KR20230164950A - Apparatus and method for detecting road pothole - Google Patents

Abstract

A road pothole detection device and method for accurately detecting potholes on a road surface based on data received from a photography terminal attached to moving vehicles through a network are disclosed. A road pothole detection device according to one aspect includes a receiving unit that receives pothole data including pothole location and pothole shape information from a photographing terminal installed in each of a plurality of moving vehicles; A selection unit that compares porthole data to select and group porthole data of the same porthole; and an analysis unit that derives representative pothole data for each group.

Description

Road pothole detection device and method {Apparatus and method for detecting road pothole}

The present invention relates to a road pothole detection device and method, and more specifically, to a road pothole detection device and method for detecting potholes on the road surface using a moving vehicle.

Due to road aging and climate change, the performance of the road surface quickly deteriorates, and potholes occur on the road surface due to the moving load of vehicles. A pothole is a pot-shaped hole that is formed by localized dents in the surface of an asphalt road. Basically, potholes are detected based on the naked eye, and recently, various porthole detection methods have been proposed based on artificial intelligence. Typically, road management agencies such as the Korea Expressway Corporation and the Ministry of Land, Infrastructure and Transport attach pothole detection terminals to road patrol vehicles and automatically detect potholes. However, when only road patrol vehicles are used as mobile vehicles, many vehicles and manpower are required, and since only road patrol vehicles are used, analysis is limited. In particular, pothole detection is performed locally through a porthole detection terminal attached to the vehicle. The accuracy is low. Therefore, a method to increase the accuracy of detecting potholes on the road surface is needed.

The present invention was proposed to solve the above-mentioned problems, and provides a road pothole detection device and method for accurately detecting potholes on the road surface based on data received from a photography terminal attached to moving vehicles through a network. It has a purpose.

In particular, the present invention has another purpose of providing a road pothole detection device and method for accurately detecting potholes on the road surface based on data received from imaging terminals attached to a mobile vehicle that repeatedly moves circularly on the same road. there is.

A road pothole detection device according to one aspect includes a receiving unit that receives pothole data including pothole location and pothole shape information from a photographing terminal installed in each of a plurality of moving vehicles; A selection unit that compares porthole data to select and group porthole data of the same porthole; and an analysis unit that derives representative pothole data for each group.

The selection unit may determine that the two porthole data are porthole data of the same porthole when the normalized difference value of the location and shape information of the two porthole data is less than or equal to a predetermined threshold.

The selection unit may apply a weight to each of the position and shape information when calculating the difference value.

The road pothole detection device further includes a classification unit that classifies the regions of the received pothole data, and the selection unit can compare pothole data for each classified region to select and group pothole data of the same pothole.

The classification unit may classify the area based on any one of a GPS-based area, a cell ID of a base station, and a route map.

The analysis unit may derive the average value of the pothole shape information for each group as representative pothole data.

The porthole shape information may include at least one of the porthole area, diameter, depth, pattern, and length.

A road pothole detection device according to another aspect includes a receiving unit that receives pothole data including the pothole location and a captured image from a photographing terminal installed in each of a plurality of moving vehicles; A selection unit that analyzes porthole shape information in the received captured image and adds it to the received porthole data, compares the porthole data to which the porthole shape information is added, and selects and groups porthole data of the same porthole; and an analysis unit that derives representative pothole data for each group.

A method of detecting a pothole in a road pothole detection device according to another aspect includes receiving pothole data including pothole location and pothole shape information from a photographing terminal installed in each of a plurality of moving vehicles; Comparing porthole data to select and group porthole data of the same porthole; and deriving representative pothole data for each group.

In the grouping step, if the normalized difference value of the position and shape information of the two porthole data is less than or equal to a predetermined threshold, the two porthole data may be determined to be porthole data of the same porthole.

The grouping step may apply a weight to each of the position and shape information when calculating the difference value.

The method further includes classifying regions of the received pothole data, and the grouping step can select and group pothole data of the same porthole by comparing pothole data for each classified region.

