KR101515482B1 - Driving assist device according as the risk of obstacles around the vehicle and method thereof - Google Patents

Abstract

The present invention relates to a driving assistance device considering a risk of obstacles around a vehicle and an operation method thereof. The driving assistance device comprises: an acquisition unit acquiring surrounding images including the obstacles around the vehicle; a control unit extracting the obstacle from the surrounding images, calculating the risk of the extracted obstacles, and determining a warning level depending on the calculated risk; and a warning unit giving a warning to a driver by outputting a different warning signal in accordance with the warning level determined from the control unit.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a driving assist device and a driving assist device,

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a driving support apparatus, and more particularly, to a driving support technique that takes into consideration the risk of an obstacle around a vehicle.

Generally, in order for a driver to recognize the movement of another vehicle or an object located at the rear or side of the vehicle when the vehicle is running or when the vehicle is parked, a vehicle mirror (for example, a rearview mirror and a side mirror) . However, with such a vehicle mirror, the driver can not know the details of the blind spot around the vehicle.

For this reason, in recent years, a vehicle bumper is provided with an obstacle detecting device for a vehicle in order to prevent a safety accident caused by a collision with an obstacle or a person when the vehicle is backed up or parked. The obstacle detecting device detects the presence of an obstacle around the vehicle using a sensor mounted on the vehicle, and notifies the driver of the presence of an obstacle by an alarm sound or an indicator. Ultrasonic sensors are mainly used for this obstacle detection device. Specifically, the obstacle sensing device transmits an ultrasonic wave of a specific band through an ultrasonic sensor, receives an ultrasonic signal of a specific band reflected by the obstacle, and determines an approach direction and an approach distance of an obstacle existing behind the vehicle. When the obstacle approaches within a certain distance, the obstacle detection device provides the information of the obstacle to the driver to prevent safety accidents such as various contact accidents.

However, such an obstacle detection device only detects the presence of an obstacle around the vehicle and the distance between the vehicle and the obstacle, and provides information on the presence of the obstacle to the driver, but does not consider the accident risk according to the characteristics of the obstacle.

An object of the present invention is to provide a technical solution that can change the warning level according to the accident risk in consideration of the characteristics of obstacles.

According to an aspect of the present invention, there is provided a driving assistance apparatus including an acquisition unit for acquiring a surrounding image including an obstacle around a vehicle, an extraction unit for extracting the obstacle from the surrounding image, And a warning unit for outputting a warning signal differently according to the warning level determined by the control unit and alerting the driver to the driver, The risk is calculated in consideration of at least one of the characteristics of the obstacle and the position of the obstacle.

Here, the photographing unit may acquire a plurality of the surrounding images on a predetermined time basis, and the controller may further calculate the risk by taking into consideration a distance change between the vehicle and the obstacle, And the risk is calculated by dividing the characteristic of the obstacle into at least one of a person, an object, a child, an adult, an elderly person, a fixed object, and a moving object.

Further, the photographing unit is a camera for an Around View System (AVM) including at least one camera that photographs the direction of at least one of the front, rear, left, and right rooms of the vehicle.

According to another aspect of the present invention, there is provided a driving support method considering a risk of an obstacle around a vehicle by a driving support device, the method comprising: obtaining a surrounding image including an obstacle around the vehicle; The method of claim 1, further comprising: extracting the obstacle from the image; calculating a risk of the extracted obstacle; and alerting the driver to a different warning level according to the calculated risk level, And calculating the risk by considering at least one of the characteristics of the obstacle and the position of the obstacle as a standard.

Here, the acquiring may include acquiring a plurality of the peripheral images in units of a predetermined time, and the calculating may include calculating a distance between the vehicle and the obstacle obtained using the peripheral images acquired in the predetermined time unit, And calculating the risk by further considering the change.

The calculating step may include calculating the risk by dividing the obstacle characteristic into at least one of a person, an object, a child, an adult, an elderly person, a fixed object, and a moving object, And acquiring the peripheral image using a camera for an overview system including at least one camera that captures a direction of at least one of a back, a left room, and a right room.

