KR20140052769A - Apparatus and method for correcting distored image - Google Patents

Abstract

The present invention relates to correcting distorted images. Particularly, the present invention relates to apparatus for correcting distorted images capable of providing reality images since a difference between an image photographed by a fisheye lens and a target object can be minimized by producing corrected image by optimizing a non-linear area of the image photographed by the fisheye lens and a method thereof. For this, according to an embodiment of the present invention, the apparatus for correcting distorted images comprises: an image front-end processing unit for adjusting the major and shortening rates of an inputted image when an image photographed by at least one camera is inputted; a parameter outputting unit for outputting camera parameter for optimizing the non-linear area of the adjusted image when the adjusted image is applied through the image front-end processing unit; and a corrected image providing unit for providing corrected images using the camera parameter outputted from the adjusted images.

Description

[0001] APPARATUS AND METHOD FOR CORRECTING DISTORED IMAGE [0002]

The present invention relates to a distortion image correction method and, more particularly, to a method and an apparatus for correcting distortion by optimizing a nonlinear region of an image photographed through a fisheye lens to generate a corrected image, And more particularly, to a distortion compensating apparatus and method capable of providing a more realistic image.

The contents described in this section merely provide background information on the present embodiment and do not constitute the prior art.

In general, a fisheye lens can be used to capture a surrounding image included in a camera installed in the rear of the vehicle or a video security surveillance camera to assist parking. These fisheye lenses can acquire an area of more than 180 degrees, so that the maximum camera angle can be secured with a minimum of camera, and intentional barrel distortion can be generated to maintain uniform brightness and sharpness over an angle of view of 180 degrees or more Or < / RTI > As a result, it is possible to acquire a wide-area image through a fish-eye lens.

However, in the fisheye lens, the subject captured at the center of the lens is shot extremely large, and the background is taken very small. Therefore, there is a problem that the image photographed through the fisheye lens is severely distorted, and therefore, there is a difference from the actual photographing object and the reality is deteriorated.

Therefore, various techniques for correcting distortion of an image captured through such a fish-eye lens have been developed. However, there is no technology that can optimize and correct a corner portion of an image and a non-linear portion existing in the image.

The present invention has been proposed in order to solve the inconvenience of the prior art, and it is an object of the present invention to minimize a difference between an image photographed by a fish-eye lens and an actual photographing object by optimizing a nonlinear region of the image photographed by the fish- And a method for correcting a distorted image.

To this end, the present invention reduces the time required for the calculation by binarizing the calculation process of the camera parameters capable of optimizing the non-linear region of the photographed image, and can reduce the distortion correction ratio calculated using the camera parameters organically And more particularly, to a distortion image correcting apparatus and method capable of generating a more accurate corrected image by applying the present invention to an image.

According to an aspect of the present invention, there is provided an apparatus for correcting a distorted image, the apparatus comprising: an image preprocessing unit configured to adjust a long axis and a short axis ratio of an input image, A parameter calculation unit for calculating a camera parameter for optimizing a non-linear region of the adjustment image when the adjusted image is applied through the image preprocessing unit; And a corrected image generating unit for generating a corrected image using the calculated camera parameters in the adjusted image.

In this case, the image preprocessor extracts the minutiae points of the input image, determines the long axis and the minor axis length of the area connecting the minutiae points, calculates the scaling factor using the long axis and the minor axis length, The long axis and the short axis ratio of the image can be adjusted.

The parameter calculator may calculate the camera parameter so that the value of the predefined function is minimized using the feature point calculated through the image preprocessing unit.

The camera parameters may include an internal parameter including one of a focal length, a field of view, and a skew vector of a lens provided in the camera, And an external parameter including any one of rotation, movement, and rotation.

The parameter calculation unit may calculate the internal parameter, and calculate the external parameter using the calculated internal parameter and the feature point calculated through the image preprocessing unit.

The correction image generating unit may generate a corrected image by calculating a distortion correction ratio using the camera parameters calculated through the parameter calculating unit in the adjusted image, and generate a corrected image based on a distance from the center point to the adjusted image center point, The correction image can be generated by adjusting the correction ratio.

