KR20170040632A - Control Method and Apparatus of Vehicle collision case - Google Patents

Abstract

According to one embodiment of the present invention, a control apparatus in case a risk of a vehicle crash occurs includes: a dangerous situation determiner configured to determine whether a dangerous situation occurs when a vehicle is driven; a target vehicle tracker configured to search for a target vehicle likely to cause a dangerous situation and performing a tracking function for the target vehicle; and a controller configured to calculate a crash timing with respect to the target vehicle and determine whether a crash is likely to occur. Accordingly, the present invention is able to reduce a probability of a wrong warning and control since the present invention focuses on verifying the wrong recognition of a target in a warning and control situation.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention [0002] The present invention relates to a control device and method for controlling a collision hazard, and more particularly, to a control device and a control method for a collision hazard using a front camera alarm system.

Generally, a vehicle alarm system includes a camera attached to the front of an automobile and an alarm output unit connected to the camera to output a warning sound. Here, the camera is a CCD camera, and it can detect whether or not the vehicle has departed from the lane as it acquires image information in front of the road in real time. The alarm output unit analyzes the road image information output by the camera in real time and outputs an alarm signal to inform the driver of the emergency situation when the vehicle leaves the lane.

Such a front camera-based alarm system can be largely composed of two parts, a vehicle detection and a collision alarm.

In the conventional case, it takes the same time to perform two functions, i.e., vehicle detection and collision warning, for each frame captured by the camera. That is, the alarm system processes the two functions uniformly at every moment by applying the same time ratio to the image.

1 is a control flowchart for explaining an operation method of a conventional alarm system. As shown in the figure, the collision of the vehicle is determined in the same manner under any circumstances.

First, an alarm system such as a forward camera detects a vehicle candidate having a possibility of a collision among vehicles picked up ahead (110).

Then, at least one candidate vehicle is determined (120).

The candidate vehicle may be a charter located in the front or side lane including the front of the vehicle in the current driving direction, the front side in the diagonal direction, and may be determined to be a multiple of the position of the vehicle in operation or the traffic volume of the nearby road.

A target vehicle having a high possibility of colliding with the user's vehicle among at least one candidate vehicle is selected (130).

The target vehicle can be selected in consideration of the direction, the distance, the speed of the vehicle, and the like, with the vehicle most likely to collide with the current vehicle.

Thereafter, the alarm system calculates a time to collision (TTC) with the selected target vehicle (140) and determines whether a collision with the target vehicle is possible (150).

If the possibility of collision of the vehicle is high, the warning system alerts the driver of the emergency situation.

On the other hand, in the actual collision situation, the accuracy of the collision warning function is given priority over the vehicle detection function, but it consumes more processor resources than necessary for detecting the vehicle, making it difficult to improve and concentrate the collision warning function.

Therefore, it is necessary to adaptively operate the alarm system according to traffic and vehicle conditions.

An embodiment of the present invention provides a vehicle collision risk control device and a control method for performing a vehicle collision detection function and a collision warning function by flexibly controlling the vehicle in a safe running situation and a collision risk situation.

In addition, one embodiment of the present invention provides a vehicle collision risk control device and a control method for increasing the weight of the front vehicle detection function in a safe running situation and improving the performance of a collision warning in a collision risk situation.

The vehicle collision risk control device, which is an embodiment of the present invention, includes a risk situation determination unit for determining whether the vehicle is in a dangerous state when driving, a target detecting unit for searching a target vehicle capable of causing a dangerous situation, And a controller for determining a collision by calculating a collision time with respect to the target vehicle.

The target vehicle tracking unit may select the target vehicle by skipping the detection of the target vehicle candidate and searching the existing target vehicle and the existing target vehicle when the dangerous situation determining unit determines that the dangerous situation exists.

The target vehicle tracking unit may perform the additional verification of the target vehicle using at least one of the svm classifier and the classification template image expansion for the selected target vehicle.

The target vehicle tracking unit may measure the distance from the target vehicle using an optical-based tracking and perspective conversion method.

The risk situation determination unit may determine whether the collision time of the constant-velocity model is less than a predetermined time, whether the driver operates the vehicle, whether the traveling direction of the vehicle is toward the front vehicle, and whether the lamp of the front vehicle is turned on.

In this case, the risk situation determination unit may verify the collision time.

