A method and device for assessing risk sources of floating objects around railways

Abstract

The present invention relates to the technical field of railway perimeter risk source assessment, and particularly to a railway perimeter floating object risk source assessment method and device. The method comprises obtaining a hyperspectral remote sensing image to be assessed; identifying the railway perimeter floating object risk source based on the hyperspectral remote sensing image to be assessed, and obtaining an identification result; determining first information based on the identification result, the first information including the distance between the floating object risk source to be assessed and a railway safety clearance; dividing the railway perimeter risk area based on the railway safety clearance, and obtaining the divided risk area; obtaining second information, the second information including the ambient wind speed corresponding to the floating object risk source to be assessed; and calculating the probability of the floating object risk source invading the divided risk area based on the first and second information, and obtaining an assessment result. The present invention accurately assesses the risk level of the floating object risk source and can effectively guide on-site hidden danger remediation.

Description

Technical Field

[0001] The present invention relates to the technical field of railway perimeter risk source assessment, and in particular to a railway perimeter floating object risk source assessment method and device. Background Art

[0002] During strong winds, lightweight floating objects such as billboards, banners, plastic sheds, plastic sheeting, and dust screens along the railway perimeter, as well as hard floating objects such as color-coated steel plates, color-coated steel roofs, and color-coated steel sheds, can be blown into the railway safety clearance. In minor cases, these objects can snag the contact line, damage railway equipment, and cause train delays; in more serious cases, they can collide with high-speed trains, endangering operational safety. These various floating objects along the railway perimeter pose a significant safety hazard to safe railway operations.

[0003] Currently, limited research has been conducted domestically and internationally on the prevention and control of floating debris within railway perimeters. This research focuses on drone-based image recognition of floating debris risk sources and image-based detection, identification, and early warning of intruding floating debris. Currently, there is no quantitative assessment method for wind-induced intrusion risk of both lightweight and rigid floating debris risk sources, based on the destructive intensity of the risk source and the wind-induced motion trajectory of the hazard. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and device for assessing risk sources of floating objects around railway perimeters, so as to improve the above-mentioned problems.

[0005] In order to achieve the above objectives, the embodiments of the present application provide the following technical solutions:

[0006] In one aspect, an embodiment of the present application provides a method for assessing risk sources of floating debris around a railway perimeter, the method comprising:

[0007] Acquiring a hyperspectral remote sensing image to be evaluated, wherein the hyperspectral remote sensing image includes a hyperspectral remote sensing image of a railway perimeter;

[0008] Identifying risk sources of floating objects around the railway based on the hyperspectral remote sensing image to be assessed, and obtaining an identification result;

[0009] determining first information according to the identification result, the first information including the distance between the risk source of the floating object to be assessed and the railway safety clearance;

[0010] Dividing the risk area of ​​the railway perimeter according to the railway safety clearance to obtain the divided risk area;

[0011] Acquiring second information, where the second information includes an ambient wind speed corresponding to a floating debris risk source to be assessed;

[0012] The probability of the floating object risk source invading the divided risk area is calculated based on the first information and the second information to obtain an assessment result, which includes a danger level of the floating object risk source.

[0013] In a second aspect, an embodiment of the present application provides a railway perimeter floating object risk source assessment device, the device comprising:

[0014] A first acquisition module is configured to acquire a hyperspectral remote sensing image to be evaluated, wherein the hyperspectral remote sensing image includes a hyperspectral remote sensing image of a railway perimeter;

[0015] A first processing module is configured to identify risk sources of floating objects around the railway according to the hyperspectral remote sensing image to be evaluated, and obtain an identification result;

[0016] a second processing module, configured to determine first information based on the identification result, wherein the first information includes a distance between a floating object risk source to be assessed and a railway safety clearance;

[0017] A third processing module is used to divide the risk area of ​​the railway perimeter according to the railway safety clearance to obtain the divided risk area;

[0018] A second acquisition module is configured to acquire second information, wherein the second information includes an ambient wind speed corresponding to a floating object risk source to be assessed;

[0019] The fourth processing module is configured to calculate the probability of the floating object risk source invading the divided risk area based on the first information and the second information to obtain an assessment result, wherein the assessment result includes a danger level of the floating object risk source.

