KR20180096236A - Apparatus and mathod for detecting obstacle of a vehicle - Google Patents

Abstract

The present invention relates to an apparatus and a method for detecting an obstacle of a vehicle to detect various obstacles in a driving image, wherein the apparatus comprises: an image acquisition unit acquiring an image; a characteristic map generating unit generating a characteristic map of the acquired image; a scan line setting unit setting at least one scan line corresponding to the generated characteristic map; a space time pattern map generating unit generating a space time pattern map corresponding to the set scan line; an obstacle detecting unit detecting an obstacle by analyzing the generated space time pattern map; and a control unit controlling driving of a vehicle in accordance with the detected obstacle.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to an obstacle detecting apparatus,

The present invention relates to a vehicle, and more particularly, to an apparatus and method for detecting obstacles in a vehicle that detect various obstacles in a running image.

Obstacle detection techniques in general driving images are divided into using features of obstacles, recognizing shapes of obstacles and analyzing motion of obstacles.

The way of using the feature of the obstacle is a method of using the symmetry of vehicle, shadow or SIFT.

The problem with this approach is that the performance is significantly reduced in frames where the characteristics of the obstacle are not fully expressed, and there is not a high probability that the features effective for obstacle detection are fully present.

In addition, the method of recognizing the shape of the obstacle is to detect only obstacles included in the target of the classifier using a classifier.

The problem with this method is that it is difficult to perform real-time calculation due to the complexity of the operation of the classifier, and it is impossible to recognize obstacles other than those specified in the classifier.

In addition, in the method of analyzing motion, it is difficult to acquire motion information from the running image, and a correspondence matching method such as optical flow is mainly used. In the optical flow, The first problem mentioned above may occur at the same time, and when the motion is large, the error may be large and the detection performance may be reduced.

Therefore, there is a demand for an obstacle detection method capable of accurately and quickly detecting an obstacle in a running image in a simple manner in the future.

An object of the present invention is to provide an apparatus and method for detecting an obstacle in a vehicle capable of detecting a rapidly moving obstacle by generating a space time pattern map corresponding to a scan line.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of the invention, unless further departing from the spirit and scope of the invention as defined by the appended claims. It will be possible.

According to an aspect of the present invention, there is provided an apparatus for detecting an obstacle in a vehicle, including an image acquisition unit for acquiring an image, a characteristic map generator for generating a characteristic map of the acquired image, A space line pattern map generation unit for generating a space line pattern map corresponding to the set scan line, a space line pattern map generation unit for analyzing the generated space line pattern map to detect an obstacle, And a control unit for controlling the driving of the vehicle in accordance with the detected obstacle.

According to another aspect of the present invention, there is provided a method for detecting an obstacle in a vehicle, the method comprising: acquiring an image; generating a characteristic map of the acquired image; setting at least one scan line corresponding to the generated characteristic map; Generating a space-time pattern map corresponding to the set scan line, analyzing the generated space-time pattern map to detect an obstacle, and controlling operation of the vehicle according to the detected obstacle .

An apparatus and method for detecting an obstacle in a vehicle according to at least one embodiment of the present invention configured as described above is a technology for analyzing a change of an obstacle using a continuous image obtained by a front camera and detecting an obstacle showing a specific change, An obstacle moving faster than the car can be detected by using the space-time pattern map.

In addition, since the present invention detects an obstacle moving faster than a car, the present invention provides a faster calculation speed than existing methods of analyzing the moving image.

Further, since the temporal change and the spatial change of the traveling image can be used simultaneously, the present invention provides a fast processing time for detecting an obstacle.

In addition, the present invention provides an effect that is not affected by camera performance such as lens distortion and the image acquisition environment because an obstacle is detected based on a space-time pattern map instead of a method of detecting an obstacle based on an original image .

The effects obtained by the present invention are not limited to the above-mentioned effects, and other effects not mentioned can be clearly understood by those skilled in the art from the following description will be.