In the classification step, the area may be classified based on any one of a GPS-based area, a cell ID of a base station, and a route map.

In the deriving step, the average value of the pothole shape information for each group can be derived as representative pothole data.

The porthole shape information may include at least one of the porthole area, diameter, depth, pattern, and length.

The present invention can detect portholes more accurately by selecting porthole data at the same point and analyzing the portholes based on the similarity of the porthole data received from a photography terminal attached to a plurality of moving vehicles through a network.

The present invention can reduce the cost of operating separate vehicles and personnel by analyzing potholes on the road using mobile vehicles that repeatedly move in a circular motion on the same road, and can analyze potholes on the road over a wide area.

Figure 1 is a diagram showing a system for detecting road potholes according to an embodiment of the present invention.
Figure 2 is a diagram showing the configuration of the road pothole detection device of Figure 1.
Figure 3 is a diagram showing areas based on GPS location according to an embodiment of the present invention.
Figure 4 is a diagram showing cells of base stations according to an embodiment of the present invention.
Figure 5 is a flowchart explaining a method for detecting road potholes according to an embodiment of the present invention.
Figure 6 is a flowchart explaining a method for detecting road potholes according to another embodiment of the present invention.

Hereinafter, embodiments disclosed in the present specification will be described in detail with reference to the attached drawings. However, identical or similar components will be assigned the same reference numbers regardless of reference numerals, and duplicate descriptions thereof will be omitted. The suffix "part" for the components used in the following description is given or used interchangeably only considering the ease of preparing the specification, and does not have a distinct meaning or role in itself. Additionally, in describing the embodiments disclosed in this specification, if it is determined that detailed descriptions of related known technologies may obscure the gist of the embodiments disclosed in this specification, the detailed descriptions will be omitted. In addition, the attached drawings are only for easy understanding of the embodiments disclosed in this specification, and the technical idea disclosed in this specification is not limited by the attached drawings, and all changes included in the spirit and technical scope of the present invention are not limited. , should be understood to include equivalents or substitutes.

Terms containing ordinal numbers, such as first, second, etc., may be used to describe various components, but the components are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

In implementing the present invention, the components may be subdivided for convenience of explanation, but these components may be implemented in one device or module, or one component may be divided into multiple devices or modules. It can also be implemented in

Figure 1 is a diagram showing a system for detecting road potholes according to an embodiment of the present invention. Referring to FIG. 1, the system according to this embodiment includes a photographing terminal 111 installed in a mobile vehicle 110, a road pothole detection device 130, and a mobile communication network 120 connecting them. Here, the mobile communication network 120 includes 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth communication, and infrared communication. , ultrasonic communication, visible light communication (VLC), LoRA (Long Range), etc., but are not limited thereto, and may be connected to a wired communication network.

The photographing terminal 110 may include a camera, a communication module, a GPS receiver, memory, and a processor. The camera captures images of the road surface, the communication module communicates with the mobile communication network 120, and the GPS receiver receives satellite signals. The memory stores a program for operating the photographing terminal 110, the program can be executed by a processor, and stores information on the vehicle in which the photographing terminal 110 is installed. The processor can obtain the current location, date, time, vehicle speed, etc. through a GPS receiver or communication module. The processor of the recording terminal 110 analyzes the road surface image captured by the camera and transmits the pothole data to the road pothole detection device 130 through the communication module and mobile communication network 120. Additionally, the processor can transmit the captured image along with the pothole data to the road pothole detection device 130. The processor can acquire pothole data using a pre-trained artificial intelligence model.

