Tunnel portal dark ice monitoring and early warning method, early warning system and electronic equipment

Abstract

The invention relates to the field of tunnel portal road monitoring, in particular to a tunnel portal dark ice monitoring and early warning method and system and electronic device.The early warning system comprises a data acquisition module, a data preprocessing module, a detection module, an analysis module and an early warning module.The pavement condition of a tunnel road is acquired through a hyperspectral camera; and the spatial information and the spectral information are combined to realize real-time monitoring and early warning of the dark ice at the tunnel portal, so that the safety of the road traffic accident high-incidence section at the tunnel portal is greatly improved.

Description

Technical Field

[0001] The invention belongs to the field of tunnel entrance road monitoring, and in particular relates to a tunnel entrance dark ice monitoring and early warning method, an early warning system and electronic equipment. Background Art

[0002] As a key component of the transportation network, tunnels carry important social and economic significance. Due to the characteristics of closed, restrictive and narrow space, once an accident occurs, the complexity and difficulty of rescue and evacuation are far greater than that of open roads, so its safe operation is crucial to ensure traffic safety. However, in the cold winter, tunnels are often the hardest hit areas for traffic accidents. Due to the large temperature difference between the inside and outside of the tunnel and the relatively low solar radiation inside the tunnel, the ground water vapor at the entrance and exit of the tunnel is easily condensed into ice, forming "dark ice". Dark ice is a colorless and transparent deadly threat. It is almost the same color as the road surface and difficult to be detected by the driver. If the vehicle encounters dark ice obstacles while driving at high speed, it will lose control of the vehicle. In addition, dark ice will also affect the braking of the vehicle, making the driver unable to react normally and causing the vehicle to lose control. Therefore, dark ice will bring great threats to driving and easily cause traffic accidents. Dark ice at the tunnel entrance is an important issue affecting tunnel safety. Therefore, further research on the early warning of dark ice at the tunnel entrance has important practical significance. Hidden ice also appears in the following three scenarios: Toll stations. Cars passing through toll stations stop and go frequently. The car temperature plus the tire temperature make it easy for hidden ice to form after snowfall. Bridge decks and culverts. The temperature is relatively high during the day after snowfall. In addition, the bridge or culvert is ventilated, so a thin layer of hidden ice forms on the bridge at night. On slopes, due to the long exposure to sunlight on the slopes, the snow melts easily, resulting in a thin layer of ice after sunset. The current hidden ice warning method uses the same method to monitor hidden ice warnings in various scenarios, and cannot provide the most appropriate judgment information and road conditions for hidden ice information at the tunnel entrance for moving vehicles. Summary of the invention

[0003] In order to overcome the above problems or at least partially solve the above problems, the present invention provides a tunnel entrance dark ice monitoring and early warning method, an early warning system and an electronic device, so as to effectively overcome the inaccuracy in the current tunnel entrance dark ice early warning and effectively improve the accuracy of data extraction and the early warning effect.

[0004] In a first aspect, the present invention provides a tunnel entrance hidden ice monitoring and early warning method, comprising the following steps:

[0005] 1. Collect hyperspectral images of dark ice roads and safe roads at tunnel entrances to establish an image database;

[0006] 2. Extract the spectral reflectance of different roads in the image database and perform preprocessing to establish a spectral database; the reflectance in the hyperspectral image is Where θ represents a pixel point in the hyperspectral image, I m (θ) is the original hyperspectral image, I d (θ) is the dark background image, I w (θ) is the standard whiteboard image; the fitting curve y=a o +a1x+a2x 2 +...+a m x m As a baseline, the baseline was subtracted from the original spectral curve to obtain the corrected spectral curve;

[0007] 3. Collect hyperspectral images of the tunnel entrance road in real time and perform dimensionality reduction operations on the image information, as follows:

[0008] H M×N×j For each sample hyperspectral data, M, N represents the length of a single band image, j represents the total number of bands, and X i =(X1,X2…,Xj), representing different band images, remove the mean of all bands and get a new set of features:

[0009]

[0010] Find its covariance matrix:

[0011]

[0012] Among them, each covariance is calculated according to the formula:

[0013]

[0014] Eigenvalues ​​and eigenvectors of C:

