KR100955889B1 - Apparatus And Method For Generating Panorama Image And Apparatus For Monitoring Rear View Of Vehicle Based On Panorama Image - Google Patents

Abstract

The present invention relates to an apparatus and method for generating a panoramic image and to an apparatus for monitoring a vehicle rear based on the panoramic image. The present invention includes an image acquisition step of acquiring a first image and a second image; An area acquiring step of acquiring an overlapping area in which the first image and the second image overlap with respect to the obtained first and second images based on a pixel orientation; An image synthesizing step of synthesizing the first image and the second image based on the obtained overlapping region to generate a panoramic image; And a panorama image generating method including an image displaying step of displaying the generated panorama image, a panorama image generating apparatus for performing the same, and a vehicle rear monitoring apparatus based on the panorama image.

Panoramic image, pixel directionality, first-order differential edge operator, Sobel operator

Description

Apparatus And Method For Generating Panorama Image And Apparatus For Monitoring Rear View Of Vehicle Based On Panorama Image}

The present invention relates to a technical field of generating a panorama image by synthesizing a plurality of images, and more particularly, to a panorama image generating apparatus and method for generating a panorama image in real time by reducing the complexity of the image synthesis process, and a panorama image. It relates to a vehicle rear monitoring device based.

Panoramic images provide a wider field of view. When moving the camera up, down, left, and right, the panorama image reconstruction, which combines several frames including the partial images, and reconstructs the whole image, shows the difference in magnification between the frames, the geometric distortion between the center and the edges, and the image by the moving camera. In addition to researches to correct and solve blur, the researches for converting and reconstructing frames have been conducted. In addition, when converting a digital image, values of pixels outside the integer lattice position are frequently used, and therefore an algorithm capable of effectively interpolating them is required. Although research is being actively conducted in relation to the construction of the virtual environment or the research of ultra high resolution, there are still problems regarding complexity.

Conventional techniques for synthesizing panoramic images can be divided into model-based representation methods and image-based representation methods. Model-based representation requires a long processing time to generate a 3-D model, and there is a limitation that complex models cannot be represented. Therefore, it is difficult to actually implement a real-time panorama image. In addition, since only two-dimensional images are used as the image-based expression method, there is less data to process than the model-based expression method, but there are problems in real-time processing and image synthesis is not well performed in complex scenes.

The present invention solves the above problems and has been proposed in accordance with recent trends and requests, and has an object to provide a panorama image generating apparatus and method capable of generating a panorama image in real time by reducing the complexity of the image synthesis process. .

Another object of the present invention is to reduce the complexity of the image synthesis process for the images obtained from a plurality of cameras mounted on the rear of the vehicle to generate a panoramic surveillance image in real time, allowing the driver to efficiently monitor the rear of the vehicle in real time. It is to provide a vehicle rear monitoring apparatus based on a panoramic image that can be performed.

As an aspect of the present invention for achieving the above object, a method for generating a panoramic image according to the present invention, the image acquisition step of obtaining a first image and a second image; An area acquiring step of acquiring an overlapping area in which the first image and the second image overlap with respect to the obtained first and second images based on a pixel orientation; An image synthesizing step of synthesizing the first image and the second image based on the obtained overlapping region to generate a panoramic image; And an image displaying step of displaying the generated panoramic image.

The area acquiring step may include: (a) a boundary area of the second image corresponding to the first boundary area to form a boundary area of the first image (hereinafter referred to as a “first boundary area”) and a panoramic image; Filtering (hereinafter referred to as “second boundary region”) using a first order differential edge operator; And (b) comparing the directionality of each of the pixels corresponding to each other with respect to the filtered first and second boundary regions to obtain a region having a distribution ratio of pixels having the same direction within an error range as a threshold value as the overlapping region. Can be.

The first derivative edge operator may be a technical feature that is a Sobel operator.

In the step (a), for each pixel constituting the first boundary region and the second boundary region, filtering is performed on the x-axis direction, the y-axis direction, the left diagonal direction and the right diagonal direction using the Sobel operator. Obtaining values and summing these values are set as the filtering values of the respective pixels, and in the step (b), the directionality can be compared by comparing the set filtering values for each corresponding pixel. .

