WO2017120796A1

WO2017120796A1 - Pavement distress detection method and apparatus, and electronic device

Info

Publication number: WO2017120796A1
Application number: PCT/CN2016/070792
Authority: WO
Inventors: 庞梓维
Original assignee: 富士通株式会社; 庞梓维
Priority date: 2016-01-13
Filing date: 2016-01-13
Publication date: 2017-07-20

Abstract

A pavement distress detection method and apparatus (100, 705), and an electronic device (700). The detection apparatus (100, 705) comprises a region-of-interest determining unit (101) used for determining a region of interest in the reference frame images of a dynamic image, wherein in the dynamic image, images of a predetermined number of frames exist between adjacent reference frame images; a filtering parameter determining unit (102) that determines a first filtering parameter value according to the result of filtering the region of interest; and a filtering unit (103) that filters, according to the first filtering parameter value, the reference frame images and the images of a predetermined number of frames behind the reference frame images to obtain a pavement distress detection result. The technical solution can meet the requirements for dynamically detecting a pavement and computational complexity is low, thereby improving the real-time characteristic and accuracy of detection.

Description

Method for detecting road surface disease, device thereof, and electronic device

Technical field

The present application relates to the field of image processing technologies, and in particular, to a method and device for detecting road surface diseases based on image processing technology, and an electronic device.

Background technique

Pavement Distress includes Cracks and Potholes, which can cause serious damage to driving safety.

The traditional method of detecting road surface disease requires a lot of manpower and financial resources. In recent decades, automatic detection technology for pavement diseases has gradually developed (see literature [1]). Pavement disease automatic detection technology uses digital cameras, analog video recording devices or laser sensors to obtain road surface information, and based on image processing technology to process road surface information to detect road surface diseases, the road surface disease detection results can be used to evaluate road surface conditions (pavement) Condition).

Generally, the method for evaluating road surface conditions is divided into three major steps: first, obtaining road surface information; second, detecting road surface diseases, that is, extracting road surface disease characteristics; and third, calculating road surface condition index. Among them, the most important is the second step.

Existing methods for automatically detecting pavement diseases include: 1. Edge detection methods, for example, Canny algorithm; 2. High-pass filtering, for example, wavelet transform using mother wavelet To segment the image with ordinary intensity (see [2]); 3. Color/gray feature extraction method, which is based on the abnormal color/gray feature of the diseased part of the road surface, where the color/ Grayscale features include HSV features, entropy features or moments of higher order features; 4, texture filtering, which uses a local binary pattern (local binary pattern, LBP) to extract feature regions (see [3]).

[1] Wang, Kelvin C P, and O. Smadi. "Automated Imaging Technologies for Pavement Distress Surveys." Transportation Research E-Circular (2011).

[2] Subirats, P., et al. "Automation of Pavement Surface Crack Detection using the Continuous Wavelet Transform." Image Processing IEEE International Conference on (2006): 3037-3040.

[3] Ding, Ying, et al. "A fuzzy background model for moving object detection." Computer-Aided Design and Computer Graphics, 2009. CAD/Graphics '09.11th IEEE International Conference on IEEE, 2009: 610-613.

It should be noted that the above description of the technical background is only for the purpose of facilitating a clear and complete description of the technical solutions of the present application, and is convenient for understanding by those skilled in the art. The above technical solutions are not considered to be well known to those skilled in the art simply because these aspects are set forth in the background section of this application.

Application content

In the above-mentioned conventional method for automatically detecting a road surface disease, some of the road surface images are processed using predetermined fixed parameters, and therefore, it is difficult to adapt to the requirement for dynamic detection of the road surface; and some are for dynamic road image images. One frame is used to set parameters to process the frame image, but this method is slower to process, so the timeliness of dynamic detection is poor.

The embodiment of the present application provides a method for detecting a road surface disease, a device thereof, and an electronic device, which detects a disease of a road surface according to a moving image obtained by imaging the road surface, according to a reference frame of a predetermined number of frames in the moving image. The region of interest of the image is subjected to filtering processing to determine the value of the filtering parameter, and the filtering parameter is used to filter the image of the reference frame and a predetermined number of frames thereafter to obtain a detection result of the disease on the road surface. Therefore, the value of the filter parameter can be updated in time according to the dynamic image, thereby adapting to the requirement for dynamic detection of the road surface, and determining the value of the filter parameter based on the region of interest of the reference frame, the calculation amount is small and the value is Appropriate, can improve the timeliness and accuracy of dynamic detection.

