TW201439988A - Driving assistance device and method thereof - Google Patents

Abstract

The present invention discloses a driving assistance device and method thereof. The driving assistance includes a camera and a processing module. The camera disposed on the back-end of a vehicle picks up pictures of the surroundings of its back-end, so as to generate a surrounding image. The processing module reads the surrounding image, and selectively identify a driving image and back-up moving image of the vehicle according to forward or backward movements of the vehicle and control a display unit to display. By using the camera simultaneously picking up the driving image and back-up moving image of the vehicle, the amount of cameras disposed on the back-end of the vehicle can be reduced.

Description

Driving assistance device and method thereof

The present invention relates to a driving assistance device and a method thereof, and more particularly to a driving assistance device and a method thereof that can simultaneously capture a driving image of a rear end of a vehicle and a reverse image.

When a car is driving, unintended events are often caused by driver's carelessness, blind spots, or changes in the external environment. With the development of electronic technology, many researchers are developing the parking assistance system through the powerful computing power of the driving computer combined with the imaging technology, so that they can be alerted in advance and effectively assist the driver in the driving process. Parking assist systems (such as the common reversing radar system) mostly use ultrasonic sensors to sense the distance from the rear obstacles, and then distinguish the obstacles by the sound size or frequency. With the popularization of image sensors, some reversing radar systems also capture actual scene images for the driver to intuitively feel the spatial relationship between the vehicle and the surrounding obstacles. Drivers with more drastic driving skills can assist the driver in reversing through such parking assistance systems to avoid collisions with obstacles around the vehicle and protect the vehicle from collision damage.

Please refer to FIG. 1 , which is a schematic diagram of a lens assembly behind a vehicle of the prior art. As shown in the figure, since the reversing radar system is used to take an image of the rear of the vehicle 99 at the time of reversing, it is required to be installed at the position of the rear bumper 991. At the same time, in the process of driving, it is often necessary to take images of the rear of the vehicle, so a lens must also be installed at the rear windshield 992 to take an image of the road behind the vehicle while driving. In this way, at least two or more lenses must be installed behind the vehicle to fully present the environmental image of the rear end of the car.

In view of the above-described problems of the prior art, it is an object of the present invention to provide a driving assistance apparatus and method thereof for reducing the number of lens mounts in the prior art.

According to one aspect of the present invention, a driving assistance device is provided, including a lens and a processing module. The lens is placed at the rear of the vehicle to capture the environment behind the vehicle to produce an environmental image. The processing module reads the environmental image, and selectively distinguishes the driving image and the reverse image from the environmental image according to the driving state or the reverse state of the vehicle, and controls the display unit to display.

Preferably, the driving assistance device further comprises an image segmentation module and a determination module. The image segmentation module distinguishes the environment image into a first partial image and a second partial image, and the first partial image and the second partial image have overlapping feature regions. The determining module determines, according to the position of the feature area in the first partial image and the second partial image, that the first part of the image is a driving image, and the second part of the image is a reverse image.

Preferably, the driving assistance device further comprises a deformed image correcting module. When driving, the deformed image correcting module reads the first part of the image with radial distortion, and restores the first part of the image to the driving image according to the calibration parameter. When reversing, the deformed image correction module reads the second part of the image with the radial distortion, and restores the second part of the image to the reverse image according to the correction parameter.

Preferably, the processing module calculates the image deformation rate between the deformed image and the normal image according to the normal image and the deformed image of the normal image by the lens to obtain the correction parameter.

Preferably, the rear end of the vehicle may include a rear windshield portion and a rear cover portion, and the lens is used to capture an environmental image of the rear windshield portion and the rear cover portion when the processing module reads the environmental image. The environment image is selectively divided into a driving image facing the windshield portion of the vehicle or a reversing image of the hood portion facing the vehicle according to whether the vehicle is in a driving or reversing state.

According to another object of the present invention, a driving assistance method is provided, comprising: mounting a lens at a rear end of a vehicle and capturing an environment behind the vehicle to generate an environmental image; and reading the environmental image by using the processing module, and processing the mode The group selectively distinguishes the driving image and the reversing image from the environmental image according to the driving state or the reversing state of the vehicle, and controls the display unit to display.

Preferably, the driving assistance method further comprises: using an image segmentation module to distinguish the environment image as the first partial image and the second partial image, wherein the first partial image and the second partial image have overlapping feature regions; and the use of the prediction mode The group determines, according to the position of the feature area in the first part image and the second part image, that the first part image is a driving image, and the second part image is a reverse image.

