JP2021177123A - Information processing apparatus and information processing method, and program - Google Patents

Abstract

To provide an information processing apparatus, an information processing method, and a program capable of improving the calibration accuracy.SOLUTION: A plurality of feature points based on a pattern on a first pattern captured image obtained by imaging a calibration pattern 14 using a first imaging device 12-1, and a plurality of feature points based on a pattern on a second pattern captured image obtained by imaging a calibration pattern using a second imaging device 12-2 are detected. Then, the first imaging device and the second imaging device are calibrated using the plurality of feature points detected from the first pattern captured image and the plurality of feature points detected from the second pattern captured image. At this time, the calibration pattern is composed of a first pattern in which a plurality of first figures are arranged and a second pattern in which a plurality of second figures having a size different from that of the first figure are arranged.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to an information processing apparatus, an information processing method, and a program, and more particularly to an information processing apparatus, an information processing method, and a program capable of improving calibration accuracy.

Conventionally, in an imaging system using a plurality of imaging devices, by calibrating the imaging devices, for example, internal parameters indicating distortion included in the image captured by each imaging device and the imaging devices are used. Acquires an external parameter indicating the positional relationship of.

For example, Non-Patent Document 1 discloses a method of imaging a pattern having a known shape, such as a checker, and estimating the distortion of the imaging device and the imaging position from the position where the pattern is detected in the image. ing.

By the way, in this method, when calibration is performed between a plurality of imaging devices having different viewing angles and arrangement positions, the accuracy may be lowered. That is, with respect to a pattern having an optimum size for detecting a feature point in a certain image pickup device, the pattern is too large or too small for another image pickup device, and each image pickup device has a feature point from the pattern. This is because the detection accuracy for detecting the above is lowered.

Therefore, in Patent Document 1, when a pattern used for calibration is imaged, the position of the feature point remains constant and the size is changed with time, and the feature is obtained from the imaged calibration patterns of a plurality of sizes. A camera calibration method has been proposed to improve the accuracy of camera calibration by estimating points.

JP-A-2017-125772

Z. Zhang, A Flexible New Technique for Camera Calibration, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol 22,pp 1330-1334, 2000.

However, the camera calibration method proposed in Patent Document 1 described above requires an environment in which a plurality of calibration patterns can be displayed or projected, so that the apparatus becomes large-scale. Also. Since multiple patterns are displayed, it takes time to calibrate one, and if the pattern moves even a little due to display blurring or shaking that occurs during pattern display, the calibration accuracy will deteriorate. was there.

The present disclosure has been made in view of such a situation, and makes it possible to improve the calibration accuracy.

The information processing device on one aspect of the present disclosure includes a plurality of feature points based on a pattern on a first pattern captured image obtained by imaging a calibration pattern with the first imaging device, and a second imaging device. A feature point detection unit that detects a plurality of feature points based on a pattern on a second pattern captured image obtained by imaging the calibration pattern, and a plurality of feature points detected from the first pattern captured image. The calibration processing unit is provided with a calibration processing unit that calibrates the first imaging device and the second imaging device using a plurality of feature points detected from the second pattern captured image. The motion pattern is composed of a first pattern in which a plurality of first figures are arranged, and a second pattern in which a plurality of second figures having a size different from that of the first figure are arranged.

The information processing method or program of one aspect of the present disclosure includes a plurality of feature points based on a pattern on a first pattern captured image obtained by imaging a calibration pattern with a first imaging device, and a second imaging. Detection of a plurality of feature points based on a pattern on a second pattern captured image obtained by imaging the calibration pattern with an apparatus, a plurality of feature points detected from the first pattern captured image, and The calibration pattern includes calibrating the first imaging device and the second imaging device using a plurality of feature points detected from the second pattern captured image. It is composed of a first pattern in which a plurality of first figures are arranged, and a second pattern in which a plurality of second figures having a size different from that of the first figure are arranged.

In one aspect of the present disclosure, a plurality of feature points based on a pattern on a first pattern captured image obtained by imaging a calibration pattern with a first imaging device, and a calibration pattern with a second imaging device. A plurality of feature points based on the pattern on the second pattern captured image obtained by imaging the image are detected, and the plurality of feature points detected from the first pattern captured image and the plurality of feature points detected from the second pattern captured image are detected. The first image pickup apparatus and the second image pickup apparatus are calibrated using the plurality of feature points. The calibration pattern is composed of a first pattern in which a plurality of first figures are arranged and a second pattern in which a plurality of second figures having a size different from that of the first figure are arranged. NS.