According to a first aspect of the embodiments of the present application, there is provided a device for detecting a road surface disease, which detects a disease of a road surface based on a dynamic image obtained by imaging a road surface, the detecting device comprising:

a region of interest determining unit for determining a region of interest in a reference frame image of the dynamic image, wherein in the dynamic image, an image of a predetermined number of frames is spaced between adjacent reference frame images ;

a filtering parameter determining unit that determines a first filtering parameter value according to a result of performing filtering processing on the region of interest;

a filtering unit that performs filtering processing on the reference frame image and the image of the predetermined number of frames after the reference frame image according to the first filter parameter value to obtain a detection result of a disease on a road surface.

According to a second aspect of embodiments of the present application, an electronic device is provided that is disposed in a vehicle and is capable of detecting a road And the electronic device has the detection device for the road surface disease according to the first aspect described above, and the electronic device further has:

a data input device for capturing a road surface on which the vehicle travels to obtain the dynamic image;

a positioning device for determining position information of the vehicle when each frame of the dynamic image is captured;

a data storage device for correspondingly storing each frame of the dynamic image, position information of the vehicle, and detection results of a road surface disease based on each frame of the dynamic image;

A display device for displaying the detection result corresponding to position information of the vehicle.

According to a third aspect of the embodiments of the present application, a method for detecting a road surface disease is provided, which detects a disease of a road surface according to a dynamic image obtained by imaging a road surface, and the detecting method includes:

Determining a region of interest in a reference frame image of the dynamic image, wherein in the dynamic image, an image of a predetermined number of frames is spaced between adjacent reference frame images;

Determining a first filter parameter value according to a result of performing filtering processing on the region of interest;

And filtering the reference frame image and the image of the predetermined number of frames after the reference frame image according to the first filter parameter value.

The beneficial effects of the embodiments of the present application are: according to the implementation of the present application, the requirement for dynamic detection of the disease on the road surface can be adapted, and the real-time and accuracy of the detection is improved.

Specific embodiments of the present application are disclosed in detail with reference to the following description and accompanying drawings, in which <RTIgt; It should be understood that the embodiments of the present application are not limited in scope. The embodiments of the present application include many variations, modifications, and equivalents within the scope of the appended claims.

Features described and/or illustrated with respect to one embodiment may be used in one or more other embodiments in the same or similar manner, in combination with, or in place of, features in other embodiments. .

It should be emphasized that the term "comprising" or "comprises" or "comprising" or "comprising" or "comprising" or "comprising" or "comprises"

DRAWINGS

The drawings are included to provide a further understanding of the embodiments of the present application, and are intended to illustrate the embodiments of the present application Obvious The drawings in the following description are only some of the embodiments of the present application, and those skilled in the art can obtain other drawings according to the drawings without any inventive labor. In the drawing:

Figure 1 is a schematic diagram of a composition of the detecting device of the first embodiment;

2 is a schematic diagram of a composition of a region of interest determining unit of the first embodiment;

3 is a schematic diagram of a composition of a filter parameter determining unit of the first embodiment;

4 is a schematic diagram of a composition of a filtering unit of the first embodiment;

Figure 5 is a schematic diagram showing the composition of the first processing unit of the first embodiment;

Figure 6 is a schematic diagram showing the workflow of the detecting device of the first embodiment;

7 is a schematic diagram of a composition of an electronic device according to Embodiment 2 of the present application;

8 is a schematic flow chart of a detecting method of the third embodiment;

9 is a schematic diagram of a method of determining a region of interest according to the third embodiment;

FIG. 10 is a schematic diagram of a method for determining a first filter parameter value according to Embodiment 3; FIG.

Fig. 11 is a schematic diagram showing a method of performing filtering processing in the third embodiment.

Fig. 12 is a schematic diagram showing a method of synthesizing a plurality of third filtering results in the third embodiment.

detailed description

The foregoing and other features of the present application will be apparent from the description, The specific embodiments of the present application are specifically disclosed in the specification and the drawings, which illustrate a part of the embodiments in which the principles of the present application may be employed, it being understood that the present application is not limited to the described embodiments, but instead The application includes all modifications, variations and equivalents falling within the scope of the appended claims. Various embodiments of the present application will be described below with reference to the accompanying drawings. These embodiments are merely exemplary and are not limiting of the application.

