TW202040416A - Pavement detection system and method thereof - Google Patents

Abstract

Provided is a pavement detection system, which includes a pavement imaging device for capturing positioning information of a pavement and images of the pavement to provide the positioning information and images of the pavement; and a server for receiving the positioning information and images of the pavement from the pavement imaging device, wherein a pavement imaging distress identification and a pavement imaging geometric operation are performed based on the positioning information and images of the pavement. In addition, the present invention also provides a pavement detection method.

Description

Road detection system and detection method thereof

The present invention relates to a road detection system, in particular to a road detection system and a detection method using a road imaging device and a server.

Generally speaking, the current road surface detection can be roughly divided into manual inspection methods and fully automatic image recognition methods. The manual inspection method is carried out in accordance with the relevant road regulations. When implementing road inspections, at least multiple engineers are required to assist each other. Moreover, the types of road damage and serious situations are assessed by visual inspection. Therefore, the manual inspection method The test results tend to be subjective, and at the same time, it is more prone to human error.

However, the automatic image recognition method uses sensors, cameras, cameras, feature detection equipment or sensing devices to collect road surface images, so the detection results of the automatic image recognition method are better than the manual inspection method.

However, the fully automatic image recognition methods used today still have the following problems: 1. The detection results are easily interfered by sunlight and shadows, which will make image processing difficult and reduce the detection efficiency, 2. The detection results are easily affected by the light source, and 3. The test results are easily affected by road dirt.

Therefore, how to provide a better road detection system and method to overcome the above The shortcomings are indeed one of the important issues at present.

In view of the shortcomings of the aforementioned conventional technologies, the present invention provides a pavement detection system and a road detection method.

According to an embodiment of the present invention, the road detection system of the present invention includes: a road imaging device that captures location data of a road and shoots images of the road to provide location information and road images of the road; and a server, Receive the location information of the road and the road image from the road image device, and perform road image destruction identification and road image geometric calculations based on the location information and the road image.

Preferably, the road imaging device is installed on a windshield in front of a vehicle.

Preferably, the road imaging device includes a GPS device, a GPS processing module, a camera device, an image processing module, a road data processing module, and a road data transmission module.

Preferably, the GPS device provides positioning data of the road, and transmits the positioning data to the GPS processing module, the GPS processing module calculates the positioning information from the positioning data, and the camera device performs Shooting and transmitting the captured road image to the image processing module, and the image processing module pre-processes the road image.

Preferably, the road data processing module combines the location information of the road and the pre-processed road image.

Preferably, the road data transmission module transmits the combined positioning information of the road and the pre-processed road image to the server.

Preferably, the server includes a road data receiving module, an image detection module Group, an image calibration module, a damage identification module and a road database.

Preferably, the road data receiving module receives the positioning information of the road and the road image, the image detection module detects the road image of the road, and the image calibration module extracts an image from the road image Range, and geometrically transform the image range into an orthographic image.

Preferably, the damage identification module recognizes the damaged part from the orthographic image, and stores the damaged part in the road database.

Preferably, the destruction identification module includes a destruction classification module and a destruction calculation module, the destruction classification module uses deep learning technology to classify the destruction part, and the destruction calculation module The geometric information is calculated for the destroyed part.

Preferably, the classification includes patching, potholes, cracks or a combination thereof.

Preferably, the geometric information is length, width, depth or area.

According to an embodiment of the present invention, the road detection method of the present invention includes the following steps: using a road imaging device to capture location data of a road and shooting images of the road to provide location information and road images of the road; using a servo The device receives the location information of the road and the road image transmitted from the road imaging device; and uses the server to perform road image destruction identification and road image geometric calculations based on the location information and the road image.

According to an embodiment of the present invention, the road detection method of the present invention further includes the following steps: installing the road imaging device on a windshield in front of a vehicle.

