KR101835632B1 - Apparatus and method for calculating moving distance of vehicle - Google Patents

Abstract

The present invention relates to an apparatus and method for calculating a moving distance of a vehicle through camera image analysis without using a distance sensor. To this end, an apparatus for calculating a travel distance of a vehicle, which is applied to a vehicle equipped with a camera and a steering angle sensor of the present invention, includes an image obtaining unit for obtaining a camera image photographed from a camera; A mapping information retrieval unit for retrieving the detected steering angle value detected from the steering angle sensor and retrieving the image mapping information corresponding to the detected steering angle value in the storage unit; A comparison object region extraction unit for extracting a comparison object region from the plane image generated based on the camera image according to the image mapping information retrieved from the mapping information search unit; And a comparison object image generation unit for generating a comparison object image by scaling the comparison object area based on the image mapping information, wherein the bird's-eye image of the comparison object area has a ring segment shape, and the shape of the ring segment .

Description

TECHNICAL FIELD [0001] The present invention relates to an apparatus and a method for calculating a travel distance of a vehicle,

The present invention relates to an apparatus and method for calculating a travel distance of a vehicle, and more particularly, to an apparatus and method for calculating a travel distance of a vehicle through camera image analysis without using a distance sensor.

2. Description of the Related Art Generally, a vehicle is a device that drives a motor vehicle such as an engine installed in a vehicle body to drive a road or the like and carries a person or a freight or perform various operations. A driver of the vehicle safely drives the vehicle while observing the driving direction .

However, when the vehicle is parked, the driver of the vehicle is hard to watch the running direction, which is the rear of the vehicle. Accordingly, there is known a display device for displaying the rear of a vehicle, which outputs an image from a camera installed behind the vehicle to the monitor as it is, or converts the image to output a bird's-eye image of the surroundings of the vehicle.

In particular, Korean Laid-Open Patent Application No. 2015-0116116 (hereinafter referred to as Prior Art 1) discloses a technique of converting a camera image photographed by a camera into a bird's-eye view image and outputting the bird's-eye view image through a display device. In the prior art document 1, an object (for example, a parking line) existing in a space in which a vehicle has already passed is also displayed together with a bird's-eye view image at a current time and a bird's-eye view image at a current time Discloses a technique for performing display.

In the case of combining the bird's-eye images described above, the distance traveled by the vehicle must be considered, so that the configuration of the distance sensor installed in the vehicle must exist. However, in the case of an actual vehicle environment, since there are many vehicles without such a distance sensor, there is a problem that there is a limit to objects to which the above-described bird's-eye image synthesis technique can be applied.

Therefore, there is a need for a new apparatus and method that can accurately calculate the travel distance of the vehicle, even if the vehicle is not equipped with a distance detection sensor (e.g., a wheel pulse sensor).

Korean Patent Laid-Open Publication No. 2015-0116116 (entitled " Vehicle periphery image generating apparatus and method)

An object of the present invention is to provide an apparatus and a method for calculating a travel distance of a vehicle without using a distance sensor.

An apparatus for calculating a moving distance of a vehicle, which is applied to a vehicle equipped with a camera and a steering angle sensor of the present invention to solve the above problems, includes an image obtaining unit for obtaining a camera image photographed from a camera; A mapping information retrieval unit for retrieving the detected steering angle value detected from the steering angle sensor and retrieving the image mapping information corresponding to the detected steering angle value in the storage unit; A comparison object region extraction unit for extracting a comparison object region from the plane image generated based on the camera image according to the image mapping information retrieved from the mapping information search unit; And a comparison object image generation unit for generating a comparison object image by scaling the comparison object area based on the image mapping information, wherein the bird's-eye image of the comparison object area has a ring segment shape, and the shape of the ring segment .

In addition, the apparatus for calculating the moving distance of a vehicle according to an embodiment of the present invention may further include a first comparing unit that compares a first comparison image at a first point of time generated by the comparison object image generating unit with a second comparison image at a second point of time before the first point of time, And a movement distance calculation unit for calculating a movement distance of the vehicle between the first and second points of time by calculating the coordinate difference of the object included in the target image.

In addition, the movement distance calculating unit may calculate the movement distance of the vehicle between the first viewpoint and the second viewpoint by calculating a vertical movement distance between the object included in the first comparison object image and the object included in the second comparison object image.

Further, the comparison target area may be a part of the area between the two circles having the same center and different radii.

The vehicle movement distance calculating apparatus according to an embodiment of the present invention may further include a bird's-eye image generating unit for generating a bird's-eye view image of a camera image by performing a viewpoint conversion of a camera image.

Also, the comparison region extracting unit can extract the comparison region from the bird's-eye image of the camera image.

Also, when there is a linear component in the vertical direction in the object included in the bird's-eye view image of the comparison object region, distortion may occur in at least a part of the linear component of the object included in the comparison object image.

Also, the comparison object image generator may scale the comparison object area into a rectangular shape using the image mapping information.

In addition, the scaling of the comparison area may be performed through a GPU.

According to another aspect of the present invention, there is provided a method of calculating a moving distance of a vehicle, the method including: acquiring a camera image photographed by a camera using an image obtaining unit; Obtaining a detected steering angle value detected from the steering angle sensor by the mapping information searching unit; Retrieving image mapping information corresponding to the detected steering angle value in the storage unit by the mapping information searching unit; Extracting a comparison object region from a plane image generated based on the camera image according to the image mapping information searched by the comparison object region extraction unit; And generating a comparison object image by scaling the comparison object area based on the image mapping information by the comparison object image generating unit, wherein the bird's-eye view image of the comparison object area has a ring segment shape, The shape of the ring segment can be changed.

A moving distance calculation method of a vehicle according to the present invention is characterized in that the moving distance calculation unit calculates a moving distance of a vehicle based on a first comparison image at a first point of time and a second comparison point at a second point of time before a first point of time, And calculating the movement distance of the vehicle between the first and second points of view by calculating the coordinate difference of the object included in the comparison object image.

The step of calculating the moving distance of the vehicle between the first viewpoint and the second viewpoint may be performed by calculating a vertical movement distance between the object included in the first comparison object image and the object included in the second comparison object image.

Further, the comparison target area may be a part of the area between the two circles having the same center and different radii.

The method may further include generating a bird's-eye image for the camera image by performing a viewpoint conversion of the camera image by the bird's-eye image generating unit according to an exemplary embodiment of the present invention.

In addition, the step of extracting the comparison object region may be performed by extracting the comparison object region from the bird's-eye image of the camera image.

In addition, if there is a linear component in the vertical direction in the object included in the bird's-eye view image of the comparison object area, distortion may occur in at least a part of the linear component of the object included in the comparison object image.

In addition, the step of generating the comparison object image may scale the comparison object area into a rectangular shape using the image mapping information.

Also, in the step of generating the comparison object image, the scaling of the comparison object area can be performed by the GPU.

According to the vehicle movement distance calculating apparatus and method of the present invention, it is possible to calculate the travel distance of the vehicle through image analysis even in a vehicle without a distance sensor such as a wheel pulse sensor.

Further, according to the apparatus and method for calculating the travel distance according to the embodiment of the present invention, by using the steering angle information and the camera image of the vehicle, which can be supported by most of the vehicles, even if the vehicle moves in a curved direction, The distance traveled by the vehicle can be calculated.

