KR101491849B1 - fail-safe system and method for inter-vehicle distance - Google Patents

Abstract

A sensor fault compensation system and method for inter-vehicle distance are provided. The sensor fault compensation system for the inter-vehicle distance includes a camera for obtaining a front image of the vehicle; An image analyzer for obtaining first distance information between the vehicle and the preceding vehicle on the front image of the vehicle; A sensor unit transmitting a wavelength to the front vehicle to obtain second distance information between the vehicle and the front vehicle; An operation unit for generating an inter-vehicle distance estimation model by comparing the first distance information and the second distance information; And an inter-vehicle distance utilization system using distance information between the vehicle and the preceding vehicle, wherein the inter-vehicle distance utilization system uses the second distance information when the sensor unit normally operates, and the sensor unit performs an abnormal operation The inter-vehicle distance information estimated using the first distance information and the inter-vehicle distance estimation model is used.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a fault-

The present invention relates to a sensor fault compensation system and method for inter-vehicle distance.

Conventional techniques measure the distance between vehicles using only a camera or only a sensor. Korean Patent Laid-Open Publication No. 2010-0061289 discloses an invention in which a vehicle distance is measured using a radar system and the distance between the vehicles is maintained and the minimum distance is set. In Korean Patent Laid-Open Publication No. 2013-0110020, To detect the distance between the front or rear of the vehicle. In addition, Korean Patent Laid-Open Publication No. 2012-0093373 discloses an invention in which a vehicle distance is measured more accurately by a plurality of cameras.

A problem to be solved by the present invention is to provide a sensor fault compensation system and method for an inter-vehicle distance which can measure an inter-vehicle distance by using a sensor unit when the sensor unit is normal and can estimate the inter-vehicle distance even when the sensor unit fails .

Another problem to be solved by the present invention is to provide a sensor fault compensation system and method for an inter-vehicle distance which can acquire an inter-vehicle distance with a small error by analyzing image information acquired by a camera.

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

According to an aspect of the present invention, there is provided a system for compensating for a headway distance error compensator, comprising: a camera for obtaining a front image of a vehicle; An image analyzer for obtaining first distance information between the vehicle and the preceding vehicle on the front image of the vehicle; A sensor unit transmitting a wavelength to the front vehicle to obtain second distance information between the vehicle and the front vehicle; An operation unit for generating an inter-vehicle distance estimation model by comparing the first distance information and the second distance information; And an inter-vehicle distance utilization system using distance information between the vehicle and the preceding vehicle, wherein the inter-vehicle distance utilization system uses the second distance information when the sensor unit normally operates, and the sensor unit performs an abnormal operation The inter-vehicle distance information estimated using the first distance information and the inter-vehicle distance estimation model is used.

In some embodiments of the present invention, the arithmetic operation unit includes a distance information database for storing statistics of the first distance information and the second distance information, an arithmetic model generation module for generating the inter-vehicle distance estimation model, And a distance estimation module for estimating an inter-vehicle distance using the inter-vehicle distance estimation model.

In some embodiments of the present invention, the calculation model generation module calculates a proportionality constant between the first distance information and the second distance information using the statistic of the first distance information and the statistic of the second distance information .

In some embodiments of the invention, the sensor may comprise an ultrasonic sensor and / or a radar sensor. The inter-vehicle distance utilization system monitors the failure of the sensor unit to use the second distance information when the sensor unit is not in trouble, and uses the second distance information when the sensor unit fails, Distance information is available.

According to another aspect of the present invention, there is provided a method of compensating for a fault in a headway distance sensor, the method comprising: obtaining a front image of a vehicle; The image analysis unit acquiring first gullibility information between the vehicle and the preceding vehicle on the front image of the vehicle; The sensor unit transmits a wavelength to the front vehicle to obtain second distance information between the vehicle and the front vehicle; The operation unit compares the first distance information and the second distance information to generate an inter-vehicle distance estimation model; The inter-vehicle distance utilization system determining whether the sensor unit is faulty; And the inter-vehicle distance utilization system uses the second distance information when the sensor unit is not in failure, and the inter-vehicle distance information estimated using the first distance information and the inter-vehicle distance estimation model when the sensor unit fails Lt; / RTI >

In some embodiments of the present invention, the arithmetic part generates the inter-vehicle distance estimation model, the distance information database storing statistics of the first distance information and the second distance information; Generating an inter-vehicle distance estimation model by the calculation model generation module; And estimating an inter-vehicle distance using the first distance information and the inter-vehicle distance estimation model.

