JPH01243104A - Mark identifying device in image pickup means - Google Patents

Abstract

PURPOSE:To obtain the degree of a freedom to immediately deal even with a layout change time by identifying a mark with an image pickup means on an unmanned vehicle, causing the unmanned vehicle to always recognize the present position of its own, and simultaneously, causing it to travel. CONSTITUTION:An unmanned vehicle 1 is travelable and steerable, a CCD camera 3 which is the image pickup means is mounted on a vehicle base, and further, marks 5 to be identifiable, respectively, are arrange-stuck on a ceiling surface 4 in prescribed positions. The unmanned vehicle 1 image-picks up the ceiling 4 by the CCD camera 3, detects and identifies the marks 5, and thereby, it recognizes the present position and proceeding direction of its own. Thus, it is sufficient that only the data of coordinates given to the unmanned vehicle 1 are changed at the time of changing a traveling route, and other changes of a hardware can be made unnecessary.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a mark identification device in an imaging means, and more particularly to a device for guiding an unmanned vehicle based on image information of the imaging means.

[Background of the invention]

The guidance method of the above-mentioned unmanned vehicle (hereinafter simply referred to as unmanned vehicle) is to lay a guidance wire such as an electromagnetic induction wire or optical tape on the floor during the course of the vehicle, and to detect the guidance by detecting the guidance installed on the unmanned vehicle. Many fixed-route guidance systems for unmanned vehicles, which detect the position of unmanned vehicles and control the steering of the unmanned vehicles so that they follow the guide line, are currently in practical use.

However, the fixed route guidance method has a disadvantage in that there is no flexibility in changing the driving course because the driving course is permanently set. Furthermore, the method using electromagnetic induction wires has the problem of requiring a great deal of time and effort to bury the guide wires, and the method using optical tape has the problem that the tape may be damaged due to foot traffic, etc. There is a problem in that guidance errors occur due to dirt or damage.

Therefore, in order to solve the above problems, several new guidance methods other than the fixed route guidance method are currently being considered. One of the new guidance methods is one that guides unmanned vehicles based on image information. Rapid improvements in the performance of image processing technology and microcomputers in recent years, as well as significant reductions in the prices of components such as microcomputers, memory, and A-D/D-A converters, have led to the use of small and inexpensive images in unmanned vehicles. It has become possible to incorporate a processing system and is attracting attention as a next-generation guidance method.

A method for guiding an unmanned vehicle based on the above image information (hereinafter,
For example, as an image guidance method (simply referred to as an image guidance method),
The technology described in Publication No. 144106, that is, an imaging device is placed directly above and along the driving path, the imaging device performs visual recognition of the unmanned vehicle, and detects the amount of driving state of the unmanned vehicle. 2. Description of the Related Art There is a known technique for guiding an unmanned vehicle by transmitting the detection result to the steering and traveling device of the unmanned vehicle via a wireless communication device.

However, in the conventional technology described above, the degree of freedom of the unmanned vehicle is limited to some extent. In other words, even though the price has become cheaper, it is still economically difficult to install somewhat expensive imaging equipment (including its attached computing equipment and communication equipment) throughout the building where unmanned vehicles are installed. As mentioned above, they have no choice but to be placed along the travel route. Therefore, when changing the layout of a driving route or a building, a problem arises in that the imaging device has to be reinstalled on the new driving path. Furthermore, the basic problem with the above conventional example is that the unmanned vehicle does not know its own position by seeing it with its own eyes, but rather with the eyes of others on the ground. The purpose is to know one's own position by being taught.

In the future, more intelligent non-vehicle vehicles will inevitably be required to see and make judgments with their own eyes. In other words, rather than simply receiving commands such as "go left,""gostraight," and "stop" from the ground side, the user does not simply receive commands such as "go left,""gostraight," or "stop." By guiding itself by comparing the destination with the current location, it will become closer to the above-mentioned intelligent system,
Each driverless vehicle will be unique.

Therefore, by equipping each unmanned vehicle with an imaging device, the unmanned vehicle can
A technology that allows humans to "see" is being developed as a next-level guidance method. For example, data regarding the arrangement and shape of components may be input into the storage means in advance as a predicted pattern based on the position information of the unmanned vehicle, and the actual image sent from the imaging device on the moving unmanned vehicle and the predicted pattern There is a known technique for guiding an unmanned vehicle in such a way as to reduce the difference between the two patterns.