[0015] Cu-λu=0

[0016] Select the largest first k eigenvalues ​​and their corresponding k eigenvectors, use the k eigenvectors as new projection axes, and obtain the k-dimensional features after dimensionality reduction. For each sample, the new features are:

[0017]

[0018] 4. Use the target detection neural network to monitor the abnormal road surface data in real time based on the road surface image information; extract the abnormal road surface data and compare it with the spectral information in the spectral database, as follows:

[0019] C 1…j is the continuous spectrum data of the detected abnormal area, S i For the spectral data of different road conditions in the database, C is calculated respectively. 1…j With each S 1-iThe distance to the curve, the road condition closest to it is the predicted road condition, and the distance formula used is the Euclidean distance, which is as follows:

[0020]

[0021] Among them, i represents different road conditions and j represents the number of bands.

[0022] D i Sort from small to large, then the smallest D i The corresponding pavement type is the result obtained from the final analysis;

[0023] 5. Send a warning message when hidden ice is detected on the road.

[0024] In a second aspect, the present invention provides a tunnel entrance dark ice monitoring and early warning system, comprising:

[0025] The data acquisition module is used to take hyperspectral images of the dark ice road and the safe road at the tunnel entrance, respectively, to establish an image database with positive and negative sample images, to extract the spectral reflectance of the road surface in different areas in the spectral dimension, and to pre-process the spectral data to establish a spectral database;

[0026] A data preprocessing module is used to reduce the dimension of the image dimension of the dark ice road at the tunnel entrance collected in real time;

[0027] The detection module uses a target detection neural network to detect the road surface condition in real time and transmits the detected abnormal road surface data to the analysis module, which further determines whether the road surface is covered with hidden ice.

[0028] The analysis module extracts the spectral information of the detected abnormal road area and compares it with the spectral information in the database, optimizes the output results of the processing module network, and transmits the analyzed results to the early warning module;

[0029] The early warning module is used to receive the analysis results transmitted by the analysis module, and send early warning information when the analysis module detects the presence of hidden ice on the road surface.

[0030] Furthermore, the data acquisition module is composed of a hyperspectral camera and a light source mounted above the tunnel. The preprocessing method of the spectral curve in step 1 is specifically as follows:

[0031] The reflectance in the hyperspectral image is extracted as an evaluation index for the classification of different substances. The specific formula is as follows:

[0032]

[0033] Where θ represents a pixel point in the hyperspectral image data, I m(θ) is the original hyperspectral image, I d (θ) is the dark background image, I w (θ) is the standard whiteboard image;

[0034] A baseline correction method based on polynomial fitting is used to construct a set of curves to fit the spectral curve with background noise:

[0035] y=a o +a1x+a2x 2 +…+a m x m

[0036] Select a series of non-peak points (x1, x2, ... x i ), then the sum of the squares of the distances from each known point on the spectral curve to this curve is:

[0037]

[0038] For a i Taking partial derivatives we get:

[0039]

[0040] Using matrix representation, we can get:

[0041]

[0042] Let XA=Y, then A=X -1 Y

[0043] We get y = a o +a1x+a2x 2 +...+a m x m is the desired fitting curve;

[0044] The obtained fitting curve is used as the baseline, and the baseline is subtracted from the original spectrum curve to obtain the corrected spectrum curve.

[0045] Furthermore, the hyperspectral camera is equipped with a light source for supplementary lighting, and the spectral range of the light source is between 400-1000 nanometers. The camera and the light source are mounted above the tunnel entrance to perform real-time monitoring of the road surface at the tunnel entrance.

[0046] Furthermore, the dimensionality reduction operation is as follows:

[0047] Assume there are M samples, H M×N×j For each sample hyperspectral data, M, N represents the length of a single band image, j represents the total number of bands, and X i =(X1,X2…,X j), representing different band images. First, remove the mean of all bands and get a new set of features:

[0048]

[0049] Find its covariance matrix:

[0050]

[0051] Where each covariance is calculated as follows:

[0052]

[0053] Find the eigenvalue and eigenvector of C according to the following formula:

[0054] Cu-λu=0

[0055] Select the largest first k eigenvalues ​​and their corresponding k eigenvectors, and use these k eigenvectors as new projection axes to obtain new k-dimensional features after dimensionality reduction. For each sample, the new features are calculated by the following formula:

[0056]

[0057] Furthermore, the network is an improved target detection model of yolov8, which is used to monitor the road surface conditions in real time. When an abnormality is detected, the location information of the abnormal area is automatically detected and the location information is output to the analysis module.

