KR102405361B1 - Apparatus and method for tracking position of moving object based on slop of road - Google Patents

Abstract

The present invention relates to an apparatus and method for tracking a location of a moving object based on a road inclination, and the location tracking apparatus according to an embodiment comprises: a location information calculating unit for calculating a slope value of the own vehicle based on a slope corresponding to the own vehicle; and a gradient calculator configured to calculate a gradient value corresponding to the counterpart vehicle, and an absolute coordinate calculator configured to calculate absolute coordinates of the counterpart vehicle based on the inclination value of the host vehicle and the gradient value corresponding to the counterpart vehicle.

Description

Apparatus and method for tracking the position of a moving object based on road inclination

The present invention relates to an apparatus and method for tracking a location, and more particularly, to a technical idea of tracking an exact location of a vehicle based on a road inclination.

Recently, vehicles are equipped with an around view monitoring (AVM) system. The around-view monitoring system synthesizes images obtained from four cameras installed on the front, side mirrors, and trunk of the vehicle, respectively, and displays the around-view image in a top-view form looking around the vehicle from above. to provide.

The existing around-view monitoring system outputs bounding boxes corresponding to surrounding objects (for example, surrounding vehicles, etc.) using a tracking algorithm when displaying in top-view, a section with a steep slope. There is a problem in that the position of the bounding box is output incorrectly.

Korean Patent Laid-Open Patent No. 10-2016-0120467, "Azimuth angle correction apparatus and method for 2D radar for vehicle" Korean Patent No. 10-0575933, "Method for measuring speed of moving object using accelerometer and route guidance data and device therefor" Korean Patent Laid-Open Patent No. 10-2014-0080874, "Steering Assist Parking Guide Device and Method"

An object of the present invention is to provide a location tracking apparatus and method capable of calculating absolute coordinates corresponding to the current location of the counterpart vehicle in consideration of the inclination of the inclination on which the host vehicle and the counterpart vehicle are located.

Another object of the present invention is to provide a position tracking apparatus and method capable of correcting the position of a bounding box corresponding to the relative vehicle based on the calculated absolute coordinates of the relative vehicle.

In addition, an object of the present invention is to provide a location tracking device and method capable of more accurately and stably tracking the position of an opponent vehicle, not only in a section with a steep front, back, left and right slope, but also when driving on a bumpy or bumpy road surface.

A location tracking apparatus according to an embodiment of the present invention includes a location information calculator for calculating a gradient value of the host vehicle based on a gradient corresponding to the own vehicle, a gradient calculator for calculating a gradient value corresponding to the counterpart vehicle, and the and an absolute coordinate calculator for calculating absolute coordinates of the counterpart vehicle based on the inclination value of the host vehicle and the inclination value corresponding to the counterpart vehicle.

According to one side, the location information calculating unit is the inclination value of the host vehicle corresponding to at least one of an x-axis corresponding to the moving direction of the host vehicle, a y-axis corresponding to a direction orthogonal to the x-axis, and a z-axis. can be calculated.

According to one side, the location information calculator includes a pitch value corresponding to the inclination of the host vehicle in the x-axis direction, a roll value corresponding to the inclination in the y-axis direction of the host vehicle, and the z-axis of the host vehicle. At least one value among yaw values corresponding to the direction gradient may be calculated.

According to one side, the absolute coordinate calculating unit calculates the absolute coordinates of the relative vehicle through an operation based on the pitch value of the own vehicle, the roll value of the own vehicle, the yaw value of the own vehicle, and the inclination value corresponding to the counterpart vehicle. can

According to one side, the gradient calculator may calculate a gradient value corresponding to the counterpart vehicle based on at least one of an inertial measurement unit (IMU) and a captured image of the counterpart vehicle.

According to one side, the gradient calculator may calculate a gradient value corresponding to the counterpart vehicle based on a difference between a frame corresponding to a current time point and a frame corresponding to a previous time point in the captured image of the counterpart vehicle. .

According to one side, the gradient calculator may calculate a gradient value corresponding to the counterpart vehicle through an operation based on a linear distance value between the host vehicle and the counterpart vehicle and a height value of the counterpart vehicle.