In addition, the apparatus and method for calculating the travel distance according to an embodiment of the present invention do not need to additionally consider the steering angle when calculating the travel distance because the travel distance is calculated while the steering angle information of the vehicle is grasped. And it is possible to calculate the moving distance at high speed or in real time.

1 to 6 are conceptual diagrams for explaining a distance calculation method according to the related art.
7A and 7B are conceptual diagrams for explaining a method of calculating a travel distance of a vehicle through a vehicle travel distance calculating apparatus according to an embodiment of the present invention.
8 to 12 are conceptual diagrams for explaining a method of calculating a travel distance of a vehicle through a vehicle travel distance calculating apparatus according to an embodiment of the present invention.
13 is a block diagram of a vehicle travel distance calculating apparatus according to an embodiment of the present invention.
14 is a conceptual diagram for explaining a method of generating image mapping information according to an embodiment of the present invention.
15 is a block diagram of an apparatus for calculating travel distance of a vehicle according to another embodiment of the present invention.
16 is a flowchart illustrating a method of calculating a travel distance of a vehicle according to an embodiment of the present invention.
17 is a flowchart of a method of generating image mapping information according to an embodiment of the present invention.
18 is a flowchart illustrating a method of calculating a travel distance of a vehicle according to another embodiment of the present invention.

The present invention will now be described in detail with reference to the accompanying drawings. Hereinafter, a repeated description, a known function that may obscure the gist of the present invention, and a detailed description of the configuration will be omitted. Embodiments of the present invention are provided to more fully describe the present invention to those skilled in the art. Accordingly, the shapes and sizes of the elements in the drawings and the like can be exaggerated for clarity.

Before describing the vehicle travel distance calculating apparatus according to an embodiment of the present invention, a distance calculating method according to the related art will be described. The distance calculation method according to the related art can calculate the distance based on the sensor device mounted on the vehicle or calculate the moving distance of the vehicle through the image analysis technique as described below with reference to Figs. 1 to 6 have.

1 shows an example of a camera image photographed at time points t ₁ and t ₂ through a camera mounted on a vehicle. Specifically, FIG. 1 shows an example of a camera image photographed at t ₁ and t ₂ for the vehicle being parked. In Fig. 1, pl ₁ represents a parking line photographed at time t ₁ , and pl ₂ represents a parking line photographed at time t ₂ .

According to the distance calculating method according to the related art, as shown in Fig. 1, when the camera image at time t ₁ and t ₂ is acquired, the area including the parking lines cpl ₁ and cpl ₂ And converts each camera image into a bird's-eye view image. Specifically, the feature points included in as a distance calculating process according to the prior art is illustrated in Figures 2a and 3a, respectively, parking line (cpl _1, cpl ₂₎ in a camera image shot in the t ₁ and t ₂ time (p11, p12, p21, p22) and converts the camera image into a bird's-eye view image as shown in Figs. 2B and 3B. Here, the minutiae points p11, p12, p21, and 22 may be selected from corners in the parking line. Further, in the example shown in Figs. 2A and 3A, the shape of the grid lines set in the camera image is schematically shown, and is not actually limited to the shapes shown in Figs. 2A and 3A. For example, the lines in the horizontal and vertical directions in the actually applied graticule may have a shape of a curve, and the intervals may be set at various intervals.

Also, in the above description, the bird's-eye view image is an image as seen from above the peripheral region of the vehicle, and does not necessarily represent the image generated with the reference point as a point perpendicular to the center of the vehicle. That is, the bird's-eye view image represents the viewpoint-converted image so that the surrounding area including the vehicle appears in one image. Preferably, the bird's-eye image described below may represent a top view image in which the vehicle is represented at the center of the bird's-eye image when the reference point is set perpendicular to the vehicle. However, this is merely an example, and in the present invention, it is also possible that the reference point is set at various points on the upper part of the vehicle to generate a bird's-eye image at various points in time.

Then, according to the distance-calculation method according to the prior art, as shown in Fig. 4, t ₁ and t of feature points included in the bird's eye image of the _second point in time the vehicle by comparing the coordinates of (p11, p12, p21, p22) Can be calculated. Here, the moving distance of the vehicle corresponds to at least one of the moving distance _dc of the center reference point of the vehicle, the moving distance d1 of the first characteristic points p11 and p21, and the moving distance d2 of the second characteristic point p12. . ≪ / RTI >

As described above, the distance calculating method according to the related art can accurately calculate the moving distance according to the movement of the vehicle when the vehicle moves in the linear direction.

Now, as shown in Figures 5a and 5b, it is assumed the situation the vehicle is moving in the direction of the curve t ₁ point. In the case of the prior art, as described above, and extracts the feature point (p31, p32) in the camera image of the point in time t ₁ shown in Figure 5a. Thereafter, the coordinates of the camera image at the time t ₁ are calculated, and the camera image at the time t _{1 is} transformed into a viewpoint, thereby generating a bird's-eye image at the time t ₁ as shown in FIG. 5B.

Then, it is possible to even the as the example described with reference 3, extracts feature points (p21, p22) in the camera image of the point in time t _2, and performs coordinate calculations and generates a bird's eye view image of a time point t _2.

Moving Then, by comparing the coordinates of a, t ₁ and the characteristic point (p31, p32, p21, p22) contained in the bird's eye view image of a t ₂ time as conventionally distance calculating process according to the technique shown in Fig vehicle The distance can be calculated. However, unlike the example described with reference to Figs. 2 to 4, when the vehicle performs the curved movement, the moving distance of the vehicle must be taken into consideration not only the x-axis and y-axis but also the wheel angle of the vehicle. That is, as shown in the right-hand side of FIG. 6, when the vehicle performs a curve motion, not only the x-coordinate and y-coordinate but also the wheel angle of the vehicle must be further considered. , There is a problem that the calculation accuracy of the moving distance is considerably deteriorated because the wheel angle of the vehicle is estimated using only the image analysis.

Therefore, the apparatus for calculating the travel distance of a vehicle according to an embodiment of the present invention is not limited to a vehicle in which a distance sensor (for example, a wheel pulse sensor) is mounted, So that the moving distance of the vehicle can be accurately calculated with only a small amount of calculation. A description will now be given of the movement distance calculation apparatus 100 according to an embodiment of the present invention.

In the following description, a rear camera is mounted on the vehicle and a situation is assumed assuming that the vehicle moves backward. However, the same technical idea can be applied even in a situation where a front camera is mounted on a vehicle and a front camera image is photographed through a front camera when the vehicle moves in a forward direction. Therefore, the scope of right of the present invention may include not only technology using a rear camera but also technology using a front camera.

7A and 7B are conceptual diagrams for explaining a vehicle travel distance calculation apparatus 100 according to an embodiment of the present invention. The vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention generates a comparison object image at a time point t _{1 and a} time point t ₂ and generates a comparison image based on two comparison object images The moving distance of the vehicle can be calculated. However, unlike the related art, the apparatus 100 for calculating the travel distance of a vehicle according to an embodiment of the present invention generally receives a detected steering angle value from a steering angle sensor 12 existing in the vehicle, And an angle value is used.