The image synthesizing step may be a technical feature of applying a low pass filter to the obtained overlapped region.

The first image and the second image may be characterized in that the resolution is the same.

As another aspect of the present invention for achieving the above object, the panorama image generating apparatus according to the present invention, the image acquisition unit for obtaining a first image and a second image of the same resolution; A region obtaining unit obtaining an overlapping region in which the first image and the second image overlap with each other based on a direction of a pixel with respect to the obtained first and second images; An image synthesizer configured to synthesize the first image and the second image based on the obtained overlapped area to generate a panorama image; A display unit displaying the generated panoramic image; And a controller for controlling the image acquisition unit, the area acquisition unit, the image synthesis unit, and the display unit.

The area acquirer may include a boundary area of the first image (hereinafter referred to as a “first boundary area”) and a boundary area of the second image corresponding to the first boundary area (hereinafter referred to as a “second” area) to form a panoramic image. Boundary region ") using a first order differential edge operator, and compares the directionality of each pixel corresponding to each other with respect to the filtered first and second boundary regions so that It may be a technical feature that an area having a distribution ratio equal to or greater than a threshold is obtained as the overlapped area.

The first derivative edge operator may be a technical feature that is a Sobel operator.

The area obtaining unit may be configured to filter the values of the x-axis direction, the y-axis direction, the left diagonal direction and the right diagonal direction for each pixel constituting the first boundary area and the second boundary area by using the Sobel operator. It may be a technical feature to compare the directivity by obtaining the respective values and adding the summed values as the filtering values of the respective pixels and comparing the set filtering values for each pixel corresponding to each other.

The image synthesizing unit may be a technical feature of applying a low pass filter to the obtained overlapped region.

As another aspect of the present invention for achieving the above object, the vehicle rear monitoring apparatus based on the panoramic image according to the present invention is installed at a rear of the vehicle at a specific separation distance, each of the subject to take a first surveillance image and First and second image acquisition units respectively acquiring a second surveillance image; An area obtaining unit obtaining an overlapping area in which the first surveillance image and the second surveillance image overlap with respect to the acquired first and second surveillance images based on a pixel orientation; An image synthesizer configured to generate the panoramic surveillance image by synthesizing the first surveillance image and the second surveillance image based on the obtained overlapped area; A display unit displaying the generated panoramic surveillance image; And a controller for controlling the image acquisition unit, the area acquisition unit, the image synthesis unit, and the display unit.

The area obtaining unit may include a boundary area of the first surveillance image (hereinafter referred to as a “first boundary region”) and a boundary area of the second surveillance image corresponding to the first boundary region (hereinafter, referred to as a “first boundary region”). Filter the " second boundary region " using a first-order differential edge operator and compare the directionality for each pixel corresponding to the filtered first and second boundary regions so that the directionality is within the error range. The technical feature may be to obtain, as the overlapping region, an area in which a distribution ratio of the same pixels is greater than or equal to a threshold.

The first derivative edge operator may be a technical feature that is a Sobel operator.

The area obtaining unit may be configured to filter the values of the x-axis direction, the y-axis direction, the left diagonal direction and the right diagonal direction for each pixel constituting the first boundary area and the second boundary area by using the Sobel operator. It may be a technical feature to compare the directivity by obtaining the respective values and adding the summed values as the filtering values of the respective pixels and comparing the set filtering values for each pixel corresponding to each other.

The controller is configured to control the image acquisition unit, the area acquisition unit, and the image synthesizing unit in real time to synthesize the panoramic surveillance image in real time and to monitor the rear side of the vehicle in real time. It may be characterized by the technical features.

According to the panorama image generating apparatus and method and the rear view vehicle based on the panoramic image according to the present invention has the following advantages.

First, according to the panorama image generating apparatus and method according to the present invention, it is possible to reduce the complexity of the image synthesis process to generate a panorama image in real time.