According to one side, the position tracking apparatus may further include a position correcting unit for correcting a position of a bounding box corresponding to the relative vehicle based on the calculated absolute coordinates of the relative vehicle.

A location tracking method according to an embodiment of the present invention comprises the steps of calculating a slope value of the host vehicle according to the slope corresponding to the own vehicle in a location information calculating unit, and calculating a slope value corresponding to the counterpart vehicle in the slope calculating unit and calculating, in the absolute coordinate calculator, the absolute coordinates of the relative vehicle based on the inclination value of the host vehicle and the inclination value corresponding to the counterpart vehicle.

According to one side, the calculating of the inclination value of the host vehicle corresponds to at least one of an x-axis corresponding to a moving direction of the host vehicle, a y-axis corresponding to a direction orthogonal to the x-axis, and a z-axis. The inclination value of the host vehicle may be calculated.

According to one side, the calculating of the inclination value of the host vehicle includes a pitch value corresponding to the inclination of the host vehicle in the x-axis direction, a roll value corresponding to the inclination in the y-axis direction of the host vehicle, and At least one value of yaw values corresponding to the z-axis direction inclination of the host vehicle may be calculated.

According to one side, the calculating of the absolute coordinates of the counterpart vehicle may include calculating a pitch value of the own vehicle, a roll value of the own vehicle, a yaw value of the own vehicle, and a slope value corresponding to the counterpart vehicle through an operation. The absolute coordinates of can be calculated.

According to one embodiment, the present invention may calculate absolute coordinates corresponding to the current location of the counterpart vehicle in consideration of the inclination of the inclination on which the host vehicle and the counterpart vehicle are located.

In addition, the present invention may correct the position of the bounding box corresponding to the relative vehicle based on the calculated absolute coordinates of the relative vehicle.

In addition, according to the present invention, it is possible to more accurately and stably track the position of the other vehicle even when the road surface is bumpy or when driving on a bump as well as a section with a steep slope in front, back, left and right.

1A to 1E are diagrams for explaining a pushing phenomenon of a bounding box occurring in a top-view image.
2 is a view for explaining a location tracking device according to an embodiment.
3 is a view for explaining an example of calculating the absolute coordinates of the relative vehicle using the location tracking device according to an embodiment.
4 is a view for explaining a location tracking method according to an embodiment.

Hereinafter, various embodiments of the present document will be described with reference to the accompanying drawings.

Examples and terms used therein are not intended to limit the technology described in this document to a specific embodiment, but it should be understood to include various modifications, equivalents, and/or substitutions of the embodiments.

In the following, when it is determined that a detailed description of a known function or configuration related to various embodiments may unnecessarily obscure the gist of the present invention, a detailed description thereof will be omitted.

In addition, the terms to be described later are terms defined in consideration of functions in various embodiments, which may vary according to intentions or customs of users and operators. Therefore, the definition should be made based on the content throughout this specification.

In connection with the description of the drawings, like reference numerals may be used for like components.

The singular expression may include the plural expression unless the context clearly dictates otherwise.

In this document, expressions such as “A or B” or “at least one of A and/or B” may include all possible combinations of items listed together.

Expressions such as "first," "second," "first," or "second," can modify the corresponding elements regardless of order or importance, and to distinguish one element from another element. It is used only and does not limit the corresponding components.

When an (eg first) component is referred to as being “connected (functionally or communicatively)” or “connected” to another (eg, second) component, one component is the other component. may be directly connected to, or may be connected through another component (eg, a third component).

As used herein, "configured to (or configured to)" according to the context, for example, hardware or software "suitable for," "having the ability to," "modified to ," "made to," "capable of," or "designed to" may be used interchangeably.

In some circumstances, the expression “a device configured to” may mean that the device is “capable of” with other devices or parts.

For example, the phrase "a processor configured (or configured to perform) A, B, and C" refers to a dedicated processor (eg, an embedded processor) for performing the corresponding operations, or by executing one or more software programs stored in a memory device. , may refer to a general-purpose processor (eg, a CPU or an application processor) capable of performing corresponding operations.