A method for controlling a collision risk of a vehicle according to another embodiment of the present invention includes the steps of: determining whether the vehicle is in a dangerous state during driving; searching for a target vehicle capable of causing a dangerous situation and performing a tracking function on the target vehicle; , And calculating a collision time for the target vehicle to determine whether or not a collision occurs.

According to an embodiment of the present invention, there is provided a vehicle collision risk control apparatus and method for controlling a vehicle detecting function and a collision warning function flexibly in a safe running situation and a collision risk situation.

In addition, an embodiment of the present invention provides a vehicle collision risk control device and a control method for increasing the weight of a front vehicle detection function in a safe running situation and improving a collision warning performance in a collision risk situation.

Through this, it is possible to concentrate on the false recognition verification of the target in the alarm and control situation, thereby reducing the probability of false alarm and false control.

1 is a control flowchart for explaining an operation method of a conventional alarm system.
2 is a control block diagram of a vehicle collision risk control device according to an embodiment of the present invention.
FIG. 3 is a view for explaining the performance of a vehicle detection function and a collision warning function according to an embodiment of the present invention.
4 is a control flowchart for explaining a control method of a vehicle collision risk control method according to an embodiment of the present invention.
5 is a control flowchart for explaining a vehicle collision risk detection and a risk situation determination method according to the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In the following description of the embodiments of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present disclosure rather unclear.

The components shown in the embodiments of the present invention are shown separately to represent different characteristic functions and do not mean that each component is composed of separate hardware or software constituent units. That is, each constituent unit is included in each constituent unit for convenience of explanation, and at least two constituent units of the constituent units may be combined to form one constituent unit, or one constituent unit may be divided into a plurality of constituent units to perform a function. The integrated embodiments and separate embodiments of the components are also included within the scope of the present invention, unless they depart from the essence of the present invention.

In addition, some of the components are not essential components to perform essential functions in the present invention, but may be optional components only to improve performance. The present invention can be implemented only with components essential for realizing the essence of the present invention, except for the components used for the performance improvement, and can be implemented by only including the essential components except the optional components used for performance improvement Are also included in the scope of the present invention.

2 is a control block diagram of a vehicle collision risk control device according to an embodiment of the present invention.

As shown in the figure, the vehicle collision risk monitoring device according to the present embodiment includes a risk situation determination unit 210, a target vehicle tracking unit 220, and a control unit 230 for controlling them. A control device for a vehicle collision hazard may be implemented as an independent module included in a vehicle, an independent module included in the vehicle, or an independent module capable of detachably attaching to and detaching from a vehicle to set or check a collision risk situation. The vehicle collision hazard control device may further include a camera (not shown).

The dangerous situation determination unit 210 determines whether the vehicle is in a dangerous state when driving the vehicle, and determines whether the vehicle is in a dangerous state based on various factors.

The dangerous situation determination unit 210 determines whether or not the time to collision (TTC) of the constant-velocity model is less than a preset time, whether the driver is operating, whether the traveling direction of the vehicle is toward the front vehicle, It is possible to judge whether or not the vehicle is in a dangerous state.

Since the constant velocity model is more stable than the equivalent velocity model, the dangerous situation determination unit 210 can calculate the TTC using the constant velocity model.

In addition, the risk-situation determination unit 210 also determines whether the target vehicle and the current vehicle driver perform other operations such as steering, acceleration, or braking, and also uses whether the brake or emergency light of the preceding vehicle is turned on .

The dangerous situation determination unit 210 according to another embodiment of the present invention may further determine the dangerous situation in addition to the determination condition. For example, there may be an anomaly in the data for TTC calculation, specifically whether the verified TTC is abnormal, or whether the reliability of the data can be additionally verified.

In addition, the dangerous situation determination unit 210 may determine whether the external environment in which the current data is collected is in a bad condition due to rain, snow, or backlight. Based on the data on the various conditions and environments thus determined, it can be judged whether or not the risk situation is comprehensive.

FIG. 3 is a view for explaining the performance of a vehicle detection function and a collision warning function according to an embodiment of the present invention.

As shown in FIG. 3, when the dangerous situation determination unit 210 determines that the vehicle is in a safe running condition other than a dangerous situation, the control apparatus according to the present embodiment can provide more time and control to the vehicle detection function Logic is used.

In this case, as shown in Fig. 1, the control device can detect a vehicle candidate, select a target vehicle, and calculate a collision time to determine whether or not the vehicle is collided.

