KR20220089138A - Road Dangerous Object Recognition Apparatus and Method - Google Patents

Abstract

An embodiment of the present invention relates to an apparatus and method for recognizing dangerous substances on the road, so as to recognize and determine the occurrence of road hazards including potholes in an economical way without expensive devices/terminals, avoidance of drivers and It is possible to calculate the presence and location of dangerous substances on the road by collecting related driving habits and vehicle driving data generated accordingly, statistically extracting their characteristics, and analyzing them to create rules according to driving behavior in front of dangerous substances on the road.

Description

Road Dangerous Object Recognition Apparatus and Method

The present invention relates to a technology for recognizing dangerous substances on the road, and more particularly, by collecting driving habits related to the driver's avoidance and vehicle operation data generated according to the occurrence of dangerous substances on the road, statistically extracting and analyzing its characteristics, The present invention relates to an apparatus and method for recognizing a road hazard, which can calculate the presence and location of a dangerous material on a road by generating a rule according to a driving behavior in front of the road hazardous material.

In general, a pothole refers to a place where an asphalt road is damaged and a hole is dug like a pot, and there is a high risk of causing an accident. There are various causes, but mainly it is due to poor construction, calcium chloride/salt that melts snow, rainy season/thaw and road cracks due to the driving load of large vehicles.

Looking at the current situation, the number of potholes is increasing year by year due to the recent climate change from temperate to subtropical and the increase in rainfall. In the annual budget, 308 billion won is allocated for porthole improvement and repair of poor roads.

As a conventional porthole recognition method, there are a dedicated vehicle method, a manual report method, an intelligent vision method, and the like.

The dedicated vehicle method requires expensive equipment, a detector (about KRW 300 million) and dedicated operating personnel, and the porthole determination is made by the operator directly.

The manual report method is a method in which the bus/taxi driver directly checks with the naked eye and transmits the event information (for example, location information, photos, etc.) to the porthole report system while driving. Overall, it has the disadvantage of being inefficient.

The intelligent vision method is the latest method to learn and recognize a porthole by applying artificial intelligence by collecting the camera image of a vision-based, that is, a smart phone. There are disadvantages such as performance limitation due to the heat of the terminal and the like.

Registered Patent Publication No. 10-1546700 (2015.08.18.)

The present invention is to solve the above-mentioned conventional problems, the object of which is to provide an apparatus and method for recognizing road hazards that can provide the best performance while being efficient in terms of cost compared to the conventional method using expensive devices/terminals will be.

That is, an object of the present invention is to recognize and determine the occurrence of road hazards including potholes in an economical way without expensive devices/terminals, so that when dangerous substances on the road occur, driving habits related to the driver's avoidance and vehicles generated accordingly It is to provide an apparatus and method for recognizing dangerous substances on the road by collecting driving data, statistically extracting their characteristics, and analyzing them to generate rules according to driving behavior in front of dangerous substances on the road, thereby calculating the presence and location of dangerous substances on the road.

In order to achieve the above object, the device for recognizing road hazards according to an aspect of the present invention analyzes the driving behavior of a corresponding vehicle based on data collected from the vehicle, and the analyzed driving behavior occurs when the driver recognizes a road hazardous material a driving behavior analysis/judgment unit for determining whether or not the driving behavior corresponds to a predetermined specific driving behavior based on the statistical type of driving behavior; and when the analyzed driving behavior corresponds to the preset specific driving behavior, it is predicted that a road hazard has occurred (in the front), and vehicle location information, vehicle speed information, and vehicle type information at the first occurrence of the specific driving behavior may include; a dangerous material location calculation unit for calculating the location of the predicted road dangerous material based on When it is within a radius of the size, it is determined that a statistically significant road hazardous material event has occurred (at the center of the area), and a hazardous material determination unit for confirming the determined type of road hazardous material based on the relevant image information collected from the vehicle ; and a geo-fencing area is set based on the relevant information on road hazardous materials confirmed and confirmed by the dangerous material determination unit, and the presence of a corresponding road hazardous material for a target vehicle within the set geo-fencing area It may further include at least one of an alarm unit for transmitting an alarm message informing the user.