7A and 7B, FIG. 7A is a conceptual diagram of a process of generating a comparison object image at time t ₁ in the bird's-eye view image, FIG. 7B is a process of generating a comparison object image at time t ₂ in the bird's- Fig. Here, the image to be compared refers to an image used for image comparison in the calculation of the travel distance through the vehicle travel distance calculation apparatus 100 according to an embodiment of the present invention. The comparison target image may be defined as an image generated based on the comparison target area in the camera image of the vehicle and the comparison target area may be defined as the area set in the camera image of the vehicle according to the detected steering angle value of the vehicle have.

That is, the process of generating the comparison object image through the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention can be summarized as follows.

The apparatus 100 for calculating the travel distance of a vehicle according to an embodiment of the present invention first receives the detected steering angle value at the steering angle sensor 12. Then, the vehicle movement distance calculation apparatus 100 according to the embodiment of the present invention searches for image mapping information based on the detected steering angle value detected from the steering angle sensor 12. [ Here, the image mapping information may include comparison area setting information for setting the above-mentioned comparison area, and scaling information used for generating the comparison image. The image mapping information may be stored, for example, in a storage (not shown), and different image mapping information may exist depending on the detected steering angle value.

Thereafter, the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention extracts a comparison object area from the camera image using the image mapping information, and based on the image mapping information and the comparison object area, Lt; / RTI > Specifically, the vehicle movement distance calculation apparatus 100 can extract a comparison object area corresponding to the steering angle detection value through the comparison object area setting information included in the image mapping information. Here, the comparison target area setting information may include the type and position information of the comparison target area to be set in the camera image according to the detected steering angle value. Thereafter, the vehicle movement distance calculation apparatus 100 can generate a comparison object image by performing a scaling process on the set comparison object region through the scaling information included in the image mapping information. Here, the generation of the comparison target image can be performed using the GPU. That is, although the generation of the comparison object image can be realized by other processing apparatuses, it is preferable to use the GPU for processing at a higher speed.

As another example, the vehicle movement distance calculation apparatus 100 according to the embodiment of the present invention can generate the comparison object image in a different manner in addition to the above-described method. That is, the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention can convert a camera image of a vehicle into a bird's-eye view image, and set a comparison target area according to a detected steering angle value of the vehicle in the bird's-eye view image.

For example, as shown in FIG. 7A, the apparatus 100 for calculating travel distance of a vehicle according to an embodiment of the present invention extracts a region to be compared tr ₁ from a bird's-eye image of a vehicle, ₁ ), the comparison object image can be generated. As shown in FIG. 7A, when the comparison area is extracted in the bird's-eye image, it may have a ring segment shape. As mentioned above, since the shape of the comparison target area varies in accordance with the detected steering angle value, the shape may be changed according to the detected steering angle value.

In a manner similar to, even in the case of the example shown in Figure 7b, extracting a comparison target area (tr ₂₎ from the images taken on the moving distance is t ₂ point calculation device 100 for a vehicle according to an embodiment of the present invention , And the comparison object image can be generated based on the comparison object area tr ₂ . As described above, the shape of the comparison object region tr ₂ may be changed depending on whether the object to be extracted is a camera image or a bird's-eye image, and in the case of a bird's-eye image, a ring segment shape. Thereafter, the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention can generate a comparison object image based on the comparison object region tr ₂ .

In the prior art, there is a problem in that a required calculation amount is large because both the x-axis, the y-axis, and the wheel angle must be considered in order to calculate the moving distance of the vehicle when the vehicle is curved. On the other hand, in the present invention, when the two images are matched, the wheel angle can be grasped using the detected steering angle value obtained through the steering angle sensor, so that only the value of the y axis, which is the distance traveled according to the wheel angle, can be considered. For example, if the prior art finds an optimal value among 10 values for each of the x-axis, the y-axis, and the wheel angle, all 1000 values must be compared. On the other hand, since the present invention obtains an optimal value for only one y-axis value (i.e., a vertical movement distance), only 10 values need to be compared. Therefore, the amount of computation required to calculate the movement distance can be significantly reduced, It is possible.

In addition, in the case of the related art, the calculation accuracy is low because the wheel angle must be calculated only by comparing two images. However, since the present invention can be calculated based on the detected steering angle value, Does not occur. Accordingly, more precise matching between the images to be compared can be performed, so that it is possible to accurately calculate the distance of movement even when the vehicle is curved.

8 to 11, a method for generating a comparison object image through the apparatus 100 for calculating the movement distance of a vehicle according to an embodiment of the present invention is further described.

As described above, the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention converts a camera image into a bird's-eye view image, extracts a comparison target area from the bird's-eye view image, The target image can be generated.

Specifically, the vehicle movement distance calculation apparatus 100 according to the embodiment of the present invention converts the camera image (ci ₅ ) at time t ₁ into a bird's-eye image (bi ₅ ) as shown in FIG. As described above, the example illustrated with reference to Figs. 8 and 9 assumes that the vehicle backs into a curved motion, so that the parking line pl ₅ included in the camera image ci ₅ has two curved lines . On the other hand, the parking line (bpl ₅ ) included in the bird's-eye image (bi ₅ ) may appear as a straight line in its original form.

Thereafter, the vehicle movement distance calculation apparatus 100 according to the embodiment of the present invention sets the comparison object area tr ₁ in the bird's-eye image bi ₅ . As described above, the comparison area tr ₁ represents an area set based on the image mapping information retrieved according to the detected steering angle value detected by the steering angle sensor (not shown). Further, as, compared to the region (tr ₁₎ shown in Figure 8 may have a shape of the case is set in the bird's eye view image, the ring segments. Specifically, the region to be compared tr ₁ can be set as a part of the area between two circles whose centers coincide and radii are different, as will be described later.

Thereafter, the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention can generate the comparison object image cti ₅ by scaling the comparison object area tr ₁ through the image mapping information. In other words, compared to the region (tr ₁₎ scaling, the image map information containing the coordinate information of the comparison-object region (tr ₁₎ in accordance with the detected steering angle value is used, the comparison-object image through the mapping process in the coordinate (cti of ₅ ) may be generated. Here, the comparison object image cti ₅ may have the form of a rectangle or a square for comparison with another comparison object image. As mentioned above, the generation of the comparison object image (cti ₅ ) is preferably performed using the GPU among various processing apparatuses for high-speed processing.

As described above, the movement distance calculation apparatus 100 according to an exemplary embodiment of the present invention extracts a comparison object area using previously stored image mapping information and generates a comparison object image, so that the calculation amount required for the process is minimized And it is possible to process the movement distance calculation at high speed or in real time. Of course, it is also possible to extract the comparison object area and generate the comparison object image without using the above-described image mapping information according to the setting of the user.

For example, when the comparison object image is generated without using the image mapping information, the movement distance calculation apparatus 100 according to the embodiment of the present invention includes the comparison region tr ₁ , And a coordinate calculation for the comparison object area tr ₁ can be performed based on the virtual grid line. Thereafter, it is also possible to generate the comparison object image by scaling the comparison object area tr ₁ on the basis of the coordinate calculation result.

However, each time the calculation is performed, overhead may be caused in the processing apparatus that repeatedly performs the above operations. Therefore, it is more preferable to generate the comparison target image using the generated image mapping information by performing the coordinate calculation process . In other words, the above-described calculation process is performed only when image mapping information is generated. In actual application, it is preferable to extract the comparison target area using the image mapping information generated in advance or to generate the comparison target image.

