Icing risk assessment method applied to bridge floor and road surface and related equipment

Abstract

The embodiment of the invention belongs to the technical field of artificial intelligence, and relates to an icing risk assessment method and related equipment applied to a bridge floor and a road surface, and the method comprises the steps: obtaining a remote sensing image related to a target geographic position; performing land surface temperature inversion operation according to the remote sensing image to obtain land surface temperature information related to the target geographic position; performing Logistic regression analysis operation on the surface temperature information according to a Logistic function to obtain a risk prediction result; and outputting the risk prediction result. According to the method, the meteorological factors influencing the icing of the bridge surface and the road surface of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the Yunnan section of the

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an icing risk assessment method and related equipment applied to bridge decks and road surfaces. Background Art

[0002] With the rapid development of my country's social economy and science and technology, transportation has become an important lifeline for national economic production and people's social life. Meteorological disasters on highways, such as low temperature and icing on the road surface, low visibility, heavy precipitation, squall lines and other traffic meteorological disasters, have a serious impact on the normal operation, safe driving and facility maintenance of highways, often leading to a large number of traffic accidents and instability in social life.

[0003] Among many traffic meteorological disasters, low temperature and icing of roads in winter can easily cause major traffic accidents and pose a serious threat to traffic safety. For example, in winter, under low temperature and near-freezing weather conditions, due to the difference in temperature of different underlying surfaces during the same period, ordinary roads have high surface temperatures and have not yet frozen, while special sections such as elevated bridges have low surface temperatures but have already frozen. At this time, when motor vehicles pass through high-risk sections that have frozen first from normal roads, it is very easy to cause traffic accidents.

[0004] However, the applicant found that existing technologies are unable to accurately monitor, fine-tune early warnings, and prevent and mitigate meteorological disasters on highways. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose an icing risk assessment method and related equipment for bridge decks and road surfaces, so as to solve the problem that the existing technology is unable to accurately monitor, fine-tune early warning and prevent and reduce meteorological disasters on highways.

[0006] In order to solve the above technical problems, the present application provides an icing risk assessment method for bridge decks and road surfaces, which adopts the following technical solutions:

[0007] Acquire remote sensing images related to the target geographic location;

[0008] Performing a surface temperature inversion operation according to the remote sensing image to obtain surface temperature information related to the target geographical location;

[0009] Performing a Logistic regression analysis on the surface temperature information according to a Logistic function to obtain a risk prediction result;

[0010] The risk prediction result is output.

[0011] Furthermore, the step of performing a surface temperature inversion operation according to the remote sensing image to obtain surface temperature information related to the target geographical location specifically includes the following steps:

[0012] Performing a preprocessing operation on the remote sensing image to obtain a preprocessed image;

[0013] Extracting water and land pixels and a normalized vegetation index according to the preprocessed image, and calculating the emissivity according to the water and land pixels and the normalized vegetation index;

[0014] Calculating the brightness temperature of the preprocessed image according to the simplified Plank equation;

[0015] Extracting atmospheric water vapor content according to the preprocessed image, and calculating transmittance according to the atmospheric water vapor content;

[0016] The emissivity, the brightness temperature, and the transmittance are calculated according to a split-window algorithm to obtain the ground surface temperature information.

[0017] Furthermore, the step of performing a preprocessing operation on the remote sensing image to obtain a preprocessed image specifically includes the following steps:

[0018] Bow-tie processing is performed on the remote sensing image to obtain the pre-processed image.

[0019] Furthermore, the step of performing a preprocessing operation on the remote sensing image to obtain a preprocessed image specifically includes the following steps:

[0020] A geometric correction operation is performed on the remote sensing image to obtain the preprocessed image.

[0021] Furthermore, the step of performing a preprocessing operation on the remote sensing image to obtain a preprocessed image specifically includes the following steps:

[0022] A projection conversion operation is performed on the remote sensing image to obtain the preprocessed image.

[0023] Furthermore, the expression of the Logistic function is:

[0024]

[0025] Wherein, a and b represent least squares fitting parameters, and x represents the surface temperature information.

