages 1 are similar to each other, the carriages 101 to 104 cannot be identified.

In SB4 of FIG. 10, the detection unit 523 determines whether or not there is a difference between the “pre-movement target area image” and the “post-movement target area image” selected in SB2. Specifically, although it is arbitrary, for example, the reference camera ID in which the “pre-movement target area image” and the “post-movement target area image” selected in SB2 are divided by SB1 is specified, and the equipment information in FIG. 4 is referred to. Then, the installation position information corresponding to the specified camera ID is specified, and in the drawing information of the recording unit 51 in FIG. 2, the drawing information of the number of floors corresponding to the number of floors of the specified installation position information is selected in SB2 as "move". By referring to the drawing information corresponding to the "pre-target area image" and the "post-movement target area image", the "pre-movement target area image" and the "post-movement target area image" selected in SB2 are recognized by the image recognition of SB3. The position of the trolley 1 is specified by using the coordinates on the drawing specified by the above-mentioned referenced drawing information, and is determined based on the specific result. Then, when the coordinates of the trolley 1 specified for the "pre-movement target area image" and the "post-movement target area image" are all the same, it is determined that there is no difference (NO in SB4), and the detection target is detected. Without detecting the existence of the trolley 1 (that is, the trolley to be detected in the target area corresponding to the reference camera ID obtained by dividing the "pre-movement target area image" and the "post-movement target area image" selected in SB2 by SB1. Detects that 1 does not exist) and shifts to SB6. Further, when the coordinates of the trolley 1 specified for the "target area image before movement" and the "target area image after movement" are not all the same (that is, when there are different ones), it is determined that there is a difference. (YES of SB4), the existence of the trolley 1 to be detected is detected (that is, the "pre-movement target area image" and the "post-movement target area image" selected in SB2 correspond to the reference camera ID divided by SB1. Detects that the trolley 1 to be detected exists in the target area), and shifts to SB5.

Here, for example, in the image of the first floor portion 901 of FIG. 7 and the image of the first floor portion 901 of FIG. 8 selected in SB2, the plan view of the first floor portion 901 of the drawing information of the recording unit 51 of FIG. 2 is specified. By referring to the drawing information, the position of the trolley 1 recognized by the image recognition of SB3 for each image is specified by using the coordinates on the plan view of the first floor portion 901. As an example, the trolley of FIG. 7 is specified. "(X11, y11)" which is the coordinates of 101 and "(x13, y11)" which is the coordinates of the trolley 102, and "(x11, y00)" which is the coordinates of the trolley 101 of FIG. 8 and the coordinates of the trolley 102. "(X13, y11)" and the like are specified, and since the coordinates of the trolley 101 are different between "(x11, y11)" and "(x11, y00)", it is determined that there is a difference. It is detected that the trolley 1 to be detected exists in the first floor portion 901.

In SB5 of FIG. 10, the detection unit 523 detects the position and orientation of the dolly 1 to be detected. Specifically, although it is optional, for example, first, the reference camera ID in which the “pre-movement target area image” and the “post-movement target area image” selected in SB2 are divided by SB1 is specified, and the equipment information in FIG. 4 is specified. The installation position information corresponding to the specified camera ID is specified with reference to, and the number of floors specified by the specified installation position information is detected as the number of floors on which the trolley 1 to be detected is provided. Next, in the coordinates of the trolley 1 specified by SB4 (coordinates on the drawing specified by the drawing information of the recording unit 51), the "pre-movement target area image" and the "post-movement target area image" are different from each other. Identify the coordinates. Next, the coordinates of the "pre-movement target area image" in each of the specified coordinates are specified as the position before the movement of the trolley 1 to be detected, and the "post-movement target area image" in each of the specified positions is specified. The coordinates of the above are specified as the positions after the movement of the trolley 1 to be detected, and among these specified positions, the position before the movement of the trolley 1 is detected as the position of the trolley 1, and in the "pre-movement target area image". The trolley 1 provided at the detected position is detected as the trolley to be detected. Next, the direction from the position before the movement of the identified trolley 1 to be detected to the position after the movement of the trolley 1 to be detected is detected as the front side direction of the trolley 1 to be detected and returned. ..