The alarm message may include at least one of a driving direction, a lane, a location, and an image of a road dangerous material related to the corresponding road dangerous material.

The type of road hazards may include at least one of a pothole, a manhole subsidence, a sinkhole, and a falling object.

The data collected from the vehicle by the driving behavior analysis/determination unit may include at least one of vehicle location data, vehicle state and driving data, and image data.

The preset specific driving behavior may include at least one of a sudden deceleration, a sudden stop, a sudden left lane advance change, and a sharp right lane advance change.

The predicted location of the dangerous material on the road in the dangerous material location calculation unit may be calculated as a location added by a preset speed distance according to the vehicle type and speed from the location of the vehicle at the time of the first occurrence of the specific driving behavior.

In order to achieve the above object, a method for recognizing a road hazardous material according to another aspect of the present invention includes the steps of: (a) analyzing the driving behavior of the vehicle based on data collected from the vehicle; (b) determining whether the analyzed driving behavior corresponds to a preset specific driving behavior, wherein the preset specific driving behavior is a statistical type of driving behavior generated when the driver recognizes a road hazardous material; And (c) if the analyzed driving behavior corresponds to the preset specific driving behavior, it is predicted that a road hazard has occurred (in front), and vehicle location information, vehicle speed information, and vehicle speed information at the time of the first occurrence of the specific driving behavior, and may include; (d) the number of occurrences of road hazardous materials predicted in step (c) is greater than or equal to a preset number and predicted in step (c) based on vehicle type information When the occurrence location of each road hazardous material is within a radius of a preset size, it is determined that a statistically significant road hazardous material event has occurred (at the center of the area), and the determined road hazardous material is based on the related image information collected from the vehicle for determining the type of and (e) setting a geo-fencing area based on the relevant information on road hazards confirmed and confirmed in step (d), and corresponding to the target vehicle within the set geo-fencing area The method may further include at least one of transmitting an alarm message notifying the presence of a road dangerous object.

The alarm message may include at least one of a driving direction, a lane, a location, and an image of a road hazardous material related to the corresponding road hazardous material, and the type of the road hazardous material may include at least one of a pothole, a manhole subsidence, a sinkhole, and a falling object. The predetermined specific driving behavior may include at least one of abrupt deceleration, sudden stop, sudden left lane advance change, and sharp right lane advance change.

The data collected from the vehicle in step (a) may include at least one of vehicle location data, vehicle state and driving data, and image data, and the predicted occurrence location of road hazards in step (c) can be calculated as a position added by a preset speed distance according to the vehicle type and speed from the vehicle position at the time of the first occurrence of the specific driving behavior.

According to another aspect of the present invention in order to achieve the above object, it is possible to provide a computer-readable recording medium in which a program for executing the method for recognizing a road hazardous material is recorded in a computer.

According to another aspect of the present invention in order to achieve the above object, it is possible to provide an application stored in a computer-readable recording medium in order to execute the method for recognizing a road hazardous material in combination with hardware.

According to another aspect of the present invention to achieve the above object, it is possible to provide a computer program stored in a computer-readable recording medium in order to execute the method for recognizing road hazards in a computer.

As described above, according to various aspects of the present invention, when a dangerous substance on the road occurs, driving habits related to the driver's avoidance and vehicle operation data generated accordingly are collected, and statistically the characteristics are extracted and analyzed, By creating rules according to driving behavior, the presence and location of dangerous objects on the road can be calculated. Therefore, there is an effect of recognizing and judging the occurrence of road hazards including potholes in an economical, efficient and accurate way only by collecting vehicle data that can determine the driver's driving behavior without separately providing an expensive device/terminal.