Also, the term 'or' means 'inclusive or' rather than 'exclusive or'.

That is, unless stated otherwise or clear from context, the expression 'x employs a or b' means any one of natural inclusive permutations.

In the above-described specific embodiments, elements included in the invention are expressed in the singular or plural according to the specific embodiments presented.

However, the singular or plural expression is appropriately selected for the situation presented for convenience of description, and the above-described embodiments are not limited to the singular or plural component, and even if the component is expressed in plural, it is composed of a singular or , even a component expressed in the singular may be composed of a plural.

On the other hand, although specific embodiments have been described in the description of the invention, various modifications are possible without departing from the scope of the technical idea contained in the various embodiments.

Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined by the claims described below as well as the claims and equivalents.

1A to 1E are diagrams for explaining a pushing phenomenon of a bounding box occurring in a top-view image.

Referring to FIGS. 1A to 1E , when the host vehicle and the other vehicle are traveling on a general flat section (reference numeral 110), it can be confirmed that the other vehicle's bounding box displayed in the top-view is displayed at the correct position.

However, when the host vehicle and the other vehicle are traveling on an uphill road or a downhill road having an inclination θ greater than or equal to a threshold inclination (reference numerals 120 to 130), the other vehicle's bounding box displayed as a top-view is displayed in the front direction of the opposite vehicle. It can be seen that the output is pushed to .

Accordingly, as shown in reference numerals 140 to 150, the location tracking apparatus according to an embodiment calculates the absolute coordinates of the relative vehicle in consideration of the inclination θ, and based on the calculated absolute coordinates, the relative vehicle's bounding box By correcting the position of the vehicle, it is possible to track the position of the other vehicle more accurately and stably.

2 is a view for explaining a location tracking device according to an embodiment.

Referring to FIG. 2 , the location tracking apparatus 200 according to an embodiment may calculate absolute coordinates corresponding to the current location of the counterpart vehicle in consideration of the inclination of the inclination on which the own vehicle and the counterpart vehicle are located.

Also, the position tracking apparatus 200 may correct the position of the bounding box corresponding to the counterpart vehicle based on the calculated absolute coordinates of the counterpart vehicle.

In addition, the location tracking device 200 can more accurately and stably track the location of the other vehicle even when the road surface is bumpy or when driving on a bump as well as a section with a steep slope in front, back, left and right.

To this end, the location tracking apparatus 200 may include a location information calculator 210 , a gradient calculator 220 , and an absolute coordinate calculator 230 .

The location tracking apparatus 200, which will be described below, is located in the own vehicle and may calculate absolute coordinates corresponding to the current location of the other vehicle. In addition, the location tracking apparatus 200 may calculate absolute coordinates for an object having a threshold size or larger located on an incline in addition to the relative vehicle located on the incline.

The location information calculating unit 210 according to an exemplary embodiment may calculate a slope value of the own vehicle based on the slope corresponding to the own vehicle.

According to one side, the location information calculating unit 210 is the inclination value of the own vehicle corresponding to at least one of the x-axis corresponding to the moving direction of the host vehicle, the y-axis and the z-axis corresponding to a direction orthogonal to the x-axis. can be calculated.

In other words, the location information calculating unit 210 calculates the value of the host vehicle corresponding to at least one of the traveling direction (x-axis) of the own vehicle, the left-right direction (y-axis) of the own vehicle, and the height direction (z-axis) of the inclination. The slope value can be calculated.

According to one side, the location information calculating unit 210 is a pitch value corresponding to the inclination in the x-axis direction of the host vehicle, a roll value corresponding to the inclination in the y-axis direction of the host vehicle, and the z-axis of the own vehicle At least one value among yaw values corresponding to the direction inclination may be calculated as the inclination value of the host vehicle.

For example, the location information calculating unit 210 may calculate a pitch value, a roll value, and a yaw value of the own vehicle through an inertial measurement unit (IMU) mounted on the own vehicle.