However, in the image guidance method described above, the storage capacity for storing the predicted pattern is large, the comparison and processing of the predicted pattern with the actual image takes time, and it is difficult to change the layout of the composition. It has been pointed out that there is a problem in that the above-mentioned predicted pattern needs to be re-written manually every time the unmanned vehicle changes course.

Now, in the flow of the prior art as described above, the purpose of the present application is to push forward the intelligentization of unmanned vehicles by proposing an image guidance device with a higher degree of freedom, and to do so in the imaging means. The purpose of this invention is to propose a mark identification device.

[Means to solve the problem]

The present invention provides: (1) a grid-like template into which the binary signal of each pixel in the mark captured image is input in advance; (11) the template and the binary signal of each pixel in the actually captured image; (iii) means for aggregating the coincidence signals output from the aggregation means; (IV) comparing the value output from the aggregation means with a predetermined value, and determining the predetermined value. This mark is provided with a means for identifying items that exceed the mark as the mark.

〔Example〕

FIG. 1 schematically shows an outline of an unmanned vehicle (1) in a building (2) that is operated by the image guidance system according to the present invention.The unmanned vehicle (1) according to the present invention is known It is possible to run, steer, etc. using this technology, and a CCD camera (3) as an imaging means is mounted on the base.Furthermore, there are distinguishable marks at predetermined positions on the ceiling surface (4). (5) is placed and pasted.

The unmanned vehicle (1) images the ceiling (4) with the CCD camera (3) (hereinafter simply referred to as the camera) and marks (5).
By detecting and identifying information, it recognizes its current location and direction of travel.

According to the schematic diagram in Figure 2, the camera (3) has a lens (
6) and a screen (7), the screen (
7) is composed of many CCD element rows. The center of the lens (6) and the center of the screen (7) are at the same position in the vertical direction, and a coordinate system (x, y) is created within the screen (7) with the center on the screen (7) as the origin.
) is set. The X-axis coincides with the vertical center line of the unmanned vehicle (1), and there is a distance (L) between the y-axis and the horizontal center line (S) of the unmanned vehicle (1). Furthermore, each mark (5) has a factory coordinate system (X, Y) set within the ceiling surface. Note that there is a distance (D) between the lens (6) and the screen (7), and there is a distance (D) between the lens (6) and the ceiling surface (
4) It is assumed that there is a distance (H) between them. next,
The concept of measuring the current position and traveling direction of an unmanned vehicle using the above configuration will be described. Note that the above mark 5) and the image processing of the mark will be described later.

A) Concept of recognizing the current position and direction of movement of an unmanned vehicle using 2-mark recognition; The basic concept is to recognize the coordinates (x,
First, camera coordinates (X'') are obtained by translating the coordinates (x, y) directly to the ceiling surface.

y') and further the camera coordinates (x'.

y') and the factory coordinates (x, y) on the ceiling surface, the current position and direction of travel are recognized. below,
I will explain this in more detail, but first I will list the prerequisites for this idea. (i) Camera (3) is mounted on the ceiling (
4) is oriented vertically. (ii) Create multiple types of marks (5) and place them at intervals of about half the field of view of the camera (3) so that at least two marks are always imaged within the screen (7) of the camera (3). I will do so. (
iii) If 3 or more marks are imaged, select any 2 marks.
Adopt the individual and ignore the others. (iv) It is assumed that the distance between the camera (3) and the ceiling surface (4) is known and constant. If there is variation, it is assumed that the height of each mark from the floor is also different.

Now, if the coordinates of marks A'' and B'' on the screen are (xa, ya) and (xb, yb), respectively, and the distortion correction functions EX and 6y of the optical system, then the camera coordinates (X'', yo The coordinates (xa, ya) and (Xb, yb) of marks A and B at ) can be expressed as follows.

On the other hand, the coordinates of marks A and B in the factory coordinate system are ? -riA (Xa, Yb), ? -riB (Xb, Y
b) [n) is known in advance.

When the factory coordinates of the origin P of the camera coordinates (X', y') are p (xo, yo), the relational expression for coordinate transformation is as follows, and the equation [III) is replaced with the above [Equation 13, (II)]. By substituting the coordinate values in the equation, P (XO, yo) and θ are obtained. In addition, considering the distance (L) between the center of the camera and the center of the unmanned vehicle body, the position coordinates of the unmanned vehicle in the factory coordinate system and the mounting direction of the camera from the center of the unmanned vehicle are such that the direction of the center is from the X axis of the factory coordinate system. The number of degrees to which the vehicle is tilted to the left is determined.

