KR102239992B1 - Methods for warning of vehicle collision and Apparatuses thereof - Google Patents

Abstract

The present invention relates to a vehicle collision warning method and apparatus, wherein the present invention relates to an image acquisition unit that obtains vehicle image information and external vehicle image information, and a front vehicle that acquires speed information of a front vehicle and distance information from a vehicle in front of the vehicle. The information acquisition unit and the first weight calculation unit that calculates a first weight based on the image information inside the vehicle and the vehicle external image information calculates weather condition information or road surface condition information, and according to the weather condition information or road surface condition information Analyzing the risk of collision with the vehicle ahead by using at least one of information obtained by the second weight calculation unit and the front vehicle information acquisition unit that calculates the second weight, the own vehicle speed information, the first weight, and the second weight. It provides a vehicle collision warning apparatus, method, and system including a collision risk analysis unit and a warning processing unit that generates a warning control signal according to a result of the collision risk analysis.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention Method and apparatus for warning of vehicle collision

The present invention relates to a vehicle collision warning method and apparatus, and more particularly, to a method and apparatus for providing a more accurate collision warning by calculating an estimated stopping distance of a vehicle in consideration of a driver condition and a road surface condition.

In general, automobiles are a comprehensive collection of mechanical and electronic technologies that have been developed with the development of civilization. In addition to the recent prosperity of life, in line with the rapidly changing environment, smooth work, convenience of daily life, use of leisure, etc. For this purpose, the spread is greatly expanding.

When driving such a vehicle, it is essential that the driver maintains a safe distance from other vehicles to prevent various safety accidents.

However, since the driver only visually judges the calculation of the distance to another vehicle, especially the vehicle ahead, in some cases, there is a concern that safety accidents such as a collision may occur due to the driver's misunderstanding.

Therefore, recently, in order to facilitate the driver's convenience, a sensor is installed in the front of the vehicle to automatically calculate the distance to another vehicle, and then, when a vehicle is within the distance of a potential collision, an alarm sound is generated to call the driver's attention. A collision warning system (Forward Collision Warning, FCW) is being developed.

However, such a vehicle collision warning system has a problem in that it does not reflect a road surface condition and a climatic condition by determining whether to warn a collision using speed information and distance information of the own vehicle and other vehicles. There is a problem in that an accurate warning cannot be executed as a significant difference occurs in the stopping distance of the vehicle depending on the road surface and weather conditions.

In addition, there is a problem in that an accident may not be caused according to the driver's driving concentration even if a warning is provided within an appropriate stopping distance because the driver's driving concentration cannot be reflected.

Against this background, an object of the present invention is to determine whether a collision warning has occurred in a vehicle collision warning system by comprehensively considering a vehicle external situation and a driver's driving concentration situation.

In addition, in calculating the predicted collision time, an object of the present invention is to calculate an accurate predicted collision time by additionally considering information on external conditions of the vehicle and information on changes in the driver's condition.

In addition, an object of the present invention is to provide a method and apparatus for warning of a vehicle collision with low cost and high efficiency by calculating an accurate collision predicted time using a simplified algorithm.

In order to achieve the above object, in one aspect, the present invention provides an image acquisition unit for acquiring image information inside a vehicle and image information outside a vehicle, and front vehicle information acquiring speed information of a front vehicle and distance information from a front vehicle. A first weight calculation unit that calculates a first weight based on the acquisition unit and the image information inside the vehicle, and the weather condition information or road surface condition information, are calculated based on the image information outside the vehicle, and are determined according to the weather condition information or the road surface condition information. 2 Collision that analyzes the risk of collision with the vehicle in front using at least one of information obtained by the second weight calculation unit and the front vehicle information acquisition unit that calculates the weight, the own vehicle speed information, the first weight, and the second weight. It provides a vehicle collision warning device including a risk analysis unit and a warning processing unit that generates a warning control signal according to the result of the collision risk analysis.

In another aspect, the present invention provides an image acquisition step of acquiring image information inside a vehicle and image information outside a vehicle, a front vehicle information acquisition step of acquiring speed information of a front vehicle and distance information from a vehicle in front, and the vehicle interior image information. A first weight calculation step for calculating a first weight based on the first weight and a second weight for calculating weather condition information or road surface condition information based on external image information of the vehicle, and calculating a second weight according to the weather condition information or road surface condition information. Collision risk analysis step and collision risk analysis result that analyzes the risk of collision with the vehicle in front using one or more of the information acquired by the calculation step and the front vehicle information acquisition step, the own vehicle speed information, the first weight and the second weight According to the present invention, a vehicle collision warning method including a warning processing step of generating a warning control signal is provided.

