WO2018124388A1

WO2018124388A1 - Method and apparatus for notifying object around vehicle

Info

Publication number: WO2018124388A1
Application number: PCT/KR2017/002362
Authority: WO
Inventors: 엄정흠
Original assignee: 주식회사 캠시스
Priority date: 2016-12-29
Filing date: 2017-03-06
Publication date: 2018-07-05
Also published as: KR20180078361A

Abstract

The present invention relates to a method for notifying an object around a vehicle, the method comprising the steps of: detecting an object around a moving vehicle by using an image acquired from a camera; determining whether a lane image is abnormal by analyzing the image acquired from a direction for which an object does not exist as a result of the detection; and notifying, to a driver of the moving vehicle, the presence of the object around the moving vehicle when a part of the lane image is not present as a result of the determination, thereby greatly reducing an occurrence of vehicle accidents by enabling the driver to recognize, in advance, a risk of accident according to a lane change.

Description

Method and device for notification of objects around vehicles

The present invention relates to a method for notifying objects around vehicles, and more particularly, when a vehicle without headlights turned on near a driving vehicle but is not detected by a camera of the driving vehicle, lane shapes are analyzed by analyzing lane information within a certain distance. The present invention relates to a method and apparatus for notifying a vehicle around an object that can notify a driver that a vehicle or an object is nearby to greatly reduce the occurrence of a vehicle accident.

The AVM (Around View Monitoring) system is a system that acquires images of surrounding vehicles with front / rear and left / right cameras, and enables the driver to recognize objects in each direction. The AVM system shows the driver the vehicle around them, helping them to prevent accidents.

However, the conventional AVM system has a difficulty in recognizing a headlight failure vehicle or a vehicle that does not turn on the headlight at night in a low light situation. In addition, the conventional AVM system was unable to recognize an object located in a relatively dark area at low light, and if the object is present but not recognized by the AVM camera, the user cannot be warned in advance about the possibility of an accident. There was a problem.

Therefore, the first problem to be solved by the present invention is when the vehicle is not turned on the headlights, the vehicle around the object that can significantly reduce the occurrence of a vehicle accident can be recognized by the driver in advance the risk of accidents due to lane change To provide a way.

The second problem to be solved by the present invention is to provide a vehicle around the object notification method that can improve the function of the existing AVM product because it can recognize a vehicle, a moving object, or a person even in low light.

The third problem to be solved by the present invention is to provide an object notification method around the vehicle capable of producing a low-cost product to increase the object recognition using only the camera even in low light.

Further, the present invention provides a computer-readable recording medium having recorded thereon a program for executing the above method on a computer.

In order to solve the technical problem, by using the image obtained from the camera to detect the surrounding objects of the vehicle driving, by analyzing the image obtained from the direction in which no object as a result of determining the abnormality of the lane image, the lane image If there is no part of the present invention provides a method for notifying objects around the vehicle informing the driver that there is an object around.

According to the present invention, when there is a vehicle that does not turn on the headlights, the driver can recognize the risk of an accident due to a lane change in advance, thereby greatly reducing the occurrence of a vehicle accident. In addition, according to the present invention, a vehicle, a moving object, or a person can be recognized even at low light, thereby improving the function of an existing AVM product. Furthermore, according to the present invention, it is possible to recognize an object at low light at a relatively low cost than using a radar or an infrared signal, and to produce a low-cost product that raises object recognition using only a camera even at low light.

1 is a block diagram of a vehicle surrounding object notification device according to an embodiment of the present invention.

2 is a flowchart illustrating a method of notifying a vehicle surrounding object according to an exemplary embodiment of the present invention.

3 is a flowchart illustrating a method for notifying a vehicle surrounding object according to another exemplary embodiment of the present invention.

4 is a flowchart illustrating a method for notifying a vehicle surrounding object according to another exemplary embodiment of the present invention.

FIG. 5 conceptually illustrates a situation in which a driving vehicle senses a surrounding vehicle and determines whether a lane image is abnormal according to an embodiment of the present disclosure.

The present invention is to detect the surrounding objects of the vehicle driving by using the image obtained from the camera to achieve the first object; Determining whether the lane image is abnormal by analyzing an image acquired from the direction in which the object is not found as a result of the detection; And informing the driver of the driving vehicle that there is an object around when there is no part of the lane image as a result of the determination.