1 is a block diagram illustrating an apparatus for detecting an obstacle in a vehicle according to the present invention.
FIG. 2 is a block diagram illustrating a scan line setting unit of FIG. 1. FIG.
FIG. 3 is a block diagram illustrating a space-time pattern map generator of FIG. 1. FIG.
FIGS. 4 to 7 are diagrams for explaining a process of setting a scan line.
8 is a diagram for explaining a process of generating a characteristic map.
9 is a view showing a scan line set in the original image.
FIG. 10 is a diagram for explaining a process of generating a space-time pattern map.
11 is a diagram showing an accumulated space-time pattern map and its subunits.
12 is a view showing a trend line slope of the space-time pattern map.
13 is a view showing the moving speed of the obstacle according to the slope of the trend line.
FIG. 14 is a diagram for explaining a micro-slope calculation process. FIG.
15 to 17 are views showing a space-time pattern map according to the obstacle detection result.
18 is a flowchart for explaining an obstacle detection method of a vehicle according to the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Throughout the specification, when an element is referred to as "comprising ", it means that it can include other elements as well, without excluding other elements unless specifically stated otherwise. Also, the terms " part, "" module," and " module ", etc. in the specification mean a unit for processing at least one function or operation and may be implemented by hardware or software or a combination of hardware and software have.

Throughout the specification, when an element is referred to as "comprising ", it means that it can include other elements as well, without excluding other elements unless specifically stated otherwise. In addition, parts denoted by the same reference numerals throughout the specification denote the same components.

Hereinafter, an apparatus and method for detecting an obstacle of a vehicle, which can be applied to embodiments of the present invention, will be described in detail with reference to Figs. 1 to 18. Fig.

FIG. 1 is a block diagram illustrating an apparatus for detecting an obstacle in a vehicle according to the present invention. FIG. 2 is a block diagram illustrating a scan line setting unit of FIG. 1, and FIG. 3 is a block diagram of a space- Fig.

1 to 3, an apparatus 1000 for detecting an obstacle in a vehicle according to the present invention includes an image obtaining unit 100, a characteristic map generating unit 200, a scan line setting unit 300, A map generation unit 400, an obstacle detection unit 500, and a control unit 600.

Here, the image acquisition unit 100 may be a camera for acquiring an image.

For example, the camera may be mounted in front of the vehicle to photograph the forward image of the vehicle in real time.

Then, the characteristic map generation unit 200 can generate a characteristic map of the acquired image.

Here, the characteristic map generation unit 200 can generate the characteristic map based on the edge of the acquired image.

The reason for generating the characteristic map is that when the space-time pattern map is generated based on the acquired original image, the data amount is too large. However, when the space-time pattern map is generated based on the characteristic map, Therefore, it is possible to rapidly detect the obstacle by reducing the processing time.

In addition, the characteristic map generating unit 200 can remove the noise of the characteristic map by generating the characteristic map based on the edge of the acquired image.

The reason is that removing the noise of the characteristic map makes only the required components appear sharper.

In some cases, the characteristic map generator 200 may further perform post-processing to apply smoothing after binarizing the generated characteristic map.

Next, the scan line setting unit 300 may set at least one scan line corresponding to the generated characteristic map.

2, the scan line setting unit 300 includes a front direction vector calculating unit 310, a first scan line generating unit 320, a second scan line generating unit 330, (340).

At this time, the front direction vector calculation unit 310 can calculate the front direction vector of the camera from the characteristic map.

For example, the frontal direction vector calculation unit 310 may calculate the frontal direction vector based on the difference between the calculated two coordinates and the ground coordinates corresponding to the principal point of the camera and the ground coordinates of the camera.

Then, the first scan line generation unit 320 can generate the first scan line in the ground coordinate system based on the calculated front direction vector.

Here, the first scan line generator 320 calculates a straight line that is orthogonal to the calculated front direction vector, divides the selected area based on the calculated straight line into a plurality of line segments, sets the center point of the divided line segments as a reference point, It is possible to generate a first scan line parallel to the front direction vector after passing through a predetermined reference point.