1‧‧‧Road imaging device

11‧‧‧GPS device

12‧‧‧Camera Device

13‧‧‧GPS Processing Module

14‧‧‧Image Processing Module

15‧‧‧Road data processing module

16‧‧‧Road data transmission module

3‧‧‧Server

31‧‧‧Road data receiving module

32‧‧‧Image Detection Module

33‧‧‧Image Calibration Module

34‧‧‧Destruction recognition module

341‧‧‧Destruction classification module

342‧‧‧Destruction calculation module

35‧‧‧Road Database

S21, S23, S25‧‧‧Step

Figure 1 shows a block diagram of the road detection system of the present invention; and Figure 2 shows a flowchart of the steps of the road detection method of the present invention.

The following is a specific embodiment to illustrate the implementation of the present invention. Those skilled in the art can easily understand the other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied by other different specific examples, and various details in the specification of the present invention can also be modified and changed based on different viewpoints and applications without departing from the spirit of the present invention.

It should be noted that the structure, ratio, size, etc. shown in the drawings of the present invention are only used to match the content disclosed in the manual for those who are familiar with the art to read and understand, and are not used to limit the implementation of the present invention. Therefore, it does not have any technical significance. Any structural modification, proportional relationship change or size adjustment, without affecting the effects and objectives that can be achieved by the invention, should fall within the disclosure of the invention The technical content must be covered.

The present invention proposes a pavement detection system, which records all road/pavement damage conditions in a database through the detection function of positioning information and road images, which can effectively provide assistance for relevant personnel in diagnosing road/pavement damage conditions.

Figure 1 shows a block diagram of the road detection system of the present invention. As shown in Figure 1, the road detection system of the present invention includes a road imaging device 1 and a server 3. The road imaging device 1 can be installed in front of a vehicle On the windshield, the server 3 can be a cloud server, a back-end server or an Automated Pavement Distress Analyzer (APDA), but the present invention is not limited.

As shown in Figure 1, the road imaging device 1 includes a GPS device 11, a GPS processing module 12, a camera device 13, an image processing module 14, a road data processing module 15 and a Road data transmission module 16. The road imaging device 1 mainly captures location data of a road and shoots an image of the road to provide location information and road images of the road.

Then, as shown in Fig. 1, the server 3 will receive the road location information and road image from the road imaging device 1, and use the location information and the road image to perform road image destruction identification and road image geometric calculations, where, The server 3 includes a road data receiving module 31, an image detection module 32, an image calibration module 33, a damage identification module 34, and a road database 35.

Specifically, as shown in FIG. 1, the GPS device 11 can provide road location data and send the location data to the GPS processing module 12. The GPS processing module 12 can calculate the location information from the location data. 13 will photograph the road and send the photographed road image to the image processing module 14. After that, the image processing module 13 will pre-process the road image.

Then, as shown in FIG. 1, the road data processing module 15 merges the location information of the road and the pre-processed road image, and the road data transmission module 15 merges the combined location information and the pre-processed road The image is transmitted to the server 3 in real time.

Subsequently, the road data receiving module 31 in the server 3 of the present invention receives the positioning information and the road image, and the image detection module 32 divides the positioning information and the road image, and detects the road image. Then, The image calibration module can extract an image range from the road image, and at the same time geometrically convert the image range into an orthographic image.

Please continue to refer to FIG. 1, the damage identification module 34 in the server 3 can identify the damaged part from the orthographic image, and store the damaged part in the road database 35. Since all the real-time damage conditions of roads are collected and stored in the road database 35 of the present invention, the present invention allows engineers or related personnel to directly check the damage conditions of the road through a user interface. Inquiry, and then effectively and instantly grasp the road damage situation.

Wherein, the damage identification module 34 may include a damage classification module 341 and a damage calculation module 342. In other words, the damage classification module 341 uses deep learning technology to classify the damaged part or determine its damage category The classification can be repair frays, potholes, cracks or a combination thereof, but does not limit the present invention. In addition, the damage calculation module 342 calculates the damaged part and provides geometric information. The geometric information can be length, width, depth, or area, but the present invention is not limited.

In addition, in addition to the road detection system proposed by the invention, the invention also proposes a road detection method.

As shown in FIG. 2, according to an embodiment of the present invention, the road detection method of the present invention may include the following steps S21-S25. Step S21: Use a road imaging device to capture the positioning data of a road and shoot the image of the road to provide positioning information and road images of the road; Step S23: Use a server to receive the road imaging device sent from the road The positioning information of the road and the road image; and step S25: using the server to perform road image destruction identification and road image geometric calculation based on the positioning information and the road image.