In another aspect, the present invention provides a radar sensor that acquires one or more cameras for capturing an image inside a vehicle and an image outside the vehicle, speed information of a vehicle in front, and distance information from a vehicle in front, and information received from the camera and radar sensor. A vehicle collision warning device that analyzes a vehicle collision risk based on the vehicle collision risk and generates a warning control signal, wherein the vehicle collision warning device acquires image information from one or more cameras and an image acquisition unit that acquires information of the vehicle in front from the radar sensor. A first weight calculator that calculates a first weight based on the front vehicle information acquisition unit and the image information inside the vehicle, and calculates weather condition information or road surface condition information based on the image information outside the vehicle, and weather condition information or road surface condition information The risk of collision with the vehicle in front is reduced by using at least one of information obtained by the second weight calculation unit and the front vehicle information acquisition unit, which calculates the second weight according to, the own vehicle speed information, the first weight, and the second weight. It provides a vehicle collision warning system comprising a collision risk analysis unit to analyze and a warning processing unit for generating a warning control signal according to the collision risk analysis result.

As described above, according to the present invention, in the vehicle collision warning system, an effect of determining whether a collision warning has occurred by comprehensively considering a vehicle external situation and a driver's driving concentration situation is provided.

In addition, in calculating the predicted collision time, it provides an effect of calculating an accurate predicted collision time by additionally taking into account information on external conditions of the vehicle and information on changes in the driver's condition.

In addition, a vehicle collision warning method and apparatus with low cost and high efficiency are provided by calculating an accurate collision predicted time using a simplified algorithm.

1 is a view showing the configuration of a vehicle collision warning device according to an embodiment of the present invention.
2 is a diagram illustrating an operation of a first weight calculation unit according to another embodiment of the present invention.
3 is a diagram illustrating an operation of a first weight calculation unit according to another embodiment of the present invention.
4 is a view for explaining an operation of calculating weather condition information based on road surface information according to another embodiment of the present invention.
5 is a view for explaining an operation of calculating weather condition information based on raindrop information of a windshield according to another embodiment of the present invention.
6 is a flowchart illustrating an operation of a collision risk analysis unit based on an expected stopping distance according to another embodiment of the present invention.
7 is a flowchart illustrating an operation of a collision risk analysis unit based on an expected collision time according to another embodiment of the present invention.
8 is a flowchart illustrating a vehicle collision warning method according to another embodiment of the present invention.
9 is a block diagram showing a vehicle collision warning system according to another embodiment of the present invention.
10 is a diagram for explaining an effect when the present invention is applied.

The present invention discloses a vehicle collision warning apparatus, a vehicle collision warning method, and a vehicle collision warning system.

Hereinafter, some embodiments of the present invention will be described in detail through exemplary drawings. In describing the constituent elements of the present invention, terms such as first, second, A, B, (a), and (b) may be used. These terms are for distinguishing the constituent element from other constituent elements, and the nature, order, or order of the constituent element is not limited by the term. When a component is described as being "connected", "coupled" or "connected" to another component, the component may be directly connected or connected to that other component, but another component between each component It will be understood that elements may be “connected”, “coupled” or “connected”.

1 is a view showing the configuration of a vehicle collision warning device according to an embodiment of the present invention.

Referring to FIG. 1, the present invention provides an image acquisition unit 110 for acquiring image information inside a vehicle and image information outside a vehicle, and a front vehicle information acquisition unit 120 acquiring speed information of a front vehicle and distance information from a front vehicle. ) And a first weight calculation unit 130 that calculates a first weight based on the image information inside the vehicle and the weather condition information or road surface condition information based on the image information outside the vehicle, and the weather condition information or the road surface condition information Therefore, collision with the front vehicle by using at least one of information obtained by the second weight calculation unit 140 for calculating the second weight and the front vehicle information acquisition unit, the own vehicle speed information, the first weight, and the second weight. It provides a vehicle collision warning apparatus 100 including a collision risk analysis unit 150 for analyzing the risk and a warning processing unit 160 for generating a warning control signal according to the result of the collision risk analysis.

The image acquisition unit 110 may receive image information inside the vehicle or outside the vehicle from an image device configured in the vehicle. The imaging device may mean a camera that can be installed and operated in a vehicle. For example, the imaging device may be installed inside the vehicle to take a picture of the front of the vehicle, and may take a picture of the inside of the vehicle. In addition, the imaging device may photograph the front of the vehicle or the interior of the vehicle with one camera, and a plurality of camera devices may photograph the exterior of the vehicle and the interior of the vehicle, respectively.