In some embodiments of the present invention, the step of generating the headway distance estimation model may include calculating the headway distance estimation model based on the statistic of the first distance information and the statistic of the second distance information, A constant can be calculated.

Other specific details of the invention are included in the detailed description and drawings.

According to an aspect of the present invention, an inter-vehicle distance can be estimated even when a sensor is broken due to an estimation of an inter-vehicle distance with a small error in image information acquired by a camera using accumulated data. .

1 is a block diagram for explaining a sensor fault compensation system for an inter-vehicle distance according to an embodiment of the present invention.
2 is a block diagram for explaining the operation unit of FIG. 1 in detail.
FIG. 3 is a block diagram for explaining the inter-vehicle distance utilization system of FIG. 1 in detail.
4 is an exemplary view illustrating a process of estimating a distance X1 between a past vehicle and a preceding vehicle using a forward image of the vehicle.
FIG. 5 is a diagram illustrating an example of a process of obtaining a distance Y between a vehicle and a preceding vehicle by a sensor unit.
6 is an exemplary view illustrating a process of estimating a distance X2 between a current vehicle and a preceding vehicle using a forward image of the vehicle.
FIG. 7 is an exemplary view illustrating a process of estimating a distance Z between a current vehicle and a preceding vehicle when the sensor unit fails.
FIG. 8 is a flowchart illustrating a method of compensating a sensor failure for an inter-vehicle distance according to an embodiment of the present invention.
FIG. 9 is a flowchart for explaining the vehicle-to-vehicle distance estimation model generation step of FIG. 8 in detail.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention and the manner of achieving them will become apparent with reference to the embodiments described in detail below with reference to the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Is provided to fully convey the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims. The relative sizes of layers and regions in the figures may be exaggerated for clarity of illustration. Like reference numerals refer to like elements throughout the specification. "And / or" include each and every combination of one or more of the mentioned items.

Although the first, second, etc. are used to describe various elements, components and / or sections, it is needless to say that these elements, components and / or sections are not limited by these terms. These terms are only used to distinguish one element, element or section from another element, element or section. Therefore, it goes without saying that the first element, the first element or the first section mentioned below may be the second element, the second element or the second section within the technical spirit of the present invention.

The terminology used herein is for the purpose of illustrating embodiments and is not intended to be limiting of the present invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. It is noted that the terms "comprises" and / or "comprising" used in the specification are intended to be inclusive in a manner similar to the components, steps, operations, and / Or additions.

Unless defined otherwise, all terms (including technical and scientific terms) used herein may be used in a sense commonly understood by one of ordinary skill in the art to which this invention belongs. Also, commonly used predefined terms are not ideally or excessively interpreted unless explicitly defined otherwise.

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

1 is a block diagram for explaining a sensor fault compensation system for an inter-vehicle distance according to an embodiment of the present invention.

Referring to FIG. 1, an inter-vehicle distance sensor fault compensation system includes a camera 100, an image analysis unit 200, a sensor unit 300, an operation unit 400, and an inter-vehicle distance utilization system 500.

The camera 100 is mounted in front of the vehicle to obtain an image of the front of the vehicle. The camera 100 may acquire an image of the rear end of the preceding vehicle.

The image analysis unit 200 analyzes the front image acquired by the camera 100 to acquire the first distance information between the camera-mounted vehicle (hereinafter referred to as "the vehicle ") and the preceding vehicle. The first distance information is not suitable for utilization as the inter-vehicle distance. This is because the image information acquired by the camera may be distorted by environmental conditions such as the state of the camera, the temperature and the climate. Therefore, the first distance information can not be directly used as the inter-vehicle distance.