[0020] In a third aspect, embodiments of the present application provide a device for assessing the risk sources of floating debris at railway perimeters, the device comprising a memory and a processor. The memory is configured to store a computer program, and the processor is configured to implement the steps of the aforementioned method for assessing the risk sources of floating debris at railway perimeters when executing the computer program.

[0021] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned railway perimeter floating object risk source assessment method are implemented.

[0022] The beneficial effects of the present invention are:

[0023] The present invention uses high-resolution remote sensing satellites to regularly scan the external environment of the railway and collect hyperspectral remote sensing images, thereby identifying floating object risk sources around the railway. Compared with manual inspections and drone inspections, this method has lower costs, higher efficiency, and a wider monitoring range. The risk areas around the railway are then divided based on the identification results, locking in the distribution space of potential risk sources, shrinking the scope of hidden danger remediation, and reducing the cost of hidden danger remediation. Finally, the probability of floating object risk sources invading the divided risk areas is calculated based on the first information and the second information to obtain an assessment result, thereby achieving an accurate assessment of the risk level of floating object risk sources and effectively guiding on-site hidden danger remediation.

[0024] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1 Schematic diagram of the flow of the railway perimeter floating object risk source assessment method described in an embodiment of the present invention.

[0027] Figure 2 Schematic diagram of the structure of the railway perimeter floating object risk source assessment device described in an embodiment of the present invention.

[0028] Figure 3 Schematic diagram of the structure of the railway perimeter floating object risk source assessment device described in an embodiment of the present invention.

[0029] Figure 4 Schematic diagram of the risk area after division.

[0030] Labels in the figure: 800, railway perimeter floating object risk source assessment equipment; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component; 901, first acquisition module; 902, first processing module; 903, second processing module; 904, third processing module; 905, second acquisition module; 906, fourth processing module. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0032] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are used only to distinguish the description and should not be understood as indicating or implying relative importance.

[0033] Example 1:

[0034] This embodiment provides a method for assessing risk sources of floating objects at the railway perimeter. It is understandable that in this embodiment, a scenario can be laid out, for example, a scenario for assessing the risk level of risk sources of floating objects at the railway perimeter.

[0035] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4, step S5 and step S6.

[0036] Step S1: obtaining a hyperspectral remote sensing image to be evaluated, wherein the hyperspectral remote sensing image includes a hyperspectral remote sensing image of a railway perimeter;

[0037] In this step, high-resolution remote sensing satellites are used to regularly scan the external environment of the railway to collect hyperspectral remote sensing images, thereby identifying the risk sources of floating objects around the railway. Compared with manual inspections and drone inspections, this method is lower in cost, more efficient, and has a wider monitoring range.

[0038] Step S2: identifying the risk source of floating objects around the railway according to the hyperspectral remote sensing image to be evaluated, and obtaining an identification result;

[0039] Step S2 also includes steps S21, S22, S23, and S24, which specifically include:

[0040] Step S21: extracting features from the hyperspectral remote sensing image to be evaluated to obtain feature information corresponding to each floating object risk source;

[0041] Step S22: constructing a semantic feature label for each floating object risk source based on the feature information corresponding to each floating object risk source;

[0042] Step S23: constructing a floating object risk source identification model based on a deep learning algorithm and the semantic feature labels of each floating object risk source;

[0043] Step S24: sending the hyperspectral remote sensing image to be evaluated to the floating object risk source identification model to obtain the identification result.