According to another aspect of the present invention, there is provided a distortion image correcting method comprising: adjusting a long axis and a shortening ratio of an input image when a captured image is input from one or more cameras; Calculating a camera parameter for optimizing a non-linear region of the adjusted image; And generating a corrected image using the camera parameters in the adjusted image.

The step of adjusting the long axis and the short axis ratio may include extracting minutiae points of the input image; Calculating a ratio of the long axis and the short axis length of the region connecting the extracted minutiae; Calculating a scaling factor based on the ratio of the major axis and the minor axis length; And adjusting the long axis and the short axis ratio of the input image by applying the scaling factor to the input image.

In the calculating of the camera parameter, the camera parameter may be calculated so that the value of the predefined function is minimized using the extracted feature points.

The generating of the corrected image may include calculating a distortion correction ratio using the camera parameter; And generating a corrected image by adjusting a distortion correction ratio according to a distance from a center point with respect to a center point of the adjusted image.

In addition, the present invention can further provide a computer-readable recording medium characterized in that a program for executing the distortion image correction method described above is recorded.

According to the distortion image correcting apparatus and method of the present invention, the ratio of the major axis and the minor axis length of the image taken through the fish-eye lens of the camera is matched, the parameter value for the camera is calculated, The nonlinear region of the matched image is optimized to generate the corrected image, so that the maximum viewing angle can be ensured by using the wide viewing angle of the fisheye lens.

Therefore, it is possible to provide a realistic image by minimizing the difference between the image photographed using the fisheye lens and the actual photographed object, and the maximum viewing angle can be secured with the minimum camera in the parking assistance system using the same, And more accurate information can be provided to the user.

1 is a diagram illustrating a configuration of an image processing system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a distortion image correcting apparatus according to an embodiment of the present invention. Referring to FIG.
3 is an exemplary diagram illustrating a FOV model according to an embodiment of the present invention.
4 is a diagram for explaining a process of adjusting a long axis and a short axis ratio of an input image according to an embodiment of the present invention.
5 is an exemplary view for explaining a real-world coordinate system and a camera coordinate system according to an embodiment of the present invention.
FIG. 6 is a flowchart for explaining a process of calculating camera parameters including one-step and two-step according to an embodiment of the present invention.
7 is a flowchart illustrating a method of compensating for a distorted image according to an embodiment of the present invention.
8 and 9 are views illustrating an input image and a corrected image according to an exemplary embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description and the accompanying drawings, detailed description of well-known functions or constructions that may obscure the subject matter of the present invention will be omitted. It should be noted that the same constituent elements are denoted by the same reference numerals as possible throughout the drawings.

The terms and words used in the present specification and claims should not be construed to be limited to ordinary or dictionary meanings and the inventor is not limited to the concept of terminology for describing his or her invention in the best way. It should be interpreted as meaning and concept consistent with the technical idea of the present invention. Therefore, the embodiments described in the present specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention, and not all of the technical ideas of the present invention are described. Therefore, It is to be understood that equivalents and modifications are possible.

First, an image processing system according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram illustrating a configuration of an image processing system according to an embodiment of the present invention.

Referring to FIG. 1, the image processing system may include at least one camera 100, a distortion correction apparatus 200, and a video output apparatus 300.

The at least one camera 100 is a device capable of acquiring a wide-area image. The at least one camera 100 may include a fish eye lens, preferably an ultra-wide angle lens having an angle of view of 180 degrees or more. The camera 100 including the fisheye lens may be installed in the rear of the vehicle to support the parking of the vehicle, and may provide the driver with the image of the rear of the vehicle and the image of the blind zone.

At this time, the camera 100 including the fisheye lens acquires a three-dimensional image as a two-dimensional image. At this time, the acquired image has severe distortion. For example, when the distortion is radially expanded on the basis of the lens center point There may be reduced radial distortion.

An example of such radial distortion is shown in Fig. 8, in which the subjects at the lens center point become extremely large, and the surrounding subjects become very small compared to the subject at the lens center point, as shown in Fig.

The distorted image correction apparatus 200 corrects an input image and generates a corrected image when the image captured from one or more cameras 100 is input. In particular, the distortion-compensating apparatus 200 of the present invention adjusts the long axis and the shortening ratio of the input image, calculates a camera parameter for optimizing the non-linear region of the adjusted image, and generates a corrected image using the camera parameter.

