KR20190053612A - Apparatus for tracking vehicle and operating method thereof - Google Patents

Abstract

According to the present invention, an apparatus for tracking a vehicle comprises: a radar transmitting a radar signal to a front vehicle, and receiving the reflected radar signal to generate first vehicle information with respect to the front vehicle; a camera generating second vehicle information by detecting an image of the front vehicle; and a front vehicle tracking device tracking the front vehicle based on the first vehicle information, the second vehicle information, and lane information. The front vehicle tracking device has sensor fusion logic for fusing the first vehicle information with the second vehicle information using the lane information and search logic for tracking the front vehicle in a curve road driving condition.

Description

[0001] APPARATUS FOR TRACKING VEHICLE AND OPERATING METHOD THEREOF [0002]

The present invention relates to a vehicle tracking apparatus and a method of operating the same.

In recent years, most vehicles have been equipped with a navigation system, which allows the driver to provide the destination and route guidance. In recent years, the user has also been able to project desired information to the windshield of the vehicle, Vehicles with a head-up display (HUD) are also on the market. Further, studies are being conducted to enable specific information to be displayed in the form of an augmented reality through the head-up display. Conventional researches related to laser and vision sensor fusion technologies of augmented reality head-up display devices are mainly focused on the recognition of forward vehicles. Studies related to the tracking of the front vehicle have been conducted to estimate the lane information around the front object and determine whether the front object is in the traveling direction of the host vehicle. In previous researches related to this, when judging whether the front object is in the lane of the host vehicle, it is possible to track the wrong object by causing the judgment of the logic (logic) when the lane is blurred or broken, There is a problem that is difficult to recognize the vehicle.

Registered Patent: 10-1644370, Registered Date: Jul. 26, 2016 Title: Object Detecting Apparatus and Its Operation Method. Registered Patent: 10-1742365, Registered: May 25, 2017 Title: Change in the behavior of autonomous vehicles based on the predictive behavior of other vehicles. Open Patent: 10-2015-0055181, Pub. Date: May 21, 2015 Title: Apparatus and method for displaying night vision information using head-up display.

It is an object of the present invention to provide a vehicle tracking apparatus that recognizes a front vehicle even when there is no lane and an operation method thereof.

A method of operating a vehicle tracking device according to an embodiment of the present invention includes: determining whether the host vehicle is driving immediately on the basis of lane information of the host vehicle; Calculating the distance between the coordinates of the target sensed by the radar and the coordinates of the targets sensed by the camera if the host vehicle is a straight run; Extracting coordinates of the camera corresponding to a first minimum distance, a second minimum distance longer than the first minimum distance, and a third minimum distance longer than the second minimum distance among the calculated distances; Calculating a relative angle between each of the extracted coordinates and a lateral or longitudinal coordinate within a lane of the host vehicle; And selecting one of the extracted coordinates as the output coordinates of the target using the calculated relative angle.

In the embodiment, if the host vehicle is not in the straight run, performing the front_dest_logic to select one of the camera coordinates corresponding to the one minimum distance and the coordinates of the radar .

In one embodiment, the step of performing the front_destination_logic logic comprises: if the curve ratio is greater than the threshold value of the road surface angle and the longitudinal coordinate of the radar is the maximum value of the longitudinal radar coordinate, Step < / RTI >

In the embodiment, if the curve ratio is not greater than the threshold of the road surface angle, or if the longitudinal coordinate of the radar is not the maximum value of the longitudinal radar coordinate, performing the middle_dest_ logic by the search algorithm can do.

In one embodiment, performing the middle_destination logic comprises: when the lateral coordinate of the radar is not zero, or when there is no output coordinate of the sensor fusion logic in the lane of the host vehicle, And selecting the output coordinates of the logic.

In the embodiment, the step of performing the middle_destination_logic logic may further include, when the lateral coordinates of the radar are zero and the output coordinates of the sensor fusion logic are present in the lane of the host vehicle, Determining whether the difference in the longitudinal coordinates of the camera is less than a predetermined threshold; And selecting the radar coordinate when the difference between the longitudinal coordinate of the radar and the longitudinal coordinate of the camera is less than the predetermined threshold value.

In one embodiment, the step of performing the middle_destination_logic logic comprises: when the difference between the longitudinal coordinate of the radar and the longitudinal coordinate of the camera is not less than a predetermined threshold, Determining whether the longitudinal radar coordinate is a maximum value; Determining whether the output coordinate of the sensor fusion logic is present in the lane of the host vehicle; And selecting the radar coordinate when the longitudinal coordinate of the radar is the maximum value of the longitudinal radar coordinate and the output coordinate of the sensor fusion logic is in the lane of the host vehicle.