In one example, the region selected based on the obtained straight line may be an area for detecting an obstacle.

The first scan line may include a front direction vector and a corresponding reference point.

In one example, the first scan lines in the ground coordinate system may be plural, and the plurality of first scan lines may be parallel to each other.

Next, the second scan line generation unit 330 can generate the second scan line in the image coordinate system based on the generated first scan line.

For example, the second scan line generation unit 330 obtains the horizon line based on the generated first scan line, obtains the vanishing point based on the straight line obtained by converting the first scan line to the image coordinates, A reference point and a second scan line passing through the vanishing point can be generated.

Here, the second scan line generation unit 330 may set a straight line passing through the vanishing point as a horizon line when the first scan lines are gathered at one vanishing point in the image coordinate system when finding the horizon line.

When the vanishing point is found, the second scan line generating unit 330 may convert the first scan line in the ground coordinate system into a straight line in the image coordinate system, and set the intersection of the converted straight line and the horizon line as a vanishing point.

Next, the scan line correction unit 340 can correct the error of the generated second scan line.

Here, the scan line correction unit may correct an error of the second scan line by removing a part of the second scan line located in the vicinity of the horizon line.

Meanwhile, the space-time pattern map generator 400 may generate a space-time pattern map corresponding to the set scan line.

3, the space-time pattern map generator 400 may include a first generator 410, a storage 420, and a second generator 430.

At this time, the first generating unit 410 may generate a row image corresponding to each scan line for each frame.

The storage unit 420 may accumulate and accumulate one or more frames of the row image of each generated scan line.

The second generating unit 430 may generate a space-time pattern map in which the row images of the respective scan lines are accumulated, based on the row images stored in the storage unit 420. [

In one example, the space-time pattern map includes a plurality of sub-units, and the plurality of sub-units may include an accumulated row image of at least three frames or more.

Next, the obstacle detecting unit 500 can detect an obstacle by analyzing the generated space time pattern map.

Here, the obstacle detector 500 may analyze the generated space-time pattern map to obtain the slope of the trend line included in the space-time pattern map, and may detect the obstacle based on the slope.

If the slope is positive, the obstacle detecting unit 500 recognizes the obstacle as a faster obstacle than the car, and if the inclination is negative, the obstacle detecting unit 500 can recognize the obstacle as a slower obstacle than the car.

When there are a plurality of trend lines included in the space time pattern map, the obstacle detecting unit 500 can select the brightest trend line as the representative trend line and obtain the slope of the selected representative trend line.

In some cases, when there are a plurality of representative trend lines, the obstacle detection unit 500 may select one representative trend line based on the most constant rule and obtain the slope of the selected representative trend line.

Next, the control unit 600 can control the vehicle operation according to the detected obstacle.

As described above, the present invention can detect an obstacle moving faster than a car by using a space-time pattern map, by analyzing a change of an obstacle by using a continuous image obtained by a front camera and detecting an obstacle showing a specific change.

In addition, since the present invention detects an obstacle moving faster than a car, the calculation speed can be faster than existing methods of analyzing the moving original image.

Further, since the present invention can simultaneously use the temporal change and the spatial change of the traveling image, the processing time for detecting the obstacle can be fast.

In addition, the present invention detects an obstacle based on a space-time pattern map instead of detecting an obstacle based on an original image, so that it may not be affected by camera performance such as lens distortion and an image acquisition environment.

FIGS. 4 to 7 are diagrams for explaining a process of setting a scan line.

As shown in Figs. 4 to 7, in order to generate a space time pattern map (STP Map) for detecting the direction of movement, information on the vehicle front direction is required.

The present invention assumes that the frontal direction of the camera coincides with the frontal direction of the vehicle since the camera of the vehicle is disposed toward the front of the vehicle.

7, the ground coordinates corresponding to the camera principal point and the ground coordinates of the camera are calculated using a projective transformation, and the camera front direction vector 510 can be obtained through the difference .