[0044] In this example, because the spectral and textural features of the two types of floating debris risk sources in remote sensing images differ significantly, remote sensing satellites were used to capture hyperspectral remote sensing images of typical railway perimeters in typical terrains, such as plains, mountains, and offshore areas. The spectral curve characteristics, spectral transformation characteristics, spectral metric characteristics, and textural characteristics of each type of risk source in these typical terrains were statistically analyzed. Semantic feature labels for the risk source remote sensing images were then constructed. A deep learning algorithm was then combined with the spectral and textural semantic labels of the risk sources to establish a multimodal fusion framework model for remote sensing images of the risk sources, namely the floating debris risk source identification model. The model's accuracy was improved through training and validation using a large number of remote sensing images. First, remote sensing images of railway perimeters in some typical terrains were sliced ​​to create training and validation sets for the model. The training set was then substituted into the model for training and comparison analysis with the validation set until the validation accuracy reached no less than 95%. Finally, the floating debris risk source identification model was obtained and applied to the semantic segmentation of remote sensing images of railway perimeter risk sources in these typical terrains for accurate identification. It should be noted that the two types of floating objects include (1) light floating objects: billboards, banners, plastic greenhouses, plastic sheets, and dust nets; and (2) hard floating objects: light steel buildings and the protective colored steel plates of color steel sheds.

[0045] Step S3: determining first information according to the identification result, where the first information includes the distance between the risk source of the floating object to be assessed and the railway safety clearance;

[0046] Step S3 further includes steps S31, S32, S33, S34, and S35, which specifically include:

[0047] Step S31: determining the center point of the floating object risk source pattern according to the recognition result;

[0048] Step S32: obtaining coordinate data information of the railway line;

[0049] Step S33: generating a railway line centerline according to the coordinate data information of the railway line;

[0050] Step S34: generating a railway safety clearance according to a preset line rule and the center line of the railway line;

[0051] Step S35: Calculate the vertical distance between the railway safety clearance and the center point of the floating object risk source pattern to obtain first information.

[0052] In this embodiment, the floating object risk source identification model is connected to the geographic information platform, and the identification results are automatically imported into the geographic information platform. The geographic information platform uses stereo projection and computational geometry tools to calculate the area of ​​the risk source patch and the geodetic coordinates of its center point. The coordinate data of the railway line is imported into the geographic information platform. The geographic information platform draws the center line center of the railway line based on the coordinate data of the railway line, and then generates the railway safety limit according to the preset line rules. At the same time, the platform calculates the vertical distance from the center point of the risk source patch to the safety limit through the patch coordinates and the line coordinates, thereby realizing rapid distance measurement calculation of the risk source.

[0053] Step S4: dividing the risk area of ​​the railway perimeter according to the railway safety clearance to obtain the divided risk area;

[0054] Step S4 further includes steps S41, S42, S43, S44, and S45, which specifically include:

[0055] Step S41: Acquire third information, where the third information includes a limit drift distance corresponding to a historical extreme wind field;

[0056] In this step, by establishing a motion trajectory model, the drift distance of floating objects under different wind directions, wind forces, and durations can be calculated. Then, the maximum drift distance of floating objects can be calculated based on historical extreme wind field information. It can be understood that the motion trajectory model is based on numerical simulation analysis and actual measured data of floating object intrusion. The specific process of establishing the motion trajectory model of floating object disaster factors is as follows:

[0057] S=(k1,k2,k3,t)

[0058] In the above formula, S represents the three-dimensional distance of the floating object caused by wind; k1 represents the wind speed parameter; k2 represents the wind direction parameter; k3 represents the starting height parameter; and t represents the time of wind load action.

[0059] It should be noted that k1 represents the wind speed parameter; k2 represents the wind direction parameter; k3 represents the starting height parameter, which is determined by establishing a wind field remote sensing prediction model. The specific construction process of the wind field remote sensing prediction model is: continuous multi-band imaging of the atmosphere around the railway is performed by meteorological remote sensing satellites, tracking the displacement of characteristic targets such as clouds and water vapor in the atmosphere within a known time interval in the image, and using the radiation information or three-dimensional geometric relationship of each spectral channel to invert the atmospheric height layer where the target is located, and obtain the atmospheric wind vector corresponding to the height layer, and then obtain the wind vector field of the railway perimeter; the atmospheric images corresponding to the wind vector fields of different time series are input into a deep learning model based on convolution-long short-term memory network combined with attention mechanism, using CNN to capture local patterns and features in the image, using LSTM to process the image to capture medium- and long-term dependencies, and using the Attention mechanism to provide the model with the ability to focus on key information, so as to accurately predict the wind vector field after a specified time step, thereby adjusting k1 and k 2、 k3 makes accurate predictions.