Specifically, the image information inside the vehicle may be image information photographed by the above-described camera device. For example, the image information inside the vehicle may include one or more of information on a driver's face direction, gaze information, and posture information. That is, the image captured by the camera includes the driver, and may include information on the driver's face direction or information on the driver's gaze direction. In addition, the image information inside the vehicle may include the driver's posture information.

The image information outside the vehicle may be generated by an imaging device such as a camera that may be installed inside or outside the vehicle. For example, the image information outside the vehicle may include an image photographing a vehicle in front or an image photographing a road surface in a direction in which the vehicle travels.

The front vehicle information acquisition unit 120 may acquire information on a vehicle running or stopping in front of the own vehicle. For example, the front vehicle information acquisition unit may receive information such as a speed and a position of a vehicle in front generated using a sensor installed in a vehicle such as an infrared sensor or a radar or ultrasonic sensor.

The first weight calculation unit 130 may calculate a first weight used to calculate the estimated stopping distance of the vehicle based on the above-described image information inside the vehicle.

The second weight calculation unit 140 may calculate a second weight used to calculate the estimated stopping distance of the vehicle based on the above-described vehicle external image information.

Operations of the first weight and the second weight will be described in detail below with reference to the drawings.

The collision risk analysis unit 150 comprehensively analyzes the information obtained from the front vehicle information acquisition unit 120 and the weight information calculated by the first weight calculation unit 130 and the second weight calculation unit 140 You can analyze the risk of collision with For example, the collision risk analysis unit 150 may analyze the collision risk of the vehicle by comparing and analyzing the estimated stopping distance and the distance to the vehicle ahead. Alternatively, the collision risk analysis unit 150 may analyze a collision risk with a vehicle in front by calculating an expected collision time. In addition, the collision risk analysis unit 150 may analyze and determine the collision risk in various ways based on the relationship between the distance and the speed with the vehicle ahead and weight information.

When it is determined that there is a risk of collision, the warning processing unit 160 may generate a warning control signal capable of notifying the driver of the danger. For example, the warning control signal may generate a warning control signal that can be recognized by a driver using one or more of visual, auditory and tactile senses. In addition to this, the warning control signal is a signal that controls whether or not a warning signal is generated to enable the driver to recognize a danger, and there is no limitation on the method.

2 is a diagram illustrating an operation of a first weight calculation unit according to another embodiment of the present invention.

The first weight calculation unit according to another embodiment of the present invention may change the first weight according to time information in which the driver's face direction information or gaze information deviates from the vehicle traveling direction by a predetermined angle or more.

Referring to FIG. 2, the first weight calculator may calculate a first weight related to a driver's driving concentration. The estimated stopping distance of the vehicle can be calculated as the sum of the Gongju distance and the braking distance, and the Gongju distance means the time until the driver recognizes and operates the vehicle when a danger occurs. That is, the Gongju distance may vary depending on the concentration and reaction time such as the driver's forward gaze.

Accordingly, in the present invention, in order to calculate the predicted collision distance by reflecting the driver's concentration, the first weight according to the driver's concentration may be set and changed.

For example, the first weight calculation unit calculates the angle 201 formed between the driving direction of the vehicle and the driver's face direction based on the driver's face direction information or gaze information that may be included in the image information inside the vehicle, and the corresponding angle is When it is more than a preset reference value, it may be determined that the driver's attention is dispersed. Meanwhile, the first weight calculator may count a duration when the driver's attention is dispersed and may change a value of the first weight according to the counting time.

The first weight calculator may increase the first weight when time information increases. As an example, the first weight value may be set by a table corresponding to the aforementioned counting time. As another example, the first weight value may be set to increase in proportion to the counting time. That is, the default value of the first weight may be set to 1, and as the counting time increases, the first weight value may be increased at a preset ratio.

3 is a diagram illustrating an operation of a first weight calculation unit according to another embodiment of the present invention.

The first weight calculation unit according to another embodiment of the present invention may detect an arm position based on posture information and change the first weight when the arm position exists at a preset position for a predetermined time or longer.

Referring to FIG. 3, the first weight calculator may calculate a first weight based on the driver's posture information that may be included in the image information inside the vehicle. For example, the driver's posture information may include the driver's arm position information 301, and if it is determined that the driver's arm position 301 is formed on the face side for a predetermined time, the first weight may be changed. That is, in the case of making a call while the driver is driving, the driver's arm position 301 is formed on the face side. This may be transmitted to the first weight determination unit through image information inside the vehicle obtained by the imaging device.