An inertial measurement device is a sensor that uses a combination of an accelerometer and a tachometer or magnetometer to measure a specific force, angular rate, and/or magnetic field surrounding a body, using one or more accelerometers to sense linear acceleration and one or more gyro The scope can be used to sense the rotational speed and operate.

In addition, the inertial measurement apparatus may calculate a pitch value, a roll value, and a yaw value for the vehicle using an accelerometer, a gyroscope sensor, and a magnetic measurement device respectively disposed on each axis of the vehicle.

The gradient calculator 220 according to an exemplary embodiment may calculate a gradient value corresponding to the counterpart vehicle.

According to one side, the gradient calculator 220 may calculate a gradient value corresponding to the counterpart vehicle based on at least one of the inertia measuring device and a captured image corresponding to the counterpart vehicle.

Specifically, the gradient calculating unit 220 calculates a gradient value corresponding to the relative vehicle based on the xy plane coordinates and z coordinates generated during absolute coordinate transformation according to the map generation, or uses an inertia measurement device to calculate the relative gradient. A gradient value corresponding to the vehicle may be calculated.

Also, the gradient calculator 220 may calculate a gradient value corresponding to the counterpart vehicle based on a difference between a frame corresponding to the current view and a frame corresponding to a previous view among images captured by the other vehicle.

Preferably, the gradient calculator 220 may calculate a gradient value corresponding to the counterpart vehicle through an operation based on a linear distance value between the host vehicle and the counterpart vehicle and a height value of the counterpart vehicle. For example, the inclination calculating unit 220 may calculate a linear distance value between opposing vehicles and a height value of the opposing vehicle by using a LiDAR sensor mounted on the own vehicle.

The lidar sensor is a sensor that irradiates a laser onto a target and detects the distance to the target, direction, speed, temperature, material distribution and concentration characteristics, etc. based on the signal reflected by the target. It may include a signal collection/processing unit.

For example, the lidar sensor may include any one of a mechanical lidar sensor and a fixed lidar sensor, and the fixed lidar sensor includes a MEMS lidar sensor, a flash lidar sensor, and an optical phase array (OPA) lidar sensor. and a frequency-modulated continuous wave (FMCW) lidar sensor.

Specifically, a mechanical lidar sensor is a sensor that can realize a wide (for example, 360 degrees) field of view (FOV) using advanced optical components or rotating assemblies. noise ratio) can be implemented.

The fixed lidar sensor is a low-cost sensor that does not have mechanical components, and can implement a FOV similar to that of a mechanical lidar sensor by fusing the data using various channels on the front, rear, and side of the vehicle.

A MEMS lidar sensor is a sensor that uses a small mirror whose tilt angle changes when an electrical stimulus such as a voltage is applied, and can replace mechanical scanning hardware with an electromechanical one. The MEMS lidar sensor has a receiver condensing aperture of several mm, which determines the reception SNR, and is implemented very small, which can reduce the overall sensor size.

A flash lidar sensor is a sensor that behaves very similarly to a standard digital camera using an optical flash, in which a single large-area laser pulse illuminates the environment in front and an array of focal planes of photodetectors located close to the laser in the rear. It can operate by capturing scattered light.

The flash lidar sensor can improve data capture speed by capturing the entire scene in a single image compared to mechanical laser scanning, and since the entire image is captured by a single flash, it can minimize the effect of vibration effects that can distort the image. can

The OPA lidar sensor is a sensor that controls the speed of light passing through a lens by an optical phase modulator like a phased array radar. By controlling the speed of light, the shape of the optical wavefront can be controlled.

The OPA LiDAR sensor can steer the laser beam in multiple directions by controlling the top beam to be retarded, but not retarded, but the middle and lower beams to be retarded in increasing amounts.

The FMCW lidar sensor is a sensor that generates short chirped frequency-modulated laser light using a coherent method. It can measure both distance and speed by measuring the phase and frequency of the returned chirp. can be implemented.

The absolute coordinate calculator 230 according to an embodiment may calculate the absolute coordinates of the counterpart vehicle based on the inclination value of the own vehicle and the inclination value corresponding to the counterpart vehicle.

