Road surface condition detection device and system, and road surface condition detection method using the same

Abstract

The present invention relates to a road surface condition detection device and system for determining road surface conditions through acoustic signals, and a road surface condition detection method using the same. The road surface condition detection device according to the present invention includes a sensor unit that is installed on a road and measures acoustic signals generated by the movement of a moving object on the road, and a control unit that classifies the acoustic signals measured by the sensor unit into normal or abnormal states and, if abnormal, determines the road surface condition to include at least one of wet, icy, slush, and snowy, and can quickly and accurately take measures corresponding to the road surface condition of a specific section from a remote location.

Description

[Technical Field]

[0001] The present invention relates to a road surface condition detection device, and more particularly to a road surface condition detection device and system for determining road surface conditions through acoustic signals, and a road surface condition detection method using the same. [Background technology]

[0002] Thin ice occurs when snow or rain that falls during the day seeps into the cracks in the asphalt road and mixes with oil and dust from the road overnight, forming a thin layer of ice on the road.

[0003] Thin ice has emerged as a major cause of serious vehicle accidents because it is not noticeable when driving on the road and is often mistaken for a slightly wet road.

[0004] As a result, various researches are being conducted recently to detect thin ice in advance and warn drivers or perform snow removal work.

[0005] Korean Patent Publication No. 10-2019-0140272 discloses a "thin ice detection device and method" that can detect thin ice.

[0006] The disclosed thin ice detection device is mounted on a vehicle and detects thin ice. It includes a sensing unit that measures road surface temperature, which is the temperature on the road surface, and atmospheric temperature, which is the temperature in the atmosphere, a control unit that uses the road surface temperature and atmospheric temperature to determine whether or not the ice is thin, and a communication unit that transmits thin ice information to a navigation device if the control unit determines that the ice is thin.

[0007] The disclosed thin ice detection device can detect thin ice by transmitting a laser or ultrasonic wave, receiving a waveform, and measuring the temperature, but the detection range is only a few meters ahead of the vehicle, which means that the driver has little time to react to the hazard.

[0008] In addition, various researches have been conducted, such as ABS (Anti-lock brake system) operation, i.e., detecting thin ice through the difference in wheel rotation speed of the car, but the above problems have still not been resolved. Summary of the Invention [Problem to be solved by the invention]

[0009] Therefore, an object of the present invention is to provide a road surface condition detection device and system that can remotely determine the road surface condition of a specific section and quickly and accurately take measures corresponding to the road surface condition, and a road surface condition detection method using the same. [Means for solving the problem]

[0010] The road surface condition detection device according to the present invention includes a sensor unit that is installed on a road and measures an acoustic signal generated by the movement of a moving object on the road, and a control unit that classifies the acoustic signal measured by the sensor unit into a normal or abnormal state, and if the acoustic signal is abnormal, determines the road surface condition to include at least one of wet, icy, slush, and snowy.

[0011] In the road surface condition detecting device according to the present invention, the control unit learns the acoustic signal measured by the sensor unit and determines the road surface condition based on the stored learning data.

[0012] In the road surface condition detection device according to the present invention, the control unit filters background values ​​and noise from the acoustic signal measured by the sensor unit, and then determines the road surface condition based on whether the signal falls within a frequency range set for each road surface condition.

[0013] In the road surface condition detection device according to the present invention, the control unit judges the road surface condition for one of the moving bodies in real time, and when the road surface conditions for a predetermined number of the moving bodies match, determines that road surface condition.

[0014] In the road surface condition detecting device according to the present invention, the sensor unit measures the surface temperature, ambient temperature and humidity of the road.

[0015] In the road surface condition detection device according to the present invention, the control unit determines the road surface condition through the acoustic signal, calculates a dew point based on the surface temperature and humidity measured by the sensor unit, and reflects the calculated dew point and ambient temperature in determining the road surface condition.

[0016] In the road surface condition detecting device according to the present invention, the control unit determines that an icy condition exists when the calculated dew point exceeds a predetermined value and the ambient temperature is lower than a predetermined value.

[0017] In the road condition detecting device according to the present invention, the control unit determines whether a pothole, an accident, or a skid has occurred based on the acoustic signal measured from the sensor unit.