At this time, the image can be corrected by adjusting the distortion correction ratio when generating the corrected image. In order to allow the user to perceive the image without loss of the maximum viewing angle, the distortion correction ratio is set according to the distance from the center point By doing so, a corrected image can be generated.

For example, the distortion compensated image compensating apparatus 200 can obtain a maximum viewing angle with a minimum camera at the time of stopping / stopping the vehicle, And corrects the radial distortion of the photographed image due to the characteristics of the fisheye lens.

The video output apparatus 300 is a device that can provide the user with the corrected video by the distortion correction apparatus 200. For example, the video output apparatus 300 may be a display apparatus, a vehicle navigation system, a terminal apparatus, have.

The distorted image correcting apparatus according to an embodiment of the present invention corrects distortion of a photographed image by using a fisheye lens. However, the present invention is not limited to this, and if the lens is capable of photographing a wide area image, Lenses are also applicable to the present invention.

In addition, the camera 100, the distortion correction device 200, and the image output device 300 may be implemented independently of each other, and may be connected to each other through a wired or wireless connection.

The distortion compensating apparatus 200 may be embodied in the camera 100 or may be embodied in the image output apparatus 300. The distortion compensating apparatus 200 may be implemented by a camera 100, 200 and the image output apparatus 300 may be implemented as a single apparatus.

Hereinafter, a main configuration and an operation method of the distortion compensating apparatus 200 according to an embodiment of the present invention will be described.

2 is a block diagram showing a main configuration of a distortion image correction apparatus in an image processing system according to an embodiment of the present invention.

1 and 2, a distortion compensating apparatus 200 according to an exemplary embodiment of the present invention includes an image acquiring module 210, an image processing module 220, a video output module 230, and an image storage module 240 ). ≪ / RTI >

More specifically, the image collecting module 210 collects images photographed through one or more cameras 100. In particular, the image acquisition module 210 of the present invention collects images photographed through a camera 100 including a fisheye lens. An image photographed through the camera 100 including a fisheye lens is obtained as described above It has a radial distortion as well.

That is, as shown in FIG. 3, the FOV model assumes that the distance between one point m on the image plane at the center point C of the image is proportional to the angle formed by one point M on the corresponding three-dimensional plane and the optical axis Cz, The distortion function of the FOV model can be defined as Equation (1).

는 왜곡된 거리를 나타내며,

는 렌즈의 왜곡이 없는 경우, 영상 중심에서 해당 픽셀까지의 거리를 나타낸다. 즉, 영상 중심에서 해당 픽셀까지의 거리

는 상기의 <수학식 1>에 의해 왜곡되어 왜곡된 거리

가 산출되는 것이며, 이때의

는 어안 렌즈의 화각으로, 카메라 내부 파라미터가 된다. 이상적인

는 1의 값을 가질 수 있다.here,

Represents a distorted distance,

Represents the distance from the center of the image to the corresponding pixel when there is no distortion of the lens. That is, the distance from the center of the image to the corresponding pixel

Is distorted by the above-mentioned < EMI ID =

Is calculated. At this time,

Is a fisheye angle of a fisheye lens, and is a camera internal parameter. ideal

Can have a value of one.

The image acquisition module 210 can digitize an image collected in an analog form at a speed of, for example, 30 frames / second, and transmit the digitized image to the image processing module 220.

The image processing module 220 generates a corrected image by correcting distortion of the image collected through the image acquisition module 210. Particularly, the image processing module 220 of the present invention optimizes the nonlinear region of the distorted image A distortion correction ratio is calculated based on the calculated camera parameters, and a distortion correction ratio is applied to the collected image to generate a corrected image.

For this, the image processing module 220 of the present invention may include an image preprocessing unit 221, a parameter calculation unit 222, and a correction image generation unit 223.

More specifically, the image preprocessing unit 221 matches the long axis and the short axis ratio of the image collected through the image acquisition module 210 before correcting the distorted image.

를 계산하고, 이를 특징점 좌표 변환에 적용하여 비율을 일치시킨다. More specifically, since the fisheye lens is generally designed to have a larger horizontal angle of view than the vertical angle of view, it is necessary to match the long axis and the short axis ratio of the image before the correction of the image. To this end, the image preprocessing unit 212 uses an ellipse-fitting algorithm to calculate a scaling factor

And applies it to the minutiae coordinate transformation to match the ratios.

