JP7300646B2 - Conveyor - Google Patents

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a conveying apparatus for conveying pallets.

A transportation device such as a forklift transports a pallet having a predetermined shape. The pallet is provided with holes (fork pockets), and the transport device is provided with forks that can be inserted into the fork pockets.

An operator of the carrier device must adjust the height of the forks, operate the carrier device while performing a steering operation, and insert the forks into the fork pockets.

JP 2017-151650 A

However, it is not easy for an inexperienced operator to successfully insert the fork into the fork pocket. If the forks collide with anything other than the fork pockets, the load on the pallet may collapse. Also, even if the forks are inserted into the fork pockets, if the forks collide with the inner walls of the fork pockets, the pallet may shift or unfavorable stress may be applied to the forks.

The present invention has been made in view of such problems, and one exemplary purpose of certain aspects thereof is to provide a transport apparatus capable of assisting an operator's operation.

One aspect of the present invention relates to a conveying device. The transport device can acquire a distance sensor, (i) a distance image in which pixel values represent distances based on the output of the distance sensor, and (ii) based on the distance image, a pallet or a specific part of the pallet. and a computing unit having a discriminator obtained by machine learning so that a certain detection target can be specified.

3D point cloud data obtained by ranging sensors such as TOF (Time Of Flight) sensors, LiDAR (Light Detection and Ranging), stereo cameras, and structure cameras is mapped to a 2D range image, and the range image is input. By constructing a discriminator that does so, it is possible to improve the accuracy of specifying the pallet or its part. The operator can be assisted by reflecting the obtained detection result in the operation of the conveying apparatus or notifying the operator.

The object to be detected may include pallet holes and girders separating the holes. Pallets come in a variety of shapes and structures, and they all have holes and girders separating the holes. Therefore, it is possible to detect the positions of holes in various pallets by installing a discriminator that detects girders.

The calculation unit may specify the positions of the holes based on the geometric information of the pallet held in advance.

After specifying the pallet or the specific part of the pallet to be detected, the result may be used to specify the hole in the pallet based on the range image. Constructing the classifier to identify pallet holes directly from the original range image may result in reduced accuracy. Therefore, by configuring a discriminator that identifies a pallet or a specific portion of the pallet, and further configuring a discriminator that identifies a hole based on the result, it is possible to improve the hole identification accuracy.

The transport device may further comprise a display for visually indicating to the operator the positions of the holes in the pallet. Accordingly, the operator can intuitively know the position of the hole by looking at the display unit.

The conveying device may further include a notification unit that notifies the operator whether or not the forks can be inserted into the holes of the pallet when the conveying device is run in the current state. Notification may be made visually or audibly.

The computing unit may generate position information indicating the existing position of the detection target from the range image by using the discriminator. The calculation unit may detect the position of the detection target with relatively high accuracy by template matching using a template image corresponding to the position information. That is, as preprocessing, a classifier performs rough position detection to narrow down the rough existence position or existence range of a specific portion. As the next step, by performing template matching using a template image suitable for the existence range within the narrowed down range, the position of the detection target can be accurately detected.

A plurality of template images may be prepared in advance. The calculation unit may specify the position of the detection target based on the output of the discriminator, and select one image corresponding to the specified position from among the plurality of template images.

The calculation unit may generate the template image in real time based on the existing position of the detection target.

It should be noted that arbitrary combinations of the above-described constituent elements and mutually replacing the constituent elements and expressions of the present invention in methods, devices, systems, etc. are also effective as aspects of the present invention.

According to the present invention, an operator's operation can be supported.

1 is a perspective view showing an external view of a forklift that is one aspect of a conveying device; FIG. It is a figure which shows an example of the cockpit of a forklift. FIGS. 3A to 3H are diagrams showing pallets to be transported by a forklift. 1 is a functional block diagram of a forklift according to an embodiment; FIG. 5(a) and 5(b) are diagrams for explaining the installation locations of the range finding sensors. It is a figure which shows an example of a distance image. FIGS. 7A and 7B are diagrams schematically showing specific parts to be detected. It is a figure which shows the distance image of the specific site|part of Fig.7 (a). It is a figure explaining the driving assistance using a display. FIG. 11 is a block diagram of part of a controller according to Modification 1; It is a figure which shows the relative positional relationship of a pallet and a ranging sensor. 12A and 12B are diagrams showing distance images obtained by photographing each of the plurality of pallets in FIG. 11 with a distance measuring sensor; FIG. FIG. 11 is a block diagram of a controller according to Modification 3; 14A to 14C are diagrams for explaining the processing of the controller according to Modification 3. FIG. 15A to 15C are diagrams for explaining the processing of the controller according to Modification 4. FIG.