In addition, the first weight may be changed even when a situation in which the driver's arm position is separated by a predetermined distance from the steering wheel continues. For example, when the driver moves both arms off the steering wheel while driving and performs other tasks, the first weight calculator may detect this and change the first weight.

For example, the first weight value may be changed so as to be proportional to the duration time that the position of the driver's arm is formed at a specific position. For example, it may be set to increase in proportion to the duration time.

The first weight calculator described above for example may calculate the first weight by comprehensively determining the driver's posture information, gaze information, and face direction information.

That is, the first weight calculator may change the first weight when the driver is making a phone call in a situation where the driver's gaze is spaced apart from the driving direction of the vehicle by a predetermined angle or more. In this case, the first weight calculation unit may calculate the first weight so as to be distinguished from a case in which the driver is performing only a phone call. That is, the first weight can be changed to a higher value.

Meanwhile, the vehicle external image information acquired by the image acquisition unit may include at least one of road surface brightness information, road surface color distribution information, and raindrop information formed on a windshield. The image information outside the vehicle includes image information acquired by an imaging device installed inside or outside the vehicle, and the image information may include road surface information or a windshield image.

Accordingly, the vehicle collision warning apparatus of the present invention may determine a road surface condition or a weather condition based on image information outside the vehicle, and determine a collision risk of a vehicle in consideration of the road surface condition or the weather condition.

4 is a view for explaining an operation of calculating weather condition information based on road surface information according to another embodiment of the present invention.

The second weight calculation unit according to another embodiment of the present invention calculates weather condition information of a snowfall condition or a rainfall condition based on at least one of road surface brightness information, road surface color distribution information, and raindrop information, and responds to the weather condition information. The second weight to be used may be calculated.

Referring to FIG. 4, the second weight calculator may determine a weather condition using image information outside the vehicle.

For example, the image information outside the vehicle may include road surface brightness information and/or road surface color distribution information.

The second weight calculator may determine whether the road surface is covered with snow based on the road surface brightness information and/or the road surface color distribution information. In addition, the image information outside the vehicle may further include lane information, and it may more accurately determine whether the road surface is snowed, including lane information.

For example, the snow regions 401 to 406 may represent brightness information distinguished from the surrounding road surface. In addition, the snow regions 401 to 406 may include color information that is distinguished from the surrounding road surface. Accordingly, the second weight calculation unit may determine a weather condition such as a snowfall condition by determining the snow regions 401 to 406 having color or brightness information distinguished from the surroundings in the image information outside the vehicle.

As another example, when the second weight calculation unit further includes lane information, it determines whether the driving path is a snow cover area (402, 403, 405, 406) of the driving path in which the vehicle is traveling among the snow cover areas 401 to 406. You can also judge.

5 is a view for explaining an operation of calculating weather condition information based on raindrop information of a windshield according to another embodiment of the present invention.

In the case of raining as shown in FIG. 5, the second weight calculation unit may determine the rainfall situation by checking raindrop information of the windshield. Referring to FIG. 5, in the windshield image information, areas 501 to 510 to be blurred by raindrops are determined, and when the areas to be blurred (501 to 510) are present, it will be recognized as a rainy situation. I can.

For example, the areas 501 to 510 that are blurred by raindrops may be recognized as raindrops, and the degree of rainfall may be determined according to the number of recognized raindrops. That is, as the number of raindrops increases, it can be determined that there is more rainfall.

As shown in FIGS. 4 and 5, the second weight calculator may determine a weather condition based on image information outside the vehicle.

Meanwhile, the second weight calculator may determine a road surface condition based on image information outside the vehicle. That is, the second weight calculation unit calculates road surface condition information including the degree of slipping of the road surface based on at least one of road surface brightness information, road surface color distribution information, and raindrop information, and calculates a second weight corresponding to the road surface condition information. can do.

For example, as shown in FIGS. 4 and 5, a snow cover area on a road surface may be recognized using image information outside the vehicle, and a rainfall situation may be recognized. Through this, the second weight calculator may obtain information on the degree of slipping of the road surface. For example, when the number of raindrops formed on the windshield increases, it may be determined that the degree of slipping increases, and when the snow cover area of the road surface increases, the degree of slipping may also be determined to increase.

In addition, the second weight calculator may further receive a signal indicating whether the wiper is operating, and may calculate information on a weather condition or a road surface condition. That is, when the wiper operates, it is possible to recognize that there is a rainfall or snowfall situation, and the amount of rainfall or snowfall may be predicted based on the information on the wiper operation period to predict the degree of slipping of the road surface. The degree of slippage, which is changed according to the snow area or rainfall, can also be checked by mapping of a table set in advance.

