KR101832918B1 - Simulation system for autonomous driving - Google Patents

Abstract

The present invention relates to a system to simulate an image recognition driving test for an autonomous driving vehicle, capable of enabling a camera, which is installed in an autonomous driving vehicle, to normally recognize a target regardless of weather condition and safely testing whether the camera is operating in a preset state. More specifically, to test an image recognition rate of the camera of the autonomous driving vehicle depending on weather conditions, a test road, which is identical to an actual road, is installed in an installation space isolated from the outside to avoid the influence of external weather conditions. As a test camera is installed in an actual vehicle to test a recognition rate for a target in accordance with a driving velocity of the vehicle, and weather conditions such as rain, snow, fog, yellow dust, and backlight and dark states are set and tested through a weather control unit.

Description

{SIMULATION SYSTEM FOR AUTONOMOUS DRIVING} BACKGROUND OF THE INVENTION 1. Field of the Invention [

[0001] The present invention relates to a self-driving vehicle image recognition running test simulation system, and more particularly, to a self-driving vehicle running test simulation system in which a camera mounted on an autonomous vehicle can recognize whether an object is normally detected, The present invention relates to an autonomous running vehicle image recognition running test simulation system.

In recent years, various studies have been conducted for self-propelled vehicles as interest in autonomous driving has been increasing. The present invention has been made in view of the fact that the lane change detection function, the automatic parking function, It is an early stage technology.

For autonomous navigation, objects such as people, animals, other vehicles and traffic lights should be accurately identified regardless of weather conditions, and the vehicle must operate in a set state after identification.

In addition, since the vehicle automatically recognizes all the situations and runs as it is an autonomous driving vehicle, in order to test it, it is necessary to check the normal operation state while the person is in the automatic driving vehicle, It has been pointed out that it is not possible for a person to carry out a test on an autonomous vehicle that has not received the test, and it is impossible for the person to individually deal with the safety test of the occupant, the test time required for a long time, and the accurate and objective test result can not be obtained.

Meanwhile, interest in autonomous vehicles using a large number of cameras is increasing, and autonomous vehicles using cameras must be able to operate normally regardless of weather conditions.

However, until now, in order to confirm whether or not the identification and the operation are correctly performed, the passenger must check the vehicle while mounted on the actual vehicle, and there is no method for improving the identification.

In addition, since there is a possibility that a trial vehicle of such a test vehicle is actually driven on a road on which other vehicles are running, it may lead to a major accident, so the problem should also be solved.

(0001) Korean Patent Laid-Open No. 10-2017-0034696 (Driving control system and method for autonomous driving vehicle) (0002) Korean Patent No. 10-1510745 (Unmanned autonomous vehicle system of a vehicle) Korean Patent No. 10-1701901 (Method and System for Control of Autonomous Vehicles according to Traffic Signals)

SUMMARY OF THE INVENTION It is an object of the present invention to provide an autonomous running vehicle image recognition driving test simulation capable of testing whether a vehicle is correctly operated in accordance with the performance of a camera device installed in a vehicle for a self- ≪ / RTI >

Another technical problem to be solved by the present invention is to determine whether a camera device installed in a vehicle for an autonomous driving vehicle operates correctly even under weather (weather) conditions such as day, night, rain, snow, fog, The present invention relates to an autonomous running vehicle image recognition running test simulation system capable of testing a vehicle.

Another aspect of the present invention is to provide an autonomous driving vehicle image recognition driving test simulation system capable of safely and accurately testing the performance of the camera device.

According to another aspect of the present invention, there is provided an autonomous driving vehicle image recognition running test simulation system including a first test road, a belt conveyor, a test camera, An object, a climate control means, an image processing means, and a central processing unit.

In addition, at least one second test road is installed on both sides of the first test road and is connected to the first test road by inclining at a predetermined angle.

In addition, the climate control means includes a water spraying means, a snow remover, a smog generating means, and a lighting lamp.
The test camera may further include: a forward surveillance camera including a visible light camera, a thermal imaging camera, and a front wide angle camera; A rear surveillance camera including a first rear camera, a second rear camera, and a rear wide angle camera; And a side surveillance camera, each of which is composed of one left and right side surveillance cameras. The cameras are photographed 360 degrees around the vehicle through the front surveillance camera, the rear surveillance camera, and the side surveillance camera.

