JP2019015681A - Position estimation system and position estimation method - Google Patents

Abstract

To provide a position estimation system and a position estimation method capable of precisely estimating a position of a moving body, such as a forklift.SOLUTION: A position estimation system includes a plurality of identifiers, an imaging part and an information processor. The plurality of identifiers are installed in a predetermined posture in a predetermined position on a traveling surface of a moving body, and furnished with each different piece of first identification information. The imaging part is mounted to the moving body, and is configured so as to be capable of imaging at least one identifier from among the plurality of identifiers. The information processor includes: an image processing part for extracting the first identification information of an identifier within an image, and second identification information relating to a relative positional relationship between the identifier within the image and the moving body by processing the image captured by the imaging part; and an estimation part for estimating a position on the traveling surface of the moving body, based on the first and second identification information.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a position estimation system and a position estimation method for estimating the position of a moving object on a running surface.

  Conventionally, various methods are known as a method for estimating the position of a moving body such as a forklift that works indoors.

  For example, in Patent Document 1, a plurality of labels each having a different pattern are arranged on a ceiling portion of a space such as a warehouse, and an image obtained by capturing the labels with a camera attached to a forklift, A technique for estimating the position of a forklift is described.

  According to this technique, since the plurality of labels provided on the ceiling of the space have different patterns, the position of the forklift can be estimated based on the label pattern in the captured image.

JP 11-29299 A

  However, the invention described in Patent Document 1 estimates the position of the forklift only from the pattern, position, and orientation of the label in the image in which the label is imaged, and can roughly estimate the position of the forklift in the warehouse. It is difficult to estimate the position of the forklift with higher accuracy.

  In view of the circumstances as described above, an object of the present invention is to provide a position estimation system and a position estimation method capable of estimating the position of a moving body such as a forklift with high accuracy.

In order to achieve the above object, a position estimation system according to an aspect of the present invention includes a plurality of identifiers, an imaging unit, and an information processing device.
The plurality of identifiers are installed in a predetermined posture at a predetermined position on the traveling surface of the moving body, and different first identification information is given to each.
The imaging unit is attached to the moving body and configured to capture at least one identifier among the plurality of identifiers.
The information processing apparatus processes the image picked up by the image pickup unit, so that the first identification information of the identifier in the image and the relative positional relationship between the identifier in the image and the moving object are processed. And an estimation unit for estimating the position of the moving body on the traveling surface based on the first and second identification information.

  According to the above configuration, the position of the moving body on the traveling surface is estimated based on the absolute position of the identifier on the traveling surface and the relative positional relationship of the moving body with respect to this identifier. Thereby, the position on the traveling surface of the moving body can be estimated with higher accuracy.

  The image processing unit may calculate a distance between the identifier in the image and the moving body as the second identification information.

  The image processing unit may calculate a direction of the moving body with respect to an identifier in the image as the second identification information.

The image processing unit calculates an orientation of the moving body by processing an image in which an identifier having anisotropy with respect to an arrangement direction in which the plurality of identifiers are arranged along a uniaxial direction is processed. Also good.
This makes it easier to estimate the direction of the moving body with respect to the identifier.

The plurality of identifiers have a rectangular shape, and one corner is provided with an index portion indicating that the corner is different from the other corner,
The image processing unit may calculate the orientation of the moving body based on the position of the index unit in the image.
This makes it easier to estimate the traveling direction and direction of the moving body from the image obtained by capturing the identifier.

The image processing unit may extract the first identification information including at least two types of identification symbols having different attributes, for each identification symbol.
Thereby, since the kind of information to extract is limited rather than extracting the whole 1st identification information, the misrecognition at the time of recognizing 1st identification information is suppressed.

The information processing apparatus may further include a communication unit configured to be able to output information regarding the position of the moving body on the traveling surface.
Thereby, the estimated position of the moving body on the traveling surface can be notified to the outside.

Further comprising a detection unit configured to be able to detect the amount of movement of the moving body,
The estimation unit may further estimate the position of the mobile body on the travel surface based on the position of the mobile body on the travel surface estimated by the estimation unit and the output of the detection unit.
As a result, the position of the moving object can be estimated even if the identifier is not within the field of view of the imaging unit.

