KR101927754B1 - Method and apparatus for providing around view image using front camera and rear camera - Google Patents

Abstract

A method and apparatus are provided for providing an overview image. The method for providing the surround view image according to an embodiment of the present invention includes the steps of (a) receiving an Around View Monitoring (AVM) request, Generating a first transformed image obtained by performing planarization on an image obtained from a first camera and a second camera from a first point; (b) integrating and displaying the first converted image on the screen for each of the front camera and the rear camera; (c) generating a second converted image obtained by performing plane conversion on an image obtained from the front camera and the rear camera from a second point, which is a position of the vehicle where the steering angle is changed, when the steering angle of the vehicle is changed; And (d) combining the second converted image with the first converted image and displaying the combined image on the screen.

Description

TECHNICAL FIELD The present invention relates to a method and apparatus for generating an overview image using a front camera and a rear camera,

BACKGROUND OF THE INVENTION 1. Field of the Invention [0002] The present invention relates to a method and apparatus for generating an overview image, and more particularly, to a technique for generating an overview image using a front camera and a rear camera.

With the development of automotive technology, various technologies have been provided to assist driver's parking. Among them, Around View Monotoring (AVM) system uses four high-definition cameras mounted on the front, rear, left, and right sides of the vehicle to make it easier to recognize the driver's space. .

This AVM system is very popular with drivers who are difficult to park because they can easily park and travel even in a tight space. In the past, it was installed as an option in luxury cars, but recently it can be easily installed in aftermarket. And it is gradually becoming popularized.

However, in order to implement the AVM system, four high-definition cameras are required, and thus the cost of the AVM system is a great burden on the consumers. Therefore, it is required to implement AVM system at a lower cost.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a method for implementing an AVM system using a front camera and a rear camera without using all four cameras as in the prior art.

According to an aspect of the present invention, there is provided a method of generating an overview image by an apparatus for generating an overview image, the method comprising the steps of: (a) receiving an Around View Monitoring (AVM) Generating a first transformed image obtained by plane-transforming an image obtained from a forward camera and a backward camera from a first point, which is a vehicle position at a time when an AVM request is input; (b) integrating and displaying the first converted image on the screen for each of the front camera and the rear camera; (c) generating a second converted image obtained by performing plane conversion on an image obtained from the front camera and the rear camera from a second point, which is a position of the vehicle where the steering angle is changed, when the steering angle of the vehicle is changed; And (d) combining the second converted image with the first converted image and displaying the combined image on the screen.

In order to achieve the above object, an apparatus for generating an ambient view image according to an embodiment of the present invention, when an Around View Monitoring (AVM) request is input, A first conversion image obtained by performing plane conversion on an image obtained from a front camera and a rear camera from a first point is generated, and when the steering angle of the vehicle is changed, A planar image converter for generating a second transformed image obtained by performing planar transformation on an image obtained from the rear camera; And an image integrating unit for integrating the first converted image for each of the front camera and the rear camera and displaying the combined image on the screen by integrating the second converted image with the first converted image .

According to the embodiment of the present invention, since the AVM system can be implemented using the front camera and the rear camera without using all the four cameras as in the conventional art, it can contribute to the cost reduction in mounting the AVM system .

In addition, the AVM system can be installed at a low cost, thereby contributing to prevention of accidents occurring during parking.

It should be understood that the effects of the present invention are not limited to the above effects and include all effects that can be deduced from the detailed description of the present invention or the configuration of the invention described in the claims.

1 is a block diagram of an apparatus for generating an overview image according to an embodiment of the present invention.
FIGS. 2A to 2D illustrate an image integration method for generating an overview image according to an exemplary embodiment of the present invention. Referring to FIG.
3 is a flowchart illustrating a process of generating an overview image according to an exemplary embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described with reference to the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.

In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Throughout the specification, when a part is referred to as being "connected" to another part, it includes not only "directly connected" but also "indirectly connected" .

Also, when an element is referred to as "comprising ", it means that it can include other elements, not excluding other elements unless specifically stated otherwise.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

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

An apparatus for generating an overview image 100 according to an exemplary embodiment of the present invention includes a front image input unit 110, a rear image input unit 120, a planar image conversion unit 130, an image integration unit 140, a control unit 150, And a storage unit 160.

The present invention provides an approach view image using two front cameras and two rear cameras without using four cameras in front, back, left, and right in order to provide an overview image.

The front image input unit 110 may be connected to the front camera so as to receive a front image captured by the front camera. The rear image input unit 120 may be connected to the rear camera, Can be input.

For reference, the front camera and the rear camera can start shooting when an Around View Monitoring (AVM) request is input, and the AVM request can be started by using a touch screen display device for providing an AVM, Can be requested.

