JP3069952B2 - Vehicle Recognition Method Using Video System - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for recognizing the presence of a vehicle using an image system.
From the camera video signal to be input, accurately recognize the Yin dripping between the bumper and the tires of the vehicle, through the shadow of the recognized vehicle, using a video system to determine the presence of vehicles approaching vehicle This is related to the recognition method.

[0002]

2. Description of the Related Art In general, an image system applied to an automobile is, in many cases, an apparatus mounted on an unmanned automobile and capable of controlling the traveling of the vehicle by itself. In many cases, the above-mentioned unmanned vehicles distinguish a road form and a lane from the front of the running vehicle to distinguish the state of the road surface, and further, the front of the running vehicle to determine an approaching obstacle or the like. It is monitored sequentially, and operation is performed based on the results determined.
The rudder device, the brake device, and the acceleration device are automatically controlled, and as a result, the vehicle itself can travel.

[0003]

[SUMMARY OF THE INVENTION] However, conventional video systems, from the front of the vehicle running, in order to recognize the opponent vehicle approaching the vehicle by identifying the shade of the vehicle from the video system input Although it is possible to recognize, fallacy of mistaking look at the shadow of such as buildings and trees in the vehicle of the shadow is generated
Was . Conventional video systems used a method for classifying approaching vehicles by identifying a shadow in contact with the surface of the road between the bumper and the tire in front of the approaching vehicle and classifying the approaching vehicle. the building of shade and general shadow that hung on top of, cases commit to recognize errors by mistake as a vehicle occurs
I was In other words, conventional video systems, vehicles and the side lane, the structure of the road, or a shade such as buildings and trees are hanging on the surface of the road, there is a problem that commit recognizing errors erroneous as a vehicle .

[0004] The present invention, in order to solve the problems described above, from the screen of travel ahead of the image inputted from the camera unit, is fractionated shade by comparing the gray level sequentially, which is the fractionated shade By calculating the variance value for the brightness, it is the shade formed at the bottom of the vehicle, or
Common anionic and is of exactly when determined by discriminated result by recognizing vehicle approaching, which can eliminate the errors that were Oite occurred conventional video system, video system It is an object of the present invention to provide a method for recognizing a vehicle using a vehicle.

[0005]

The video signal detected by the camera is sequentially compared with the gray level in one direction from a predetermined direction to detect a portion where the gray level changes rapidly. further forming only a sensing step of recognizing shade portion of the shade, in order to analyze the portion of the sensed negative, the U Indou so the portion where the gray level changes suddenly in the center of the lower surface of the window over and the window over formation step of, from behind, which is set on the lower surface of the formed window over compares the calculation step of calculating a variance value for the brightness, the reference value set the previous SL computed variance And a step of recognizing the approach of the vehicle by recognizing the shadow of a road surface formed at a lower part of the vehicle.

[0006] The identification stage of shade, the steps of dispersion value obtained is determined as the shadow of the vehicle if the reference Ne以, is less than the reference value before <br/> Symbol resulting dispersion value And determining a general shade. Further, in the shade identification step, a control signal is output according to the determined result, and the steering control unit, the brake control unit,
And a control step of controlling the associated devices of the acceleration controller, after executing the above SL control step, whether comparison completion of the gray level
Judge, and if the comparison is not completed, repeat the gray level
A routine stage for performing the following comparisons and controlling the associated device:
It is characterized by comprising a floor .

[0007]

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, refer to the accompanying drawings,
Hazuki group to an embodiment of the present invention, a method of recognizing a vehicle 3 using a video system according to the present invention (see FIG. 2) will be described in detail. Figure 1 is a block diagram illustrating a control state of the present invention and general video systems, is mounted on one side of the front of the vehicle 3, the camera unit 10 to take an image of the object 1, the camera unit 10 A main control unit 12 that outputs a control signal as a video signal, a steering control unit 14 that controls a steering device using a control signal from the main control unit 12, and a main control unit 12
A brake control unit 16 that controls the brake device by the control signal of the above, and an acceleration control unit 18 that controls the acceleration device by the control signal of the main control unit 12.

[0008] The main control unit 12 of the configuration video system as described above, from the video signal input through the camera unit 10, and fractionated further in detail the object 1 in the running direction, to determine the presence of the vehicle 3 It becomes possible.

FIG. 2 shows a state in which a video signal input from the camera unit 10 is covered with a certain type of window 2 so that analysis can be easily performed. As shown in FIG. In addition, when the vehicle 3 is captured through the window 2, a line L1 that contacts the surface of the road can be searched for at the edge of the lower part of the object 1.

FIG. 3 is a diagram showing a state in which the image of a shadow and a road are sensed by an image system to which the present invention is applied. The main control unit 12 operates according to an image signal input from the camera unit 10. , It is possible to search for all the shades 4 in which the brightness has changed suddenly while sequentially comparing the gray levels from the bottom to the top, and the recognized shades 4
By calculating a variance value for the brightness of the vehicle 3 and comparing the calculated value with a set value, it is possible to identify only the shadow 4 formed at the lower part of the vehicle 3.

[0011] For example, anionic 4 formed through vehicle 3 buildings and side lane, sometimes dripping on the surface of the road ahead running. If the shadow 4 is erroneously recognized as the shadow 4 of the approaching vehicle 3, the imaging system will cause an error.
Ri, a variance value for the brightness of the sensed negative 4, comparing the value set by the comparison result, it is possible to identify the shade 4 of the vehicle 3.