The detecting of the surrounding objects of the vehicle in operation may include detecting a vehicle within a predetermined distance from the vehicle, and the predetermined distance may be determined in consideration of a vehicle congestion degree or speed around the vehicle.

In addition, the image obtained from the camera may include at least one or more of the front, rear, left, or right of the vehicle.

The present invention comprises the steps of sensing the surrounding objects of the vehicle driving by using the image obtained from the camera to achieve the second object; Determining whether the lane image is abnormal by analyzing an image acquired from the direction in which the object is not found as a result of the detection; Performing color correction or brightness correction on the obtained image when there is no part of the lane image as a result of the determination; Checking the presence or absence of an object around the vehicle from the corrected image; And informing the driver of the driving vehicle that the object is around when there is an object around the vehicle as a result of the checking.

The brightness correction may include generating a plurality of images having different exposure times based on a brightness value of an image acquired in a partial region of the lane image, and in the plurality of images, brightness values of boundary lines of objects. The lower part increases the brightness value by using an image with a long exposure time, and the higher brightness value at the boundary line of an object lowers the brightness value by using an image with a short exposure time, and then synthesizes the plurality of images. You can make corrections.

In addition, the color correction may perform a white balance to correct the color temperature of light.

In the color correction or brightness correction, when there is no part of the lane image, color correction or brightness correction may be performed on a partial region having an abnormality in the vehicle image regardless of the surrounding brightness of the vehicle. .

According to an aspect of the present invention, there is provided a method including: detecting a surrounding object of a driving vehicle by using an image acquired from a rear of a driving vehicle to achieve the third object; Performing color correction or brightness correction on an area within a predetermined distance when there is no object as a result of the detection; Checking the presence of an object behind the vehicle from the corrected image; And informing the driver of the driving vehicle that there is an object behind the vehicle when there is an object behind the vehicle as a result of the checking.

SUMMARY OF THE INVENTION In order to solve the above technical problem, the present invention provides a computer-readable recording medium having recorded thereon a program for executing the above-mentioned vehicle surrounding object notification method on a computer.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but can be embodied in various different forms, and the present embodiments only make the disclosure of the present invention complete, and those of ordinary skill in the art to which the present invention belongs. It is provided to fully inform those skilled in the art of the scope of the invention, which is defined only by the scope of the claims.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, "comprises" and / or "comprising" does not exclude the presence or addition of one or more other components in addition to the mentioned components. Like reference numerals refer to like elements throughout.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used in a sense that can be commonly understood by those skilled in the art. In addition, terms that are defined in a commonly used dictionary are not ideally or excessively interpreted unless they are specifically defined clearly.

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

Referring to FIG. 1, an object information notification apparatus around a vehicle according to the present exemplary embodiment includes an object detecting unit 110, a lane abnormality determining unit 120, and an information notification unit 130.

The object detecting unit 110 detects a peripheral object of a driving vehicle by using the image acquired from the camera. The object detecting unit 110 may selectively detect a surrounding object by using a general mode 113 using a basic camera and an HDR mode 116 using a high dynamic range (HDR) function.

The HDR mode 116 described herein refers to a mode in which regions having a large amount of color information are synthesized for each region of an image to generate an entire image having a large amount of color information. On the other hand, HDR (high dynamic range) technology is a technology for improving the recognition rate of the image, to shoot the image at different shutter speeds, to increase the resolution of the dark area brightness value of the image with a slow shutter speed, It is a technology that adjusts the resolution of brightness values of bright areas to make the hue and brightness of the entire image frame clear. However, because hue and brightness are adjusted for the entire image frame, a high-end image processor is required.

The object detecting unit 110 uses the normal mode 113 to determine the presence or absence of the surrounding object, and uses the HDR mode 116 when the lane abnormality determining signal comes from the lane abnormality determining unit 120. In the mode 113, an object not detected may be recognized. In addition, the processing speed can be improved by restricting the processing region of the HDR mode to the lane abnormality region.

Meanwhile, when the object detecting unit 110 recognizes the surrounding object of the vehicle in the normal mode 113, the object detecting unit 110 transmits the surrounding object information to the information notification unit 130 to notify the driver without passing through the lane abnormality determining unit 120. Can be.

The lane abnormality determining unit 120 determines whether the lane image is abnormal by analyzing an image obtained from the direction in which the object is not detected as a result of the detection by the object detecting unit 110. The abnormality of the lane image may be determined to be abnormal in the lane image when there is no part of the continuous or repeated lane image, but is not limited thereto.