Here, for example, first, the “pre-movement target area image” and the “post-movement target area image” selected in SB2 are separated by SB1 to identify the reference camera ID “ID21”, and the equipment information in FIG. 4 is obtained. By referring to the specified camera ID, the installation position information "1st floor" corresponding to the specified camera ID "ID21" is specified, and the specified "1st floor" is detected as the number of floors on which the trolley 1 to be detected is provided. .. Next, at the position of the trolley 1 specified by SB4 (coordinates on the drawing specified by the drawing information of the recording unit 51), the "pre-movement target area image" and the "post-movement target area image" are different from each other. The coordinates "(x11, y11)" and "(x11, y00)" of the above-mentioned trolley 101 are specified as the positions. Next, "(x11, y11)", which is the position of the "pre-movement target area image" in each of the specified positions, is specified as the position before the movement of the trolley 1 to be detected, and the specified positions are also specified. "(X11, y00)", which is the position of the "post-movement target area image" in the above, is specified as the position after the movement of the trolley 1 to be detected, and among these specified positions, before the movement of the trolley 1. The position "(x11, y11)" is detected as the position of the trolley 1, and the trolley 101 provided at the detected position "(x11, y11)" in the "pre-movement target area image" is detected. Detected as a dolly. Next, the direction from "(x11, y11)", which is the position before the movement of the identified trolley 101 to be detected, to "(x11, y00)", which is the position after the movement of the trolley 1 to be detected. The direction of "south" (-Y direction) is detected as the direction of the front side of the dolly 1 to be detected, and the vehicle returns.

On the other hand, after determining that there is no possibility that the trolley 1 to be detected exists in the processing of SB3 in FIG. 10 (NO in SB3), or in the processing of SB4, it is determined that there is no difference (SB4). NO) In SB6 executed after, the detection unit 523 determines whether or not to return the carriage detection process. Specifically, it is arbitrary, but for example, all the combinations divided by SB1 are determined based on whether or not they are selected by SB2. Then, when it is determined that all of them have been selected, it is determined that the carriage detection process is returned (YES in SB6), and the return is performed. Further, when it is determined that not all of them have been selected, it is determined that the carriage detection process does not return (NO of SB6), the process proceeds to SB2, and the above-mentioned process is repeated.

In SA5 of FIG. 6, the moving unit 521 returns to the position before the movement in SA2 by moving the carriage 1. Specifically, although it is arbitrary, for example, the trolley ID selected in SA1 is acquired, a reverse tremor signal including the acquired trolley ID and a reverse tremor command is generated, and the generated reverse tremor signal is used in the communication device 3. It is transmitted to the trolley 1 via. Then, the transmitted reverse fine movement signal reaches all the carriages 1 and is received by each carriage 1. The "backward fine movement command" is a command for moving the bogie 1 backward by a predetermined distance (for example, the same as the predetermined distance of the forward fine movement command, about 10 cm to 30 cm), and for example, the traveling of the bogie 1. This is a command for rotating a motor (not shown) of unit 12 counterclockwise by a predetermined distance. Here, for example, by acquiring the trolley ID "ID101" selected in SA1, generating and transmitting a forward / backward tremor signal including the acquired trolley ID "ID101" and a reverse tremor command, " The reverse fine movement signal including "ID101" will be received by the carriages 101 to 104 of FIG.

On the other hand, the control unit 15 of the trolley 1 that has received the reverse tremor signal acquires the trolley ID included in the received reverse tremor signal, performs the same processing as that described in SA2, and performs the reverse tremor signal for itself. When it is determined that the above is true, the motor (not shown) of the traveling unit 12 is rotated counterclockwise to move the carriage 1 backward by a predetermined distance.

