Driving safety control system and control method using environmental noise

Abstract

The present disclosure relates to a driving safety control system using ambient noise and a control method thereof. The driving safety control system using ambient noise may include: a microphone installed in a running vehicle and configured to receive ambient noise; and a signal processing controller configured to compare the ambient noise with vehicle noise characteristic data and determine driving information related to nearby vehicles through artificial intelligence-based analysis.

Description

Technical Field

[0001] The present invention relates to a driving safety control system using environmental noise and a control method thereof, and more particularly, to a driving safety control system using environmental noise and a control method thereof that assists safe driving by analyzing the environmental noise of a running vehicle through artificial intelligence. Background Art

[0002] Today's vehicles are equipped with various safety devices to assist drivers in driving safely.

[0003] Accidents with moving vehicles often occur when changing lanes.

[0004] Therefore, when a driver changes the driving lane, it is important to confirm nearby vehicles approaching from behind the lane to change.

[0005] The driver uses the rearview mirror to identify nearby vehicles approaching from behind.

[0006] However, rearview mirrors have blind spots where nearby vehicles may not be recognized.

[0007] Blind spots indicate areas that the driver of my vehicle would be unaware of even if nearby vehicles were approaching.

[0008] When the driver fails to detect a vehicle in the blind spot and changes lanes to the same lane, a collision may result.

[0009] Conventionally, wide-angle side mirrors have been provided to reduce blind spots, but blind spots have not been completely eliminated.

[0010] Meanwhile, a blind spot warning system has recently been introduced to identify a vehicle in a blind spot by attaching a motion detection sensor to the side of the vehicle.

[0011] However, the blind spot warning system is a method of displaying the rearview mirror in a separate manner so that the driver checks the rearview mirror and determines whether to change lanes.

[0012] At the same time, autonomous vehicle technology has been developing in recent years.

[0013] That is, a technology is also included that displays a flashing light on the vehicle's rearview mirror and, at the same time, temporarily restricts turning to the same lane while the driver determines whether to change lanes.

[0014] However, such conventional technology only limits steering in autonomous vehicles and has the limitation of not being able to assist more active autonomous driving.

[0015] At the same time, the driver is unaware of the travel speeds of nearby vehicles approaching from the sides and rear of the running vehicle.

[0016] The driver cannot tell the approaching speed of nearby vehicles by looking at the rearview mirror.

[0017] Therefore, even if the driver determines through the rearview mirror that a nearby vehicle approaching from behind is far away, there is a problem if the speed of the nearby vehicle is relatively fast relative to the speed of the driver's vehicle.

[0018] In the present case, when the driver changes lanes only because a nearby vehicle approaching from the rear is far away, there is a possibility of a rear collision.

[0019] Furthermore, in terms of safe driving, it is important to know whether a nearby vehicle approaching from behind is a car or a heavy truck.

[0020] Under the same situation, it is preferable that the driver not rush to change the lane to the same traveling lane because the nearby vehicle approaching from behind is a large vehicle.

[0021] This is because in the case of large vehicles, the risk of a rear collision is higher due to the increased rapid braking distance.

[0022] That is, speed information about a nearby vehicle approaching from behind and type information about the vehicle are also important factors for safe driving.

[0023] The information included in this Background of the Invention section is only for enhancement of understanding of the general background of the invention and is not to be taken as an admission or any form of suggestion that this information constitutes prior art already known to a person skilled in the art. Summary of the Invention

[0024] Various aspects of the present invention are directed to providing a driving safety control system and a control method thereof using environmental noise.

[0025] Various aspects of the present invention provide a driving safety control system using ambient noise, which includes a microphone installed in a running vehicle and used to receive the ambient noise; and a signal processing controller for comparing the ambient noise with vehicle noise characteristic data and determining driving information related to nearby vehicles through artificial intelligence-based analysis.

[0026] Furthermore, at least one pair of microphones are spaced apart from each other along a length direction on one side of the running vehicle.