The sensor unit 300 transmits a wavelength to the front vehicle to obtain second distance information between the vehicle and the front vehicle. The sensor unit may comprise a plurality of sensors. The plurality of sensors may be an ultrasonic wave or a radar sensor. The second distance information is more accurate than the first distance information. The image information of the camera may be distorted by the image information acquired by the camera due to the environmental conditions such as the condition of the camera, the temperature and the climate, but the sensor is relatively free from environmental conditions. Therefore, the second distance information is utilized as the inter-vehicle distance to the inter-vehicle distance utilization system 500 as long as the sensor unit 300 does not fail.

The operation unit 400 receives the first distance information and the second distance information. Then, the first distance information and the second distance information are compared to generate an inter-vehicle distance estimation model. The inter-vehicle distance estimation model is a mathematical estimation model for reducing the error of the current first distance information using the accumulated first and second distance information. It is possible to estimate and utilize the inter-vehicle distance even when the second distance information can not be used, that is, when the sensor unit 300 fails.

The inter-vehicle distance utilization system 500 can perform various safety assisting and traveling functions at the time of traveling by using the inter-vehicle distance between the preceding vehicle and the preceding vehicle. For example, it can be applied to an inter-vehicle distance maintenance system (ACC) or a system that warns when the inter-vehicle distance is reduced. The inter-vehicle distance utilization system 500 immediately uses the second distance information when the sensor unit 300 operates normally. However, when the sensor unit 300 fails, the inter-vehicle distance utilization system 500 uses the inter-vehicle distance information estimated using the first distance information and the inter-vehicle distance estimation model.

According to the above-described sensor fault compensation system for inter-vehicle distance according to an embodiment of the present invention, even when the sensor unit 300 fails, an inter-vehicle distance can be provisionally provided to the inter-vehicle distance utilization system 500 . That is, even when the inter-vehicle distance sensor unit 300 fails, the inter-vehicle distance information estimated using the inter-vehicle distance estimation model can be continuously provided to the inter-vehicle distance utilization system 500. Also, by estimating using the inter-vehicle distance estimation model capable of reducing the error, the inter-vehicle distance utilization system can operate properly by providing relatively accurately estimated inter-vehicle distance information.

2 is a block diagram for explaining the operation unit of FIG. 1 in detail.

Referring to FIG. 1, an operation unit 400 includes a distance information database 410, an operation model generation module 420, and a distance estimation module 430.

The distance information database 410 receives the first distance information from the image analysis unit 200. And receives the second distance information from the sensor unit 300. The distance information database 410 stores such distance information. Accordingly, the statistics of the first and second distance information are accumulated and stored in the distance information database 410.

The calculation model generation module 420 receives the first distance information and the second distance information from the distance information database 410. The calculation model generation module 420 generates an inter-vehicle distance estimation model using past accumulated first and second distance information. The inter-vehicle distance estimation model may be a mathematical operation model.

The distance estimation module 430 estimates the inter-vehicle distance using the first distance information and the inter-vehicle distance estimation model generated by the calculation model generation module 420. Since the first distance information is inaccurate but corrected using the inter-vehicle distance estimation model, a relatively accurate inter-vehicle distance estimation value that can be temporarily used can be obtained.

FIG. 3 is a block diagram for explaining the inter-vehicle distance utilization system of FIG. 1 in detail.

Referring to FIG. 3, the inter-vehicle distance utilization system 500 includes a sensor monitoring unit 510 and an inter-vehicle distance utilization unit 520.

The sensor monitoring unit 510 monitors the sensor unit 300 to determine whether the sensor unit 300 is malfunctioning. The sensor monitoring unit 510 transmits the second distance information received from the sensor unit 300 to the headway distance utilization unit 520 when the sensor unit 300 is normal. If the sensor unit 300 fails, the sensor monitoring unit 510 receives the estimated inter-vehicle distance information from the operation unit 400 and transmits the estimated inter-vehicle distance information to the inter-vehicle distance utilization unit 520. Therefore, when the sensor unit 300 is in failure, the estimated distance information is transmitted to the inter-vehicle distance utilization unit 520, so that the fault compensation function can be provided without interfering with the inter-vehicle distance utilization.