[0026] In order to solve the above technical problems, the embodiment of the present application further provides an icing risk assessment device for bridge decks and road surfaces, which adopts the following technical solution:

[0027] A remote sensing image acquisition module, used to acquire remote sensing images related to the target geographical location;

[0028] A land surface temperature inversion module, used to perform a land surface temperature inversion operation according to the remote sensing image to obtain land surface temperature information related to the target geographical location;

[0029] A regression analysis module, used to perform a Logistic regression analysis operation on the surface temperature information according to a Logistic function to obtain a risk prediction result;

[0030] The result output module is used to output the risk prediction result.

[0031] Furthermore, the surface temperature inversion module includes:

[0032] A preprocessing submodule, used for performing a preprocessing operation on the remote sensing image to obtain a preprocessed image;

[0033] An emissivity calculation submodule, used for extracting water and land pixels and a normalized vegetation index according to the preprocessed image, and calculating the emissivity according to the water and land pixels and the normalized vegetation index;

[0034] A brightness temperature calculation submodule, used to calculate the brightness temperature of the preprocessed image according to the simplified Plank equation;

[0035] a transmittance calculation submodule, used for extracting atmospheric water vapor content according to the preprocessed image, and calculating transmittance according to the atmospheric water vapor content;

[0036] The surface temperature inversion submodule is used to calculate the emissivity, the brightness temperature and the transmittance according to the split-window algorithm to obtain the surface temperature information.

[0037] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0038] The invention comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the icing risk assessment method applied to bridge decks and road surfaces as described above are implemented.

[0039] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0040] The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the icing risk assessment method applied to bridge decks and road surfaces as described above are implemented.

[0041] The present application provides an icing risk assessment method for bridge decks and roads, including: obtaining remote sensing images related to the target geographic location; performing surface temperature inversion operations based on the remote sensing images to obtain surface temperature information related to the target geographic location; performing Logistic regression analysis operations on the surface temperature information according to the Logistic function to obtain risk prediction results; and outputting the risk prediction results. Compared with the prior art, the present application conducts a comprehensive quantitative analysis and evaluation of meteorological factors that affect the icing of bridge decks and roads in the Yunnan section of the Chongqing-Kunming Expressway based on the Logistic regression analysis method, and on this basis, constructs bridge deck and road icing risk level warning models respectively, providing an accurate reference for safe travel on winter highways. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0044] Figure 2 is a flowchart of an implementation of an icing risk assessment method for bridge decks and road surfaces provided in an embodiment of the present application;

[0045] Figure 3 is a schematic diagram of the Bow-tie effect provided in an embodiment of the present application;

[0046] Figure 4 is a flow chart of the LST (Land Surface Temperature) inversion algorithm provided in an embodiment of the present application;

[0047] Figure 5 It is a structural schematic diagram of an icing risk assessment device for bridge decks and road surfaces provided in an embodiment of the present application;

[0048] Figure 6 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0050] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0051] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0052] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0053] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0054] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0055] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .

[0056] It should be noted that the icing risk assessment method applied to bridge decks and road surfaces provided in the embodiments of the present application is generally executed by a server / terminal device, and accordingly, the icing risk assessment device applied to bridge decks and road surfaces is generally arranged in a server / terminal device.

[0057] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0058] Continue to refer Figure 2 , shows a flow chart of an embodiment of an icing risk assessment method for bridge decks and roads according to the present application. The icing risk assessment method for bridge decks and roads comprises: step S201, step S202, step S203, step S204, step S205, step S206 and step S207.

[0059] In step S201, a remote sensing image related to a target geographical location is acquired.

[0060] In the embodiment of the present application, the target geographic location refers to the address where the icing risk assessment for the bridge deck and the road surface is to be performed. The present application takes the "Chongqing-Kunming Expressway" as an example for the following description.