In one embodiment, performing the middle_destination logic comprises: determining whether the longitudinal coordinate of the radar is greater than or equal to a maximum value of the longitudinal radar coordinate; Determining whether the output coordinate of the sensor fusion logic is present in the lane of the host vehicle; And when the longitudinal coordinate of the radar is greater than or equal to the maximum value of the longitudinal radar coordinates and there is an output coordinate of the sensor fusion logic in the lane of the host vehicle, the longitudinal coordinate is set as the longitudinal radar maximum value, Gt; 0 < / RTI >

In one embodiment, the step of performing the middle_destination_logic logic comprises: if the longitudinal coordinate of the radar is less than a maximum value of the longitudinal radar coordinate, or if the output coordinate of the sensor fusion logic is within the lane of the host vehicle Determining whether a difference between the lateral coordinate of the radar and the lateral coordinate of the camera is larger than the coordinates of the host vehicle, Determining whether the output coordinate of the sensor fusion logic is present in the lane of the host vehicle; And selecting the radar coordinate when the difference between the lateral coordinate of the radar and the lateral coordinate of the camera is larger than the coordinates of the host vehicle and the output coordinate of the sensor fusion logic is present in the lane of the host vehicle .

When the difference between the lateral coordinate of the radar and the lateral coordinate of the camera is not larger than the coordinates of the host vehicle or when there is no output coordinate of the sensor fusion logic in the lane of the host vehicle, Defense < RTI ID = 0.0 > logic. ≪ / RTI >

In one embodiment, the step of performing the Rear_Destination_logic logic may include: selecting one of the coordinates selected by the front_destination_logic, the coordinates selected by the middle_destination_ logic, and the radar coordinates as the output coordinates As shown in FIG.

A vehicle tracking apparatus according to an embodiment of the present invention includes: a radar that transmits a radar signal to a preceding vehicle and generates first vehicle information for the preceding vehicle by receiving a reflected radar signal; A camera for generating second vehicle information by sensing an image of the preceding vehicle; And a forward vehicle tracker that tracks the forward vehicle based on the first vehicle information, the second vehicle information, and the lane information, wherein the forward vehicle tracker uses the lane information to generate the first vehicle information and the second vehicle information, Sensor fusion logic fusing the second vehicle information; And search logic for tracking the forward vehicle in curve road driving conditions.

In an embodiment, the sensor fusion logic may calculate a relative Euclidean distance between the coordinates of the preceding vehicle sensed by the radar and the coordinates of the preceding vehicle sensed by the camera based on a minimum distance search algorithm.

In an embodiment, the sensor fusion logic may include front_display_ logic for selecting the coordinates of the camera as the coordinates of the front vehicle when the host vehicle is traveling along a curve path.

In one embodiment, the search logic is configured to select the coordinates of the preceding vehicle in consideration of a driving situation in which disturbance occurs when the curve ratio is larger than a threshold value of the road surface angle, or when the longitudinal coordinate of the radar is not the maximum value. Gt; _ < / RTI > defense logic.

In an embodiment, the apparatus may further comprise a combinational decision logic having a rear_dest_logic for receiving an output value of the search logic and outputting a final output coordinate for the preceding vehicle.

The forward vehicle tracking apparatus and the operation method thereof according to the embodiment of the present invention are capable of tracking the forward target vehicle in the course lanes of the hose vehicle with the defense logic comparing only the maximum of two conditions, Do.

Further, the front vehicle tracking apparatus and the operation method thereof according to the embodiment of the present invention can be applied to a vehicle tracking system and a method of operating the same, in which even when the lane information is inaccurate or the radar or camera detects the front vehicle, The host vehicle can track the target target vehicle in the progress path lane of the host vehicle.

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention. However, the technical features of the present embodiment are not limited to the specific drawings, and the features disclosed in the drawings may be combined with each other to constitute a new embodiment.
1 is an exemplary illustration of an apparatus 10 for tracking a forward vehicle in accordance with an embodiment of the present invention.
2 is an exemplary block diagram illustrating a forward vehicle tracker 300 in accordance with an embodiment of the present invention.
FIG. 3 is an exemplary diagram illustrating a coordinate output method of a forward vehicle tracker 300 according to an embodiment of the present invention.
FIG. 4 is an exemplary diagram illustrating the minimum distance search algorithm 312. FIG.
FIG. 5 is a flow diagram illustrating an operation of the front_display_logic 311 according to an embodiment of the present invention.
FIG. 6 is an exemplary illustration of the middle_dest_ logic 331 shown in FIG.
7 is a flow diagram illustrating an exemplary operation of a first function block 331-1 of a middle_destination_logic 331 according to an embodiment of the present invention.
FIG. 8 is a flow diagram illustrating an exemplary operation of a second function block 331-2 of the middle_destination_logic 331 according to an embodiment of the present invention.
FIG. 9 is a flow diagram illustrating an operation of a third function block 331-3 of the middle_destination_logic 331 according to an embodiment of the present invention.
10 is a flow chart illustrating an operation of a fourth function block 331-4 of the middle_dest_ logic 331 according to an embodiment of the present invention.
FIG. 11 is a flow diagram illustrating an operation of the fifth function block 331-5 of the middle_destination_logic 331 according to an embodiment of the present invention.
12 is a flowchart illustrating an exemplary operation of the Rear_Defence_logic 351 according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The above and other objects, features and advantages of the present invention will be more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which: FIG.

The present invention is capable of various modifications and various forms, and specific embodiments are illustrated in the drawings and described in detail in the text. It is to be understood, however, that the invention is not intended to be limited to the particular forms disclosed, but on the contrary, is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms.