Preferably, the driving assistance method is further included in the driving, using the deformed image correcting module to read the first part of the image with the radial distortion, and correcting the first part of the image according to the correction parameter to become the driving image; Reading a second portion of the image with a radial distortion and restoring the second portion of the image to a reverse image based on the calibration parameters.

Preferably, the processing module can use the normal image, and the deformed image of the normal image is taken by the lens, and the image deformation rate between the deformed image and the normal image is calculated to obtain the correction parameter.

Preferably, the rear end of the vehicle may include a rear windshield portion and a rear cover portion, and the lens is used to capture an environmental image of the rear windshield portion and the rear cover portion when the processing module reads the environmental image. The environment image is selectively divided into a driving image of the windshield facing the vehicle or a reversing image of the hood portion facing the vehicle according to whether the vehicle is in a driving or reversing state.

According to the invention, the driving assistance device and the method thereof can be equipped with an imaging lens capable of simultaneously capturing driving images and reversing images at the rear end of the vehicle, thereby reducing the number of rear lens settings of the vehicle.

110. . . Lens

99, 100, 200. . . vehicle

101, 992. . . Rear windshield

102. . . Rear cover

120. . . Processing module

130. . . Display unit

140. . . Image segmentation module

150. . . Judging module

160. . . Image correction module

201. . . Rear hatchback

991. . . Rear bumper

A. . . Environmental image

A1. . . First part image

A2. . . Part II image

B1. . . Driving image

B2. . . Reverse image

S. . . Characteristic area

P1, P2. . . Reference point

S11-S12, S121-S123. . . Step flow

Figure 1 is a schematic view of a lens arrangement behind a vehicle of the prior art.
Figure 2 is a first schematic view of the driving assistance device of the present invention.
Figure 3A is a schematic diagram of an environmental image taken by the lens of the present invention.
Figure 3B is a schematic diagram of the corrected environmental image of the present invention.
Figure 4 is a block diagram of the system of the driving aid of the present invention.
Fig. 5 is a schematic view showing the lens mounting of the driving assistance device according to another embodiment of the present invention.
Figure 6 is a flow chart of a driving assistance method according to an embodiment of the present invention.
Figure 7 is a flow chart showing the operation of a processing module according to an embodiment of the present invention.

Please refer to FIG. 2, FIG. 3A, FIG. 3B and FIG. 4, FIG. 2 is a schematic diagram of the driving assistance device of the present invention, and FIG. 3A is a schematic diagram of an environmental image taken by the lens of the present invention. 3B is a schematic diagram of the corrected environmental image of the present invention, and FIG. 4 is a system block diagram of the driving assistance device of the present invention.

As shown, the driving assistance device includes a lens 110 and a processing module 120. The lens 110 is mounted at the rear end of the vehicle 100 to capture the environment behind the vehicle 100 and generate an environmental image A. The processing module 120 selectively distinguishes the environmental image A from the driving image and the reversing image according to the state in which the vehicle 100 is in the driving state or the state of reversing, and controls the display unit 130 to perform display.

It should be noted that the lens 110 of the embodiment is a fisheye lens, but is not limited thereto. In other embodiments of the invention, lens 110 can be other types of wide-angle lenses.

In this way, since the angle of view of the fisheye lens is almost 180 degrees, the environmental image A behind the car can be completely captured. Therefore, the environmental image A of the embodiment can further distinguish the driving image B1 and the reversing image B2. More specifically, the driving image B1 is an image of the rear of the vehicle displayed by the driving recorder on the market when the vehicle 100 is moving forward, and the driving image B1 is roughly the environmental image A that the windshield portion 101 faces after the vehicle. The reversing image B2 is an environmental image A that the hood portion 102 faces after the rear end of the vehicle 100 is used to assist the driver in reversing the vehicle.

In this embodiment, since the lens 110 is a wide-angle lens, the vehicle 100 only needs to install a lens at the rear end of the car, which can replace the function of the rear driving recorder lens and the parking sensor to simplify the function. The effect of the lens setting.

Since the lens 110 of the present embodiment is a fisheye lens, the captured environmental image A is a radially distorted scene image, as shown in FIG. 3A. In this embodiment, a series of image processing methods can be used to restore the radially distorted scene image in FIG. 3A to the normal environmental image in FIG. 3B, and distinguish the upper part of the environmental image A on the third road as the driving image. B1, the lower part is the reversing image B2. The image processing method of this embodiment will be described in detail below.