[0061] In the embodiment of the present application, the remote sensing data refers to the bridge deck and road surface of the Chongqing-Kunming Expressway from January 2011 to February 2017. There were 21 ice formations on the bridge deck and road surface, and the ice formation dates were 2011.1.17, 2011.12.24, 2012.12.25, 2012.12.31, 2013.1.5, 2013.12.15, 2013.12.17, 2014.1.21, 2014.2.19, 2014.12.12, 2014.12.17, 2015.1.11, 2015.10.10, 2015.12.16, 2015.12.29, 2016.1.23, 2016.2.1, 2016.2.2, 2016.2.24, 2016.2.26, 2017.2.12, therefore, 21 MODIS remote sensing images of the above dates were used to extract the bridge deck and road surface temperatures, and the data came from the Remote Sensing Department of the Yunnan Provincial Climate Center.

[0062] In the embodiment of the present application, the ambient temperature refers to the temperature at the corresponding time of the meteorological station closest to each sample point, which is taken at each of the 72 bridges along the Yunnan section of the Chongqing-Kunming Expressway and the road surface adjacent to the bridges.

[0063] In step S202, a land surface temperature inversion operation is performed based on the remote sensing image to obtain land surface temperature information related to the target geographical location.

[0064] In the embodiment of the present application, the ground temperature extraction is sequentially subjected to the steps of sensor calibration, bow-tie processing, geometric correction, projection conversion, image cropping, and ground temperature inversion to extract the ground temperatures of the 21 freezing events at the selected sample points on the 72 bridge decks and nearby roads of the Yunnan section of the Chongqing-Kunming Expressway.

[0065] In step S203, a Logistic regression analysis operation is performed on the surface temperature information according to the Logistic function to obtain a risk prediction result.

[0066] In the embodiments of the present application, Logistic regression is mainly used to solve the problem of binary variables. Since the value range of the Logistic function is between 0 and 1, it is often used in meteorology to establish risk level or probability forecast models.

[0067] The general expression of the logistic function y=f(x) is:

[0068]

[0069] It is nonlinear and has an S-shaped distribution characteristic. It can be linearly converted to:

[0070]

[0071] It can be regarded as the dependent variable Linear regression model with independent variable x. By fitting a and b parameters with a certain amount of samples Yi and Xi using the least squares method, the equation of the Logistic function y = f(x) can be obtained. The Logistic curve has 3 key points, and the first and second order derivatives of the Logistic function are solved respectively. Let y' = 0, and get x = -a / b, which represents the base point where the curve changes fastest (y reacts most sensitively with changes in x); let y" = 0, and get x = (-a±1.317) / b, which represents the two inflection points of the curve change process (the starting point and saturation point of the curve change).

[0072] In the present application embodiment, SPSS (Statistical Product and Service Solutions), "Statistical Product and Service Solutions" software is a general term for a series of software products and related services for statistical analysis operations, data mining, predictive analysis and decision support tasks launched by IBM, and has versions such as Windows and Mac OS X. The software can be applied to various fields of natural sciences, technical sciences, and social sciences. The basic functions of SPSS include data management, statistical analysis, chart analysis, output management, etc. The SPSS statistical analysis process includes several major categories such as descriptive statistics, mean comparison, general linear model, correlation analysis, regression analysis, log-linear model, cluster analysis, data simplification, survival analysis, time series analysis, and multiple responses. Each category is divided into several statistical processes, such as linear regression analysis, curve estimation, logistic regression, Probit regression, weighted estimation, two-stage least squares method, nonlinear regression, etc., and each process allows users to select different methods and parameters. SPSS also has a special drawing system that can draw various graphics according to data. This application uses SPSS19.0 software to perform logistic regression analysis on the air temperature, bridge deck temperature, and road surface temperature data series of the Yunnan section of the Chongqing-Kunming Expressway.

[0073] In step S204, the risk prediction result is output.

[0074] In an embodiment of the present application, a method for assessing the risk of icing on bridge decks and roads is provided, including: obtaining remote sensing images related to the target geographic location; performing surface temperature inversion operations based on the remote sensing images to obtain surface temperature information related to the target geographic location; performing Logistic regression analysis operations on the surface temperature information based on the Logistic function to obtain risk prediction results; and outputting risk prediction results. Compared with the prior art, the present application conducts a comprehensive quantitative analysis and evaluation of meteorological factors affecting the icing of bridge decks and roads on the Yunnan section of the Chongqing-Kunming Expressway based on the Logistic regression analysis method, and on this basis, respectively constructs bridge deck and road icing risk level warning models, providing an accurate reference for safe travel on highways in winter.