The terms may be used for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

Other expressions that describe the relationship between components, such as "between" and "between" or "neighboring to" and "directly adjacent to" should be interpreted as well. The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, the terms "comprises" or "having" are intended to specify the presence of stated features, integers, steps, operations, components, parts, or combinations thereof, wherein one or more other features, , Steps, operations, components, parts, or combinations thereof, as a matter of course. Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries should be construed as meaning consistent with meaning in the context of the relevant art and are not to be construed as ideal or overly formal in meaning unless expressly defined in the present application .

1 is an exemplary illustration of a vehicle tracking device 10 for tracking a forward vehicle in accordance with an embodiment of the present invention. Referring to FIG. 1, the vehicle tracking device 10 may include a radar 100, a camera 200, and a forward vehicle tracker 300.

The radar 100 may be implemented to transmit radar signals around the vehicle and receive radar signals reflected from other vehicles.

The camera 200 may be implemented as a sensing sensor for sensing an image of the vehicle ahead. In an embodiment, the camera 200 may include a charge coupled device (CCD) image sensor, a metal oxide semi-conductor (MOS) image sensor, a charge priming device (CPD) And may be implemented as any one of image sensors such as a sensor.

The forward vehicle tracker 300 receives the first vehicle information for the target vehicle detected by the radar 100 and the second vehicle information for the target vehicle detected by the camera 200, Information can be fused to track the target vehicle ahead.

In an embodiment, the forward vehicle estimator 300 is configured to determine the sensor fusion logic of the radar 100 and the camera 200, and the sensor fusion logic of the radar 100 and the camera 200 to precisely track a target in front of the path of travel of the host And may include defense logic (defense logic) for tracking an object ahead of the host vehicle in road driving conditions. In an embodiment, the forward vehicle tracker 300 may be implemented in hardware / software / firmware.

Common radar and vision sensor fusion algorithms are being studied based on specific scenarios. In other words, when the radar recognizes multiple targets for a single obstacle, recognizes obstacles other than the vehicle (road structures such as guard rails), and most cases where the lateral position information is different when traveling on a curve . However, in case of actual highway driving, there may be some difference depending on the performance of the radar. However, when there are many vehicles in front, including a stationary vehicle due to traffic congestion, do. In particular, in the case of adaptive cruise control (ACC) or forward collision warning (ACC) systems, it is essential to select a primary vehicle in the host vehicle travel route to be controlled by the host vehicle. , There is a high risk of sudden braking, so the stability of the system is inevitable. In other words, previous researches related to the tracking of the front vehicle have been conducted to determine whether the front vehicle is in the traveling direction of the host vehicle using the lane information of the front vehicle or the inertial measurement unit (IMU) sensor information. In previous researches related to this, when judging whether the front object is in the lane of the host vehicle, if the lane is blurred or broken, it may cause a problem in the judgment of the logic, so that the wrong object can be tracked. There is a problem that it is difficult to judge whether the front vehicle recognized by the host vehicle is located in the host vehicle traveling route.

On the other hand, the vehicle tracking device 10 according to the embodiment of the present invention accurately tracks the target in the forward path of the host vehicle in various driving situations by using the sensor fusion logic and the defense logic, You can track the object in front of the vehicle.

2 is an exemplary block diagram illustrating a forward vehicle tracker 300 in accordance with an embodiment of the present invention. 2, forward vehicle tracker 300 includes sensor fusion logic 310, road condition determination logic 320, search logic 330, target vehicle lane estimation logic 340, and combination decision logic 350, . ≪ / RTI >

The sensor fusion logic 310 may be implemented to receive first vehicle information from the radar 100 and second vehicle information from the camera 200 and to fuse the vehicle information using road condition information. In an embodiment, the sensor fusion logic 310 may include front_display_logic 310 as first defense logic during curve travel.

The road condition determination logic 320 may be implemented to receive lane information and generate road condition information. Here, the lane information can be transmitted from an external electronic control unit (ECU) via controller area network (CAN) communication. On the other hand, it should be understood that the communication method is not necessarily restricted to CAN communication. The lane information can be transmitted by various communication methods such as MOST, LIN, FlexRay, and the like.

Further, the function module for determining the straight line or curve of the host vehicle on the road is composed of the following equation.

First, Curvature information is received via CAN communication.

The formula for determining the straight ahead or curve of the host vehicle is as follows.

Min_Max_Normalize {(Exponential_Smoothing_Function (left lane Curvature) + Exponential_Smoothing_Function (right lane Curvature)) / 2}

Here, the output value of the function has a value of 0 to 100%, and the straightness or curve running state of the host vehicle is determined based on the ratio.

Here, Exponential_Smoothing_Function is internally composed of Kalman Filter and Moving Average Filter. The formula is as follows.

Exponential_Smoothing_Function (Curvature) = Moving Average Filter (taps, Curvature) * (1 - weight factor) + Kalman Filter (Curvature) * weight factor

In this case, the weight factor sets the output ratio of the Kalman filter to a high direction in order to reflect the actual lane information, and sets the taps of the moving average filter to a high value in order to reduce the tremble of the large period.

The search logic 330 may be implemented to search for a target vehicle based on the lane information of the target vehicle. In an embodiment, the search logic 330 may include middle_dest_flush 330 as second defense logic during curve driving. Here, the middle_destrength logic 330 may include substantial defense logic that takes into account disturbing driving situations.