The second weight calculator may calculate a second weight based on at least one of the above-described weather condition information and road surface condition information.

For example, when it is determined that the weather condition is a rainfall or snowfall condition, the second weight calculator may increase a second weight value related to the calculation of the braking distance of the vehicle. This is because the braking distance may change as the probability of the vehicle slipping increases in a rainy or snowy situation.

As another example, the second weight calculator may change the second weight value according to the road surface condition. That is, the second weight value may be differentially changed according to the degree of slipping of the road surface calculated by the change in the snow cover area of the road surface or the degree of raindrops on the windshield. As an example, when the snow cover area of the road surface increases, the second weight value may be increased by setting an increase width larger than that of a rainfall situation.

As another example, the second weight calculation unit may calculate the second weight by comprehensively considering the weather condition and the road surface condition. For example, there may be cases where there is no snowfall on the road surface in a snowfall situation, and there may be cases where there is snowfall. By dividing such a case, the second weight change may be performed in consideration of the weather conditions and the road surface conditions, respectively.

As described above, the vehicle collision warning apparatus of the present invention may apply first and second weights in calculating the estimated stopping distance of the vehicle based on image information inside or outside the vehicle. In addition, by calculating the first and second weights by the above-described method, it is possible to calculate an accurate expected stopping distance suitable for each situation.

Hereinafter, an operation of analyzing a collision risk based on the calculated first and second weight information and front vehicle information will be described with reference to the drawings.

6 is a flowchart illustrating an operation of a collision risk analysis unit based on an expected stopping distance according to another embodiment of the present invention.

The collision risk analysis unit according to another embodiment of the present invention may analyze that a collision risk exists when the estimated stopping distance of the vehicle is greater than the distance to the front vehicle.

Referring to FIG. 6, the collision risk analysis unit may calculate an estimated vehicle stopping distance (S610). The estimated stopping distance of the vehicle can be determined by the sum of the princess distance and the braking distance. As an example, the princess distance refers to the travel distance of the vehicle until the driver of the vehicle detects a danger ahead and operates the brake to start braking. In addition, the braking distance refers to the distance the vehicle travels until the vehicle actually stops the vehicle by receiving the braking signal. Accordingly, the estimated stopping distance of the vehicle may mean a distance that the vehicle proceeds until a forward hazard occurs and the vehicle actually stops.

In calculating the predicted braking distance of the vehicle, the collision risk analysis unit may use the aforementioned first weight and second weight. Therefore, the estimated stopping distance of the vehicle calculated by the collision risk analysis unit of the present invention may be calculated by Equation 1 below.

[Equation 1]

Estimated stopping distance = 1st weight x Princess distance + 2nd weight x Braking distance

In Equation 1, the first weight varies according to the driver's driving concentration, and may have a value of 1 or more. In addition, the second weight is variable according to the road surface or weather conditions, and may have a value of 1 or more. Accordingly, the expected stopping distance may increase when the driver's driving concentration decreases and the weather condition or the road surface condition worsens.

Thereafter, the collision risk analysis unit may compare the distance information of the vehicle in front of the vehicle in front and the calculated vehicle estimated stopping distance (S620). For example, when the distance to the vehicle in front is smaller than the expected stopping distance, it may be determined that there is a risk of collision (S630). As another example, when the distance to the vehicle in front is greater than the expected stopping distance, it is determined that the collision risk is low or not, and the estimated stopping distance of the vehicle may be calculated again.

The collision risk analysis unit may determine a more accurate collision probability by determining the collision risk in consideration of the driver's driving concentration and the weather or road conditions outside the vehicle by performing the above operation.

7 is a flowchart illustrating an operation of a collision risk analysis unit based on an expected collision time according to another embodiment of the present invention.

The collision risk analysis unit according to another embodiment of the present invention calculates a collision predicted time (TTC) by applying a first weight and a second weight, and analyzes that a collision risk exists when the collision predicted time is less than a preset reference value. can do.

Specifically, the collision risk analysis unit may calculate the expected stopping distance based on the first weight and the second weight calculated by the first weight calculation unit and the second weight calculation unit (S720). The expected stopping distance can be calculated by Equation 1 above.

The collision risk analysis unit calculates an expected collision time based on the estimated stopping distance and information obtained from the front vehicle information acquisition unit (S730). The expected collision time may be determined by Equation 2 below.