1 is a block diagram of a road hazardous material recognition system according to an exemplary embodiment of the present invention;
2 is a block diagram of a road hazardous material recognition device included in the vehicle terminal of FIG. 1 according to an exemplary embodiment of the present invention;
3 is a block diagram of a road hazardous material recognition device included in the server of FIG. 1 according to an exemplary embodiment of the present invention;
4 is a view illustrating various driving behavior events according to road hazardous material recognition in an embodiment of the present invention;
5 is a flowchart of a method for recognizing a road hazard according to an exemplary embodiment of the present invention.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In adding reference numerals to the components of each drawing, the same components are to have the same reference numerals as much as possible even though they are indicated in different drawings. In addition, when it is determined that a detailed description of a known configuration or function related to the embodiment of the present invention may obscure the gist of the present invention, the detailed description thereof will be omitted.

1 is a block diagram of a road hazardous material recognition system according to an exemplary embodiment of the present invention, and as shown in the drawing, it may include a communication network 1 , a vehicle terminal 2 , and a server 3 .

The communication network 1 may be any single or complex network that enables communication between the vehicle terminal 2 and the server 3 by wire, wireless, and/or the Internet, and the like.

The vehicle terminal 2 collects various vehicle-related data, including vehicle location data, vehicle state and operation data, and image data, and transmits it to the server 3, and road hazardous material-related information provided from the server 3 can be received and provided to the driver in the form of various alarms.

The server 3 may generate road hazardous material-related information based on various vehicle-related data provided from the vehicle terminal 2 and provide it to the vehicle terminal 2 . That is, the server 3 collects driving habits related to the driver's avoidance when dangerous substances on the road occur and vehicle (driving) related data generated accordingly, statistically extracts the characteristics and analyzes the driving behavior in front of the dangerous substances on the road. By creating a rule according to the rules, the presence and location of dangerous objects on the road can be calculated.

2 is a block diagram of a road hazardous material recognition device 20 included in the vehicle terminal 2 of FIG. 1 according to an exemplary embodiment of the present invention, and the device 20 is a sensor unit 21 as shown in the drawing. ), a sensor data collection unit 23 , and a communication unit 25 .

The sensor unit 21 is pre-installed on a vehicle and includes various sensors or devices for acquiring various data related to (operation of) the vehicle, for example, providing precise positioning within a 3 to 30 cm error. A GNSS-based position error correction and precise positioning terminal device, a CAN (vehicle operation) device for providing vehicle status and operation data to the outside of the vehicle through vehicle CAN or OBU-II matching, and vehicle-mounted to acquire image data It may include a camera or a vehicle-mounted terminal (eg, a black box) including a camera.

The sensor data collection unit 23 selectively collects and processes data (eg, CAN/precision positioning/image data) required for road hazard recognition among various vehicle-related data acquired through the sensor unit 21 in real time. can

The communication unit 25 transmits the data collected and processed through the sensor data collection unit 23 to the server 3 , and receives road hazardous material-related information (eg, an alarm message, etc.) transmitted from the server 3 . can be provided to the driver.

3 is a block diagram of a road hazardous material recognition device 30 included in the server 3 of FIG. 1 according to an exemplary embodiment of the present invention. As shown in the figure, the device 30 includes a communication unit 31 . , a driving behavior analysis/determination unit 33 , a hazardous material location calculation unit 35 , a hazardous material determination unit 37 , and an alarm unit 39 may be included.

The communication unit 31 receives necessary data for recognizing a road hazardous material transmitted from the vehicle terminal 2 of the vehicle, and transmits road hazardous material related information (eg, alarm information, etc.) generated by the server 3 to the vehicle terminal ( 2) can be transmitted.

In this embodiment, data necessary for recognizing road hazards may include CAN/precise positioning/image data, etc., and more specifically, for example, at least one or more of vehicle location data, vehicle state and driving data, and image data. may include

The driving behavior analysis/determination unit 33 analyzes the driving behavior of the vehicle based on the data necessary for recognizing road hazards from the vehicle terminal 2 collected through the communication unit 31, and the analyzed driving behavior is In order to determine whether the driving behavior corresponds to a predetermined specific driving behavior, whether the real-time driving behavior of the vehicle corresponds to a change in the driver's vehicle operation (ie, a specific driving behavior) according to whether the vehicle is a dangerous road ahead in the driving direction during driving. can determine whether

In this embodiment, the specific driving behavior may be preset based on a statistical type of driving behavior generated when the driver recognizes a road hazard, for example, rapid deceleration (A), sudden stop, as shown in FIG. 4 . It may include at least one of (B), a sudden left lane change (C), and a sharp right lane advance change (D).