[0075] In some optional implementations of the embodiments of the present application, the above step of performing a surface temperature inversion operation based on a remote sensing image to obtain surface temperature information related to a target geographical location specifically includes the following steps:

[0076] Performing preprocessing operations on the remote sensing image to obtain a preprocessed image;

[0077] Extracting water and land pixels and normalized vegetation index according to the preprocessed image, and calculating the emissivity according to the water and land pixels and the normalized vegetation index;

[0078] Calculate the brightness temperature of the preprocessed image according to the simplified Plank equation;

[0079] Extract atmospheric water vapor content according to the preprocessed image, and calculate the transmittance according to the atmospheric water vapor content;

[0080] The emissivity, brightness temperature and transmittance are calculated according to the split-window algorithm to obtain the surface temperature information.

[0081] In the embodiment of the present application, the preprocessing operation may be sensor calibration and correction, wherein:

[0082] Sensor calibration: The "gain" and "drift" of the sensor, the differences between the various detection elements of the sensor, and the "shot noise" and "banding" caused by the errors in the instrument system are all system radiation errors. System radiation correction is mainly carried out for these system radiation errors, including the processing of "gain" and "drift", and the correction of "shot noise" and "banding". The former is also called sensor calibration. Sensor calibration is the process of converting the digital quantization value (DN) of the image into physical quantities such as radiation brightness or reflectivity or surface temperature. Among them, the reflectivity is divided into the apparent reflectivity of the outer layer of the atmosphere and the actual reflectivity of the surface. The latter belongs to the category of atmospheric correction. Sometimes atmospheric correction is also included in the sensor calibration. In general, the method of sensor calibration is to obtain the calibration gain coefficient and offset from the header file and calibration file, and then convert the DN (Digital Number) value of the remote sensing image into the radiation value received by the sensor according to these calibration coefficients.

[0083] Geometric correction: eliminates the geometric deformation of remote sensing images and adds geographic information to them. The geometric correction of MODIS data refers to the process of correcting the geometric distortion of images caused by the combined influence of the geometric characteristics of the MODIS detector's field of view of balloon observation, the curvature of the earth's surface, terrain factors, and the jitter of the detector during movement.

[0084] In the present application embodiment, there are usually two kinds of geometric correction methods for MODIS L1B level data, the first one uses the Georeference MODIS tool integrated in ENVI, and uses the MOD03 geographic location information carried in the MODIS02 data file to perform geometric correction, and the process of its correction is to assign the longitude and latitude coordinates of each pixel in MOD03 to the corresponding pixel in the MOD02 image, and define its projection type and reference surface and other information. The operation object of this tool is plastic data, and reflectivity or radiance image can be directly obtained after operation, which is convenient for further processing and analysis, and is more suitable for quantitative remote sensing processing. The second method utilizes MRTSwath (MODIS Swath Reprojection Tool) processing software for processing, and this software is a special processing software developed by NASA for MODIS data. This software operation obtains SI value image, which is not conducive to further processing application, but this tool has a faster processing speed and is suitable for fast batch processing data. The core of both tools is to carry out projection matching based on the onboard data table.

[0085] In the embodiment of the present application, after obtaining the preprocessed image, the preprocessed image can be subjected to an image cropping operation. Specifically, image cropping refers to the process of obtaining a remote sensing image of a smaller range of the study area from an original large-scale full-scene image, including regular range cropping and irregular range cropping. Regular cropping includes rectangular images. Irregular cropping includes remote sensing images of irregular polygonal ranges.