The present invention differs from the existing driving support technology in which only the distance of the obstacle is warned by taking into consideration only the distance of the obstacle. The obstacle is extracted from the surrounding image of the vehicle, the characteristic, the position and the distance of the obstacle are grasped and the risk is calculated. By warning the driver at a different level, the driver can be provided with a specific risk of an accident with respect to an obstacle around the vehicle, and the driver's awareness of the accident risk can be increased.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram of a driving support device in consideration of the risk of an obstacle around a vehicle according to an embodiment of the present invention; FIG.
2 is a diagram for explaining acquisition of a peripheral image according to the present invention;
3 is a view for explaining distinction of an obstacle according to the present invention;
4 is a flowchart of a driving support method considering a risk of an obstacle around a vehicle by a driving support device according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The foregoing and further aspects of the present invention will become more apparent from the following detailed description of preferred embodiments with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1 is a block diagram of a driving assistance apparatus considering the risk of an obstacle around a vehicle according to an embodiment of the present invention. As shown in the figure, the driving support apparatus 10 includes an acquisition unit 100, a control unit 200, and a warning unit 300.

The acquiring unit 100 is a camera for acquiring a peripheral image of the surroundings of the vehicle, and is a camera. Specifically, the obtaining unit 100 is one or more cameras that photograph the direction of at least one of the front, rear, left and right rooms of the vehicle. Preferably, the acquiring unit 100 may include front cameras, rear cameras, left cameras, and right cameras as illustrated in FIG. 2 to acquire front, rear, left, and right peripheral images of the vehicle. To this end, the obtaining unit 100 may use a camera for an Around View System (AVM) of a vehicle.

In addition, the acquiring unit 100 acquires a plurality of peripheral images in units of a predetermined time (for example, one second), and the obtained peripheral images may be stored in a separate memory. Here, the memory may be implemented in the driving support apparatus 10 in the form of a NAND flash memory. Alternatively, the memory may be a Universal Serial Bus (USB) memory or a Secure Digital (SD) card memory.

The control unit 200 is a unit for controlling the driving support apparatus 10 considering the risk of the obstacle around the vehicle, and calculates the risk of the obstacle extracted from the surrounding image and determines the warning level according to the risk level.

First, the control unit 200 extracts an obstacle from a surrounding image obtained from the obtaining unit 100. [ For this purpose, the controller 200 may extract an obstacle from the surrounding image using an image signal processor (ISP). Before extracting the obstacle, the control unit 200 may pre-process the surrounding image obtained from the obtaining unit 100 to improve the accuracy of obstacle extraction. In addition, the control unit 200 can extract an obstacle from the surrounding image and detect the movement using different techniques according to the vehicle's stop state or running state.

For example, when the vehicle is stopped, that is, when the speed of the vehicle is equal to or lower than a predetermined speed (for example, 10 km / h), the control unit 200 can extract an obstacle using a weighted average difference. Specifically, the control unit 200 can separate the background region and the object (obstacle) region using the weighted average difference of the pixels of the surrounding image obtained from the obtaining unit 100. Further, the control unit 200 can extract obstacles and detect motion by checking the boundary of the object candidate region or the object. Such an obstacle extraction method using a weighted average difference is mainly used in the field of surveillance and is a suitable image processing processor in a vehicle stop state because a simple algorithm requires less computation burden.

If the speed of the vehicle is higher than a predetermined speed (for example, 10 km / h), the controller 200 analyzes the texture of the surrounding image obtained from the obtaining unit 100 You can separate the road area and the object (obstacle) area. The controller 200 performs a histogram standard deviation histogram on the texture-analyzed surrounding image to remove the lane area that has not been removed through texture analysis. In addition, the controller 200 extracts obstacles from the object area through texture analysis and histogram standard deviation analysis, and detects movement of the obstacle by applying a weight to the extracted area of the obstacle.