Secondly, according to the rear-vehicle monitoring apparatus based on the panoramic image according to the present invention, by reducing the complexity of the image synthesizing process for the images obtained from a plurality of cameras mounted on the rear of the vehicle to generate a panoramic surveillance image in real time It is effective to monitor the rear of the vehicle efficiently in real time.

The above objects, features and advantages of the present invention will become more apparent from the following detailed description taken in conjunction with the accompanying drawings. Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Like numbers refer to like elements throughout. In addition, when it is determined that the detailed description of the known function or configuration related to the present invention may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted.

1 is a block diagram of a panoramic image generating apparatus according to an embodiment of the present invention. Referring to FIG. 1, a panoramic image generating apparatus according to an embodiment of the present invention will be described in detail.

In the panorama image generating apparatus according to an embodiment of the present invention, the image obtaining unit 100, the region obtaining unit 110, the image synthesizing unit 120, the display unit 130, the storage unit 140 and the controller 150 It may be configured to include.

The image acquisition unit 100 acquires a first image and a second image. For example, as illustrated in FIG. 1, the image acquisition unit 100 may include a first camera 103 and a second camera 104. The first camera 103 may acquire the first image, and the second camera 104 may acquire the second image. The first image and the second image may have the same resolution.

The area acquisition unit 110 acquires an overlapping area in which the first image and the second image overlap with respect to the obtained first and second images based on the direction of the pixel. The overlapping area refers to an area in which directionalities of pixels are common to the first and second images. This does not require that the directionality of the pixels match 100%. The overlapping area refers to an area in which the distribution ratio of pixels having the same directionality within the error range with respect to the first and second images is greater than or equal to a threshold. Details of the overlapping region will be described later.

The image synthesizing unit 120 generates a panoramic image by synthesizing the first image and the second image based on the obtained overlapping region. The image synthesizer 120 may apply a low pass filter to the obtained overlapped region.

The display unit 130 is a display device for displaying the state or various information of the panoramic image generating apparatus by the control signal output from the control unit 150. For example, the display unit 130 displays the panoramic image generated by the image synthesizing unit 120 according to the control signal of the controller 150.

The storage unit 140 stores a predetermined program for controlling the overall operation of the panoramic image generating apparatus according to an embodiment of the present invention, and the overall operation of the panoramic image generating apparatus is performed by the controller 150. When the data is stored, the data input and output and the various data processed are stored. The storage unit 140 may temporarily or permanently store various image data generated by the operations of the image acquisition unit 140, the area acquisition unit 110, and the image synthesis unit 120. have. For example, the storage 140 may store the images acquired by the image acquisition unit 100 and the panorama image generated by the image synthesis unit 120.

The controller 150 controls the components and manages the overall operation of the panoramic image generating apparatus according to an embodiment of the present invention.

2 is a flowchart illustrating a panorama image generating method according to an embodiment of the present invention. Referring to FIG. 2 and necessary drawings, a detailed operation of the panoramic image generating apparatus according to an embodiment of the present invention and a panomamara image generating method according to an embodiment of the present invention will be described in detail.

First, a first image and a second image are obtained [S200]. The step S200 may be performed by the image acquisition unit 100.

In operation S210, an overlapping region in which the first image and the second image overlap with each other is obtained based on the direction of the pixel with respect to the obtained first and second images. The step S210 may be performed by the area acquisition unit 110.

3 is a detailed flowchart of the overlapped area obtaining step (S210). The region obtaining unit 110 may include a boundary region of the first image (hereinafter referred to as a “first boundary region”) and a boundary region of the second image corresponding to the first boundary region to form a panoramic image. Hereinafter, the "second boundary region" is filtered using a first derivative edge operator [S300]. Examples of the first derivative edge operator include the Sobel operator, the Roberts operator, the Prewitt operator, the Frei-Chen operator, and the like.

4 is a flowchart of an embodiment of a method of filtering a specific pixel to obtain a filtering value. 5 is a filter coefficient of the Sobel operator. FIG. 6 illustrates an example of obtaining a filtering value in the x-axis direction for a specific pixel by using the Sobel operator. 4 to 6, an embodiment of a method of filtering a pixel to obtain a filtering value will be described in detail.