9 is a conceptual diagram illustrating a method for generating a camera image of the _second point in time t (ci ₆₎ based on the comparison in the region of t ₂ time (tr _2). Of t ₂ the time shown in Fig compare the region (tr ₂₎ a method of generating a way to generate a comparison target area (tr ₁₎ of the t ₁ point described with reference to Figure 8 and is identical, further description is It is omitted.

FIGS. 10A and 10B show an example of a comparison object region tr ₁ and a comparison object image cti ₅ at a time t ₁ , respectively, in which the dotted line block of FIG. 8 is expressed again. As mentioned above, when generating the comparison object image cti ₅ , the image mapping information searched based on the detected steering angle value can be used. Specifically, the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention extracts a comparison region tr ₁ at a time t ₁ based on the image mapping information searched and scales it. As described above, the generation of the comparison object image is preferably performed using the GPU among the various processing apparatuses for high-speed processing.

Here, the comparison area tr ₁ may have a ring segment shape, and may be defined as a part of the area between two circles whose centers coincide with each other and whose radii are different according to the detected steering angle values. Accordingly, the length of one side of the comparison target area tr ₁ may be shorter than the length of the other side as shown in FIG. 10A. Accordingly, the sizes of the planes formed through the virtual lattice lines formed in the comparison area tr ₁ may be different from each other.

Through this scaling process, a comparison object image cti ₅ is generated as shown in FIG. 10B. The comparative image cti ₅ may have a predefined resolution for comparison with the comparison image at another viewpoint. For example, the comparison object image cti ₅ preferably has a rectangular or square shape. In addition, when there is a linear component in the vertical direction in the object included in the bird's-eye view image of the comparison object region, distortion may occur in at least a part of the linear component of the object included in the comparison object image cti5. This is because, when there is a linear component in the comparison target area, the corresponding component is changed in the scaling process. However, in the case of the present invention, since only the y-axis direction distance calculation, that is, the vertical movement distance, can be calculated more precisely, even if distortion occurs in the straight line component in the vertical direction, There is no adverse effect on the calculation of the moving distance of the vehicle.

11A and 11B show an example of a comparison object region tr ₂ and a comparison object image cti ₆ at the time t _{2, which is a} representation of the dotted line block in FIG. 9, respectively. Here, the method of generating the comparison object image (cti ₆ ) at the time t ₂ is the same as the method of generating the comparison object image (cti ₅ ) described above with reference to FIGS. 10A and 10B, and further explanation will be omitted. The time t _{2 indicates the} time when the vehicle is moved backward by a certain distance in the direction of the curve as compared with the time t ₁ .

FIG. 12 is a conceptual diagram for explaining a method of calculating a moving distance of a vehicle through comparison between comparison images shown in FIG. 10B and FIG. 11B. Specifically, the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention calculates the distance between the objects to be compared based on the characteristics of extracting the comparison object area in consideration of the detected steering angle value, It is possible to calculate the moving distance based on only the moving distance.

In the case of the related art, the moving distance of the vehicle is calculated by calculating the coordinates between the minutiae points. Since the angle of the wheels of the vehicle is not considered, not only the calculation amount is high but also the calculation accuracy of the moving distance is low There was a problem. On the other hand, since the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention takes into consideration the detected steering angle values that can be provided in most vehicles, it is possible to accurately calculate the rotation angle of the vehicle can do.

In addition, when the moving distance of the vehicle is calculated by simply comparing the bird's-eye images of two view points, the moving distance should be calculated in consideration of both the x-axis, the y-axis, and the rotation angle. On the other hand, According to the vehicle movement distance calculation apparatus 100, since the rotation angle is already reflected in the comparison target area and the image, if the y-axis distance between the minutiae points, that is, the vertical movement distance between the minutiae points is calculated, can do.

Of course, such a movement distance calculation process is not limited to the calculation of the coordinates of the above-mentioned minutiae points, but also to the calculation of the correspondence degree of the objects included in the two comparison images, It is also possible to calculate the moving distance of the vehicle on the basis of the reference. For example, the calculated travel distance of the vehicle in accordance with one embodiment of the present invention device 100 may compare the destination image for t ₁ time (cti _5), the comparison target image in a coordinate distance by t ₂ time of the (cti ₆₎ The moving distance of the vehicle can be calculated. Of course, the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention may calculate the movement distance of the comparison object image cti ₆ at the time t ₂ by one coordinate distance in the direction of the comparison object image cti ₅ at the time t ₁ It is also possible to calculate the moving distance of the vehicle.

13 is a block diagram of a moving distance calculation apparatus 100 for a vehicle according to an embodiment of the present invention. As described above, the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention calculates the distance to be compared at each point of time based on the detected steering angle value obtained by the steering angle sensor 12 mounted on the vehicle And calculates the moving distance of the vehicle through matching of the comparison images of the two points of view considering the detected steering angle value. The moving distance calculation apparatus 100 for a vehicle according to an embodiment of the present invention includes a storage unit 110, an image acquisition unit 120, a coordinate calculation unit 130, a bird's-eye view image generation unit 140, A comparison object region extracting unit 160, a comparison object image generating unit 170, and a movement distance calculating unit 180. The information searching unit 150, the comparison object region extracting unit 160, In order to facilitate the understanding of the present invention, each of the components included in the vehicle movement distance calculation apparatus 100 according to the embodiment of the present invention is divided into functional components, and actually, a CPU, an MPU, a GPU, or an ECU And the like. Referring now to FIG. 13, a description will be given of an apparatus 100 for calculating a travel distance of a vehicle according to an embodiment of the present invention.

The storage unit 110 may store a camera image photographed through the camera 11. Also, the storage unit 110 may store image mapping information necessary for creating a bird's-eye image, and extracting a comparison object area and generating a comparison object image. As described above, the image mapping information may store different mapping information according to the detected steering angle value.

The image acquiring unit 120 acquires a camera image captured through the camera 11 mounted on the vehicle and stored in the storage unit 110.

The coordinate calculation unit 130 adds a virtual grid line to the camera image acquired through the image acquisition unit 120 and calculates the coordinates of each point in the camera image formed along the virtual grid line. The addition and coordinate calculation of the virtual lattice line through the coordinate calculation unit 130 are for generating the bird's-eye image described below.

The bird's-eye view image generating unit 140 functions to generate a bird's-eye view image by performing a viewpoint conversion of a camera image obtained through the image obtaining unit 120. For example, a bird's-eye image can be generated using perspective transformation. For example, a method of generating a bird's-eye image according to an embodiment of the present invention is a method in which position data of an image on the ground is projected onto a screen plane T having a focal length f from a position R of the camera Perspective transformation can be performed. However, the method of generating the bird's-eye view image may be applied to various methods other than the above-mentioned method, so that further explanation will be omitted. The bird's-eye image generated through the bird's-eye image generating unit 140 may be transmitted to the storage unit 110 and stored in the storage unit 110.

The mapping information searching unit 150 obtains the detected steering angle value from the steering angle sensor 12 and searches the storage unit 110 for the image mapping information corresponding to the obtained detected steering angle value. As described above, the storage unit 110 stores a plurality of image mapping information for extracting a comparison object area and used for generating a comparison object image. The image mapping information may be stored according to the detected steering angle value of the vehicle. Accordingly, the mapping information searching unit 150 can search the storage unit 110 for optimal image mapping information corresponding to the wheel angle of the current vehicle according to the detected steering angle value acquired through the steering angle sensor 12 have.