[0086] In the embodiment of the present application, a surface temperature inversion algorithm suitable for MODIS remote sensing data is proposed by analyzing and improving the existing methods ( Figure 4 ). This algorithm contains three main parameters: the brightness temperature of the thermal infrared band, the atmospheric transmittance and the surface emissivity, among which the surface emissivity is the most critical parameter. For the brightness temperature, channels 31 and 32 in the thermal infrared band are selected for calculation using the simplified Plank equation. Taking advantage of the fact that the near-infrared channel data of MODIS is very sensitive to the atmospheric water vapor content, a method for inverting the water vapor content in the MODIS remote sensing data of the same scene is proposed, and then the atmospheric transmittance of each pixel is estimated. For the most critical parameter, emissivity, for the 1km resolution band of the MODIS thermal infrared band, the pixels can basically divide the ground objects into three categories, namely water bodies, vegetation and bare soil. The normalized vegetation index (NDVI) is calculated using bands 1 and 2 in the MODIS remote sensing data, and then the vegetation coverage is obtained. The surface emissivity is calculated according to the emissivity estimation method, and finally the surface temperature is inverted using the split window algorithm, where:

[0087] Split Window Algorithm: The main principle of the split window algorithm is to invert the surface temperature through the brightness temperature of two adjacent thermal infrared bands based on the thermal radiation transfer equation. Due to the influence of the atmosphere and the complexity of the surface structure, different split window algorithms are formed by different calculations of its parameters.

[0088] Estimation of atmospheric transmittance: Atmospheric transmittance is the ratio of the energy of surface radiation and reflection penetrating the atmosphere to reach the sensor to the surface radiation energy and reflection energy. Studies have found that water vapor in the atmosphere is the main factor affecting atmospheric transmittance, especially in the thermal infrared band, the effect of atmospheric water vapor on thermal radiation is more significant, so the atmospheric water vapor content is a very important parameter in the inversion of surface temperature. The usual practice is to simulate the relationship between atmospheric transmittance and atmospheric water vapor content through atmospheric model software such as MODTRAN, 6S and LOWTRAN. Since real-time atmospheric profile data is very limited, the accuracy of this simulation result is also limited. Directly inverting the atmospheric water vapor content from MODIS images and further calculating the atmospheric transmittance can greatly improve the accuracy of the parameters.

[0089] The MODIS near-infrared channel is used to invert the atmospheric water vapor content. The ratio method of water vapor absorption channels (channels 17, 18, and 19) and atmospheric window channels (channels 2 and 5) is selected as the inversion method. The basis of the inversion method is to use the reflected solar radiation to detect the absorption of radiation by water vapor.

[0090] Surface emissivity: The emissivity is a fixed value in the sea surface temperature inversion, which makes the sea surface temperature inversion simple. However, since the surface emissivity is affected by many factors such as surface structure, water content, temperature, wavelength of surface radiation, and observation angle, it is difficult to accurately estimate it. Many studies have found that the emissivity of different surfaces in the 8-13m spectrum range is between 0.90 and 0.99. Although the surface structure and morphology vary greatly in space, for MODIS data with a resolution of 1km, the surface can be divided into three categories: vegetation, bare soil, and water bodies, and then the emissivity of different vegetation coverage types can be estimated separately.

[0091] In some optional implementations of the embodiments of the present application, the above-mentioned step of performing a preprocessing operation on the remote sensing image to obtain a preprocessed image specifically includes the following steps:

[0092] Bow-tie processing is performed on the remote sensing image to obtain a preprocessed image.

[0093] In the present application embodiment, the pre-processing operation may also include Bow-tie processing, wherein the Bow-tie effect is also known as the "bow tie" effect, the "double eyelid" effect or the "bow" effect, which is mainly caused by the imaging characteristics of the detector. The MODIS detector adopts a passive swing scanning method of "multiple and scan", which scans in a direction perpendicular to the track, and its transverse scanning angle is ± 55 °. The width of the scanning strip is 10 pixels, 20 pixels, and 40 pixels, respectively, and its corresponding spatial resolution is 1km, 500m, and 250m, respectively. The field of view of the MODIS detector to earth observation is affected by some factors, such as: the curvature of the earth's surface, the ups and downs of the terrain, the geometric characteristics, and the jitter in the detector movement, so in fact, the actual span of a scanning strip in the scanning direction is 2330km. For MODIS1km resolution images, along the track direction, the longitudinal width of the scanning strip is 10km at the subsatellite point. After each scan, the detector moves 10km along the track, and the forward area is a scanning strip. As the scanning angle increases, the width of the scanning strip increases towards the edge. When the image edge increases to 20 km, the misalignment between the scanning strips is the most serious. There is a 10km repeated scanning area at the edge of two adjacent scanning strips, and 50% of the scanning data is information from the same area on the ground. This effect is called the Bow-tie effect. Figure 3 shown.