Here, for example, in the control unit 15 of the dolly 101 of FIG. 8, the dolly ID “101” included in the reverse fine movement signal and the own dolly ID “ID 101” match each other. Determining that it is a reverse tremor signal with respect to itself, the motor (not shown) of the traveling unit 12 is rotated counterclockwise to move the dolly 101 backward by a predetermined distance. In this case, the dolly 101 moves from the position shown in FIG. 8 toward the position shown in FIG. 7 toward the north side (+ Y direction) by a predetermined distance, and returns to the position before the movement in SA2.

In SA6 of FIG. 6, the detection unit 523 stores the trolley position information in the trolley information of FIG. 5 based on the processing result of SA4. Specifically, although it is arbitrary, for example, after acquiring the trolley ID selected in SA1 and the number of floors, coordinates, and orientation detected in SB5 in FIG. 10, the above-mentioned trolley information in FIG. 5 is described above. The information corresponding to the acquired floor number and coordinates is stored as the trolley position information corresponding to the acquired trolley ID, and the trolley direction information corresponding to the acquired trolley ID in the trolley information of FIG. 5 is acquired. Stores the information corresponding to the orientation. Here, for example, the dolly ID "ID101" selected in SA1 is acquired, and the number of floors "1st floor" detected in SB5 of FIG. 10, the coordinates "(x11, y11)", and the orientation. After acquiring the "south", the information shown at the top of the trolley information of FIG. 5 is stored.

Here, for example, in the trolley detection process of FIG. 10, it is assumed that the floor number, coordinates, and orientation detected by SB5 are not detected, but in such a case, the SA6 process is skipped. It may be possible to shift to SA7.

In SA7 of FIG. 6, the control unit 52 determines whether or not to end the detection process. Specifically, it is arbitrary, but for example, it is determined based on whether or not all the trolley IDs included in the operation signal received at the start of the detection process are selected by SA1. Then, when it is determined that all of them have been selected, it is determined that the detection process is terminated (YES of SA7), and the process is terminated. Further, when it is determined that not all of them have been selected, it is determined that the detection process is not completed (NO of SA7), the process proceeds to SA1, and the above-mentioned process is repeated. This ends the detection process.

(Processing-Move processing)
Next, the movement process will be described. The "movement process" is generally a process executed by the server device 5, and is, for example, a process of operating the movement of the carriage 1 based on the detection result of the detection unit 523. The timing at which this movement process is executed is arbitrary, but for example, by performing the detection process of FIG. 6, the dolly name corresponding to the dolly ID in which the dolly position information and the dolly direction information in the dolly information of FIG. 5 are stored. Is configured to be displayed and notified to the user of the terminal device 4 by transmitting the server device 5 to the terminal device 4 via the communication device 3. Then, when the user who confirms the dolly name inputs the dolly name of one of the dolly names displayed on the touch panel of the terminal device 4 and the destination information of the dolly 1, the dolly name corresponds to the dolly name. When the terminal device 4 transmits a moving signal including the dolly ID and the destination information to the server device 5 and the control unit 52 of the server device 5 receives the moving signal via the communication device 3, the moving process is performed. It is assumed that the movement process is started, and the description will be made from the place where the movement process is started. Here, for example, the dolly name of the dolly 101 in FIG. 1 is "Unit 1", and the coordinates of the second floor portion 902 as the destination information for specifying the destination of movement of the "Unit 1", "2nd floor, ( When "x99, y99)" is input, the terminal device 4 transmits a mobile signal including "ID101" and "second floor, (x99, y99)" to the server device 5, and the server device 5 receives the operation signal. The case where the movement process is started will be described as an example.

The movement operation unit 524 remotely controls the dolly 1 toward the destination to move the dolly 1. Specifically, although it is optional, for example, roughly, as described in SA3 of FIG. 6, in the image of the target area transmitted from the camera 2 at predetermined time intervals, the dolly position information and the dolly of FIG. 5 are shown. By recognizing the image using the direction information, the dolly 1 of the dolly ID included in the movement signal received at the start of the movement processing is remoted to the destination specified by the destination information included in the movement signal. Operate and move.