[0027] Furthermore, the signal processing controller is configured to determine the relative speed of the nearby vehicle and the running vehicle by analyzing the sound pressure variation of the ambient noise, and to identify the type and engine type of the nearby vehicle by analyzing the frequency variation of the ambient noise.

[0028] In addition, the driving safety control system using environmental noise further includes a control module that controls driving of the running vehicle based on driving information related to nearby vehicles.

[0029] In addition, the control module includes at least one of an accelerator pedal control unit, a brake braking control unit, and a wheel steering control unit.

[0030] Furthermore, the signal processing controller includes an LSTM learning algorithm.

[0031] Additionally, the microphone is directional.

[0032] In addition, microphones are installed at the front, rear, right and left of the running vehicle respectively.

[0033] Furthermore, the driving safety control system further includes a display unit that visualizes information related to the running vehicle and driving information related to nearby vehicles by receiving driving condition data and road condition data of the running vehicle during driving.

[0034] Furthermore, the driving condition data includes at least one of a CAN signal, a vehicle speed, a pedal opening, a gear position, and congestion information and speed limit information about a road during driving.

[0035] Furthermore, the display unit displays to select any one of the automatic driving and the manual operation according to the predicted driving state of the nearby vehicle.

[0036] Furthermore, the driving safety control system using environmental noise further includes an image acquisition unit that provides the signal processing controller with image information on nearby vehicles by using at least one of a radar, a camera, and a GPS.

[0037] In addition, the present invention includes a safe driving control method using environmental noise, which includes receiving environmental noise through a microphone installed in a running vehicle; and comparing the received environmental noise with vehicle noise characteristic data through the artificial intelligence of a signal processing controller to determine the type of nearby vehicles, and analyzing the sound pressure change and frequency change of the environmental noise through artificial intelligence to determine driving information related to nearby vehicles.

[0038] Furthermore, the safe travel control method further includes controlling at least one of a vehicle speed and a steering direction of the running vehicle based on travel information related to nearby vehicles.

[0039] In addition, artificial intelligence includes LSTM learning algorithms.

[0040] Furthermore, determining the type of the nearby vehicle includes determining whether the nearby vehicle is in any one of an accelerating state, a decelerating state, and a constant speed traveling state by determining the relative speed between the running vehicle and the nearby vehicle using sound pressure variation analysis of ambient noise.

[0041] Additionally, the AI is configured to identify the type and engine type of nearby vehicles through frequency change analysis.

[0042] In addition, the safe driving control method further includes displaying, through a display unit, visual information related to the running vehicle and driving information related to nearby vehicles by receiving driving condition data and road condition data of the running vehicle during driving.

[0043] Furthermore, the driving condition data includes at least one of a CAN signal, a vehicle speed, a pedal opening, a gear position, and congestion information and speed limit information about a road during driving.

[0044] In addition, the safe driving control method further includes the step of receiving image information about nearby vehicles using at least one of radar information, camera information, and global positioning system (GPS) information through an image acquisition unit to acquire an image to add the received image to the determination.

[0045] According to the exemplary embodiments of the present invention as described above, the following effects can be obtained.

[0046] First, lane changes can be made safer by using the ambient noise of the running vehicle to confirm driving information related to nearby vehicles through artificial intelligence.

[0047] Second, by using artificial intelligence, it can understand environmental noise and maximize driving safety by predicting the behavior of cyclists or pedestrians and nearby vehicles.

[0048] Third, by using artificial intelligence to analyze environmental noise, active control of the running vehicle, such as acceleration, deceleration, braking and steering, can be performed.

[0049] Fourth, by using artificial intelligence to analyze environmental noise, the surrounding situation can be displayed to the driver in real time, allowing the driver to choose automatic driving or manual operation, which can be operated more safely.

[0050] The method and apparatus of the present invention have other features and advantages that will be set forth in more detail from or in the accompanying drawings, which are incorporated herein, and in the following detailed description, which together serve to explain certain inventive principles. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 12 is a diagram illustrating a travel pattern of a running vehicle and nearby vehicles according to an exemplary embodiment of the present invention.