[0094] In the embodiment of the present application, the Bow-tie effect mainly manifests itself in two phenomena on the image: one is the overlapping phenomenon of edge pixels, and the closer to the edge, the more serious the overlapping phenomenon; the second is the compression distortion along the satellite scanning direction.

[0095] In some optional implementations of the embodiments of the present application, the above-mentioned step of performing a preprocessing operation on the remote sensing image to obtain a preprocessed image specifically includes the following steps:

[0096] Perform geometric correction operations on remote sensing images to obtain preprocessed images.

[0097] In the embodiment of the present application, the pre-processing operation can also include a geometric correction operation. The MODIS data itself carries detailed longitude and latitude band information, which is the longitude and latitude information of the corresponding pixel in the 1km resolution MODIS data, and is stored in the form of a band. The ENVI software can use the built-in geographic information in the MODIS data to perform geometric correction on the image, and there is no need to select the control points on the ground, which shortens the time of correction and is more accurate than the method of selecting ground control points. It should be noted that when selecting parameters (pixels Between Lat / LonValues), it should be treated differently according to the different resolutions. The channel with a resolution of 250m takes 4, the channel with a resolution of 500m takes 2, and the channel with a resolution of 1km takes 1. In order to facilitate the subsequent processing of the last derived data, the projection method selected is the longitude and latitude projection.

[0098] The basic principle of this geometric correction is that each pixel in the image corresponds to a coordinate. However, the size of the built-in latitude and longitude data is not equal to the size of the image data, resulting in the inability of the built-in geographic coordinates to correspond to the image pixels one by one. For example, the size of the latitude and longitude data corresponding to an image with a resolution of 1km (1354*1020) is 271*204, while the size of the latitude and longitude data corresponding to an image with a resolution of 500m (2708*2040) and 250m (5416*8120) is 677*610. Therefore, the latitude and longitude data or image data must be resampled during correction to make them consistent in size.

[0099] In the embodiment of the present application, the resampling method can be: cubic convolution interpolation method; bilinear interpolation method; nearest neighbor interpolation method. None of the three methods is very perfect, and each has its own advantages and disadvantages. Among them, the cubic convolution method can obtain a higher quality image, but the amount of data to be processed is relatively large, the processing speed is not fast, and the efficiency is relatively low. The bilinear interpolation method improves the phenomenon of discontinuous brightness in the image, but it is based on the principle of pixel averaging, which will make the boundaries of objects in the image blurred. The principle of the nearest neighbor method is relatively simple, which can effectively maintain the original pixel value, and the processing speed is also relatively fast, but the accuracy is not high, and the "sawtooth" effect is easy to produce in the image. Since the present application wants to retain as much original information of the image as possible and achieve a certain processing speed, the bilinear interpolation method is selected for resampling.

[0100] In the embodiment of the present application, the remote sensing image is geometrically corrected to match the actual geographical location.

[0101] In some optional implementations of the embodiments of the present application, the above-mentioned step of performing a preprocessing operation on the remote sensing image to obtain a preprocessed image specifically includes the following steps:

[0102] Perform projection transformation operation on the remote sensing image to obtain a preprocessed image.

[0103] In the embodiment of the present application, the preprocessing operation may further include a projection conversion operation, specifically, converting the remote sensing image into a unified projection coordinate system, specifically, converting the MODIS original positive projection into a UTM projection.