BEST MODE FOR CARRYING OUT THE INVENTION The present invention will be described below based on preferred embodiments with reference to the drawings. The same or equivalent constituent elements, members, and processes shown in each drawing are denoted by the same reference numerals, and duplication of description will be omitted as appropriate. Moreover, the embodiments are illustrative rather than limiting the invention, and not all features and combinations thereof described in the embodiments are necessarily essential to the invention.

FIG. 1 is a perspective view showing an external view of a forklift, which is one mode of a transport device. The forklift 600 includes a vehicle body (chassis) 602 , a fork 604 , a lifting body (lift) 606 , a mast 608 and wheels 610 and 612 . A mast 608 is provided in front of the vehicle body 602 . Elevating body 606 is driven by a power source such as a hydraulic actuator (not shown in FIG. 1) to ascend and descend along mast 608 . A fork 604 is attached to the lifting body 606 for supporting a load. The forklift 600 carries a pallet with two forks 604 inserted into holes (fork pockets) of the pallet (not shown).

FIG. 2 is a diagram showing an example of a cockpit 700 of a forklift. The cockpit 700 includes an ignition switch 702 , a steering wheel 704 , a lift lever 706 , an accelerator pedal 708 , a brake pedal 710 , a dashboard 714 and a forward/reverse lever 712 .

The ignition switch 702 is a switch for starting the forklift 600 . A steering wheel 704 is an operation means for steering the forklift 600 . A lift lever 706 is an operating means for moving the lifting body 606 up and down. The accelerator pedal 708 is an operating means for controlling the rotation of wheels for traveling, and the travel of the forklift 600 is controlled by the operator adjusting the amount of depression. When the operator depresses the brake pedal 710, the brake is applied. The forward/reverse lever 712 is a lever for switching the traveling direction of the forklift 600 between forward and reverse. In addition, an inching pedal (not shown) may be provided.

The operator needs to operate the steering wheel 704 , the accelerator pedal 708 and the brake pedal 710 to control the position of the vehicle body, and operate the lift lever 706 to control the position of the fork 604 .

3A to 3H are diagrams showing pallets to be transported by the forklift 600. FIG. Pallet 800 has a top plate 806 , holes 802 and girders 804 . The shape of the pallet 800 is defined by JIS standards, and there are various shapes depending on the purpose and application. 3(a) to (h) are represented by JIS standards as S2, SU2, DP4, R4, RW2, D2, DU2 and D4, respectively. As shown in FIGS. 3(a) to 3(h), pallets generally come in various shapes and structures, and for unfamiliar operators, a plurality of operation input means (704, 706, 708, 710, 706) to accurately insert the fork into the fork pocket.

A configuration capable of assisting the scooping operation of a pallet will be described below. FIG. 4 is a functional block diagram of the forklift 300 according to the embodiment. FIG. 4 shows only the blocks related to assisting the scooping operation, and omits the other blocks.

The forklift 300 includes a distance measuring sensor 302 , a camera 303 , notification means 304 and a controller 310 . A distance measuring sensor 302 is attached in front of the forklift 300 to obtain distance information in front of the vehicle. Although not limited to this, as the ranging sensor 302, a ToF camera, LiDAR, a sensor using a structured light method, a stereo camera, or the like can be used. The distance measurement sensor 302 generates distance measurement data D1 including three-dimensional point cloud data of structures, articles, etc. located in front of the vehicle.

5(a) and 5(b) are diagrams for explaining the installation location of the distance measuring sensor 302. FIG. FIG. 5(a) is a top view. Since it is necessary to detect the position of the hole into which the fork should be inserted, it is preferable to place the distance measuring sensor 302 in the center of the two forks in the horizontal direction. As a result, when the fork is inserted into the pallet, the distance measuring sensor 302 can photograph the pallet from the front. In particular, when a specific portion including a girder is to be detected as will be described later, the distance image of the specific portion can be successfully captured by arranging the distance measuring sensor 302 in the center of the fork.

FIG. 5B is a side view. With respect to the vertical direction, it may be at the same height as the fork 604 as indicated by 302c, but it is preferable to provide it at a slightly upper position 302a (or a lower position 302b). This is because the upper surface S1 of the upper plate 806 of the pallet 800 (or the lower surface S2 of the upper plate 806) can thereby be reliably captured. This position also has the advantage of being less obscured by the fork or other vehicle structure during the final adjustment phase of the fork height.