In order to achieve the above object, a position estimation method according to an aspect of the present invention is provided in a predetermined posture on a traveling surface of a moving body in a predetermined posture, and each of which is provided with different first identification information. At least one of the identifiers is imaged.
By processing the image in which the identifier is imaged, first identification information of the identifier in the image and second identification information regarding the relative positional relationship between the identifier in the image and the moving object are extracted. Is done.
Based on the first and second identification information, the position of the moving body on the traveling surface is estimated.

  As described above, according to the present invention, it is possible to provide a position estimation system and a position estimation method capable of estimating the position of a moving body such as a forklift with high accuracy.

It is a figure which shows an example of the mobile body to which the position estimation system which concerns on embodiment of this invention is applied. It is a figure which shows the running surface on which the said mobile body drive | works. It is a figure which shows the structural example of the identifier of the said embodiment. It is a figure which shows the structural example of the identifier of the said embodiment. It is a functional block diagram which shows the structural example of the information processing apparatus of the said embodiment. It is a flowchart which shows the position estimation method of the said position estimation system. It is an image figure which shows the image which the imaging part of the said embodiment imaged the identifier. It is an image figure which shows the image which the imaging part of the said embodiment imaged the identifier.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the present embodiment, for example, a position estimation system for a moving body such as a forklift for cargo handling traveling in a factory will be described. In the following drawings, the X, Y, and Z axis directions indicate triaxial directions orthogonal to each other, and the Z axis direction corresponds to the height direction.

<Outline of position estimation system>
FIG. 1 is a diagram illustrating a moving body 1 to which the position estimation system 100 according to the present embodiment is applied, and FIG. 2 is a diagram illustrating a running surface S of the moving body 1. The configuration of the position estimation system 100 is not limited to the following description.

  The position estimation system 100 according to the present embodiment includes a plurality of identifiers 10, an imaging unit 11, an information processing device 12, a display unit 13, a detection unit 14, and an operation management system 15 (see FIG. 5). Have.

  The plurality of identifiers 10 are installed at predetermined positions on the traveling surface S of the moving body 1 in a predetermined posture. The traveling surface S is typically a floor surface on which the moving body 1 travels indoors, such as a factory, and is divided in an area from the luggage storage area by a white line W or the like. A plurality of linear or curved passages extending in a direction intersecting with the line.

  The plurality of identifiers 10 are installed on the traveling surface S at regular intervals along the X and Y axis directions, and have a shape showing anisotropy with respect to the X and Y axis directions. The interval R between the identifier 10 and the identifier 10 is not particularly limited, and is, for example, about several tens cm to several hundreds cm.

  Different first identification information I is given to each of the plurality of identifiers 10. In the example of FIG. 2, the first identification information I is composed of three-digit alphanumeric characters, but of course not limited to this, it may be composed of a character string of four digits or more (see FIGS. 3 and 4). . In the first identification information I shown in FIG. 2, the alphabetic symbols (“A”, “F”, “C”, etc.) in the preceding stage specify individual passages, and the intersection position between the passages is “P” or the like. Common symbols are used. The numerical symbols in the subsequent stage represent position information in each passage.

  The identifier 10 according to the present embodiment is typically rectangular, and an index portion 10a indicating that the corner portion is different from the other corner portions is provided at one corner portion. The indicator portion 10a is, for example, a notch formed in a corner portion of the identifier 10 (see FIG. 3) or a marking (see FIG. 4) applied to the corner portion.

  Thereby, when a plurality of identifiers 10 are regularly arranged in a uniaxial direction in a predetermined posture as shown in FIG. 2, a moving object is obtained from an image in which the identifiers 10 are captured using notches and markings as indices. 1 traveling direction, direction, etc. can be estimated. The shape of the identifier 10 is typically a rectangular shape, but is not limited to this, and any type such as a triangular shape or a rhombus shape may be used.

  FIGS. 3 and 4 are diagrams showing a configuration example of the identifier 10. The first identification information I is information indicating the location of the identifier 10 on the traveling surface S, and functions as an address of the traveling surface S.