According to one aspect of the present disclosure, it is possible to improve the calibration accuracy.

The effects described here are not necessarily limited, and may be any of the effects described in the present disclosure.

It is a figure explaining the image pickup system which applied this technology. It is a block diagram which shows the structural example of one Embodiment of a calibration apparatus. It is a figure which shows the 1st example of the calibration pattern. It is a figure which shows the 2nd example of the calibration pattern. It is a figure which shows the 3rd example of the calibration pattern. It is a flowchart explaining the calibration process. It is a figure explaining the variation of a checker pattern. It is a block diagram which shows the structural example of one Embodiment of the computer to which this technique is applied.

Hereinafter, specific embodiments to which the present technology is applied will be described in detail with reference to the drawings.

<Configuration example of imaging system>
FIG. 1 is a diagram illustrating an imaging system to which the present technology is applied.

The imaging system 11 shown in FIG. 1 is configured to include two imaging devices 12-1 and 12-2, and a calibration device 13, and can perform calibration using the calibration pattern 14. For example, the calibration pattern 14 is configured by combining the first pattern and the second pattern, as will be described later with reference to FIGS. 3 to 5.

In the example shown in FIG. 1, the calibration pattern 14 is composed of a first pattern in which nine small circles are arranged and a second pattern in which four large circles are arranged. For example, the first pattern is the size for which the feature points are accurately obtained by the image pickup apparatus 12-1, and the second pattern is the size for which the feature points are accurately required by the image pickup apparatus 12-2. The four circular center points of are combined so as to coincide with each other.

The imaging devices 12-1 and 12-2 capture the calibration pattern 14 at different viewing angles, imaging positions, and the like, and acquire the pattern captured image. As shown in the figure, the imaging device 12-1 has an imaging position closer to the calibration pattern 14 than the imaging device 12-2, and acquires a pattern captured image in which the calibration pattern 14 is largely captured. On the other hand, the imaging device 12-2 acquires a pattern captured image in which the calibration pattern 14 is captured in a small size.

The calibration device 13 detects a plurality of feature points (white x marks) from each pattern captured image, and acquires feature point information indicating the coordinates of those feature points. For example, in the pattern captured image acquired by the imaging device 12-1, the calibration pattern 14 is largely captured, and the calibration device 13 detects nine small circular centers of the first pattern as feature points. .. On the other hand, in the pattern captured image acquired by the imaging device 12-2, the calibration pattern 14 is projected small, and the calibration device 13 features four large circular centers of the second pattern as feature points. To detect.

Then, the calibration device 13 uses the feature point information indicating the coordinates of the feature points of the first pattern and the feature point information indicating the coordinates of the feature points of the second pattern, and uses the image pickup devices 12-1 and 12 -2 can be calibrated with high accuracy.

FIG. 2 is a block diagram showing a configuration example of an embodiment of the calibration device 13 of FIG.

As shown in FIG. 2, the calibration device 13 includes image acquisition units 21-1 and 21-2, feature point detection units 22-1 and 22-2, reliability estimation unit 23, calibration processing unit 24, and It is configured to include a data storage unit 25.

The image acquisition unit 21-1 acquires a pattern image obtained by the image pickup device 12-1 imaging the calibration pattern 14 and supplies it to the feature point detection unit 22-1. Similarly, the image acquisition unit 21-2 acquires a pattern image obtained by the image pickup device 12-2 imaging the calibration pattern 14 and supplies it to the feature point detection unit 22-2.

The feature point detection unit 22-1 detects a plurality of feature points included in the calibration pattern 14 captured in the pattern captured image supplied from the image acquisition unit 21-1, and for example, those feature points. The coordinates of are acquired as feature point information and supplied to the reliability estimation unit 23. Similarly, the feature point detection unit 22-2 transmits the coordinates of the feature points acquired from the calibration pattern 14 captured in the pattern captured image supplied from the image acquisition unit 21-2 to the reliability estimation unit 23. Supply.

The reliability estimation unit 23 estimates the reliability of the feature points based on the feature point information supplied from the feature point detection unit 22-1 and the feature point information supplied from the feature point detection unit 22-2.