Return to FIG. A camera 303 photographs the front of the forklift 300 . Image data D3 captured by camera 303 is displayed on display 306 . Although FIG. 4 shows the camera 303 and the distance measurement sensor 302 as separate functional blocks, this does not necessarily mean that they are independent of the distance measurement sensor 302 as hardware. 303 may also serve. For example, when the distance measuring sensor 302 is a TOF camera or a stereo camera, a monocular image (infrared intensity distribution, visible light monochrome image, visible light color image) primarily obtained therefrom can be used as the image data D3.

Controller 310 comprehensively controls forklift 300 . The controller 310 includes a distance image acquisition section 330 and a discriminator 340 . The distance image acquisition unit 330 generates a distance image D2 based on the distance measurement data D1 including point cloud data. The distance image D2 is image data having a plurality of pixels vertically and horizontally, and is data in which pixel values represent distances. FIG. 6 is a diagram showing an example of a distance image. Note that when the output of the distance measuring sensor 302 is distance data, the processing of the distance image acquisition unit 330 is simplified or omitted.

Return to FIG. The classifier 340 is configured by machine learning so as to identify the pallet or a specific part of the pallet based on the distance image D2.

The processing unit 350 identifies the positions of the holes in the pallet based on the detection result of the discriminator 340 . Based on the detected result, the notification means 304 is controlled to notify the operator. Notification means 304 may include display 306 and speaker 308 . A display 306 is used to visually notify the operator of pallet hole locations and other information. A speaker 308 can be used to audibly notify the operator of pallet locations and other information. Notification by notification means 304 will be described later.

The discriminator 340 and the processing unit 350 can be configured by a microcomputer 320 having an arithmetic processing unit (CPU) and memory, and a software program executed by the microcomputer 320 . Furthermore, the distance image acquisition section 330 can also be implemented as a function of the microcomputer 320 . Therefore, the distance image acquisition unit 330, the discriminator 340, and the processing unit 350 are not necessarily recognized as separate hardware, but represent functions realized by a combination of an arithmetic processing unit and software programs.

Alternatively, the distance image acquisition unit 330 and the discriminator 340 may be configured with separate hardware. For example, as an interface between the distance measuring sensor 302 and the microcomputer 320, hardware (chips) such as FPGA (Field Programmable Gate Array) and ASIC (Application Specific Integrated Circuit) may be installed. In this case, the processing of the distance image acquisition unit 330 may be executed by this hardware.

The above is the configuration of the forklift 300 . According to this forklift 300, the accuracy of specifying the pallet or its part can be improved by configuring the classifier that receives the distance image obtained by the distance measuring sensor by machine learning. The operator's operation can be assisted by reflecting the obtained detection result in the operation of the conveying apparatus or notifying the operator.

As another method for detecting a pallet and its specific parts, a method of detecting characteristic parts by pattern matching using three-dimensional point group data is also conceivable. However, this method has the problem that the object must always be measured from the same direction, and it is difficult to measure three-dimensional point cloud data of characteristic parts with high density and accuracy.

Next, a specific example of the discriminator 340 and its learning will be described. In one embodiment, the discriminator 340 is composed of a combination of linear SVM (Support Vector Machine) and HOG (Histograms of Oriented Gradients) features. Linear SVMs are widely used as classifiers that can determine whether an input belongs to one of two classes. In the field of general image processing, the input of linear SVM is image data whose pixel value is luminance, but in this embodiment, the input is a range image.

A linear SVM can also be trained to detect pairs of two holes directly. However, as shown in FIGS. 3(a) to 3(h), the shape and size of the holes vary depending on the type of pallet. Specifically, the width of the hole differs depending on the pallet. Also, some pallets have bottom plates, some do not, so the holes may be open or closed at the bottom. For this reason, there are cases where a classifier that learns holes directly as objects to be classified cannot obtain a sufficiently high classification rate.

Therefore, in order to further improve the identification rate, the present inventors focused on the holes 802 of the pallet 800 and the girders 804 that separate the holes 802, and configured the discriminator 340 with a part (specific part) including the girders 804 as the detection target. It was decided to. The girder 804 is an essential component of the pallet regardless of the pallet 800 standard, is suitable as a detection target, and can be expected to have a high identification rate.