[Equation 2]

Expected collision time (TTC) = (position of the preceding vehicle-position of the own vehicle-stopping distance)/(speed of the own vehicle-speed of the preceding vehicle)

Position of the preceding vehicle-The position of the own vehicle may be determined by the distance to the vehicle in front, and the stopping distance may be determined by applying the first and second weights according to Equation (1). The speed of the host vehicle is obtained from a speed sensor, and the speed of the preceding vehicle may be confirmed by information obtained from the front vehicle information acquisition unit.

Accordingly, the collision risk analysis unit may receive the speed information of the own vehicle and calculate the collision predicted time according to Equation (2).

Thereafter, the collision risk analysis unit compares and determines the calculated collision predicted time and a preset reference value (S740). For example, when the reference value is set to 10 seconds and the collision predicted time is 20 seconds, it may be determined that there is no risk of collision.

If the predicted collision time is calculated as 5 seconds, it may be determined that there is a collision risk (S750).

Through this, the collision risk analysis unit may determine the collision risk in consideration of the driver's concentration and road surface conditions or weather conditions, thereby providing a more accurate collision risk warning.

The warning processing unit may generate a warning control signal that warns the driver of a dangerous situation through one or more senses of sight, hearing, and touch. Alternatively, the warning device can be controlled to generate a warning signal.

Hereinafter, a vehicle collision warning method according to another embodiment of the present invention described above will be briefly described again with reference to FIGS. 1 to 7.

8 is a flowchart illustrating a vehicle collision warning method according to another embodiment of the present invention.

A vehicle collision warning method according to another embodiment of the present invention includes an image acquisition step of acquiring image information inside a vehicle and image information outside a vehicle, and a front vehicle information acquisition step of acquiring speed information of a front vehicle and distance information from a front vehicle. And a first weight calculation step of calculating a first weight based on the image information inside the vehicle and the weather condition information or road surface condition information based on the image information outside the vehicle, and a second weight according to the weather condition information or the road surface condition information. Collision risk analysis that analyzes the risk of collision with the vehicle in front using one or more of the information obtained by the second weight calculation step and the front vehicle information acquisition step, the own vehicle speed information, the first weight, and the second weight. It may include a warning processing step of generating a warning control signal according to the step and the collision risk analysis result.

Referring to FIG. 8, the vehicle collision warning method includes an image acquisition step (S800). As described above, in the image acquisition step, image information inside the vehicle and image information outside the vehicle may be acquired. The image information inside the vehicle and the image information outside the vehicle may be obtained from an imaging device such as a camera that may be installed in the vehicle.

The vehicle collision warning method may include a front vehicle information acquisition step of acquiring speed information of a front vehicle and distance information with a front vehicle (S810). Front vehicle information can be obtained from devices such as radar, infrared sensors, or ultrasonic sensors.

In addition, the vehicle collision warning method includes a first weight calculation step of calculating a first weight based on the image information inside the vehicle (S820). As described with reference to FIGS. 2 and 3, in the first weight calculation step, the angle formed by the driving direction of the vehicle and the driver's face direction is calculated based on the driver's face direction information or gaze information that may be included in the image information inside the vehicle. And, when the angle is greater than or equal to a preset reference value, it may be determined that the driver's attention is dispersed. Meanwhile, the first weight calculator may count a duration when the driver's attention is dispersed and may change a value of the first weight according to the counting time. Also, the first weight calculator may calculate the first weight based on the driver's posture information that may be included in the image information inside the vehicle.

Meanwhile, the vehicle collision warning method may further include a second weight calculation step of calculating weather condition information or road surface condition information based on image information outside the vehicle, and calculating a second weight according to the weather condition information or road surface condition information. Yes (S830). For example, weather conditions and/or road condition information may be determined using road surface brightness information, road surface color information, and windshield image information, and a second weight may be calculated according to the determined result.

The vehicle collision warning method may further include a collision risk analysis step (S840). Specifically, in the collision risk analysis step, the collision risk with the front vehicle may be analyzed using one or more of information obtained by the front vehicle information acquisition step, the own vehicle speed information, and the first weight and the second weight. For example, the collision risk may be analyzed using the estimated stopping distance reflecting the first weight and the second weight and the distance to the vehicle ahead. As another example, collision risk may be analyzed based on a result of calculating an expected collision time and comparing the calculated collision predicted time with a reference value.

In the warning processing step, a warning control signal may be generated according to the collision risk analysis result (S850). That is, if it is analyzed that there is a risk of collision, it is possible to control the occurrence of a warning signal. The warning signal is a signal that warns the driver of danger through visual, audible or tactile sense, and there is no restriction on the method.