For example, the reliability estimation unit 23 uses the coordinates of the feature points detected by the feature point detection unit 22-1 and the coordinates of the feature points detected by the feature point detection unit 22-2 to obtain corresponding feature points. If it can be detected, the distance d on the image between those feature points is estimated as the reliability. For example, in the example shown in FIG. 1, among the nine circular feature points of the first pattern, the four feature points at the four corners correspond to the four circular feature points of the second pattern (calibration). The centers of the circles coincide on the calibration pattern 14).

Then, the reliability estimation unit 23 includes the coordinates of the i-th feature point according to the first pattern (x1 _i , y1 _i ) and the coordinates of the i-th feature point according to the second pattern (x2 _i , y2 _i ). Is used to calculate the distance d between the i-th feature points according to the following equation (1).

The calibration processing unit 24 uses the feature point information obtained by the feature point detection units 22-1 and 22-1 and the reliability obtained by the reliability estimation unit 23 to image images 12-1 and 12 Perform a calibration process to estimate the internal and external parameters of -2. For example, the calibration processing unit 24 can perform the calibration processing by preferentially using the feature points having high reliability or by preferentially using the pattern captured image having high reliability as a whole. Here, the calibration processing unit 24 can perform the calibration processing based on the method disclosed in Non-Patent Document 1 described above.

That is, the calibration processing unit 24, for example, matches the pattern shape detected in the pattern captured image obtained by imaging the calibration pattern 14 whose shape is known with the pattern shape of the actual calibration pattern 14. Estimates the parameters of the imaging devices 12-1 and 12-2. In many cases, by acquiring a plurality of pattern captured images, it is possible to improve the accuracy of estimation by performing nonlinear optimization so that the total error of the pattern shape is minimized.

Here, in the present embodiment, by using the reliability of each feature point as a weight at the time of nonlinear optimization, optimization is performed by preferentially using the points at which the feature points can be detected with high accuracy.

For example, the calibration processing unit 24, in m _x number of i-th pattern captured image, using distance d j-th feature point each other which can be detected feature points corresponding _{(i, j),} the following equation ( According to 2), it is possible to calculate the _{weight w (i, j)} of the j-th feature point for which the corresponding feature point can be detected in the i-th pattern-captured image of the n pattern-captured images. can.

Further, the weight of the point at which the feature point can be detected only from one of the first pattern and the second pattern of the calibration pattern 14 is the weight w _{(i, j) obtained by the equation (2). )} Is the average value.

Then, the calibration processing unit 24 outputs the estimated internal parameters and external parameters of the imaging devices 12-1 and 12-2 as a result of such optimization.

The calibration device 13 is configured as described above, and the calibration accuracy is obtained by using the calibration pattern 14 and using the reliability of the feature points of the first pattern and the feature points of the second pattern. Can be improved.

<Example of calibration pattern>
The calibration pattern 14 used in the imaging system 11 will be described with reference to FIGS. 3 to 5.

The calibration pattern 14A shown in FIG. 3 consists of a first pattern in which small red circles are arranged at equal intervals and a second pattern in which green circles having a size larger than the red circle are arranged at equal intervals. It is composed by combining. Then, the green circle is arranged so that the center points match only in the odd-numbered rows and odd-numbered examples of the red circles.

Then, the image pickup apparatus 12-1 can detect only the first pattern by extracting only the red component of the pattern captured image. Similarly, the image pickup apparatus 12-2 can detect only the second pattern by extracting only the green component of the pattern-captured image.

For example, the calibration pattern 14A is a pattern on a pattern captured image obtained by capturing the same pattern due to the positions of the imaging devices 12-1 and 12-2 being separated from each other and the viewing angle being large. It is assumed that it will be used in a configuration where the size of the is greatly different. That is, in the image pickup apparatus 12-1 capable of capturing a large calibration pattern 14A, a large number of feature points can be acquired by a large number of red circles, and highly accurate calibration can be performed. Further, in the image pickup apparatus 12-2 in which the calibration pattern 14A is imaged in a small size, the feature points can be detected with high accuracy by using the green circle in which each pattern is large, and the calibration is performed with high accuracy. be able to.

The calibration pattern 14B shown in FIG. 4 consists of a first pattern in which small black circles are arranged at equal intervals and a circle composed of a retroreflective material (dot hatching) having a size larger than the black circle at equal intervals. It is configured by combining with the second pattern arranged in. Then, the circle of the retroreflective material is arranged so that the center points coincide only with the odd-numbered rows and the odd-numbered examples among the black circles.