That is, as shown in FIG. 4, an image photographed through a fish-eye lens can be divided into a photographed region and a surrounding region. A specific number of characteristic points, for example, six characteristic points are extracted from the photographed region , And when they are connected, a certain area, that is, an ellipsoid can be obtained. Here, various known techniques may be applied to the process of extracting feature points.

) 및 단축(

)의 길이를 하기 <수학식 2>에 적용하여 스케일링 인자

를 계산하게 된다.Then, the long axis of the ellipsoid

) And shortening (

) Is applied to the following equation (2) to calculate the scaling factor

.

Here, since the adjustment image in which the ratio of the major axis and the minor axis length of the input image is matched is arbitrarily expanded, the edge (outline) portion of the image becomes nonlinear.

The image preprocessing unit 221 transfers the adjusted image obtained by matching the ratios of the long axis and the short axis length of the input image to the parameter calculation unit 222.

In addition, the image preprocessing unit 221 of the present invention can perform various image preprocessing such as noise removal in addition to the above-mentioned ratio of the long axis and short axis length of the image.

For example, when the image preprocessing unit 221 receives an image composed of 8-bit color and RGB three channels of 640 * 480 resolution and performs image processing as it is in the resolution of the received image, the calculation time becomes very long The width and height of the image can be minimized, for example, reduced to 1/2, and the received image can be converted into a monochrome image. In addition, the image preprocessing unit 221 extracts the outline of the image using the binarized image data, and regards an area having an area of a predetermined pixel, for example, 1000 pixels or less among the areas of the extracted outline as noise, You may.

The parameter calculator 222 calculates a camera parameter for optimizing the non-linear region of the image, when an image whose length ratio of the long axis and the short axis is adjusted through the image preprocessing unit 221 is applied.

개의 특징점을 이용하게 되는데, 즉, 하기의 <수학식 3>의 영상(

)가 최소화되도록 카메라 파라미터(

)에 대한 최적값을 추정하게 된다.At this time, the image preprocessing unit 221

(3) < / RTI >&lt; RTI ID = 0.0 &gt;

) To minimize camera parameters (

). &Lt; / RTI &gt;

은 왜곡되지 않은 점을 외부 파라미터

과

, 내부 파라미터

를 사용하여 왜곡시킨 점을 의미하는 것으로, 외부 파라미터 중

은 3x3의 회전 행렬을 의미하며,

는 3x1의 이동 행렬이 될 수 있다.here,

Lt; RTI ID = 0.0 &gt; non-distorted &

and

, Internal parameters

Quot ;, and &quot;

Denotes a rotation matrix of 3 x 3,

Lt; RTI ID = 0.0 &gt; 3x1 &lt; / RTI &gt;

는 어안 렌즈의 화각이며,

는 어안 렌즈의 초점 거리(focal length)를 의미하며,

는 센서에 따른 변형을 나타내는 파라미터를 의미한다.Also, among the internal parameters

Is an angle of view of a fish-eye lens,

Means a focal length of a fisheye lens,

Means a parameter representing a deformation according to the sensor.

More specifically, the camera parameter according to the embodiment of the present invention may be configured of an internal parameter and an external parameter. The internal parameter is a relationship between the image coordinates and the camera coordinates And can be determined at the time of manufacture of the camera. The internal parameter may be a focal length, a skew vector, a lens center, and the like as described above. On the other hand, the external parameter refers to the relationship between the camera coordinate and the spatial coordinate, for example, information about the rotation or movement of the camera. These external parameters may vary from one shot to another.