According to one side, the absolute coordinate calculator 230 may calculate the absolute coordinates of the counterpart vehicle through calculations based on the pitch value of the own vehicle, the roll value of the own vehicle, the yaw value of the own vehicle, and the inclination value corresponding to the counterpart vehicle. .

That is, the absolute coordinate calculator 230 calculates a slope corresponding to the traveling direction (x-axis) of the host vehicle, a slope corresponding to the left-right direction (y-axis) of the host vehicle, and a slope corresponding to the height direction (z-axis) of the inclination It is possible to more accurately calculate the absolute coordinates of the relative vehicle by considering all of them.

For example, the absolute coordinate calculator 230 may calculate the absolute coordinates of the relative vehicle through an operation based on the xy-axis rotation matrix.

Meanwhile, the location tracking apparatus 200 according to an embodiment may further include a location correcting unit for correcting the location of a bounding box corresponding to the counterpart vehicle based on the calculated absolute coordinates of the counterpart vehicle.

The location tracking apparatus 200 according to an embodiment will be described in more detail with reference to FIG. 3 in the following embodiment.

3 is a view for explaining an example of calculating the absolute coordinates of the relative vehicle using the location tracking device according to an embodiment.

Referring to FIG. 3 , the location tracking device according to an embodiment provided in the own vehicle 310 may calculate the inclination value of the own vehicle 310 by the inclination θ _cur corresponding to the own vehicle.

According to one side, the location tracking device includes a pitch value (θ _{cur _x} ) corresponding to the inclination in the x-axis direction of the host vehicle 310 , a roll value (θ _{cur _y} ) corresponding to the inclination in the y-axis direction of the host vehicle, and At least one of the yaw values θ _{cur _z} corresponding to the inclination in the z-axis direction may be calculated as the inclination value of the host vehicle 310 .

Next, the location tracking device may calculate the inclination value θ _obj corresponding to the counterpart vehicle 320 .

According to one side, the location tracking device is the opposite vehicle through Equation 1 based on the linear distance value l between the own vehicle 310 and the counterpart vehicle 320 and the height value h of the counterpart vehicle 320 . A gradient value θ _obj corresponding to (320) may be calculated. For example, the inclination calculating unit 220 uses a LiDAR sensor mounted on the own vehicle to determine the linear distance value l between the opposing vehicles 320 and the height value h of the opposing vehicle 320 . can be calculated.

[Equation 1]

θ _obj = arcsin(h/l)

Next, the position tracking device determines the absolute coordinates (X _{obj _g,} Y _{obj _g} ) of the counterpart vehicle 320 based on the inclination value of the own vehicle 310 and the inclination value θ _obj corresponding to the counterpart vehicle 320 . can be calculated.

According to one side, the location tracking device includes a pitch value θ _{cur _x} of the own vehicle 310 , a roll value θ _{cur _y} of the own vehicle 310 , a yaw value θ _{cur _z} of the own vehicle 310 , and a counterpart vehicle. The relative vehicle 320 through an operation based on the x-coordinate value (x _obj ), the y-coordinate value (y _obj ) of the relative coordinate corresponding to 320 , and the inclination value (θ _obj ) corresponding to the counterpart vehicle 320 . ) of the absolute coordinates (X _{obj _g,} Y _{obj _g} ) can be calculated.

For example, the location tracking device may calculate an x-coordinate value (x _obj ) and a y-coordinate value (y _obj ) corresponding to the counterpart vehicle 320 by using a lidar sensor mounted on the own vehicle 310 . .

Specifically, the location tracking device is a value obtained by adding the pitch value of the host vehicle 310 to the x-coordinate value (x _obj ) of the counterpart vehicle 320 and the inclination value corresponding to the counterpart vehicle 320 (θ _{cur _x} + θ _obj ) and the yaw value (θ _{cur_z} ) of the host vehicle 310 are reflected, and the y-coordinate value (y _obj ) of the other vehicle 320 corresponds to the roll value of the own vehicle 310 and the counterpart vehicle 320 . _The absolute coordinates (X _{obj_g} , X _{obj_g ,} Y _{obj_g} ) can be calculated.