  As shown in FIGS. 3 and 4, the first identification information I is composed of, for example, two types of character strings (identification symbols) having different attributes. As the character string constituting the first identification information I, typically, kana such as katakana and hiragana, alphanumeric characters such as numerals and alphabets, figures and the like are adopted, but not limited thereto, “@> = − A special character such as “” or a mathematical symbol may be employed.

  As shown in FIG. 1, the imaging unit 11 is attached to the rear of the moving body 1 and configured to be able to image the traveling surface S behind the moving body 1 in the traveling direction. Imaging conditions such as an inclination angle and a field angle of the optical axis of the imaging unit 11 with respect to the traveling surface S are input to the information processing apparatus 12 as known information. The imaging conditions are typically fixed, but may be variable. The imaging unit 11 is connected to the information processing apparatus 12 wirelessly or by wire and outputs a captured image to the information processing apparatus 12.

  The imaging unit 11 includes an image sensor such as a CCD (Charge Coupled Device) sensor or a CMOS (Complementary Metal Oxide Semiconductor) sensor, and acquires a moving image behind the moving body 1 in the traveling direction at a predetermined frame rate. The imaging unit 11 is typically a video camera such as a CCD camera. However, the imaging unit 11 is not limited thereto, and a still camera, a stereo camera, or the like that can obtain a still image behind the moving body 1 in the traveling direction at a predetermined imaging interval. It may be.

  The information processing apparatus 12 includes hardware necessary for a computer such as a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and an HDD (Hard Disk Drive). When the CPU loads a program stored in the ROM or HDD into the RAM and executes it, each block operation of the information processing apparatus 12 to be described later is controlled.

  The program is installed in the information processing apparatus 12 via, for example, various storage media (internal memory). Alternatively, program installation may be executed via the Internet or the like. In the present embodiment, for example, a PC (Personal Computer), a tablet terminal, or the like is used as the information processing apparatus 12, but any other computer may be used.

  The display unit 13 is configured to be able to display an image captured by the imaging unit 11, an image output from the information processing apparatus 12, and the like. The display unit 13 is a display device using, for example, liquid crystal, organic EL (Electro-Luminescence), or the like. The display unit 13 may have a configuration including an input unit for inputting a user operation. As the input unit, for example, an operation device such as a touch panel or a keyboard is employed.

  The detection unit 14 is provided in the moving body 1 and is connected to the information processing apparatus 12 wirelessly or by wire. The detection unit 14 is configured to detect the amount of movement of the moving body 1 and output it to the information processing apparatus 12. The detection unit 14 is, for example, a wheel speed sensor, an acceleration sensor, a rudder angle sensor, an angular velocity sensor, or the like, and the type thereof is not limited.

  The operation management system 15 acquires information regarding the position on the traveling surface S of the moving body 1 output from the information processing apparatus 12 (see FIG. 5). Based on this information, the operation management system 15 informs the user operating the moving body 1 of the current position, navigates the moving body 1, manages the movement locus of the moving body 1, etc., via the display unit 13. To do.

  FIG. 5 is a functional block diagram illustrating a configuration example of the information processing apparatus 12. As illustrated in FIG. 5, the information processing apparatus 12 includes an image processing unit 121, an estimation unit 122, a map data file 123, and a communication unit 124.

  The image processing unit 121 processes the image acquired from the imaging unit 11, thereby information about the first identification information I of the identifier 10 in the image and the relative positional relationship between the identifier 10 in the image and the moving body 1. (Hereinafter referred to as second identification information).

  The estimation unit 122 estimates the position of the moving body 1 on the traveling surface S based on the first identification information I and the second identification information.

  The map data file 123 is a database that stores information (hereinafter, position registration data) in which the first identification information I of the identifier 10 is associated with the absolute position of the identifier 10 on the traveling surface S. For example, the map data file 123 causes the display unit 13 to display the first identification information I and the absolute position of the identifier 10 on the traveling surface S as text data.