)를 카메라 초점을 기준으로 하는 카메라 좌표계(

)로 변환하게 되는 데, 외부 파라미터인 회전 행렬

과 이동 행렬

를 이용하여 하기의 <수학식 4>에 따라 수행하게 된다.In order to calculate the camera parameters of the applied image, the parameter calculation unit 222 calculates the camera parameters of the virtual camera in the real world coordinate system (

) To the camera's coordinate system based on the camera's focus

), Which is an external parameter, a rotation matrix

And movement matrix

(4) &quot; (4) &quot;

)에서 2차원 영상으로 투영될 때, 이 둘 사이의 관계는 점 사영(point projection)에 기반한 핀홀(pin hole) 카메라 모델로 가정할 수 있는 데, 이때, 다양한 사영 기법 중 원근 사영(perspective projection)에 따라 원거리 물체는 작게, 근거리 물체는 크게 표현될 수 있다.Here, the camera coordinate system (

When the two-dimensional image is projected onto a two-dimensional image, the relationship between the two can be assumed to be a pin hole camera model based on a point projection. In this case, The distant object can be expressed small, and the near object can be expressed largely.

는 사영 중심과 영상 평면 사이의 거리를 의미한다.5, a three-dimensional point P = (Xc, Yc, Zc) is calculated as a point P '= (x, y) in the image plane by applying Equation And the internal parameter focal length

Is the distance between the center of the projection and the image plane.

Finally, since the input image is digitized and stored, it is affected by characteristics of a sensor such as a CCD (Charge Coupled Device) and a CMOS (Complementary Metal Oxide Semiconductor).

Therefore, if the pixels to be stored are not square, the scaling factor K for the size of the two coordinate axes of the image should be considered. In the conversion between the camera image coordinate system and the real image coordinate system, the deformation according to the sensor is calculated according to Equation (6) below in consideration of the internal parameter K.

는 내부 파라미터로 이용하게 된다.Further, as described above with reference to Equation (1), the angle of view of the fish-eye lens

Is used as an internal parameter.

Previously, the internal parameters could be the intrinsic property values of the camera, and the extrinsic parameters could vary from one image to another.

That is, the focal length and the degree of warp of the camera, which are internal parameters, are determined at the time of manufacture of the camera, and information about the rotation or movement of the camera, which is an external parameter, There is a problem that when the position or angle of the camera is changed, the camera must be recalculated.

Therefore, in the embodiment of the present invention, the internal parameter is calculated first, and the external parameter is calculated each time the position and angle of the camera 100 are changed using the calculated internal parameter, thereby improving the speed of the calculation.

개의 특징점을 추출한 후, 이를 이용하여 기 정의된 <수학식 3>을 이용하여 내부 파라미터를 먼저 산출하게 된다(S103). 여기까지가 파라미터 추출 1단계이다.That is, as shown in FIG. 6, when an image is inputted (S101), an input image (a three-dimensional real world image obtained in a two-dimensional form)

After extracting the feature points, the internal parameters are first calculated using Equation (3) defined previously (S103). Here is the parameter extraction step 1.

개의 특징점의 좌표와 S103 단계에서 산출된 내부 파라미터를 이용하여(S105) 외부 파라미터를 산출하게 된다(S107). 여기까지가 파라미터 추출 2단계로 이후, 카메라(100)의 위치 및 각도가 변경될 1단계는 생략하고 2단계만을 수행함으로써, 파라미터 산출 시의 연산 속도가 보다 더 빨라질 수 있다.Then,

The coordinates of the minutiae points and the internal parameters calculated in step S103 are used to calculate the external parameters (S105) (S107). The calculation speed at the time of parameter calculation can be further increased by omitting the step of changing the position and angle of the camera 100 and performing only the second step after the parameter extraction step 2 up to this point.

The corrected image generating unit 223 generates a final corrected image in which the image distortion is corrected.

That is, the corrected image is generated by transforming the coordinates of the distorted input image using a predefined function such as Equation (7) below.

At this time, the coordinates of the corrected image may be calculated by applying the distortion correction ratio to the coordinates of the input image.

Here, the distortion correction ratio can be previously allocated according to the system setting.

)일 경우 하기의 <수학식 8>에 따라 왜곡 보정 후 영상 좌표의 위치에 따른 비율

를 계산하여 보정하게 된다.For example, if the size of the image after distortion correction is (

), The ratio according to the position of the image coordinates after the distortion correction according to the following Equation (8)

Is calculated and corrected.