Specifically, for example, first, the trolley ID included in the movement signal received at the start of the movement processing is acquired, and in the trolley information of FIG. 5, the trolley position information and the trolley direction information corresponding to the acquired trolley ID are obtained. To get. Next, in the image of the target area transmitted from the camera 2 at predetermined time intervals, in the image of the number of floors specified by the above-mentioned acquired trolley position information, at the position specified by the above-mentioned acquired trolley position information. The provided trolley 1 is recognized as the trolley 1 to be moved, and the orientation of the trolley 1 specified by the acquired trolley direction information described above is recognized as the recognized trolley 1. Next, with reference to the drawing information recorded in the recording unit 51 of FIG. 2 as appropriate, the recognized trolley 1 to be moved is moved to the destination specified by the destination information included in the movement signal. A movement route, which is a route for making the vehicle, is generated in consideration of the orientation of the dolly 1 recognized above. Next, in the image transmitted from the camera 2, the purpose is along the above-mentioned generated movement route while specifying the position of the trolley 1 to be moved and the situation around the trolley 1 (for example, the presence or absence of an obstacle). Move to the ground. The specific control for moving the trolley 1 here is arbitrary. For example, in consideration of the orientation of the trolley 1 recognized above at an appropriate timing via the communication device 3, the trolley 1 in FIG. 2 It is controlled by wirelessly transmitting a control signal for controlling the traveling unit 12 and the steering unit 13.

FIG. 11 is a diagram illustrating the movement route of the dolly. Here, for example, first, the trolley ID "ID101" included in the movement signal received at the start of the movement processing is acquired, and in the trolley information of FIG. 5, the acquired trolley ID "ID101" is used. The corresponding trolley position information "1st floor, (x11, y11)" and the trolley direction information "180" are acquired. Next, in the image of the target area transmitted from the camera 2 at predetermined time intervals, the “1st floor” which is the number of floors specified by the “1st floor, (x11, y11)” which is the above-mentioned acquired trolley position information. In the image from the camera 21 that captured the image, the trolley 101 provided at the position specified by the above-mentioned acquired trolley position information "1st floor, (x11, y11)" is recognized as the trolley 1 to be moved. Further, the direction of "south" corresponding to the direction "180" of the dolly 101 specified by the above-mentioned acquired dolly direction information is recognized as the direction of the recognized dolly 101. Next, with reference to the drawing information recorded in the recording unit 51 of FIG. 2 as appropriate, the recognized trolley 101 to be moved is referred to the destination information included in the movement signal, "2nd floor, ( The movement route shown in FIG. 11 is generated as a route for moving to the destination specified by "x99, y99)". Next, while specifying the position of the trolley 101 and the situation around the trolley 101 (for example, the presence or absence of obstacles) in the image transmitted from the camera 2, the user moves to the destination along the generated movement route described above. Let me. Then, by processing in this way, the situation around the dolly 101, which may change from moment to moment, is grasped based on the image received from the camera 2 at predetermined time intervals, and then the dolly 101 is automatically operated. It is possible to move to the destination. Here, by also controlling the elevator 903, the dolly 101 can be moved to the destination. This ends the move process.

(Effect of this embodiment)
According to the present embodiment, the difference between the images of the first floor portion 901 and the second floor portion 902 of the warehouse 900 captured before and after moving the trolley 1 (that is, the difference between the images of the warehouse 900 before and after moving the trolley 1). By detecting the trolley 1 based on the difference between the images of the first floor portion 901 and the difference between the images of the second floor portion 902 of the warehouse 900 before and after moving the trolley 1, for example, a shield (for example, a pillar or a pillar) Even if a part of the trolley 1 is hidden by the installed materials or the like and is not shown in the image, the trolley 1 can be detected, so that the trolley 1 can be reliably detected. Further, for example, since it is not necessary to install a marker, a lamp, or the like for detection on the trolley 1, the trolley 1 can be detected with high efficiency. Further, for example, it is possible to reliably detect the trolleys 1 that have been randomly arranged by a person without any intention or relationship in the order of use with high efficiency.