9 is a block diagram showing a vehicle collision warning system according to another embodiment of the present invention.

A vehicle collision warning system according to another embodiment of the present invention includes at least one camera 910 for capturing an image inside a vehicle and an image outside the vehicle, and a radar sensor 920 for obtaining speed information of a vehicle in front and distance information of a vehicle in front. ), and a vehicle collision warning device 100 for generating a warning control signal by analyzing a vehicle collision risk based on information received from a camera and a radar sensor, wherein the vehicle collision warning device 100 includes image information from one or more cameras. The image acquisition unit 110 for acquiring and the front vehicle information acquisition unit 120 for acquiring information on the vehicle in front of the radar sensor, and the first weight calculation unit 130 for calculating a first weight based on the image information inside the vehicle. And a second weight calculation unit 140 and a front vehicle information acquisition unit that calculates weather condition information or road surface condition information based on the vehicle external image information, and calculates a second weight according to the weather condition information or road surface condition information. A collision risk analysis unit 150 that analyzes the risk of a collision with a vehicle in front using at least one of the acquired information, the own vehicle speed information, the first weight and the second weight, and generates a warning control signal according to the result of the collision risk analysis. It may include a warning processing unit 160.

As described above, according to the present invention, in the vehicle collision warning system, an effect of determining whether a collision warning has occurred by comprehensively considering a vehicle external situation and a driver's driving concentration situation is provided.

10 is a diagram for explaining an effect when the present invention is applied.

FIG. 10A is a diagram illustrating an estimated stopping distance of a vehicle when the first weight and the second weight are not considered. FIG. 10B is a diagram illustrating an estimated stopping distance of the vehicle when the first weight and the second weight are considered.

Referring to FIG. 10, when a first weight according to a driver's driving concentration and a second weight in consideration of weather or road conditions are not applied, the estimated stopping distance of the vehicle may be calculated as D1. Accordingly, in this case, it is determined that the distance to the vehicle in front is greater than or equal to D1, so that the vehicle collision warning device may determine that there is no risk of collision.

However, the vehicle collision warning apparatus according to the present invention may calculate the expected stopping distance as D2 as shown in FIG. 10B by considering the first weight and the second weight. Therefore, even when analyzing the risk of collision with vehicles in front separated by the same distance, a more accurate analysis is possible.

For example, when the driver is not looking ahead, a warning is not provided by calculating the estimated stopping distance as D1 as shown in FIG. 10(a) in the related art. However, in the case of the present invention, by calculating the estimated stopping distance D2 to which the first weight is applied based on the driver's face direction or gaze direction, the risk of collision is determined and a warning is provided.

Even when the second weight according to the road surface or weather conditions is calculated and applied, the above-described effect may be provided.

As described above, in calculating the predicted collision time, according to the present invention, it is possible to calculate an accurate predicted collision time by additionally considering information on external conditions of the vehicle and information on the driver's attitude.

In addition, a vehicle collision warning method and apparatus with low cost and high efficiency are provided by calculating an accurate collision predicted time using a simplified algorithm.

In the above, even if all the constituent elements constituting the embodiments of the present invention have been described as being combined into one or operating in combination, the present invention is not necessarily limited to these embodiments. That is, within the scope of the object of the present invention, all the constituent elements may be selectively combined and operated in one or more. The above description is merely illustrative of the technical idea of the present invention, and those of ordinary skill in the art to which the present invention pertains will be able to make various modifications and variations without departing from the essential characteristics of the present invention. The scope of protection of the present invention should be construed by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

Claims (14)