The comparison region extracting unit 160 receives the bird's-eye image from the storage unit 110 and extracts a comparison object region from the bird's-eye image based on the image mapping information retrieved from the mapping information search unit 150. For example, when the current time is t ₁ , the bird's-eye image generator 140 generates a bird's-eye image based on the camera image at time t ₁ . At this time, based on the image mapping information corresponding to the detected steering angle value at the time point t ₁ detected from the steering angle sensor 12, the comparison region extracting unit 160 extracts the comparison object region from the bird's-eye view image at the time t ₁ can do.

As described above, the comparison target area can be extracted not only from the bird's-eye view image but also from the camera image itself. Further, when the comparison object area is set in the bird's-eye image, it may have a ring segment shape. Here, the comparison target area is defined as a part of the area between two circles having different radii based on the rotation center point of the vehicle, according to the image mapping information classified based on the detected steering angle value detected from the steering angle sensor 12 . A description of how to generate the image mapping information used to set the comparison object area will be specifically described below with reference to FIG.

The comparison object image generation unit 170 generates a comparison object image based on the comparison object region extracted through the comparison object region extraction unit 160. [ As described above with reference to FIGS. 8 to 12, the comparison object image generating unit 170 may generate a comparison object image by performing scaling using image mapping information. As described above, the image mapping information may include scaling information for setting a virtual lattice line for the comparison target area, and the comparison target image generating unit 170 may perform scaling through image mapping information based on the virtual lattice line Can be performed. Of course, it is also possible to perform scaling through other schemes known outside of the virtual grid lines. Also, the process of generating a comparison object image through the scaling process is preferably performed through the GPU for high-speed processing among other processing devices.

Also, as described with reference to FIGS. 10 and 11, it is preferable that the comparison target image has a rectangular or square shape for comparison with other comparison target images. The generated comparison target image may be transferred to the storage unit 110 and stored. That is, the storage unit 110 stores the comparison image generated for each viewpoint.

The travel distance calculating unit 180 calculates the travel distance of the vehicle between the two points of view through the matching process of the images to be compared at the two points of view. Specifically, the movement distance calculating unit 180 compares the comparison image of the current time generated by the comparison image generating unit 170 with the comparison image of the previous time stored in the storage unit 110, The moving distance of the inter-vehicle can be calculated.

For example, when the current time is referred to as a first time point and the previous time point is referred to as a second time point, the movement distance calculation unit 180 may compare the first comparison image with the second comparison image, The moving distance of the vehicle can be calculated. That is, as described with reference to FIG. 12, the travel distance calculating unit 180 can calculate the travel distance of the vehicle by calculating the distance between the minutiae points of the objects included in each comparison target image.

In addition, since the comparison object image is generated through scaling of the comparison object area extracted in consideration of the detected steering angle value, the movement distance calculating unit 180 calculates only the y-axis distance of the object, that is, The moving distance of the vehicle can be calculated. This is because the comparison target area can be set based on the image mapping information that is classified according to the detected steering angle value.

On the other hand, in the related art, a method of calculating the moving distance of the vehicle through the calculation of the coordinates between the minutiae points in two images having different viewpoints has been adopted. In this case, since the conventional technique does not consider the wheel angle of the vehicle, the calculation amount is high, and the rotational angle of the vehicle can not be precisely grasped. On the other hand, in the case of the present invention, the movement distance calculating unit 180 calculates the vertical movement distance between objects in order to use the comparison object image generated according to the detected detection steering angle value in advance. Accordingly, the vehicle movement distance calculation apparatus 100 according to the embodiment of the present invention can calculate the movement distance of the vehicle with only a small amount of calculation compared with the prior art, and the calculation result is also higher than the conventional technology.

In addition to the calculation of the coordinates between the minutiae points described above, the movement distance calculating unit 180 may calculate the distance between the comparison target image at the first point of time and the reference image at the second point of time at one coordinate distance (for example, Or moving the comparison object image at the second viewpoint to the comparison object image at the first viewpoint and performing the matching process to calculate the travel distance.

Also in this case, the image matching process through the movement distance calculating unit 180 uses the detected steering angle value detected through the steering angle sensor 12, so that one comparison target image is compared with another comparison target The moving distance of the vehicle can be calculated while rotating the image by one coordinate distance. That is, the detection steering angle value is used in the matching process while moving one comparison target image, so that the amount of calculation required to calculate the moving distance of the vehicle can be significantly reduced.

When the travel distance of the vehicle between two view points is calculated through the travel distance calculating unit 180, the calculated travel distance can be stored in the storage unit 110. [ Accordingly, the moving distance calculation apparatus 100 for a vehicle according to an embodiment of the present invention can accurately calculate a moving distance between a plurality of bird's-eye images stored in the storage unit 110. [ Accordingly, at the time of combining the bird's-eye view images of the past viewpoints and the bird's-eye view image of the current viewpoint, which are made through the synthesized bird's-eye view image generating unit 20, the moving distance of the vehicle can be grasped accurately and a more accurate result can be calculated . The composite bird's-eye view image reflecting the vehicle distance between the points calculated through the vehicle movement distance calculation apparatus 100 according to the embodiment of the present invention is displayed through the display unit 30 and used for assisting the parking of the driver .

In other words, through the above-described configurations, the vehicle movement distance calculation apparatus 100 according to the embodiment of the present invention can not provide the distance detection signal among the vehicles, or can not provide the distance detection signal to the vehicles Can be applied. In addition, the apparatus 100 for calculating the moving distance of the vehicle according to an embodiment of the present invention grasps the moving direction of the vehicle through the steering angle detection value, and therefore, a method of calculating the moving value using only the image There is no error with respect to the rotation value, and in the image comparison process, not only the three-dimensional comparison considering the direction of rotation but also the one-dimensional comparison (since the present invention can know the direction of rotation of the vehicle in advance) .

14 is a conceptual diagram for explaining a method of generating comparison area creation information used for calculating a comparison area in image mapping information according to an embodiment of the present invention. A method of generating comparison area creation information according to an embodiment of the present invention will now be described with reference to FIG. In the following description, an explanation is made centering on an example of extracting a comparison object area from a bird's-eye view image of a vehicle. However, in order to facilitate the understanding of the present invention, a similar method can be applied to a comparison object area in a camera image captured through a camera of a vehicle rather than a bird's-eye image.

First, a ROI is set in the bird's-eye image. Here, the region of interest (ROI) may be defined as part of the rear area of the vehicle in the bird's-eye image. For example, the ROI may be defined as the regions within a predetermined distance from the vehicle in the rear area of the vehicle. Wherein the bird's-eye image may be any bird's-eye image that can be used to generate image mapping information.

Thereafter, a process of calculating the center turning radius Rc of the vehicle is performed. Here, the central turning radius Rc of the vehicle can be calculated on the basis of the wheel angle phi of the vehicle calculated using the detected steering angle value and the vertical distance between the first and second wheel axles of the vehicle . That is, the center turning radius Rc of the vehicle can be expressed by the following equation (1).

In Equation (1),? Represents the wheel angle of the vehicle, and L represents the vertical distance between the wheel axes of the vehicle.