Further, by detecting the presence or absence of the dolly 1 in the first floor portion 901 and the second floor portion 902 of each warehouse 900 in which the dolly 1 can exist, for example, arbitrary processing related to the dolly 1 (for example, considering the presence or absence of the dolly 1) is taken into consideration. , Processing for remote control of the dolly 1 etc.) can be performed.

Further, by detecting the position of the dolly 1, for example, it is possible to perform arbitrary processing related to the dolly 1 (for example, a process of remotely controlling the dolly 1) in consideration of the position of the dolly 1.

Further, by detecting the orientation of the trolley 1, for example, it is possible to perform arbitrary processing related to the trolley 1 (for example, a processing for remotely controlling the trolley 1) in consideration of the orientation of the trolley 1.

Further, by operating the movement of the trolley 1 based on the detection result of the detection unit 523, for example, the trolley 1 can be moved, so that the convenience of the trolley 1 can be improved.

[III] Modifications to the Embodiment The embodiments according to the present invention have been described above, but the specific configuration and means of the present invention are within the scope of the technical idea of each invention described in the claims. Can be arbitrarily modified and improved. Hereinafter, such a modification will be described.

(About the problem to be solved and the effect of the invention)
First, the problem to be solved by the invention and the effect of the invention are not limited to the above-mentioned contents, and may differ depending on the implementation environment and the details of the configuration of the invention, and only a part of the above-mentioned problems. Or may produce only some of the effects described above.

(About distribution and integration)
Further, each of the above-mentioned electrical components is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of dispersion or integration of each part is not limited to the one shown in the figure, and all or part of them are functionally or physically dispersed or integrated in arbitrary units according to various loads and usage conditions. Can be configured. Further, the "system" in the present application is not limited to a system composed of a plurality of devices, but includes a system composed of a single device. Further, the "device" in the present application is not limited to a device composed of a single device, but includes a device composed of a plurality of devices.

(About shape, numerical value, structure, time series)
With respect to the components illustrated in the embodiments and drawings, the shapes, numerical values, or the interrelationships of the structures or time series of the plurality of components shall be arbitrarily modified and improved within the scope of the technical idea of the present invention. Can be done.

(About movement (1))
Further, in SA2 of FIG. 6 of the above-described embodiment, it has been described that the vehicle is advanced by a predetermined distance (for example, about 10 cm to 30 cm), but the present invention is not limited to this. For example, it may be moved backward by a predetermined distance, may be moved by a distance shorter than about 10 cm to 30 cm, or may be moved by a distance longer than the said 10 cm to 30 cm.

(About movement (2))
Further, the case where the carriage 1 is returned to the original position has been described in SA5 of FIG. 6 of the above embodiment, but the present invention is not limited to this. For example, SA5 may be omitted and the state may be left as it is moved by SA2. In this case, in SB5 of FIG. 10, the position after the movement of the carriage 1 may be detected as the position of the carriage 1.

(About the camera)
Moreover, various cameras may be used as the camera 2 of FIG. 2 of the above-described embodiment. For example, a monocular camera may be used, a stereo camera may be used, or an RGB-D camera may be used. In addition, for example, these cameras can be configured so that the size of the luggage on the trolley 1 can be recognized by calibrating the size of the object that can be imaged in advance, or the type of luggage can be recognized by image recognition by AI. May be configured so that the quantity in the construction site can be grasped by specifying.

(About trolley detection processing (1))
Further, the image recognition performed on the "pre-movement target area image" and the "post-movement target area image" performed in SB3 of FIG. 10 of the above embodiment is optional, but for example, the trolley 1 to which the automatic driving system 100 is applied. A model that can distinguish the trolley 1 from other objects is generated based on the outer shape of the trolley 1 by machine learning or the like performed in advance, and the generated model is used for image recognition. Alternatively, it may be configured to perform other known image recognition. In this case, the trolley 1 is loaded with the luggage 8, but since the shape and size of the loaded luggage 8 can be assumed in advance, the model is generated by reflecting the shape and size of the luggage 8. You may. Further, for example, it is conceivable that a part of the trolley 1 is hidden by another trolley 1 or a shield and is not captured in the image of the camera 2. Therefore, even if a part of the trolley 1 is not captured in this way, the trolley 1 In order to be able to recognize the image, a model may be generated by machine learning assuming such a case.