[Equation 2]

X _{obj _g} = x _obj * cos(θ _{cur _x} + θ _obj ) * cos(θ _{cur _z} ) - y _obj * cos(θ _{cur _y} + θ _obj ) * sin(θ _{cur_z} )

Y _{obj _g} = x _obj * cos(θ _{cur _x} + θ _obj ) * sin(θ _{cur _z} ) + y _obj * cos(θ _{cur _y} + θ _obj ) * cos(θ _{cur_z} )

On the other hand, the position tracking device may correct the position of the bounding box corresponding to the relative vehicle 320 in the top-view image based on the absolute coordinates (X _{obj _g,} Y _{obj _g} ) calculated through Equation 2 .

For example, the position tracking apparatus may correct the position of the bounding box by setting the calculated absolute coordinates (X _{obj _g,} Y _{obj _g} ) as the center point of the bounding box corresponding to the counterpart vehicle 320 .

4 is a view for explaining a location tracking method according to an embodiment.

In other words, FIG. 4 is a view for explaining an operation method of the location tracking apparatus according to an embodiment described with reference to FIGS. 1A to 3 , and among the contents described with reference to FIG. 4 , it will be described with reference to FIGS. 1A to 3 . A description that overlaps with the content will be omitted.

Referring to FIG. 4 , in step 410 , in the location tracking method according to an embodiment, the location information calculating unit may calculate the inclination value of the own vehicle according to the inclination corresponding to the own vehicle.

According to one side, in step 410, the location tracking method according to an embodiment includes a ruler corresponding to at least one of an x-axis corresponding to the moving direction of the own vehicle, a y-axis corresponding to a direction orthogonal to the x-axis, and a z-axis. It is possible to calculate the inclination value of the vehicle.

In other words, in step 410 , the location tracking method according to the embodiment corresponds to at least one of the traveling direction (x-axis) of the own vehicle, the left-right direction (y-axis) of the own vehicle, and the height direction (z-axis) of the inclination. It is possible to calculate the inclination value of the host vehicle.

According to one side, in step 410, the location tracking method according to an embodiment includes a pitch value corresponding to the inclination in the x-axis direction of the own vehicle, a roll value corresponding to the inclination in the y-axis direction of the own vehicle, and a ruler At least one of yaw values corresponding to the inclination of the vehicle in the z-axis direction may be calculated as the inclination value of the host vehicle.

Next, in step 420 , in the location tracking method according to an embodiment, the gradient calculator may calculate a gradient value corresponding to the opposite vehicle.

According to one side, in step 420 , the location tracking method according to an embodiment may calculate a gradient value corresponding to the counterpart vehicle based on at least one of the inertia measuring apparatus and a captured image corresponding to the counterpart vehicle.

Specifically, in step 420, the location tracking method according to an embodiment calculates an inclination value corresponding to a relative vehicle based on the xy plane coordinates and z coordinates generated during absolute coordinate transformation according to map generation, or measures inertia The device may be used to calculate a gradient value corresponding to the other vehicle.

Further, in step 420, the location tracking method according to an embodiment calculates a gradient value corresponding to the counterpart vehicle based on a difference between a frame corresponding to the current time point and a frame corresponding to a previous time point among the captured images of the other vehicle. You may.

Preferably, in step 420 , the location tracking method according to an embodiment may calculate a gradient value corresponding to the counterpart vehicle through calculation based on a linear distance value between the own vehicle and the counterpart vehicle and a height value of the counterpart vehicle. .

Next, in step 430 , the location tracking method according to the embodiment may calculate the absolute coordinates of the counterpart vehicle based on the inclination value of the own vehicle and the inclination value corresponding to the counterpart vehicle in the absolute coordinate calculator.

According to one side, in step 430, the location tracking method according to an embodiment determines the absolute coordinates of the counterpart vehicle through calculations based on the pitch value of the own vehicle, the roll value of the own vehicle, the yaw value of the own vehicle, and the inclination value corresponding to the counterpart vehicle. can be calculated.

Meanwhile, the location tracking method according to an embodiment may further include correcting the position of a bounding box corresponding to the counterpart vehicle based on the absolute coordinates of the counterpart vehicle calculated by the position corrector.