Portholes include common potholes and cracks. A general pothole refers to a jar-shaped hole formed in the road, and a crack refers to a gap in the road. Therefore, the pothole in the present invention should be understood to include both general portholes and cracks. The porthole data includes porthole type (general porthole, crack, etc.), porthole diameter, porthole area, porthole depth, porthole pattern (e.g., crack pattern), porthole length (e.g., crack length), and porthole shape (e.g., circular, oval). etc.), pothole location (e.g. GPS coordinates, cell ID, etc.), pothole shooting date (00/00/0000), pothole shooting time (00:00:00), pothole shooting weather (cloudy, rain, clear, etc.) ), device information (e.g. camera and device information), vehicle information, vehicle movement speed, lane information (e.g. 1 lane/2 lane/3 lane, etc.). However, it is not limited to this and various other elements can be added.

The moving vehicle 110 may be a bus, a resource recovery vehicle, a passenger car, etc. that repeatedly move on the same road surface in a circular motion. In the case of operating a separate dedicated road patrol vehicle as in the past, rapid response may be difficult because road management requires a large number of vehicles and manpower to manage the surface of all roads. In the present invention, in order to solve this problem and quickly detect potholes, pothole data is collected by installing a photographing terminal 110 in a circulating vehicle that runs on the road every day. In particular, dedicated road patrol vehicles cannot frequently drive on the same road, but circular vehicles repeatedly drive on the same road, so a large amount of pothole data can be collected for the same road. For example, a bus can be assumed as a representative example of a circular moving vehicle. Basically, the bus operation route is determined, and multiple buses are assigned to the same route, so that pothole data can be collected and transmitted to the road pothole detection device 130 as multiple vehicles pass on the same road.

The road pothole detection device 130 detects potholes on the road surface by analyzing pothole data received from the photographing terminals 110 installed in the moving vehicles 110. More specifically, the road pothole detection device 130 classifies the pothole data by region, compares the pothole data for each region, selects and groups the pothole data at the same point, and groups the pothole data at the same point based on the grouped pothole data at the same point. Derive the average data of Here, the average data includes the diameter, area, and depth of the pothole. The road pothole detection device 130 may be implemented in the form of a cloud server, or in the form of a local server or mobile edge computing (MEC) server close to the area for fast real-time processing and large-capacity data processing. Hereinafter, it will be described in more detail with reference to the drawings.

Figure 2 is a diagram showing the configuration of the road pothole detection device of Figure 1. Referring to FIG. 2, the road pothole detection device 130 may include a receiving unit 131, a classification unit 132, a sorting unit 133, an analysis unit 134, and a storage unit 135. The road pothole detection device 130 may include a memory, one or more processors (CPU), a peripheral interface, an input/output (I/O) subsystem, a display device, an input device, and a communication circuit. The memory may include high-speed random access memory, and may also include one or more magnetic disk storage devices, non-volatile memory such as flash memory devices, or other non-volatile semiconductor memory devices. Memory can store various information and program instructions, and the program is executed by the processor. Peripheral interfaces connect input/output peripheral devices with the processor and memory. One or more processors execute various software programs and/or sets of instructions stored in memory to perform various functions and process data for the system. The I/O subsystem provides an interface between input/output peripheral devices such as display devices and input devices and peripheral interfaces. The communication circuit performs communication through an external port or communication by RF signals. Communications circuitry converts electrical signals to RF signals and vice versa, through which RF signals can be communicated with communications networks, other mobile gateway devices, and communications devices. The reception unit 131, classification unit 132, selection unit 133, analysis unit 134, and storage unit 135 are implemented as programs, stored in memory, and executed by at least one processor, and are implemented with hardware and It can be implemented and operated through a combination of software.

The receiving unit 131 receives pothole data and captured images from the recording terminals 110 installed in the mobile vehicles 110 through the mobile communication network 120 and stores them in the storage unit 135. The received porthole data is as follows: porthole type, porthole diameter, porthole area, porthole depth, porthole shape, porthole location, porthole pattern, porthole length, porthole shooting date, pothole shooting time, pothole shooting weather, device information, and vehicle. Contains information, vehicle movement speed, and lane information fields. However, it is not limited to this and various other elements can be added.

Porthole data i=[Porthole type, porthole diameter, porthole area, porthole depth, porthole pattern, porthole length...]