The apparatus may further include monitoring means connected to the central processing unit for displaying a test result on the test camera.

As described above, according to the present invention, it is possible to test a test camera used for autonomous driving in a separate installation space that is not affected by an external weather condition, thereby improving test stability and performing various verification procedures .

In addition, since the climate control means is installed and verified to test the image recognition rate according to the actual weather condition, accurate verification of the test camera is possible.

Further, since the test camera is mounted on the belt conveyor provided with a narrow width in the center longitudinal direction on the first test road having the actual road width, the same result as the test result on the actual road can be obtained, On the first test road on the left and right, a person (mannequin is also possible), animal, model car can be installed and verified, so that recognition and follow-up of the object that jumped or suddenly appear on the road can be performed have.

Further, since the speed of the belt conveyor is verified while being rotated in accordance with the running speed of the vehicle, the same result as that on the actual road can be obtained.

In addition, since the image processing means operated in conjunction with the test camera is configured to control the belt conveyor, not only the image recognition rate verification through the test camera but also the vehicle control operation according to the recognition can be verified.

Further, it is possible to carry out the verification for the vehicle joining the configuration of the second test road.

Also, the test result of the test camera can be confirmed in real time through the monitoring means.

FIG. 1 is a conceptual diagram illustrating an autonomous vehicle image recognition running test simulation system according to an embodiment of the present invention.
FIG. 2 is a schematic view illustrating a test state according to an embodiment of the autonomous driving vehicle image recognition running test simulation system according to the present invention.
3 is a conceptual illustration of a list that can be tested through the climate control means according to an embodiment of the autonomous driving vehicle image recognition running test simulation system according to the present invention,
4 is a view showing a test progress state according to an embodiment of a self-driving car image recognition running test simulation system according to the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail.

It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals are used for like elements in describing each drawing.

The terms including ordinal, such as second, first, etc., may be used to describe various elements, but the elements are not limited to these terms.

The terms used herein are used only for the purpose of distinguishing one element from another. For example, without departing from the scope of the present invention, the second component may be referred to as a first component, and similarly, the first component may also be referred to as a second component. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.

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.

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 the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, 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 are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Do not.

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

FIG. 1 is a conceptual block diagram of an autonomous driving vehicle image recognition running test simulation system according to an embodiment of the present invention. FIG. 2 is a conceptual diagram of a self- FIG. 3 is a conceptual view illustrating a list that can be tested through the climate control means according to an embodiment of the autonomous vehicle image recognition running test simulation system according to the present invention, and FIG. 4 Is a diagram showing a test progress status according to an embodiment of the autonomous driving vehicle image recognition running test simulation system according to the present invention.

1 to 4, an autonomous driving vehicle image recognition running test simulation system according to the present invention will now be described.

The autonomous vehicle image recognition running test simulation system of the present invention includes a first test road 100, a plurality of second test roads 200, a belt conveyor 300 on which a plurality of test cameras 400 are installed, an object 500, A climate control unit 600, an image processing unit 700, a central processing unit 800, and a monitoring unit 900. In order to test the image recognition rate of the vehicle according to the weather condition of the camera for autonomous driving, (Not shown) so as not to be influenced by external weather conditions.

The installation space may be a tunnel or a separately installed facility and it is preferable to calculate the area considering the largest area of the first test road 100, the second test road 200, and the climate control means 600 Do.

In this specification, each test camera 400 for autonomous driving will be described as an 8-channel surround camera as shown in FIG.

The 8-channel surround camera includes forward surveillance cameras 1, 2 and 3, rear surveillance cameras 6, 7 and 8, side surveillance cameras 4 and 5, and a video control unit.

The forward surveillance cameras 1, 2 and 3 are cameras for monitoring the front of the vehicle, and in the present specification, a state in which they are composed of a visible light camera 2, a thermal image camera 1 and a front wide angle camera 3 .

The visible light camera 2 may use a camera using a CMOS (Complementary Metal Oxide Semiconductor) sensor, which is a well-known technology, and thus a detailed description thereof will be omitted.

The thermal imaging camera 1 can use a camera using a TOD (Thermal Observation Device) sensor, which is also a known technology, so that a detailed description thereof will be omitted.