Thereafter, a process of calculating the inside turning radius R1 of the vehicle and the outside turning radius R2 of the vehicle is performed. Here, the inside turning radius R1 of the vehicle and the outside turning radius R2 of the vehicle can be calculated in consideration of the center turning radius of the vehicle calculated through Equation (1) and the position of the wheels of the vehicle. The inside turning radius R1 of the vehicle can be calculated through the following equation (2), and the outside turning radius R2 of the vehicle can be calculated through the following equation (3).

In Equations (2) and (3), 1.0 represents a value set for illustration and represents a value that can be set in advance according to the model and size of the vehicle. In other words, the inside turning radius R1 of the vehicle and the outside turning radius R2 of the vehicle can be set based on the center turning radius of the vehicle and the distance between one side and the other side of the first wheel axle.

Thereafter, setting is made for the turning center point p of the vehicle. Here, the rotation center point p may be set at a point extending from one of the wheel axes of the vehicle and spaced apart from the center of the wheel axle by a center turning radius distance. Likewise, the turning center p is set at a point extending from one wheel axis and spaced apart from the inner turning wheel by an inner turning radius distance from the inner turning wheel, or at a position spaced by an outer turning radius distance from the inner turning wheel It is also possible. Here, the reference rotation axis is referred to as a first rotation axis.

The comparison target area tr can be defined as a part of the area between two circles having different radii with respect to the rotation center point p as shown in Fig. Here, the two circles having different radii represent circles formed according to the inside turning radius R1 and the outside turning radius R2 based on the rotation center point p.

In addition, the comparison area tr may be defined as an area between the first object area setting line and the second object area setting line in the area between the two circles having different radii. Here, the first object area setting line may be defined as a line connecting the reference center line connecting the rotation center point and the first wheel axis with the first area setting angle, and the second object area setting line may be defined by the reference line and the second area setting angle Can be defined as a line connecting Here, the first area setting angle and the second area setting angle can be expressed by the following equations (4) and (5), respectively.

In Equation (4), y1 represents the vertical distance between the lower side of the ROI and the reference line, and y2 represents the vertical distance between the upper side of the ROI and the reference line. That is, the first area setting angle? 1 can be calculated based on the vertical distance between the lower side of the ROI and the first wheel axis, and the center turning radius Rc, and the second area setting angle? Can be calculated based on the vertical distance between the upper side of the ROI and the first wheel axis, and the center turning radius Rc.

Further, when generating the image mapping information, the setting of the area to be compared is generated according to the inside turning radius R1 and the outside turning radius R2 of the vehicle through the above-described process in the area of interest (tr) In the area between the two circles, the area between the first object area setting line and the second object area setting line. Thus, the comparison area tr has the shape of a ring segment, and since the inside and outside turning radii of the vehicle are different from each other, the lengths of both sides may be different from each other. Of course, as described above, the comparison area tr may be formed differently depending on the detection steering angle value of the vehicle, that is, the shape of the comparison area tr may be different depending on the wheel angle of the vehicle.

The image mapping information according to the detected steering angle value can be generated through the above-described process. That is, the image mapping information may include information about an area formed according to the detected steering angle value through the above processes. Accordingly, the vehicle movement distance calculation apparatus 100 according to an embodiment of the present invention can extract, from the bird's-eye view image, an area corresponding to the coordinates, shape, and size of the area as a comparison object area based on the information .

In addition, the image mapping information may further include scaling information for coordinate calculation and scaling for the area. Of course, the scaling information can also store different information depending on the detected steering angle value.

15 is a block diagram of an apparatus 200 for calculating a travel distance of a vehicle according to another embodiment of the present invention. As described above, in the vehicle movement distance calculating apparatus of the present invention, the distance calculation is performed by extracting the comparison object region and the comparison object image from the bird's-eye view image described with reference to FIG. 13, It is also possible to generate a comparison object image based on the extracted comparison object area.

To this end, the vehicle travel distance calculation apparatus 200 according to another embodiment of the present invention includes structures similar to the vehicle travel distance calculation apparatus 100 according to the embodiment of the present invention described with reference to FIG. 13 And there may be some differences in the control process. As shown in FIG. 13, each of the configurations shown in FIG. 15 is configured to divide each of the components into functions in order to facilitate understanding of the present invention. In practice, one processing device such as a CPU, MPU, GPU, or ECU It is also possible to implement it through. Now, with reference to FIG. 15, description will be made mainly on configurations for performing other functions, except for those parts that perform the same functions as those of the embodiment of the present invention.

The comparison region extracting unit 260 extracts a region to be compared from the camera image obtained from the image obtaining unit 220. That is, the comparison region extracting unit 260 may extract the comparison region from the camera image itself, as opposed to setting the comparison region in the bird's-eye image in the embodiment of the present invention.

When the extraction of the comparison object area is completed, a process of adding a virtual lattice line to the comparison object area through the coordinate calculation unit 230 and performing coordinate calculation is performed.

Thereafter, the bird's-eye view image generating unit 240 may convert the comparison target region into a bird's-eye view image and transmit the converted bird's-eye view image to the storage unit 210 and the comparison object image generating unit 270. Here, the bird's-eye image generated through the bird's-eye view image generating unit 240 may be the same image as the comparison target image referred to with reference to FIG. 13 because it is the bird's-eye image for the comparison target area.

That is, the movement distance calculating unit 280 calculates the distance between the first viewpoint image at the first viewpoint and the bird's-eye view image at the second viewpoint, that is, the first comparison image at the first viewpoint and the second viewpoint image at the second viewpoint, The moving distance of the vehicle can be calculated by performing the matching process between the second comparison object images. Here, the process of calculating the travel distance of the vehicle through the travel distance calculating unit 280 has been described in detail above, and a further explanation will be omitted.

16 is a flowchart illustrating a method of calculating a travel distance of a vehicle according to an embodiment of the present invention. As described above, in the method of calculating the moving distance of the vehicle according to the embodiment of the present invention, the comparison target image at each point of view is extracted based on the detected steering angle value acquired by the steering angle sensor mounted on the vehicle, The moving distance of the vehicle is calculated through matching of the comparison images of the two points of view in consideration of the value of the distance. Now, with reference to FIG. 16, a description will be given of a method of calculating a moving distance of a vehicle according to an embodiment of the present invention.

Step S110 is a step of acquiring a camera image photographed by a camera mounted on the vehicle and stored in the storage unit, by the image acquisition unit. As described above, in the storage unit, camera images photographed through a camera can be stored, image mapping information necessary for generating a bird's-eye image described below, and comparison target area extraction and image comparison necessary for creating a comparison target image can be stored have. Here, the image mapping information may store different mapping information according to the detected steering angle value.

In step S120, the bird's-eye view image generating unit generates a bird's-eye view image by performing a viewpoint transformation on the camera image acquired in step S110. A step of adding a virtual grid line to the camera image through the coordinate calculation unit and performing coordinate calculation may be performed before the bird's-eye view image generation process through step S120. Here, although the step S120 may be performed through the perspective transformation, the bird's-eye images may be generated through various methods, so that further explanation will be omitted.