The target vehicle lane estimation logic 340 may be configured to receive lane information and generate lane information of the target vehicle based on the received lane information. Here, the lane information can be transmitted from an external electronic control unit (ECU) via controller area network (CAN) communication.

The function module for calculating the lane information around the target vehicle that is running is composed of the following equations. First, lane-related information is received via CAN communication.

 The formula for estimating the lane next to the target vehicle, which is the input value of the condition expression of the middle_dest_type 3330, is as follows.

The left vehicle's lane is the left vehicle's lane and the left vehicle's lane is the left vehicle's lane. coordinate of the host vehicle's lane) + host vehicle's position

The host vehicle's lane is the host vehicle's lane and the host vehicle's lane is the host vehicle's lane * 3 + right curvature * coordinate of the host vehicle's lane) + host vehicle's position

Since the estimated lane of the target vehicle contains ripples, the formula of Exponential_Smoothing_Function (Curvature) was applied to grasp the original signal trend while improving tremor.

Combination decision logic 350 may include a lear_destination_logic 350 as third defense logic during curve driving. In an embodiment, the Rear_Defence_ logic 350 may complement the middle_dest_ logic 330 and perform the function of combining the output values together.

In general, radar and camera may track objects other than the target ahead of the path, depending on the driving situation. In order to solve such a problem, it is necessary to configure the logic to track an object in the path of the host vehicle using various signals including the lane information of the camera 200. [ However, the radar or camera signal may be discontinuous due to disturbance in the actual driving environment. In the case of the camera in particular, the reliability of the lane information signal is greatly degraded when the lane is blurred or disconnected. The front vehicle tracker 300 according to the embodiment of the present invention implements the sensor fusion logic 310 and the defense logic 310, 330 and 350 of the radar and the camera even in the driving state of the various disturbance conditions, It is possible to accurately track the target ahead of the travel path of the vehicle.

The forward vehicle tracker 300 according to the embodiment of the present invention can perform the sensor fusion method of the radar 100 and the camera 200 and the curve driving method of the curve driving method in order to accurately track the target in the forward path of the host vehicle, Discloses defense logic for tracking an object in front of a host vehicle in a condition.

First, a function module for sensor fusion between the radar 100 and the camera 200 is configured as follows.

FIG. 3 is an exemplary diagram illustrating a coordinate output method of a forward vehicle tracker 300 according to an embodiment of the present invention.

Using the lane information of the host vehicle, it can be determined whether the host vehicle is a straight running or a curve running (S110). If it is a straight-ahead driving, one of the three coordinates obtained previously may be selected through the following steps S120, S130, and S140. On the other hand, if it is not a straight travel, coordinates can be selected through step S150.

4, the x and y coordinates of the target sensed by the radar 100 and the x and y coordinates of the targets sensed by the camera 200 are calculated based on the minimum distance search algorithm 312, The relative Euclidean distance can be calculated. Here, the equation for obtaining the relative Euclidean distance is as follows.

Relative Euclidean distance = sqrt {(Radar_xn - Camera_xn) ² + (Radar_yn - Camera_yn) ² }

Where sqrt is the root function, Radar_xn is the x coordinate of the radar, Radar_yn is the y coordinate of the radar, Camera_xn is the x coordinate of the camera, and Camera_yn is the y coordinate of the camera. (Xc2, yc2) corresponding to the coordinates (xc1, yc1) corresponding to the minimum distance (first minimum distance), the second minimum distance (second minimum distance> first minimum distance) Coordinates (xc3, yc3) corresponding to the minimum distance (third minimum distance> second minimum distance) may be extracted (S120).

In an embodiment, a relative angle between the coordinates corresponding to the extracted three minimum distances and the lateral and longitudinal coordinates within the lane of the host vehicle may be calculated (S130). Coordinate values close to 90 degrees out of the calculated relative angles can be extracted (S140).

In an embodiment, if the host vehicle is not straight ahead, the output coordinates of the front_dest_logic 311 (see FIG. 2)) may be selected (S140).

In the embodiment, the front_display_logic 311 can select one of coordinates (xc1, yc1) and radar 100 coordinates corresponding to the smallest relative Euclidian distance. When the lateral coordinate of the radar 100 is zero, the running angle of the host vehicle can be compared with the threshold 1. As a result of comparison, when the running angle? Is smaller than the threshold value 1 (TH1) (? TH1), the absolute value of xc1 calculated above is smaller than the threshold value 2 (| xc1 | <TH2) When the driving angle? Of the host vehicle is larger than the threshold value TH3 ((? TH3) and the driving angle? Of the host vehicle is smaller than the threshold value 2 (?? TH2 , The coordinates of the radar 100 may be used.

And, in the opposite condition to the previous conditions, xc1 and yc1 can be selected. The physical meaning of these conditions is that the front object is not detected in the radar 100 but the camera 200 is judged that a specific object has been detected in front of the camera 200 and xc1 and yc1 are detected only when the host vehicle is traveling in a rapid curve path And in the other cases, the signal of the radar 100 is used.