FIGS. 7A and 7B are diagrams schematically showing a specific site 801 to be detected. A specific portion 801 includes a portion of an upper plate 806 , a portion of a lower plate 808 , a girder 804 and two holes 802 . This specific portion 801 can be grasped as including two facing U-shapes. FIG. 8 is a diagram showing a distance image of the specific portion 801 in FIG. 7(a).

As shown in FIG. 3(b), etc., some pallets do not have a lower plate. Therefore, as shown in FIG. 7(b), the classifier 340 may be learned by using the T-shape excluding the lower plate 808 as the specific portion 801. FIG.

The processing unit 350 holds geometric information of the pallet. The processing unit 350 can identify the positions of the two holes into which the forks should be inserted by arithmetic processing based on the position of the specific portion 801 identified by the discriminator 340 and the geometric information. For example, the geometric information may include the relative positional relationship between the position (coordinates) of the center of the pallet and the positions of the holes. The processing unit 350 can detect the center position of the pallet 800 based on the output of the discriminator 340, and set a position offset to the left and right by a predetermined amount from the center position as the position of the hole into which the fork should be inserted.

FIG. 7(c) is a diagram showing a portion of another palette. A pallet may have three (or more) holes, in which case one pallet contains two (or more) girders and two girders per pallet. It is also possible that the specific parts 801 are detected adjacent to each other. In this case, the center of the two specific parts 801 (that is, the center of the two girders 804) may be determined as the center position of the entire pallet 800. FIG.

Next, the notification means 304 will be described. FIG. 9 is a diagram illustrating driving assistance using the display 306. As shown in FIG. The display 306 displays image data D3 captured by the camera 303 in FIG. The processing unit 350 may display a graphic 810 that emphasizes the hole in the pallet 800 or its outer shape so as to overlap the image data D3. As shown in FIG. 9, image data D3 captured by camera 303 preferably includes two forks 604 . As a result, the operator can intuitively grasp the relative relationship between the fork 604 and the position of the hole while viewing the display 306 .

Further, the notification means 304 may notify the operator whether or not the fork 604 can be inserted into the hole 802 of the pallet 800 when the forklift is driven in the current state (steering angle, accelerator opening). This notification can be done using the display 306 of FIG. 9, for example, drawing shape 810 in a first color (eg, blue) if insertable, and drawing shape 810 in a second color if not insertable. color (eg red).

In addition to controlling the drawing color of the graphic 810, or in place of it, the speaker 308 may be used to inform the operator whether or not the insertion is possible.

The present invention has been described above based on the examples. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments, and that various design changes and modifications are possible, and that such modifications are within the scope of the present invention. By the way. Such modifications will be described below.

(Modification 1)
FIG. 10 is a block diagram of part of the controller 310A according to Modification 1. As shown in FIG. In this modification, two discriminators 340 and 342 are used. The identifier 340 at the front stage receives the distance image D2 as an input and is configured to be able to identify the pallet or a specific portion of the pallet. The discriminator 342 in the latter stage is trained to identify holes using the discrimination result of the discriminator 340 . For example, when the pallet is specified by the discriminator 340 in the preceding stage, the pallet portion of the distance image D2 is input to the discriminator 342 in the subsequent stage. The classifier 342 in the latter stage is configured to be able to identify the hole from the local range image. Constructing the classifier to identify pallet holes directly from the original range image may result in reduced accuracy. Therefore, by configuring a discriminator that identifies a pallet or a specific portion of the pallet, and further configuring a discriminator that identifies a hole based on the result, the hole identification accuracy can be improved. This modification has the advantage that the processing unit 350 does not need to hold the geometrical information of the pallet.

(Modification 2)
The discriminator 340 may be composed of a multi-layered neural network and may use deep learning.

(Modification 3)
When an object (subject) is photographed by a distance measuring sensor, the appearance of the object greatly differs depending on the positional relationship between the object and the distance measuring sensor. FIG. 11 is a diagram showing the relative positional relationship between the pallet 800 and the distance measuring sensor 302. As shown in FIG. For example, the pallet 800m# (#=l, c, r) is positioned at the same height as the distance measuring sensor 302, the pallet 800u# is positioned higher than the distance measuring sensor 302, and the pallet 800l# exists at a position lower than the ranging sensor 302 .