[0052] Figure 2A and Figure 2B 2 is a diagram illustrating a sound pressure change analysis graph A of the ambient noise generated by the nearby vehicle 201 at a first moment and a sound pressure change analysis graph B of the ambient noise generated by the nearby vehicle 202 at a second moment according to an exemplary embodiment of the present invention.

[0053] Figure 3A 、 Figure 3B and Figure 3C According to an exemplary embodiment of the present invention, a frequency analysis graph A of a third engine instruction and a sixth engine instruction of a six-cylinder engine, a frequency change analysis graph B of the ambient noise generated by a nearby vehicle 201 at a first moment, and a frequency change analysis graph C of the ambient noise generated by a nearby vehicle 202 at a second moment are shown.

[0054] Figure 4 is a control flow chart according to an exemplary embodiment of the present invention.

[0055] Figure 5 is a diagram illustrating a learning process based on vehicle noise big data implemented by artificial intelligence of a signal processing controller according to various exemplary embodiments of the present invention.

[0056] Figure 6 and Figure 7 is a flow chart of a control algorithm according to an exemplary embodiment of the present invention.

[0057] Figure 8 is a flow chart of a control algorithm according to various exemplary embodiments of the present invention.

[0058] It will be understood that the drawings are not necessarily drawn to scale and present a somewhat simplified representation of various features illustrating the basic principles of the invention. The specific design features of the present invention as incorporated herein, including, for example, specific dimensions, orientations, locations, and shapes will be determined in part by the specific intended application and use environment.

[0059] In the drawings, reference numbers refer to the same or equivalent parts of the present invention throughout the several figures of the drawing. DETAILED DESCRIPTION

[0060] Reference will now be made in detail to various embodiments of the present invention, examples of which are shown in the accompanying drawings and described below. Although the present invention will be described in conjunction with exemplary embodiments thereof, it should be understood that this description is not intended to limit the present invention to those exemplary embodiments. On the other hand, the present invention is intended to cover not only the exemplary embodiments of the present invention, but also various alternatives, modifications, equivalents and other embodiments, which may be included within the spirit and scope of the present invention as defined by the appended claims.

[0061] Various modifications and embodiments can be made according to various aspects of the present invention, so that specific embodiments are shown in the drawings and described in detail in the specification. However, it should be understood that this is not intended to limit the present invention to a specific included form, but rather to include all modifications, equivalent forms and alternative forms that fall within the spirit and technical scope of the present invention.

[0062] In describing each of the figures, the same reference numerals are used for the same elements.

[0063] The terms "first," "second," etc. may be used to illustrate different components, but these components may not be limited by the terms. These terms are used to distinguish one element from another.

[0064] For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component. The term "and / or" includes a combination of a plurality of related listed items or any one of the plurality of related listed items.

[0065] Unless otherwise defined, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which exemplary embodiments of the present invention belong.

[0066] It will be further understood that terms, such as those defined in commonly used dictionaries, should otherwise be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and not in an idealized or overly formal sense unless expressly defined in this application.

[0067] A driving safety control system using environmental noise according to an exemplary embodiment of the present invention includes a microphone and a signal processing controller.

[0068] The running vehicle described below refers to a vehicle equipped with a driving safety control system for environmental noise using an exemplary embodiment of the present invention, and nearby vehicles are vehicles operated by other drivers and traveling near the running vehicle (e.g., in front, behind, to the right or to the left of the running vehicle).

[0069] Microphones are installed in running vehicles to pick up ambient noise.

[0070] The environmental noise may include engine noise generated from nearby vehicles, road noise from nearby vehicles, and wind noise from nearby vehicles.

[0071] Meanwhile, environmental noise can be various noises generated by motorcycles, bicycles or pedestrians around running vehicles.

[0072] The signal processing controller 112 analyzes the ambient noise based on artificial intelligence to compare it with the vehicle noise characteristic data and determines driving information related to nearby vehicles.

[0073] That is, the signal processing controller 112 is provided with artificial intelligence, and the artificial intelligence may have vehicle noise characteristic data.

[0074] At the same time, artificial intelligence can be databased by learning the ambient noise input from the microphone.