The driving behavior analysis/determination unit 33, for example, as described in Table 1, the driving behavior of the vehicle based on data on the vehicle speed, latitude and longitude, time, and yaw rate per second If the vehicle decelerates 17 km/h or more and the speed falls below 6.0 km/h, the driving behavior is judged as rapid deceleration (A), and based on the data on vehicle speed, latitude and longitude, time, and yaw rate If the driving behavior of the vehicle decelerates more than 17 km/h per second and falls below the speed 5.0 km/h, the driving behavior is judged as a sudden stop (B), and the vehicle speed, driving direction, latitude and longitude, steering wheel angle, wheel angle, Based on the data on time and yaw rate, the driving behavior of the vehicle is changed to the left 10 sec or more lane at a speed of 30 km/h or more, and the accumulated angle for 5 seconds belongs to 3 ㅀ/sec or less In this case, the driving behavior is determined as a sudden left lane change (C), and the vehicle is based on data on the vehicle speed, driving direction, latitude and longitude, steering wheel angle, wheel angle, time, and yaw rate. If the driving behavior of the driver is at a speed of 30 km/h or higher, the direction of travel changes to the right lane for 10 sec or more, and the accumulated angle for 5 seconds falls within 3 ˚/sec or less, the driving behavior can be judged as a right-hand lane change (D). have.

[Table 1]

If the driving behavior analyzed through the driving behavior analysis/judging unit 33 corresponds to a preset specific driving behavior, the dangerous substance location calculation unit 35 predicts that a dangerous substance has occurred on the road (in front), and the specific driving behavior is Based on the vehicle location information, vehicle speed information, and vehicle type information at the time of first occurrence, it is possible to calculate the location of the occurrence of the dangerous object on the road.

The dangerous material location calculation unit 35 may calculate the location of the occurrence of the dangerous material on the road based on the vehicle location information at the time of the first occurrence of the specific driving behavior (that is, the first location information of the discovery of the dangerous material on the road) and preset speed distance information. have.

Dangerous material location calculation unit 35, for example, as shown in FIG. 4, the location (i.e., A + B) plus the speed distance (B) for each vehicle type from the initial location (A) of finding a road hazardous material It can be calculated by the (central) position.

In this embodiment, the speed distance (m) information for each vehicle type is the vehicle type (eg, bus, truck, passenger car, etc.) and the speed (eg, 100km/h, 80km/h, 50km/h) can be preset.

[Table 2]

If the number of occurrences (number) of road dangerous substances predicted by the dangerous substances location calculation unit 35 is greater than or equal to a preset number and each occurrence location is within a radius of a preset size, the dangerous substance determination unit 37 is statistically located at the center of the area. It is possible to determine that a significant road hazardous material event has occurred, and the determined type of road hazardous material can be confirmed based on the related image information collected from the vehicle.

For example, as shown in Table 3, the dangerous substance determination unit 37 may set the threshold for the number of occurrences (number) of dangerous substances on the road to 5, and set the threshold for the occurrence distance to a radius of 1.5 m. That is, when the number of occurrences (number) of road dangerous substances predicted by the dangerous substance location calculation unit 35 is 5 or more, which is a preset threshold, and each occurrence location is within a radius of 1.5 m, which is a preset threshold, statistical information is located at the center of the area. It can be confirmed that a significant road hazard event has occurred.

[Table 3]

When it is determined that a statistically significant road hazardous material event has occurred, the dangerous material determination unit 37 may determine the type of the road hazardous material based on the relevant image information collected from the vehicle. For example, the type of the road hazardous material is a pothole, a manhole. It may include subsidence, sinkholes, and falling objects.