[0060] Step S42: determining radius information according to the third information and a preset safety factor;

[0061] In this step, let the limit drift distance corresponding to the historical extreme wind field be S f , the preset safety factor is K, the radius information R=S f ·K.

[0062] Step S43: Divide the railway perimeter according to the radius information and the railway safety clearance to obtain a safe area and a risk area;

[0063] In this step, the external environment is divided into two areas with the railway safety limit as the starting point and R as the radius. It is impossible for wind-induced drift of floating objects in the external area to intrude into the railway safety limit. Therefore, it is only necessary to conduct a risk assessment on the floating object risk source in the internal area of ​​R. That is, the area outside the R boundary is the floating object intrusion safety area, and the area inside the R boundary is the floating object intrusion risk area.

[0064] Step S44: Acquire fourth information, wherein the fourth information includes the maximum value of the average wind speed information and the instantaneous peak wind speed information within a preset time;

[0065] In this step, a specific implementation is to set the maximum value of the 2-minute average wind speed of the site in the past year as V1 and the instantaneous peak wind speed as V2 as the fourth information.

[0066] Step S45: Divide the risk area according to the fourth information.

[0067] In this step, the corresponding wind-induced drift distances of floating objects can be determined as S1 and S2 according to V1 and V2. It can be understood that the limit drift distance is Sf The corresponding limit wind speed is V f , V1<V2<V f , then under the same conditions, S1<S2<R. According to S1, S2, and R, the risk area can be divided into three areas from the inside to the outside, such as Figure 4 shown.

[0068] In this embodiment, the motion trajectory model is used to divide the site into risk areas and safe areas, thereby locking the distribution space of potential risk sources, shrinking the scope of hidden danger remediation, and reducing the cost of hidden danger remediation.

[0069] Step S5: Acquire second information, where the second information includes the ambient wind speed corresponding to the floating debris risk source to be assessed;

[0070] Step S6: Calculate the probability of the floating object risk source invading the divided risk area based on the first information and the second information to obtain an assessment result, which includes the danger level of the floating object risk source.

[0071] Step S6 further includes steps S61, S62, S63, S64, and S65, which specifically include:

[0072] Step S61: Calculate the critical wind speed corresponding to the floating debris risk source to be assessed based on the floating debris risk source damage aging time series model to obtain fifth information;

[0073] In this step, the critical wind speed corresponding to the wind-induced damage of the risk source at any time can be inversely calculated through the damage aging time series model of the floating debris risk source. The specific calculation process is as follows:

[0074] v t =G(F t )

[0075] In the above formula, v t represents the critical wind speed corresponding to the wind-induced damage of the risk source at any time; G(F t ) represents the critical wind speed function corresponding to Ft at any time.

[0076] The step S61 further includes steps S611, S612, and S613, which specifically include:

[0077] Step S611: Obtain aging damage factors of at least five floating object risk sources;

[0078] Step S612: Calculate the material damage aging intensity corresponding to the floating object risk source based on at least five of the risk source aging damage aging factors;

[0079] In this step, the specific calculation formula for the material damage aging strength corresponding to the floating debris risk source is:

[0080] F=(f1,f2,f3,f4,f5)

[0081] In the above formula, F represents the material damage and aging intensity corresponding to the floating object risk source, f1 represents the static strength factor of the floating object material, f2 represents the fatigue strength factor of the floating object material, f3 represents the wind-induced damage intensity factor of the floating object material, f4 represents the environmental corrosion intensity factor of the floating object material, and f5 represents the sunlight aging intensity factor of the floating object material.

[0082] Step S613: constructing a floating object risk source damage aging time series model based on the material damage aging intensity corresponding to the floating object risk source.

[0083] In this step, based on the strength aging time series characteristics of the risk source material and the gale damage intensity characteristics, the Transformer-GRU time series prediction algorithm is introduced into the damage aging constitutive model to realize the prediction of the aging failure time of the risk source strength and the gale coupling damage intensity, thereby establishing a damage aging time series model of the risk source.