Step S130 is a step of obtaining, by the mapping information searching unit, the detected steering angle value detected from the steering angle sensor. In FIG. 16, step S130 is performed sequentially after step S110 and step S120. However, this step may be performed separately from steps S110 and S120, and may be repeatedly performed at each time point. Further, the detected steering angle value can be obtained by distinguishing the steering angle value with respect to the time of acquisition of each camera image.

In step S140, the mapping information searching unit searches the image mapping information corresponding to the detected steering angle value obtained in step S130. As described above, the image mapping information classified according to the detected steering angle value can be stored in the storage unit, and step S140 shows a process of searching for image mapping information corresponding to the detected steering angle value obtained in step S130 .

In step S150, the comparison object area extracting unit extracts a comparison object area according to the image mapping information retrieved through step S140 in the bird's-eye image generated in step S120. As mentioned above, the comparison region can be extracted as the shape of the ring segment in the bird's-eye image. As mentioned above, the area to be compared can be defined as a part of the area between two circles with different radii, based on the rotation center point in the bird's-eye image. 14, the area to be compared can be defined as the area between the first target area setting line and the second target area setting line with respect to the rotation center point in the area between the two circles having different radii have. The method of generating the image mapping information used for extracting the comparison object area will be described below with reference to FIG. 17, and a further explanation will be omitted.

Step S160 is a step of generating a comparison object image by scaling the comparison object area extracted in step S150. Here, the scaling may use the scaling information contained in the image mapping information. In other words, step S160 is a step of generating a comparison object image by scaling the comparison object area based on the image mapping information searched in step S140. It is preferable that the comparison target image generated through step S160 has a square or rectangular shape for comparison with other comparison target images.

Step S170 is a step of calculating the coordinate difference of the object included in the comparison target images between the two views by comparing the comparison images with respect to the two viewpoints. As described above, in step S170, it is possible to extract the same minutiae from the two comparison images and obtain the coordinate difference between minutiae. However, as mentioned above, since the comparison object image is generated in consideration of the detected steering angle value, the calculation of the coordinate difference can be performed by calculating only the y-axis distance, i.e., the vertical movement distance.

In step S170, the comparison target image at the first time point is moved to the comparison target image at the second time point, or the comparison target image at the second time point is moved by one coordinate distance to the comparison target image at the first time point It is also possible to perform.

As described above, the method of calculating the moving distance of the vehicle according to the embodiment of the present invention is able to move the image based on the obtained detected steering angle value since the detected steering angle value is obtained through step S130. Accordingly, image matching is performed while moving one comparison object image by one coordinate distance in consideration of the detection steering angle value as a comparison object image at another viewpoint, and a coordinate movement distance when the image matching rate is the highest is calculated can do.

Step S180 is a step of calculating the moving distance of the vehicle between the two time points based on the coordinate difference calculated through step S170. The calculated travel distance is stored in the storage unit and can be used to generate the composite bird's-eye image described above.

17 is a flowchart of a method of generating image mapping information according to an embodiment of the present invention. Specifically, FIG. 17 is a flowchart for explaining a method of generating comparison target area setting information among the image mapping information. Now, with reference to FIG. 17, a method of generating comparison area setting information according to an embodiment of the present invention is further described.

Step S210 is a step of setting a region of interest in the bird's-eye image. As described above, the ROI can be defined as part of the rear area of the vehicle within the bird's-eye image. For example, the ROI can be defined as the regions within the predetermined distance from the vehicle, and can be used for extracting the ROI as described below.

Step S220 is a step of calculating the center turning radius of the vehicle. Here, the center turning radius can be defined as the distance between the center of rotation and the center of the wheel axis of the vehicle. The step S220 may be defined as a step of calculating a center turning radius with respect to the detected steering angle value of the vehicle when the vehicle is curved in accordance with the detected steering angle value. Specifically, the central turning radius of the vehicle can be calculated based on the vertical distance between the first and second wheel axles of the vehicle and the wheel angle of the vehicle calculated using the detected steering angle value. Since the method of calculating the central turning radius of the vehicle through step S220 has been described in detail with reference to Equation 1, further description thereof will be omitted.

Step S230 is a step of calculating the inside turning radius and the outside turning radius of the vehicle. Here, the inner radius of rotation may be defined as the distance between the center of rotation and one side of the first wheel axis, and the outer radius of rotation may be defined as the distance between the center of rotation and the other side of the first wheel axis. Accordingly, the step S230 can be performed using the central turning radius of the vehicle calculated in the step S220. Specifically, in step S230, the inner turning radius may be calculated based on a predetermined variable according to the model or size of the vehicle at the center turning radius.

Step S240 is a step of setting the turning center point of the vehicle. Here, the center of rotation extends from one of the wheel axles of the vehicle (i.e., the first wheel axle) as described with reference to Fig. 14, and is located at a position spaced from the center of the wheel axle by a center turning radius Can be set. Likewise, the center of rotation extends from one wheel axis (i.e., the first wheel axis), at a point spaced by an inner turning radius distance from the inner turning wheel at the first wheel axis, or at an outer turning radius distance from the inner turning wheel It is also possible to set it at a separate point.

As described above, the comparison object area can be defined as a part of the area between two circles having different radii based on the rotation center point set in step S240. Here, the two circles represent circles formed according to the inner radius of rotation and the outer radius of rotation calculated through step S230 with respect to the center of rotation. Further, the area to be compared can be defined as the area between the first object area setting line and the second object area setting line described below in the area between the two circles having different radii. Now, a description will be given of a method of generating the first target area setting line and the second target area setting line.

Step S250 is a step of calculating the first area setting angle and the second area setting angle. In step S260, a first object area setting line is formed that forms a first area setting line and a reference line connecting the rotation center point and the wheel axis. In step S270, a second object area setting line And generating a line.

Here, the first area setting angle used to generate the first object area setting line can be calculated based on the vertical distance between the lower side of the ROI and the reference line, and the center turning radius of the vehicle (see Equation 4). The second area setting angle used to generate the second object area setting line can be calculated based on the vertical distance between the upper side of the ROI and the reference line and the center turning radius of the vehicle (see equation (5)). In this way, the first target area setting line and the second target area setting line can be calculated in consideration of the center turning radius of the vehicle and the ROI.

Step S280 is a step of extracting a region set in accordance with the inner and outer radius of rotation between the first object region setting line and the second object region setting line as a region to be compared and generating the region setting information to be compared. In other words, the comparison area can be generated in consideration of the curvilinear motion of the vehicle based on the detected steering angle value of the vehicle, and has the shape of the ring segment in the bird's-eye image.

18 is a flowchart illustrating a method of calculating a travel distance of a vehicle according to another embodiment of the present invention. As described above, the method of calculating the moving distance of the vehicle of the present invention is not limited to the method of extracting the comparison object area in the bird's-eye image, but may be performed by extracting the comparison object area from the camera image captured by the camera. Now, with reference to FIG. 18, a description will be given of a method of calculating a travel distance of a vehicle according to another embodiment of the present invention. In the following description, the overlapping portions of the method for calculating the moving distance of the vehicle according to the embodiment of the present invention described with reference to FIG. 16 will be omitted.

Step S310 is a step of acquiring a camera image, which is photographed by a camera mounted on the vehicle and stored in the storage unit, by the image acquisition unit.

Step S320 is a step of obtaining, by the mapping information searching unit, the detected steering angle value detected from the steering angle sensor. As described above, the acquisition of the detected steering angle value can be repeatedly performed at each acquisition time of the camera image.