FIG. 5 is a flow diagram illustrating an operation of the front_display_logic 311 according to an embodiment of the present invention. Referring to FIG. 5, the operation of the front_dest_flag 311 may proceed as follows.

The front_dest_logic 311 can determine whether the curve ratio is greater than the threshold value of the road surface angle at step S210 and determine whether the radar 100 is equal to the maximum value of the longitudinal coordinate and the longitudinal radar coordinate S220). If not, that is, when the longitudinal coordinate of the radar 100 is not the maximum value while the curve ratio is not larger than the threshold value of the road surface angle, the radar coordinate becomes the output of the middle_dest_logic2 331-2 Otherwise, the coordinate by the search algorithm may be selected as shown in FIG. 4 (S230).

In order to accurately track the target ahead of the host vehicle in various driving situations, the forward vehicle tracker 300 of the present invention can be implemented with three levels of defense logic. The first defense logic may be applied to the sensor fusion logic 310 of the radar 100 and the camera 200 as a functional block named Front_Dest_logic 311 (see FIG. 2). The second defense logic is a middle_destination_logic 331 (see FIG. 2), and a total of five functional blocks 331-1, 331-2, 331-3, 331-4, 331 -5). The middle_dest_ logic 331 may correspond to substantial defense logic that takes into account disturbing driving situations. The third defense logic can complement the middle_dest_ logic 331 with the rear_dest_ logic 351 (see FIG. 2) and perform the function of combining the output values into one.

7 is a flow diagram illustrating an exemplary operation of a first function block 331-1 of a middle_destination_logic 331 according to an embodiment of the present invention. Referring to FIG. 7, the first middle_dest_ logic 331-1 may be performed as follows.

If the lateral coordinate value of the radar 100 is 0 and the value of the lateral coordinate among the final output coordinates of the sensor fusion logic 310 is within the traveling path of the host vehicle, the final output coordinate of the sensor fusion logic 310 is The first middle_dest_ logic 331-1 is used to select one of the output coordinates of the second through fifth functional blocks 331-2 through 331-5 of the middle_dest_ logic 331, Can be configured.

The first middle_destination_logic 331-1 determines whether the lateral coordinate value of the radar 100 is zero (S310), determines whether there is an output coordinate of the sensor fusion logic module in the lane of the host vehicle S320). If all are true, the coordinates of the second through fifth middle_dest_ logic 331-2 through 331-5 may be selected, and the coordinates of the sensor fusion logic 310 may be selected otherwise S330).

The physical meaning of the first middle defense_logic 331-1 is that there is no object in front of the radar 100. When the camera 200 senses an object ahead of the object, the camera corresponds to a curve path, The second middle_dest_ logic 331-2 which considers the situation is disabled and the third middle_dest_ logic 331-3 which considers the driving state at the time of the curve driving is executed.

FIG. 8 is a flow diagram illustrating an exemplary operation of a second function block 331-2 of the middle_destination_logic 331 according to an embodiment of the present invention. Referring to FIG. 8, the second middle_dest_ logic 331-2 may be performed as follows.

The absolute value of the absolute value of the longitudinal coordinate value of the radar 100 and the absolute value of the absolute value of the longitudinal coordinate value of the final output coordinate of the sensor fusion logic 310 is smaller than the threshold value 4 (TH4) If the absolute value of the absolute value of the lateral coordinate value of the radar 100 and the absolute value of the absolute value of xc1 is greater than the threshold value 4 (TH4)), Logic 331-2 may be configured.

The second middle_destination_logic 331-2 determines whether the difference between the longitudinal coordinate of the radar 100 and the longitudinal coordinate of the camera 200 is greater than a threshold value 4 (S410) If the longitudinal difference is smaller than the threshold value 4 (TH4), the coordinates of the radar 100 are selected, and other coordinates other than the third to fifth middle_destination_ logic 331-3 to 331-5 are selected (S420).

The physical meaning of the second middle_dest_ logic 331-2 is that if the host vehicle and the target vehicle are running straight ahead and the radar 100 coordinates and the final output coordinates of the sensor fusion logic 310 are the same , And the radar 100 coordinates. This is because the coordinate of the radar 100 with respect to the camera 200 is excellent in the ripple characteristic in the longitudinal direction.

FIG. 9 is an exemplary diagram illustrating the operation of a third function block 331-3 of the middle_destination_logic 331 according to an embodiment of the present invention. Referring to FIG. 9, the third middle_dest_ logic 331-3 may be performed as follows.

If the longitudinal coordinate value of the radar 100 is the maximum value and the lateral coordinate value of the final output coordinate of the sensor fusion logic 310 is within the host vehicle's progress path lane, the final output coordinate of the sensor fusion logic 310 The third middle_dest_ logic 331-3 may be configured to select the third middle_dest_ logic 331-3.

The third middle_destination_logic 331-3 determines whether the longitudinal coordinate value of the radar 100 is the maximum value of the longitudinal radar coordinate (S510), and the output of the sensor fusion logic 310 in the host vehicle lane (S520). If S510 and S520 are both true, the radar coordinate may be selected and other coordinates may be selected in consideration of the fourth to fifth middle_destination_logic 331-4 to 331-5 (S530).