The classification unit 132 classifies the pothole data received from the receiving unit 131 by region. Here, the region can be divided into a GPS-based area, a telecommunication company's cell ID, a route map (e.g., a bus route map), etc. Preferably, the classification unit 132 may classify the pothole data stored in the storage unit 135 by inserting a region classification field. Examples are shown in [Table 1] to [Table 3] below.

Region category 1 Regional classification 2 … Route A_Pothole data_1 Route B_Pothole data_1 … Route A_Pothole data_2 Route B_Pothole data_2 … Route A_Pothole data_3 Route B_Pothole data_3 … Route A_Pothole data_4 Route B_Pothole data_4 … Route A_Pothole data_5 Route B_Pothole data_5 … … … …

[Table 1] is an example of classifying pothole data using bus routes as a regional classification field. A method of classifying the pothole data received from the filming terminals 110 installed on buses on route A into the same area, and classifying the pothole data received from the filming terminals 110 installed on buses on route B into the same area. Pothole data is classified as follows.

Region category 1 Regional classification 2 … GPS area 1_pothole data_1 GPS Area 2_Pothole Data_1 … GPS area 1_pothole data_2 GPS area 2_pothole data_2 … GPS area 1_pothole data_3 GPS area 2_pothole data_3 … GPS area 1_pothole data_4 GPS area 2_pothole data_4 … GPS Area 1_Pothole Data_5 GPS Area 2_Pothole Data_5 … … … …

[Table 2] is an example of classifying pothole data using the GPS location-based area as a regional classification field. GPS locations are displayed in degrees latitude/longitude and typically have an accuracy of 10 to 50 meters. Pothole data can be classified as shown in [Table 2] by dividing the region into an area (e.g., latitude/longitude range) that reflects the error range in the GPS location coordinates at the time the pothole data was collected. Figure 3 is a diagram showing areas based on GPS location according to an embodiment of the present invention. As shown in FIG. 3, a specific geographical range is divided into a plurality of areas based on latitude/longitude, and pothole data may be classified for each divided area.

In the example of [Table 2], pothole data received from the photographing terminals 110 of buses passing through the same GPS area (eg, GPS area 1 in FIG. 3) are classified as data from the same area. Basically, GPS includes Assisted GNSS (Global Navigation Satellite System) and standalone GNSS. With traditional standalone GNSS, the device's GNSS receiver receives satellite signals and calculates the location. A-GNSS performs location determination with higher accuracy by augmenting the stand-alone GNSS function with data provided by the network.

Region category 1 Regional classification 2 … Cell ID 1_Porthole data_1 Cell ID 2_Porthole data_1 … Cell ID 1_Porthole data_2 Cell ID 2_Porthole data_2 … Cell ID 1_Porthole data_3 Cell ID 2_Porthole data_3 … Cell ID 1_Porthole data_4 Cell ID 2_Porthole data_4 … Cell ID 1_Porthole data_5 Cell ID 2_Porthole data_5 … … … …

[Table 3] is an example of classifying porthole data using the cell ID of the base station as a region classification field. Here, the cell ID is identification information of the base station where the photographing terminal 110 is camped. Since the installation location, cell coverage, and cell ID of the base station are already known, each cell coverage based on the installation location of each base station can be set as the area where porthole data is classified. Figure 4 is a diagram showing cells of base stations according to an embodiment of the present invention. As shown in Figure 4, a specific geographic range can be divided into the coverage of cells of base stations. Porthole data can be classified according to the coverage of each divided cell. In the example of [Table 3], pothole data containing the same cell ID are classified as data in the cell coverage area corresponding to the cell ID. At this time, at a location where cells from multiple base stations are detected overlapping, the cell ID with the highest signal quality (e.g., RSRP, SINR, RSRQ, RSSI) can be simply set as the region classification field.