As a result, by using the present invention, absolute coordinates corresponding to the current position of the counterpart vehicle can be calculated in consideration of the inclination of the inclination on which the host vehicle and the counterpart vehicle are located.

Also, the position of the bounding box corresponding to the counterpart vehicle may be corrected based on the calculated absolute coordinates of the counterpart vehicle.

In addition, it is possible to track the position of the other vehicle more accurately and stably, not only in sections with a steep front, back, left and right slope, but also when driving on a bumpy or bumpy road surface.

As described above, although the embodiments have been described with reference to the limited drawings, various modifications and variations are possible by those skilled in the art from the above description. For example, the described techniques are performed in an order different from the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

200: location tracking device 210: location information calculator
220: slope calculation unit 230: absolute coordinate calculation unit

Claims (12)

a location information calculator configured to calculate a slope value of the host vehicle based on a slope corresponding to the host vehicle;
a gradient calculator for calculating a gradient value corresponding to the other vehicle; and
Absolute coordinate calculation unit for calculating absolute coordinates of the counterpart vehicle based on the inclination value of the host vehicle and the inclination value corresponding to the counterpart vehicle
including,
The inclination value of the host vehicle is,
and an inclination value corresponding to at least one of an x-axis corresponding to the moving direction of the host vehicle, a y-axis corresponding to a direction orthogonal to the x-axis, and a z-axis,
The location information calculation unit,
A pitch value corresponding to the inclination in the x-axis direction of the host vehicle, a roll value corresponding to the inclination in the y-axis direction of the host vehicle, and a yaw corresponding to the inclination in the z-axis direction of the host vehicle Calculate at least one of the values,
The absolute coordinate calculation unit,
Calculating the absolute coordinates of the relative vehicle through an operation based on a pitch value of the own vehicle, a roll value of the own vehicle, a yaw value of the own vehicle, and a slope value corresponding to the counterpart vehicle
location tracking device. delete delete delete According to claim 1,
The slope calculation unit,
calculating an inclination value corresponding to the counterpart vehicle based on at least one of an inertial measurement unit (IMU) and a captured image of the counterpart vehicle;
location tracking device. 6. The method of claim 5,
The slope calculation unit,
Calculating a gradient value corresponding to the counterpart vehicle based on a difference between a frame corresponding to a current time point and a frame corresponding to a previous time point among the captured images of the counterpart vehicle;
location tracking device. According to claim 1,
The slope calculation unit,
calculating a gradient value corresponding to the counterpart vehicle through calculation based on a linear distance value between the host vehicle and the counterpart vehicle and a height value of the counterpart vehicle
location tracking device. According to claim 1,
A position correcting unit correcting a position of a bounding box corresponding to the relative vehicle based on the calculated absolute coordinates of the relative vehicle
A location tracking device further comprising a. calculating, by the location information calculating unit, a slope value of the host vehicle based on a slope corresponding to the host vehicle;
calculating, by the gradient calculator, a gradient value corresponding to the other vehicle; and
Calculating the absolute coordinates of the relative vehicle based on the inclination value of the host vehicle and the inclination value corresponding to the counterpart vehicle, in the absolute coordinate calculator
including,
The inclination value of the host vehicle is,
and a slope value corresponding to at least one of an x-axis corresponding to the moving direction of the host vehicle, a y-axis corresponding to a direction orthogonal to the x-axis, and a z-axis,
Calculating the inclination value of the host vehicle comprises:
A pitch value corresponding to the inclination in the x-axis direction of the host vehicle, a roll value corresponding to the inclination in the y-axis direction of the host vehicle, and a yaw corresponding to the inclination in the z-axis direction of the host vehicle Calculate at least one of the values,
Calculating the absolute coordinates of the relative vehicle comprises:
Calculating the absolute coordinates of the relative vehicle through an operation based on a pitch value of the own vehicle, a roll value of the own vehicle, a yaw value of the own vehicle, and a slope value corresponding to the counterpart vehicle
How to track location. delete delete delete

Images