The physical meaning of the third middle defense_logic 331-3 is that the target vehicle is not captured in the radar 100 but the target vehicle is caught in the camera 200 and therefore corresponds to the curve path, Since the output of the _Defence_logic 331-2 is not selected, it is in the situation that an object with a distance slightly out of the view angle of the AR Hud is being tracked. In this situation, since there is no object in the radar 100, the final output coordinates of the sensor fusion logic 310 may be selected.

10 is an exemplary diagram illustrating the operation of the fourth function block 331-4 of the middle_destination_logic 331 according to an embodiment of the present invention. Referring to FIG. 10, the fourth middle_dest_ logic 331-4 may be performed as follows.

The output of the sensor fusion logic 310 is greater than the threshold value 6 (TH6) while the longitudinal coordinate of the radar 100 is greater than or equal to the threshold value 5 (TH5) If it is in the vehicle heading lane, the fourth middle_display_ logic 331-4 can be configured to initialize the final output lateral coordinate to zero and the final output longitudinal coordinate to a value of the threshold 5 (TH5) .

The fourth middle defense_ logic 331-4 determines whether the longitudinal coordinate value of the radar 100 is equal to or greater than the maximum value of the longitudinal radar coordinate (S610), and determines whether the sensor fusion logic 310 in step S620. If both of the determination results in S610 and S620 are true, the vertical coordinate is set to the vertical radar maximum value and the horizontal coordinate is set to zero. Otherwise, It is possible to select a coordinate in consideration of the def_logic 331-5 (S630).

The physical meaning of the fourth middle_destination_logic 331-4 is that the fourth middle_destination_logic 331-4 in the situation where the second to third middle_destination_logic 331-2 and 331-3 are not selected 331-4 are true, the target vehicle is in a state of running away from a gentle curve road, and the target vehicle is highly likely not to be in the driving lane of the host vehicle. In this situation, it is meaningless to track the target, so even if the camera 200 recognizes the target vehicle, it will ignore it and initialize the final output coordinates as follows. That is, the longitudinal coordinate may be set to the maximum vertical value of the radar 100, and the lateral coordinate may be set to zero.

11 is an exemplary diagram illustrating the operation of the fifth function block 331-5 of the middle_destination_logic 331 according to an embodiment of the present invention. Referring to FIG. 11, the fifth middle_dest_ logic 331-5 may be performed as follows.

The absolute value of the difference between the lateral coordinate of the radar 100 and the lateral coordinate value of the final output coordinate of the sensor fusion logic 310 is larger than the left and right lane coordinate values of the host vehicle, If the coordinate value is not 0, the fifth middle_dest_ logic 331-5 can be configured to select the radar 100 coordinate as the final output coordinate.

The fifth middle defense_ logic 331-5 determines whether the difference between the radar lateral coordinate and the camera lateral coordinate is larger than the coordinates of the host vehicle (S710), and detects the sensor fusion logic 310 in the host vehicle lane. (S720). If both of S710 and S720 are true, it is possible to select the radar coordinate and otherwise, the coordinates considering the rear_front_logic 351 (S730).

The physical meaning of the fifth middle defense_logic 331-5 is that the radar 100 and the camera 200 are tracking the target vehicle ahead because the lateral coordinate value of the radar 100 is not zero Since the absolute value of the difference value between the lateral coordinate of the radar 100 and the final coordinate of the output of the sensor fusion logic 310 is out of the lane of the host vehicle, There is a situation. In this situation, the camera 200 tracks the target vehicle in the next lane, and the radar 100 tracks the target vehicle at a straight line distance. Therefore, the coordinate of the radar 100 is used as the final output coordinate.

12 is a flowchart illustrating an operation of the Rear_Defence_logic 351 according to an embodiment of the present invention. Referring to FIG. 12, the functional block of the Rear_Defence_logic 351 may be implemented as follows.

The rear_destination_logic 351 includes output coordinates in which the first to fifth middle_destination_logic 331-1 to 331-5 are all considered, first to third middle_destination_logic 331-3, 331-3), and coordinates of one of the coordinates of the radar 100 can be finally selected.

Among the output coordinates considered only from the first to third middle_destination_logic 331-3 to 331-3, the vertical coordinate value is set to the first to fifth middle_destination_logic 331-1 to 331-5 If the output coordinate is larger than the longitudinal coordinate value and at the same time is not the value of the threshold value 5 (TH5), the output considering only the first to third middle_destination_logic 331-1 to 331-3 as the final output coordinate value And if the condition is false, the coordinate value of the longitudinal direction is set to the threshold value 7 (TH7) among the output coordinates considering all of the first to fifth middle_destination_logic 331-1 to 331-5, The coordinate values of the radar 100 are used as the final output coordinate values, and among the output coordinates considering all of the first to fifth middle_destination_logic 331-1 to 331-5, 7 (TH7), the output coordinate values considering all of the first to fifth middle_dest_ logic 331-1 to 331-5 as final output coordinate values And the Rear_Dest_ logic 351 can be configured to select the Rear_Dest_ logic 351.