Meanwhile, the planar image converting unit 130 may perform planar conversion on each of the images input to the front image input unit 110 and the rear image input unit 120. Since an image captured by a front camera and a rear camera is an image having a perspective, it is necessary to convert an image having a perspective to a plane image in order to provide an image that looks like a vehicle at a high place. The planar image transform unit 130 may use an inverse perspective method as an embodiment of planar transformation, and the driver can intuitively perceive the surrounding situation through the transformed planar image.

In addition, the planar image conversion unit 130 converts the perspective image captured by the front camera and the rear camera into a plane image and stores the distance to a surrounding object appearing in the image, such as a pillar, a boundary, The distance traveled by the vehicle, the steering angle of the steering wheel, and the like at a vehicle position (hereinafter, referred to as 'first point') when the AVM request is inputted.

To this end, the planar image conversion unit 130 includes a distance sensor for sensing the distance between the vehicle and surrounding objects or the distance traveled by the vehicle, a position sensor such as a GPS for sensing the position of the vehicle, And a steering angle sensor for sensing the steering angle of the vehicle.

In one embodiment, the planar image transforming unit 130 performs planar transformation on the images obtained from the first camera and the rear camera from the first point at predetermined time intervals, and calculates a steering angle of the steering wheel, , The moving distance from the first point, and the like.

When the steering angle of the vehicle is changed, the image plane conversion unit 130 converts the image obtained from the front camera and the rear camera from the position of the vehicle at which the steering angle is changed (hereinafter referred to as the 'second point' The steering angle of the steering wheel, the position of the vehicle, the travel distance from the second point, and the like may be reflected and stored for each converted image.

For reference, only the second point is referred to as the point at which the steering angle is changed, but this does not mean that the steering angle is changed only once at the first point, but extends to all the positions of the vehicle at which the steering angle changes during parking . That is, the second point is a third point, a fourth point ... An Nth point, and the like.

As described above, the planar image conversion unit 130 reflects and stores the sensing information received from the sensors on the converted planar image, so that the image integration unit 140, which will be described later, That is, the surround view image.

On the other hand, the image integrating unit 140 may integrate the planar image converted by the planar image converting unit 130 for each of the front camera and the rear camera, and display the planar image on the screen. Here, the image integration unit 140 may integrate the plane images based on the steering angle of the steering wheel, the position of the vehicle, and the movement distance included in the plane image.

Hereinafter, an image integrating method of an image integrating unit for generating an surround view image will be described with reference to FIGS. 2A to 2D. For reference, the driver finds a space to be parked and inputs an AVM request through a screen of the display device, and the overall moving path of the vehicle is shown in FIG.

2B, from the first point where the driver finds the parking space and inputs the AVM request to the second point at which the steering angle is changed, the image integrating unit 140 converts the plane image converted from the planar image transform unit 130 (Hereinafter referred to as " first converted image ") can be integrated for each of the front camera and the rear camera.

Here, since the steering wheel of the vehicle is not steered, the image integrating unit 140 moves in the forward direction at the first point, so that the planar image can be integrated at a predetermined time interval without rotating the planar image.

2C, when the steering wheel of the vehicle is steered at the second point, the vehicle moves according to the steering angle of the steering wheel, and the planar image conversion unit 130 converts the front image and the rear image of the moving vehicle To a plane image (hereinafter, referred to as 'second converted image'). The image integration unit 140 may integrate the second converted images converted by the planar image conversion unit 130 for each of the front camera and the rear camera.

In this case, the image integrating unit 140 may integrate with the first transformed image having a region overlapping the region corresponding to the second transformed image or an area adjacent to the region corresponding to the second transformed image, The steering wheel of the vehicle is rotated by the steering angle and integrated with the first converted image. For reference, the rotation reference may be the central axis of the first transformed image.

If the steering angle of the steering wheel is changed later, the third converted image may be rotated by the steering angle with respect to the central axis of the second converted image and may be integrated with the second converted image, have.

Here, if the first converted image integrated with the second converted image is included in the range of the surrounding view image generated around the vehicle, it can be determined that the first converted image is adjacent to the first converted image.

Referring to FIG. 2d, when the range of the surround view image is 3m and the range is 3m, the converted image captured within 3m of the first converted image, It is determined that the second transformed image is adjacent to the second transformed image, and can be displayed on the screen as one image as shown in FIG. 2D. At this time, alpha blending is applied to integrate the images to smoothly process the empty space existing between the merged images.

In this way, an entire view image can be generated by integrating the images captured by the front camera and the rear camera every time the vehicle moves. That is, although the complete surround view image is not generated at first, the surround view image can be completed using the image captured while the vehicle is moving for parking.

For reference, as the angle of view between the front camera and the rear camera is wider, at least the moving view of the vehicle can be easily generated.

The control unit 150 may include elements of the apparatus for generating an overview image 100 such as a front image input unit 110, a rear image input unit 120, a planar image conversion unit 130, and an image integration unit 140 Can perform the above-described operation, and the storage unit 160 can also be controlled.