Example 1

Embodiment 1 of the present application provides a road surface disease detecting device that detects a disease on a road surface based on a moving image obtained by imaging a road surface.

1 is a schematic diagram of a composition of the detecting apparatus of the first embodiment. As shown in FIG. 1, the detecting apparatus 100 includes a region of interest determining unit 101, a filtering parameter determining unit 102, and a filtering unit 103.

The region of interest determining unit 101 is configured to determine a region of interest in the reference frame image of the dynamic image, wherein in the dynamic image, images of a predetermined number of frames may be spaced between adjacent reference frame images, For example, an image of a predetermined number of frames spaced between two adjacent reference frame images may be 50; the filtering parameter determining unit 102 determines a value of the first filtering parameter according to a result of performing filtering processing on the region of interest; The filtering unit 103 performs filtering processing on the reference frame image and the image of the predetermined number of frames after the reference frame image according to the first filtering parameter to obtain a detection result of a disease on the road surface.

With the embodiment, the value of the filter parameter can be updated in time according to the reference image of the dynamic image, thereby adapting to the requirement for dynamic detection of the road surface; and, compared with determining the value of the filter parameter for each frame of the image, the implementation The calculation amount of the example is small, and the real-time detection is improved; and, based on the region of interest, determining the value of the filter parameter can obtain a more appropriate value, thereby improving the accuracy of the detection.

In this embodiment, the moving image processed by the detecting device 100 may be a grayscale image, which may be directly obtained by the imaging device, or may be obtained by converting the color image, which is not used in this embodiment. limit.

In the present embodiment, the region of interest determined by the region of interest determining unit 101 may be an image region corresponding to a normal road surface in the reference image.

FIG. 2 is a schematic diagram of a composition of the region of interest determining unit 101 of the present embodiment. As shown in FIG. 2, the region of interest determining unit 101 may include a first filtering unit 201, a first determining unit 202, and a second determining unit 203. .

The first filtering unit 201 is configured to perform a first filtering process on the reference frame image to obtain a filtered reference frame image. The first determining unit 202 is configured to determine a first frequency with the highest frequency of the pixel intensity of the filtered reference frame image. a pixel intensity value; the second determining unit 203 is configured to set, in the filtered reference frame image, a region centered on the pixel having the first pixel intensity value, and determine an area in the reference frame image corresponding to the region as Area of interest.

In this embodiment, the first filtering process performed by the first filtering unit 201 on the reference image may be an average value filtering process. For example, the first filtering unit 201 may calculate a predetermined area around the center of the reference image. The average of the pixel intensities, wherein the predetermined area may be a square area of size w*w, which may be, for example, 64-128 pixels. After the average filtering process of the first filtering unit 201, the filtered reference frame image can be generated. Of course, in the embodiment, the predetermined area may have other shapes and sizes, and the first filtering unit 201 may also perform the first filtering process on the reference image by using other filtering methods, which is not limited in this embodiment. .

In the present embodiment, the first determination unit 202 may be filtered by the intensity of the first filtering unit 201 generates a reference pixel in the image frame count to determine the highest frequency of the first pixel intensity value I _max, e.g., The first determining unit 202 may draw a histogram of the intensities of the pixels in the filtered reference frame image, the horizontal axis of the histogram may represent the intensity of the pixel, and the vertical axis of the histogram may represent the frequency of occurrence of the intensity of the pixel, the histogram The intensity of the pixel corresponding to the peak of the graph is determined as the first pixel intensity value I _max . Of course, in this embodiment, the first determining unit 202 may also determine the first pixel intensity value with the highest frequency of occurrence in other manners.

In this embodiment, since most of the regions in each frame of the moving image correspond to a normal road surface, the first pixel intensity value I _{max having the} highest frequency of occurrence can reflect the pixel intensity of the image corresponding to the normal road surface. .

In this embodiment, the second determining unit 203 may set the first region in the filtered reference frame image centering on the pixel having the first pixel intensity value I _max , and the first region may also be, for example, the size w *w square area. And, the second determining unit 203 may determine the region in the reference frame image corresponding to the first region as the region of interest in the reference frame image, for example, the size of the region of interest and the position of the center point are respectively The size of the first area is the same as the position of the center point.

In this embodiment, the region of interest of the reference frame image may correspond to a normal road surface. Therefore, using the region of interest to determine the filtering parameters enables the filtering parameters to accurately reflect the characteristics of the normal road surface, thereby filtering the image. The image information corresponding to the normal road surface can be effectively filtered out during processing, and the image information corresponding to the disease of the road surface is retained in the filtered image.