For example, it is assumed that the calibration pattern 14B uses an imaging device that acquires a color image and an imaging device that acquires an infrared image at the same time, and is used in a configuration in which the viewing angles and resolutions of the imaging devices are different from each other. That is, since the retroreflective material has a property of strongly returning the received light in the direction in which it is received, when viewed in an infrared image, it appears to shine white regardless of the color seen in the color image. Therefore, it is possible to detect a pattern composed of black circles in a color image and a pattern composed of a retroreflective material in an infrared image. Further, in the infrared image, a pattern consisting of black circles can be detected in the same manner.

The calibration pattern 14C shown in FIG. 5 has a configuration in which a first pattern in which black and white circles are arranged at equal intervals is superimposed on a second pattern composed of a black and white checker. Then, the center point of the black-and-white circle and the intersection of the black-and-white checkers are arranged so as to coincide with each other.

Further, it is assumed that the calibration pattern 14C is also used in a configuration in which the imaging devices 12-1 and 12-2 are separated from each other and the viewing angles are significantly different from each other, as in the calibration pattern 14A. .. For example, in the calibration pattern 14C, when the pattern appears large, the feature points of the first pattern consisting of a circle can be detected with high accuracy, and when the pattern appears small, the feature points of the second pattern consisting of a checker can be detected. Feature points can be detected with high accuracy.

As described above, in the imaging system 11, it is possible to use the calibration pattern 14 composed of the first and second patterns capable of extracting the feature points with high accuracy by the imaging devices 12-1 and 12-2, respectively. can. Further, the calibration pattern 14 has a configuration in which the first and second patterns are combined so that the first and second patterns do not interfere with each other's detection. As a result, even if the imaging devices 12-1 and 12-2 have different viewing angles, the feature points can be inspected with high accuracy, and the calibration accuracy can be improved.

Further, unlike the above-mentioned Patent Document 1, the imaging system 11 can image the calibration pattern 14 without changing the pattern in the time direction. As a result, the calibration pattern 14 can be imaged with a simpler configuration and in a short time, and for example, the influence of blurring during imaging can be reduced.

Further, in the image pickup system 11, when the feature points can be simultaneously detected from the calibration patterns 14 by the image pickup devices 12-1 and 12-2, the feature points are the same in the first and second patterns. , The reliability of feature point detection can be estimated by comparing the positions of each feature point. As a result, the accuracy of calibration can be improved by performing calibration using only highly reliable pattern-captured images.

<Calibration process>
The calibration process executed in the calibration device 13 will be described with reference to the flowchart of FIG.

For example, the process is started when the imaging system 11 of FIG. 1 is started to be used. In step S11, the image acquisition units 21-1 and 21-2 acquire a pattern captured image obtained by imaging the calibration pattern 14 by the imaging devices 12-1 and 12-2, respectively.

In step S12, the calibration processing unit 24 determines whether or not a sufficient number of pattern-captured images for calibration has been acquired, and steps S11 until a sufficient number of pattern-captured images are acquired. Repeat the process of. Then, in step S12, when the calibration processing unit 24 determines that a sufficient number of pattern captured images for performing calibration have been acquired, the processing proceeds to steps S13 and S14.

In step S13, the feature point detection unit 22-1 detects the feature points of the first pattern constituting the calibration pattern 14 captured in the pattern captured image acquired by the image acquisition unit 21-1 in step S11. , The feature point information is supplied to the reliability estimation unit 23.

In step S14, the feature point detection unit 22-2 detects the feature points of the second pattern constituting the calibration pattern 14 captured in the pattern captured image acquired by the image acquisition unit 21-2 in step S11. , The feature point information is supplied to the reliability estimation unit 23.

The processes of steps S13 and S14 are performed in parallel, and after each process is completed, step S15 is performed. In step S15, the reliability estimation unit 23 is based on the feature point information supplied from the feature point detection unit 22-1 in step S13 and the feature point information supplied from the feature point detection unit 22-2 in step S14. Estimate the reliability of the feature points.