FIG. 12 is a diagram showing a distance image obtained by photographing each palette 800 of FIG. Depending on the relative positional relationship between the pallet 800 and the distance measuring sensor 302, the image of the specific portion (beam 804) to be detected by the discriminator 340 also varies greatly. If, in the learning stage of the discriminator 340, the machine learning of the discriminator 340 is performed using a teacher data group that includes only the specific part 801## of the pallet 800## that has a specific positional relationship (for example, 800mc that faces the pallet 800##) , there is a risk that the position detection accuracy of the specific portion 801** of the pallet 800** (where **≠##) in a different positional relationship will be degraded. This problem is conspicuous when the viewing angle of the ranging sensor 302 is wide.

In order to insert the fork 604 into the hole 802 of the pallet 800 without interference, it is necessary to control the relative position of the fork 604 and the pallet 800 with an accuracy higher than several centimeters. It is necessary to detect the position with a high accuracy of centimeters. According to the inventors' study, during the learning stage of the discriminator 340, when specific parts 801 of the pallet having various relative positional relationships are photographed and machine learning is performed using them as teacher data, the discriminator 340 Although it becomes easier to find the specific part 801 by , the accuracy of position detection may not be so high.

Modification 3 will explain a technique for solving this problem and improving the position detection accuracy. FIG. 13 is a block diagram of a controller 310B according to Modification 3. As shown in FIG. The controller 310B has a microcomputer 320B. The microcomputer 320B includes a pattern matching processor 360 and a template image generator 362 in addition to the discriminator 340 and processor 350 .

Discriminator 340 is as described above, and is configured to be able to detect specific part 801 using a prediction model obtained by prior machine learning. As described above, in Modification 3, it is assumed that the position detection accuracy of the specific part 801 in the classifier 340 is not so high.

The discriminator 340 extracts a partial range image D4, which is a portion of the original range image D2 including the detected specific part 801, and provides it to the pattern matching section 360. FIG. The discriminator 340 also generates position information D5 of the detected specific part for the template image generation unit 362 and supplies the position information D5 to the template image generation unit 362 . The position information D5 may be the coordinates of the detected specific part, or may be data indicating the range including the specific part when the original distance image D2 is divided into a plurality of ranges.

Template image generator 362 generates template image D6 based on position information D5. Note that this template image D6 is a distance image. When the position information D5 is given, the relative positional relationship between the specific part and the distance measuring sensor 302 is known. can be estimated. The template image generation unit 362 supplies the distance image corresponding to this positional relationship to the pattern matching unit 360 as a template image.

The pattern matching unit 360 uses the template image D6 corresponding to the positional information to detect the position of the specific region to be detected from the partial distance image D4 by template matching, and obtains the final positional information D7. Output.

The above is the configuration of the controller 310B according to the third modification. Next, the operation will be explained. FIGS. 14A to 14C are diagrams for explaining the processing of the controller 310B according to Modification 3. FIG. FIG. 14(a) shows a distance image D2 obtained in a certain situation. This distance image D2 is input to the discriminator 340, and the specific portion 801 of the pallet 800 is detected. However, the position detection accuracy is not so high, and the approximate position of the specific part 801 is detected.

A region of interest (ROI) is set so as to include the position of the specific part 801 detected by the classifier 340, and the ROI is supplied to the pattern matching section 360 as the partial distance image D4. FIG. 14(b) shows the partial distance image D4. The partial distance image D4 is a range in which the specific portion 801 can exist, and can be a rectangular area centered on the position P detected by the classifier 340, for example.

Template image generator 362 is prepared with a plurality of template images D6_1 to D6_N as shown in FIG. The template image generator 362 selects one of the plurality of template images D6_1 to D6_N according to the position information D5. The selected template image D6_i is suitable for the range in which the specific portion 801 can exist.

As shown in FIG. 14(d), the pattern matching unit 360 detects the template image D6_9 from the partial distance image D4 by template matching, and detects the position of the specific part 801 with high accuracy. The above is the operation of the controller 310B.

In this way, according to the controller 310B, as preprocessing, the discriminator 340 performs rough position detection to narrow down the rough existence position or existence range of the specific part. By performing template matching using a template image suitable for the existence range within the narrowed down range as the next step, the position of the detection target can be accurately detected.

(Modification 4)
15A to 15C are diagrams for explaining the processing of the controller according to Modification 4. FIG. FIG. 15(a) shows a distance image D2 obtained in a certain situation. This distance image D2 is input to the discriminator 340, and the specific portion 801 of the pallet 800 is detected. However, its position detection accuracy is not so high. For example, the distance image D2 is divided into a plurality of ranges 900_1 to 900_N (N=9 in this example). (ROI: Region Of Interest), and the ROI is supplied to the pattern matching unit 360 as the partial distance image D4. Also, position information D5 indicating the position of the ROI is output to the template image generator 362 .

