Apparatus and method for estimating camera external parameter by using one camera placed in vehicle

Abstract

The present invention relates to an apparatus and a method for estimating a camera external parameter by using one camera placed in a vehicle. To this end, an apparatus for estimating a camera external parameter by using one camera placed in a vehicle according to an embodiment of the present invention may comprise a camera placed in a vehicle, and a processor electrically connected to the camera, wherein the processor is configured to: identify whether a rear wheel of the vehicle is located at a boundary line of a parking area; if the rear wheel is located on the boundary line, acquire a first distance value from a corner of the parking area to a center point of a rear wheel axle of the vehicle; acquire a second distance between a reference point that is the center point of the rear wheel axle of the vehicle and a marker attached to a wall located on one side of the vehicle; acquire a third distance between the camera and the marker; convert the acquired first distance, the acquired second distance, and the acquired third distance into respective matrices; and estimate an external parameter of the camera by using each of the converted matrices.

Description

Device and method for estimating camera external parameters using a single camera placed on a vehicle

[0001] The present invention relates to a device and method for estimating camera external parameters using a single camera placed in a vehicle.

[0002] The automotive industry is experiencing remarkable growth, but this growth has exceeded expectations, creating challenges for road expansion and parking space expansion. The labor required to manage parking spaces is also incurring significant labor costs, and parking lot maintenance is also costly.

[0003] The prior art document (Korean Patent Publication No. 10-2014-0036592, March 26, 2014) relates to a method and device for estimating external parameters of a vehicle-installed camera, and discloses estimating external parameters of a vehicle-installed camera using a triangular pattern.

[0004] However, conventionally, external parameters of a camera are estimated using multiple cameras, but in cases where there is only one camera, external parameters of the camera are not estimated.

[0005] Therefore, when an unmanned vehicle has one camera, there is a need to identify the location of the camera by estimating the external parameters of the camera.

[0006] Accordingly, the present invention provides a device and method for estimating camera external parameters using one camera disposed in a vehicle.

[0007] In addition, the present invention provides a method for more accurately measuring external parameters of a camera based on a coordinate system of a vehicle using lanes and markers while the vehicle is stopped.

[0008] The purposes of the present invention are not limited to those mentioned above, and other unmentioned purposes and advantages of the present invention can be understood through the following description and will be more clearly understood through embodiments of the present invention. Furthermore, it will be readily apparent that the purposes and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims.

[0009] In order to achieve this purpose, an apparatus for estimating a camera external parameter using a camera disposed in a vehicle according to an embodiment of the present invention includes a camera disposed inside the vehicle; and a processor electrically connected to the camera, wherein the processor is configured to identify whether a rear wheel of the vehicle is positioned at a boundary line of a parking area, and if the rear wheel is positioned on the boundary line, obtain a first distance between a center point of a rear wheel axle of the vehicle from a corner of the parking area, obtain a second distance between a reference point which is the center point of the rear wheel axle of the vehicle and a marker attached to a wall located on one side of the vehicle, obtain a third distance between the camera and the marker, convert each of the obtained first distance, the obtained second distance, and the obtained third distance into a matrix, and estimate the external parameter of the camera using each of the converted matrices.

[0010] In addition, a method for estimating camera external parameters using a single camera disposed on a vehicle according to an embodiment of the present invention may include: a step of identifying whether a rear wheel of the vehicle is positioned at a boundary line of a parking area; a step of obtaining a first distance between a center point of a rear wheel axle of the vehicle and a corner of the parking area if the rear wheel is positioned on the boundary line; a step of obtaining a second distance between a reference point, which is a center point of the rear wheel axle of the vehicle, and a marker attached to a wall located on one side of the vehicle; a step of obtaining a third distance between the camera and the marker; a step of converting each of the obtained first distance, the obtained second distance, and the obtained third distance into a matrix; and a step of estimating the external parameters of the camera using each of the converted matrices.