The alarm unit 39 sets a geo-fencing area based on the related information (information such as location, type, etc.) of the road dangerous material confirmed and confirmed through the dangerous material determination unit 37, and the set geo-fencing It is possible to transmit an alarm message notifying the presence of a dangerous object on the road to a target vehicle within the (Geo-Fencing) area.

In this embodiment, the alarm message may include information such as a driving direction, a lane, a location, and an image of a road dangerous material related to the corresponding road hazardous material.

In addition, the server 3 can provide vehicle operation driver information and vehicle type (eg, passenger car/bus/truck/heavy equipment) information, etc. It is possible to manage the in/out of the vehicle to be managed and provide a list, and the driving behavior analysis/judgment unit 33 analyzing the driving behavior of individual vehicles, that is, the event information on the occurrence of dangerous substances on the road, that is, the final road considering the street speed by vehicle type By statistically checking the location group values on the lanes of dangerous substances, the occurrence of road hazards is judged if it meets the preset road hazard occurrence threshold criteria. When the type is determined and the occurrence/existence of this road hazardous material is finally determined, the target vehicle is managed by targeting the previously confirmed calculation location of the road hazardous material and the geo-fencing area, and the monitoring/display unit (not shown) and the external Related information may be provided to a linkage unit (not shown).

The monitoring/display unit can provide vehicle operation, event occurrence location/geo-fencing area target vehicle display, and surrounding images on the map as a control expression function.

The external link unit can share precise locations/addresses, events and surrounding images with the road management office, road-related public institutions, and interlocking systems upon recognizing road hazards.

5 is a flowchart of a method for recognizing a road hazardous material according to an exemplary embodiment of the present invention. Since it is applied to the server 3 of FIGS. 1 and 3 , the operation of the corresponding server 3 device will be described in parallel.

First, data necessary for recognizing road hazards transmitted from the vehicle terminal 2 of the vehicle through the communication unit 31, for example, CAN/precise positioning (GNSS)/vehicle location data as image-related data (latitude and longitude), the vehicle state and driving data (vehicle speed, driving direction, steering wheel angle, wheel angle, time, yaw rate, etc.), and image data are received and collected (S501).

Next, the driving behavior analysis/determination unit 33 analyzes the driving behavior of the vehicle based on the data required for recognizing road hazards from the vehicle terminal 2 collected through the communication unit 31 in step S501 (S503) ), the analyzed driving behaviors are preset as shown in FIG. 4 and Table 1 for specific driving such as sudden deceleration (A), sudden stop (B), sudden left lane change (C), and sharp right lane change (D). It is determined whether it corresponds to the behavior (S505).

Next, the hazardous material location calculation unit 35 determines that the driving behavior analyzed through the driving behavior analysis/determination unit 33 in step S503 corresponds to a preset specific driving behavior as a result of the determination of step S505 (in front). It is predicted to have occurred, and the location of occurrence of the relevant road hazardous material is calculated based on vehicle location information, vehicle speed information, and vehicle type information when the specific driving behavior first occurred, for example, the road hazardous material of FIG. Calculate the location (ie, A + B) from the initial location (A) of discovery (ie, the starting point of the first driving behavior of the lane) plus the speed distance (B) for each vehicle type (see Table 2) as the (center) position of the road hazard It can be done (S507).

Next, the hazardous material determination unit 37 checks the expected location of the road dangerous material calculated in step S507, collects the image of the starting point of the event, that is, the first location (A) of the road hazardous material discovery in FIG. 4 (S509), the corresponding It is determined by examining whether the expected location of the road hazardous material is a location with a statistically significant frequency of occurrence (based on the predicted location of the road hazardous material previously calculated using information received from terminals of a plurality of vehicles) (S511), step As a result of the determination of S511, it is determined that a statistically significant road hazardous material event has occurred, and based on the related image information collected from the vehicle, whether the determined type of road hazardous material is a pothole, a manhole subsidence, a sinkhole, and a falling object Confirm (S513).