It is preferable that the front wide angle camera 3 monitors the entire front of the vehicle and uses a fisheye lens camera.

The rear surveillance cameras 6, 7, and 8 are cameras for monitoring the rear of the vehicle. The cameras include a first rear camera 6, a second rear camera 7, and a rear wide-angle camera 8, Respectively.

The first rear camera 6 and the second rear camera 7 can also use a CMOS (Complementary Metal Oxide Semiconductor) sensor, and the rear wide angle camera 8, which monitors the entire rear, also uses a fisheye lens camera .

The side surveillance cameras 4 and 5 are constituted by at least one camera for monitoring both sides (left and right sides) of the vehicle. The state in which the side surveillance cameras 4 and 5 are arranged one by one on the left and right sides of the vehicle, respectively As an example.

The side surveillance cameras 4 and 5 can also use cameras using CMOS (Complementary Metal Oxide Semiconductor) sensors.

The video control unit (VCU) processes the video captured from the forward surveillance cameras 1, 2 and 3, the rear surveillance cameras 6, 7 and 8 and the lateral surveillance cameras 4 and 5, Detects and analyzes an object obstructing the running of the vehicle from the captured image to warn the driver and controls the electronic control unit (ECU) of the vehicle.

When an object such as a running vehicle or the like joining not only the other traveling vehicle located within the cognitive distance but also the moving image of each camera appears through each camera, the distance between the object and the vehicle, the traveling direction of the object, Speed, direction of the vehicle, driving speed of the vehicle, traffic signals, etc., and alerts, controls and guides the vehicle in a set state.

If the vehicle running speed is not lowered after the warning to the driver as described above, the electronic control unit installed in the vehicle is controlled to gradually reduce the vehicle running speed in the set state. Since the electronic control unit is connected to the video control unit, it can be controlled through the video control unit. In the stepwise deceleration, the driver is alerted to the driver through automatic braking first, and then the driver recognizes the surrounding situation and induces him / .

Also, if there is no additional action by the user after the first or several automatic braking, continuous automatic braking is performed at a certain distance, and the vehicle is controlled to stop completely before the occurrence of the contact accident.

The video control unit is constituted by the test camera 400 and the image processing unit 700 connected to the driving unit of the belt conveyor 300.

On the other hand, the angle of view of the thermal imaging camera 1 is 20 to 40 degrees, that of the visible light camera 2 is 50 to 70 degrees, that of the front wide angle camera 3 and the rear wide angle camera 8 is 110 to 130 degrees, It is preferable that the camera 6 and the second rear camera 7 are 75 to 85 degrees and the side surveillance cameras 4 and 5 are 80 to 100 degrees.

The recognition distance and the range of each camera are shown in different colors on the drawing, and the angle of view of each camera is configured as described above to guide the autonomous driving while monitoring 360 degrees around the vehicle.

In order to test the test camera 400 configured as described above, it is preferable that the first test road 100 is installed with a road of 250 meters having an actual lane width.

The belt conveyor 300 is installed in the center of the first test road 100 in a longitudinal direction narrower than the width of the first test road 100 and is capable of adjusting the rotational speed in accordance with the running speed of the vehicle.

The test camera 400 is fixed to the belt conveyor 300 at the same height as the height of the test camera 400 and rotates together when the belt conveyor 300 is rotated. It can be fixed by using separate structure, or model car can be made and installed. The test camera 400 may be any camera that can be installed for autonomous driving. In the present specification, the test camera 400 described above will be applied for the sake of convenience.

The object 500 is an object such as a person, a vehicle, a bicycle, a traffic signal, an animal, etc. to be recognized by the test camera 400 when the vehicle is actually traveling. Install it so that it does not interfere. It is preferable that the installation position and the installation number of the object 500 are configured in consideration of actual road conditions, and can be applied differently in each test. It can also be installed on both sides of the second test road 200 and the belt conveyor 300 of the first test road 100, which will be described later. The object 500 may be a real person, a vehicle, an animal, or a mannequin, a model car, or a model animal.

The image processing means 700 is connected to the test camera 400 and recognizes and identifies the object 500 from the image acquired through the test camera 400. The image processing means 700 recognizes and recognizes the object 500 according to the recognition of the object 500 The belt conveyor 300 is controlled, so that the belt conveyor 300 can be correctly identified and verified.