[0011] The present invention estimates external parameters for a camera by obtaining a first distance between the center point of a rear wheel axis of a vehicle from a corner of a parking area when the rear wheel of a vehicle on which one camera is placed is positioned on a parking area, a second distance between a reference point which is the center point of the rear wheel axis of the vehicle and a marker attached to a wall located on one side of the vehicle, and a third distance between the camera and the marker, and converting each of these into a matrix.

[0012] In addition, the present invention can convert the positioning results using the front windshield camera into a vehicle coordinate system based on the camera external parameters, and can directly use this as input to the control logic of indoor automatic parking and automatic valet parking.

[0013] In addition to the effects described above, specific effects of the present invention are described below while explaining specific details for carrying out the invention.

[0014] FIG. 1 is an exemplary diagram showing a state for estimating camera external parameters using one camera placed on a vehicle according to one embodiment of the present invention.

[0015] FIG. 2 is a block diagram of a device for estimating camera external parameters using one camera placed on a vehicle according to one embodiment of the present invention.

[0016] FIG. 3 is a flowchart illustrating a method for estimating camera external parameters using one camera placed on a vehicle according to one embodiment of the present invention.

[0017] Figure 4 is an exemplary diagram showing a marker according to one embodiment of the present invention.

[0018] FIG. 5 is an exemplary diagram showing a state of estimating camera external parameters using one camera placed on a vehicle according to one embodiment of the present invention.

[0019] The above-described objects, features, and advantages will be described in detail below with reference to the accompanying drawings, so that those skilled in the art can easily practice the technical idea of ​​the present invention. In describing the present invention, if it is determined that a detailed description of known technologies related to the present invention may unnecessarily obscure the gist of the present invention, a detailed description thereof will be omitted. Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the drawings, the same reference numerals are used to indicate the same or similar components.

[0020] Although terms like "first" and "second" are used to describe various components, these components are not limited by these terms. These terms are used merely to distinguish one component from another, and unless otherwise specified, a "first" component may also be a "second" component.

[0021] Hereinafter, the phrase "any configuration is placed on (or below)" a component or "on (or below)" a component may mean that any configuration is placed in contact with the upper surface (or lower surface) of said component, and that other configurations may be interposed between said component and any configuration placed on (or below) said component.

[0022] Additionally, when it is described that a component is "connected," "coupled," or "connected" to another component, it should be understood that the components may be directly connected or connected to one another, but that other components may also be "interposed" between the components, or that each component may be "connected," "coupled," or "connected" through another component.

[0023] Throughout the specification, unless otherwise specifically stated, each element may be singular or plural.

[0024] As used herein, singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as "consisting of" or "comprising" should not necessarily be construed to include all of the components or steps described in the specification, and should be construed to mean that some of the components or steps may not be included, or that additional components or steps may be included.

[0025] Throughout the specification, when we refer to "A and / or B", this means A, B, or A and B, unless otherwise stated, and when we refer to "C to D", this means C or more and D or less, unless otherwise stated.

[0026] Hereinafter, a device and method for estimating camera external parameters using a single camera placed on a vehicle according to some embodiments of the present invention will be described.

[0027] FIG. 1 is an exemplary diagram showing a state for estimating camera external parameters using one camera placed on a vehicle according to one embodiment of the present invention.

[0028] Referring to FIG. 1, a vehicle (110) may be positioned in a parking area (130), and a rear wheel axle (140) of the vehicle (110) may be positioned at a boundary line (132) of the parking area. Typically, the parking area (130) is rectangular and is formed by four boundary lines (131, 132, 133, 134). A marker (121) is placed on a wall (120) at the front of the vehicle (110).

[0029] The present invention can estimate the external parameters of a camera (210 in FIG. 2) placed inside a vehicle (110) in this state. The external parameters of the camera can include three-dimensional spatial coordinates (x, y, z) and pan, tilt, and roll angles (θψΦ) of the camera.