Meanwhile, the storage unit 160 may store various data required or derived in the control process according to the algorithm and the algorithm for allowing the controller 150 to control the components of the surround view image generating apparatus 100.

3 is a flowchart illustrating a process of generating an overview image according to an exemplary embodiment of the present invention.

The process of FIG. 3 can be performed by the surround view image generating apparatus 100, and the driver finds a space to be parked and inputs an AVM request through the screen of the display device.

The surround view image generating apparatus 100 generates a first converted image obtained by performing plane conversion on an image obtained from the front camera and the rear camera from the first position, which is the vehicle position at the time when the AVM request is input (S301).

Here, the surround view image generating apparatus 100 may use an inverse-perspective transform technique as an embodiment of the plane transform, and may generate a first transformed image and calculate a distance between the vehicle and surrounding objects appearing in the image, A distance detection sensor for detecting the distance, a position detection sensor such as a GPS for detecting the position of the vehicle, and a steering angle detection sensor for detecting the steering angle of the steering wheel.

After step S301, the surround view image generating apparatus 100 integrates the first converted image for each of the front camera and the rear camera and displays the first converted image on the screen (S302).

After step S302, the surround view image generating apparatus 100, when the steering angle of the vehicle is changed, converts the image obtained from the front camera and the rear camera from the second point, which is the position of the vehicle, (S303).

Here, the surround view image generating apparatus 100 may use an inverse-perspective transformation technique as an embodiment of the plane transformation in the same manner as in step S301. When generating the second transformed image, the distance estimation sensor, the position detection sensor, Sensing information received from a sensor or the like.

After step S303, the surround view image generating apparatus 100 displays an image obtained by rotating the second transformed image by the steering angle of the vehicle, integrating the transformed image with the first transformed image, and applying alpha blending to the screen (S304).

Here, the first transformed image integrated with the second transformed image is an image having a region overlapping the region corresponding to the second transformed image or an area adjacent to the region corresponding to the second transformed image.

After that, the surround view image generating apparatus 100 may repeat steps S302 to S304 until parking of the vehicle is completed. For reference, the first transformed image of S302 in the repeated process means the transformed image before the steering angle is changed.

After the step S304, the surround view image generating apparatus 100 deletes the surround view images generated by integrating the transformed images and the transformed images stored in the above-described procedure, when parking of the vehicle is completed (S305).

Here, the surround-view image generating apparatus 100 may delete the images immediately or may store the images for a predetermined time and delete the images when the time is exceeded. Of course, the erase time may vary depending on the driver's settings. Whether or not the parking of the vehicle is completed can be judged as completion of parking when the gear mode is located at the parking P or when the driver inputs the end of the AVM through the display device.

As described above, the present invention can implement an AVM system using a front camera and a rear camera without using all four cameras, and it is possible to reduce the number of cameras required to implement the surround view image, It is possible to reduce the cost of mounting the AVM system, thereby contributing to popularization of the AVM system and prevention of accidents occurring during parking.

The above-described technical features may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium.

The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination.

The program instructions recorded on the medium may be those specially designed and constructed for the embodiments or may be available to those skilled in the art of computer software.

Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like.

Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like.

The hardware device may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be.

It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive.

For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included within the scope of the present invention.

100: Around view image generating device
110: Front image input unit
120: rear image input unit
130:
140:
150:
160:

Claims (9)

A method of generating an overview image, the apparatus comprising: a front image input unit, a rear image input unit, a planar image conversion unit, an image integration unit, a control unit, and a storage unit,
When an Around View Monitoring (AVM) request is input, the image obtained from the front camera and the rear camera from the first point, which is the vehicle position at the time of input of the AVM request, And the distance to the surrounding object appearing in the obtained image is reflected on the sensing information of the distance sensor installed in the vehicle, and the sensing information inputted from the position sensor and the steering angle sensor installed in the vehicle are reflected, Generating a first transformed image;
Integrating the first converted image for each of the front camera and the rear camera and displaying the first converted image on a screen;
When the steering angle of the vehicle is changed, an image obtained from the front camera and the rear camera from a second point, which is the position of the vehicle at which the steering angle is changed, is applied to the planar image transform unit A distance sensor for sensing a distance between the vehicle and a surrounding object appearing in the obtained image, a sensing sensor installed in the vehicle, and a second conversion that reflects the sensed information input from the steering angle sensor, Generating an image; And
Rotating the second transformed image by the modified steering angle with the center axis of the first transformed image as a rotation reference to display the second transformed image on the screen by integrating the second transformed image with the first transformed image; And generating an overhead view image.
The method according to claim 1,
And integrating the first transformed image and integrating the second transformed image with the first transformed image, alpha blending is applied to the first transformed image to display the image on the screen. delete delete delete delete delete delete delete

Images