[0075] The vehicle noise characteristic data may include various information according to the size, engine type, and engine kind of the vehicle.

[0076] For example, they include whether the vehicle is a car or a truck, a large vehicle or a small vehicle, etc.

[0077] At the same time, it includes vehicle noise characteristic data based on whether the vehicle's engine type is diesel or gasoline, the engine displacement is, and the number of cylinders in the engine is 4 cylinders, 6 cylinders, 8 cylinders or 12 cylinders.

[0078] The signal processing controller 112 can determine the relative speed of the nearby vehicle and the running vehicle by analyzing the sound pressure change of the ambient noise, and can identify the type of the nearby vehicle and its engine type by analyzing the frequency change of the ambient noise.

[0079] At least one pair of microphones may be disposed to be spaced apart from each other in a longitudinal direction on one side of the running vehicle.

[0080] The microphones may be installed at the front, rear, right, and left of the running vehicle 100, respectively.

[0081] The microphone may preferably be directional.

[0082] Figure 1 The direction of the middle arrow is the front of the vehicle.

[0083] Reference Figure 1 , the microphones are arranged such that a pair of the first microphone 111 and the second microphone 121 are spaced apart from each other along the longitudinal direction on the right side surface and / or the left side surface of the running vehicle 100 .

[0084] The operating vehicle 100 and the nearby vehicle 201 at the first moment travel straight in directions parallel to each other, and the following expression means that the operating vehicle 100 and the nearby vehicle 201 at the first moment are close to each other but not in contact with each other.

[0085] The second microphone 121 is disposed on the front right side and / or the front left side of the running vehicle 100 , and the first microphone 111 is disposed on the rear right side and / or the rear left side of the running vehicle 100 .

[0086] The vehicle 100 travels straight while maintaining a constant travel speed.

[0087] At the first time, the neighboring vehicle 201 is before overtaking the running vehicle 100 , and at the second time, the neighboring vehicle 202 is accelerating by overtaking the running vehicle 100 .

[0088] The nearby vehicle 201 at the first time and the nearby vehicle 202 at the second time are the same nearby vehicle.

[0089] At the first moment, the neighboring vehicle 201 is in the right lane of the lane in which the traveling vehicle 100 is traveling, and is approaching the traveling vehicle 100 from behind the traveling vehicle 100 .

[0090] That is, when the speed of the nearby vehicle 201 at the first moment is faster than the speed of the running vehicle 100 , the nearby vehicle 201 at the first moment will overtake the running vehicle 100 after a predetermined time.

[0091] The first microphone 111 collects ambient noise generated from the nearby vehicle 201 at a first moment.

[0092] Assume that the nearby vehicle 202 at the second time is accelerating by overtaking the operating vehicle 100 at the second time after the first time.

[0093] The second microphone 121 collects ambient noise generated from the nearby vehicle 202 at the second moment.

[0094] The control module 122 receives driving information related to nearby vehicles and controls the accelerator pedal, brake pedal, or steering wheel to drive the vehicle. The display unit 123 receives data to visualize information related to the situation and displays a selection of either automatic driving or manual operation. The image acquisition unit 113 receives data to generate image information and provides this image information to the signal processing controller 112.

[0095] Description will be made with reference to the results of analyzing the thus collected environmental noise.

[0096] Figure 2A and Figure 2B2 is a diagram illustrating a sound pressure change analysis graph A of the ambient noise generated by the nearby vehicle 201 at a first moment and a sound pressure change analysis graph B of the ambient noise generated by the nearby vehicle 202 at a second moment according to an exemplary embodiment of the present invention.

[0097] The first microphone 111 receives the environmental noise at time T1 and time T2, and the second microphone 121 receives the environmental noise at time T3 and time T4.

[0098] That is, time T1 and time T2 are times when the nearby vehicle 201 at the first moment approaches the running vehicle 100 from behind the running vehicle 100, and time T3 and time T4 are times when the nearby vehicle 201 at the first moment accelerates after overtaking the running vehicle 100.