[0030] The device (200 of FIG. 2) of the present invention can identify whether the rear wheels of the vehicle (110) are positioned at the boundary line (132) of the parking area, and if the rear wheels are positioned on the boundary line (132), can obtain a first distance between the center point of the rear wheel axle of the vehicle and the edge of the parking area. In addition, the device (200 of FIG. 2) can obtain a second distance between a reference point, which is the center point of the rear wheel axle of the vehicle (110), and a marker (121) attached to a wall (120) located on one side (e.g., the front) of the vehicle (110), and can obtain a third distance between a camera and the marker (121). In addition, the device (200 of FIG. 2) can convert each of the obtained first distance, the obtained second distance, and the obtained third distance into a matrix, and estimate external parameters regarding a camera disposed inside the vehicle (110) using each of the converted matrices.

[0031] Additionally, the device (200 in FIG. 2) can convert the positioning results using the camera into a vehicle coordinate system based on the estimated external parameters.

[0032] Below, we describe in detail how to estimate external parameters for the camera.

[0033] FIG. 2 is a block diagram of a device for estimating camera external parameters using one camera placed on a vehicle according to one embodiment of the present invention.

[0034] Referring to FIG. 2, a device (200) for estimating camera external parameters using a single camera placed on a vehicle according to an embodiment of the present invention may include a camera (210), a memory (220), and a processor (230) electrically connected to the camera (210) and the memory (220).

[0035] The configuration of the device (200) illustrated in FIG. 2 is according to one embodiment, and the components of the device (200) are not limited to the embodiment illustrated in FIG. 2, and some components may be added, changed, or deleted as needed. For example, the device (200) may include a motion detection sensor (not illustrated) that detects the movement of the vehicle (110). This sensor (not illustrated) is placed in a location where it is easy to detect the movement of the vehicle, and the motion detection result may be transmitted to the processor (230).

[0036] According to one embodiment, the camera (210) may be mounted on the front of the vehicle (110). The camera (210) may include a camera mounted on a black box installed in the vehicle. The camera (210) may acquire an image (e.g., a marker image) located in front of the vehicle and then transmit it to the processor (230).

[0037] The camera (210) may include at least one image sensor. The camera (210) may acquire images of markers located within a parking space. The camera (210) may include an image intelligence camera (or smart image intelligence camera) with a built-in artificial intelligence chip. The image intelligence camera may be used to recognize objects, people, lanes, crosswalks, intersections, etc., in front or behind the vehicle.

[0038] For example, the camera (210) may include a camera (e.g., an RGB (Red Green Blue) camera) that can acquire images of the front or rear of the vehicle even in situations with high illumination due to lighting, and an IR (infrared) camera that can acquire images in situations with low illumination. The camera (210) may include a device (e.g., an LED, an IR pattern light) that emits light necessary to acquire images.

[0039] According to one embodiment, the memory (220) may store information, data, programs, etc. necessary for the operation of the device (200). Specifically, various information or data described below may be stored in advance in the memory (220). Accordingly, the processor (230) may perform the control operation described below with reference to the information stored in the memory (220). The memory (220) may store signals and data processed by the processor (230), and may store a program for estimating external parameters. The memory (220) may also store various platforms. For example, the memory (220) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., an SD or XD memory, etc.), a RAM, and a ROM (e.g., an EEPROM).

[0040] According to one embodiment, the memory (220) can store map information for various parking spaces. For example, map information corresponding to various parking spaces may be pre-stored in the memory (220), or may be received from a server (not shown) and stored in the memory (220). For example, when a vehicle is parked in a new parking space, the processor (150) can identify the location of the vehicle's current parking space via GPS and request map information for the current parking space from a server (not shown). In addition, the processor (230) can store the received map information in the memory (220) in response to the request.

[0041] According to one embodiment, the memory (220) can store an image (e.g., a marker image) acquired from the camera (210).

[0042] According to one embodiment, the processor (230) may include circuitry capable of controlling components of the device (200). For example, the processor (230) may be electrically connected to a camera (210) and a memory (220).

[0043] According to one embodiment, the processor (230) may be implemented as a physical element of at least one of application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, micro-controllers, microprocessors, microcontroller units (MCUs), and microprocessors (MPUs).