In operation S330, the mapping information retrieving unit retrieves image mapping information corresponding to the detected steering angle value obtained in operation S320. As described above, the image mapping information classified according to the detected steering angle value may be stored in the storage unit, and in step S330, the image mapping information corresponding to the detected steering angle value acquired in step S320 may be retrieved have.

In step S340, the comparison object region extracting unit extracts the comparison object region from the camera image according to the image mapping information. Unlike the embodiment of the present invention, in step S340, the comparison object area may be extracted from the camera image itself instead of the bird's-eye view image. Here, when the comparison object region is extracted from the bird's-eye view image, the shape of the ring segment can be determined, but the shape of the camera image can be determined according to the image mapping information corresponding to the detected steering angle value.

In step S350, the comparison object image generation unit generates a comparison object image by scaling the comparison object area extracted in step S340. Specifically, in step S350, a comparison object image is generated by scaling a comparison object area using the image mapping information searched through step S330. As described above, the comparison target image can be used for calculating the moving distance of the vehicle through comparison of comparison images at different points in time, as described below. To this end, the image to be compared may be an image in the form of a rectangle or a square. In addition, it is preferable that the step S350 is performed through the GPU for high-speed processing.

Step S360 is a step of calculating the coordinate difference of the object included in the comparison target images between the two viewpoints by comparing the comparison images with respect to the two viewpoints. Specifically, the step S360 may be performed by extracting the feature points from the comparison image at the first time point and the comparison object image at the second time point, and calculating the coordinate difference between the feature points. Also, step S360 may be performed by considering only the y-axis distance, i.e., the vertical movement distance, not the x-axis, y-axis, and wheel angles. Since the above description has been described in detail above, further explanation is omitted.

In step S360, the comparison target image at the first time point is moved to the comparison target image at the second time point, or the comparison target image at the second time point is moved by one coordinate distance to the comparison target image at the first time point , And a method of calculating the coordinate difference is also possible.

Step S370 is a step of calculating the moving distance of the vehicle between the two viewpoints based on the coordinate difference calculated through step S360. The calculated travel distance is stored in the storage unit and can be used to generate the composite bird's-eye image described above.

As described above, the moving distance calculation method of the present invention can extract not only the bird's-eye view image but also the comparison target area from the camera image itself, and generate the comparison target image based on the extracted comparison target area. Therefore, in the method of calculating the moving distance of the vehicle of the present invention, the image required for calculation of the moving distance is not limited to a specific image.

As described above, an optimal embodiment has been disclosed in the drawings and specification. Although specific terms have been employed herein, they are used for purposes of illustration only and are not intended to limit the scope of the invention as defined in the claims or the claims. Therefore, those skilled in the art will appreciate that various modifications and equivalent embodiments are possible without departing from the scope of the present invention. Accordingly, the true scope of the present invention should be determined by the technical idea of the appended claims.

100: Vehicle travel distance calculating device
110: storage unit 120: image acquisition unit
130: coordinate calculation unit 140: bird's-eye view image generation unit
150: mapping information searching unit 160: comparison object area extracting unit
170: comparison object image generating unit 180: moving distance calculating unit

Claims (18)

An apparatus for calculating a moving distance of a vehicle, the apparatus being applied to a vehicle equipped with a camera and a steering angle sensor,
An image obtaining unit for obtaining a camera image photographed from the camera;
A mapping information searching unit for obtaining a detected steering angle value detected from the steering angle sensor and searching for image mapping information corresponding to the detected steering angle value in a storage unit;
A comparison region extracting unit for extracting a region to be compared in a plane image generated based on the camera image according to the image mapping information retrieved by the mapping information retrieving unit; And
And a comparison object image generation unit for generating a comparison object image by scaling the comparison object area based on the image mapping information,
Wherein the bird's-eye view image of the comparison area has a ring segment shape and the shape of the ring segment is changed according to the detected steering angle value. The method according to claim 1,
By calculating the coordinate difference of the object included in the first comparison object image at the first time and the second comparison object at the second time point that is earlier than the first time point generated through the comparison object image generating unit, And a movement distance calculation unit for calculating a movement distance of the vehicle between the first time point and the second time point. 3. The method of claim 2,
The moving distance calculating unit calculates,
And calculating a vertical movement distance between the object included in the first comparison object image and the object included in the second comparison object so as to calculate the movement distance of the vehicle between the first view point and the second view point. Distance calculating device. The method according to claim 1,
Wherein the comparison target area is a part of the area between the two circles having the same center and different radii. The method according to claim 1,
Further comprising a bird's-eye view image generating unit for generating a bird's-eye view image of the camera image by performing a viewpoint change of the camera image. 6. The method of claim 5,
Wherein the comparison region extracting unit extracts a region to be compared from the bird's-eye image of the camera image. The method according to claim 1,
Wherein distortion occurs in at least a part of a linear component in the longitudinal direction of the object included in the comparison object when a straight line component in the vertical direction exists in the object included in the bird's- Of the moving distance. The method according to claim 1,
Wherein the comparison object image generation unit scales the comparison object area into a rectangular shape using the image mapping information. The method according to claim 1,
Wherein the scaling of the comparison area is performed through a GPU. A method of calculating a travel distance of a vehicle, the method being applied to a vehicle equipped with a camera and a steering angle sensor,
Acquiring a camera image photographed by the image acquiring unit from the camera;
Obtaining a detected steering angle value detected from the steering angle sensor by a mapping information searching unit;
Retrieving image mapping information corresponding to the detected steering angle value in a storage unit by a mapping information searching unit;
Extracting a comparison object region from a plane image generated based on the camera image according to the searched image mapping information by a comparison object region extraction unit; And
Generating a comparison object image by scaling the comparison object area based on the image mapping information by the comparison object image generating unit,
Wherein the bird's-eye view image of the comparison area has a ring segment shape and the shape of the ring segment is changed according to the detected steering angle value. 11. The method of claim 10,
The movement distance calculating unit may calculate the movement distance of the object included in the first comparison image at the first time and the second comparison image at the second time that is earlier than the first time, And calculating a moving distance of the vehicle between the first point of time and the second point of time by calculating the moving distance of the vehicle. 12. The method of claim 11,
Wherein the step of calculating the moving distance of the vehicle between the first time point and the second time point comprises:
And calculating a vertical movement distance between the object included in the first comparison object image and the object included in the second comparison object image. 11. The method of claim 10,
Wherein the comparison target area is a part of the area between the two circles having the same center and different radii. 11. The method of claim 10,
Further comprising generating a bird's eye view image of the camera image by performing a viewpoint conversion of the camera image by the bird's-eye view image generating unit. 15. The method of claim 14,
Wherein the step of extracting the comparison object area comprises extracting a comparison object area from the bird's-eye image of the camera image. 11. The method of claim 10,
Wherein distortion occurs in at least a part of a linear component in the longitudinal direction of the object included in the comparison object when a straight line component in the vertical direction exists in the object included in the bird's- Of the moving distance. 11. The method of claim 10,
Wherein the step of generating the comparison object image scales the comparison object area into a rectangular shape using the image mapping information. 11. The method of claim 10,
Wherein the scaling of the comparison area is performed by a GPU in the step of generating the comparison object image.

Images