[0058] Furthermore, the analysis module classifies the spectral information of the output position and analyzes the condition of the road surface, as follows:

[0059] C 1…j is the continuous spectrum data of the detected abnormal area, S i For the spectral data of different road conditions in the database, C is calculated respectively. 1…j With each S 1-i The distance to the curve, the road condition closest to it is the predicted road condition, and the distance formula used is the Euclidean distance, which is as follows:

[0060]

[0061] Among them, i represents different road conditions and j represents the number of bands.

[0062] D i Sort from small to large, then the smallest D i The corresponding pavement type is the result obtained from the final analysis.

[0063] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for monitoring and early warning of hidden ice at a tunnel entrance as described in the first aspect above are implemented.

[0064] In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium having computer instructions stored thereon. When the computer instructions are executed by a computer, the steps of the tunnel entrance dark ice monitoring and early warning method as described in the first aspect above are implemented.

[0065] The tunnel entrance dark ice monitoring and early warning method proposed in the present invention utilizes a hyperspectral camera to collect tunnel road pavement conditions, combines spatial information with spectral information, and realizes real-time monitoring and early warning of tunnel entrance dark ice, which has a high improvement effect on the safety of high-incidence sections of tunnel entrance roads with traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 This is a flow chart of the tunnel entrance hidden ice monitoring and early warning method.

[0067] Figure 2 This is a schematic diagram of the method of carrying a hyperspectral camera in the tunnel entrance dark ice monitoring and early warning method;

[0068] The reference numerals in the drawings are: 1-carrying device, 2-hyperspectral camera, 3-light source, 4-tunnel asphalt pavement, 5-dark ice.

[0069] Figure 3 Schematic diagram of the improved network structure for feature extraction of the model. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described in combination with the drawings in the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the embodiment in the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the embodiment of the present invention. In order to solve the defects of the above-mentioned prior art.

[0071] In the face of the problem that there is no distinction between road icing and tunnel entrance dark ice warning, which seriously affects the warning effect, the embodiment of the present invention effectively combines the hyperspectral camera to collect the tunnel road surface conditions and the joint spatial information and spectral information, and optimizes the corresponding model and method, so as to effectively carry out tunnel entrance dark ice warning, which can effectively overcome the current inaccuracy in tunnel entrance dark ice warning, thereby effectively improving the warning effect. The method of the present invention will be specifically described and introduced through embodiments below.

[0072] Figure 1 A schematic flow chart of a method for monitoring and early warning of dark ice at a tunnel entrance based on hyperspectral information provided by an embodiment of the present invention includes the following steps:

[0073] S1, build image database and spectrum database;

[0074] The data acquisition module takes 1,000 positive and negative sample images of roads covered with dark ice at the tunnel entrance and safe roads respectively, and establishes an image database. The data set is divided according to the ratio of training number: test number: verification number of 8:1:1, which is used for the subsequent detection module to detect road anomalies. For the spectral dimension, the spectral reflectance of the road surface in different areas is extracted, and the spectral data is preprocessed to establish a spectral database;

[0075] The data acquisition module consists of a hyperspectral camera and a light source mounted above the tunnel. The preprocessing method for the spectral curve is as follows:

[0076] S1.1, extract reflectance;

[0077] Since the DN value does not have a quantitative index in practical applications, the reflectance in the hyperspectral image is extracted as an evaluation index for the classification of different substances. The specific formula is as follows:

[0078]

[0079] Where θ represents a pixel point in the hyperspectral image data, I m (θ) is the original hyperspectral image, I d (θ) is the dark background image, I w (θ) is the standard whiteboard image.

[0080] S1.2, polynomial fitting;

[0081] In order to eliminate the noise interference caused by the light source and background in the collected dark ice spectrum data, a baseline correction method based on polynomial fitting is adopted. First, a set of curves is constructed to fit the spectrum curve with background noise:

[0082] y=a o +a1x+a2x 2 +...+am x m

[0083] Select a series of non-peak points (x1, x2, ... x i ), then the sum of the squares of the distances from each known point on the spectral curve to this curve is:

[0084]

[0085] For a i Taking partial derivatives we get:

[0086]

[0087] Using matrix representation, we can get:

[0088]

[0089] Let XA=Y, then A=X -1 Y

[0090] We get y = a o +a1x+a2x 2 +...+a m x m is the desired fitting curve.