[0104] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0105] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0106] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0107] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0108] Further references Figure 5 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of an icing risk assessment device for bridge decks and road surfaces, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0109] like Figure 5 As shown, the icing risk assessment device 200 applied to bridge decks and road surfaces in the embodiment of the present application includes:

[0110] A remote sensing image acquisition module 210 is used to acquire a remote sensing image related to a target geographic location;

[0111] The land surface temperature inversion module 220 is used to perform a land surface temperature inversion operation based on the remote sensing image to obtain land surface temperature information related to the target geographical location;

[0112] A regression analysis module 230 is used to perform a Logistic regression analysis operation on the surface temperature information according to a Logistic function to obtain a risk prediction result;

[0113] The result output module 240 is used to output the risk prediction results.

[0114] In the embodiment of the present application, an icing risk assessment device 200 for bridge decks and roads is provided, including: a remote sensing image acquisition module 210, used to acquire remote sensing images related to the target geographical location; a surface temperature inversion module 220, used to perform surface temperature inversion operations based on remote sensing images to obtain surface temperature information related to the target geographical location; a regression analysis module 230, used to perform Logistic regression analysis operations on the surface temperature information according to the Logistic function to obtain risk prediction results; a result output module 240, used to output risk prediction results. Compared with the prior art, the present application conducts a comprehensive quantitative analysis and evaluation of meteorological factors affecting the icing of bridge decks and roads in the Yunnan section of the Chongqing-Kunming Expressway based on the Logistic regression analysis method, and on this basis, respectively constructs bridge deck and road icing risk level warning models, providing an accurate reference for safe travel on winter highways.

[0115] In some optional implementations of the embodiments of the present application, the above-mentioned surface temperature inversion module further includes:

[0116] The preprocessing submodule is used to perform preprocessing operations on the remote sensing image to obtain a preprocessed image;

[0117] The emissivity calculation submodule is used to extract water and land pixels and normalized vegetation index according to the preprocessed image, and calculate the emissivity according to the water and land pixels and the normalized vegetation index;

[0118] A brightness temperature calculation submodule is used to calculate the brightness temperature of the preprocessed image according to the simplified Plank equation;

[0119] The transmittance calculation submodule is used to extract the atmospheric water vapor content according to the preprocessed image and calculate the transmittance according to the atmospheric water vapor content;

[0120] The surface temperature inversion submodule is used to calculate the emissivity, brightness temperature and transmittance according to the split-window algorithm to obtain the surface temperature information.

[0121] To solve the above technical problems, the present application also provides a computer device. Figure 6 , Figure 6 This is a basic structural block diagram of a computer device according to an embodiment of the present application.

[0122] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 300 having components 310-330, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0123] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0124] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 310 can be an internal storage unit of the computer device 300, such as a hard disk or memory of the computer device 300. In other embodiments, the memory 310 can also be an external storage device of the computer device 300, such as a plug-in hard disk equipped on the computer device 300, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Of course, the memory 310 can also include both the internal storage unit of the computer device 300 and its external storage device. In the embodiment of the present application, the memory 310 is generally used to store an operating system and various application software installed on the computer device 300, such as computer-readable instructions for a bridge deck and road icing risk assessment method. In addition, the memory 310 can also be used to temporarily store various data that have been output or are to be output.

[0125] The processor 320 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 320 is generally used to control the overall operation of the computer device 300. In the embodiment of the present application, the processor 320 is used to run the computer-readable instructions or process data stored in the memory 310, such as running the computer-readable instructions of the icing risk assessment method applied to the bridge deck and the road surface.

[0126] The network interface 330 may include a wireless network interface or a wired network interface. The network interface 330 is generally used to establish a communication connection between the computer device 300 and other electronic devices.

[0127] The computer equipment provided in this application conducts a comprehensive quantitative analysis and evaluation of the meteorological factors that affect the icing of the bridge deck and road surface in the Yunnan section of the Chongqing-Kunming Expressway based on the Logistic regression analysis method, and on this basis, constructs warning models for the risk level of icing of the bridge deck and road surface, respectively, to provide an accurate reference for safe travel on highways in winter.

[0128] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned icing risk assessment method applied to bridge decks and road surfaces.