The climate control means 600, which can form the inside of the installation space same or similar to the actual weather conditions, includes a water spraying means, a snow remover, a smog generating means, and a lamp. It is possible to set the situation of rain through the water spraying means, to set the snowing situation through the snow remover, to set the mist or the yellow dust through the smog generating means, and to set the light condition Can be set. In the case of DSS In case of creating actual environment such as DSS, it may cause device trouble due to various dusts and contaminants. Therefore, when setting the visible distance constraint due to DSS, .

It is possible to control all situations related to the test situation in the central processing unit 800 (microcomputer) and to analyze and store the respective situations. Basically, it is possible to determine whether the object of the image processing means 700 is identified, And controls the climate control means 600 and receives the status information of the belt conveyor 300 and the climate control means 600.

In addition, a monitoring means 900 connected to the central processing unit 800 for displaying a test result on the test camera 400 is further provided to present test results in real time.

On the other hand, a plurality of second test roads 200, each of which is connected to both sides of the first test road 100 by being inclined at a predetermined angle, and on which the object 500 is installed, is further provided. It is preferable that the inclination angle of the second test road 200 is determined by reflecting the angle of entry of the actual merge road and that the object 500 entering the second test road 200 is installed, Check whether it is detected.

By using the autonomous driving vehicle image recognition driving test simulation system configured as described above, it is possible to create conditions that are the same as the actual road conditions, and also provide a safe and accurate test condition.

100: first test road 200: second test road
300: Belt conveyor 400: Test camera
500: Object 600: Climate control means
700: image processing means 800: central processing unit
900: Monitoring means

Claims (4)

The present invention relates to an autonomous running vehicle image recognition driving test simulation system installed in an installation space which is isolated from the outside so as not to be influenced by an external weather condition in order to test an image recognition rate according to a weather condition of a camera installed in a vehicle for autonomous driving,
A first test road having a width of an actual lane and installed at a length of 250 meters;
A belt conveyor installed at a center of the first test road in a longitudinal direction narrower than the width of the first test road and capable of adjusting the rotational speed in accordance with the running speed of the vehicle;
A plurality of test cameras fixed to the belt conveyor at the same height as the height of the vehicle, and rotated together with the belt conveyor;
An object to be sensed by the test camera when the vehicle is actually traveling, provided so as not to interfere with the rotation of the test camera at both ends of the belt conveyor in the traveling direction thereof;
A climatic control means including a water spraying means, a snow remover, a smog generating means, and a lighting lamp so as to form the inside of the installation space in the same condition as the actual gas condition;
Image processing means connected to the test camera to recognize and identify the object from the image acquired through the test camera and to control the belt conveyor in a state that is set according to whether the object is the object;
Wherein the image processing means analyzes and stores the object identification information and whether the control operation is performed in a predetermined state, controls the climate control means, and receives the status information of the belt conveyor and the climate control means Device; And
And monitoring means connected to the central processing unit and displaying a test result on the test camera,
Each said test camera comprising:
A forward surveillance camera consisting of a thermal imaging camera using a CMOS (Complementary Metal Oxide Semiconductor) sensor and a front wide angle camera using a fisheye lens using a visible light camera and a TOD (Thermal Observation Device) sensor;
A backward surveillance camera including a first rear camera using a CMOS sensor, a second rear camera, and a rear wide angle camera using a fisheye lens; And
A left side and a right side, and a lateral security camera using a CMOS sensor,
The front surveillance camera, the rear surveillance camera, and the side surveillance camera,
Wherein the view angle of the thermal imaging camera is 20 to 40 degrees, the angle of view of the visible light camera is 50 to 70 degrees, the angle of view of the front wide angle camera and the rear wide angle camera is 110 to 130 degrees, The angle of view of the rear camera is 75 to 85 degrees, and the angle of view of the side surveillance camera is 80 to 100 degrees,
Wherein the image processing means comprises:
And a control unit for processing the images acquired from the front monitoring camera, the rear monitoring camera, and the side monitoring camera, detecting, analyzing, and alerting an object obstructing the running of the vehicle from the captured image, And a video control unit (VCU) for controlling the vehicle in a set state.
The method according to claim 1,
And a plurality of second test roads connected to both sides of the first test road at respective predetermined angles and provided with the object are further provided.
delete delete

Images