[0084] F t =(F, t)

[0085] In the above formula, F t It represents the damage aging time series intensity of the risk source material, and t represents the time interval between the calculation time and the new construction time.

[0086] In this embodiment, the damage aging time series model of floating debris risk sources can accurately calculate the true strength of the risk source at the current moment through historical wind field, rainfall, and temperature information, and can also predict its strength aging failure time, wind-induced damage intensity and its corresponding wind speed; and then, the wind-induced damage level of the risk source can be quantitatively evaluated by predicting the wind speed.

[0087] Step S62: Calculate the drift distance corresponding to the risk source of the floating object to be assessed based on the motion trajectory model to obtain sixth information;

[0088] Step S63: Determine whether the first information is less than or equal to the sixth information and record it as a first event;

[0089] In this step, the first event is recorded as L≤D, where L represents the distance between the floating object risk source to be assessed and the railway safety clearance, and D represents the drift distance corresponding to the floating object risk source to be assessed.

[0090] Step S64: Determine whether the second information is greater than or equal to the fifth information and record it as a second event;

[0091] In this step, the second event is recorded as v0≥vt , where v0 represents the ambient wind speed corresponding to the floating debris risk source to be assessed, v t Indicates the critical wind speed corresponding to wind-induced damage of risk sources.

[0092] Step S65: Evaluate the danger level of the floating object risk source according to the probability of occurrence of the first event and the second event.

[0093] In this step, the probability of the first event occurring is multiplied by the probability of the second event occurring to obtain P C =P A ·P B , where P A and P B They represent the probability of the first event occurring and the probability of the second event occurring, P C It represents the probability of wind-induced intrusion of floating objects. It should be noted that the wind speed statistics adopt the extreme value type I probability distribution. The probability distribution function when the wind speed is v0 is as follows:

[0094]

[0095] In the above formula, P(v0) represents the probability that the wind speed is less than or equal to v0; α represents the scale parameter of the distribution; and u represents the mode of the distribution.

[0096] (1) The probability of the second event is:

[0097] P B =1-P(v t )

[0098] The probability of wind-induced intrusion of floating objects in different areas is:

[0099]

[0100] In the above formula, P B Indicates the probability of critical wind speed for the destruction of floating materials. When v0<v t When P B =0; P(v t ) indicates that the wind speed is less than or equal to [v t ]; P A1 represents the probability of floating debris intrusion in high-risk areas; P(v1) represents the probability when the wind speed is less than or equal to v1; P A2 represents the probability of floating debris intrusion in the medium risk area; P(v2) represents the probability when the wind speed is less than or equal to v2; P A3 represents the probability of floating debris intrusion in low-risk areas; P(v f ) indicates that the wind speed is less than or equal to v f The probability of time.

[0101] In summary, the probability of wind-induced intrusion of floating objects can be quantitatively calculated as follows:

[0102] When P C =0, that is, v0<vt, the risk source will not cause material damage and cannot invade the railway safety limit;

[0103] When 0<P C <0.25, that is, v0≥v t , the risk source has material damage, but it is far away from the safety limit. The floating objects need a very high wind speed to invade the railway safety limit. This type of risk source can be assessed as a low risk source;

[0104] When 0.25≤P C <0.5, that is, v0≥v t , the risk source has material damage, but it is far away from the safety limit. The floating objects need a higher wind speed to invade the railway safety limit. This type of risk source can be assessed as a medium risk source;

[0105] When P C ≥0.5, that is, v0≥v t , material damage occurs at the risk source, but it is close to the safety limit, and floating objects can invade the railway safety limit at a lower wind speed, so this type of risk source is assessed as a high-risk risk source.