, 즉 왜곡 영상의 중심에서 해당 픽셀까지의 거리가 길어져 역방향 사상으로 가져올 수 있는 정보가 적어 해상도가 낮아지게 되며, 퍼짐 현상 등 여러가지 문제로 인해 오히려 인지하기 어려운 결과 영상을 출력할 수 있다는 문제점이 있다.At this time, if the image is closer to the center of the image, the distortion correction ratio is increased and the distortion correction ratio is decreased toward the outer edge. When the image is corrected on the two-dimensional plane by applying the pinhole camera model to the input image having an angle of view of 180 degrees or more as described above,

That is, the distance from the center of the distorted image to the corresponding pixel becomes long, the information that can be brought back to the reverse mapping is small and the resolution is low, and the resulting image can be output with difficulty in recognition due to various problems such as spreading .

Therefore, if the image is closer to the center of the image, the distortion correction ratio is increased, and by decreasing the distortion correction ratio toward the outer side, the above-described problem can be solved.

에서 왜곡 보정 비율 (

)를 조절하기 위해 하기의 <수학식 9>를 이용하여 왜곡 보정 비율을 산출할 수 있다.Further, the coordinates

The distortion correction ratio (

The distortion correction ratio can be calculated using Equation (9) below.

는 사용자가 직접 입력할 수도 있다.Here, the distortion constant

May be entered directly by the user.

Thereafter, the distortion correction ratio calculated through the process described above may be applied to Equation (10) to generate a corrected image reflecting the distortion correction ratio.

That is, the corrected image for the input image shown in FIG. 8 is shown in FIG. 9, and it can be seen that the nonlinear regions are significantly reduced.

The distortion compensating apparatus 200 according to the present invention includes an image storage module 240 for temporarily or permanently storing various images generated according to a process of the image processing module 220, And a video output module 230 for delivering the video signal to the video output module 230.

At this time, the image storage module 240 stores various information generated in the correction image generation process. For example, control information for driving the distortion image correction device 200 and an image input from one or more cameras 100 are stored A corrected image obtained by correcting the distortion of the image, or a camera parameter value calculated for each camera 100 may be stored. The image storage module 240 may be an optical storage medium such as a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, a compact disk read only memory (CD-ROM), and a digital video disk ), A magneto-optical medium such as a floppy disk and a ROM, a random access memory (RAM), and a flash memory.

The distortion image correction method in the image processing system constructed as above will now be described in detail with reference to the accompanying drawings.

7 is a flowchart illustrating a method of compensating for a distorted image according to an embodiment of the present invention.

Referring to FIGS. 1 and 7, first, an image photographed from one or more cameras 100 is received and input (1101). In this case, the input image may be a distorted image as shown in FIG.

Thereafter, the distortion-compensated image correcting apparatus 200 performs a process of matching the ratio of the major axis and the minor axis length of the input image (1102).

At this time, as described above, the feature points of the input image are extracted first. At this time, as shown in FIG. 8, the region where the image exists and the surrounding region can be input together. After extracting the feature points from the region where the image exists, the ellipsoid is displayed by connecting the feature points.

Thereafter, the lengths of the long and short axes of the region are calculated, and the scaling factor is calculated according to the ratio of the lengths of the long and short axes. Then, the scaling factor of the region connecting the minutiae, And the shortening ratio is adjusted.

Then, the camera parameter is calculated to optimize the generated non-linear region of the adjusted image (1103).

The camera parameters include an internal parameter and an external parameter. The value of each parameter is estimated so that the result of Equation (3) is minimized as described above. Here, at the time of parameter calculation, first, an internal parameter is calculated, and an external parameter can be calculated using the coordinates of the internal parameter and the minutiae point of the input image.

Thereafter, a distortion correction ratio is calculated using the camera parameters to generate a corrected image, and a distortion correction ratio is applied to the adjusted image whose lengths of the long and short axes are adjusted (1104) to generate a corrected image (1105 ).

The corrected image can be generated by adjusting the distortion correction ratio according to the distance from the center point based on the center point of the adjusted image at the time of generating the corrected image.

Thereafter, when the corrected image is transmitted to the image output apparatus 300, the image output apparatus 300 receiving the corrected image outputs the corrected image (1106).

The distortion image correction method according to the embodiment of the present invention has been described above.

The distortion image correcting method as described above can derive the image most similar to the real image from the image taken through the fish-eye lens, so that the distance between the camera and the target can be accurately calculated using the information of the corrected image , And as a result, it is applied to a vehicle parking system and the like, thereby realizing an obstacle recognition, a surrounding space securing, a situation control, and the like.