Regions can be classified in various ways without being limited to the examples of [Table 1] to [Table 3] above. For example, the location coordinates of the photographing terminal 110 are estimated based on the angle of arrival (AoA) and round-trip time (RTT) of the signal transmitted and received between the photographing terminal 110 and the base station. And, the pothole data can be classified by dividing the region into an area that reflects the error range (e.g., 150m) in the estimated location coordinates. In addition to the angle of arrival (AoA) and round trip time (RTT), pothole data can be classified by estimating the location coordinates of the photographing terminal 110 using the observed time difference of arrival (OTDOA) method and then setting the region. Alternatively, when the photographing terminal 110 detects multiple cell IDs at a location where cells of several base stations overlap using the estimated position coordinates, the ID of the cell closest to the photographing terminal 110 is divided into regions. It can be set as a field.

The basic principle of OTDOA is to estimate the received signal time difference (RSTD) of the Positioning Reference Signal (PRS) sent by each cell, estimate the intersection area based on the time difference from at least three cells, and estimate the intersection area at the imaging terminal (110). ) can be estimated. In PRS, PRS transmission information for up to 24X3 (3-sector) cells can be set to the photography terminal 110 through higher-layer signaling. The detection accuracy of OTDOA is 50-200m. Additionally, OTDOA is a structure commonly used in 4G LTE/5G NR (New Radio) cellular communications and provides similar performance.

The selection unit 133 compares the classified pothole data for each region to select and group the pothole data at the same point. For example, when there are N pieces of porthole data received in a specific area, the porthole data of the same porthole is selected and grouped. Porthole data of the same porthole can be selected based on the porthole location and shape information (depth, diameter, area, etc.) included in the porthole data. In the case of the same porthole, the location and shape information of the porthole match and the difference value is theoretically 0. Therefore, various methods such as maximum value comparison and correlation analysis can be applied as a method of evaluating the similarity of porthole data of the same porthole, but in this embodiment, similarity is evaluated based on the difference value of the position and shape information of the pothole.

The selection unit 133 calculates the difference value (D) of the position and shape information between the two pothole data for all pothole data in a specific area by the following (Equation 1), and the difference value (D) is predetermined. If it is less than the threshold (R _th ), it is determined that the two porthole data match.

(Equation 1)

Difference value (D) = [(Porthole location _i - Porthole location _j ) ² + (Porthole depth _i - Porthole depth _j ) ² + (Porthole diameter _i - Porthole diameter _j ) ² + (Porthole width _i - Porthole width _j ) ² +… )] / normalized value

Normalized value = (porthole location _i ) ² + (porthole depth _i ) ² + (porthole diameter _i ) ² + (porthole width _i ) ² +… )

Here, index i is input data and index j is comparison data, which are two data selected from all pothole data in a specific area.

According to Equation 1 above, the difference value (D) of the position and shape information between the two porthole data is normalized and basically exists in the range of 0≤D≤1. The threshold (R _th ) is set to a value within the range between 0 and 1, and if the difference value (D) is less than or equal to the threshold value (R _th ), it can be determined that the two pothole data match. That is, if D≤R _th , the two porthole data coincide, and if D>R _th , the two porthole data may be determined to be different. When the range of similarity is wide, the threshold (R _th ) can be set close to '1', and to narrow the range of similarity and increase accuracy, the threshold (R _th ) can be set close to '0'.

In another embodiment, the selection unit 133 may reflect the importance of a specific parameter of the pothole data as high when comparing two pothole data. For example, the location of the pothole may be reflected as more important than information related to the size of the pothole. To this end, the selection unit 133 may assign higher weight to parameters to be reflected as more important. For example, the selection unit 133 may calculate the difference value (D) by applying different weights to each parameter as shown in Equation 2 below.