An image acquisition unit for acquiring image information inside the vehicle and image information outside the vehicle including one or more of information on a driver's face direction, gaze information, and posture information;
A front vehicle information acquisition unit that acquires speed information of a front vehicle and distance information from the front vehicle;
A first weight calculator configured to calculate a first weight based on the image information inside the vehicle;
A second weight calculator configured to calculate weather condition information or road surface condition information based on the image information outside the vehicle, and calculate a second weight according to the weather condition information or the road surface condition information;
A collision risk analysis unit for analyzing a collision risk with the front vehicle by using at least one of information obtained by the front vehicle information acquisition unit, the own vehicle speed information, and the first weight and the second weight; And
Includes a warning processing unit for generating a warning control signal according to the collision risk analysis result,
The collision risk analysis unit,
When the estimated stopping distance of the vehicle calculated by the sum of the value obtained by multiplying the first weight by the princess distance and the value obtained by multiplying the braking distance by the second weight is greater than the distance to the vehicle in front, it is analyzed that there is a risk of collision,
The first weight is,
A vehicle collision warning device that is changed by combining time information in which the face direction information and the gaze information deviate from a vehicle traveling direction by a predetermined angle or more and time information during which the posture information lasts in a predetermined posture. delete delete The method of claim 1,
The first weight calculation unit,
When the time information increases, the first weight is increased. The method of claim 1,
The first weight calculation unit,
Based on the posture information, the arm position is detected and the first weight is changed when the arm position is present at a preset position for a predetermined time or longer. The method of claim 1,
The vehicle external image information,
A vehicle collision warning device comprising at least one of information on brightness of a road surface, information on color distribution of a road surface, and information on raindrops formed on a windshield. The method of claim 6,
The second weight calculation unit,
Computing the weather condition information of a snowfall condition or a rainfall condition based on one or more of the road surface brightness information, the road surface color distribution information, and the raindrop information, and calculating the second weight corresponding to the weather condition information. Vehicle crash warning device, characterized in that. The method of claim 6,
The second weight calculation unit,
Calculating the road surface condition information including a degree of slipping of the road surface based on one or more of the road surface brightness information, the road surface color distribution information, and the raindrop information, and calculating the second weight corresponding to the road surface condition information. Vehicle crash warning device, characterized in that. The method of claim 1,
The second weight calculation unit,
A vehicle collision warning device, characterized in that for calculating the weather condition information or the road surface condition information by further receiving a wiper operation signal. delete delete The method of claim 1,
The collision risk analysis unit,
A vehicle collision warning device, characterized in that for calculating a collision predicted time (TTC) by applying the first weight and the second weight, and analyzing that a collision risk exists when the collision predicted time is less than or equal to a preset reference value. An image acquisition step of acquiring image information inside the vehicle and image information outside the vehicle including one or more of information on a driver's face direction, gaze information, and posture information;
A front vehicle information acquisition step of obtaining speed information of a front vehicle and distance information from the front vehicle;
A first weight calculation step of calculating a first weight based on the image information inside the vehicle;
A second weight calculation step of calculating weather condition information or road surface condition information based on the vehicle external image information, and calculating a second weight according to the weather condition information or the road surface condition information;
A collision risk analysis step of analyzing a collision risk with the front vehicle using at least one of information obtained by the front vehicle information obtaining step, the own vehicle speed information, and the first weight and the second weight; And
Including a warning processing step of generating a warning control signal according to the collision risk analysis result,
The collision risk analysis step,
When the estimated stopping distance of the vehicle calculated by the sum of the value obtained by multiplying the first weight by the princess distance and the value obtained by multiplying the braking distance by the second weight is greater than the distance to the vehicle in front, it is analyzed that there is a risk of collision,
The first weight is,
A vehicle collision warning method in which the face direction information and the gaze information are changed by combining time information that deviates from a vehicle traveling direction by a predetermined angle or more and time information that the posture information lasts in a predetermined posture. At least one camera for capturing an image inside a vehicle and an image outside the vehicle including at least one of information on a driver's face direction, gaze information, and posture information;
A radar sensor that acquires speed information of a vehicle in front and distance information from the vehicle in front; And
A vehicle collision warning device for generating a warning control signal by analyzing a vehicle collision risk based on information received from the camera and the radar sensor,
The vehicle collision warning device may include an image acquisition unit that acquires image information from the one or more cameras;
A front vehicle information acquisition unit that obtains information on the front vehicle from the radar sensor;
A first weight calculator configured to calculate a first weight based on the image information inside the vehicle;
A second weight calculator configured to calculate weather condition information or road surface condition information based on the image information outside the vehicle, and calculate a second weight according to the weather condition information or the road surface condition information;
A collision risk analysis unit for analyzing a collision risk with the front vehicle by using at least one of information obtained by the front vehicle information acquisition unit, the own vehicle speed information, and the first weight and the second weight; And
Includes a warning processing unit for generating a warning control signal according to the collision risk analysis result,
The collision risk analysis unit,
When the estimated stopping distance of the vehicle calculated by the sum of the value obtained by multiplying the first weight by the princess distance and the value obtained by multiplying the braking distance by the second weight is greater than the distance to the vehicle in front, it is analyzed that there is a risk of collision,
The first weight is,
A vehicle collision warning system that is changed by combining time information in which the face direction information and the gaze information deviate from a vehicle traveling direction by a predetermined angle or more and time information during which the posture information lasts in a predetermined posture.

Images