Template images D6_1 to D6_9 corresponding to a plurality of ranges 900_1 to 900_9 are prepared in the template image generation unit 362, respectively. Since the current ROI is the ninth region, the template image generator 362 selects the template image D6_9 corresponding thereto and supplies it to the pattern matching unit 360 .

The pattern matching unit 360 detects the template image D6_9 from the partial distance image D4 by template matching, and detects the position of the specific part 801 with high accuracy. The above is the operation of the controller 310B.

In this way, according to the controller 310B, as preprocessing, the discriminator 340 performs rough position detection to narrow down the rough existence position or existence range of the specific part. By using a more appropriate template image within the narrowed range, the position of the detection target can be accurately detected.

(Modification 5)
The template image generator 362 may generate the template image D6 in real time based on the position information D5. The template image generator 362 stores the data of the three-dimensional model of the palette 800 . Then, by arranging the distance measuring sensor and the model of the pallet 800 in a virtual three-dimensional space, it is possible to generate a distance image of a specific portion that will be photographed by the distance measuring sensor. In this case, the position detection accuracy can be further improved.

(Modification 6)
Modifications 3 and 4 discussed differences in the relative positional relationship between the distance measuring sensor 302 and the pallet 800 in the horizontal/vertical directions. In Modified Example 6, the difference in distance in the depth direction between the distance measurement sensor 302 and the pallet 800 will be examined. The appearance from the distance measurement sensor 302 also changes depending on the distance between the palette 800 and the distance measurement sensor 302 in the depth direction. For example, even when the pallet 800 and the distance measuring sensor 302 face each other, the size of the distance image of the specific portion 801 changes when the distance between them changes.

Therefore, the position information D5 may include distance information between the range sensor 302 and the specific part 801 in the depth direction. The template image generator 362 can generate a template image according to the distance in the depth direction. Most simply, the template image may be enlarged or reduced according to the distance in the depth direction.

(Modification 7)
In the embodiments, a forklift was described as an example of a transport device, but the application of the present invention is not limited to that. It can be applied to various conveying devices that handle pallets.

600 forklift 602 vehicle body 604 fork 606 lifting body 608 mast 610 front wheel 612 rear wheel 700 cockpit 702 ignition switch 704 steering wheel 706 lift lever 708 accelerator pedal 710 brake pedal 712 forward/reverse lever 714 dashboard 300 forklift 302 range sensor 30 3 camera 304 Notification means 306 Display 308 Speaker 310 Controller 320 Microcomputer 330 Range image acquisition unit 340 Discriminator 350 Processing unit 360 Pattern matching unit 362 Template image generation unit D1 Range data D2 Range image D3 Image data D4 Partial range image D5 Position information D6 Template image 800 pallet 801 specific part 802 hole 804 column

Claims (8)

a ranging sensor;
(i) It is possible to acquire a distance image in which pixel values represent distances based on the output of the distance measuring sensor, and (ii) Based on the distance image, it is possible to specify a detection target, which is a pallet or a specific part of the pallet. A calculation unit having a discriminator configured by machine learning in
with
The calculating unit generates position information indicating the existing position of the detection target from the distance image by the classifier,
The conveying device, wherein the calculation unit detects the position of the detection target with relatively high accuracy by template matching using a template image corresponding to the position information. 2. The conveying apparatus according to claim 1, wherein said detection target includes girders separating holes of said pallet. 3. The conveying apparatus according to claim 2, wherein the calculation unit specifies the positions of the holes based on prestored geometric information of the pallet. 2. The conveying apparatus according to claim 1, wherein after specifying the detection target, the hole in the pallet is specified based on the distance image by using the result. 5. The conveying apparatus according to any one of claims 1 to 4, further comprising a display for visually displaying the positions of the holes in the pallet to an operator. 5. Any one of claims 1 to 4, further comprising a notification unit for notifying an operator whether or not the fork can be inserted into the hole of the pallet when the transport device is driven in the current state. A conveying device as described. A plurality of template images are prepared in advance,
2. The operation unit specifies the position of the detection target based on the output of the discriminator, and selects one of the plurality of template images corresponding to the specified position. 7. The conveying device according to any one of 6 . 7. The conveying apparatus according to any one of claims 1 to 6, wherein the calculation unit generates the template image in real time based on the existing position of the detection target.

Images