The relational expression and the theoretical explanation that can obtain the variance value for the brightness of the recognized shadow 4 are briefly described as follows. In the present invention, such a variance value is referred to as a local variance in the present invention because the variance value for the brightness that can be obtained from the recognized shade 4 is analyzed by covering a window of the form. Obtained shade 4
Is subdivided into lattice stripes of a fixed size, it is possible to obtain a gray level for brightness from each lattice stripe. For example, if the gray level that can be obtained from each of the subdivided grid patterns is in units of 8 bits, 256
It is possible to classify up to. In addition, the shade 4 subdivided and stylized by the above-mentioned lattice fringe of a certain size can obtain its variance (local variance) through the following relational expression.

[0013]

(Equation 1)

Μ is the average value of the gray levels of the shade 4, N is the number of grids subdivided into shades, and Xi is the gray level (value of each function) of each subdivided grid.

[0015] In other words, the physical meaning of the local variance value that can be obtained through a relational expression mentioned above, each lattice fringes, represents whether distributed by area of how much than the average value, negative When 4 is very dark, its value (the local variance value described above) is close to 255, while when shade 4 is very bright, it is close to 0.

Therefore, by comparing the obtained variance value (local variance value) with the set comparison value, and discriminating the magnitude of the value, the shadow 4 hanging at the lower part of the vehicle 3 is removed. It becomes possible to recognize, and as a result, it becomes possible to classify the approaching vehicle 3.

Further, like the illustrated histogram for local variance of FIG. 4, the distribution of the histogram is
When concentrated on one side, the variance value (local variance value) becomes small.

Contrary to the histogram shown in FIG. 4, in the case of the vehicle 3, the distribution of the histogram is not biased to one side as in the histogram shown in FIG. And when the distribution is relatively uniform, the obtained variance value (local variance value) becomes large.

As described above, the image of the object 1 photographed by the camera unit 10 shows the degree of dispersion with respect to the brightness in the case of the single ship shade 4 and the case of the vehicle 4 shade 4. by but represented by each different, the main control unit 12 through those comparison results, outputs a control signal when the vehicle 3 approaches Sutiarin grayed control part 14, the brake control unit 16 and the acceleration controller 18, It is possible to automatically control the traveling of the vehicle 3 to an optimal state.

Therefore, in the video system according to the present invention, as shown in the control flowchart of the main control unit 12 shown in FIG. 6, the shade 4 of the vehicle 3 and the general shade 4 are transmitted to the camera unit 10. By discriminating and recognizing the input image screen and outputting the control signal, it is possible to prevent the object 1 from being erroneously recognized.

Furthermore, when the video system according to the present invention is used in combination with the logic of a different video system, it becomes possible to make the recognition of the vehicle more accurate and to greatly improve its reliability.

The main control unit, to which a video signal is input from the camera unit, sequentially compares gray levels and separates portions where brightness changes abruptly to separate shadows.
In addition, the local variance value is calculated by a predetermined method through the classified shadows, and is compared with a set reference value, whereby it is possible to accurately separate the vehicle shadows and general shadows. Furthermore, by outputting a control signal based on the sorted result and automatically controlling the running of the vehicle, it is possible to prevent a mistake in recognition of an approaching vehicle and increase the reliability of the image system. Become.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a control state of a conventional video system.

FIG. 2 is a state diagram illustrating a state in which an input video signal is analyzed with a window of a fixed format applied thereto according to the present invention;

FIG. 3 is a diagram illustrating a state where an image of a shadow and a road is sensed by an image system to which the present invention is applied;

FIG. 4 is a histogram of local variance when classified into general shadows according to the present invention;

FIG. 5 is a histogram of local variance when classified according to the present invention behind a vehicle.

FIG. 6 is a control flowchart controlled by a main control unit to apply the present invention.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Target object 2 Window 3 Vehicle 4 Shadow 10 Camera section 12 Main control section 14 Steering control section 16 Brake control section 18 Acceleration control L1 Line where vehicle and road surface contact.

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ identification code FI G08G 1/16 G06F 15/62 380 H04N 5/225 15/70 410 (58) Investigated field (Int.Cl. ⁷ , DB name) ) G01C 3/00-3/32 B60R 21/00 620 G01B 11/00-11/30 102 G06T 1 / 00,7 / 00,7 / 20 G08G 1/16 H04N 5/225

Claims (3)

(57) [Claims] The method according to claim 1] signal of the video screen the camera is detected through a predetermined direction, detecting a portion where the gray level changes rapidly by comparing the unidirectional gray levels sequentially, only the further portions of the shade the The stage of sensing the shade to recognize,
To analyze the portion of the sensed negative, and the window over forming step of forming a U Indou so the portion where the gray level changes suddenly in the center of the lower surface of the window over, the formed window over A calculation step of calculating a variance value for brightness from the shadow set on the lower surface ;
Pre SL computed variance value, is compared with a reference value set,
Recognizing the approach of the vehicle by recognizing the shadow of a road surface formed at the lower part of the vehicle. Identification stage 2. The upper Kikage, the step of the dispersion value obtained is determined as the shadow of the vehicle if the reference Ne以 and, before <br/> Symbol variance reference Nehitsuji fully obtained 2. A method for recognizing a vehicle using an image system according to claim 1, further comprising a step of determining the vehicle as a general shadow. Identification stage wherein upper Kikage outputs a control signal by a result of the judgment, the steering control unit, a brake
A control stage for controlling related devices of the control unit and the acceleration control unit ;
After executing the above Symbol controlling step, comparison completion gray levels
And if the comparison is not complete,
2. The method according to claim 1, further comprising the step of: performing a sequential comparison of bells and a routine for controlling the related devices .