In step S16, the calibration processing unit 24 has the feature point information detected by the feature point detection unit 22-1 in step S13, the feature point information detected by the feature point detection unit 22-2 in step S14, and the step. After estimating the internal and external parameters of the image pickup devices 12-1 and 12-2 using the reliability estimated by the reliability estimation unit 23 in S15, the process is terminated.

Here, with respect to the two image pickup devices 12a and 12b, each pattern is matched so that each feature point of the pattern image pickup image acquired by the image pickup device 12b matches each feature point of the pattern image pickup image acquired by the image pickup device 12a. An example of finding a deformation that minimizes the distance between each feature point of the captured image will be described. For example, when using n pattern captured images obtained by capturing a pattern having m feature points, each feature point mx _ij of the pattern captured by the imaging device 12x (x is a or b) and the imaging device 12x The internal parameter Int _x and the external parameter Ext _x of the image pickup apparatus 12x are obtained by non-linear optimization of the parameters that minimize the following equation (3).

As described above, the calibration device 13 can obtain the internal parameters and the external parameters with high accuracy.

<Another example of how to acquire the corresponding points between pattern captured images>
With reference to FIG. 7, another example of a method of acquiring corresponding points between the pattern captured images used at the time of calibration will be described.

As described with reference to FIGS. 3 and 4 described above, calibration is performed using the circular center points as feature points and the corresponding feature points between the pattern captured images. In addition, for example, the intersection of the checker patterns as shown in FIG. 7A can be used as a feature point, and calibration can be performed using the feature points corresponding to each other in the pattern captured images. Further, as shown in B of FIG. 7, it is possible to perform calibration using the feature points corresponding to each other in the pattern captured images, with the center of gravity point and the intersection point of the triangle as the feature points.

By acquiring the center point, the intersection point, and the center of gravity point of the pattern as feature points in this way, it is possible to perform calibration more accurately than, for example, a configuration in which the lines and surfaces of the pattern correspond to each other.

<Computer configuration example>
Next, the series of processes (information processing method) described above can be performed by hardware or software. When a series of processes is performed by software, the programs constituting the software are installed on a general-purpose computer or the like.

FIG. 8 is a block diagram showing a configuration example of an embodiment of a computer in which a program for executing the above-mentioned series of processes is installed.

The program can be recorded in advance on the hard disk 105 or ROM 103 as a recording medium built in the computer.

Alternatively, the program can be stored (recorded) in the removable recording medium 111 driven by the drive 109. Such a removable recording medium 111 can be provided as so-called package software. Here, examples of the removable recording medium 111 include a flexible disc, a CD-ROM (Compact Disc Read Only Memory), an MO (Magneto Optical) disc, a DVD (Digital Versatile Disc), a magnetic disc, and a semiconductor memory.

The program can be installed on the computer from the removable recording medium 111 as described above, or can be downloaded to the computer via a communication network or a broadcasting network and installed on the built-in hard disk 105. That is, for example, the program transfers wirelessly from a download site to a computer via an artificial satellite for digital satellite broadcasting, or transfers to a computer by wire via a network such as LAN (Local Area Network) or the Internet. be able to.

The computer has a built-in CPU (Central Processing Unit) 102, and the input / output interface 110 is connected to the CPU 102 via the bus 101.

When a command is input by the user by operating the input unit 107 or the like via the input / output interface 110, the CPU 102 executes a program stored in the ROM (Read Only Memory) 103 accordingly. .. Alternatively, the CPU 102 loads the program stored in the hard disk 105 into the RAM (Random Access Memory) 104 and executes it.

As a result, the CPU 102 performs a process according to the above-mentioned flowchart or a process performed according to the above-mentioned block diagram configuration. Then, the CPU 102 outputs the processing result from the output unit 106, transmits it from the communication unit 108, and further records it on the hard disk 105, if necessary, via the input / output interface 110, for example.

The input unit 107 is composed of a keyboard, a mouse, a microphone, and the like. Further, the output unit 106 is composed of an LCD (Liquid Crystal Display), a speaker, or the like.

Here, in the present specification, the processing performed by the computer according to the program does not necessarily have to be performed in chronological order in the order described as the flowchart. That is, the processing performed by the computer according to the program also includes processing executed in parallel or individually (for example, parallel processing or processing by an object).

Further, the program may be processed by one computer (processor) or may be distributed by a plurality of computers. Further, the program may be transferred to a distant computer and executed.