[0044] According to one embodiment, the processor (230) may identify, through a sensor (not shown), whether the rear wheels of the vehicle (110) are positioned on the boundary line (132) of the parking area (130), and if the rear wheels are positioned on the boundary line (132) of the parking area (130), obtain a first distance between the center point of the rear wheel axle of the vehicle and a corner (e.g., the lower left corner) of the parking area (130). Then, the processor (230) may convert the obtained first distance value into a 4X4 matrix and generate a first inverse matrix of the converted 4X4 matrix. This first distance is a measured distance between the global coordinate system and the reference vehicle center coordinate system.

[0045] According to one embodiment, the processor (230) may obtain (or calculate) a second distance between a reference point, which is the center point of the rear wheel axle of the vehicle (110), and a marker (121) attached to a wall (120) located on one side (e.g., the front) of the vehicle (110). Then, the processor (230) may convert the obtained second distance into a 4X4 matrix.

[0046] According to one embodiment, the processor (230) can obtain (or calculate) a third distance between the camera (210) and the marker (121). Then, the processor (230) can convert the obtained third distance into a 4X4 matrix and generate a second inverse matrix of the converted 4X4 matrix.

[0047] According to one embodiment, the processor (230) may convert the acquired first distance value (i.e., the first distance value between the edge of the parking area and the center point of the rear wheel axle of the vehicle) into a matrix, convert the acquired second distance (i.e., the distance between the reference point, which is the center point of the rear wheel axle of the vehicle (110), and the marker (121)) into a matrix, and convert the acquired third distance (i.e., the distance between the camera (210) and the marker (121)) into a matrix.

[0048] In addition, the processor (230) can estimate external parameters regarding the camera (210) using each of the transformed matrices. In addition, the processor (230) can convert the positioning results using the camera (210) into a vehicle coordinate system based on the estimated external parameters.

[0049] According to one embodiment, the processor (230) can estimate the external parameters of the camera (210) by multiplying the first inverse matrix, the matrix transformed based on the second distance, and the second inverse matrix.

[0050] FIG. 3 is a flowchart illustrating a method for estimating camera external parameters using a single camera positioned on a vehicle according to an embodiment of the present invention. FIG. 4 is an exemplary diagram illustrating a marker according to an embodiment of the present invention. FIG. 5 is an exemplary diagram illustrating a state of estimating camera external parameters using a single camera positioned on a vehicle according to an embodiment of the present invention.

[0051] Hereinafter, with reference to FIGS. 3, 4 and 5, a method for estimating camera external parameters using one camera disposed in a vehicle according to an embodiment of the present invention will be described in detail.

[0052] According to one embodiment, the processor (230) can identify whether the reference point of the vehicle is located at the boundary line of the parking area (S310). The processor (230) can identify whether the reference point of the vehicle (110) (i.e., the center point of the rear wheel axle of the vehicle) is located at the boundary line (132) of the parking area (130) (e.g., the boundary line perpendicular to the direction of travel of the vehicle). The processor (150) can identify the current location of the vehicle and the size of the parking area (e.g., the horizontal length and the vertical length) through the map information acquired from the memory (220), and can identify the location of the reference point of the vehicle on the map information.

[0053] According to one embodiment, the processor (230) can obtain a first distance between the center points of the rear wheel axles of the vehicle from the edge of the parking area (S312). When the rear wheels of the vehicle (110) are located on the boundary line (132) of the parking area (130), the processor (230) can obtain a first distance (321) between the center points of the rear wheel axles of the vehicle from the edge of the parking area. This first distance (321) can be obtained through map information about the parking space.

[0054] For example, the first distance (321) may be a value stored in the memory (220) by measuring the actual distance after mounting the camera (210), or may be a value obtained through a correction procedure after installing a correction plate according to a predetermined procedure in front of the vehicle and stored in the memory (220). Alternatively, the first distance may be a value in a table created by accumulating previous installation experience depending on the type of vehicle and the installation location.