[0091] S1.3, baseline correction;

[0092] The obtained fitting curve is used as the baseline, and the baseline is subtracted from the original spectrum curve to obtain the corrected spectrum curve.

[0093] S2, collecting tunnel entrance road images;

[0094] The data acquisition module collects the hyperspectral image of the road surface condition of the tunnel entrance in real time, and transmits the data to the data preprocessing module in real time;

[0095] like Figure 2 As shown, the hyperspectral camera is equipped with a light source for supplementary lighting, and the spectral range of the light source is between 400 and 1000 nanometers. The hyperspectral camera and the light source are mounted above the tunnel entrance to perform real-time monitoring of the road surface at the tunnel entrance.

[0096] S3, preprocessing the image information;

[0097] The preprocessing module receives the image dimension information transmitted by the data acquisition module, which is used by the detection module to locate the abnormal road surface area. Considering the processing capacity of the equipment, the preprocessing module performs a dimensionality reduction operation on the image information; the dimensionality reduction method is as follows:

[0098] Assume there are M samples, H M×N×jFor each sample hyperspectral data, M, N represents the length of a single band image, j represents the total number of bands, and X i =(X1,X2…,X j ), representing different band images. First, remove the mean of all bands and get a new set of features:

[0099]

[0100] Find its covariance matrix:

[0101]

[0102] Where each covariance is calculated as follows:

[0103]

[0104] Find the eigenvalue and eigenvector of C according to the following formula:

[0105] Cu-λu=0

[0106] Select the largest first k eigenvalues ​​and their corresponding k eigenvectors, and use these k eigenvectors as new projection axes to obtain new k-dimensional features after dimensionality reduction. For each sample, the new features can be calculated by the following formula:

[0107]

[0108] S4, building a target detection neural network to detect the road condition in real time, and transmitting the detected abnormal road data to the analysis module, which further determines whether the road surface is caused by hidden ice;

[0109] The network built is an improved target detection model of yolov8, which is used to monitor the road surface conditions in real time. When an abnormality is detected, the location information of the abnormal area is automatically detected and output to the analysis module. In order to meet the lightweight deployment requirements of the road monitoring system, the feature extraction backbone network of the model adopts MobileNetv1. The improved network structure is as follows Figure 3 shown.

[0110] The analysis module uses the KNN method to classify the spectral information of the output position and analyze the road condition, as follows:

[0111] C is the continuous spectrum data of the detected abnormal area, S i For the spectral data of different road conditions in the database, C and each S are calculated separately. i The distance to the curve, the road condition closest to it is the predicted road condition, and the distance formula used is the Euclidean distance, which is as follows:

[0112]

[0113] Among them, i represents different road conditions and j represents the number of bands.

[0114] D i Sort from small to large, then the smallest D i The corresponding pavement type is the result obtained from the final analysis.

[0115] S5, extracting the spectral information of the detected abnormal road surface area, and comparing it with the spectral information in the database, optimizing the output result of the processing module network, and transmitting the analyzed result to the early warning module;

[0116] S6. Receive the analysis result transmitted by the analysis module. When the analysis module detects the presence of hidden ice on the road surface, the warning information is sent to the relevant departments or the vehicle control system through the warning module, and displayed on the road traffic facilities such as the roadside variable information board, so as to realize the real-time warning of icy road conditions.

[0117] Based on the same concept, an embodiment of the present invention provides a tunnel entrance dark ice monitoring and early warning system according to the above embodiments, and the system is used to implement tunnel entrance dark ice monitoring and early warning in the above embodiments.

[0118] Therefore, the description and definition in the tunnel entrance dark ice monitoring and early warning method in the above embodiment can be used for understanding each execution module in the embodiment of the present invention. For details, please refer to the above embodiment and will not be repeated here.