In step S511-S513, if the number of occurrences (number) of road hazardous substances predicted to date is greater than or equal to a preset number and each occurrence location is within a radius of a preset size, the dangerous substance determination unit 37 is statistically located at the center of the corresponding area. It can be determined that a significant road hazard event has occurred (refer to the number and location of occurrences ① to ⑩ in FIG. 4 and Table 3).

The alarm unit 39 sets a geo-fencing area based on the related information (information such as location, type, etc.) of the road dangerous material confirmed and confirmed through the dangerous material determination unit 37 in step S513, and the set A target vehicle entering the geo-fencing area is checked (S515).

Finally, the alarm unit 39 transmits an alarm message including information such as driving direction, lane, location, and road dangerous material image related to the corresponding road dangerous material in real time to the target vehicle identified in step S515 in real time, Notifies the existence (S517). In addition, the terminal 2 of the target vehicle informs the driver of the occurrence of road hazards in various ways such as a warning sound, voice guidance, guidance message, and guidance image based on the alarm message received from the server 3 in step S517, The received alarm message may be transmitted to another nearby vehicle in real time (S519).

On the other hand, according to the method for recognizing road hazards according to the exemplary embodiment of the present invention described above, it is possible to implement a computer-readable recording medium in which a program for executing the method in a computer is recorded.

On the other hand, according to the method for recognizing a road hazard according to an exemplary embodiment of the present invention described above, an application stored in a computer-readable recording medium may be implemented in order to execute the method in combination with hardware.

On the other hand, according to the method for recognizing a road hazardous material according to an exemplary embodiment of the present invention described above, a computer program stored in a computer-readable recording medium may be implemented in order to execute the method in a computer.

For example, as described above, the method for recognizing a road hazardous material according to an exemplary embodiment of the present invention is a computer-readable recording medium including program instructions for performing various computer-implemented operations or an application stored in the recording medium. can be implemented. The computer-readable recording medium may include program instructions, local data files, local data structures, and the like alone or in combination. The recording medium may be specially designed and configured for the embodiment of the present invention, or may be known and used by a person skilled in the art of computer software. Examples of the computer-readable recording medium include hard disks, magnetic media such as floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floppy disks, and ROMs, RAMs, flash memories, and the like. Hardware devices specially configured to store and execute the same program instructions are included. Examples of program instructions may include high-level language codes that can be executed by a computer using an interpreter or the like as well as machine language codes such as those generated by a compiler.

The above description is merely illustrative of the technical spirit of the present invention, and various modifications and variations will be possible without departing from the essential characteristics of the present invention by those skilled in the art to which the present invention pertains. Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to explain, and the scope of the technical spirit of the present invention is not limited by these embodiments. The protection scope of the present invention should be construed by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

1: network
2: car terminal
3: Server
20; Road hazard recognition device included in vehicle terminal
21: sensor unit
23: sensor data collection unit
25: communication department
30: Road hazard recognition device included in the server
31: communication department
33: Driving behavior analysis/judgment unit
35: dangerous goods location calculation unit
37: Dangerous Goods Confirmation Department
39: alarm unit

Claims (19)