[0099] At time T1 , when the nearby vehicle 201 at the first time approaches the rear of the running vehicle 100 , the sound pressure input to the first microphone 111 increases, and the nearby vehicle 201 at the first time accelerates, thereby increasing the RPM of the engine to be measured.

[0100] At time T2 , the engine RPM is momentarily reduced and then increased again as the nearby vehicle 201 at the first time passes, and the sound pressure input to the first microphone 111 is reduced.

[0101] At time T3, when the nearby vehicle 202 of the second time decelerates the accelerator, the engine RPM decreases instantaneously and then increases again with the change of gear, and the sound pressure received by the second microphone 121 gradually increases.

[0102] At time T4, when the nearby vehicle 202 at the second time continues to maneuver the accelerator, the engine RPM of the nearby vehicle 202 at the second time increases linearly, and the sound pressure received in the second microphone 121 increases.

[0103] The graph of the engine RPM may change according to changes in the opening degree of the accelerator pedal of a nearby vehicle.

[0104] Figure 3A 、 Figure 3B and Figure 3C According to an exemplary embodiment of the present invention, a frequency analysis graph A of a third engine instruction and a sixth engine instruction of a six-cylinder engine, a frequency change analysis graph B of the ambient noise generated by a nearby vehicle 201 at a first moment, and a frequency change analysis graph C of the ambient noise generated by a nearby vehicle 202 at a second moment are shown.

[0105] The engine command is the proportionality constant between RPM and crankshaft frequency.

[0106] That is, the engine command is an indicator indicating how many times the crankshaft rotates per second.

[0107] For example, the third engine command indicates engine noise due to the sequence of three crankshaft revolutions, and the sixth engine command indicates engine noise due to six crankshaft revolutions.

[0108] exist Figure 3A , a third engine command component and a sixth engine command component for a six-cylinder engine are shown.

[0109] The signal processing controller 112 performs frequency analysis on the right rear noise data of the running vehicle 100 through the environmental noise collected by the first microphone 111 at time T1 and time T2.

[0110] Therefore, the acceleration level and speed change information about the nearby vehicle 201 at the first moment can be extracted.

[0111] The signal processing controller 112 performs frequency analysis on the right front noise data of the running vehicle 100 through the environmental noise collected through the second microphone 121 at time T3 and time T4.

[0112] Therefore, the acceleration level and speed change information related to the nearby vehicle 202 at the second moment can be extracted.

[0113] The driving information about the nearby vehicles thus extracted is provided to the control module 122 for supporting safe operation of the operating vehicle.

[0114] That is, the control module 122 controls the travel of the running vehicle based on the travel information about the nearby vehicles.

[0115] The control module 122 may include at least one of an accelerator pedal control unit, a brake braking control unit, and a wheel steering control unit.

[0116] The signal processing controller 112 may include an LSTM (Long Short-Term Memory) learning algorithm.

[0117] The display unit 123 may visualize information related to the running vehicle and driving information related to nearby vehicles by receiving driving condition data and road condition data of the running vehicle during driving.

[0118] The display unit 123 may also display to select any one of automatic driving and manual operation according to the predicted driving state of the nearby vehicle.

[0119] The driver can select whether to maintain automatic driving or switch to manual operation while viewing the driving status of nearby vehicles displayed on the display unit 123.

[0120] The driving condition data may include at least one of a CAN signal, a vehicle speed and a pedal opening, a gear position, and congestion information and speed limit information about a road during driving.

[0121] Another exemplary embodiment of the present invention may further include an image acquiring unit 113 .

[0122] The image acquisition unit 113 provides the signal processing controller 112 with image information about nearby vehicles by using at least one of a radar, a camera, and a GPS.

[0123] Therefore, the signal processing controller 112 may provide for more accurate analysis and prediction of the driving conditions of the nearby vehicles by using the image information about the nearby vehicles and the environmental noise information about the nearby vehicles.

[0124] Next, a safe driving control method using environmental noise according to an exemplary embodiment of the present invention will be described.