When the obstacle is extracted from the surrounding image, the control unit 200 calculates the risk of the extracted obstacle. To calculate the risk, the control unit 200 calculates the risk by considering at least one of the characteristics of the obstacle, the position of the obstacle, and the distance change of the obstacle. Hereinafter, a description will be given of a method for confirming the characteristics, position, and distance changes of obstacles for calculating the risk.

In order to calculate the risk, the control unit 200 confirms the characteristics of the obstacle. Specifically, the control unit 200 distinguishes whether the extracted obstacle is a person or an object.

As an example, the control unit 200 can distinguish a person or an object by comparing the similarity of the extracted obstacle with the stored person model and the object model. Here, the pre-stored person model and the object model can be preset and stored by the manager or the user in advance. For example, the human model may be a model having various forms according to a human body shape and a kind of object, and the model information may be stored in a separate memory.

As another example, the control unit 200 can determine whether the extracted obstacle is a person by using a pedestrian detection algorithm of the image processing processor. Here, the pedestrian detection algorithm is widely used in image processing technology, and there are various algorithms for detecting a person in an image.

If it is determined that the extracted obstacle is a person, the control unit 200 determines whether the identified person is a child, an adult, or an elderly person. This is because children (infants) or the elderly are at higher risk of accidents (crashes) than adults.

Specifically, the control unit 200 can distinguish a person from the identified person's key, body ratio (ratio of head to body) and existence of auxiliary means. In general, the body proportion of a person is 1: 4 for a newborn (less than 2 years old), 1: 5 for an infant (about 2 to 6 years old) 1: 6 for adolescents (approximately 12 to 20 years old) and 1: 8 for adults (approximately 20 years and older). In addition, the control unit 200 can check the height or the height of the extracted obstacle according to the person or object. If the extracted obstacle is a person and the ratio is less than 1: 6 at a height of 110 cm or less as shown in FIG. 3A, the controller 200 classifies the obstacle identified as a human being as a child (infant) .

In addition, when the obstacle identified as a person is not a child, it is difficult to distinguish an adult and an elderly person as a key or a body ratio, so that the control unit 200 can distinguish an elderly person by confirming whether or not the extracted obstacle has an auxiliary means. Here, the auxiliary means is a means for assisting the walking of a person who has difficulty in walking, such as a walking stick or a moving aid. That is, the control unit 200 determines whether a person has an auxiliary means through image processing of an obstacle identified as a person, and a person having an auxiliary means is classified as an elderly person. Otherwise, as shown in FIG. 3 (b) Adults who can walk without assistance.

Also, the controller 200 can determine whether the extracted obstacle is an object by using an object detection algorithm in the image processing processor. Alternatively, the control unit 200 can confirm an obstacle that has not been confirmed as a person as an object. If the obstacle is identified as an object, the control unit 200 can classify the object type. For example, the control unit 200 can classify a type of object into a moving object such as a bicycle, a vehicle in FIG. 3C, and a fixed object such as a molding or a facility. This is because moving objects have a higher risk of accidents than fixed objects.

If the characteristics of the obstacle extracted from the surrounding image are confirmed, the control unit 200 can obtain the risk score from the memory according to the identified obstacle characteristic. Here, the risk score according to the characteristics of the obstacle can be preset in the memory as shown in Table 1 and stored in the memory.

obstacle
Kinds child Elderly (auxiliary means) adult bicycle car Fixed object Risk
score 30 15 10 12 8 5

The risk score according to the characteristics of the obstacle can be set and changed by the administrator or the user in advance, and the classification of the obstacle characteristic can be also deleted and added.

In order to calculate the risk, the control unit 200 confirms the position of the obstacle. Specifically, the control unit 200 determines in which direction the extracted obstacle is located based on the vehicle. That is, the control unit 200 determines the position of the obstacle (the position of the obstacle in front of the vehicle, the direction of the vehicle, and the like) according to which of the cameras (front, rear, left and right rooms) , Rear and left and right rooms).