[0129] The computer-readable storage medium provided in this application conducts a comprehensive quantitative analysis and evaluation of the meteorological factors that affect the icing of the bridge deck and road surface in the Yunnan section of the Chongqing-Kunming Expressway based on the Logistic regression analysis method, and on this basis, constructs a bridge deck and road surface icing risk level warning model respectively, providing an accurate reference basis for safe travel on highways in winter.

[0130] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0131] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for assessing icing risk on bridge decks and roads, characterized in that: The steps include: Acquire remote sensing images related to the target geographic location; Performing a surface temperature inversion operation according to the remote sensing image to obtain surface temperature information related to the target geographical location; Performing a Logistic regression analysis on the surface temperature information according to a Logistic function to obtain a risk prediction result; The risk prediction result is output.

2. The icing risk assessment method for bridge decks and roads according to claim 1 is characterized in that: The step of performing a surface temperature inversion operation according to the remote sensing image to obtain surface temperature information related to the target geographical location specifically includes the following steps: Performing a preprocessing operation on the remote sensing image to obtain a preprocessed image; Extracting water and land pixels and a normalized vegetation index according to the preprocessed image, and calculating the emissivity according to the water and land pixels and the normalized vegetation index; Calculating the brightness temperature of the preprocessed image according to the simplified Plank equation; Extracting atmospheric water vapor content according to the preprocessed image, and calculating transmittance according to the atmospheric water vapor content; The emissivity, the brightness temperature, and the transmittance are calculated according to a split-window algorithm to obtain the ground surface temperature information.

3. The icing risk assessment method for bridge decks and roads according to claim 2 is characterized in that: The step of performing a preprocessing operation on the remote sensing image to obtain a preprocessed image specifically comprises the following steps: Bow-tie processing is performed on the remote sensing image to obtain the pre-processed image.

4. The icing risk assessment method for bridge decks and road surfaces according to claim 1, characterized in that: The step of performing a preprocessing operation on the remote sensing image to obtain a preprocessed image specifically comprises the following steps: A geometric correction operation is performed on the remote sensing image to obtain the preprocessed image.

5. The icing risk assessment method for bridge decks and road surfaces according to claim 1, characterized in that: The step of performing a preprocessing operation on the remote sensing image to obtain a preprocessed image specifically comprises the following steps: A projection conversion operation is performed on the remote sensing image to obtain the preprocessed image.

6. The icing risk assessment method for bridge decks and road surfaces according to claim 1, characterized in that: The expression of the Logistic function is: Wherein, a and b represent least squares fitting parameters, and x represents the surface temperature information.

7. An icing risk assessment device for bridge decks and roads, characterized in that: include: A remote sensing image acquisition module, used to acquire remote sensing images related to the target geographical location; A land surface temperature inversion module, used to perform a land surface temperature inversion operation according to the remote sensing image to obtain land surface temperature information related to the target geographical location; A regression analysis module, used to perform a Logistic regression analysis operation on the surface temperature information according to a Logistic function to obtain a risk prediction result; The result output module is used to output the risk prediction result.

8. The icing risk assessment device for bridge decks and roads according to claim 7, characterized in that: The surface temperature inversion module includes: A preprocessing submodule, used for performing a preprocessing operation on the remote sensing image to obtain a preprocessed image; An emissivity calculation submodule, used for extracting water and land pixels and a normalized vegetation index according to the preprocessed image, and calculating the emissivity according to the water and land pixels and the normalized vegetation index; A brightness temperature calculation submodule, used to calculate the brightness temperature of the preprocessed image according to the simplified Plank equation; a transmittance calculation submodule, used for extracting atmospheric water vapor content according to the preprocessed image, and calculating transmittance according to the atmospheric water vapor content; The surface temperature inversion submodule is used to calculate the emissivity, the brightness temperature and the transmittance according to the split-window algorithm to obtain the surface temperature information.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the icing risk assessment method applied to bridge decks and road surfaces as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the icing risk assessment method for bridge decks and road surfaces as described in any one of claims 1 to 6.

Images