(Equation 2)

Difference value (D) = [(Porthole location _i - Porthole location _j ) ² × Weight _position + (Porthole depth _i - Porthole depth _j ) ² × Weight _depth + (Porthole diameter _i - Porthole diameter _j ) ² × Weight _diameter + ( Porthole area _i - Porthole area _j ) ² × weight _area +… )] / normalized value

Normalized value = (porthole position _i ) ² × weight _position + (porthole depth _i ) ² × weight _depth + (porthole diameter _i ) ² × weight _depth + (porthole width _i ) ² × weight _width +… )

For example, weight _position = 1, weight _diameter = 0.5, weight _depth = 0.2, weight _width = 0. In this case, the weight of location information is twice as important as diameter information and five times as important as depth information.

The analysis unit 134 derives representative pothole data for each group selected and grouped by the selection unit 133. For example, the analysis unit 134 may derive average data such as the average diameter, average area, and average depth of potholes for each group. The example is as shown in [Table 4] below. Alternatively, the analysis unit 134 may derive the maximum and minimum values, such as the diameter, area, and depth of the pothole for each group, as representative pothole data.

group 1 group 2 group 3 no similarity Pothole data-1 Pothole data-7 Pothole Data-12 Pothole Data-15 Pothole data-2 Pothole Data-8 Pothole Data-13 Pothole Data-16 Pothole data-3 Pothole data-9 Pothole Data-14 Pothole Data-17 Pothole data-4 Pothole data-10 Pothole Data-18 Pothole data-5 Pothole Data-11 Pothole Data-19 Pothole data-6 ... Average value of group 1
{Depth: OOOm
Diameter: OOOm
Height: OOOm
...} Average value of group 2
{Depth: OOOm
Diameter: OOOm
Height: OOOm
...} Average value of group 3
{Depth: OOOm
Diameter: OOOm
Height: OOOm
...}

The analysis unit 134 may output the derived representative pothole data for each group (e.g., average data, maximum or minimum value, etc.) through a display device, etc. In one embodiment, the analysis unit 134 may match the location of the pothole of each group to map data and output representative pothole data at the corresponding location of the map data, and may be close to the representative pothole data among the captured images in each group. Captured images with shapes can also be output. In detail, road lane information may also be output with reference to lane information included in the pothole data.

In the above embodiment, it has been described that the photographing terminal 110 analyzes the shape information (diameter, area, depth, etc.) of the pothole and transmits it to the road pothole detection device 130, but the photographing terminal 110 is not limited thereto. In addition to the shape information of the pothole, only the remaining parameters (location, shooting time, date, etc.) are transmitted as pothole data together with the captured image to the road pothole detection device 130, and the selection unit 133 of the road pothole detection device 130 By analyzing the captured image, the shape information (diameter, area, depth, etc.) of the pothole can be analyzed and stored in the storage unit 135 for use.

Figure 5 is a flowchart explaining a method for detecting road potholes according to an embodiment of the present invention.

Referring to FIG. 5, in step S501, the road pothole detection device 130 receives pothole data from the photographing terminals 110 installed in the moving vehicles 110 through the mobile communication network 120 and stores them in the storage unit 135. ) to save it. In one embodiment, the road pothole detection device 130 may also receive captured images from the capturing terminals 110. The received porthole data includes porthole type, porthole diameter, porthole area, porthole depth, porthole shape, porthole location, porthole pattern, porthole length, pothole shooting date, pothole shooting time, pothole shooting weather, device information, vehicle information, and vehicle movement. Includes speed and lane information fields. However, it is not limited to this and various other elements can be added.

In step S502, the road pothole detection device 130 classifies the received pothole data by region. Here, the region can be divided into a GPS-based area, a telecommunication company's cell ID, a route map (e.g., a bus route map), etc. Preferably, the road pothole detection device 130 can classify the pothole data stored in the storage unit 135 by inserting a region classification field.