The lane abnormality determiner 120 determines that the image is acquired by the general mode 113 of the object detector 110, and when a portion of the surrounding lane that is continuous or repeated is not detected, the lane abnormality determiner 120 lanes the object to the object detector 110. An abnormality detection signal can be transmitted.

When the object detecting unit 110 receives the lane abnormality detection signal, the object detecting unit 110 corrects the received image or the lane abnormality area through the HDR mode 116 and determines whether a neighboring object exists based on the corrected image. can do. If the object detecting unit 110 determines that there is a surrounding object, the object detecting unit 110 transmits information indicating that an object is in the vicinity of the vehicle.

If the information notification unit 130 receives a lane abnormality detection signal from the lane abnormality determining unit 120 because a part of the lane image that is continuous or repeated is not found as a result of the determination of the lane abnormality determining unit 120, the information notification unit 130 may notify the driver of the driving vehicle. You can tell that there is an object around.

In addition, when the object detector 110 detects an object in the normal mode 113 or the HDR mode 116, the information detector 130 receives object information from the object detector 110 and transmits the object information to the driver. You can tell if there is an object. When the object detecting unit 110 detects a surrounding object through the HDR mode 116, when the object detecting unit 110 receives a lane abnormal signal from the lane abnormality determining unit 120 or a nearby vehicle behind the driving vehicle enters a certain distance. It is preferable that it is a case of judgment.

Referring to FIG. 2, the method for notifying a vehicle surrounding object according to the present embodiment includes steps that are processed in time series in the apparatus for notification of a vehicle surrounding object shown in FIG. 1. Therefore, even if omitted below, the above descriptions of the apparatus for notifying the surrounding objects of the vehicle shown in FIG. 1 also apply to the method for notifying the surrounding objects of the vehicle according to the present embodiment. In addition, the content overlapping with what is described in FIGS. 3 to 4 will be omitted.

In the vehicle surrounding object notification method illustrated in FIG. 2, the surrounding object is detected by using the general mode 113 of the object detecting unit 110, and the lane is abnormal after determining whether the lane is abnormal for the area without the surrounding object. If it is determined, a warning signal is sent to the vehicle driver.

In operation 210, the vehicle surrounding object notification device detects a surrounding object of a driving vehicle using an image obtained from a camera.

The apparatus for notifying surrounding object information according to the present invention may detect an object within a certain distance from the vehicle using the AVM system. Therefore, the image obtained from the camera of the AVM system may include at least one or more of the front, rear, left, or right of the vehicle. The predetermined distance is an object recognition distance at which the neighboring object information notification device recognizes an object, and is a distance that is variably determined in consideration of a traffic density. In this case, the speed of the surrounding vehicle within a predetermined distance may be determined based on the speed of the current driving vehicle, and the vehicle congestion degree may be calculated in consideration of the number of the surrounding vehicles.

For example, when the speed of the traveling vehicle is low and the number of surrounding vehicles having similar speeds is large, the congestion degree is high and the predetermined distance to be maintained between the vehicles can be set relatively short. On the other hand, when the speed of the traveling vehicle is low and the number of surrounding vehicles having similar speeds is small, the vehicle congestion degree is low and the predetermined distance to be maintained between the vehicles can be set relatively long.

On the other hand, when the speed of the driving vehicle is high and the number of vehicles with similar speeds is small, the vehicle congestion is low. Therefore, a certain distance of the vehicle to be maintained may be relatively large, and conversely, the number of vehicles with similar speeds may be large. In this case, since the vehicle congestion degree is high, the constant distance can be set relatively short.

However, even in the same vehicle congestion degree, it is preferable to set a predetermined distance to be maintained between vehicles when the speed of the traveling vehicle is higher than when the speed of the driving vehicle is high.

In addition, the peripheral object information notification device according to an embodiment of the present invention determines the direction in which the object is not in accordance with the result of the object detection unit 110 detects the surrounding object, and the lane abnormality determination unit for the image area of the determined direction ( It is preferable that 120 determines whether the lane is abnormal. The direction without an object may be any one of four directions: front, rear, left, and right, but may be increased in 8 directions, 16 directions, or the like for more accurate results.

On the other hand, the peripheral object information notification device according to another embodiment of the present invention in step 210 detects the object within a certain distance from the vehicle proceeds to step 230 to inform the driver of the detected object information. However, if the object is not detected within a certain distance from the vehicle in step 210, after determining the direction without the object proceeds to step 220.