FIG. 3 is a schematic diagram of a composition of the filtering parameter determining unit of the embodiment. As shown in FIG. 3, the filtering parameter determining unit 102 may include a second filtering unit 301 and a third determining unit 302.

The second filtering unit 301 may perform a second filtering process on the region of interest according to the plurality of candidate values to obtain a plurality of second filtering results corresponding to the plurality of candidate values. The third determining unit 302 may And determining, according to the plurality of second filtering results, the first filtering parameter value.

In the following description of the embodiment, the second filtering process may be a Gabor filtering process, and the first filtering parameter value may be a value of the spatial frequency λ used in the Gabor filtering process. Of course, the second filtering process may be other filtering processing manners, and the first filtering parameter value may be a value of a parameter corresponding to the filtering processing mode.

In this embodiment, the Gabor filtering process is a band pass filtering method, which can perform filtering processing according to the following formula (1):

Where I(ξ,η) represents the intensity of the pixel at the position (ξ,η) in the image to be filtered, and r(x,y) represents the pixel at the position (x,y) in the filtered image. The intensity, g(x, y), represents the Gabor convolution kernel, which is expressed as the following equation (2):

Where x'=x cosθ+y sin θ, y'=-x sin θ+y cosθ, σ=0.56λ, γ=0.5～1, λ is a spatial frequency, θ is a spatial orientation,

Is the phase offset, λ, θ, and

It is three filtering parameters in the Gabor filtering process, and θ can generally take any value from 0 to 180°.

Generally, any value of ±90 and ±180° can be taken.

In this embodiment, the second filtering unit 301 may perform Gabor filtering processing on the region of interest of the reference frame image according to the above formula (1), wherein the filtering parameter θ and

The value may be fixed, and λ may be assigned a plurality of candidate values, and Gabor filtering processing is performed once for each candidate value, thereby obtaining a plurality of second filtering results corresponding to the plurality of candidate values. Wherein, the plurality of candidate values may be gradually increased from small to large.

In this embodiment, the third determining unit 302 may determine the first filtering parameter value according to the plurality of second filtering results obtained by the second filtering unit 301. In this embodiment, the third determining unit 302 may determine, as the value of the filtering parameter λ, the candidate value corresponding to the second filtering result that meets the preset condition, that is, the first filtering parameter value, for example, the preset condition. It may be that the filtering result is empty or the like.

In the present application, the third determining unit 302 may determine the first filtering parameter value based on the following principle: when λ=λ1, the filtering process is responsive to the texture of the ordinary road surface in the image, and the filtering result is not empty due to the road surface texture. The gray level change is fine, λ1 can be smaller; when λ=λ2, the filtering process responds to the texture of the road surface disease in the image, and the filtering result is not empty, because the texture of the road surface disease is compared with the texture of the ordinary road surface, the gray The degree of transformation is more intense, so the value of λ2 can be larger; when the value of λ is larger than λ1 and smaller than λ2, the filtering process does not respond to the texture of the ordinary road surface in the image, but responds to the texture of the road surface disease in the image. Therefore, in the process of gradually increasing the candidate value given to λ from small to small, when the filtering process for the region of interest has just become unresponsive, that is, when the filtering result is changed from non-empty to empty, at this time, the λ is given. The candidate value is slightly larger than the above λ1 and smaller than the above λ2. Therefore, when the candidate value is given to λ, the filtering process does not respond to the texture of the normal road surface, but responds to the texture of the road surface disease. In this embodiment, the first filter parameter value determined by the filter parameter determining unit 102 may be used for the reference frame image and the reference frame image. The predetermined number of frame images are subjected to filtering processing, whereby image information corresponding to a normal road surface in the image can be effectively filtered out, and image information corresponding to the road surface disease is retained.

FIG. 4 is a schematic diagram of a composition of the filtering unit of the embodiment. As shown in FIG. 4, the filtering unit 103 may include a third filtering unit 401 and a first processing unit 402.

Wherein, for each of the reference frame image and the image of the predetermined number of frames after the reference frame image, the third filtering unit 401 may use a plurality of predetermined values and the first filter parameter value. And a plurality of filtering parameter groups respectively performing third filtering processing on each frame image to obtain a plurality of third filtering results corresponding to the plurality of filtering parameter groups; and the first processing unit 402 synthesizes the plurality of third filtering results deal with.