[0018] The road surface condition detection system according to the present invention includes a road surface condition detection device that is installed on a road and measures an acoustic signal generated by the movement of a moving object on the road, and a management server that receives the acoustic signal measured by the road surface condition detection device, classifies the acoustic signal as normal or abnormal, and if abnormal, determines the road surface condition to include at least one of wet, icy, slush, and snowy.

[0019] In the road surface condition detection system according to the present invention, a plurality of the road surface condition detection devices are provided and installed at regular intervals on the road.

[0020] In the road surface condition detection system according to the present invention, the management server measures the distance and passing time of a moving object between preset road surface condition detection devices through the acoustic signal measured from the road surface condition detection devices, and calculates the speed.

[0021] In the road surface condition detection system according to the present invention, the management server determines the range of road surface conditions depending on whether the road surface conditions determined from the adjacent road surface condition detection devices overlap.

[0022] In the road surface condition detection system according to the present invention, the management server outputs the determined road surface condition through a road electronic sign (VMS) or operates a snow removal device installed at the corresponding location according to the determined road surface condition.

[0023] The road surface condition detection method according to the present invention includes the steps of: a road surface condition detection device installed on a road measuring an acoustic signal generated by the movement of a moving object on the road; the road surface condition detection device classifying the road surface condition into a normal or abnormal state based on the measured acoustic signal; and if the road surface condition detection device determines that the road surface condition is abnormal, determining that the road surface condition includes at least one of wet, icy, slush, and snowy.

[0024] The road surface condition detection method according to the present invention includes the steps of: a management server receiving an acoustic signal generated by the movement of a moving object on a road from a road surface condition detection device installed on the road; the management server classifying the acoustic signal as a normal or abnormal state; and if the management server determines that the state is abnormal, determining that the road surface condition includes at least one of wet, icy, slush, and snowy. [Effects of the Invention]

[0025] The road surface condition detection device according to the present invention determines road surface conditions, including at least one of wet, icy, slush, and snowy, through acoustic signals, and can quickly and accurately process measures corresponding to the road surface conditions of a specific section in a remote location with wide coverage and no shadow areas. [Brief explanation of the drawings]

[0026] [Figure 1] 1 is a diagram illustrating a road surface condition detection system according to an embodiment of the present invention. [Figure 2] 1 is a block diagram showing a configuration of a road surface condition detection device according to an embodiment of the present invention. [Figure 3] FIG. 2 is a block diagram illustrating a configuration of a management server according to an embodiment of the present invention. [Figure 4] 3 is a flowchart illustrating a road surface condition detection method according to an embodiment of the present invention. [Figure 5] 3 is a flowchart illustrating a road surface condition detection method according to an embodiment of the present invention. [Figure 6] 10 is a graph showing frequency characteristics of an acoustic signal depending on road surface conditions. [Figure 7] 10 is a graph showing frequency characteristics of an acoustic signal depending on road surface conditions. DETAILED DESCRIPTION OF THE INVENTION

[0027] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, in the following description and the accompanying drawings, detailed descriptions of known functions or configurations that may obscure the gist of the present invention will be omitted. Furthermore, it should be noted that the same components are denoted by the same reference numerals throughout the drawings, whenever possible.

[0028] The terms and phrases used in the following specification and claims should not be construed as being limited to their ordinary or dictionary meanings, but should be construed in accordance with the meaning and concept consistent with the technical idea of ​​the present invention, in accordance with the principle that the inventor can appropriately define the concept of terms to best describe his / her invention. Therefore, it should be understood that the embodiments described in this specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention and do not represent the entire technical idea of ​​the present invention, and that there may be various equivalents and modifications that can replace them at the time of filing this application.

[0029] Furthermore, terms including ordinal numbers such as "first," "second," etc. are used to describe various components and are used only to distinguish one component from another, not to limit the components. For example, a second component can be named the "first component," and similarly, a first component can be named the "second component," without departing from the scope of the present invention.

[0030] Additionally, when a component is said to be "coupled" or "connected" to another component, this means that the components may be logically or physically coupled or connected. In other words, a component may be directly coupled or connected to another component, but it should be understood that there may be other components in between, or the components may be indirectly coupled or connected.