The area obtaining unit 110 may use the Sobel operator with respect to each pixel constituting the first boundary area and the second boundary area, and use the Sobel operator in an x-axis direction, a y-axis direction, and a left-diagonal direction. And calculating filtering values for a right-diagonal direction, respectively (S410), and adding the sums of the filtering values (S420) to the filtering values of the respective pixels (S430), and setting the filtering values for each of the corresponding pixels. By comparing these, the directivity can be compared. For example, referring to FIG. 6, it can be seen that the filtering value for the x-axis direction of the specific pixel 201 of the first image 200 is obtained as −27.

In addition, the area obtaining unit 110 compares the direction of each pixel corresponding to each other with respect to the filtered first and second boundary areas, and acquires an area having a distribution ratio of pixels having the same direction within an error range as a threshold value as the overlapping area. [S310].

7A and 7B are diagrams for describing boundary regions and overlapping regions of the first and second images. For example, referring to FIG. 7A, pixels P _{A , 14} , P _{A , 24} , P _{A , 34} , P _{A ,} which exist on the rightmost side of the first image 200 corresponding to the left image. A pixel line constituting a ₄₄ becomes the first boundary region 300a and the pixels P _{B , 11} , and P _B that exist on the leftmost side of the second image 210 corresponding to the right image. Pixel lines constituting _{, 21} , P _{B , 31} , P _{B , 41} become the second boundary region 300a. P _{A , 14} , P _{B , 11} , P _{A , 24} , P _{B , 21} , P _{A , 34} , P _{B, 31,} and P _{A , 44} , P _{B , 41} are pixels corresponding to each other. The first boundary area 300a and the second boundary area 300b correspond to the overlapping area. That is, the pixels corresponding to each other with respect to the pixels constituting the first boundary area 300a and the second boundary area 300b are compared. For example, the directions of the pixels P _{A , 14} and the pixels P _{B , 11} are compared with each other. In this case, the direction of the pixels may be compared by the filtering values described above with reference to FIGS. 4 to 6. When comparing the directions of pixels corresponding to each other by the filtering value, the filtering values do not necessarily have to match exactly. If the respective filtering values of the pixels corresponding to each other are the same within a preset error range, the pixels are determined to have the same direction.

For example, referring to FIG. 7B, the pixels P _{A , 14} , P _{A , 24} , P _{A , 34} , P _{A ,} which exist on the rightmost side of the first image 200 corresponding to the left image. Pixel line 303a constituting ₄₄ and pixel line 301a constituting pixels P _{A , 13} , P _{A , 23} , P _{A , 33} , P _{A , 43 which} are next to the left It becomes the first boundary area 300a. The pixel line 301b constituting pixels P _{B , 11} , P _{B , 21} , P _{B , 31} , P _{B , 41} which exist on the leftmost side of the second image 210 corresponding to the right image. The pixel line 303b constituting the pixels P _{B , 12} , P _{B , 22} , P _{B , 32} , P _{B, 42} next to and to the right becomes the second boundary region 300a. . Here, the pixel line 303a and the pixel line 303b are pixel lines corresponding to each other, and the pixel line 301a and the pixel line 301b are pixel lines corresponding to each other. Pixels constituting the pixel lines corresponding to each other are compared with each other by using the filtering value.

The distribution ratio of the pixels having the same directionality within the error range means that the first boundary region 300a and the second boundary region 300b are oriented for each pixel, and thus, the first boundary region 300a or the second boundary region. The ratio of the number of pixels having the same directivity to the number of pixels constituting the boundary area 300b refers to the ratio. For example, in FIG. 7A, when the directionality of the first boundary area 300a and the second boundary area 300b is compared for each pixel, if the directionality of the three pixels is the same within the error range, the directionality is within the error range. The distribution ratio of the same pixels is 3/4 = 0.75 = 75%. If the threshold value is 70%, the first boundary area 300a and the second boundary area 300b shown in FIG. 7A are regarded as an area composed of the same pixels and become the overlapping area.