B) Concept of recognition of the current position and direction of movement of an unmanned vehicle by one mark recognition; Recognizing information about which mark the mark is based on one mark, and determining the direction of movement of the unmanned vehicle with respect to the standard installation direction of the mark. If information such as the degree of inclination of the vehicle can be recognized (details will be described later), the current position and direction of travel of the unmanned vehicle can be determined just by recognizing one mark.

That is, by substituting the value of θ obtained by the measurement of the above CI) formula, the above P (XO) is obtained.

yo) is required. The subsequent processing is the same as in case A) above.

C) Control structure of unmanned vehicle (see block diagram in Figure 4) Next, the control structure of the unmanned vehicle (1) according to the present application will be explained.

That is, this control structure is composed of the following blocks.

a) CCD camera (3): This camera (3) is oriented perpendicularly to the ceiling surface (4), and the image input through the lens is projected as image information on a screen composed of multiple pixels. It will be done.

b) Vision controller (10): Extracts only the target mark (5) from the image data of the ceiling surface captured by the CCD camera (3), reads out the center coordinates of the mark on the CCD screen and the code of the mark. Regularly reports to the main controller (11).

C) Main controller (11): Calculation unit (12), coordinate table (13), travel control unit (described below)
14), map data (15), and transfer control unit (1
6).

d) Arithmetic unit (12): calculates the above A from the local coordinate values of the mark (5) obtained from the vision controller (10) and the coordinate values of each mark in the factory coordinate system obtained from the mark coated mark coordinate table (13). ) and B), the position coordinates and orientation of the unmanned vehicle (1) in the factory coordinate system are calculated and periodically reported to the travel control unit (14).

e) Coordinate table (13): In the factory coordinate system for each mark (5) The coordinates are manually determined.

f) Travel control unit (14)': Determines the travel route based on the destination and memory map data (15) instructed by the communication controller (17), and controls the servo driver (18) which is the travel and steering drive system.
Instructs driving data.

Compare the position and direction data of the unmanned vehicle reported from the calculation unit (12) with the destination information from the map data (15), and if there is a discrepancy beyond tolerance, correct the driving data and drive. , servo driver (1) which is the steering drive system
8) Give instructions.

In addition to data on the position and orientation of the unmanned vehicle (1) reported from the calculation unit (12), the encoder output (19) from the motor (M) of the driving/steering drive system is used to calculate the position and orientation of the unmanned vehicle (1). and interpolates the observation interval based on vision.

Data on the position, direction, and status of the unmanned vehicle (1) are periodically reported to the communication controller (17>).

g) Communication controller (17): The communication unit receives destination, start, stop, transfer instructions, etc. from the ground controller (20) via the ground side communication controller (21) and communication unit (22).
3) and reports each time to the main controller (11).

Information such as the current point, next stop position, status code, etc. from the main controller (11) is sent to the ground controller (20).
Report in response to a call from.

h) Ground controller (20): Receives transport requests from the host CPU (24), transport request setting board, etc., and assigns the transport requests to the unmanned vehicle considered to be the most efficient.

Collision prevention is managed based on data such as the next stop reported from the unmanned vehicle (1), and instructions to stop and start are given to the unmanned vehicle (1) as necessary.

Various status data reported from the unmanned vehicle (1) is displayed in animation on the graphic display (25) to enable real-time monitoring of the system status.

In offline mode, use the CAD function to define maps and mark coordinates to create an unmanned vehicle (1
) has a data creation function to download to.

l) Transfer robot control unit (26): In this embodiment, the transfer robot 7) (27) is mounted on the unmanned vehicle (1), but the transfer robot (27) A detailed explanation will be omitted since it is outside the scope of the present application.

D) About the mark.

Next, the mark will be explained in detail. Note that the marks described in detail below are related to the recognition of the current position and traveling direction of the unmanned vehicle based on mutual knowledge in item A).