[0031] Furthermore, the terms used in this specification are used only to describe specific embodiments and are not intended to limit the present invention. A singular expression includes a plural expression unless the context clearly dictates otherwise. Furthermore, terms such as "comprise" or "have" used in this specification are intended to specify the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and should be understood not to preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0032] Hereinafter, embodiments of the present invention will be described in more detail with reference to the accompanying drawings.

[0033] FIG. 1 is a diagram showing a road surface condition detection system according to an embodiment of the present invention.

[0034] Referring to FIG. 1, a road surface condition detection system 300 according to an embodiment of the present invention includes a road surface condition detection device 100 and a management server 200.

[0035] The road surface condition detection devices 100 are installed at regular intervals on the road. The road surface condition detection devices 100 may be installed in a zigzag pattern at both ends of the road, or in a row at one end. For example, the road surface condition detection devices 100 may be installed at intervals of 100 m in sections where icing is weak, or at intervals of 80 m in sections where icing is weak, centered on steep slopes and sharp curves.

[0036] In addition, the road surface condition detection device 100 measures in real time the acoustic signals generated by the movement of moving objects on the road. Here, the moving object is typically a vehicle, but is not limited thereto, and may be various moving objects such as a motorcycle that generate noise while moving on the road.

[0037] The road surface condition detection device 100 also classifies the measured acoustic signal as normal or abnormal, and if abnormal, determines the road surface condition, including wet, icy, slush, and snowy. Here, a normal road surface is a dry state. In addition, the road surface condition detection device 100 can determine a pothole, crash, or skid through the acoustic signal. In particular, the road surface condition detection device 100 according to the present invention learns the road surface condition from the measured acoustic signal and determines the road surface condition based on the stored learning data.

[0038] In this way, the road surface condition detection device 100 can measure the acoustic signal by itself and determine the road surface condition from the measured acoustic signal. In this case, if the road surface condition detection device 100 determines the road surface condition by itself, the configuration of the device becomes complicated and each road surface condition detection device 100 must store a large amount of data. Therefore, preferably, the road surface condition detection device 100 can collect acoustic signals due to the movement of a mobile object and transmit the collected acoustic signals to the management server 200 in real time.

[0039] The management server 200 has an ID of each road surface condition detection device 100 and a reference value for each road surface condition detection device 100, that is, a frequency spectrum of a sound when traveling on a normal dry road.

[0040] As a result, the management server 200 can receive an acoustic signal from the road surface condition detection device 100 and classify the acoustic signal as a normal or abnormal state. That is, the management server 200 can primarily determine whether the road surface is in a normal state or an abnormal state.

[0041] In addition, when the road surface condition is abnormal, the management server 200 determines the road surface condition to include at least one of wet, icy, slush, and snowy. In particular, the road surface condition detection device 100 according to an embodiment of the present invention learns the road surface condition based on the measured acoustic signal and determines the road surface condition based on the stored learning data.

[0042] The management server 200 can output the determined road surface condition via a road electronic sign (VMS) and operate snow removal equipment installed at the corresponding location based on the determined road surface condition. For example, the management server 200 can operate in conjunction with a control system that manages and monitors road conditions, or can be installed within the control system and automatically display abnormal road conditions and locations on a screen. As a result, the control system can output a warning message via a road electronic sign, spray salt water or calcium chloride using snow removal equipment installed on the corresponding road, or dispatch a tow truck in the event of an accident.

[0043] In addition, the management server 200 can calculate the speed of a moving object by measuring the distance between preset road surface condition detection devices 100 and the time it takes for the moving object to pass through them based on the acoustic signal measured by the road surface condition detection devices 100. That is, the management server 200 can determine the peak value of the acoustic signal measured by the road surface condition detection devices 100 as the time when the moving object passes through, and calculate the speed by measuring the time it takes for the moving object to pass through the preset road surface condition detection devices 100. The measured speed can be used to crack down on moving objects by linking with cameras installed on the road. This can reduce the cost of expensive speed detection devices embedded in the road. Meanwhile, although the management server 200 has been described as performing the function of measuring the speed of a moving object, this is not limited thereto, and the management server 200 can also measure the speed of a moving object itself through communication between road surface condition detection devices 100 and operate in conjunction with a camera.