In addition, such a distorted image correction method may be implemented by a program and implemented in a computer-readable recording medium.

The program instructions to be recorded for executing the distortion image correction method according to the present invention may be those specially designed and configured for the present invention or may be those known and used by those skilled in the computer software. For example, the recording medium may be an optical recording medium such as a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, a compact disk read only memory (CD-ROM), a digital video disk (DVD) Includes a hardware device that is specially configured to store and execute program instructions such as a magneto-optical medium such as a floppy disk and a ROM, a random access memory (RAM), a flash memory, do. Examples of program instructions may include machine language code such as those generated by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like. Such a hardware device may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

It should be noted that the embodiments of the present invention disclosed in the present specification and drawings are only illustrative of specific examples for the purpose of understanding and are not intended to limit the scope of the present invention. It will be apparent to those skilled in the art that other modifications based on the technical idea of the present invention are possible in addition to the embodiments disclosed herein.

The present invention relates to a distortion image correction method and, more particularly, to a method and an apparatus for correcting distortion by optimizing a nonlinear region of an image photographed through a fisheye lens to generate a corrected image, This is a useful invention that generates effects that can provide a more realistic image, thereby contributing to the development of the service industry.

100: camera 200: distortion image correction device 210: image acquisition module
220: image processing module 221: image preprocessing unit
222: parameter calculating unit 223:
230: video output module 240: video storage module
300: Video output device

Claims (11)

An image preprocessing unit for adjusting a long axis and a short axis ratio of the input image when an image photographed from one or more cameras is input;
A parameter calculation unit for calculating a camera parameter for optimizing a non-linear region of the adjustment image when the adjusted image is applied through the image preprocessing unit; And
A corrected image generating unit for generating a corrected image using the calculated camera parameters in the adjusted image;
And a distortion correcting unit for correcting distortion of the input image. The method according to claim 1,
The image preprocessing unit
After calculating the scaling factor using the long axis and the short axis length after extracting the minutiae points of the input image and confirming the long axis and the short axis length of the area connecting the minutiae points and then applying the scaling factor to the input image, And the distortion correction unit corrects the distorted image. The method according to claim 1,
The parameter calculation unit
Wherein the camera parameter is calculated so that a value of a predefined function is minimized by using the feature point calculated through the image preprocessing unit. The method of claim 3,
The camera parameters
An internal parameter including one of a focal length, a field of view, and a skew vector of a lens provided in the camera, and an internal parameter including any one of rotation and movement of the camera And an external parameter including one parameter. 5. The method of claim 4,
Wherein the parameter calculator comprises:
And calculates the external parameter by using the calculated internal parameter and the feature point calculated through the image preprocessing unit. The method according to claim 1,
Wherein the corrected image generating unit comprises:
A correction image is generated by calculating a distortion correction ratio using the camera parameter calculated through the parameter calculation unit in the adjustment image, and the distortion correction ratio is adjusted according to the distance from the center point with respect to the adjustment image center point, And outputs the distorted image. Adjusting a major axis and a minor axis ratio of the input image when an image photographed from one or more cameras is input;
Calculating a camera parameter for optimizing a non-linear region of the adjusted image; And
Generating a corrected image using the camera parameters in the adjusted image;
And correcting the distorted image. 8. The method of claim 7,
The step of adjusting the long axis and the short axis ratio
Extracting feature points of the input image;
Calculating a ratio of the long axis and the short axis length of the region connecting the extracted minutiae;
Calculating a scaling factor based on the ratio of the major axis and the minor axis length; And
Adjusting the long axis and the short axis ratio of the input image by applying the scaling factor to the input image;
And correcting the distorted image. 9. The method of claim 8,
The step of calculating the camera parameters
And calculating a camera parameter such that a value of a previously defined function is minimized using the extracted feature points. 8. The method of claim 7,
The step of generating the corrected image
Calculating a distortion correction ratio using the camera parameters; And
Generating a corrected image by adjusting a distortion correction ratio according to a distance from a center point with respect to a center point of the adjusted image;
And correcting the distorted image. A computer-readable recording medium storing a program for executing the distortion image correction method according to any one of claims 7 to 10.

Images