(About dolly detection processing (2))
Further, the processing of SB3 and SB4 in FIG. 10 of the above embodiment may be arbitrarily changed. For example, instead of SB3 and SB4, the following processing may be performed. Specifically, the distance moved by SA2 in FIG. 6 is recorded, and in the "pre-movement target area image" and "post-movement target area image" selected in SB2, the object moved by the recorded distance is recorded. When it is determined whether or not the object exists and it is determined that the object that has moved by the recorded distance exists, the moving object is detected as the trolley 1 to be detected, and the object is transferred to SB5 and recorded. When it is determined that there is no object that has moved by a distance, the trolley 1 to be detected may not be detected, and the SB 6 may be set after the object. Further, in the case of such a configuration, for example, when various devices and people other than the trolley 1 exist in the warehouse 900 and the devices and people move, the “pre-movement target area image” selected in SB2 is selected. In the "image of the target area after movement", there may be a plurality of objects that have moved by the recorded distance. In this case, the following processing may be performed. For example, when image recognition is performed on a plurality of objects to determine whether or not it is the outer shape of the trolley 1, and it is determined that the image is an image of the trolley 1, the determined object is the trolley 1 to be detected. It may be configured to detect a thing. Alternatively, for example, by performing the same processing as SA2 and SA3 in FIG. 6, the processing for moving the carriage 1 is performed again, and in the "pre-movement target area image" and "post-movement target area image" selected in SB2. , It may be configured to determine whether or not there is an object that has moved by the recorded distance. The process of moving the dolly 1 may be repeated until it is determined that there is only one object that has moved by the recorded distance, or until it is determined that there is no object that has moved by the recorded distance. Good. Further, when this process is repeated, the distance moved by SA2 may be gradually increased, randomly changed, or gradually shortened to the extent that the image can be recognized.

(About dolly detection processing (3))
Further, in the above-mentioned "(About the carriage detection process (No. 1))", the case where the image recognition is performed by paying attention to the outer shape of the carriage 1 is described, but the present invention is not limited to this. For example, a marker (that is, an object indicating that the trolley 1 is a target in the trolley detection process) at a predetermined position of the trolley 1 or a predetermined position of a load (for example, a single pipe or the like) loaded on the trolley 1. May be provided, the marker may be recognized by image recognition, and the processing of SB3 and SB4 in FIG. 10 may be executed focusing on the recognized marker. As the "marker" here, any object can be used, but for example, a medium (paper or the like) to which code information (two-dimensional code information) is attached may be used, or A medium having a mutually common shape (for example, a triangle or a star shape) attached to each trolley 1 may be used, or the above-mentioned code information or the common shape is described on the trolley 1 and the said The described one may be used as a marker. Further, as the "marker" here, for example, an object having a three-dimensional structure having an arbitrary shape may be used, and as an example, a spherical object (that is, a ball shape) coated with a retroreflective material is used as a trolley. It may be attached to an arbitrary position of 1 or an arbitrary position of a load (for example, a single pipe or the like) loaded on the trolley 1, and the spherical object may be used as a marker. Whether or not the material (paint) is applied to the three-dimensional structure here, and the material (paint) to be applied are arbitrary. For example, any material other than the retroreflective material (for example, fluorescent paint or Luminescent paint) may be applied, or no material may be applied.