In step S503, the road pothole detection device 130 compares the classified pothole data for each region to select and group the pothole data at the same point. The road pothole detection device 130 can select and group pothole data at the same point based on the pothole location and shape information (depth, diameter, area, etc.) included in the pothole data. In one embodiment, the road pothole detection device 130 calculates the difference value (D) of the position and shape information between two pothole data for all pothole data in a specific area using Equation 1, and If the difference value (D) is less than or equal to a predetermined threshold (R _th ), it is determined that the two porthole data match, and the porthole data at the same point is selected and grouped. In one embodiment, the road pothole detection device 130 may reflect the importance of a specific parameter of the pothole data as high when comparing two pothole data. To this end, the road pothole detection device 130 may assign higher weight to parameters to be reflected as more important, as shown in Equation 2 above.

In step S504, the road pothole detection device 130 derives representative pothole data for each selected and grouped group. For example, the road pothole detection device 130 can derive average data such as the average diameter, area average, and depth average of potholes for each group, or the maximum diameter, area, depth, etc. of potholes for each group. Values, minimum values, etc. can also be derived as representative pothole data. The road pothole detection device 130 may output representative pothole data for each group (e.g., average data, maximum or minimum value, etc.) through a display device, etc. In one embodiment, the road pothole detection device 130 may match the location of the pothole of each group to map data and output representative pothole data at the corresponding location of the map data, and representative pothole data among images captured within each group. A captured image with a shape close to can be output together.

Figure 6 is a flowchart explaining a method for detecting road potholes according to another embodiment of the present invention.

Referring to FIG. 6, in step S601, the road pothole detection device 130 receives pothole data and captured images from the photographing terminals 110 installed in the moving vehicles 110 through the mobile communication network 120. It is stored in the storage unit 135. The received pothole data includes pothole location, pothole shooting date, pothole shooting time, pothole shooting weather, device information, vehicle information, vehicle movement speed, and lane information fields.

In step S602, the road pothole detection device 130 classifies the received pothole data by region. Here, the region can be divided into a GPS-based area, a telecommunication company's cell ID, a route map (e.g., a bus route map), etc. Preferably, the road pothole detection device 130 can classify the pothole data stored in the storage unit 135 by inserting a region classification field.

In step S603, the road pothole detection device 130 analyzes the captured images received in step S601 to extract shape information (area, depth, diameter, etc.) of the pothole and stores it in the pothole data stored in the storage unit 135. Add.

In step S604, the road pothole detection device 130 selects and groups pothole data at the same point by comparing pothole data for each region to which pothole shape information has been added and the region has been classified. The road pothole detection device 130 can select and group pothole data at the same point based on the pothole location and shape information (depth, diameter, area, etc.) included in the pothole data. In one embodiment, the road pothole detection device 130 calculates the difference value (D) of the position and shape information between two pothole data for all pothole data in a specific area using Equation 1, and If the difference value (D) is less than or equal to a predetermined threshold (R _th ), it is determined that the two porthole data match, and the porthole data at the same point is selected and grouped. In one embodiment, the road pothole detection device 130 may reflect the importance of a specific parameter of the pothole data as high when comparing two pothole data. To this end, the road pothole detection device 130 may assign higher weight to parameters to be reflected as more important, as shown in Equation 2 above.

In step S605, the road pothole detection device 130 derives representative pothole data for each selected and grouped group. For example, the road pothole detection device 130 can derive average data such as the average diameter, average area, average depth, and average length of potholes for each group, or the diameter, area, and depth of potholes for each group. , maximum and minimum values of length, etc. can also be derived as representative porthole data. The road pothole detection device 130 may output representative pothole data for each group (e.g., average data, maximum or minimum value, etc.) through a display device, etc. In one embodiment, the road pothole detection device 130 may match the location of the pothole of each group to map data and output representative pothole data at the corresponding location of the map data, and representative pothole data among images captured within each group. A captured image with a shape close to can be output together.

While this specification includes many features, such features should not be construed as limiting the scope of the invention or the scope of the claims. Additionally, features described in individual embodiments herein may be combined and implemented in a single embodiment. Conversely, various features described in a single embodiment herein may be implemented individually or in combination as appropriate in various embodiments.