First, the embodiment further includes an image segmentation module 140, a determination module 150, and an image correction module 160. The image segmentation module 140 can distinguish the environment image A from the first partial image A1 and the second partial image A2. The first partial image A1 and the second partial image A2 have feature regions S overlapping each other.

The determining module 150 is electrically connected to the image dividing module 140. The determining module 150 of the embodiment can determine the first partial image A1 and the second portion according to the position of the feature region S in the first partial image A1 and the second partial image A2. The image A2 belongs to the driving image B1 or to the reverse image B2, respectively.

In more detail, the position of the feature area S of the embodiment is located below the first partial image A1, and the determination module 150 can determine that the first part of the image A1 should belong to the driving image B1. Similarly, since the location of the feature area S is located above the second partial image A2, the determination module 150 can determine that the second partial image A2 should belong to the reverse image, but the invention is not limited thereto. In other embodiments of the present invention, the location of the feature area S may be above the first partial image A1. At this time, the determination module 150 may determine that the first part of the image should be a reverse image.

The distortion correction module 160 is electrically connected between the determination module 150 and the processing module 120 for correcting the first partial image A1 or the second partial image A2 of the radiation distortion. In more detail, the determining module 150 can correct the first partial image A1 or the second partial image A2 according to a calibration parameter.

For example, when the vehicle 100 is traveling, the deformed image correcting module 150 of the embodiment can read the first partial image A1 with a radial distortion, and restore the first partial image A1 to the normal driving image B1 according to the calibration parameter. Similarly, when reversing, the deformed image correcting module 15 can read the second partial image A2 with the radial distortion, and restore the second partial image A2 to the normal reverse image B2 according to the correction parameter.

The correction parameter may be processed by the processing module 120 according to a normal image, and the deformed image of the normal image is taken by the lens 110, and the image deformation rate between the deformed image and the normal image is calculated to obtain the correction parameter.

For example, FIG. 3A is a schematic diagram of an environmental image captured by a lens according to an embodiment of the present invention. Among them, the characteristics of the scene taken by the fisheye lens are that the pixel pitch of the central area is small, and the farther away from the central area, the larger the pixel pitch. The overall image perception is like the center point of the image, which is radially distorted around the image. Figure 3B is a schematic diagram of the corrected environmental image of the present invention. Taking the corrected normal image in FIG. 3B as an example, the image deformation rate can refer to the two reference points P1 and P2 in FIG. 3B and the positions of the two reference points P1 and P2 in FIG. 3A, and the third AA can be known. In the figure, the image deformation rate of the radiation-distorted environmental image is obtained, and the correction parameters are obtained.

It should be noted that the calibration parameters of the driving assistance device of the present invention can be set before the driving assistance device is shipped from the factory, and the setting manner is not limited to the manner of calculating the image deformation rate. In other embodiments of the present invention, parameters such as the radius of curvature of the fisheye lens itself may be calculated, and the image deformation rate of the image taken by the fisheye lens may be pushed back.

It is worth mentioning that, in this embodiment, the number of lenses 110 required to be installed at the rear end of the vehicle 100 can be substantially reduced by simultaneously capturing the reversing image and the lens 110 of the driving image. The lens 110 of the present embodiment is a wide-angle lens, such as a fisheye lens, and the lens thereof can be installed on the hood portion 102 after the rear end of the vehicle 100 as shown in FIG. 2, but not limited thereto. Please refer to FIG. 5, which is a schematic diagram of a lens assembly of a driving assistance device according to another embodiment of the present invention. As shown in the figure, the vehicle 200 of the present embodiment is a recreational vehicle, and the rear end thereof includes a rear hatchback door 201, and the lens 110 is mounted on the rear hatchback door 201 to simultaneously capture the driving image and the reversing image.

Next, please refer to FIG. 6, which is a flowchart of a driving assistance method according to an embodiment of the present invention. As shown in the figure, first, in step S11, the lens is mounted on the rear end of the vehicle, and the environment behind the vehicle is captured to generate an environmental image.

Then, in step S12: the environment image is read by the processing module, and the processing module selectively distinguishes the driving image and the reversing image from the environmental image according to the driving state or the reverse state of the vehicle, and controls the display unit to display.

Please refer to FIG. 7, which is a flow chart of the operation of the processing module according to an embodiment of the present invention. In the step S12, the method further includes the step S121: the image segmentation module is used to distinguish the environment image into the first partial image and the second partial image, and the first partial image and the second partial image have overlapping feature regions.