Analyzes the driving behavior of the vehicle based on the data collected from the vehicle, and determines whether the analyzed driving behavior corresponds to a specific driving behavior preset based on a statistical type of driving behavior generated when the driver recognizes a road hazardous material driving behavior analysis/judgment unit for judgment; and
When the analyzed driving behavior corresponds to the preset specific driving behavior, it is predicted that a road hazardous material has occurred in front, and based on the vehicle location information, vehicle speed information, and vehicle type information at the first occurrence of the specific driving behavior a hazardous material location calculation unit for calculating the predicted location of the dangerous material on the road;
A road hazard recognition device comprising a. According to claim 1,
When the number of occurrences of road hazardous substances predicted by the dangerous substance location calculator is greater than or equal to a preset number and the occurrence location is within a radius of a preset size, it is determined that a statistically significant road dangerous substance event has occurred, and related image information collected from the vehicle Road hazardous material recognition device, characterized in that it further comprises a dangerous material determination unit for confirming the type of the determined road dangerous material based on. 3. The method of claim 2,
A geo-fencing area is set based on the related information on road hazardous materials confirmed and confirmed by the dangerous material determination unit, and the presence of the relevant road hazardous material is determined for the target vehicle within the set geo-fencing area. Road hazard recognition device, characterized in that it further comprises an alarm for transmitting an alarm message informing. 4. The method of claim 3,
The alarm message is a road hazardous material recognition device, characterized in that it includes at least one of a driving direction, a lane, a location, and an image of a road dangerous material related to the corresponding road hazardous material. 3. The method of claim 2,
The type of road hazardous material is a road hazardous material recognition device, characterized in that it includes at least one of a pothole, a manhole subsidence, a sinkhole, and a falling object. According to claim 1,
The data collected from the vehicle in the driving behavior analysis/determination unit includes at least one of vehicle location data, vehicle state and driving data, and image data. According to claim 1,
The preset specific driving behavior includes at least one of a sudden deceleration, a sudden stop, a sudden left lane change, and a sudden right lane advance change. According to claim 1,
The location of the predicted road hazardous material in the dangerous material location calculation unit is a road hazardous material, characterized in that calculated by adding a preset speed distance according to the vehicle type and speed from the vehicle location at the time of the first occurrence of the specific driving behavior Device. (a) analyzing the driving behavior of the vehicle based on the data collected from the vehicle;
(b) determining whether the analyzed driving behavior corresponds to a preset specific driving behavior, wherein the preset specific driving behavior is a statistical type of driving behavior generated when a driver recognizes a road hazardous material; and
(c) If the analyzed driving behavior corresponds to the preset specific driving behavior, it is predicted that a road hazardous material has occurred in front, and vehicle location information, vehicle speed information, and vehicle type information at the first occurrence of the specific driving behavior calculating the location of the predicted road hazards based on the;
A method for recognizing dangerous goods, including 10. The method of claim 9,
(d) If the number of occurrences of road hazardous substances predicted in step (c) is greater than or equal to a preset number and the predicted occurrence location of each road dangerous substance is within a radius of a preset size, it is determined that a statistically significant road hazardous substance event has occurred and identifying the determined type of road hazardous material based on the relevant image information collected from the vehicle. 11. The method of claim 10,
(e) Set a geo-fencing area based on the relevant information on road hazards confirmed and confirmed in step (d), and apply the corresponding road to the target vehicle within the set geo-fencing area The method for recognizing dangerous substances on the road, characterized in that it further comprises the step of transmitting an alarm message notifying the presence of dangerous substances. 12. The method of claim 11,
The alarm message is a road hazardous material recognition method, characterized in that it includes at least one of a driving direction, a lane, a location, and an image of a road dangerous material related to the corresponding road hazardous material. 11. The method of claim 10,
The road hazardous material type is a road hazardous material recognition method, characterized in that it includes at least one of a pothole, a manhole subsidence, a sinkhole, and a falling object. 10. The method of claim 9,
The data collected from the vehicle in step (a) comprises at least one of vehicle location data, vehicle state and driving data, and image data. 10. The method of claim 9,
The predetermined specific driving behavior includes at least one of abrupt deceleration, a sudden stop, a sudden left lane change, and a sharp right lane advance change. 10. The method of claim 9,
In step (c), the predicted occurrence location of the road hazardous material is a road hazardous material recognition, characterized in that it is calculated as a location added by a preset speed distance according to the vehicle type and speed from the vehicle location at the time of the first occurrence of the specific driving behavior Way. 17. A computer-readable recording medium in which a program for executing the method for recognizing road hazards according to any one of claims 9 to 16 on a computer is recorded. 17. An application stored in a computer-readable recording medium to execute the method for recognizing road hazards according to any one of claims 9 to 16 in combination with hardware. A computer program stored in a computer-readable recording medium in order to execute the method for recognizing road hazards according to any one of claims 9 to 16 in a computer.

Images