[0055] And, the processor (230) can convert the acquired first distance value (321) into a 4X4 matrix and generate a first inverse matrix of the converted 4X4 matrix.

[0056] According to one embodiment, the processor (230) can obtain a second distance between a reference point of the vehicle and a marker on a wall (S314). The processor (230) can obtain (or calculate) a second distance between a reference point, which is the center point of the rear wheel axle of the vehicle (110), and a marker (121) attached to a wall (120) located on one side (e.g., the front) of the vehicle (110). In addition, the processor (230) can convert the obtained second distance into a 4X4 matrix.

[0057] Referring to Fig. 4, a marker is a mark (e.g., a QR code) attached to a wall, floor, or ceiling within a parking space to identify the location of a vehicle during unmanned parking. The size of the marker image is 40 cm X 40 cm (width X height), and the boundary of the marker has a certain interval (401) from the border of the marker image. In addition, the marker has a grid structure with a certain interval (402). Such a marker satisfies the ISO23374 standard.

[0058] According to one embodiment, the processor (230) can obtain a third distance between the camera and the marker (S316). The processor (230) can obtain (or calculate) the third distance between the camera (210) and the marker (121). Then, the processor (230) can convert the obtained third distance into a 4X4 matrix and generate a second inverse matrix of the converted 4X4 matrix.

[0059] Referring to FIG. 5, the processor (230) can identify whether the axle (140) of the rear wheel of the vehicle is located on the boundary line (132) of the parking area (130) (e.g., whether the rear wheel of the vehicle is located on the boundary line (132). If the rear wheel is located on the boundary line (132), the processor (230) can obtain a first distance between the center point of the rear wheel axle of the vehicle from the edge of the parking area, and can obtain a second distance (324) between a reference point, which is the center point of the rear wheel axle of the vehicle (110), and a marker attached to a wall located on one side of the vehicle. In addition, the processor (230) can obtain a third distance (323) between the camera (210) and the marker.

[0060] According to one embodiment, the processor (230) can estimate external parameters regarding the camera using the acquired first distance, second distance, and third distance (S318). The processor (230) can convert the acquired first distance value (i.e., the first distance value between the center point of the rear wheel axle of the vehicle from the edge of the parking area) into a matrix, convert the acquired second distance (i.e., the distance between the reference point, which is the center point of the rear wheel axle of the vehicle (110), and the marker (121)) into a matrix, and convert the acquired third distance (i.e., the distance between the camera (210) and the marker (121)) into a matrix.

[0061] And, the processor (230) can estimate external parameters regarding the camera (210) using each transformed matrix.

[0062] The external parameters of the camera (210) may include three-dimensional space coordinates (x, y, z) and pan, tilt, and roll angles (θΨΦ) of the camera (210). Among the three-dimensional space coordinates (x, y, z), the coordinate (z) may correspond to the height from the ground where the vehicle (110) is located, and the height of the camera (210) may be Zc. In addition, the coordinate (x) and the coordinate (y) may correspond to the position on a virtual plane parallel to the ground where the vehicle (110) is located.

[0063] Meanwhile, the pan angle (θ) can be defined as the angle formed by the head direction of the camera (210) and the moving direction of the vehicle (110). In addition, the tilt angle (Ψ) can be defined as the angle formed by the shooting direction of the camera (210) and the ground. In addition, the roll angle (Φ) can be defined as the rotation angle of the camera (210) based on the head direction axis of the camera (210).

[0064] According to one embodiment, the processor (230) can calculate the transformation relationship between the vehicle coordinate system, the camera coordinate system, and the global coordinate system as a determinant.

[0065] The vehicle coordinate system is a coordinate system that indicates the position of the vehicle based on the rear wheel axle of the vehicle, the camera coordinate system is a coordinate system that indicates the position of the vehicle based on the camera placed inside the vehicle, and the global coordinate system is a coordinate system related to the parking area.

[0066] According to one embodiment, the processor (230) can express the transformation relationship between the vehicle coordinate system, the camera coordinate system, and the global coordinate system as [Mathematical Formula 1] below.