(About safety measures)
Further, safety measures may be taken for the automatic driving system 100 of the above embodiment. For example, when a speaker or an indicator light or the like is provided on the carriage 1 and the carriage 1 is moved by the SA2 or SA5 of FIG. 6, the moving unit 521 transmits an alarm signal to the carriage 1 to output an alarm sound from the speaker. Or, the indicator light may be made to emit light for an alarm to notify the movement of the trolley 1 to the periphery of the trolley 1 and give an alarm. Further, by mounting a contact sensor or an impact sensor on the trolley 1, the trolley 1 stops by detecting contact with an obstacle, another trolley, or a material and issuing an error, and at the same time, the trolley 1 is attached to the server device 5. It may be configured to reply an abnormality to the response. Further, before moving the carriage 1 with the SA2 or SA5 of FIG. 6, the moving unit 521 recognizes the image received from the camera 2 to image the peripheral region of the carriage 1 (for example, the four carriages of FIG. 1). It is determined whether or not a person exists in an area having a radius of 1 m to 1.5 centered on 1), and if it is determined that the person does not exist, each of these processes is executed and the person exists. If it is determined, these processes may be temporarily stopped until no one exists.

(About manual operation)
Further, the dolly 1 of the above embodiment may be configured so that the user can manually drive the dolly 1 based on the driving operation input by the user via the input means of the terminal device 4. In this case, the presence of the trolley 1 is displayed by the control unit 52 of the server device 5 transmitting the trolley position information and the trolley direction information in the trolley information of FIG. 5 stored in the detection process of FIG. 6 to the terminal device 4. The user may be notified of the presence / absence, the presence position, and the direction of the presence, and the user may be configured to perform remote control based on the notified information. In this case, for example, the camera 2 may process the image to be transmitted to the terminal device 4 at predetermined time intervals, or the server device 5 may process the image to be transmitted to the terminal device 4. Then, the trolley 1 may be configured to be manually operated remotely while the user visually recognizes the inside of the warehouse 900 on the terminal device 4 side.

(About detection processing and movement processing)
Further, the detection process of FIG. 6 and the movement process (not shown) of the above embodiment may be appropriately combined, or some processes may be changed. For example, when the user inputs a plurality of arbitrary trolley names before performing the detection process and also inputs the destination information, the detection process is performed, and then the movement process is continuously performed. May be good. In this case, for example, the detection process and the movement process may be continuously performed on the trolley 1 corresponding to one trolley name among the plurality of trolley names. In this case, for example, the trolley 1 to be detected is all hidden in the detection process due to various causes (for example, it is hidden by another trolley 1 and does not appear in the image, or the battery of the trolley 1 is insufficient). It is assumed that the processing of SB3 in FIG. 10 determines that there is no possibility that the dolly 1 to be detected exists, or the processing of SB4 determines that there is no difference. To. In this case, among the trolleys 1 that could be recognized, the one that was easy to move to the destination was moved, and after moving all the trolleys 1 that were initially visible (the trolley 1 shown in the image), they could not be seen again. It may be configured to try to recognize the dolly 1 (the dolly 1 not shown in the image), and if it can be seen, perform the process of starting the movement in the same manner.

(About judgment of image difference)
Further, the concept of the detection threshold value may be adopted for the determination of the difference in SB4 of FIG. 10 of the above embodiment. Specifically, for example, it is assumed that a predetermined distance (for example, 10 cm to 15 cm) is set as a detection threshold, and the coordinates of the trolley 1 specified for the "pre-movement target area image" and the "post-movement target area image" If the distance from the coordinates of the trolley 1 specified for "is less than the detection threshold, it is determined that there is no difference (NO in SB4), while the trolley 1 specified for the" pre-movement target area image " If the distance between the coordinates and the coordinates of the trolley 1 specified for the "image of the target area after movement" is equal to or greater than the detection threshold, it may be determined that there is a difference (YES in SB4). .. With this configuration, for example, it is possible to detect the trolley 1 using the movement amount of the trolley 1, and in particular, when the detection threshold value is set to 10 cm, an unknown movement of 10 cm or more has occurred. The dolly 1 can be detected.

(About combination)
Further, the techniques of the above-described embodiments and modifications may be arbitrarily combined.