Further, in the present specification, the system means a set of a plurality of components (devices, modules (parts), etc.), and it does not matter whether or not all the components are in the same housing. Therefore, a plurality of devices housed in separate housings and connected via a network, and a device in which a plurality of modules are housed in one housing are both systems. ..

Further, for example, the configuration described as one device (or processing unit) may be divided and configured as a plurality of devices (or processing units). On the contrary, the configurations described above as a plurality of devices (or processing units) may be collectively configured as one device (or processing unit). Further, of course, a configuration other than the above may be added to the configuration of each device (or each processing unit). Further, if the configuration and operation of the entire system are substantially the same, a part of the configuration of one device (or processing unit) may be included in the configuration of another device (or other processing unit). ..

Further, for example, the present technology can have a cloud computing configuration in which one function is shared and jointly processed by a plurality of devices via a network.

Further, for example, the above-mentioned program can be executed in any device. In that case, the device may have necessary functions (functional blocks, etc.) so that necessary information can be obtained.

Further, for example, each step described in the above-mentioned flowchart can be executed by one device or can be shared and executed by a plurality of devices. Further, when a plurality of processes are included in one step, the plurality of processes included in the one step can be executed by one device or shared by a plurality of devices. In other words, a plurality of processes included in one step can be executed as processes of a plurality of steps. On the contrary, the processes described as a plurality of steps can be collectively executed as one step.

In the program executed by the computer, the processing of the steps for describing the program may be executed in chronological order in the order described in this specification, or may be executed in parallel or called. It may be executed individually at a necessary timing such as time. That is, as long as there is no contradiction, the processing of each step may be executed in an order different from the above-mentioned order. Further, the processing of the step for writing this program may be executed in parallel with the processing of another program, or may be executed in combination with the processing of another program.

It should be noted that the present techniques described in the present specification can be independently implemented independently as long as there is no contradiction. Of course, any plurality of the present technologies can be used in combination. For example, some or all of the techniques described in any of the embodiments may be combined with some or all of the techniques described in other embodiments. It is also possible to carry out a part or all of any of the above-mentioned techniques in combination with other techniques not described above.

<Example of configuration combination>
The present technology can also have the following configurations.
(1)
A plurality of feature points based on a pattern on a first pattern captured image obtained by imaging a calibration pattern with a first imaging device, and a second image obtained by imaging the calibration pattern with a second imaging device. 2 Pattern A feature point detection unit that detects a plurality of feature points based on the pattern on the captured image, and
Using the plurality of feature points detected from the first pattern captured image and the plurality of feature points detected from the second pattern captured image, the first image pickup apparatus and the second image pickup apparatus are used. Equipped with a calibration processing unit that calibrates with
The calibration pattern is composed of a first pattern in which a plurality of first figures are arranged and a second pattern in which a plurality of second figures having a size different from that of the first figure are arranged. Information processing device.
(2)
The reliability of the plurality of feature points detected from the first pattern captured image and the plurality of feature points detected from the second pattern captured image used by the calibration processing unit for calibration is estimated. Equipped with a reliability estimation unit
The information processing apparatus according to (1) above, wherein at least a part of the plurality of feature points of the first figure and the plurality of feature points of the second figure match in the calibration pattern.
(3)
The calibration pattern is composed of a first pattern in which a plurality of circles of a first size are arranged and a second pattern in which a plurality of circles of a second size are arranged, and each circle is different. The information processing apparatus according to (1) or (2) above, which is colored.
(4)
The calibration pattern is composed of a first pattern in which a plurality of circles of a first size are arranged and a second pattern in which a plurality of circles of a second size are arranged, and at least one of the circles is formed. The information processing apparatus according to (1) or (2) above, which is formed of a retroreflective material.
(5)
The calibration pattern is composed of a first pattern in which a plurality of circles are arranged and a second pattern in which checkers are arranged in a grid pattern, and the center points of the circles are arranged at intersections of the checkers. The information processing apparatus according to (1) or (2) above.
(6)
The information processing device that performs the calibration process
A plurality of feature points based on a pattern on a first pattern captured image obtained by imaging a calibration pattern with a first imaging device, and a second image obtained by imaging the calibration pattern with a second imaging device. 2 Patterns Detecting multiple feature points based on patterns on captured images and
Using the plurality of feature points detected from the first pattern captured image and the plurality of feature points detected from the second pattern captured image, the first image pickup apparatus and the second image pickup apparatus are used. Including calibrating with
The calibration pattern is composed of a first pattern in which a plurality of first figures are arranged and a second pattern in which a plurality of second figures having a size different from that of the first figure are arranged. Information processing method.
(7)
To the computer of the information processing device that performs the calibration process
A plurality of feature points based on a pattern on a first pattern captured image obtained by imaging a calibration pattern with a first imaging device, and a second image obtained by imaging the calibration pattern with a second imaging device. 2 Patterns Detecting multiple feature points based on patterns on captured images and
Using the plurality of feature points detected from the first pattern captured image and the plurality of feature points detected from the second pattern captured image, the first image pickup apparatus and the second image pickup apparatus are used. Including calibrating with
The calibration pattern is composed of a first pattern in which a plurality of first figures are arranged, and a second pattern in which a plurality of second figures having a size different from that of the first figure are arranged. A program for executing information processing including.