[0067]

[0068] In <Mathematical Formula 1>, H consists of R, t, 0, and 1. In addition, R is a 3 x 3 rotation matrix, t is a 3 x 1 translation vector, 0 is a 1 x 3 zero matrix, and 1 is a scalar.

[0069] According to one embodiment, the processor (230) converts a first distance value between the center point of the rear wheel axle of the vehicle from the edge of the parking area into a 4X4 matrix as shown in [Mathematical Formula 2] below.

[0070]

[0071] In <Mathematical Formula 2>, d1 is the distance value measured from the center of the global coordinate system to the center of the vehicle coordinate system. In addition, the transformation relationship of the marker coordinate system with respect to the global coordinate system ( The distance between the vehicle's reference point and the marker is calculated as a 4X4 matrix as shown in [Mathematical Formula 3] below. The processor (230) converts the distance between the vehicle's reference point and the marker into a 4X4 matrix as shown in [Mathematical Formula 3] below.

[0072]

[0073] In <Mathematical Formula 3>, here are the x, y, z measurements of the marker coordinate system center relative to the global coordinate system.

[0074] Transformation relationship from camera coordinate system to marker coordinate system ( ) can be obtained using the points of the marker recognized by the camera and the internal parameters of the camera.

[0075] And, the processor (230) converts the distance between the camera (210) and the marker (121) into a 4X4 matrix as shown in [Mathematical Formula 4] below.

[0076]

[0077] When a camera estimates the pose of a marker, it includes 6 degrees of freedom information, where 6 degrees of freedom means a total of 6 parameter information, including translation components of x, y, and z + rotation components of x, y, and z. Therefore, the processor (230) can simply express the transformation between coordinates as a multiplication between matrices through the mathematical equations described above.

[0078] The processor (230) constructs the middle P vector of the above figure with three movement components of x, y, and z among the six degrees of freedom of the marker recognized by the camera, constructs a rotation matrix R using the rotation components of x, y, and z using the Rodriguez rotation formula, and can construct a matrix such as the above <Mathematical Formula 4> by combining the R matrix and the P vector.

[0079] The external camera parameters based on the vehicle coordinate system are obtained using the following [Mathematical Formula 5].

[0080]

[0081]

[0082] Contains information about the rotation and movement of the vehicle coordinate system reference marker. If the marker (121) recognized by the camera (210) contains noise, the processor (230) can apply a filter to remove the noise.

[0083] Alternatively, the external camera parameters relative to the vehicle coordinate system can be obtained using [Mathematical Formula 6] below.

[0084]

[0085] In <Mathematical Formula 6>, the r elements represent the rotation matrix elements of the marker recognized by the camera, and p represents the translation element. In addition, d consists of the previously obtained measurement values.

[0086] According to one embodiment, the processor (230) can calculate the camera external parameters based on the vehicle coordinate system through <Mathematical Formula 5> or <Mathematical Formula 6>. In addition, the calculation speed of <Mathematical Formula 6> may be faster than that of <Mathematical Formula 5>.

[0087] As described above, the processor (230) can estimate the external parameters of the camera (210) by multiplying the first inverse matrix and the matrix transformed based on the second distance, and then multiplying the second inverse matrix. Then, the processor (230) can convert the positioning results using the camera (210) into a vehicle coordinate system based on the estimated external parameters.

[0088] As described above, the present invention can estimate external parameters for a camera by obtaining a first distance value between the center point of the rear wheel axle of the vehicle from the edge of the parking area when the rear wheels of the vehicle are positioned on the parking area, a second distance between a reference point which is the center point of the rear wheel axle of the vehicle and a marker attached to a wall located on one side of the vehicle, and a third distance between the camera and the marker, and converting each of these into a matrix.

[0089] Each step in each of the flowcharts described above may be performed regardless of the order shown, or may be performed simultaneously. Furthermore, at least one component of the present invention and at least one operation performed by said at least one component may be implemented in hardware and / or software.