In addition, the control unit 200 can confirm the moving direction of the vehicle and confirm the position of the extracted obstacle more specifically. For example, the control unit 200 can sense the shift direction of the vehicle by sensing the shift range of the vehicle. The control unit 200 determines whether the obstacle is located on the moving direction side of the vehicle or on the opposite side of the moving direction of the vehicle, Regardless of whether the vehicle is located on the side (left or right) of the vehicle.

For example, when the obstacle is confirmed to be located in front of the vehicle, that is, when the camera that has captured the surrounding image including the extracted obstacle is the front camera, the shift position of the vehicle is located at the front end If it is detected, the control unit 200 can confirm that the obstacle is located in the moving direction of the vehicle. If the shift position of the vehicle is detected as being located at the rear end (R-end), the control unit 200 can confirm that the obstacle is located in the opposite direction of the vehicle movement.

As another example, when it is determined that the obstacle is located at the rear of the vehicle, that is, when the camera that has captured the surrounding image including the extracted obstacle is the rear camera, the shift position of the vehicle is located at the front end If it is detected, the control unit 200 can confirm that the obstacle is located in the opposite direction of the movement of the vehicle. If it is detected that the shift position of the vehicle is located at the rear end (R end), the control unit 200 can confirm that the obstacle is located in the moving direction of the vehicle.

If the location of the obstacle extracted from the surrounding image is identified, the controller 200 can acquire the risk score from the memory according to the identified obstacle location. Here, the risk score according to the position of the obstacle can be pre-set as shown in Table 2 and stored in the memory.

Obstacle location Direction of movement of the vehicle Left and right sides of the vehicle Movement direction of vehicle Risk score 10 5 3

The risk score according to the position of the obstacle can be set and changed by the administrator or the user in advance, and the distinction of the obstacle position can also be deleted and added.

In order to calculate the risk, the control unit 200 confirms the distance change of the obstacle. Specifically, the control unit 200 confirms the distance between the vehicle and the obstacle. The control unit 200 can confirm whether the obstacles extracted by using the peripheral images obtained in units of a predetermined time from the obtaining unit 100 are approaching, moving away from, or changing in distance . At this time, the controller 200 can acquire the depth information by using the distance calculation algorithm in the image processing technique to check the distance of the obstacle.

The controller 200 compares the distances of the obstacles identified in the current peripheral image with the distances of the obstacles identified in the previous peripheral images before a predetermined time (for example, one second ago). If the distance is shortened, You can see that the distance is approaching, and as the distance gets longer, you can see that the distance between the obstacle and the vehicle is getting farther away. If the distance to be compared is the same, that is, if the distances of the obstacles identified in the current surrounding image and the previous neighboring image are the same, the controller 200 determines that the obstacle is also a stopped obstacle when the vehicle is stationary, If there is one, it can be confirmed that the obstacle also moves at the same speed.

As described above, when the distance change of the obstacle extracted from the surrounding image is confirmed, the control unit 200 can acquire the risk score from the memory according to the distance change of the identified obstacle. Here, the risk score according to the characteristics of the obstacle can be stored in the memory in advance as shown in Table 3.

Obstacle distance change Getting closer to the car stop Distance from the vehicle Risk score 10 5 0

The risk score according to the change of the obstacle distance can be set or changed by the administrator or the user in advance, and the distinction of the obstacle distance change can also be deleted and added.

The controller 200 obtains a risk score for at least one of the characteristics of the obstacle, the position of the obstacle and the distance change of the obstacle, and calculates the risk of the obstacle by using the score. Specifically, the control unit 200 calculates the risk by summing the risk scores obtained by referring to Tables 1 to 3 for each of the characteristics, position, and distance changes of the obstacle extracted from the surrounding image.

For example, if it is determined that the obstacle extracted from the surrounding image is a child located on the left side of the vehicle and that it is approaching the vehicle, the control unit 200 adds the risk scores to the obstacle (child) Can be calculated.

As another example, if it is confirmed that the obstacle extracted from the surrounding image is located in the moving direction of the vehicle and is a bicycle away from the vehicle, the control unit 200 adds the risk scores to the obstacle (bike) Can be calculated.