That is, the frontal direction vector calculation unit of the present invention may calculate the frontal direction vector 510 based on the difference between the calculated two coordinates and the ground coordinate corresponding to the principal point of the camera and the ground coordinate of the camera.

7, a straight line 520 orthogonal to the camera front direction vector 510 is obtained, and an area 550 where a cut-in obstacle is detected on the straight line 520, And the selected region 550 is uniformly divided.

7, assuming that the midpoint of the segmented line segment 530 is a reference point 540, a straight line passing through the reference point 540 and parallel to the camera front direction vector 510 is referred to as a virtual scan (530). ≪ / RTI >

Accordingly, as shown in FIG. 7, a virtual scan line 530 is represented and stored as a front direction vector 510 and a corresponding reference point 540.

As shown in Fig. 4, the virtual scan lines in the ground coordinate system are all parallel and converge at one vanishing point P1 in the image coordinate system, and this vanishing point P1 is on the horizon C.

In the present invention, the horizontal line C is obtained in the projective transformation, and then the straight line A and the horizon line C, which are obtained by converting one of the virtual scan lines A in the ground coordinate system into image coordinates, Find the vanishing point (P1) through the intersection.

When the image distortion is removed, the virtual scan line A is converted into a straight line in the image coordinate system. Thus, the point on the image corresponding to the reference point P2 and the vanishing point P1 are successively connected to the scan lines B .

At this time, the scan line is formed below the horizon line C, starting from the vanishing point P1 and passing the reference point P2, as shown in Fig.

In the present invention, a certain length in the vicinity of the horizon line C is removed because the movement of the detection target is small in the vicinity of the horizon line C of the scan line B and an error is large.

7, the first scan line generation unit of the present invention obtains a straight line 520 orthogonal to the calculated front direction vector 510, and selects a plurality of selected regions 550 on the basis of the obtained straight line 520 A center point of the divided line segments is defined as a reference point 540 and a virtual scan line 540 parallel to the front direction vector 510 may be generated passing through a predetermined reference point 540. [

Here, the selected region 550 based on the obtained straight line may be an area for detecting an obstacle.

The virtual scan line 530 of the present invention may include a front direction vector 510 and a corresponding reference point 540.

Further, as shown in Fig. 7, there are a plurality of virtual scan lines in the ground coordinate system, and a plurality of virtual scan lines may be parallel to each other.

Next, the second scan line generation unit of the present invention generates a second scan line based on a straight line obtained by obtaining the horizon line C based on the generated virtual scan line A and converting the virtual scan line A into image coordinates, , The vanishing point P1 can be obtained and the scan line B passing through the converted reference point P2 and the vanishing point P1 can be generated.

Here, the second scan line generation unit of the present invention generates a second scan line when the virtual scan lines A converge at one vanishing point P1 in the image coordinate system when finding the horizon line C, C).

The second scan line generation unit of the present invention converts the virtual scan line A in the ground coordinate system into a straight line in the image coordinate system and obtains the intersection of the converted straight line and the horizon line C It can be set to the vanishing point P1.

Next, the scan line correction unit of the present invention can correct an error of the scan line B by removing a part of the scan line B located near the horizon line (C).

Further, in the present invention, as shown in Fig. 5, there is a need for a method of detecting a motion direction in order to detect a cut-in obstacle in a forward running image.

In the case of a cut-in obstacle, the vehicle must pass from the rear or side of the vehicle to the front of the vehicle, and thus includes a process of overtaking. This means that the cut-in obstacle must be positive in the vehicle frontal direction.

In addition, when a virtual scan line is formed in the vehicle front direction to detect the sign of the vehicle front-surface direction speed component of the object, the motion in which the vehicle front surface direction speed component is positive moves one-dimensionally forward on the virtual scan line (B)

Conversely, for objects that are stationary on the ground, they are shown to be pushed back on the virtual scan line (a)

Further, even when the vehicle is rotating, this phenomenon is preserved in the virtual scan line in which the following equation (1) holds.

Equation 1

d <V / w

In this case, d represents the distance between the virtual scan line and the camera of the vehicle, V represents the speed of the vehicle, and w represents the angular speed of the vehicle.