[0044] In addition, the management server 200 can determine the range of road surface conditions depending on whether there is an overlap in the road surface conditions determined by adjacent road surface condition detection devices 100. For example, if the road conditions of the first road surface condition detection device 100a and the second road surface condition detection device 200b are overlappingly determined as icy, the management server 200 can determine that the area between the first road surface condition detection device 100a and the second road surface condition detection device 200b is an icy area.

[0045] In this way, the road surface condition detection system 300 according to an embodiment of the present invention can quickly and accurately process measures corresponding to the road surface condition of a specific section in a remote location with wide coverage and no shadow areas by determining the road surface condition including wet, icy, slush, and snowy through acoustic signals.

[0046] The road surface condition detection device 100 according to the embodiment of the present invention will be described in more detail below.

[0047] FIG. 2 is a block diagram showing the configuration of a road surface condition detection device according to an embodiment of the present invention.

[0048] Referring to FIG. 2, the road surface condition detecting device 100 according to the embodiment of the present invention includes a communication unit 110, a sensor unit 130, a storage unit 150, a power supply unit 170, and a control unit 190.

[0049] The communication unit 110 transmits and receives data between the management server 200 or each component within the road surface condition detection device 100. In particular, the communication unit 110 transmits an acoustic signal measured from the sensor unit 130 to the control unit 170 or the management server 200, or, if the road surface condition detection device 100 itself analyzes the acoustic signal, transmits the analysis result, i.e., information on the current road condition, to the management server 200. The communication unit 110 can receive an acoustic signal from the sensor unit 130 via LoRa (Long Range) communication, LTE (Long Term Evolution) communication, 5G communication, or the like, or transmit the collected acoustic signal to the management server 200. The communication unit 110 may include a modem that modulates a transmitted signal and demodulates a received signal.

[0050] The sensor unit 130 can measure acoustic signals generated by the movement of a moving object on a road. The sensor unit 130 can use an omnidirectional, high-sensitivity microphone for measuring the acoustic signals. The sensor unit 130 can also include a temperature sensor for measuring ambient temperature, a humidity sensor for measuring ambient humidity, and an IR surface temperature sensor for measuring road surface temperature. The sensor unit 130 can transmit the measured acoustic signals, ambient temperature, ambient humidity, and road surface temperature to the control unit 170 in real time. The sensor unit 130 can be installed separately from the control unit 170 or integrated with the control unit 170. That is, the control unit 170 can be configured to cover multiple sensor units 130 via the communication unit 110, and one control unit 170 can be configured to collect acoustic signals, ambient temperature, ambient humidity, and road surface temperature from multiple sensor units 130. Alternatively, one sensor unit 130 can be integrated with one control unit 170.

[0051] The storage unit 150 serves to store programs and data required for the functional operation of the road surface condition detection device 100. In particular, the storage unit 150 may store an algorithm for distinguishing between normal and abnormal conditions based on the acoustic signal measured from the sensor unit 130. For example, the algorithm for distinguishing between normal and abnormal conditions may be a generative model. Furthermore, the storage unit 150 may store an algorithm for determining the road surface condition, including wet, icy, slush, and snowy, in the case of an abnormal condition. For example, the algorithm for determining the road surface condition may be a discriminative model.

[0052] The power supply unit 170 may serve to supply power for the functional operations of the road surface condition detection device 100. Here, the power supply unit 170 may be supplied with a regular power source or may be configured to generate and supply power by itself using a solar panel and a battery.

[0053] The control unit 190 controls the overall functional operation of the road surface condition detection device 100. The control unit 190 may include a first determination module 191 and a second determination module 192.

[0054] The primary determination module 191 classifies the acoustic signal measured by the sensor unit 130 into a normal or abnormal state. Here, the control unit 190 can classify the acoustic signal into a normal or abnormal state through a generative model stored in the storage unit 150 and learn the results.