As another example, if it is ascertained that the obstacle extracted from the surrounding image is located in a direction opposite to the direction of movement of the vehicle and is a fixture that approaches the vehicle, the control unit 200 adds the risk scores for each of the obstacles to the obstacle (fixed object) 18 can be calculated.

When the risk of the obstacle extracted from the surrounding image is calculated, the controller 200 determines the warning level according to the risk level. Preferably, the controller 200 can increase the warning level as the risk increases. For example, if the calculated risk is less than 10, it is safe (0), if the calculated risk is less than 10 (10) It can be divided.

The warning unit 300 alerts the driver of the warning signal according to the warning level of the controller 200. Here, the warning unit 300 outputs a warning sound through a speaker installed at a predetermined position of the vehicle to warn the driver. For example, according to the determination result of the warning level of the control unit 200, the alarm unit 300 may narrow the output interval of the alarm sound output or raise the volume of the alarm sound as the risk level increases.

Furthermore, the warning unit 300 may output a color screen through a display device (for example, an LCD of an AVN system) on which a peripheral image obtained by the obtaining unit 100 is displayed to alert the driver. For example, the warning unit 300 can output a color screen by overlapping the surrounding images with different colors such as green, yellow, orange, and red as the risk level increases, and in some cases, To alert the driver.

As described above, unlike the conventional driving support technology which warns only the distances of obstacles, the present invention extracts obstacles from the surrounding images of the vehicle, calculates the risk by grasping the characteristics, positions and distances of the obstacles, By warning the driver by varying the warning level according to the degree of risk, the driver can be provided with the specific risk of the accident with respect to the obstacle around the vehicle and the driver can be more aware of the risk of the accident.

4 is a flowchart illustrating a driving support method considering a risk of an obstacle around a vehicle by the driving assistance device according to the embodiment of the present invention.

First, the driving support apparatus 10 acquires a peripheral image around the vehicle (S100).

Specifically, the driving support apparatus 10 can acquire a peripheral image of the vehicle through one or more cameras that photograph the direction of at least one of the front, rear, left, and right rooms of the vehicle. Here, the driving support device 10 may use a camera for an Around View System (AVM) of a vehicle.

The driving support apparatus 10 extracts an obstacle from the surrounding image acquired in step S100 (S200).

To this end, the driving support apparatus 10 can extract an obstacle from a surrounding image using an image signal processor (ISP). In addition, the control unit 200 can extract an obstacle from the surrounding image and detect the movement using different techniques according to the vehicle's stop state or running state.

For example, when the vehicle is stationary, that is, when the speed of the vehicle is not higher than a predetermined speed (for example, 10 km / h), the driving support apparatus 10 can extract an obstacle by using a weighted average difference have.

When the vehicle is traveling, that is, when the speed of the vehicle is not less than a predetermined speed (for example, 10 km / h), the driving support apparatus 10 analyzes the texture of the surrounding image, ) Area, and the standard deviation of the histogram of the surrounding image is analyzed to remove the non-removed lane area by texture analysis. In addition, the driving support apparatus 10 extracts obstacles from the object region through texture analysis and histogram standard deviation analysis, and detects movement of obstacles by applying weights to the regions of the extracted obstacles.

When the obstacle is extracted from the surrounding image, the driving support apparatus 10 confirms the characteristic, position, and distance change of the extracted obstacle (S300).

First, the driving support device 10 confirms the characteristics of the obstacle. Specifically, the driving support apparatus 10 distinguishes whether the extracted obstacle is a person or an object.

The driving support apparatus 10 can identify whether the extracted obstacle is a person by using a pedestrian detection algorithm in the image processing processor. Here, the pedestrian detection algorithm is widely used in image processing technology, and there are various algorithms for detecting a person in an image.

If it is confirmed that the extracted obstacle is a person, the driving support apparatus 10 discriminates whether the identified person is a child, an adult, or an elderly person. This is because children (infants) or the elderly are at higher risk of accidents (crashes) than adults.