For example, in FIG. 7B, the pixel-to-pixel 301a and the pixel line 301b corresponding to each other are compared, and as a result, the distribution ratio of pixels having the same directionality within an error range is 75% and corresponds to each other. When the distribution ratio of the pixels having the same directionality with respect to the pixel line 303a and the pixel line 303b is 100% within an error range, and the threshold value is 70%, the first boundary region shown in FIG. 7B ( 300a) and the second boundary area 300b are regarded as an area composed of the same pixels, and thus become the overlapping area.

For example, in FIG. 7B, the pixel-to-pixel 301a and the pixel line 301b corresponding to each other are compared, and as a result, the distribution ratio of pixels having the same directionality within an error range is 50% and corresponds to each other. If the distribution ratio of the pixels having the same directionality with respect to the pixel line 303a and the pixel line 303b is 75%, and the threshold is 70%, the pixel line 301a shown in FIG. 7B. And the pixel line 301b are not considered to be an area composed of the same pixels and thus cannot be the overlapping area, and the pixel line 303a and the pixel line 303b are regarded as an area composed of the same pixels. To become the overlapping area.

In operation S220, a panorama image is generated by synthesizing the first image and the second image based on the obtained overlapped region. The step S220 may be performed by the image synthesizing unit 120. 8A and 8B illustrate an example of a panoramic image synthesized based on an overlapping region with respect to FIGS. 7A and 7B, respectively. 8A and 8B illustrate cases where both of the first boundary area 300a and the second boundary area 300b become the overlapping area.

The low pass filter is applied to the overlapped region among the generated panorama images [S230]. The step S230 may be performed by the image synthesizing unit 120. When a low pass filter is applied to the overlapped region, noise that may be generated by synthesis may be removed.

The panoramic image is displayed on the display unit 130 [S240].

The above-described panorama image generating apparatus and method according to an embodiment of the present invention can be applied to various fields. 9 is a diagram for describing a vehicle rear monitoring apparatus based on a panoramic image according to an exemplary embodiment. FIG. 9 illustrates an apparatus for detecting a rear of a vehicle based on a panoramic image generated by the panoramic image generating apparatus and method according to an embodiment of the present invention described above with reference to FIGS. 1 to 8. In FIG. 9, only the image acquisition unit 100 including the first camera 103 and the second camera 104 and the display unit 130 are illustrated, but the panoramic image according to an embodiment of the present invention is illustrated. The apparatus for monitoring a vehicle behind the vehicle is based on the components shown in FIG. 1, that is, the image acquisition unit 100, the area acquisition unit 110, the image synthesis unit 120, the display unit 130, and the storage. The unit 140 and the controller 150 may be configured to be included. The function and role of each component is the same as described above.

As shown in FIG. 9, two cameras 103 and 104 are installed at the rear of the vehicle, and the images provided therefrom are synthesized into a panoramic image according to an embodiment of the present invention, thereby providing a wider view to the driver. It is possible to provide a field of view. By providing the driver with a rearward view of a wide field of view, the driver may not only provide convenience to the driver in relation to obstacles, parking spaces and reversing located behind the driver, but may also inform the driver of various accidents.

According to the rear-vehicle monitoring apparatus based on the panoramic image according to an embodiment of the present invention, the amount of calculation is significantly reduced compared to the panorama image generating apparatus and method according to the prior art, it is possible to obtain the panoramic image in real time. The controller 150 controls the image acquirer 100, the region acquirer 110, and the image synthesizer 120 to monitor the rear of the vehicle in real time. Acquires the first and second surveillance images in real time, synthesizes the first and second surveillance images into the panoramic surveillance image in real time, and displays the synthesized panoramic surveillance image on the display unit 130 in real time. .

In the above-described embodiments of the present invention, an example of synthesizing the first image as the left image and the second image as the right image has been described, but the present invention is not limited thereto. For example, the first image may be synthesized by using an upper image and the second image by a lower image.