[0125] Figure 4 is a control flow chart according to an exemplary embodiment of the present invention, Figure 5 is a diagram illustrating an artificial intelligence learning process according to an exemplary embodiment of the present invention and Figure 6 and Figure 7 is a flow chart of a control algorithm according to an exemplary embodiment of the present invention.

[0126] Reference Figure 5 , the artificial intelligence of the signal processing controller 112 executes the processes of the vehicle type information block and the vehicle noise information block, and then obtains the artificial intelligence learning results based on the vehicle noise big data through the processes of the data processing block of the deep learning algorithm and the algorithm block of the deep learning algorithm.

[0127] For example, the vehicle type information block handles the steps of distinguishing between cars, trucks, large vehicles, small vehicles, diesel engines, and gasoline engines. The vehicle noise information block handles the steps of matching vehicle noise data, thereby classifying noise into differences between vehicle type, engine displacement, and the number of cylinders in the engine. The data processing block handles the steps of inputting data recognition of ambient noise data collected while driving, and outputting the vehicle type / engine type determined through input data processing based on big data. The algorithm module uses a long short-term memory (LSTM) learning algorithm to analyze vehicle noise data that changes over time, and handles the steps of constructing data for vehicle type, engine speed, vehicle speed, and sudden driving based on the learning results of ambient noise.

[0128] Reference Figure 6 and Figure 7 , the signal processing controller 112 includes an input device, an algorithm device and an output device.

[0129] The input device includes: a noise signal extractor 311, which extracts an environmental noise signal through a microphone installed in a running vehicle; a running vehicle data detector 312, which detects driving condition information during driving; and an image acquirer 321, which receives image information related to nearby vehicles to add the received image to the determination.

[0130] The algorithm device includes a nearby vehicle identifier 411 for determining the type of nearby vehicles; a vehicle travel identifier 412 for determining travel information related to nearby vehicles; a rear vehicle predictor 413 for predicting the travel of rear vehicles; a side vehicle predictor 414 for predicting the travel of left and right vehicles; a front vehicle predictor 415 for predicting the travel of front vehicles; a display 416 for displaying running vehicles; a travel information predictor 417 for receiving travel status data of running vehicles and road condition data during travel; an option selector 418 for selecting an automatic travel operation or manual operation option mode; a vehicle identifier 421 for determining the type of vehicle from an acquired image; a real-time analyzer 422 for analyzing speed and information related to nearby vehicles in real time; a condition predictor 423 for predicting travel conditions; and a condition identifier 424 for identifying changes in the relative speed of nearby vehicles.

[0131] The output device includes a control selector 510 that selects at least one of a vehicle speed and a steering direction of the operating vehicle.

[0132] The input S1 extracts an ambient noise signal through a microphone installed in a running vehicle by using the noise signal extractor 311 .

[0133] Determination S2 determines the type of nearby vehicles by comparing the ambient noise input through artificial intelligence with the vehicle noise characteristic data using the nearby vehicle identifier 411, and determines the driving information related to the nearby vehicles through sound pressure change analysis and frequency change analysis of the ambient noise using the vehicle driving identifier 412. In this step, a vehicle type information block and a vehicle noise information block are involved.

[0134] The microphones can be installed at the front, rear, right and left of the running vehicle respectively.

[0135] By using the ambient noise input from each microphone, artificial intelligence can perform rear vehicle travel prediction by the rear vehicle predictor 413 , left and right vehicle travel prediction by the side vehicle predictor 414 , and front vehicle travel prediction using the front vehicle predictor 415 .

[0136] The AI can include LSTM learning algorithms and identify the type and engine type of nearby vehicles through frequency change analysis.

[0137] Determine S2 by analyzing the sound pressure change of the ambient noise to determine the relative speed of the running vehicle and the nearby vehicles, thereby determining whether the nearby vehicles are accelerating, decelerating, or traveling at a constant speed. In this step, a data processing block and an algorithm block are involved.

[0138] The controlling S3 controls at least one of the vehicle speed and the steering of the running vehicle according to the driving information about the nearby vehicles by using the control selector 510 extracted in the determining S2.