In addition, the driving support apparatus 10 can determine whether the extracted obstacle is an object by using an object detection algorithm in the image processing processor. Alternatively, the driving support apparatus 10 can confirm an obstacle not identified as a person as an object. If the obstacle is confirmed as an object, the driving support device 10 can classify the type of object. For example, the driving support apparatus 10 can classify objects into fixed objects such as moving objects such as bicycles and vehicles, and sculptures and facilities. This is because moving objects have a higher risk of accidents than fixed objects.

Second, the driving support apparatus 10 confirms the position of the obstacle. Specifically, the driving support apparatus 10 confirms in which direction the extracted obstacle is positioned relative to the vehicle. That is, the driving support apparatus 10 determines the positions of the obstacles (front, rear, and right and left sides of the vehicle) according to which of the cameras (front, rear, left and right rooms) Room) can be confirmed.

In addition, the driving support apparatus 10 can confirm the moving direction of the vehicle and more specifically confirm the position of the extracted obstacle. For example, the driving support device 10 can detect the direction of movement of the vehicle by detecting the shift position of the vehicle. The driving support apparatus 10 confirms whether the obstacle is located on the moving direction side of the vehicle or on the opposite direction side of the vehicle movement, (Left and right) of the vehicle regardless of the direction of the vehicle.

Third, the driving support apparatus 10 confirms the distance change of the obstacle. Specifically, the driving support apparatus 10 confirms the distance between the vehicle and the obstacle. The driving support apparatus 10 can confirm whether the obstacles extracted using the peripheral images obtained on a predetermined time basis are approaching, moving away from, or having no distance change (a certain distance is maintained) based on the vehicle. At this time, the driving support apparatus 10 can obtain the depth information by using the distance calculation algorithm of the image processing technique, and can confirm the distance of the obstacle.

The driving support apparatus 10 compares the distances of the obstacles identified in the current surrounding image with the distances of the obstacles identified in the previous surrounding image before a predetermined time (for example, one second ago). If the distance is shortened, You can see that the distance of the vehicle is getting closer. If the distance is longer, you can see that the distance between the obstacle and the vehicle is getting longer. If the compared distances are the same, that is, if distances of the obstacles identified in the current peripheral image and the previous neighboring image are the same, the driving support apparatus 10 is an obstacle in which the obstacle is also stopped when the vehicle is stopped, If you are driving, you can see that the obstacles also move at the same speed.

The driving support apparatus 10 calculates the risk of the obstacle in consideration of the characteristics, position, and distance of the obstacle (S400).

Specifically, when the characteristics, position, and distance change of the obstacle extracted from the surrounding image are confirmed in step S300, the driving support device 10 can obtain the risk score for each of the obstacles from the memory. Here, the risk score according to each of the characteristic, position, and distance change of the obstacle can be preset in the memory as shown in Tables 1 to 3 and stored in the memory.

The driving support apparatus 10 calculates the risk by summing the risk scores obtained by referring to Tables 1 to 3 for each of the characteristics, position, and distance changes of the obstacles extracted from the surrounding images.

When the risk for the obstacle is calculated in step S400, the driving support apparatus 10 alerts the driver with a different warning level according to the degree of danger (S500).

Preferably, the driving support device 10 can raise the warning level as the risk increases. For example, if the calculated risk is less than 10, it is safe (0), if the calculated risk is less than 10 (10) It can be divided.

The driving support apparatus 10 outputs a warning signal at a different warning level according to the level of the risk.

For example, the driving support device 10 outputs a warning sound through a speaker mounted at a predetermined position of the vehicle to warn the driver. At this time, the driving support apparatus 10 may narrow the output interval of the alarm sound output or increase the volume of the alarm sound as the risk level increases.

As another example, the driving support apparatus 10 may output a color screen through a display device (e.g., an LCD of an AVN system) on which a peripheral image is displayed to alert the driver. At this time, the driving support apparatus 10 can output a color screen by overlapping the surrounding images with different colors such as green, yellow, orange, and red as the risk level increases, and in some cases, You can blink to warn the driver.