In the above-described embodiments of the present invention, the overlap region corresponds to the entire line, but the present invention is not limited thereto. It has already been described that the overlap region may be part of the first and second boundary regions. For example, referring to FIG. 7A, the overlapped region corresponds to a pixel set {P _{A , 24} , P _{A , 34} , P _{A , 44} } with respect to the first image 200 and the second image. For the 210, it may be an area corresponding to the pixel set {P _{B , 11} , P _{B , 21} , P _{B , 31} }. In this case, the image synthesizing unit 120 synthesizes the first image 200 and the second image 210 based on the overlapping region, and deletes the pixel line corresponding to the row that does not correspond to the overlapping region. Can be. That is, the pixel line corresponding to the pixel set {P _{A , 11} , P _{A , 12} , P _{A , 13} , P _{A , 14} } for the first image 200 and the pixel set for the second image 210. Pixel lines corresponding to {P _{B , 41} , P _{B , 42} , P _{B , 43} , P _{B, 44} } may be deleted.

The above-described panorama image generating method according to the present invention may be provided by recording on a computer-readable recording medium as a program for executing in a computer.

The panorama image generating method according to the present invention may be executed through software. When implemented in software, the constituent means of the present invention are code segments that perform the necessary work. The program or code segments may be stored on a processor readable medium or transmitted by a computer data signal coupled with a carrier on a transmission medium or network.

Computer-readable recording media include all kinds of recording devices that store data that can be read by a computer system. Examples of computer-readable recording devices include ROM, RAM, CD-ROM, DVD ± ROM, DVD-RAM, magnetic tape, floppy disks, hard disks, optical data storage devices, and the like. The computer readable recording medium can also be distributed over network coupled computer devices so that the computer readable code is stored and executed in a distributed fashion.

The present invention described above is capable of various substitutions, modifications, and changes without departing from the spirit of the present invention for those skilled in the art to which the present invention pertains. It is not limited by the drawings.

1 is a block diagram of a panoramic image generating apparatus according to an embodiment of the present invention.

2 is a flowchart illustrating a panorama image generating method according to an embodiment of the present invention.

3 is a detailed flowchart of the overlapped area obtaining step (S210).

4 is a flowchart of an embodiment of a method of filtering a specific pixel to obtain a filtering value.

5 is a filter coefficient of the Sobel operator.

FIG. 6 illustrates an example of obtaining a filtering value in the x-axis direction for a specific pixel by using the Sobel operator.

7A and 7B are diagrams for describing boundary regions and overlapping regions of the first and second images.

8A and 8B illustrate an example of a panoramic image synthesized based on an overlapping region with respect to FIGS. 7A and 7B, respectively.

9 is a diagram for describing a vehicle rear monitoring apparatus based on a panoramic image according to an exemplary embodiment.

<Explanation of symbols for the main parts of the drawings>

100: image acquisition unit 103: the first camera

104: second camera 110: area acquisition unit

120: video synthesizing unit 130: display unit

140: storage unit 150: control unit

200: first image, first surveillance image 210: second image, second surveillance image

300a: first boundary region 300b: second boundary region

400: panoramic video, panoramic surveillance video

Claims (17)