In operation 220, the neighboring object information notification device acquires an image in a direction in which the object is absent as a result of sensing in operation 210, and determines whether the lane image existing within a predetermined distance from the vehicle is abnormal. The predetermined distance may be variably determined according to the degree of vehicle congestion. If it is determined in step 220 that the lane image is normal, the process proceeds to step 210. If the lane image is determined to be abnormal, the process proceeds to step 230. The abnormality of the lane image may be determined to be abnormal in the lane image when there is no part of the continuous or repeated lane image, but is not limited thereto.

In operation 250, the apparatus for notifying the surrounding object information may notify the vehicle driver of the object information when the object is identified in step 210 or may warn the driver when it is determined that the lane shape is abnormal.

Referring to FIG. 3, the method for notifying a vehicle surrounding object according to the present embodiment includes steps that are processed in time series in the apparatus for notification of a vehicle surrounding object shown in FIG. 1. Therefore, even if omitted below, the above descriptions of the apparatus for notifying the surrounding objects of the vehicle shown in FIG. 1 also apply to the method for notifying the surrounding objects of the vehicle according to the present embodiment. In addition, the content overlapping with what is described in FIG. 2 or FIG. 4 will be omitted.

In the vehicle surrounding object notification method illustrated in FIG. 3, the surrounding object is detected by using the general mode 113 of the object detecting unit 110, and after determining whether the lane is abnormal for an area without the surrounding object, the lane is abnormal. If it is determined that the presence of the surrounding object by using the HDR mode 116 of the object detection unit 110 to inform the driver of the surrounding object information.

Since

steps

310, 320, and 350 shown in FIG. 3 overlap with descriptions of

steps

210, 220, and 250 shown in FIG. 2, a description thereof will be omitted.

In operation 330, the neighboring object information notification device performs image processing in the HDR mode 116 on the area where the lane is determined to be abnormal in operation 320.

In this case, it may be determined whether the lane image has an abnormality in the lane image when there is no part of the continuous or repeated lane image. When there is no part of the lane image, color correction or brightness correction may be performed on a portion of the vehicle image abnormality regardless of the surrounding brightness of the vehicle.

As an example of brightness correction, high dynamic range (HDR) technology is a technology for increasing the recognition rate of an image. The image is captured at different shutter speeds, the resolution of the dark area brightness value of the slow shutter speed is increased, and the shutter It is a technology that adjusts the resolution of brightness values of bright areas of a fast image so that the hue and brightness of the entire image frame are clear.

As an example of color correction, white balance may be performed on the region determined to be abnormal. White balance refers to a technique of correcting color temperature of light so that an ideal white image is captured. When the color temperature is low, the image becomes reddish, and when the color temperature is high, the light becomes blue. The white balance is adjusted to white by adjusting gains of R, G, and B values in each case.

In addition, by performing HDR image processing only on the pixel of the strange part of the lane image, it is possible to reduce the calculation amount and effectively determine whether the lane is abnormal in real time.

In operation 340, the apparatus for notifying the surrounding object information analyzes the color corrected or brightness corrected image to determine the presence of an object.

In operation 350, the neighboring object information notifying apparatus notifies the driver of the vehicle that is driving when there is an object around the vehicle.

Referring to FIG. 4, the method for notifying a vehicle surrounding object according to the present exemplary embodiment includes steps that are processed in time series in the apparatus for notification of a vehicle surrounding object shown in FIG. 1. Therefore, even if omitted below, the above descriptions of the apparatus for notifying the surrounding objects of the vehicle shown in FIG. 1 also apply to the method for notifying the surrounding objects of the vehicle according to the present embodiment. In addition, the content overlapping with what is described in FIGS. 2 to 3 will be omitted.

In the vehicle surrounding object notification method illustrated in FIG. 4, the general mode 1130 and the HDR mode (of the object detecting unit 110) may be used to detect a vehicle in which the headlight is broken or the headlight is not turned on. 116) determines whether there is a surrounding object present in the rear and informs the driver of the surrounding object information.

According to an exemplary embodiment of the present disclosure, an apparatus for notifying surrounding object information detects surrounding objects of a driving vehicle by using an image obtained from the rear of the driving vehicle, and corrects colors for an area within a certain distance when there is no object as a result of the sensing. Or proceed to step 410 to correct the brightness.