An example of mark (5) is shown in FIG. This mark (5) has a circular shape, and from its outer periphery, a first black sheet band (30) consisting of a black part all around the circumference, a first black sheet band (
a first white sheet band (31) consisting of the inner white part of 30);
The cord sheet band (3) inside the first white sheet band (31)
2), a second black sheet band (33) consisting of the black part inside the code sheet band (32), a second white sheet band (34) consisting of the white part inside the second black sheet band (33), and a central black sheet portion (35) consisting of a black portion inside a second white sheet band (34). Each black sheet band (30) (33) in the black part and the center black sheet part (35) are made of a sheet with a color that reflects less light such as black, and each sheet band (31) (34) is made of a sheet with a color such as white. Use a sheet that has a color that reflects a lot of light and is free from diffuse reflection, scratches, and stains.

Although the color of the ceiling surface may be either black or white, it is assumed that it is black in this embodiment. The code sheet band (32) is divided in the circumferential direction into n bits (7 bits in the figure, an example of 7 bits will be explained below), and each bit is further divided into 3 equal parts. . Hereinafter, the area divided into three equal parts will be referred to as a small area.

E) Regarding the vision controller; Next, a more detailed configuration of the vision controller (10) will be explained based on FIG. 7.

The video signal (al) from the CCD camera (3) is distributed by a distributor (50) to a mark position determination device (51), a synchronization detection circuit (52), and a D/A converter (53) (a2). . Vertical synchronization signal (a3) output from the synchronization detection circuit (52) and dot clock generator (54)
The clock signal (a6) output from the address counter (55) is input to the address counter (55), and the screen address value (a7) is output from the counter (55). j (56)
to use human power. The video memory (56) contains a video signal (a5) digitized via a 1/A converter (53).
is inputting. The screen address value of the mark and the mark discovery signal (a4), which are the output signals of the mark position determination device (51), are input to the image processing CPU (57), and the CPU
The U (57) is connected to the video memory (56) by an address bus and a data bus (a8), and exchanges data with the main controller (11) such as mark types, mark positions, and vision controller activation commands. (a9) (alO).

The configuration of the mark position determining device is shown in FIG.

The video signal (a2), which is an analog value, is input to an automatic optimal binarization circuit (59) and an absolute level binarization circuit (60), which convert the binarized signal (all) as a mark component and components other than disturbance light, respectively. It is output as a binary signal (a12) and inputted to the AND circuit (61). The automatic optimum binarization circuit (59) sets a threshold between the local maximum and minimum of the image signal, and performs binarization by comparing each image signal with the threshold. Note that if there is almost no difference between the local maximum and local minimum during binarization, it is considered that the area being processed has almost uniform brightness, so binarization is not performed and it is determined as "0". do. In the above-mentioned absolute level binarization circuit (60), light exceeding a certain level of brightness such as ambient light is binarized using a predetermined value, and if the circuit (60) determines that it is "0", then That is, if the brightness exceeds a certain level, the signal (a13) outputs "0" even if the automatic optimum binarization circuit (59) determines that it is rij. The binarized signal (a13) is input to a template matching circuit (62), a mark is found in the circuit, and a mark found signal (a4) is output.

FIG. 9 shows a detailed configuration of the template matching circuit (62). The above binary signal (a13)
#0 shift register (63) and shift register (6
4) Enter.

The shift register (64) applies a delay of eight horizontal lines, has one input terminal and three output terminals, and is synchronized with the clock signal (a6) from the dot clock generator (54). The vertical synchronizing signal (a3) from the separation circuit (52) is manually generated. At the above eight output terminals, the signal (a15-1) has a delay of one line compared to the signal (a15-0), the signal (a15-2) has a delay of two lines, and the signal (a15-8) has a delay of one line compared to the signal (a15-0). There is a delay of 8 lines. Furthermore, #0 shift register (63) and #1 to #8 shift registers (65) to (
72), the relevant signal and the signals of eight pixels before it are shifted in parallel and output in order. The operation of each of the above shift registers will be explained with reference to the schematic diagram in FIG. Now, the image signal at the "0" point is 2 above.
If it is manually generated as a value signal (a13), the signal (
a15-0) is "0", signal (a15-1) is "10" by shift register (64), signal (a15
-8) outputs the signals of the "80" points in parallel and simultaneously. Furthermore, the shift registers (63) and (65) to (72) of #D to #8 are used to set "0" and "1".
0 J r 20 J -- r 80 '' and the signals from this signal up to 8 pixels are sequentially output.