[0119] It includes: a data acquisition module, which is used to take hyperspectral images of dark ice roads and safe roads at tunnel entrances respectively, establish an image database with positive and negative sample images, extract the spectral reflectance of road surfaces in different areas in the spectral dimension, and pre-process the spectral data to establish a spectral database;

[0120] A data preprocessing module is used to reduce the dimension of the image dimension of the dark ice road at the tunnel entrance collected in real time;

[0121] The detection module uses a target detection neural network to detect the road surface condition in real time and transmits the detected abnormal road surface data to the analysis module, which further determines whether the road surface is covered with hidden ice.

[0122] The analysis module extracts the spectral information of the detected abnormal road area and compares it with the spectral information in the database, optimizes the output results of the processing module network, and transmits the analyzed results to the early warning module;

[0123] The early warning module is used to receive the analysis results transmitted by the analysis module, and send early warning information when the analysis module detects the presence of hidden ice on the road surface.

[0124] As another aspect of an embodiment of the present invention, this embodiment provides an electronic device according to the above embodiments, and the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the tunnel entrance dark ice monitoring and early warning method as described in the above embodiments are implemented.

[0125] An embodiment of the present invention also provides a non-transitory computer-readable storage medium according to the above embodiments, on which computer instructions are stored. When the computer instructions are executed by a computer, the steps of the tunnel entrance dark ice monitoring and early warning method as described in the above embodiments are implemented.

[0126] It is understandable that the embodiments of the apparatus, electronic device, and storage medium described above are merely illustrative, and the units described as separate components may or may not be physically separated, and may be located in one place, or may be distributed on different network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0127] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, etc., including a number of instructions to enable a computer device (such as a personal computer, a server, or a network device, etc.) to execute the methods described in the above method embodiments or some parts of the method embodiments.

[0128] In addition, it should be understood by those skilled in the art that, in the application documents of the embodiments of the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0129] In the description of the embodiment of the present invention, a large number of specific details are described. However, it should be understood that the embodiment of the embodiment of the present invention can be practiced without these specific details. In some examples, known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this specification. Similarly, it should be understood that in order to streamline the disclosure of the embodiment of the present invention and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the embodiment of the present invention, the various features of the embodiment of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof.

[0130] This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as the claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of an embodiment of the invention.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, rather than to limit them. Although the embodiments of the present invention have been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the embodiments of the present invention.

Claims

1. A tunnel entrance hidden ice monitoring and early warning method, characterized in that: The following steps are involved:

1. Collect hyperspectral images of dark ice roads and safe roads at tunnel entrances to establish an image database; 2. Extract the spectral reflectance of different roads in the image database and perform preprocessing to establish a spectral database; the reflectance in the hyperspectral image is Where θ represents a pixel point in the hyperspectral image, I m (θ) is the original hyperspectral image, I d (θ) is the dark background image, I w (θ) is the standard whiteboard image; the fitting curve y=a o +a1x+a2x 2 +...+a m x m As a baseline, the baseline was subtracted from the original spectral curve to obtain the corrected spectral curve; 3. Collect hyperspectral images of the tunnel entrance road in real time and perform dimensionality reduction operations on the image information, as follows: H M×N×j For each sample hyperspectral data, M, N represents the length of a single band image, j represents the total number of bands, and X i =(X1,X2…,Xj), representing different band images, remove the mean of all bands and get a new set of features: Find its covariance matrix: Among them, each covariance is calculated according to the formula: Eigenvalues ​​and eigenvectors of C: Cu-λu=0 Select the largest first k eigenvalues ​​and their corresponding k eigenvectors, use the k eigenvectors as new projection axes, and obtain the k-dimensional features after dimensionality reduction. For each sample, the new features are:

4. Use the target detection neural network to monitor the abnormal road surface data in real time based on the road surface image information; extract the abnormal road surface data and compare it with the spectral information in the spectral database, as follows: C 1…j is the continuous spectrum data of the detected abnormal area, S i For the spectral data of different road conditions in the database, C is calculated respectively. 1…j With each S 1-i The distance to the curve, the road condition closest to it is the predicted road condition, and the distance formula used is the Euclidean distance, which is as follows: Among them, i represents different road conditions and j represents the number of bands. D i Sort from small to large, then the smallest D i The corresponding pavement type is the result obtained from the final analysis; 5. When hidden ice is detected on the road surface, an early warning message will be sent to the relevant departments or vehicles.