An image acquiring step of acquiring a first image and a second image; An area acquiring step of acquiring an overlapping area in which the first image and the second image overlap with respect to the obtained first and second images based on a pixel orientation; An image synthesizing step of synthesizing the first image and the second image based on the obtained overlapping region to generate a panoramic image; And An image display step of displaying the generated panoramic image; The area obtaining step, A boundary region of the first image (hereinafter referred to as a “first boundary region”) and a boundary region of the second image corresponding to the first boundary region (hereinafter referred to as a “second boundary region”) to form a panoramic image. For each pixel constituting), the filtering values for the x-axis direction, the y-axis direction, the left diagonal direction, and the right diagonal direction are respectively calculated by using a first-order differential edge operator, and the sum of these values is added to each pixel. Acquiring the overlapped area by using the directionality of the panoramic image; The method of claim 1, wherein the area obtaining step comprises: (a) setting the summed value as a filtering value of each pixel for each pixel constituting the first boundary area and the second boundary area; And (b) comparing the directionality by comparing the set filtering value for each pixel corresponding to each other with respect to the first boundary area and the second boundary area so that the distribution area of pixels having the same directionality within an error range is greater than or equal to a threshold value; To obtain the steps Panoramic image generating method comprising the. The method of claim 2, wherein the first derivative edge operator is A panorama image generation method, characterized in that the Sobel operator. delete The method of claim 3, wherein the synthesizing the image comprises: A low pass filter is applied to the obtained overlapped area. The method of claim 1, wherein the first image and the second image, A panorama image generating method characterized by the same resolution. A non-transitory computer-readable recording medium having recorded thereon a computer program capable of executing the method of any one of claims 1, 2, 3, 5, or 6. An image acquisition unit for acquiring a first image and a second image having the same resolution; A region obtaining unit obtaining an overlapping region in which the first image and the second image overlap with respect to the obtained first and second images based on a directionality of a pixel; An image synthesizer configured to synthesize the first image and the second image based on the obtained overlapped area to generate a panorama image; A display unit displaying the generated panoramic image; And And a controller for controlling the image acquisition unit, the area acquisition unit, the image synthesis unit, and the display unit. The area acquisition unit, A boundary region of the first image (hereinafter referred to as a “first boundary region”) and a boundary region of the second image corresponding to the first boundary region (hereinafter referred to as a “second boundary region”) to form a panoramic image. For each pixel constituting), the filtering values for the x-axis direction, the y-axis direction, the left diagonal direction, and the right diagonal direction are respectively calculated by using a first-order differential edge operator, and the sum of these values is added to each pixel. And a panorama image generating device for acquiring the overlapped area with the directionality of. The method of claim 8, wherein the area obtaining unit, For each of the pixels constituting the first boundary area and the second boundary area, the summed value is set as a filtering value of each pixel, and corresponding to each other for the first boundary area and the second boundary area. And comparing the directionality by comparing the set filtering value for each pixel to obtain an area in which the distribution ratio of pixels having the same directionality equal to or greater than a threshold within the error range is obtained as the overlapping area. 10. The method of claim 9, wherein the first derivative edge operator is A panoramic image generating device characterized in that the Sobel operator. delete The method of claim 10, wherein the image synthesizing unit, And a low pass filter is applied to the obtained overlapped area. First and second image acquisition units installed at a rear of the vehicle at a specific separation distance and respectively photographing a subject to obtain a first surveillance image and a second surveillance image; An area obtaining unit obtaining an overlapping area in which the first surveillance image and the second surveillance image overlap with respect to the acquired first and second surveillance images based on a pixel orientation; An image synthesizer configured to generate the panoramic surveillance image by synthesizing the first surveillance image and the second surveillance image based on the obtained overlapped area; A display unit displaying the generated panoramic surveillance image; And And a controller for controlling the image acquisition unit, the area acquisition unit, the image synthesis unit, and the display unit. The area acquisition unit, A boundary area of the first surveillance image (hereinafter referred to as "first boundary region") and a second boundary image corresponding to the first boundary region (hereinafter referred to as "first boundary region") to form a panoramic image. For each pixel constituting the filter, the filtering values for the x-axis direction, the y-axis direction, the left diagonal direction, and the right diagonal direction are respectively calculated using a first-order differential edge operator, and the sum of these values is recalled. And a panoramic image based on the panoramic image for acquiring the overlapped area by the direction of each pixel. The method of claim 13, wherein the area obtaining unit, For each of the pixels constituting the first boundary area and the second boundary area, the summed value is set as a filtering value of each pixel, and corresponding to each other for the first boundary area and the second boundary area. And comparing the directionality by comparing the set filtering value for each pixel to obtain an area in which the distribution ratio of pixels having the same directionality equal to or greater than a threshold within the error range is obtained as the overlapping area. 15. The method of claim 14, wherein the first derivative edge operator is A rear view monitoring device based on a panoramic image, characterized in that the Sobel operator. delete The method of claim 13, wherein the control unit, Controlling the image acquisition unit, the area acquisition unit, and the image synthesis unit to monitor the rear of the vehicle in real time, to synthesize the panoramic surveillance image in real time and to display the synthesized panoramic surveillance image in real time on the display unit. Vehicle rear monitoring device based on panoramic image.

Images