For example, in #8 shift register (72), “8
Signals at points 0, 81, 82, and 88 are sequentially output. Each signal is manually input to the judgment circuit (73),
The judgment circuit (73) compares it with a preset template, and if the two match, a match signal (predetermined voltage amount) is output, and a totalizer (74) totals the output of the match signal. That is, the above-mentioned judgment stage II (73) includes a distributor (75), a white portion judgment section (76), and a point portion judgment section (
77), and if each signal is a mark, the distributor (75) sends a candidate that should be white to a white portion determining section (76)k, and a candidate that should be black to a point portion determining section (76)k. (77) and each judgment section (76) (77)
It is determined whether matching is achieved.

The above-mentioned template (80) is shown in FIG. 12, for example, and this template (80) is a part common to all marks with respect to the central part (Z) of the mark in FIG. In the figure, "0" is a black portion signal, and "1" is a white portion signal. For example, the signal output from the #8 shift register (72) in FIG. The distributor (75) selects "black", "white", "white", "black", "black", "black", "white", "
are distributed to each judgment section in the order of "white" and "black" (the 12th
(see figure). The signal outputted from the white portion determining section (76) is a signal (a16) in which "white" matches, and the signal outputted from the point portion determining section (77) is a signal (a17) in which "black" does not match. ). Note that the template (80) is conceptual, and in reality, the distributor (75) is only controlled in accordance with the N'r(1) signal in the template.

Aggregation output signal (a18) from the aggregator (74)
As shown in FIG. 10, the reference value (a1
9) is input to the comparison/judgment device (79), and if the total output signal (a18) exceeds the reference value (a19), a signal (a
4) is output.

In addition, in the template shown in FIG. 12, portions where the judgment is not clear, such as point portions or white portions, may be treated as unrelated to the judgment, and of course, the 9×
It is not limited to size 9.

As described above, since all image processing within the vision controller (10) is performed by hardware, the processing time is short and processing results can be obtained almost in real time. Further, the input value to the template match degree setting switch (78) is determined through experiments, and may be set to, for example, about 80% of the -matching pixel, or the manual value may be changed depending on the surrounding environment or the like.

F) Operation of mark signal identification; Next, the operation of identifying the mark (5) will be explained. That is, the image of the ceiling surface taken by the camera (3) is sent to the vision controller (10), and the center position coordinates and code contents of the mark (5) are read according to the processing flow shown in FIG.

(First step) The surface information captured by the camera (3) is manually input into the controller (10) as a single signal by scanning in the horizontal direction. As an example, signals corresponding to the scanning lines (Scl to 5c5) in FIG. 5 are shown as signal lines (Sgl to 5g5) in FIG. 6, respectively.

(2nd and 3rd steps) Matching is performed using the template (see section E above), and signal input (step ■) and matching (step ■) are repeated until mark (5) is found. Proceed to YES in step ■.

(4th step) After finding the mark (5),
5) Detect the center coordinates, that is, the coordinates of the center of the template. For example, in the case of the example shown in FIG. 11, if a mark is found by inputting an image signal at the "0" position, the coordinate values obtained by subtracting the coordinates of 4 pixels each from the horizontal and vertical coordinates of the "0" position, i.e. The coordinate value of the "44" position becomes the center coordinate of the mark (5).

(5th to 8th steps) As above, mark (5th to 8th steps)
) is detected, then the center position (Sn
) in a clockwise direction at a distance of radius (Ra).

The scanning using the radius (Ra) is to scan exactly on the code sheet band (32).

The scanning start point can be anywhere, and the start bit is a place where three or more small areas of 1 bit are consecutive.
(St) and then reads the information on the code sheet band (32). Figure 14.15 shows the reading state.

In this example, the three subareas are black (b) and white (W).
- "0" for black (b), "0" for black (b) - white (W
) - White (W) corresponds to "1". Therefore, in the embodiment, the code ro 10100J is read and the unmanned vehicle recognizes that the mark corresponds to the code. 2 for 6 bits
6=64 types, 2''=1024 types can be identified with 10 bits.

As mentioned above, the mark (5) is circular, and the code of the mark is also located on the circumference of concentric circles. Therefore, the center position of the mark and the code content can always be accurately read from any direction regardless of the tilt of the unmanned vehicle.

In addition, if the last code among the above codes is "1",
If there are five consecutive white (W) small areas, there is a risk that it may not be possible to recognize where the start bit is. When it comes to the beginning of the first bit, I try to be 8-ninja.