  The communication unit 124 is configured to output information related to the position of the moving body 1 on the traveling surface S to the operation management system 15 and acquire information from the operation management system 15. The communication unit 124 functions as an input / output interface of the information processing apparatus 12.

<Position estimation method>
FIG. 6 is a flowchart illustrating a method by which the position estimation system 100 estimates the position of the moving body 1 on the traveling surface S. Hereinafter, a method for estimating the position of the moving body 1 will be described with reference to FIG. 6 as appropriate.

[Application Example 1]
(Step S01: Location registration)
First, a plurality of identifiers 10 are arranged at regular intervals on a running surface S in an arbitrary running area (see FIG. 2). Next, position registration data in which the first identification information I assigned to the plurality of identifiers 10 and the absolute positions of the plurality of identifiers 10 in the travel area are associated with each other is created. And then. This data is stored in the information processing apparatus 12, and a database (map data file 123) is constructed.

(Step S02: Imaging)
Next, the imaging unit 11 attached to the moving body 1 that moves on the traveling surface S images the identifier 10. At this time, the imaging unit 11 images at least one identifier 10 among the plurality of identifiers 10 installed on the traveling surface S. In the present embodiment, the identifier 10 on the passage of the moving body 1 is typically imaged. However, the present invention is not limited to this, and the identifier 10 outside the passage may be imaged.

(Step S03: Determination of presence or absence of identifier)
The image processing unit 121 determines whether or not the identifier 10 is captured for the image acquired from the imaging unit 11. Here, when the image processing unit 121 determines that the identifier 10 is captured (YES in S03), the image processing unit 121 performs image processing to be described later.

(Step S04; Image processing)
The image processing unit 121 performs predetermined image processing on the image acquired from the imaging unit 11. Thereby, the first identification information I and the second identification information in the identifier 10 in the image are extracted.

  In the present embodiment, as an example of processing for extracting the first identification information I, the image processing unit 121 extracts a plurality of character strings having different attributes for each character string (identification symbol) having the same attribute. Thereby, since the kind of information to extract is limited rather than extracting the 1st identification information I whole, the misrecognition at the time of the image process part 121 recognizing the 1st identification information I is suppressed.

  For example, the first identification information I shown in FIG. 3 includes a 3-digit character string and a 4-digit number string. By recognizing in advance that the first three digits are katakana and the second four digits are numbers, the image processing unit 121 can identify the first three digits and the second four digits as different attributes. Therefore, misrecognition is suppressed. Similarly, for the combination of alphabetic characters and numbers shown in FIG. 4, for example, erroneous recognition between the alphabetic characters “B” and the numeric characters “8” is reliably prevented, so that the first identification information I Can be recognized with high accuracy.

  On the other hand, FIGS. 7 and 8 are image diagrams showing an image G in which the imaging unit 11 images the identifier 10. As an example of the process of extracting the second identification information, first, the image processing unit 121 performs, for example, a binarization process on the image G acquired from the imaging unit 11, so that the contour line of the identifier 10 in the image G The index part 10a is extracted. Thereby, the position and orientation of the identifier 10 in the image G are specified.

  Next, based on the position of the identifier 10 in the specified image G, the distance between the identifier 10 and the moving body 1 is calculated as second identification information. Specifically, for example, since the width L3 of the region (margin) other than the identifier 10 in the image G depends on the distance between the identifier 10 and the moving object 1, the image processing unit 121 is based on the width L3. The distance between the identifier 10 and the moving body 1 is calculated.

  Furthermore, the image processing unit 121 calculates the orientation of the moving body 1 with respect to the identifier 10 as the second identification information based on the identified orientation of the identifier 10 in the image G.

  Specifically, for example, when a linear virtual line passing through two arbitrary points E1 and E2 of the identifier 10 in the image G is L1, and a virtual line indicating the optical axis of the imaging unit 11 is L2, the virtual line By calculating the angle A formed by the lines L1 and L2, the direction of the moving body 1 with respect to the identifier 10 is calculated.