In this embodiment, the third filtering process performed by the third filtering unit 401 may be the same as the second filtering process. For example, the third filtering process and the second filtering process may both be Gabor filtering processes. Of course, the third filtering process and the second filtering process may also be other filtering processes.

In the third filtering process, the first filtering parameter value determined by the filtering parameter determining unit 102 and the plurality of predetermined values respectively constitute a plurality of filtering parameter groups, and each of the plurality of filtering parameter groups is used to perform image processing for each frame separately. The third filtering process obtains a corresponding third filtering result. For example, the third filtering unit 401 can take λ as the first filtering parameter value and make the parameter θ and

Is given a plurality of predetermined values, whereby λ is different from θ and

The value constitutes a plurality of filtering parameter groups, and the image is subjected to Gabor filtering processing using the plurality of filtering parameter groups to obtain a plurality of third filtering results corresponding to the plurality of filtering parameter groups.

In this embodiment, the first processing unit 402 may perform a synthesis process on the plurality of third filtering results obtained by the third filtering unit 401 to obtain a detection result of the disease on the road surface. The synthesis processing may be based on, for example, a root mean square (rms) of the pixel intensity. Of course, the embodiment is not limited thereto, and the synthesis processing may be other methods.

FIG. 5 is a schematic diagram of a composition of the first processing unit of the embodiment. As shown in FIG. 5, the first processing unit 402 includes a first calculating unit 501 and a first determining unit 502.

The first calculating unit 501 calculates a root mean square of the filtered intensity value of each pixel in each frame image according to the plurality of third filtering results; the first determining unit 502 is configured according to the filtered intensity value of each pixel. The relationship between the square root and the preset threshold is obtained as a filtered image of each frame of image.

In this embodiment, the first calculating unit 501 can calculate the root mean square of the filtered intensity value of each pixel by using the following formula (3):

Where r _i (x, y) is the intensity value of the pixel at the position (x, y) in the ith third filtering result, and I(x, y) is the filtered position (x, y) The root mean square of the intensity value of the pixel, thereby obtaining an image composed of I(x, y).

In this embodiment, the first determining unit 502 can compare I(x, y) with a preset threshold, and when I(x, y) is greater than a preset threshold, the pixel is deleted, and thus, by I(x) The image formed by y) is converted into a filtered image, in which the image information corresponding to the normal road surface is filtered out, and the image information corresponding to the disease of the road surface is retained.

In this embodiment, as shown in FIG. 1 , the road surface disease detecting apparatus 100 may further include a post-processing unit 104, which may use the image processing technology to obtain the filtered image obtained by the first processing unit 402. Optimization, for example, image blur and/or image expansion can be used to suppress blurring in the filtered image based on the vehicle's travel speed; linear crack detection is used to detect artificial cracks on the road, and from the filtered image The image information corresponding to the artificial crack is removed, and the artificial crack may be, for example, a gap between two different regions.

Next, the workflow of the detecting device of the present embodiment will be described.

Figure 6 is a schematic diagram showing the workflow of the detecting device of the embodiment, in Figure 6:

S601. Select a reference frame image from the dynamic image, where an initial frame of the dynamic image may be used as an initial reference frame image, and an image of a predetermined number of frames may be spaced between the subsequent reference frame image and the previous reference frame image. .

S602. The first filtering unit 201 may perform mean filtering on the reference frame image to obtain a filtered reference frame image.

S603. The first determining unit 202 may draw a histogram of the intensities of the pixels in the filtered reference frame image to determine a first pixel intensity value with the highest frequency of occurrence;

S604. The second determining unit 203 may traverse the filtered reference frame image, find a pixel having a first pixel intensity value, set a first region centering on the pixel, and set a reference frame image corresponding to the first region. The area in the area is determined as the area of interest;

S605. The second filtering unit 301 can assign a plurality of candidate values to λ in order from small to large, and is interested in Gabor filtering in the interesting area;

S606. The third determining unit 302 may assign a candidate value corresponding to the filtering result obtained in S605 to λ as the first filtering parameter value.

S607. The filtering unit 103 performs Gabor filtering on the dynamic image frame according to the first filtering parameter value.

S608. Determine whether the reference frame and the subsequent predetermined number of frame images are filtered. If the determination is no, the next frame image of the dynamic image is selected in S609, and the process returns to S607, and the filtering process is performed by the filtering unit 103. If yes, go to S610.

S610. It is judged whether or not the detection is stopped. If the determination in S610 is negative, the process returns to S601, and if the determination is YES, the detection flow is ended.