The rear_destination_logic 351 is configured such that the longitudinal coordinate output value considering the first to third middle_destination_logic 331-1 to 331-3 is the first to fifth middle_destination_logic 331-1 331-5 in step S810. If the output longitudinal coordinate and the longitudinal radar maximum value in consideration of the first to third middle_destination_logics 331-1 to 331-3 are determined (S820). If both S810 and S820 are true, it is determined whether or not the vertical coordinate in consideration of the middle_destination_logic is selected, otherwise, the following steps are performed (S830) It is determined whether the output longitudinal coordinate in consideration of the fifth_dest_rodies 331-1 to 331-5 is smaller than the threshold value 7 (S840). If S840 is true, the radar coordinate is selected. Otherwise, It is possible to select the output longitudinal coordinate in consideration of the middle_destination_logic (S850).

The rear_dest_ logic 351 may determine whether to consider the fourth through fifth middle_dest_ logic 331-4 through 331-5 in the final output coordinate. The fourth middle_destination_logic 331-4 is a functional block that initializes the final output coordinates, where the main tuning factor is the threshold 6 (TH6), which is the distance value for the longitudinal maximum viewing angle of the AR Head up display device, Therefore, it is possible to determine whether or not to initialize according to the setting of this value. The fifth middle_destination_logic 331-5 selects the coordinates of the radar 100 as final output coordinates if the lateral output coordinates of the output coordinates of the sensor fusion logic 310 are outside the lane of the host vehicle's traveling direction . In this case, if the longitudinal coordinate values of the first to third middle_destination_logic 331-1 to 331-3 are the longitudinal coordinates of the first to fifth middle_destination_logic 331-1 to 331-5 The output coordinates of the first to third middle_dest_ logic 331-1 to 331-3 can be selected. This is because it is difficult to consider whether the target vehicle, which is a condition expression of the fifth middle_dest_logic 331-5, is in the proceeding direction lane of the host vehicle, as the farther the object is.

If the situation is reversed, the first to fifth middle_dest_logic 331-1 to 331-5 are considered for the target vehicle in the close range. Here, comparing the value of the threshold 7 (TH7), which is an exception condition, with the longitudinal coordinate values of the first to fifth middle_destination_logic 331-1 to 331-5 is equivalent to setting the threshold 7 (TH7) Value is set to a value within a distance range very close to the host vehicle, meaning that if the target vehicle is within the range of the threshold value 7 (TH7), the radar 100 coordinate value is selected. If the camera 200 is more likely to track the nearest object than the radar 100, the rear_display_logic 351 may be modified to select the camera 200 coordinates.

As described above, the Front_Defence_logic 311 and the Middle_Dest__ logic 331 can be added in consideration of the driving situation, and the Middle_Dest_Plus_logic 311, The functional module combination of the logic 331 may also be added in consideration of the operating situation.

The steps and / or operations in accordance with the present invention may occur in different orders, in parallel, or concurrently in other embodiments for other epochs or the like, as may be understood by one of ordinary skill in the art .

Depending on the embodiment, some or all of the steps and / or operations may be performed on one or more non-transitory computer-readable media, including instructions, programs, interactive data structures, At least some of which may be implemented or performed using one or more processors. The one or more non-transitory computer-readable media can be, by way of example, software, firmware, hardware, and / or any combination thereof. Further, the functions of the " module " discussed herein may be implemented in software, firmware, hardware, and / or any combination thereof.

One or more non-transitory computer-readable media and / or means for implementing / performing one or more operations / steps / modules of embodiments of the present invention may be implemented as application-specific integrated circuits (ASICs), standard integrated circuits, But are not limited to, controllers that perform appropriate instructions, including microcontrollers, and / or embedded controllers, field-programmable gate arrays (FPGAs), complex programmable logic devices (CPLDs) .

Meanwhile, the vehicle tracking device 10 according to the embodiment of the present invention can be mounted on various kinds of vehicles (EV, PHEV, HEV, etc.). On the other hand, it should be understood that the vehicle tracking device of the present invention can be mounted in addition to the vehicle.

The above-described contents of the present invention are only specific examples for carrying out the invention. The present invention will include not only concrete and practical means themselves, but also technical ideas which are abstract and conceptual ideas that can be utilized as future technologies.

10: vehicle tracking device
100: Radar
200: camera
300: Forward vehicle tracker
310: Sensor Fusion logic
320: Road condition determination logic
330: search logic
340: Target vehicle lane estimation logic
350: Combination decision logic
311: Front_Defence_logic
331: Middle_Defence_Rogic
351: Rear_Defence_logic
331-1 to 331-5: 1st to 5th Middle_Defence_Logic

Claims (16)