[0055] 6 and 7 are graphs showing frequency characteristics of acoustic signals depending on road surface conditions. Here, FIG. 6 is a graph showing frequency characteristics due to vehicle movement on a sunny day, and FIG. 7 is a graph showing frequency characteristics due to the same vehicle movement at the same location as in FIG. 6 on a rainy day. It can be seen that the graph in FIG. 6 does not have a large difference between the value a when there is no vehicle and the value b when there is a vehicle moving, whereas the graph in FIG. 7 shows a larger difference between the value a when there is no vehicle and the value b when there is a vehicle moving compared to the graph in FIG. 6. In this way, the primary judgment module 191 can distinguish between normal and abnormal states based on the difference in frequency between the normal and abnormal states.

[0056] In the case of an abnormal state, the secondary determination module 192 determines the road surface condition including at least one of wet, icy, slush, and snowy. Here, the secondary determination module 192 may filter background values ​​and noise from the acoustic signal measured by the sensor unit 130, and then determine the road surface condition based on whether the signal falls within a frequency range set for each road surface condition. In this case, the secondary determination module 192 may determine the road surface condition through a discriminative model and learn the determined result.

[0057] In addition, in order to increase the accuracy of the road surface condition result value, the secondary judgment module 192 judges the road surface condition for one moving object in real time, and when the road surface conditions of a predetermined number of moving objects match, it can determine the road surface condition. That is, the secondary judgment module 192 does not transmit the judgment result for one moving object to the management server 200 in real time, but accumulates the judgment results for a predetermined number of moving objects, and when the road surface conditions of the predetermined number of moving objects match, it can notify the management server 200 of the road surface condition, thereby increasing accuracy.

[0058] In addition, the secondary determination module 192 can determine the road surface condition through the acoustic signal, calculate the dew point based on the surface temperature and humidity measured by the sensor unit 130, and reflect the calculated dew point and ambient temperature in determining the road surface condition. For example, the secondary determination module 192 can determine that the road surface is wet if the calculated dew point exceeds a predetermined value, and can determine that the wet road surface is frozen and in an icy state if the ambient temperature is lower than a predetermined value when the road surface is wet.

[0059] In addition, the secondary determination module 192 can determine whether a pothole, a crash, or a skid has occurred based on the acoustic signal measured by the sensor unit 130 .

[0060] In addition, the secondary determination module 192 may calculate the speed of the moving object by measuring the distance between the preset road surface condition detection devices 100 and the time it takes for the moving object to pass through the road surface condition detection device 100. That is, the secondary determination module 192 may receive the time when the moving object passed through the preset road surface condition detection device 100 from the preset road surface condition detection device 100 through communication via the communication unit 110. In this case, the preset road surface condition detection device may be a road surface condition detection device located previously based on the moving direction of the moving object. The secondary determination module 192 may calculate the time required for the moving object to pass through the current road surface condition detection device from the preset road surface condition detection device based on the time received from the preset road surface condition detection device and the time when the moving object is currently passing through. The secondary determination module 192 may calculate the speed of the moving object based on the calculated time and the distance between the road surface condition detection device and the current road surface condition detection device stored in the storage unit 150. If the calculated speed exceeds a predetermined speed, the secondary determination module 192 may transmit information to a camera installed adjacent to the preset road surface condition detection device to capture an image of the moving object. That is, the secondary determination module 192 can be used in conjunction with cameras installed on roads to enforce speed limits on moving objects, thereby reducing the cost of expensive speed measurement devices embedded in roads.

[0061] The configuration of the management server 200 according to an embodiment of the present invention will be described in more detail below.

[0062] FIG. 3 is a block diagram showing the configuration of a management server according to an embodiment of the present invention.

[0063] Referring to FIG. 3, the management server 200 includes a server communication unit 210, a server storage unit 220, and a server control unit 230.

[0064] The server communication unit 210 can transmit and receive data to and from the road surface condition detection device 100. In particular, the server communication unit 210 can receive an acoustic signal from the road surface condition detection device 100, or, when the road surface condition detection device 100 itself analyzes the acoustic signal, can receive the analysis result, i.e., information on the current road condition. The server communication unit 210 can receive the acoustic signal or the analysis result from the road surface condition detection device 100 via LTE (Long Term Evolution) communication or 5G communication. In addition, the server communication unit 210 can communicate with and transmit and receive data to and from a control system that manages and monitors road conditions.