Example 2

The embodiment of the present application provides an electronic device that can be disposed in a vehicle for detecting and displaying a disease of a road surface, and the electronic device includes the device for detecting a road surface disease according to Embodiment 1.

FIG. 7 is a schematic diagram of a composition of an electronic device 700 according to an embodiment of the present application. As shown in FIG. 7, the electronic device 700 may include a data input device 701, a positioning device 702, a data storage device 703, a display device 704, and a road surface disease detecting device 705.

The data input device 701 is configured to capture a road surface on which the vehicle travels to obtain a dynamic image; the positioning device 702 is configured to determine position information of the vehicle when each frame of the moving image is captured; and the road surface disease detecting device 705 inputs the data according to the data. The moving image acquired by the device 701 detects the road surface disease; the data storage device 703 is configured to correspondingly store each frame of the moving image, the position information of the vehicle, and the detection result of the road surface disease based on each frame of the moving image; The display device 704 is for displaying a detection result corresponding to the position information of the vehicle.

In the present embodiment, the data input device 701 may be a camera, which may be disposed at the front, the rear, or the bottom of the vehicle for capturing the road surface on which the vehicle travels to obtain a dynamic image.

The positioning device 702 may be a Global Positioning System (GPS) module, which is capable of detecting position information of the vehicle and synchronizing the position information with each frame of the captured moving image, thereby enabling The position information corresponding to each frame of the dynamic image is determined. In addition, the positioning device 702 can also detect driving information of the vehicle, such as driving speed and/or driving direction.

In the present embodiment, the road surface disease detecting means 705 can read the data input from the data storage means 703. The motion image acquired by the device 701 is entered to detect the road surface disease. For the description of the detecting device 705 for the road surface disease, reference may be made to the description of the detecting device 100 for the road surface disease in the first embodiment, and the description thereof will not be repeated here.

In this embodiment, the data storage device 703 may be a directly-accessible physical storage unit. Of course, the embodiment is not limited thereto, and the data storage device 703 may be other types of storage units.

In the present embodiment, the data storage device 703 can store the data of the moving image, and output the data of the moving image to the road surface disease detecting device 705, and the road surface disease detecting device 705 can output the detection result to the data storage. The device 703 is and/or output to the display device 704.

In this embodiment, the data storage device 703 can store each frame of the moving image, the position information of the vehicle, and the detection result of the road surface disease based on each frame of the moving image, for example, as shown in the following Table 1. The data structure described to store data.

Table I

Frame number

Dynamic image data

location information

Additional code

Test results

The extra code may record vehicle speed information, mileage information, and/or lane information, etc. The detection result may be data of the filtered image as described in Embodiment 1, or may indicate whether the road surface is diseased or diseased. Level data, etc.

In the present embodiment, the data storage device 703 may have a buffer zone, and the road surface disease detecting device 705 may use the buffer zone during the detection process, thereby reducing the data load of the road surface disease detecting device 705.

In the present embodiment, the data in the data storage device 703 can also be directly output to the display device 704, thereby displaying the data stored in the data storage device 703 in the display device 704.

In the present embodiment, the display device 704 may be, for example, a display screen capable of displaying a detection result corresponding to the position information of the vehicle. For example, the display device 704 may display an electronic map on which the road on which the vehicle travels is displayed. And marking the road based on the detection result of the disease on the road surface, for example, using a color to mark the road in which the disease exists, and different disease levels, corresponding to different colors, and the like.

According to the electronic device of the embodiment, it is possible to accurately and timely detect the disease of the road surface and display it, and the application range is wide.

Example 3

The embodiment of the present application further provides a method for detecting a road surface disease, which detects a disease on a road surface based on a moving image obtained by imaging the road surface, and corresponds to the detecting device of the first embodiment.

FIG. 8 is a schematic flowchart of the detection method of the embodiment. As shown in FIG. 8, the detection method may include:

S801. Determine a region of interest in a reference frame image of a dynamic image, wherein, in the dynamic image, an image of a predetermined number of frames is spaced between adjacent reference frame images;

S802. Determine a first filtering parameter value according to a result of performing filtering processing on the region of interest;

S803. Perform filtering processing on the reference frame image and the image of the predetermined number of frames subsequent to the reference frame image according to the first filtering parameter value.