According to an embodiment of the present invention, the road detection method of the present invention may further include the following steps: installing the road imaging device on a windshield in front of a vehicle.

It is worth mentioning that the above-mentioned embodiments of the present invention can all be performed by genetic algorithms or other algorithms, but the present invention is not limited.

In summary, the present disclosure can use the location data acquisition and road image shooting functions of the road imaging device, and use the server to perform road image damage identification and road image geometric calculations based on the location information and road images, thereby effectively improving road diagnosis /Road damage The auxiliary accuracy of the situation.

The above-mentioned embodiments are only illustrative of the effects of the present invention, but not used to limit the present invention. Anyone familiar with the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. In addition, the number of elements in the above-mentioned embodiments is merely illustrative, and is not intended to limit the present invention. Therefore, the scope of protection of the rights of the present invention should be listed in the following patent scope.

1‧‧‧Road imaging device

11‧‧‧GPS device

12‧‧‧Camera Device

13‧‧‧GPS Processing Module

14‧‧‧Image Processing Module

15‧‧‧Road data processing module

16‧‧‧Road data transmission module

3‧‧‧Server

31‧‧‧Road data receiving module

32‧‧‧Image Detection Module

33‧‧‧Image Calibration Module

34‧‧‧Destruction recognition module

341‧‧‧Destruction classification module

342‧‧‧Destruction calculation module

35‧‧‧Road Database

Claims (14)

A road detection system includes: a road imaging device that captures location data of a road and shoots an image of the road to provide positioning information and road images of the road; and a server that receives the road imaging device from the road The location information of the road and the road image, and the road image destruction identification and road image geometric calculation are performed by the location information and the road image. The road detection system described in item 1 of the scope of patent application, wherein the road imaging device is installed on a windshield in front of a vehicle. Such as the road detection system described in item 1 of the scope of patent application, wherein the road imaging device includes a GPS device, a GPS processing module, a camera device, an image processing module, a road data processing module and a road Data transmission module. For example, the road detection system described in item 3 of the scope of patent application, wherein the GPS device provides positioning data of the road, and transmits the positioning data to the GPS processing module, and the GPS processing module calculates by the positioning data After outputting the positioning information, the camera device photographs the road, and transmits the photographed road image to the image processing module, and the image processing module preprocesses the road image. For example, the road detection system described in item 4 of the scope of patent application, wherein the road data processing module combines the positioning information of the road and the pre-processed road image. For example, the road detection system described in item 5 of the scope of patent application, wherein the road data transmission module transmits the combined positioning information of the road and the pre-processed road image to the server. The road detection system described in item 1 of the scope of patent application, wherein the server includes a road Data receiving module, an image detection module, an image calibration module, a damage identification module and a road database. For example, the road detection system described in item 7 of the scope of patent application, wherein the road data receiving module receives the positioning information of the road and the road image, the image detection module detects the road image of the road, the image The calibration module extracts an image range from the road image, and geometrically converts the image range into an orthographic image. For example, the road detection system described in item 8 of the scope of patent application, wherein the damage recognition module recognizes the damaged part from the orthographic image, and stores the damaged part in the road database. For example, the road detection system described in item 9 of the scope of patent application, wherein the damage identification module includes a damage classification module and a damage calculation module, and the damage classification module uses deep learning technology for the damage The parts are classified, and the damage calculation module calculates geometric information for the damaged part. For example, the road detection system described in item 10 of the scope of the patent application, wherein the classification is a patch, a pothole, a crack or a combination thereof. For example, the road detection system described in item 10 of the scope of patent application, wherein the geometric information is length, width, depth or area. A road detection method includes: using a road imaging device to capture positioning data of a road and shooting an image of the road to provide positioning information and road images of the road; and using a server to receive data transmitted from the road imaging device The location information of the road and the road image; and the use of the server to perform road image destruction identification and road image geometric operations based on the location information and the road image. For example, the road detection method described in item 13 of the scope of patent application includes: installing the road image It is installed on the windshield in front of a vehicle.

Images