2. A tunnel entrance hidden ice monitoring and early warning system, characterized in that: include: The data acquisition module is used to take hyperspectral images of the dark ice road and the safe road at the tunnel entrance, respectively, to establish an image database with positive and negative sample images, to extract the spectral reflectance of the road surface in different areas in the spectral dimension, and to pre-process the spectral data to establish a spectral database; A data preprocessing module is used to reduce the dimension of the image dimension of the dark ice road at the tunnel entrance collected in real time; The detection module uses a target detection neural network to detect the road surface condition in real time and transmits the detected abnormal road surface data to the analysis module, which further determines whether the road surface is covered with hidden ice. The analysis module extracts the spectral information of the detected abnormal road area and compares it with the spectral information in the database, optimizes the output results of the processing module network, and transmits the analyzed results to the early warning module; The early warning module is used to receive the analysis results transmitted by the analysis module, and send early warning information when the analysis module detects the presence of hidden ice on the road surface.

3. The tunnel entrance hidden ice monitoring and early warning system according to claim 2, characterized in that: The data acquisition module is composed of a hyperspectral camera and a light source mounted above the tunnel.

4. The tunnel entrance hidden ice monitoring and early warning system according to claim 2, characterized in that: The specific preprocessing method for the spectral curve is: Taking reflectivity as an evaluation index for classifying different materials, the specific formula is as follows: Where θ represents a pixel point in the hyperspectral image data, I m (θ) is the original hyperspectral image, I d (θ) is the dark background image, I w (θ) is the standard whiteboard image; A baseline correction method based on polynomial fitting is used to construct a set of curves to fit the spectral curve with background noise: y=a o +a1x+a2x 2 +...+a m x m Select a series of non-peak points (x1, x2, ... x i ), then the sum of the squares of the distances from each known point on the spectral curve to this curve is: For a i Taking partial derivatives we get: Using matrix representation, we can get: Let XA=Y, then A=X -1 Y We get y = a o +a1x+a2x 2 +...+a m x m is the desired fitting curve; The obtained fitting curve is used as the baseline, and the baseline is subtracted from the original spectrum curve to obtain the corrected spectrum curve.

5. The tunnel entrance hidden ice monitoring and early warning system according to claim 2, characterized in that: The hyperspectral camera is equipped with a light source for supplementary lighting. The spectral range of the light source is between 400-1000 nanometers. The camera and the light source are mounted above the tunnel entrance to perform real-time monitoring of the road surface at the tunnel entrance.

6. The tunnel entrance hidden ice monitoring and early warning system according to claim 2, characterized in that: The dimensionality reduction operation is as follows: Assume there are M samples, H M×N×j For each sample hyperspectral data, M, N represents the length of a single band image, j represents the total number of bands, and X i =(X1,X2...,Xj), representing different band images; first remove the mean of all bands and get a new set of features: Find its covariance matrix: Where each covariance is calculated as follows: Find the eigenvalue and eigenvector of C according to the following formula: Cu-λu=0 Select the largest first k eigenvalues ​​and their corresponding k eigenvectors, and use these k eigenvectors as new projection axes to obtain new k-dimensional features after dimensionality reduction; for each sample, the new features are calculated by the following formula:

7. The tunnel entrance hidden ice monitoring and early warning system according to claim 2, characterized in that: The network is a target detection model of yolov8, which is used to monitor the road surface conditions in real time. When an abnormality is detected, the location information of the abnormal area is automatically detected and the location information is output to the analysis module.

8. The tunnel entrance hidden ice monitoring and early warning system according to claim 2, characterized in that: The analysis module classifies the spectral information of the output position as follows: C 1…j is the continuous spectrum data of the detected abnormal area, S i For the spectral data of different road conditions in the database, C is calculated respectively. 1…j With each S 1-i The distance to the curve, the road condition closest to it is the predicted road condition, and the distance formula used is the Euclidean distance, which is as follows: Among them, i represents different road conditions, and j represents the number of bands; D i Sort from small to large, then the smallest D i The corresponding pavement type is the result obtained from the final analysis.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the tunnel entrance hidden ice monitoring and early warning method as claimed in claim 1 are implemented.

10. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed by a computer, the steps of the tunnel entrance hidden ice monitoring and early warning method as claimed in claim 1 are implemented.

Images