On the other hand, if the dangerous situation determination unit 210 determines that the vehicle is in a dangerous state other than the safe running state, the control unit controls the vehicle with a greater emphasis on the vehicle detection function and the collision warning function.

In this case, the controller may omit the step of detecting the candidate vehicle among the control methods that have been performed in order to lower the weight of the vehicle detection function. That is, the time taken to perform the vehicle detection function can be used in addition to the collision warning function.

The target vehicle tracking unit 220 searches for a target vehicle capable of causing a dangerous situation and performs a tracking function for the detected target vehicle.

As described above, if the dangerous situation determination unit 210 determines that the dangerous situation is a dangerous situation, the target vehicle tracking unit 220 skips candidate detection of the target vehicle and searches for an existing target vehicle and an existing target vehicle, Can be selected.

To this end, the target vehicle tracking unit 220 may detect only the peripheral region of the target vehicle that was located in the previous frame. In addition, the ADABOOST candidate detector can be used to search the periphery of the target vehicle. In this case, there is an advantage that the speed is faster than the conventional one.

In addition, the target vehicle tracking unit 220 may perform additional verification of the target vehicle using at least one of svm (Support Vector Machine) classifier and classification template image expansion for the selected target vehicle. This can reduce the probability of misrecognition in the target vehicle search and search.

In addition, in order to improve the distance accuracy between the target vehicle and the vehicle currently traveling, the target vehicle tracking unit 220 can increase the distance accuracy by applying the optical-based tracking method in the existing template-based tracking. In the case of mineral-based tracking, there is a strong advantage in partial change of the image.

 The target vehicle tracking unit 220 can measure the distance from the target vehicle using the perspective transformation method in the conventional AFFINE transformation. In this case, there is an advantage that the degree of freedom of image conversion is improved.

As described above, the control apparatus according to the present embodiment applies a variety of methods and recognition methods and applies a conversion method to lower the false-recognition probability and improve the distance accuracy, rather than the existing tracking and conversion methods, .

The control unit 230 calculates a collision time with respect to the target vehicle using the information of the target vehicle obtained by the target vehicle tracking unit 220 and determines whether or not the collision occurs. The control unit 230 may calculate the TTC by a known or new method and determine whether to collide.

4 is a control flowchart for explaining a control method of a vehicle collision risk control method according to an embodiment of the present invention. A method of controlling a collision risk of a vehicle according to the present invention will now be described with reference to FIG.

First, it is determined whether or not the vehicle is in a dangerous state when the vehicle is driven by the dangerous situation determination unit (410). The determination of the dangerous situation may be made based on whether or not the collision time of the constant-speed model is less than a preset time, whether the driver operates, whether the traveling direction of the vehicle is toward the forward vehicle, have.

If it is not determined that the vehicle is running in a dangerous state, that is, if it is determined that the vehicle is in a safe running state, the conventional control method as shown in FIG. 1 is performed. In this case, more time and control logic are used for the vehicle detection function among the vehicle detection function and the crash alarm function.

On the other hand, if it is determined that the vehicle is in a dangerous state during the driving of the vehicle, the control device skips the step of detecting the candidate vehicle among the control methods that have been performed, The vehicle is searched 420 and a tracking function for the target vehicle is performed 430.

When selecting the target vehicle and performing the tracking function for the target vehicle, the svm classifier and the classification template image enlargement, the optical-based tracking method, and the perspective transformation method can be used.

Then, the control unit of the control device calculates the collision time for the target vehicle (440) and determines whether a collision occurs (450).

5 is a control flowchart for explaining a vehicle collision risk detection and a risk situation determination method according to the present invention.

According to the present invention, an alarm system, such as a front camera, can detect a vehicle candidate having a possibility of collision among the vehicles picked up ahead (510).

At this time, the vehicle candidate in which there is a possibility of collision may be at least one or more vehicles, and may be a charger that is located in a forward lane or in a next lane including the front of the currently running vehicle, diagonal direction ahead, Depending on the traffic volume of the road or surrounding roads.

Then, it is determined whether or not the vehicle is in a dangerous state according to the vehicle candidate (520).

Based on various factors, it can be judged whether or not the current running vehicle is in a dangerous situation. For example, whether or not the time to collision (TTC) of the constant-velocity model is less than a predetermined time, whether the driver is operating, whether the traveling direction of the vehicle is toward the front vehicle, So that the risk of the vehicle can be determined.