Even in the case of a low-speed U-turn, the value of the right side of the equation (1) is about 10 m, and therefore includes all the virtual scan lines of a sufficient distance.

In order to convert the virtual scan lines existing on the ground coordinate system into an adaptive scanline in the image, a projective transformation must be used.

Here, since the occlusion exists, in the converted adaptive scan line, the points on the virtual scan line can not be observed equally, but as shown in Fig. 6, the point (d ) And the point c on the virtual scan line are points on the same object, information on the motion direction can be obtained equally because the motion directions are the same.

Therefore, the present invention detects obstacles that pass by detecting an object moving forward in the adaptive scan line.

Then, in the present invention, when an obstacle is detected in a scan line of a specific area, it is determined that the obstacle is a cut-in obstacle, and otherwise, the obstacle is judged to be an obstacle that simply passes.

FIG. 8 is a view for explaining a process of generating a characteristic map, FIG. 9 is a view showing a scan line set in an original image, and FIG. 10 is a diagram for explaining a process of generating a space time pattern map.

As shown in FIGS. 8 and 9, the present invention simplifies data to be constructed in a space-time pattern map (STP Map) through an edge detector such as Sobel and SUSAN.

As shown in FIG. 8, the present invention can generate a feature map (Edge Map) based on an edge instead of a pixel value of an original image, and post-process the generated feature map.

Here, the reason for the post-processing is to remove the data noise of the feature map and make the necessary components well-exposed.

Further, the present invention may apply smoothing after binarization of the post-processed feature map.

That is, the characteristic map generator of the present invention can generate the characteristic map based on the edge of the acquired image.

In addition, the characteristic map generator of the present invention may remove the noise of the characteristic map when generating the characteristic map based on the edge of the acquired image.

On the other hand, as shown in FIG. 9, a plurality of scan lines may be set in the original image, and the length of the scan lines for each position of the original image may vary.

10, in order to generate a space time pattern map having a predetermined size, interpolation is performed to form a row image of the scan line 1 having a constant length, The scan line 1 at the same position is similarly formed into a row image having a constant length, and the operation of stacking on the previous row image is repeated.

An image in which the scan lines thus constructed are stacked is called a space-time pattern map.

Similarly, the same operation is repeated for the other scan lines (2, 3, 4) selected.

In the present invention, for example, there are four selected scan lines (1, 2, 3, 4), so that there can exist about four space time pattern maps.

That is, the space-time pattern map generator of the present invention generates a row image corresponding to each scan line for each frame, accumulates and accumulates one or more of the generated row images of the scan lines, A space-time pattern map in which a row image of a scan line is accumulated can be generated.

Here, the space time pattern map includes a plurality of subunits, and the plurality of subunits may include, but not limited to, an accumulated row image of at least three frames.

FIG. 11 is a view showing the accumulated space time pattern map and its subunits, FIG. 12 is a diagram showing the trend line slope of the space time pattern map, FIG. 13 is a diagram showing the moving speed of the obstacle according to the slope of the trend line, FIG. 8 is a view for explaining a process of calculating a micro-slope. FIG.

11, when the cumulative size of the row image is larger than 3, that is, when the space-time pattern map in which the scan lines of at least three frames are accumulated is generated, the space- And generates a lower subunit 620 of the space-time pattern map 610 in which the map is the minimum unit of obstacle detection.

This prevents the accumulation of space-time patterns from becoming larger than necessary due to accumulation of space-time patterns, and recognizes obstacles in real time using only the time of the previous two frames including the current scan line.

12, when the subunit 620 of the spatiotemporal pattern map 610 is constructed, the slope of the trend line 630, which appears most brightly, is obtained.

A common data fitting method may be used. However, in order to analyze a space-time pattern in a short time interval as in the present invention, it is proper to implement the method by a Recursive & Feedback method. When there are many trend lines 630, Based on the rule, a representative trendline (630) and one slope are selected.