  Alternatively, when a plurality of identifiers 10 are arranged in a predetermined posture along a uniaxial direction (arrangement direction), the identifier 10 according to the present embodiment exhibits anisotropy with respect to the arrangement direction, and the indicator unit 10a (see FIG. 2), for example, as shown in FIG. 8, the angles B and C formed by the long side or the short side of the identifier 10 and the inclination angle D from the arrangement direction L4 of the virtual line L2 as shown in FIG. The direction of the moving body 1 with respect to the identifier 10 can also be calculated by comprehensively considering the position of the indicator portion 10a in the image G.

  Subsequently, the image processing unit 121 outputs the first identification information I and the second identification information extracted from the image obtained by capturing the identifier 10 to the estimation unit 122.

(Step S05: Position estimation)
The estimation unit 122 collates the first identification information I acquired from the image processing unit 121 with the position registration data registered in advance in the map data file 123, so that the identifier to which the first identification information I is assigned. The absolute position on the ten running surfaces S is specified.

  Next, the estimation unit 122 estimates the position of the moving body 1 in the travel area based on the absolute position of the identifier 10 on the identified travel surface S and the second identification information for the identifier 10.

  In other words, the estimation unit 122 is based on the absolute position of the identifier 10 on the traveling surface S and the relative positional relationship (distance, orientation, etc.) of the moving body 1 with respect to this identifier 10. Estimate the position. Thereby, it becomes possible to estimate the position on the traveling surface S of the moving body 1 with higher accuracy.

  In addition, the position estimation system 100 according to the present embodiment can estimate the position of the moving body 1 as long as it has a plurality of identifiers 10, the imaging unit 11, and the information processing device 12. Thereby, the number of parts can be reduced as compared with the conventional infrastructure cooperation type using, for example, wireless communication, and the cost can be reduced.

  Furthermore, since the position estimation system 100 can complete the device configuration within a limited space such as the inside of a building, the position estimation system 100 is not limited to the outdoors, and the interior of the mobile object 1 can be used indoors where GPS (Global Positioning System) cannot be used. It is possible to estimate the position.

  Subsequently, the estimation unit 122 outputs information on the position of the moving body 1 on the traveling surface S obtained by the method described above to the display unit 13 and the communication unit 124. Thereby, the user who steers the moving body 1 can confirm the estimated position of the moving body 1 and can grasp the estimated position via the operation management system 15. In addition, by accumulating the position information over time, it can be used for operation management of the mobile body 1.

[Application Example 2]
Next, another method for the position estimation system 100 to estimate the position of the moving body 1 on the traveling surface S will be described. Note that the description of the same steps as in Application Example 1 is omitted.

(Step S03: Determination of presence or absence of identifier)
The image processing unit 121 determines whether or not the identifier 10 is captured for the image acquired from the imaging unit 11. Here, when the image processing unit 121 determines that the identifier 10 is not captured (NO in S03), the estimation unit 122 estimates the position of the moving body 1 by a method described later.

(Step S05: Position estimation)
The estimation unit 122 estimates the position of the moving body 1 on the traveling surface S based on the output of the detection unit 14 attached to the moving body 1. Specifically, the estimation unit 122 estimates the position of the moving body 1 from the movement amount on the traveling surface S of the moving body 1 detected by the detection unit 14. The amount of movement is, for example, a movement distance from the identifier 10 imaged immediately before.

  In the position estimation system 100 according to the present embodiment, since the moving body 1 includes the detection unit 14, the moving body 1 moves between the identifier 10 and the identifier 10, and the identifier 10 falls within the field of view of the imaging unit 11. Even if it is not done, the position on the traveling surface S of the moving body 1 can be estimated.

  That is, the position of the moving body 1 on the traveling surface S can be estimated from the position of the moving body 1 on the traveling surface S estimated based on the identifier 10 captured immediately before and the amount of movement with respect to the identifier 10. . Thereby, the number of identifiers 10 arranged on the traveling surface S can be reduced, and the cost can be reduced.

[Application Example 3]
Next, another method for the position estimation system 100 to estimate the position of the moving body 1 on the traveling surface S will be described. Note that the description of the same steps as those in the application examples 1 and 2 is omitted.