As a result of the determination, if it is determined that the vehicle is not in a dangerous state, the process returns to step 510 to repeat the collision candidate detection process.

In this process, the target vehicle may be selected in consideration of the direction, the distance, or the speed of the vehicle with respect to the candidate vehicle having a high possibility of collision with the user vehicle, for example, have.

It is possible to detect only the peripheral region of the target vehicle positioned in the previous frame or to search the periphery of the target vehicle using the ADABOOST candidate detector in order to verify and enhance the collision object. Further verification may be performed on the selected target vehicle using at least one of svm (Support Vector Machine) classifier and classification template image enlargement.

In addition, in order to improve the distance accuracy between the target vehicle and the current driving vehicle, it is possible to increase the distance accuracy by applying the optical-based tracking method in the existing template-based tracking, It is also possible to measure the distance from the vehicle.

When tracking of the target is completed, the collision time for the target vehicle is calculated using the information of the target vehicle (540).

Once the collision time has been calculated, it may be determined 550 whether the risk situation is maintained or the risk situation is lifted.

If the risk situation is maintained, the collision target verification and tracking enhancement process in step 530 is performed. If it is determined that the risk situation is not the danger situation, the process returns to step 510 to repeat the collision candidate detection process.

As described above, the present invention provides a vehicle collision risk control device and a control method for performing the vehicle detection function and the collision warning function flexibly by adjusting the vehicle running condition and the collision risk situation.

The present invention also provides a vehicle collision risk control device and a control method for increasing the weight of a front vehicle detection function in a safe running situation and improving the performance of a collision warning in a collision risk situation.

In addition, an embodiment of the present invention provides a user interface that allows a user to select a function capable of automatically controlling a turn signal operation.

In the above-described embodiments, the methods are described on the basis of a flowchart as a series of steps or blocks, but the present invention is not limited to the order of steps, and some steps may occur in different orders or in a different order than the steps described above have. It will also be understood by those skilled in the art that the steps depicted in the flowchart illustrations are not exclusive and that other steps may be included or that one or more steps in the flowchart may be deleted without affecting the scope of the invention You will understand.

The above-described embodiments include examples of various aspects. While it is not possible to describe every possible combination for expressing various aspects, one of ordinary skill in the art will recognize that other combinations are possible. Accordingly, it is intended that the invention include all alternatives, modifications and variations that fall within the scope of the following claims.

Claims (9)

A dangerous situation judging unit for judging whether the vehicle is in a dangerous situation when the vehicle is traveling;
A target vehicle tracking unit for searching for a target vehicle capable of causing a dangerous situation and performing a tracking function for the target vehicle;
And a controller for calculating a collision time with respect to the target vehicle to determine whether or not a collision occurs. The method according to claim 1,
Wherein the target vehicle tracking unit selects the target vehicle by skipping candidate detection of the target vehicle and searching for an existing target vehicle and a vicinity of the existing target vehicle when it is determined that the dangerous situation determining unit is in a dangerous situation . 3. The method of claim 2,
Wherein the target vehicle tracing unit performs an additional verification of the target vehicle using at least one of an svm classifier and a classification template image enlargement for the selected target vehicle. The method according to claim 1,
Wherein the target vehicle tracking unit measures a distance to the target vehicle using an optical-based tracking and perspective conversion method. The method according to claim 1,
Wherein the risk situation determination unit determines whether the collision time of the constant-velocity model is less than or equal to a predetermined time, whether the driver operates the vehicle, whether the traveling direction of the vehicle is toward the front vehicle, and whether the lamp of the front vehicle is turned on . 6. The method of claim 5,
And the risk situation determination unit verifies the collision time. A control method for a vehicle collision hazard,
Determining whether the vehicle is in a dangerous condition when driving the vehicle;
Searching for a target vehicle capable of causing a dangerous situation and performing a tracking function for the target vehicle;
And calculating a collision time for the target vehicle to determine whether or not a collision occurs. 8. The method of claim 7,
The step of performing the tracking function for the target vehicle may include selecting the target vehicle by skipping candidate detection of the target vehicle and searching the existing target vehicle and the existing target vehicle around the target vehicle Lt; / RTI > 8. The method of claim 7,
The method of claim 1,
Whether or not the collision time of the constant-velocity model is shorter than a predetermined time, whether or not the driver operates, whether the traveling direction of the vehicle is toward the front vehicle, and whether the lamp of the front vehicle is turned on.

Images