[0065] The server storage unit 220 serves to store programs and data required for the functional operation of the management server 200. In particular, the server storage unit 220 can store an algorithm for distinguishing between normal and abnormal conditions based on the acoustic signal measured by the road surface condition management device 100. For example, the algorithm for distinguishing between normal and abnormal conditions can be a generative model. Furthermore, the server storage unit 220 can store an algorithm for determining the road surface condition, including wet, icy, slush, and snowy, in the case of an abnormal condition. For example, the algorithm for determining the road surface condition can be a discriminative model.

[0066] The server control unit 230 controls the overall functional operations of the management server 200. The control unit 230 may include a first determination module 231 and a second determination module 232.

[0067] The primary determination module 231 classifies the acoustic signal received from the road surface condition detection device 100 into a normal or abnormal state. Here, the primary determination module 231 can classify the acoustic signal into a normal or abnormal state through a generative model stored in the server storage unit 220 and learn the results.

[0068] In the case of an abnormal state, the secondary determination module 232 determines the road surface condition including at least one of wet, icy, slush, and snowy. Here, the secondary determination module 232 may determine the road surface condition based on whether the sound signal falls within a frequency range set for each road surface condition after filtering out background values ​​and noise from the acoustic signal received from the road surface condition detection device 100. In this case, the secondary determination module 232 may determine the road surface condition through a discriminative model and learn the determined result.

[0069] In addition, in order to increase the accuracy of the road surface condition result value, the secondary judgment module 232 can judge the road surface condition for one moving object in real time, and determine that road surface condition when the road surface conditions of a predetermined number of moving objects match. In other words, the secondary judgment module 232 does not determine the judgment result for one moving object as the road surface condition and transmit it to the control system, but accumulates the judgment results for a predetermined number of moving objects, and when the road surface conditions of the predetermined number of moving objects match, notifies the control server of the road surface condition, thereby increasing accuracy.

[0070] Furthermore, the secondary determination module 232 can determine the road surface condition through the acoustic signal, calculate the dew point based on the surface temperature and humidity received from the road surface condition detection device 100, and reflect the calculated dew point and ambient temperature in determining the road surface condition. For example, the secondary determination module 232 can determine that the road surface is wet if the calculated dew point exceeds a predetermined value, and can determine that the wet road surface has frozen and is in an icy state if the ambient temperature is lower than a predetermined value when the road surface is wet.

[0071] In addition, the secondary determination module 232 can determine whether a pothole, an accident, or a skid exists based on the acoustic signal received from the road surface condition detection device 100 .

[0072] In addition, the secondary determination module 232 can output the determined road surface condition via a road electronic sign (VMS) or operate a snow removal device installed at the corresponding location based on the determined road surface condition. For example, the secondary determination module 232 can operate in conjunction with a control system that manages and monitors road conditions or can be installed within the control system, and can automatically display abnormal road conditions and locations on a screen. As a result, the control system can output a warning message via a road electronic sign, spray salt water or calcium chloride using a snow removal device installed on the corresponding road, or dispatch a tow truck if an accident occurs.

[0073] In addition, the secondary determination module 232 can calculate the speed of a moving object by measuring the distance between preset road surface condition detection devices 100 and the time it takes for the moving object to pass through them through the acoustic signal measured from the road surface condition detection device 100. That is, the secondary determination module 232 can determine the peak value of the acoustic signal measured by the road surface condition detection device 100 as the time when the moving object passes through, and calculate the speed by measuring the time it takes for the moving object to pass through the preset road surface condition detection device 100. The measured speed can be used to crack down on moving objects by linking with cameras installed on the road. This can reduce the cost of expensive speed measurement devices embedded in the road.

[0074] In addition, the secondary determination module 232 can determine the range of road surface conditions depending on whether there is an overlap in the road surface conditions determined by adjacent road surface condition detection devices 100. For example, if the road conditions of the first road surface condition detection device 100a and the second road surface condition detection device 200b in Fig. 1 are overlappingly determined as icy, the secondary determination module 232 can determine that the area between the first road surface condition detection device 100a and the second road surface condition detection device 200b is an icy area.

[0075] Hereinafter, a road surface condition detection method according to an embodiment of the present invention will be described in detail.

[0076] 4 and 5 are flowcharts illustrating a road surface condition detection method according to an embodiment of the present invention.