G) Marks of Other Embodiments Next, marks related to the recognition of the current position and traveling direction of an unmanned vehicle by one mark recognition in the above B) will be explained.

The mark is shown in FIG. Note that the same reference numerals are given to the same parts as in the above section D), and the description thereof will be omitted.

This mark (5) has a black part (43) on the first white sheet band (31) for direction recognition. Kurobe (43
) are attached to all marks in the same direction and at the same position. For example, the black part (
43) is attached.

The signal discrimination of the above mark (5) is based on the cordont band (
32) Along with the above scanning, the first white sheet band (3
1) is also scanned to detect the position of the black part (43).

By detecting the direction of the black part (43) in the camera image, it is possible to relatively recognize the direction of the unmanned vehicle in the factory coordinate system. In this embodiment, the starting point of scanning is an arbitrary specific point, and the direction of the mark (5) is detected based on the distance from the specific point (starting point) to the black part (43). In addition, the above starting pitch)
It is also possible to use (St) as a substitute for the above-mentioned Kurobe (43).

H) Regarding the guidance of unmanned vehicles, place the mark (5) described in item D) or item G) above on the camera (3).
), the vision controller (10) reads the center position coordinates (Sn) and code contents of each mark (5), and based on the read information, the arithmetic unit (12) calculates the above item A) or B). Through the process, the current position and traveling direction of the unmanned vehicle (1) in the factory coordinate system are recognized. Based on the information recognized by the calculation unit (12), the driving control unit (
14) to instruct the driving data to the servo driver (18)
tell. The control unit (14) includes a communication controller (
Map data (15) that stores the destination indicated by 17) and the driving route within the factory, and the above-mentioned calculation unit (12)
The driving of the unmanned vehicle is guided by the information from the system.

■) Layout changes If the travel routes stored in the map data (15) are all routes within the factory, just by changing the destination instructions from the communication controller (17), the unmanned vehicle The run will be changed. In addition, if you change the layout in the factory and make a new driving route from a part that was not a driving route, or vice versa, please use the map data (15).
All you need to do is change some of the memory contents. Of course, the mark (5) on the ceiling and the camera (3) on the unmanned vehicle remain the same.

In other words, since the unmanned vehicle can recognize its current location as the factory coordinates at any location within the factory, when changing the driving route, at least the coordinate data given to the unmanned vehicle only needs to be changed. , no other hard changes are required.

〔Effect of the invention〕

As is clear from the above description, according to the present invention, marks can be reliably and quickly identified by the imaging means on the unmanned vehicle, and the unmanned vehicle can drive while always recognizing its current position. Therefore, it has the flexibility to respond immediately when changing the layout, making it more intelligent.

[Brief explanation of the drawing]

Fig. 1 is a schematic diagram schematically showing the operation status of an unmanned vehicle in a building, Fig. 2 is a schematic diagram to explain the concept for position recognition of an unmanned vehicle, and Fig. 3 is a side view. Fig. 4 is a block diagram showing the control structure of the unmanned vehicle, Fig. 5 is a front view showing the mark, Fig. 6 is a schematic diagram for explaining the scanning state of the mark, and Fig. 7 shows the configuration of the vision controller. 8 is a block diagram showing the configuration of the mark position determining device, FIG. 9 is a block diagram showing the configuration of the template matching circuit, and FIG. 10 is a block diagram showing the configuration of the determination part of the template matching circuit. Block diagram, 1st
Figure 1 is a schematic diagram for explaining the operation of each shift register, Figure 12 is a schematic diagram showing an example of a template, and Figure 13 is a schematic diagram for explaining the operation of each shift register.
The figure is a flowchart diagram showing the processing flow for mark signal identification, Figure 14 is a schematic diagram to explain scanning for reading mark code information, and Figure 15 is a schematic diagram to explain code information analysis. The schematic diagram, FIG. 16, is a front view showing another embodiment of the mark. (51) Mark position determination device (62) Template matching circuit (73)
Judgment circuit (judgment means) (74) Aggregator (aggregation means) (79) Comparison judgment device (identification means) (80> Template Fig. 13

Claims (1)

[Claims] A grid-like template into which a binary signal of each pixel in a mark captured image is input in advance;
means for determining a match with a value-coded signal; means for summing up the matching signals output from the determining means; and comparing the value output from the summing means with a predetermined value, and the one that exceeds the predetermined value. 1. A mark identification device for an imaging means, comprising means for identifying a mark as the mark.