[0090] Although the present invention has been described with reference to the drawings exemplified above, it is to be understood that the present invention is not limited to the embodiments and drawings disclosed herein, and that various modifications may be made by those skilled in the art within the scope of the technical idea of ​​the present invention. Furthermore, even if the operational effects according to the configuration of the present invention have not been explicitly described while describing the embodiments of the present invention, it is natural that the effects predictable by the corresponding configuration should also be acknowledged.

Claims

1. A device for estimating camera external parameters using a single camera placed on a vehicle, Cameras placed inside the vehicle; and comprising a processor electrically connected to the above camera, The above processor, Identify whether the rear wheels of the above vehicle are positioned at the boundary of the parking area, If the rear wheel is located on the boundary line, a first distance value between the center point of the rear wheel axle of the vehicle and the edge of the parking area is obtained, Obtain a second distance between a reference point, which is the center point of the rear wheel axle of the vehicle, and a marker attached to a wall located on one side of the vehicle, Obtaining a third distance between the camera and the marker, Convert each of the above-obtained first distance, the above-obtained second distance, and the above-obtained third distance into a matrix, A device for estimating camera external parameters using one camera disposed on a vehicle, the device including a processor set to estimate external parameters of the camera using each of the above-mentioned transformed matrices.

2. In paragraph 1, The above processor, A device for estimating camera external parameters using one camera placed on a vehicle, the device being set to convert the first distance value obtained above into a 4X4 matrix and generate a first inverse matrix of the converted 4X4 matrix.

3. In paragraph 2, The above processor, A device for estimating camera extrinsic parameters using one camera placed on a vehicle set to convert the above-mentioned acquired second distance into a 4X4 matrix.

4. In paragraph 3, The above processor, A device for estimating camera extrinsic parameters using one camera placed on a vehicle, which is set to convert the above-mentioned acquired third distance into a 4X4 matrix and generate a second inverse matrix of the above-mentioned converted 4X4 matrix.

5. In paragraph 4, The above processor, A device for estimating camera external parameters using a camera disposed on a vehicle, the device being set to estimate external parameters of the camera by multiplying the first inverse matrix, the matrix transformed based on the second distance, and the second inverse matrix.

6. A method for estimating camera external parameters using a single camera placed on a vehicle, The process of identifying whether the rear wheels of a vehicle are positioned at the boundary of a parking area; A process of obtaining a first distance value between the center point of the rear wheel axle of the vehicle and the edge of the parking area when the rear wheel is located on the boundary line; A process of obtaining a second distance between a reference point, which is the center point of the rear wheel axle of the vehicle, and a marker attached to a wall located on one side of the vehicle; A process of obtaining a third distance between the camera and the marker; A process of converting each of the acquired first distance, the acquired second distance, and the acquired third distance into a matrix; and A method for estimating camera external parameters using one camera placed on a vehicle, the method including a process of estimating external parameters of the camera using each of the above-mentioned transformed matrices.

7. In paragraph 6, The process of obtaining the above first distance value is: A method for estimating camera extrinsic parameters using one camera placed on a vehicle, the method comprising the steps of converting the acquired height value into a 4X4 matrix and generating a first inverse matrix of the converted 4X4 matrix.

8. In paragraph 7, The process of obtaining the above second distance is: A method for estimating camera extrinsic parameters using one camera placed on a vehicle, the method comprising the process of converting the obtained second distance into a 4X4 matrix.

9. In paragraph 8, The process of obtaining the above third distance is: A method for estimating camera extrinsic parameters using one camera placed on a vehicle, the method comprising the steps of converting the obtained third distance into a 4X4 matrix and generating a second inverse matrix of the converted 4X4 matrix.

10. In paragraph 9, The process of estimating the external parameters of the above camera is: A device for estimating camera external parameters using a camera disposed on a vehicle, the device being set to estimate external parameters of the camera by multiplying the first inverse matrix, the matrix transformed based on the second distance, and the second inverse matrix.

Images