 The inter-vehicle distance utilization unit 520 may be provided with some components such as an inter-vehicle distance maintenance system or a system that warns when the inter-vehicle distance is reduced. For example, the inter-vehicle distance utilization section 520 may be provided in a Smart Cruise Control (SSC) or an Adaptive Cruise Control (ACC).

FIGS. 4 to 7 are diagrams for explaining a process of generating the inter-vehicle distance estimation model.

FIG. 4 is a view illustrating an example of a process of estimating a distance X1 at a past point of time with respect to a preceding vehicle using a forward image of the vehicle, FIG. to be. 6 is a view illustrating an example of a process of estimating a distance X2 between a current vehicle and a preceding vehicle using a forward image of the vehicle, Fig.

Illustratively, the inter-vehicle distance estimation model can be expressed by the following equation.

[Mathematical Expression]

Z = k * X2 (k = (average value of Y) / (average value of X1))

Here, Z is an estimated value of the inter-vehicle distance at the current point of time, and X2 may be the first distance information of the current point of time. Y may be the second distance information of the past time point, and X1 may be the first distance information of the past time point. k may be a value obtained by dividing the average value of the second distance information of the past time by the average value of the first distance information of the past time. In this case, the calculation model generation module 420 continuously updates the k value according to the accumulated data. As the data is accumulated, the value of k becomes constant, and the accuracy of the estimated value of the inter-vehicle distance can be increased. Therefore, when the current first distance information X2 is substituted into the above equation, a Z value with a smaller error can be obtained. The Z value can be temporarily used as the inter-vehicle distance when the sensor unit 300 fails.

When the sensor unit 300 fails, the sensor monitoring unit 510 can notify the distance information database 410 in the operation unit 400. FIG. The distance information database 410 can determine the second distance information after the failure of the sensor unit 300 as unreliable information. Therefore, when the distance information database 410 transmits the first and second distance information to the calculation model generation module 420, the sensor unit 300 can transmit only information before the failure time. Accordingly, the calculation model generation module 420 may not use the incorrect second distance information even if the sensor unit 300 fails.

Hereinafter, a fault compensating method for a headway distance sensor according to an embodiment of the present invention will be described with reference to FIGS. 8 to 9. FIG. The description overlapping with the inter-vehicle distance sensor failure compensating system described with reference to Figs. 1 to 7 will be simplified or omitted.

FIG. 8 is a flowchart illustrating a method of compensating a sensor failure for an inter-vehicle distance according to an embodiment of the present invention. FIG. 9 is a flowchart for explaining the vehicle-to-vehicle distance estimation model generation step of FIG. 8 in detail.

Referring to FIG. 8, the camera 100 obtains the front image of the vehicle (S400). The camera 100 can mainly pick up the trailing end of the preceding vehicle while driving.

Then, the image analysis unit 200 analyzes the front image to obtain the first distance information, and the sensor unit 300 transmits the wavelength, receives the reflected wavelength, and obtains the second distance information (S410). Subsequently, the calculation unit 400 generates an inter-vehicle distance estimation model (S420). The inter-vehicle distance estimation model can reduce the error with the actual inter-vehicle distance of the first distance information. Then, the sensor monitoring unit 510 determines the failure of the sensor of the sensor unit 300 (S430). The sensor monitoring unit 510 monitors the sensor unit 300 and determines whether to use the second distance information and the inter-vehicle distance information estimated by the calculating unit 400, by dividing the case of the failure or not.

If the sensor unit 300 is normal, the second distance information is directly transmitted to the inter-vehicle distance utilization unit 520. Since the second distance information has less error than the first distance information, it is utilized as the inter-vehicle distance (S440).

If the sensor unit 300 fails, the inter-vehicle distance information estimated using the first distance information and the inter-vehicle distance estimation model is transmitted to the inter-vehicle distance utilization unit 520. In this case, since the second distance information can not be utilized, the first distance information analyzed in the front image can be used. However, in order to reduce the error of the first distance information, And uses the estimated inter-vehicle distance information. In this case, it is possible to utilize the inter-vehicle distance to the failure of the sensor unit 300, thereby obtaining stability (S450).