FIG. 9 is a schematic flowchart of a method for determining a region of interest in S801 of the embodiment. As shown in FIG. 9, the method may include:

S901: Perform a first filtering process on the reference frame image to obtain a filtered reference frame image.

S902. Determine a first pixel intensity value that has the highest frequency of occurrence in the pixel intensity of the filtered reference frame image.

S903. Set an area centered on the pixel having the first pixel intensity value in the filtered reference frame image, and determine an area in the reference frame image corresponding to the area as the area of interest.

FIG. 10 is a schematic diagram of a method for determining a first filter parameter value of S802 according to the embodiment, the method includes:

S1001: Perform a second filtering process on the region of interest according to the plurality of candidate values, to obtain a plurality of second filtering results corresponding to the plurality of candidate values;

S1002. Determine the first filter parameter value according to the multiple second filtering results.

FIG. 11 is a schematic diagram of a method for performing filtering processing in S803 of the embodiment, the method includes:

S1101: using, for each of the reference frame image and the image of the predetermined number of frames after the reference frame image, using a plurality of filters composed of a plurality of predetermined values and the first filter parameter value. a parameter group, respectively performing a third filtering process on each frame image to obtain a plurality of third filtering results corresponding to the plurality of filtering parameter groups;

S1102: Perform synthesis processing on the plurality of third filtering results.

FIG. 12 is a schematic diagram of a method for synthesizing a plurality of third filtering results by S1102 of the embodiment, the method comprising:

S1201: Calculate, according to the plurality of third filtering results, a root mean square of the filtered intensity value of each pixel in each frame image; and

S1202: Obtain a filtered image of the image of each frame according to a relationship between a root mean square of the filtered intensity value of each pixel and a preset threshold.

As shown in FIG. 8, the detecting method may further include:

S804, performing post-processing on the filtered image.

For the description of the steps in the present embodiment, reference may be made to the description of each unit of the detecting device 100 for road surface disease in Embodiment 1, and the description of the present embodiment is not repeated.

The embodiment of the present application further provides a computer readable program, wherein when the program is executed in an information processing apparatus or a user equipment, the program causes the computer to execute the embodiment 3 in the information processing apparatus or the user equipment. Method for detecting road surface diseases.

The embodiment of the present application further provides a storage medium storing a computer readable program, wherein the computer readable program causes the computer to execute the method for detecting a road surface disease according to Embodiment 3 in an information processing device or a user equipment.

The embodiment of the present application further provides a computer readable program, wherein the program causes a computer to execute the road surface described in Embodiment 3 in the information processing device or the base station when the program is executed in an information processing device or a base station Method of detecting diseases.

The embodiment of the present application further provides a storage medium storing a computer readable program, wherein the computer readable program causes the computer to execute the method for detecting a road surface disease according to Embodiment 3 in an information processing device or a base station.

The apparatus and method above in the present application may be implemented by hardware, or may be implemented by hardware in combination with software. The present application relates to a computer readable program that, when executed by a logic component, enables the logic component to implement the apparatus or components described above, or to implement the various methods described above Or steps. Logic Components such as field programmable logic components, microprocessors, processors used in computers, and the like. The application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, or the like.

The present invention has been described in connection with the specific embodiments thereof, but it is to be understood that the description is intended to be illustrative and not restrictive. Various modifications and alterations of the present application are possible in light of the spirit and scope of the invention, which are also within the scope of the present application.

Claims

A device for detecting a road surface disease, which detects a disease of a road surface based on a moving image obtained by imaging a road surface, wherein the detecting device comprises:

a region of interest determining unit for determining a region of interest in a reference frame image of the dynamic image, wherein in the dynamic image, an image of a predetermined number of frames is spaced between adjacent reference frame images ;

a filtering parameter determining unit that determines a first filtering parameter value according to a result of performing filtering processing on the region of interest;

a filtering unit that performs filtering processing on the reference frame image and the image of the predetermined number of frames after the reference frame image according to the first filter parameter value to obtain a detection result of a disease on a road surface.
The apparatus for detecting a road surface disease according to claim 1, wherein the region of interest determining unit comprises:

a first filtering unit, configured to perform a first filtering process on the reference frame image to obtain a filtered reference frame image;

a first determining unit, configured to determine a first pixel intensity value that has the highest frequency of occurrence in the pixel intensity of the filtered reference frame image;

a second determining unit, configured to set, in the filtered reference frame image, an area centered on a pixel having the first pixel intensity value, and determine an area in the reference frame image corresponding to the area as Area of interest.
The apparatus for detecting a road surface disease according to claim 1, wherein the filtering parameter determining unit comprises:

a second filtering unit, configured to perform a second filtering process on the region of interest according to the plurality of candidate values, to obtain a plurality of second filtering results corresponding to the plurality of candidate values;

a third determining unit that determines the first filtering parameter value according to the plurality of second filtering results.
The apparatus for detecting a road surface disease according to claim 3, wherein:

The third determining unit determines, as the first filtering parameter value, a candidate value corresponding to the second filtering result that meets a preset condition.
The apparatus for detecting a road surface disease according to claim 1, wherein the filtering unit comprises:

a third filtering unit that is for the reference frame image and the predetermined number after the reference frame image Each frame image in the image of the frame is subjected to a third filtering process for each frame image using a plurality of filter parameter sets composed of a plurality of predetermined values and the first filter parameter value, to obtain a solution Determining a plurality of third filtering results corresponding to the plurality of filtering parameter groups;

a first processing unit that performs a synthesis process on the plurality of third filtering results.
The apparatus for detecting a road surface disease according to claim 5, wherein the first processing unit comprises:

a first calculating unit, configured to calculate a root mean square of the filtered intensity value of each pixel in each frame image according to the plurality of third filtering results;

And a first determining unit, configured to obtain a filtered image of the image of each frame according to a relationship between a root mean square of the filtered intensity value of each pixel and a preset threshold.
An electronic device that is disposed in a vehicle capable of detecting a disease of a road surface and displaying the same, the electronic device having the apparatus for detecting a road surface disease according to any one of claims 1 to 6, and wherein the electronic device further have:

a data input device for capturing a road surface on which the vehicle travels to obtain the dynamic image;

a positioning device for determining position information of the vehicle when each frame of the dynamic image is captured;

a data storage device for correspondingly storing each frame of the dynamic image, position information of the vehicle, and detection results of a road surface disease based on each frame of the dynamic image;

A display device for displaying the detection result corresponding to position information of the vehicle.
The electronic device of claim 7 wherein:

The display device displays an electronic map, and marks the road corresponding to different detection results on the electronic map.
A method for detecting a road surface disease, which detects a disease of a road surface based on a moving image obtained by imaging a road surface, wherein the detecting method comprises:

Determining a region of interest in a reference frame image of the dynamic image, wherein in the dynamic image, an image of a predetermined number of frames is spaced between adjacent reference frame images;

Determining a first filter parameter value according to a result of performing filtering processing on the region of interest;

And filtering the reference frame image and the image of the predetermined number of frames after the reference frame image according to the first filter parameter value.
A method of detecting a road surface disease according to claim 9, wherein said region of interest is determined The domain includes:

Performing a first filtering process on the reference frame image to obtain a filtered reference frame image;

Determining a first pixel intensity value having the highest frequency of occurrence in the pixel intensity of the filtered reference frame image;

A region centered on the pixel having the first pixel intensity value in the filtered reference frame image is set, and an area in the reference frame image corresponding to the region is determined as the region of interest.
The method for detecting a road surface disease according to claim 9, wherein determining the first filter parameter value comprises:

Performing a second filtering process on the region of interest according to the plurality of candidate values, to obtain a plurality of second filtering results corresponding to the plurality of candidate values;

Determining the first filter parameter value according to the plurality of second filtering results.
The method for detecting a road surface disease according to claim 11, wherein determining the first filter parameter value according to the plurality of second filtering results comprises:

The candidate value corresponding to the second filtering result that satisfies the preset condition is determined as the first filtering parameter value.
The method for detecting a road surface disease according to claim 9, wherein the filtering processing of the reference frame image and the image of the predetermined number of frames subsequent to the reference frame image according to the first filtering parameter comprises :

And using, for each of the reference frame image and the image of the predetermined number of frames after the reference frame image, a plurality of filter parameter sets composed of a plurality of predetermined values and the first filter parameter value Performing a third filtering process on each of the frame images to obtain a plurality of third filtering results corresponding to the plurality of filtering parameter groups;

Performing a synthesis process on the plurality of third filtering results.
The method for detecting a road surface disease according to claim 13, wherein the synthesizing the plurality of third filtering results comprises:

Calculating a root mean square of the filtered intensity value of each pixel in each frame image according to the plurality of third filtering results;

And obtaining a filtered image of the image of each frame according to a relationship between a root mean square of the filtered intensity value of each pixel and a preset threshold.