[0077] Referring to FIG. 4, in step S10, the road condition detector measures an acoustic signal. Next, in step S20, the road surface condition detection device makes a primary determination of the road surface condition. That is, in step S20, the road surface condition detection device classifies the road surface condition as normal or abnormal based on the acoustic signal measured in step S10. In this case, the road surface condition detection device can classify the road surface condition as normal or abnormal through a generative model and learn the results.

[0078] Next, if the road surface condition is determined to be abnormal in step S30, the road surface condition detection device may perform a second determination of the road surface condition in step S40. Here, the road surface condition detection device determines the road surface condition to include at least one of wet, icy, slush, and snowy. Here, the road surface condition detection device may filter background values ​​and noise from the acoustic signal and determine the road surface condition based on whether the signal falls within a frequency range set for each road surface condition. In this case, the road surface condition detection device may determine the road surface condition using a discriminative model and learn the determined result. Here, the road surface condition detection device may transmit the determined road surface condition to a management server.

[0079] Referring to FIG. 5, in step S110, the management server receives an acoustic signal from a road surface condition detection device.

[0080] Next, in step S120, the management server makes a primary determination of the road surface condition. That is, in step S120, the management server classifies the road surface condition as normal or abnormal based on the acoustic signal measured in step S110. In this case, the management server can classify the road surface condition as normal or abnormal through a generative model and learn the results.

[0081] Next, if the road surface condition is determined to be abnormal in step S130, the management server may perform a second determination of the road surface condition in step S140. Here, the management server determines the road surface condition to include at least one of wet, icy, slush, and snowy. Here, the management server may filter background values ​​and noise from the acoustic signal and determine the road surface condition based on whether the signal falls within a frequency range set for each road surface condition. In this case, the management server may determine the road surface condition using a discriminative model and learn the determined result. Here, the road surface condition detection device may transmit the determined road surface condition to the management server.

[0082] In step S150, the management server can output the determined road surface condition via a road electronic sign (VMS) or operate snow removal equipment installed at the corresponding location based on the determined road surface condition. For example, the management server can operate in conjunction with a control system that manages and monitors road conditions, or can be installed within the control system and automatically display abnormal road conditions and locations on a screen. As a result, the control system can output a warning message via a road electronic sign, spray salt water or calcium chloride using snow removal equipment installed on the corresponding road, or dispatch a tow truck in the event of an accident.

[0083] While this specification contains details of numerous specific embodiments, these should not be construed as limiting the scope of any invention or claimable therein, but rather as descriptions of features specific to particular embodiments of particular inventions. Certain features described herein in the context of a separate embodiment may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable subcombination. Furthermore, while features may operate in particular combinations and be initially described as claimed as such, one or more features from a claimed combination may, in some cases, be excluded from that combination, or the claimed combination may be modified into a subcombination or a variation of that subcombination.

[0084] Similarly, although acts are depicted in the figures in a particular order, this should not be understood as meaning that such acts must be performed in the particular order or sequential order shown to achieve desirable results, or that all of the depicted acts must be performed. In certain cases, multitasking and parallel processing may be advantageous. Also, the separation of various system components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems may generally be integrated together in a single software product or packaged in multiple software products.

[0085] It should be noted that the embodiments of the present invention disclosed in this specification and the drawings are merely specific examples presented to aid in understanding, and are not intended to limit the scope of the present invention. It will be obvious to those skilled in the art to which the present invention pertains that other modifications based on the technical concept of the present invention can be implemented in addition to the embodiments disclosed herein.

Claims

1. a sensor unit that is installed on a road and that measures an acoustic signal generated by the movement of a mobile object on the road; A control unit, classifying the acoustic signal measured by the sensor unit into a normal state or an abnormal state to primarily determine the road surface condition; a control unit that, when the abnormal state is detected, secondarily determines the road surface condition including at least one of wet, icy, slush, and snowy; Including, The sensor unit measures the surface temperature, ambient temperature, and humidity of the road, The road surface condition detection device is characterized in that the primary determination is performed using a generative model based on a difference in frequency between the normal state and the abnormal state, and the secondary determination is performed using a discriminative model based on a frequency range set for each of the road surface conditions.