In operation 410, the surrounding object information notification device processes the image acquired from the front or the rear of the vehicle while driving in the HDR mode. HDR image processing is a technique that readjusts color resolution, taking into account the difference and distribution of high and low pixel values throughout an image frame. HDR mode can add or replace other methods as an example of brightness correction or color correction.

The brightness correction generates a plurality of images having different exposure times based on the brightness value of the image acquired in the partial region abnormal to the lane image, and the portion of the plurality of images having the lower brightness value of the boundary line of the object is exposed. The brightness value is increased by using an image having a long time and the brightness value of the boundary line of an object is a correction that synthesizes the plurality of images after lowering the brightness value by using an image having a short exposure time. In addition, the color correction may be performed using a white balance that corrects the color temperature of light. On the other hand, it is preferable to perform the color correction or brightness correction irrespective of the ambient brightness of the vehicle.

In operation 420, the surrounding object information notification device confirms whether an object is located in front of or behind the vehicle from the corrected image in operation 410.

At this time, it is preferable to detect a vehicle within a predetermined distance from the front or rear of the vehicle, the predetermined distance may be determined in consideration of the congestion or speed of the vehicle around the vehicle.

In operation 430, the surrounding object information notification device notifies the driver of the driving vehicle that the object is in the front or the rear when the object is located in the front or the rear of the vehicle.

Referring to FIG. 2 and FIG. 5, the first embodiment of the present invention detects surrounding objects while driving by using an image acquired from the camera of the general mode 113 of the vehicle A. FIG. As a result of the sensing, an image in a direction in which the object is not obtained is determined to determine whether the lane image is abnormal. That is, the vehicle B and the vehicle D of FIG. 5 are detected as the surrounding objects by the camera of the general mode 113 of the vehicle A, but the vehicle C is not detected as the surrounding objects because the headlight is not turned on. In this case, it is determined whether the lane image is abnormal by acquiring an image in the direction of the vehicle C. If there is no part of the lane image that is continuous or repeated as a result of the determination, the driver of the driving vehicle is notified that there is an object in the vicinity.

Referring to FIG. 3 and FIG. 5, when a vehicle in which a headlight is not turned on by using a general mode 113 camera and an HDR mode 116 camera is selectively located in a side lane, It may be determined whether the vehicle is covering the lane, and HDR image processing may be performed to determine whether or not the surrounding object is present.

In addition, when the vehicle does not turn on the headlights in the diagonal diagonal direction, the camera is not recognized as a neighboring vehicle, it is determined whether the vehicle is covering the lane, it can be informed to the driver with a warning message.

The difference between the second embodiment and the first embodiment is that in the second embodiment, if it is determined that the lane image is abnormal by analyzing an image acquired from a direction in which there is no object, color correction or brightness correction is performed on the obtained image. After confirming the presence or absence of an object around the vehicle from the corrected image, the information of the surrounding vehicle is transmitted to the driver.

Referring to FIG. 4 and FIG. 5, when the vehicle without the headlights is located at the rear, the vehicle can be detected by HDR image processing without determining whether the lane image is abnormal. . High-performance cameras capable of HDR image processing for rear vehicles without headlights can be used to increase object recognition in low light.

The term '~ part' used in the present embodiment refers to software or a hardware component such as a field-programmable gate array (FPGA) or an ASIC, and '~ part' performs certain roles. However, '~' is not meant to be limited to software or hardware. '~ Portion' may be configured to be in an addressable storage medium or may be configured to play one or more processors. Thus, as an example, '~' means components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, procedures, and the like. Subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and the 'parts' may be combined into a smaller number of components and the 'parts' or further separated into additional components and the 'parts'. In addition, the components and '~' may be implemented to play one or more CPUs in the device or secure multimedia card.

All of the above functions may be performed by a processor such as a microprocessor, a controller, a microcontroller, an application specific integrated circuit (ASIC), or the like according to software or program code coded to perform the function. The design, development and implementation of the code will be apparent to those skilled in the art based on the description of the present invention.

Although the present invention has been described above with reference to the embodiments, it will be understood by those skilled in the art that various modifications and changes of the present invention can be made without departing from the spirit and scope of the present invention. I can understand. Therefore, the present invention is not limited to the above-described embodiment, and the present invention will include all embodiments within the scope of the following claims.