As described above, unlike the conventional driving support technology which warns only the distances of obstacles, the present invention extracts obstacles from the surrounding images of the vehicle, calculates the risk by grasping the characteristics, positions and distances of the obstacles, By warning the driver by varying the warning level according to the degree of risk, the driver can be provided with the specific risk of the accident with respect to the obstacle around the vehicle and the driver can be more aware of the risk of the accident.

The present invention has been described with reference to the preferred embodiments. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is defined by the appended claims rather than by the foregoing description, and all differences within the scope of equivalents thereof should be construed as being included in the present invention.

10: driving support apparatus 100:
200: control unit 300: warning unit

Claims (11)

An acquiring unit acquiring a peripheral image including an obstacle around the vehicle;
Extracting the obstacle from the peripheral image, checking the characteristics of the extracted obstacle, the position of the obstacle, the distance change between the vehicle and the obstacle, and calculating a risk score A control unit for calculating a risk level of the obstacle by summing the allocated risk scores and determining a warning level according to the calculated risk level; And
An alarm unit for outputting a warning signal differently according to the warning level determined by the control unit and warning the driver of the warning signal; , ≪ / RTI &
Wherein,
Determining whether the obstacle is a person or a person when the characteristic of the obstacle is confirmed; and assigning the risk score differently according to a key and a body ratio of the obstacle when the obstacle is judged to be a person
Driving support device considering the risk of an obstacle around the vehicle.
delete The method according to claim 1,
Wherein the acquiring unit acquires a plurality of peripheral images in units of a predetermined time,
Wherein,
And confirming a change in the distance between the vehicle and the obstacle obtained by using the peripheral images obtained in units of the predetermined time
Driving support device considering the risk of an obstacle around the vehicle.
The apparatus of claim 1,
When the characteristics of the obstacle are checked, if the obstacle is determined as an object, it is discriminated whether the obstacle is a fixed object or a moving object, and the risk score is assigned differently
Driving support device considering the risk of an obstacle around the vehicle.
The apparatus according to claim 1,
And at least one camera for photographing the direction of at least one of the front, rear, left and right rooms of the vehicle
Driving support device considering the risk of an obstacle around the vehicle.
The apparatus according to claim 1,
Camera for Around View System (AVM)
Driving support device considering the risk of an obstacle around the vehicle. Acquiring a peripheral image including an obstacle around the vehicle;
Extracting the obstacle from the surrounding image;
Identifying a characteristic of the extracted obstacle, a position of the obstacle, a distance change between the vehicle and the obstacle, and assigning a risk score to each of the identified characteristic, position, and distance change of the obstacle;
Calculating a risk of the obstacle by summing the assigned risk scores; And
Warning the driver by changing the warning level according to the calculated risk level; , ≪ / RTI &
Wherein the assigning comprises:
Determining whether the obstacle is a person or a person when the characteristic of the obstacle is confirmed; and assigning the risk score differently according to a key and a body ratio of the obstacle when the obstacle is judged to be a person
A method of driving support considering the risk of an obstacle around a vehicle.
delete 8. The method of claim 7,
And acquiring a plurality of the peripheral images in units of a predetermined time,
Wherein the assigning comprises:
And confirming a change in the distance between the vehicle and the obstacle obtained by using the peripheral images obtained in units of the predetermined time
A method of driving support considering the risk of an obstacle around a vehicle.
8. The method of claim 7,
When the characteristics of the obstacle are confirmed, if the obstacle is determined as an object, it is discriminated whether the obstacle is a fixed object or a moving object, and the risk score is assigned differently
A method of driving support considering the risk of an obstacle around a vehicle.
8. The method of claim 7, wherein the obtaining comprises:
And acquiring the peripheral image using a camera for an overview system, the at least one camera capturing a direction of at least one of the front, rear, left and right rooms of the vehicle. Driving support method considering risk.

Images