(Additional note)
The detection system of Appendix 1 is a detection system that detects a movable object, and includes a moving means for moving the object and the object imaged before and after the moving means moves the object. The object is detected based on the difference between the acquisition means for acquiring an image of a possible target area and the images of the target area captured before and after moving the object acquired by the acquisition means. It is provided with a detection means.

The detection system of Appendix 2 is the detection system of Appendix 1, wherein the detection means detects the presence or absence of the object in the target region.

The detection system of Appendix 3 is the detection system according to Appendix 1 or 2, wherein the detection means detects the position of the object.

The detection system according to the appendix 4 is the detection system according to any one of the items 1 to 3, wherein the detection means detects the orientation of the object.

The detection system of Appendix 5 includes a movement operation means for operating the movement of the object based on the detection result of the detection means in the detection system according to any one of the items 1 to 4.

The detection program of Appendix 6 is a detection program that detects a movable object, and is a moving means for moving the object and the target imaged before and after the moving means moves the object. The object is based on the difference between the acquisition means for acquiring an image of the target area in which the object can exist and the images of the target area captured before and after moving the object acquired by the acquisition means. It functions as a detection means for detecting.

(Effect of appendix)
According to the detection system described in Appendix 1 and the detection program described in Appendix 6, the object is detected, for example, by detecting the object based on the difference between the images of the target area captured before and after moving the object. , Even if a part of the object is hidden by a shield (for example, a pillar or an installed material) and is not shown in the image, the object can be detected, so that the object can be reliably detected. It becomes possible to do. Further, for example, it is not necessary to install a marker, a lamp, or the like for detection on the object, so that the object can be detected with high efficiency. Further, for example, it is possible to reliably detect objects that have been randomly arranged by a person without any intention or relationship in the order of use with high efficiency.

According to the detection system described in Appendix 2, by detecting the presence or absence of the object in each target area where the object may exist, for example, arbitrary processing related to the object (for example, considering the presence or absence of the object) is performed. It is possible to perform processing (such as remote control of an object).

According to the detection system described in Appendix 3, by detecting the position of the object, for example, arbitrary processing related to the object (for example, processing for remotely controlling the object) in consideration of the position of the object can be performed. It becomes possible to do.

According to the detection system described in Appendix 4, by detecting the orientation of the object, for example, arbitrary processing related to the object (for example, processing for remotely controlling the object) in consideration of the orientation of the object can be performed. It becomes possible to do.

According to the detection system described in Appendix 5, for example, the object can be moved by manipulating the movement of the object based on the detection result of the detection means, so that the convenience regarding the object is improved. It becomes possible.

1 dolly 2 camera 3 communication device 4 terminal device 5 server device 8 luggage 11 communication unit 12 traveling unit 13 steering unit 14 recording unit 15 control unit 21 camera 22 camera 51 recording unit 52 control unit 100 automatic driving system 101 dolly 102 dolly 103 dolly 104 Bogie 121 Wheel 521 Moving part 522 Acquisition part 523 Detection part 524 Moving operation part 900 Warehouse 901 1st floor part 902 2nd floor part 903 Elevator

Claims (6)

It is a detection system that detects movable objects.
A means of moving the object and
An acquisition means for acquiring an image of a target area in which the object may exist, which is captured before and after the moving means moves the object.
A detection means for detecting the object based on the difference between the images of the target region captured before and after moving the object acquired by the acquisition means, and a detection means for detecting the object.
Detection system with. The detecting means detects the presence or absence of the object in the target area.
The detection system according to claim 1. The detecting means detects the position of the object.
The detection system according to claim 1 or 2. The detecting means detects the orientation of the object.
The detection system according to any one of claims 1 to 3. A movement operation means for operating the movement of the object based on the detection result of the detection means is provided.
The detection system according to any one of claims 1 to 4. A detection program that detects movable objects
Computer,
A means of moving the object and
An acquisition means for acquiring an image of a target area in which the object may exist, which is captured before and after the moving means moves the object.
A detection means for detecting the object based on the difference between the images of the target region captured before and after moving the object acquired by the acquisition means, and a detection means for detecting the object.
A detection program that functions as.

Images