As shown in Fig. 12, the background is pushed backward on the screen, and the phenomenon that the obstacle, which is a cut, moves relatively forward appears as a slope on the scan line.

As shown in FIG. 13, if the slope of the estimated line 630 is a positive number 730, it is determined that the obstacle is faster than the car. If the slope of the estimated line 630 is a negative number 710, it is determined that the obstacle is a slow obstacle. , It can be judged that the car is similar to the speed.

One of the features of the present invention is that the accurate calculation of the slope is not included because it is based on the time-space pattern data of short time.

This is because the present invention uses not only the exact value of the slope but also the slope sign to detect the obstacle.

Therefore, a rather important part is to find a valid line segment to obtain the slope in the spatiotemporal pattern.

As shown in Fig. 14, the method of calculating the micro-slope of the Recursive & Feedback structure means that when a moving obstacle is erroneously detected, the erroneous detection point is moved differently from the point on the moving obstacle The probability of not being detected again is increased. Nevertheless, the point detected as a moving obstacle has reliability, and the probability of moving obstacle is high in the next interpolation.

15 to 17 are views showing a space-time pattern map according to the obstacle detection result.

As shown in FIGS. 15 to 17, the present invention is a technology for analyzing a change of an obstacle by using a continuous image obtained by a front camera and detecting an obstacle showing a specific change, Moving obstacles can be detected.

In addition, since the present invention detects an obstacle moving faster than a car, the calculation speed is faster than the conventional methods of analyzing the moving original image.

Further, since the present invention can simultaneously use the temporal change and the spatial change of the traveling image, the processing time for detecting the obstacle is fast.

In addition, the present invention does not depend on the camera performance such as lens distortion and the image acquisition environment because the obstacle is detected based on the space-time pattern map instead of the obstacle detection based on the original image.

According to another aspect of the present invention, there is provided a method of adaptively setting a scan line in the direction of the front of a camera on the basis of driving information of a vehicle in a running image, In order to compensate for the disadvantages of real - time processing, we propose a method of detecting obstacles by analyzing the generated space - time pattern using the previous feedback method.

The present invention detects a moving obstacle by calculating a slope of a pattern on a space-time pattern, so that the calculation speed is faster than conventional methods of analyzing image information at all positions of an original image, and the performance is stable independent of a camera such as lens distortion And can be applied regardless of wide angle / narrow angle.

18 is a flowchart for explaining an obstacle detection method of a vehicle according to the present invention.

As shown in Fig. 18, the present invention acquires an image (S10)

Then, the present invention generates a characteristic map of the acquired image (S20)

Then, the present invention sets at least one scan line corresponding to the generated property map (S30)

Next, the present invention generates a space-time pattern map corresponding to the set scan line (S40)

In the present invention, an obstacle is detected by analyzing the generated space-time pattern map (S50)

Then, the present invention controls the driving of the vehicle according to the detected obstacle (S60)

Next, the present invention confirms whether an obstacle detection end request is received (S70), and ends the obstacle detection if a detection end request is received.

The present invention described above can be embodied as computer-readable codes on a medium on which a program is recorded. The computer readable medium includes all kinds of recording devices in which data that can be read by a computer system is stored. Examples of the computer readable medium include a hard disk drive (HDD), a solid state disk (SSD), a silicon disk drive (SDD), a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, , And may also be implemented in the form of a carrier wave (e.g., transmission over the Internet).

Accordingly, the above description should not be construed in a limiting sense in all respects and should be considered illustrative. The scope of the present invention should be determined by rational interpretation of the appended claims, and all changes within the scope of equivalents of the present invention are included in the scope of the present invention.