The present embodiment is not limited to the above-described embodiment, and various modifications can be made without departing from the gist of the present disclosure. Further, the effects described in the present specification are merely examples and are not limited, and other effects may be obtained.

11 Imaging system, 12 Imaging device 12, 13 Calibration device, 14 Calibration pattern, 21 Image acquisition unit, 22 Feature point detection unit, 23 Reliability estimation unit, 24 Calibration processing unit

Claims (7)

A plurality of feature points based on a pattern on a first pattern captured image obtained by imaging a calibration pattern with a first imaging device, and a second image obtained by imaging the calibration pattern with a second imaging device. 2 Pattern A feature point detection unit that detects a plurality of feature points based on the pattern on the captured image, and
Using the plurality of feature points detected from the first pattern captured image and the plurality of feature points detected from the second pattern captured image, the first image pickup apparatus and the second image pickup apparatus are used. Equipped with a calibration processing unit that calibrates with
The calibration pattern is composed of a first pattern in which a plurality of first figures are arranged and a second pattern in which a plurality of second figures having a size different from that of the first figure are arranged. Information processing device. The reliability of the plurality of feature points detected from the first pattern captured image and the plurality of feature points detected from the second pattern captured image used by the calibration processing unit for calibration is estimated. Equipped with a reliability estimation unit
The information processing apparatus according to claim 1, wherein in the calibration pattern, at least a part of the plurality of feature points of the first figure and the plurality of feature points of the second figure match. The calibration pattern is composed of a first pattern in which a plurality of circles of a first size are arranged and a second pattern in which a plurality of circles of a second size are arranged, and each circle is different. The information processing apparatus according to claim 1, which is colored. The calibration pattern is composed of a first pattern in which a plurality of circles of a first size are arranged and a second pattern in which a plurality of circles of a second size are arranged, and at least one of the circles is formed. The information processing apparatus according to claim 1, which is formed of a retroreflective material. The calibration pattern is composed of a first pattern in which a plurality of circles are arranged and a second pattern in which checkers are arranged in a grid pattern, and the center points of the circles are arranged at intersections of the checkers. The information processing apparatus according to claim 1. The information processing device that performs the calibration process
A plurality of feature points based on a pattern on a first pattern captured image obtained by imaging a calibration pattern with a first imaging device, and a second image obtained by imaging the calibration pattern with a second imaging device. 2 Patterns Detecting multiple feature points based on patterns on captured images and
Using the plurality of feature points detected from the first pattern captured image and the plurality of feature points detected from the second pattern captured image, the first image pickup apparatus and the second image pickup apparatus are used. Including calibrating with
The calibration pattern is composed of a first pattern in which a plurality of first figures are arranged and a second pattern in which a plurality of second figures having a size different from that of the first figure are arranged. Information processing method. To the computer of the information processing device that performs the calibration process
A plurality of feature points based on a pattern on a first pattern captured image obtained by imaging a calibration pattern with a first imaging device, and a second image obtained by imaging the calibration pattern with a second imaging device. 2 Patterns Detecting multiple feature points based on patterns on captured images and
Using the plurality of feature points detected from the first pattern captured image and the plurality of feature points detected from the second pattern captured image, the first image pickup apparatus and the second image pickup apparatus are used. Including calibrating with
The calibration pattern is composed of a first pattern in which a plurality of first figures are arranged, and a second pattern in which a plurality of second figures having a size different from that of the first figure are arranged. A program for executing information processing including.

Images