(Step S05: Position estimation)
The estimation unit 122 detects the position of the moving body 1 in the traveling area estimated by the same method as in Application Example 1 and the movement of the moving body 1 on the traveling surface S detected by the same method as in Application Example 2. From the quantity, the position of the moving body 1 in the travel area is estimated.

  That is, the estimation unit 122 not only detects the absolute position of the identifier 10 on the traveling surface S and the relative positional relationship of the moving body 1 with respect to the identifier 10, but also on the traveling surface S of the moving body 1 detected by the detection unit 14. The position of the moving body 1 on the traveling surface S is further estimated based on the amount of movement. Thereby, the certainty in estimating the estimation part 122 in the position of the mobile body 1 on the driving | running | working surface S improves more.

  As mentioned above, although embodiment of this invention was described, this invention is not limited only to the above-mentioned embodiment, Of course, a various change can be added.

  For example, in the above embodiment, the position estimation system 100 is premised on being applied to one moving body 1, but is not limited thereto, and is applied to two or more moving bodies 1 moving on the traveling surface S. May be.

  Moreover, in the position estimation system 100 of the said embodiment, although it is the structure by which the information processing apparatus 12 and the imaging part 11 were provided separately, these may be provided integrally.

  Furthermore, although the position estimation system 100 of the said embodiment is typically applied to a forklift, it is not restricted to this. The position estimation system 100 may be applied to all moving bodies that can move on the traveling surface S, and its use is not limited. The moving body 1 is not limited to a manned moving body, and may be an unmanned moving body.

DESCRIPTION OF SYMBOLS 1 ...... Moving body 10 ... Identifier 11 ... Imaging part 12 ... Information processing device 13 ... Display part 14 ... Detection part 15 ... Operation management system 100 ... Position estimation system 121 .. Image processing unit 122.. Estimation unit 123.. Map data file 124.

Claims (9)

A plurality of identifiers installed in predetermined postures at predetermined positions on the traveling surface of the mobile body, each having different first identification information;
An imaging unit attached to the moving body and configured to image at least one of the plurality of identifiers;
By processing the image captured by the imaging unit, the first identification information of the identifier in the image, and the second identification information related to the relative positional relationship between the identifier in the image and the moving body An information processing apparatus comprising: an image processing unit that extracts the information; and an estimation unit that estimates a position of the moving body on the traveling surface based on the first and second identification information. . The position estimation system according to claim 1,
The image processing unit calculates a distance between an identifier in the image and the moving body as the second identification information. The position estimation system according to claim 1 or 2,
The image processing unit calculates a direction of the moving body with respect to an identifier in the image as the second identification information. The position estimation system according to claim 3,
The image processing unit calculates an orientation of the moving body by processing an image obtained by imaging an identifier having anisotropy with respect to an arrangement direction in which the plurality of identifiers are arranged along a uniaxial direction. Estimation system. The position estimation system according to claim 4,
The plurality of identifiers have a rectangular shape, and one corner is provided with an index portion indicating that the corner is different from the other corner,
The image processing unit calculates a direction of the moving body based on a position of the index unit in the image. The position estimation system according to any one of claims 1 to 5,
The first identification information includes at least two types of identification symbols having different attributes,
The image processing unit extracts the first identification information for each identification symbol. The position estimation system according to any one of claims 1 to 6,
The information processing apparatus further includes a communication unit configured to be able to output information on the position of the moving body on the traveling surface. The position estimation system according to any one of claims 1 to 7,
A detector configured to detect the amount of movement of the mobile body;
The said estimation part further estimates the position on the said driving surface of the said mobile body based on the position on the said driving surface of the said mobile body estimated by the said estimation part, and the output of the said detection part. At least one identifier is imaged among a plurality of identifiers that are installed in a predetermined posture at a predetermined position on the traveling surface of the moving object and are provided with different first identification information,
By processing the image in which the identifier is captured, the first identification information of the identifier in the image and the second identification information regarding the relative positional relationship between the identifier in the image and the moving body are extracted. And
A position estimation method for estimating a position of the moving body on the travel surface based on the first and second identification information.

Images