2. The control unit 2. The road surface condition detecting device according to claim 1, wherein the road surface condition is learned based on the acoustic signal measured by the sensor unit, and the road surface condition is determined based on the learned data stored.

3. The control unit 2. The road surface condition detecting device according to claim 1, wherein the road surface condition is determined based on whether the sound signal measured by the sensor unit falls within a frequency range set for each road surface condition after filtering out noise from the sound signal measured by the sensor unit.

4. The control unit 4. The road surface condition detection device according to claim 3, wherein the road surface condition is determined in real time by one of the mobile bodies, and when the road surface conditions of a predetermined number of the mobile bodies match, the road surface condition is determined to be that road surface condition.

5. The control unit 2. The road surface condition detection device according to claim 1, wherein the road surface condition is determined based on the acoustic signal, and a dew point is calculated based on the surface temperature and humidity measured by the sensor unit, and the calculated dew point and ambient temperature are reflected in the determination of the road surface condition.

6. The control unit 6. The road surface condition detecting device according to claim 5, wherein when the calculated dew point exceeds a predetermined value and the ambient temperature is lower than the predetermined value, it is determined that an icy condition exists.

7. The control unit 2. The road surface condition detecting device according to claim 1, wherein a pothole, a crash, or a skid is determined based on the acoustic signal measured from the sensor unit.

8. a road surface condition detection device that is installed on a road and measures acoustic signals generated by the movement of a mobile object on the road; a management server, receiving the acoustic signal measured from the road surface condition detection device, and classifying the acoustic signal into a normal state or an abnormal state to make a primary determination of the road surface condition; a management server that, when the road surface is in the abnormal state, secondarily determines the road surface condition to include at least one of wet, icy, slush, and snowy; Including, The road surface condition detection device measures the surface temperature, ambient temperature, and humidity of the road, The road surface condition detection system is characterized in that the primary determination is performed using a generative model based on a difference in frequency between the normal state and the abnormal state, and the secondary determination is performed using a discriminative model based on a frequency range set for each of the road surface conditions.

9. The road surface condition detection device includes:

9. The road surface condition detection system according to claim 8, wherein a plurality of the road surface condition detection systems are provided and installed at regular intervals on the road.

10. The management server 10. The road surface condition detection system according to claim 9, wherein the speed of a moving object is calculated by measuring a distance between predetermined road surface condition detection devices and a time taken for the moving object to pass through the predetermined road surface condition detection devices through the acoustic signal measured from the road surface condition detection devices.

11. The management server 10. The road surface condition detection system according to claim 9, wherein the range of road surface conditions is determined based on whether or not the road surface conditions determined by adjacent road surface condition detection devices overlap.

12. The management server 9. The road surface condition detection system according to claim 8, wherein the determined road surface condition is outputted via a road electronic sign (VMS), or a snow removal device installed at the corresponding location is operated according to the determined road surface condition.

13. a step of measuring an acoustic signal generated by a road surface condition detection device installed on a road due to the movement of a mobile object on the road; the road surface condition detecting device classifying the measured acoustic signal into a normal state or an abnormal state, thereby primarily determining the road surface condition; If the abnormal state is detected, the road surface condition detecting device secondarily determines the road surface condition including at least one of wet, icy, slush, and snowy; Including, The road surface condition detection device measures the surface temperature, ambient temperature, and humidity of the road, The road surface condition detection method, wherein the primary determination is performed using a generative model based on a difference in frequency between the normal state and the abnormal state, and the secondary determination is performed using a discriminative model based on a frequency range set for each of the road surface conditions.

14. a step of receiving, by a management server, an acoustic signal generated by a movement of a mobile object on a road from a road surface condition detection device installed on the road; the management server classifying the acoustic signal into a normal state or an abnormal state to initially determine a road surface condition; If the abnormal state is detected, the management server secondarily determines a road surface condition including at least one of wet, icy, slush, and snowy; Including, The road surface condition detection device measures the surface temperature, ambient temperature, and humidity of the road, The road surface condition detection method, wherein the primary determination is performed using a generative model based on a difference in frequency between the normal state and the abnormal state, and the secondary determination is performed using a discriminative model based on a frequency range set for each of the road surface conditions.

Images