[0139] The information related to the operating vehicle and the driving information related to nearby vehicles of the driving information predictor 417 can be predicted and visualized by using the display of the display 416 by receiving the driving condition data of the operating vehicle and the road condition data during driving using the operating vehicle data detector 312.

[0140] Currently, the driver can select either the automatic driving operation or the manual operation option mode of the option selector 418 displayed and provided for this purpose.

[0141] Meanwhile, the driving condition data of the operating vehicle data detector 312 may include at least one of a CAN (Controller Area Network) signal, vehicle speed and pedal opening, gear position, and congestion information and speed limit information about the traveling road.

[0142] Figure 8 is a flow chart of a control algorithm according to various exemplary embodiments of the present invention.

[0143] The image acquiring image acquirer 321 may receive image information about nearby vehicles using at least one of radar information, camera information, and global positioning system (GPS) information to add the received image to the determination S2.

[0144] The artificial intelligence can determine the type of vehicle by acquiring images from the image acquirer 321 and the vehicle identifier 421 , and analyze the speed and information related to nearby vehicles in real time by using the real-time analyzer 422 .

[0145] Based on the result, the driving condition can be predicted using the condition predictor 423, an unexpected situation can be identified by identifying the change in the relative speed with nearby vehicles by the condition identifier 424, and at least one of the vehicle speed and steering of the running vehicle can be controlled according to the driving information related to the nearby vehicles by using the control selector 510.

[0146] To facilitate explanation and accurately define the appended claims, the terms "above," "below," "inside," "outside," "up," "down," "upward," "downward," "front," "back," "backside," "inside," "outside," inward, "outward," "inside," "outer," "forward," and "rearward" are used to refer to features of the exemplary embodiments as they are positioned as shown in the accompanying drawings. It will also be understood that the term "connect" or its derivatives refers to both direct and indirect connections.

[0147] The foregoing descriptions of specific exemplary embodiments of the present invention have been provided for purposes of illustration and description. They are not intended to be exhaustive or to limit the invention to the precise forms disclosed, and it is apparent that many modifications and variations are possible in light of the foregoing teachings. The exemplary embodiments are chosen and described to explain certain principles of the present invention and their practical application, so as to enable others skilled in the art to make and utilize various exemplary embodiments of the present invention and various alternatives and modifications thereof. The scope of the present invention is intended to be defined by the appended claims and their equivalents.

Claims

1. A driving safety control system using environmental noise, the driving safety control system comprising: a first microphone and a second microphone, the first microphone and the second microphone being spaced apart from each other in a longitudinal direction on a side of a running vehicle, the first microphone being disposed on a right rear side and / or a left rear side of the running vehicle, the second microphone being disposed on a right front side and / or a left front side of the running vehicle, and the first microphone collecting ambient noise generated from a nearby vehicle at a first moment approaching the running vehicle from behind the running vehicle before the nearby vehicle overtakes the running vehicle, and the second microphone collecting ambient noise generated from the nearby vehicle at a second moment accelerating after the nearby vehicle overtakes the running vehicle; as well as a signal processing controller configured to compare the ambient noise collected by each of the first microphone and the second microphone with vehicle noise characteristic data, and determine driving information related to the nearby vehicle through artificial intelligence-based analysis, The signal processing controller is configured to determine the relative speed of the nearby vehicle and the running vehicle by analyzing the sound pressure changes of the ambient noise collected by the first microphone and the second microphone, thereby determining whether the nearby vehicle is in an accelerating state, a decelerating state, or a constant speed driving state. In which, the signal processing controller is configured to extract the acceleration level and speed change information related to the nearby vehicle at the first moment by analyzing the frequency changes of the ambient noise collected by the first microphone, and to extract the acceleration level and speed change information related to the nearby vehicle at the second moment by analyzing the frequency changes of the ambient noise collected by the second microphone.

2. The driving safety control system using environmental noise according to claim 1, in, The signal processing controller is configured to identify a type and an engine type of the nearby vehicle through the frequency change analysis of the ambient noise. 3 . The driving safety control system using environmental noise according to claim 1 , further comprising a control module configured to control driving of the running vehicle based on the driving information related to the nearby vehicles.