A method of operating a vehicle tracking device comprising:
Determining whether the host vehicle is immediately preceding the host vehicle based on lane information of the host vehicle;
Calculating the distance between the coordinates of the target sensed by the radar and the coordinates of the targets sensed by the camera if the host vehicle is a straight run;
Extracting coordinates of the camera corresponding to a first minimum distance, a second minimum distance longer than the first minimum distance, and a third minimum distance longer than the second minimum distance among the calculated distances;
Calculating a relative angle between each of the extracted coordinates and a lateral or longitudinal coordinate within a lane of the host vehicle; And
Selecting one of the extracted coordinates as an output coordinate of the target using the calculated relative angle. The method according to claim 1,
If the host vehicle is not a straight run, performing front_dest_logic to select either the camera coordinates corresponding to the one minimum distance and the coordinates of the radar. 3. The method of claim 2,
The step of performing the &lt; RTI ID = 0.0 &gt; front-defense-
Selecting the radar coordinate if the curve ratio is greater than the threshold of the road surface angle and the longitudinal coordinate of the radar is the maximum value of the longitudinal radar coordinate. 3. The method of claim 2,
If the curve rate is not greater than the threshold of the road surface angle, or if the longitudinal coordinate of the radar is not the maximum value of the longitudinal radar coordinate, performing the middle_dest_ logic by the search algorithm. 5. The method of claim 4,
The step of performing the middle_dest_ logic comprises:
Selecting the output coordinates of the sensor fusion logic when the lateral coordinates of the radar are not zero or the output coordinates of the sensor fusion logic are not present in the lane of the host vehicle. 5. The method of claim 4,
The step of performing the middle_dest_ logic comprises:
It is determined whether the difference between the longitudinal coordinate of the radar and the longitudinal coordinate of the camera is smaller than a predetermined threshold value when the lateral coordinate of the radar is 0 and the output coordinate of the sensor fusion logic is present in the lane of the host vehicle ; And
Selecting the radar coordinate when the difference between the longitudinal coordinate of the radar and the longitudinal coordinate of the camera is less than the predetermined threshold. 5. The method of claim 4,
The step of performing the middle_dest_ logic comprises:
Determining whether the longitudinal coordinate of the radar is the maximum value of the longitudinal radar coordinate when the difference between the longitudinal coordinate of the radar and the longitudinal coordinate of the camera is not less than a predetermined threshold;
Determining whether the output coordinate of the sensor fusion logic is present in the lane of the host vehicle; And
Selecting the radar coordinate when the longitudinal coordinate of the radar is the maximum value of the longitudinal radar coordinate and the output coordinate of the sensor fusion logic is in the lane of the host vehicle. 5. The method of claim 4,
The step of performing the middle_dest_ logic comprises:
Determining whether the longitudinal coordinate of the radar is greater than or equal to the maximum value of the longitudinal radar coordinate;
Determining whether the output coordinate of the sensor fusion logic is present in the lane of the host vehicle; And
When the coordinate of the longitudinal direction of the radar is greater than or equal to the maximum value of the longitudinal radar coordinates and the output coordinate of the sensor fusion logic is present in the lane of the host vehicle, the longitudinal coordinate is defined as the longitudinal radar maximum value, RTI ID = 0.0 &gt; 0. &Lt; / RTI &gt; 5. The method of claim 4,
The step of performing the middle_dest_ logic comprises:
When the longitudinal coordinate of the radar is smaller than the maximum value of the longitudinal radar coordinate or when there is no output coordinate of the sensor fusion logic in the lane of the host vehicle, the lateral coordinate of the radar and the lateral coordinate of the camera Determining whether the difference is greater than the coordinates of the host vehicle;
Determining whether the output coordinate of the sensor fusion logic is present in the lane of the host vehicle; And
Selecting the radar coordinates when the difference between the lateral coordinates of the radar and the lateral coordinates of the camera is greater than the coordinates of the host vehicle and the output coordinates of the sensor fusion logic are in the lane of the host vehicle How to. 10. The method of claim 9,
When the difference between the lateral coordinate of the radar and the lateral coordinate of the camera is not larger than the coordinates of the host vehicle or when there is no output coordinate of the sensor fusion logic in the lane of the host vehicle, &Lt; / RTI &gt; 11. The method of claim 10,
The step of performing the Rear_Defence_ logic includes:
Selecting one of the coordinates selected in the front_destination_logic, the coordinates selected in the middle_destination_logic, and the radar coordinate as the output coordinates of the target. A radar that transmits a radar signal to a preceding vehicle and generates first vehicle information for the preceding vehicle by receiving a reflected radar signal;
A camera for generating second vehicle information by sensing an image of the preceding vehicle; And
And a forward vehicle tracker for tracking the forward vehicle based on the first vehicle information, the second vehicle information, and the lane information,
Said forward vehicle tracker comprising:
Sensor fusion logic for fusing the first vehicle information with the second vehicle information using the lane information; And
And navigation logic for tracking said forward vehicle in curve road driving conditions. 13. The method of claim 12,
Wherein the sensor fusion logic calculates a relative Euclidean distance between the coordinates of the preceding vehicle sensed by the radar and the coordinates of the preceding vehicle sensed by the camera based on a minimum distance search algorithm. 14. The method of claim 13,
Wherein the sensor fusion logic comprises front_display_ logic for selecting the coordinates of the camera as coordinates of the front vehicle when the host vehicle is traveling along a curve path. 15. The method of claim 14,
The search logic may select the coordinates of the preceding vehicle in consideration of a driving situation in which disturbance occurs when the curve ratio is larger than a threshold value of the road surface angle or when the longitudinal coordinate of the radar is not the maximum value Included vehicle tracking device. 16. The method of claim 15,
And combine decision logic having a rear_dest_ logic for receiving an output value of the search logic and outputting a final output coordinate for the preceding vehicle.

Images