Referring to FIG. 9, the operation of generating the inter-vehicle distance estimation model by the operation unit 400 can be described in detail.

The distance information database 410 stores the first and second distance information (S421). The distance information database 410 accumulates the first and second distance information.

The calculation model generation module 420 generates an inter-vehicle distance estimation model using the first and second distance information received from the distance information database 410 (S422). The inter-vehicle distance estimation model may be an operation model that can reduce the error of the first distance information as the existing data accumulates.

The distance estimation module 430 estimates the current inter-vehicle distance using the first distance information of the current time and the inter-vehicle distance estimation model of the calculation model generation module 420 (S423). If the sensor unit 300 fails after this, the estimated inter-vehicle distance information is utilized.

According to the above-described vehicle distance sensor failure compensating system of the present invention, the stability of the sensor can be improved against malfunction of the sensor during traveling of the vehicle, and as a result, the safety and convenience of traveling can be increased.

100: camera 200: image analysis unit
300: sensor unit 400:
410: distance information database 420: calculation model generation module
430: Distance estimation module 500: Inter-vehicle distance utilization system
510: Sensor monitoring unit 520: Inter-vehicle distance utilization unit

Claims (8)

A camera for acquiring a front image of the vehicle;
An image analyzer for obtaining first distance information between the vehicle and the preceding vehicle on the front image of the vehicle;
A sensor unit transmitting a wavelength to the front vehicle to obtain second distance information between the vehicle and the front vehicle;
An operation unit for comparing the first distance information and the second distance information to estimate an inter-vehicle distance; And
And an inter-vehicle distance utilization system using distance information between the vehicle and the preceding vehicle,
The inter-vehicle distance utilization system uses the second distance information when the sensor unit normally operates, and when the sensor unit operates abnormally, the inter-vehicle distance estimated using the first distance information and the inter-vehicle distance estimation model Using information,
The operation unit,
A distance information database for periodically receiving the first distance information and the second distance information and accumulating and storing statistics of the first distance information and the second distance information,
An inter-vehicle distance estimation model is generated based on the statistics of the first distance information and the second distance information, and a calculation model for updating the inter-vehicle distance estimation model using the newly transmitted first distance information and the second distance information Generation module and
And a distance estimation module for estimating an inter-vehicle distance using the first distance information and the inter-vehicle distance estimation model. delete The method according to claim 1,
The calculation model generation module includes:
And calculates a proportional constant between the first distance information and the second distance information using the statistic of the first distance information and the statistic of the second distance information. The method according to claim 1,
Wherein the sensor comprises at least one of an ultrasonic sensor and a radar sensor. delete The camera acquiring a forward image of the vehicle;
The image analysis unit acquiring first gullibility information between the vehicle and the preceding vehicle on the front image of the vehicle;
The sensor unit transmits a wavelength to the front vehicle to obtain second distance information between the vehicle and the front vehicle;
Calculating an inter-vehicle distance by comparing the first distance information and the second distance information;
The inter-vehicle distance utilization system determining whether the sensor unit is faulty; And
The inter-vehicle distance utilization system uses the second distance information when the sensor unit is not in trouble and uses the inter-vehicle distance information estimated using the first distance information and the inter-vehicle distance estimation model when the sensor unit is in failure ≪ / RTI >
The calculation unit estimates the inter-vehicle distance,
Accumulating statistic values of the first distance information and the second distance information by periodically receiving the first distance information and the second distance information;
The calculation model generation module generates an inter-vehicle distance estimation model based on the statistics of the first distance information and the second distance information, and calculates the inter-vehicle distance estimation using the newly transmitted first distance information and the second distance information Updating the model; And
And the distance estimation module estimates the inter-vehicle distance using the first distance information and the inter-vehicle distance estimation model. delete The method according to claim 6,
The step of generating the inter-vehicle distance estimation model includes:
And calculating a proportional constant between the first distance information and the second distance information using the statistic of the first distance information and the statistic of the second distance information.

Images