100:
200: characteristic map generation unit
300: scan line setting unit
400: Spatiotemporal pattern map generator
500:
600:

Claims (20)

An image acquiring unit acquiring an image;
A characteristic map generation unit for generating a characteristic map of the acquired image;
A scan line setting unit setting at least one scan line corresponding to the generated characteristic map;
A space time pattern map generator for generating a space time pattern map corresponding to the set scan line;
An obstacle detection unit for detecting an obstacle by analyzing the generated space-time pattern map; And,
And a control unit for controlling operation of the vehicle in accordance with the detected obstacle. The method according to claim 1,
Wherein the characteristic map generator generates a characteristic map based on the edge of the acquired image. 3. The method of claim 2,
Wherein the characteristic map generator removes noise of the characteristic map when generating the characteristic map based on the edge of the acquired image. The method according to claim 1,
The scan line setting unit,
A front direction vector calculation unit for calculating a front direction vector of the camera from the characteristic map;
A first scan line generation unit for generating a first scan line in the ground coordinate system based on the calculated front direction vector;
A second scan line generation unit for generating a second scan line in the image coordinate system based on the generated first scan line;
And a scan line correction unit for correcting an error of the generated second scan line. 5. The method of claim 4,
Wherein the front direction vector calculation unit calculates the ground coordinates corresponding to the principal point of the camera and the ground coordinates of the camera and calculates the front direction vector based on the difference between the two calculated coordinates, Detection device. 5. The method of claim 4,
Wherein the first scan line generation unit obtains a straight line orthogonal to the calculated front direction vector and divides the selected area based on the obtained straight line into a plurality of line segments, sets the center point of the divided line segments as a reference point, And generates a first scan line parallel to the front direction vector passing through the reference point. The method according to claim 6,
And the area selected based on the obtained straight line is an area for detecting an obstacle. The method according to claim 6,
Wherein the first scan line includes the front direction vector and a corresponding reference point. 5. The method of claim 4,
A plurality of first scan lines in the ground coordinate system,
And the plurality of first scan lines are parallel to each other. 5. The method of claim 4,
The second scan line generator obtains a horizon on the basis of the generated first scan line and obtains a vanishing point based on a straight line obtained by converting the first scan line into image coordinates, And generates a second scan line passing through the vanishing point. 11. The method of claim 10,
Wherein the second scan line generator sets a straight line passing through the vanishing point as a horizon line when the first scan lines converge to one vanishing point in the image coordinate system when the horizon line is calculated, . 11. The method of claim 10,
Wherein the second scan line generation unit converts the first scan line in the ground coordinate system into a straight line in the image coordinate system and sets the intersection of the converted straight line and the horizon line as a vanishing point when the vanishing point is found. . 5. The method of claim 4,
Wherein the scan line correction unit corrects an error of the second scan line by removing a part of a second scan line located near the horizon line. The method according to claim 1,
Wherein the space-time pattern map generator comprises:
A first generating unit for generating a row image corresponding to each scan line for each frame;
A storage unit for accumulating one or more frames of the generated row images of the scan lines;
And a second generation unit for generating a space time pattern map in which a row image of each scan line is accumulated based on the row images stored in the storage unit. 15. The method of claim 14,
Wherein the space-time pattern map includes a plurality of sub-units,
Wherein the plurality of subunits include an accumulated row image of at least three frames. The method according to claim 1,
Wherein the obstacle detection unit analyzes the generated space time pattern map to obtain an inclination of a trend line included in the space time pattern map, and detects an obstacle based on the inclination. 17. The method of claim 16,
Wherein the obstacle detecting unit recognizes the obstacle as a obstacle faster than the car if the inclination is positive and recognizes the obstacle as a slower obstacle than the car if the inclination is negative. 17. The method of claim 16,
Wherein the obstacle detection unit selects a brightest trend line as a representative trend line and obtains a slope of the selected representative trend line when a plurality of trend lines included in the space time pattern map are included. 19. The method of claim 18,
Wherein the obstacle detection unit selects one representative trend line based on the most constant rule when a plurality of the representative trend lines are present and obtains a slope of the selected representative trend line. Acquiring an image;
Generating a characteristic map of the acquired image;
Setting at least one scan line corresponding to the generated characteristic map;
Generating a space time pattern map corresponding to the set scan line;
Analyzing the generated space-time pattern map to detect an obstacle; And,
And controlling operation of the vehicle in accordance with the detected obstacle.

Images