Although operations in the drawings are illustrated in a particular order, it should not be understood that such operations are performed in a particular order as shown, or that they are performed in a sequential order, or that all of the described operations are performed to achieve a desired result. . Multitasking and parallel processing can be advantageous in certain environments. In addition, it should be understood that the division of various system components in the above-described embodiments does not require such division in all embodiments. The program components and systems described above may generally be implemented as a package in a single software product or multiple software products.

The method of the present invention as described above can be implemented as a program and stored in a computer-readable form on a recording medium (CD-ROM, RAM, ROM, floppy disk, hard disk, magneto-optical disk, etc.). Since this process can be easily performed by a person skilled in the art to which the present invention pertains, it will not be described in further detail.

The present invention described above is capable of various substitutions, modifications and changes without departing from the technical spirit of the present invention to those of ordinary skill in the technical field to which the present invention pertains. It is not limited by the drawings.

110: moving vehicle
111: shooting terminal
120: mobile communication network
130: Road pothole detection device
131: Receiving unit
132: classification department
133: Sorting unit
134: analysis department
135: storage unit

Claims (15)

In the road pothole detection device,
A receiving unit that receives porthole data including porthole location and porthole shape information from a photographing terminal installed in each of a plurality of mobile vehicles;
A selection unit that compares porthole data to select and group porthole data of the same porthole; and
A road pothole detection device that includes an analysis unit that derives representative pothole data for each group. According to paragraph 1,
The selection unit,
A road pothole detection device characterized in that when the normalized difference value of the location and shape information of the two pothole data is less than a predetermined threshold, the two pothole data are determined to be pothole data of the same pothole. According to paragraph 2,
The selection unit,
A road pothole detection device characterized in that weights are applied to each of the location and shape information when calculating the difference value. According to paragraph 1,
Further comprising a classification unit that classifies the region of the received pothole data,
The selection unit,
A road pothole detection device that compares pothole data for each classified region and selects and groups pothole data of the same pothole. According to paragraph 4,
The classification department,
A road pothole detection device characterized by classifying areas based on one of GPS-based areas, cell IDs of base stations, and route maps. According to paragraph 1,
The analysis unit,
A road pothole detection device characterized in that the average value of pothole shape information for each group is derived as representative pothole data. According to clause 6,
The porthole shape information is,
A road pothole detection device comprising at least one of pothole area, diameter, depth, pattern, and length. In the road pothole detection device,
A receiving unit that receives porthole data including the porthole location and captured images from a photographing terminal installed in each of a plurality of moving vehicles;
A selection unit that analyzes porthole shape information in the received captured image and adds it to the received porthole data, compares the porthole data to which the porthole shape information is added, and selects and groups porthole data of the same porthole; and
A road pothole detection device that includes an analysis unit that derives representative pothole data for each group. In the method of detecting potholes in a road pothole detection device,
Receiving porthole data including porthole location and porthole shape information from a photographing terminal installed in each of a plurality of moving vehicles;
Comparing porthole data to select and group porthole data of the same porthole; and
A method including the step of deriving representative pothole data for each group. According to clause 9,
The grouping step is,
A method characterized in that when the normalized difference value of the position and shape information of the two porthole data is less than or equal to a predetermined threshold, the two porthole data are determined to be porthole data of the same porthole. According to clause 10,
The grouping step is,
A method characterized in that weights are applied to each of the position and shape information when calculating the difference value. According to clause 9,
Further comprising classifying a region of the received pothole data,
The grouping step is,
A method characterized by comparing pothole data for each classified region and selecting and grouping pothole data of the same porthole. According to clause 12,
The classification step is,
A method characterized by classifying an area based on any one of a GPS-based area, a cell ID of a base station, and a route map. According to clause 9,
The derivation step is,
A method characterized by deriving the average value of pothole shape information for each group as representative porthole data. According to clause 14,
The porthole shape information is,
A method comprising at least one of pothole area, diameter, depth, pattern, and length.