4. The driving safety control system using environmental noise according to claim 3, in, The control module includes at least one of an accelerator pedal controller, a brake controller, and a wheel steering controller.

5. The driving safety control system using environmental noise according to claim 1, in, The signal processing controller includes a long short-term memory learning algorithm.

6. The driving safety control system using environmental noise according to claim 1, in, The microphone is directional.

7. The driving safety control system using environmental noise according to claim 1, further comprising: A display unit that visualizes information related to the running vehicle and the running information related to the nearby vehicles by receiving running condition data and road condition data of the running vehicle during running.

8. The driving safety control system using environmental noise according to claim 7, in, The driving condition data includes at least one of a controller area network signal, a vehicle speed, a pedal opening, a gear position, and congestion information and speed limit information related to a road during driving.

9. The driving safety control system using environmental noise according to claim 8, in, The display unit displays to select one of automatic driving and manual operation according to a predicted driving state of the nearby vehicle.

10. The driving safety control system using environmental noise according to claim 1, further comprising an image acquisition unit that provides the signal processing controller with image information related to the nearby vehicles by using at least one of a radar, a camera, and a global positioning system.

11. A safe driving control method using environmental noise, the safe driving control method comprising: receiving the ambient noise by a first microphone and a second microphone installed in the running vehicle, wherein the first microphone and the second microphone are spaced apart from each other in a longitudinal direction on a side of the running vehicle, the first microphone is arranged on the right rear side and / or the left rear side of the running vehicle, and the second microphone is arranged on the right front side and / or the left front side of the running vehicle, and the first microphone collects the ambient noise generated from the nearby vehicle at a first moment when the nearby vehicle approaches the running vehicle from the rear before the nearby vehicle overtakes the running vehicle, and the second microphone collects the ambient noise generated from the nearby vehicle at a second moment when the nearby vehicle accelerates after overtaking the running vehicle; and The method comprises comparing the ambient noise collected by the first microphone and the second microphone with the vehicle noise characteristic data through artificial intelligence to determine the type of the nearby vehicle; and determining the driving information related to the nearby vehicle by analyzing the sound pressure change and frequency change of the ambient noise collected by the first microphone and the second microphone. Among them, determining the driving information related to the nearby vehicle through sound pressure change analysis and frequency change analysis of the ambient noise includes determining the relative speed of the nearby vehicle and the running vehicle through sound pressure change analysis of the ambient noise collected by the first microphone and the second microphone respectively, thereby determining whether the nearby vehicle is in an acceleration state, a deceleration state and a constant speed driving state, and extracting the acceleration level and speed change information related to the nearby vehicle at the first moment through frequency change analysis of the ambient noise collected by the first microphone, and extracting the acceleration level and speed change information related to the nearby vehicle at the second moment through frequency change analysis of the ambient noise collected by the second microphone.

12. The safe driving control method using environmental noise according to claim 11, further comprising: At least one of a vehicle speed and a steering direction of the running vehicle is controlled based on the driving information related to the nearby vehicle.

13. The safe driving control method using environmental noise according to claim 11, in, The artificial intelligence includes a long short-term memory learning algorithm.

14. The safe driving control method using environmental noise according to claim 11, in, The artificial intelligence is configured to identify the type and engine type of the nearby vehicle through the frequency change analysis.

15. The safe driving control method using environmental noise according to claim 11, further comprising: By receiving the driving condition data and the road condition data of the running vehicle during driving, visualization information related to the running vehicle and the driving information related to the nearby vehicles are displayed.

16. The safe driving control method using environmental noise according to claim 15, in, The driving condition data includes at least one of a controller area network signal, a vehicle speed, a pedal opening, a gear position, and congestion information and speed limit information related to a road during driving.

17. The safe driving control method using environmental noise according to claim 11, further comprising: Image information related to the nearby vehicle is received by using at least one of radar information, camera information, and global positioning system information, and an image is acquired to add the acquired image to the determination.

Images