Claims

Detecting a peripheral object of a driving vehicle using an image obtained from a camera;

Determining whether the lane image is abnormal by analyzing an image acquired from the direction in which the object is not found as a result of the detection; And

And informing the driver of the driving vehicle that there is an object around when there is no part of the lane image as a result of the determination.
According to claim 1,

Detecting a peripheral object of the driving vehicle,

Detect a vehicle within a certain distance from the vehicle,

The predetermined distance is determined in consideration of vehicle congestion or speed around the vehicle surrounding object notification method.
According to claim 1,

The image obtained from the camera comprises at least one of the front, rear, left, or right side of the vehicle at least one object notification method.
Detecting a peripheral object of a driving vehicle using an image obtained from a camera;

Determining whether the lane image is abnormal by analyzing an image acquired from the direction in which the object is not found as a result of the detection;

Performing color correction or brightness correction on the obtained image when there is no part of the lane image as a result of the determination;

Checking the presence or absence of an object around the vehicle from the corrected image; And

If there is an object around the vehicle as a result of the checking, informing the driver of the driving vehicle that the object is around the vehicle.
The method of claim 4, wherein

The brightness correction step,

A plurality of images having different exposure times are generated based on brightness values of an image acquired in a part of the lane image that is abnormal, and a portion of the plurality of images having a low brightness value of an edge of an object has a long exposure time image. Increasing the corresponding brightness value using the image, and lowering the corresponding brightness value by using an image having a short exposure time in a portion where the brightness value of the boundary line of the object is reduced, and then synthesizing the plurality of images. .
The method of claim 4, wherein

Wherein the color correction step is a vehicle around the object notification method, characterized in that for performing a white balance to correct the color temperature of the light.
The method of claim 4, wherein

The color correction or brightness correction step,

When the part of the lane image does not exist, the object around the vehicle notification method characterized in that the color correction or brightness correction for a partial region of the vehicle image irrespective of the ambient brightness of the vehicle.
The method of claim 4, wherein

Detecting a peripheral object of the driving vehicle,

Detect a vehicle within a certain distance from the vehicle,

The predetermined distance is determined in consideration of vehicle congestion or speed around the vehicle surrounding object notification method.
Detecting a peripheral object of the driving vehicle using an image acquired from the rear of the driving vehicle;

Performing color correction or brightness correction on an area within a predetermined distance when there is no object as a result of the detection;

Checking the presence of an object behind the vehicle from the corrected image; And

And informing the driver of the driving vehicle that there is an object behind the vehicle when there is an object behind the vehicle as a result of the checking.
The method of claim 9,

The brightness correction step,

Generate a plurality of images having different exposure times based on the brightness value of the obtained image, and increase the corresponding brightness value by using an image having a long exposure time in a portion where the brightness value of the boundary of the object is low in the plurality of images, The high-brightness value of the boundary line of the object lowers the brightness value by using an image having a short exposure time, and then synthesizes the plurality of images.
The method of claim 9,

Wherein the color correction step is a vehicle around the object notification method, characterized in that for performing a white balance to correct the color temperature of the light.
The method of claim 9,

The color correction or brightness correction step,

Color correction or brightness correction method for the area within the predetermined distance irrespective of the ambient brightness of the vehicle.
The method of claim 9,

The predetermined distance is determined in consideration of vehicle congestion or speed around the vehicle surrounding object notification method.
An object detecting unit detecting an object around the vehicle while driving by using an image obtained from a camera;

A lane abnormality determining unit which analyzes an image acquired from a direction in which no object exists and determines whether the lane image is abnormal; And

And an information notification unit for notifying a driver of the driving vehicle that there is an object in the vicinity when the lane image is not part of the determination result.
The method of claim 14,

If there is no lane image as a result of the determination of the lane abnormality determining unit, the object detecting unit corrects color or brightness of the image of the area having the abnormality of the lane image, and confirms the presence or absence of an object around the vehicle from the corrected image. and,

And the information notification unit notifies the driver of the driving vehicle that the object is present when there is an object around the vehicle.
Using the image acquired from the rear of the driving vehicle to detect the surrounding objects of the driving vehicle, if there is no object as a result of the detection, color correction or brightness correction for the area within a certain distance, and from the corrected image An object detecting unit checking an object behind the object; And

And an information notification unit for notifying a driver of the driving vehicle that there is an object behind the vehicle when there is an object behind the vehicle.
A computer-readable recording medium having recorded thereon a program for executing the method of any one of claims 1 to 13 on a computer.