Then, in step S122, the determining module determines, according to the position of the feature area in the first partial image and the second partial image, that the first partial image is a driving image, and the second partial image is a reverse image.

Then, when driving, in step S123, the first partial image with the radial distortion is read by the deformed image correcting module, and the first partial image is corrected according to the correction parameter to become the driving image. When reversing, in step S124, the second partial image with the radial distortion is read by the deformed image correcting module, and the second partial image is restored to the reverse image according to the calibration parameter.

In summary, the present invention can reduce the number of lens installations at the rear end of the vehicle by installing a reversing image required for reversing at the rear of the vehicle and a lens for traveling images of the vehicle required for driving. In other words, the driving assistance system and method of the present invention do not need to separately provide a driving record lens and a reversing image lens in the rear windshield and the rear bumper of the vehicle, so that the number of lens mounts can be reduced by the present invention.

The above is intended to be illustrative only and not limiting. Any equivalent modifications or alterations to the spirit and scope of the invention are intended to be included in the scope of the appended claims.

100. . . vehicle

101. . . Rear windshield

102. . . Rear cover

110. . . Lens

Claims (10)

A driving assistance device comprising: a lens mounted at a rear end of a vehicle, capturing an environment behind the vehicle to generate an environmental image; and a processing module for reading the environmental image, the processing module The group selectively distinguishes a line of vehicle images and a reversing image from the environmental image according to the driving state or the reversing state of the vehicle, and controls a display unit to display. The driving assistance device of claim 1, further comprising: an image segmentation module, wherein the environment image is a first partial image and a second partial image, the first partial image and the second partial image And a determining module, wherein the first part of the image is the driving image according to the position of the characteristic area in the first partial image and the second partial image, and the second partial image is The reversing image. The driving assistance device according to claim 2, further comprising a deformation image correction module, wherein when the vehicle is driving, the deformation image correction module reads the first partial image with a radial distortion, and according to a calibration parameter The first partial image is restored to the driving image, and when the vehicle is reversed, the deformed image correcting module reads the second partial image with the radial distortion, and restores the second partial image to the reverse image according to the calibration parameter. . The driving assistance device of claim 3, wherein the processing module calculates a deformation image between the deformed image and the normal image according to a normal image and a lens that is imaged relative to the normal image. Image deformation rate to obtain the correction parameters. The driving assistance device according to claim 1, wherein the rear end of the vehicle includes a rear windshield portion and a rear hood portion, and the lens captures the rear windshield portion and the rear hood portion The environmental image that is faced by the processing module, when the processing module reads the environmental image, selectively distinguishes the environmental image as the rear windshield facing the vehicle according to whether the vehicle is in a driving or reversing state One of the driving images or a reversing image of the rear cover of the vehicle. A driving assistance method comprising: installing a lens at a rear end of a vehicle and capturing an environment behind the vehicle to generate an environmental image; and reading the environmental image by using a processing module, the processing module is configured according to The driving state or the reversing state of the vehicle selectively distinguishes a line of vehicle images and a reversing image from the environmental image, and controls a display unit to display. The driving assistance method of claim 6, further comprising: using an image segmentation module to distinguish the environment image as a first partial image and a second partial image, wherein the first partial image and the second partial image have And a plurality of feature areas overlapping each other; and determining, by the determining module, the first part of the image as the driving image according to the position of the characteristic area in the first partial image and the second partial image, wherein the second partial image is the reverse image image. The driving assistance method according to claim 7 is further included in the driving, wherein the first image of the radial distortion is read by using a deformed image correcting module, and the first partial image is performed according to a calibration parameter. Correcting to become the driving image; when reversing, reading the second partial image with radial distortion, and restoring the second partial image to the reverse image according to the correction parameter. The driving assistance method of claim 8, wherein the processing module utilizes a normal image, and the lens detects a deformed image relative to the normal image, and calculates a difference between the deformed image and the normal image. Image deformation rate to obtain the correction parameters. The driving assistance method according to claim 6, wherein the rear end of the vehicle includes a rear windshield portion and a rear hood portion, and the lens captures the rear windshield portion and the rear hood portion When the processing module reads the environmental image, the environmental image is selectively divided into one face of the windshield facing the vehicle according to whether the vehicle is in a driving or reversing state. A car image or a reversing image of one of the hoods facing the vehicle.