[0106] Example 2:

[0107] like Figure 2 As shown, this embodiment provides a device for assessing risk sources of floating objects around a railway, the device comprising a first acquisition module 901, a first processing module 902, a second processing module 903, a third processing module 904, a second acquisition module 905, and a fourth processing module 906, which specifically include:

[0108] A first acquisition module 901 is configured to acquire a hyperspectral remote sensing image to be evaluated, wherein the hyperspectral remote sensing image includes a hyperspectral remote sensing image of a railway perimeter;

[0109] The first processing module 902 is configured to identify the risk source of floating objects around the railway according to the hyperspectral remote sensing image to be evaluated, and obtain an identification result;

[0110] The second processing module 903 is configured to determine first information according to the identification result, where the first information includes the distance between the risk source of the floating object to be assessed and the railway safety clearance;

[0111] The third processing module 904 is configured to divide the risk area of ​​the railway perimeter according to the railway safety clearance to obtain the divided risk areas;

[0112] A second acquisition module 905 is configured to acquire second information, where the second information includes an ambient wind speed corresponding to a floating debris risk source to be assessed;

[0113] The fourth processing module 906 is configured to calculate the probability of the floating object risk source invading the divided risk area based on the first information and the second information to obtain an assessment result, wherein the assessment result includes a danger level of the floating object risk source.

[0114] In a specific embodiment of the present disclosure, the first processing module further includes a first processing unit, a second processing unit, a third processing unit, and a fourth processing unit, which specifically include:

[0115] A first processing unit is configured to extract features from the hyperspectral remote sensing image to be evaluated to obtain feature information corresponding to each floating object risk source;

[0116] A second processing unit is configured to construct a semantic feature label for each floating object risk source based on feature information corresponding to each floating object risk source;

[0117] a third processing unit, configured to construct a floating object risk source identification model based on a deep learning algorithm and a semantic feature label of each floating object risk source;

[0118] The fourth processing unit is configured to send the hyperspectral remote sensing image to be evaluated to the floating object risk source identification model to obtain the identification result.

[0119] In a specific embodiment of the present disclosure, the second processing module further includes a fifth processing unit, a first acquiring unit, a sixth processing unit, a seventh processing unit, and an eighth processing unit, which specifically include:

[0120] a fifth processing unit, configured to determine a center point of a floating object risk source pattern according to the identification result;

[0121] A first acquiring unit, configured to acquire coordinate data information of a railway line;

[0122] a sixth processing unit, configured to generate a railway line centerline according to the coordinate data information of the railway line;

[0123] a seventh processing unit, configured to generate a railway safety clearance according to a preset line rule and the center line of the railway line;

[0124] The eighth processing unit is configured to calculate a vertical distance between the railway safety clearance and a center point of the floating object risk source pattern to obtain first information.

[0125] In a specific embodiment of the present disclosure, the third processing module further includes a second acquisition unit, a ninth processing unit, a tenth processing unit, a third acquisition unit, and an eleventh processing unit, which specifically include:

[0126] A second acquiring unit is configured to acquire third information, wherein the third information includes a limit drift distance corresponding to a historical extreme wind field;

[0127] a ninth processing unit, configured to determine radius information according to the third information and a preset safety factor;

[0128] a tenth processing unit, configured to divide the railway perimeter according to the radius information and the railway safety clearance to obtain a safe area and a risk area;

[0129] a third acquiring unit, configured to acquire fourth information, wherein the fourth information includes a maximum value of the average wind speed information and instantaneous peak wind speed information within a preset time;

[0130] An eleventh processing unit is configured to divide the risk area according to the fourth information.

[0131] In a specific embodiment of the present disclosure, the fourth processing module further includes a first calculation unit, a second calculation unit, a first judgment unit, a second judgment unit, and an evaluation unit, which specifically include:

[0132] The first calculation unit is configured to calculate a critical wind speed corresponding to a floating debris risk source to be assessed based on a floating debris risk source damage aging time series model to obtain fifth information;

[0133] a second calculation unit, configured to calculate a drift distance corresponding to a risk source of floating objects to be assessed based on the motion trajectory model to obtain sixth information;

[0134] A first judging unit, configured to judge whether the first information is less than or equal to the sixth information as a first event;

[0135] A second judging unit, configured to judge whether the second information is greater than or equal to the fifth information as a second event;

[0136] An evaluation unit is configured to evaluate the danger level of the floating object risk source according to the probability of occurrence of the first event and the second event.

[0137] In a specific embodiment of the present disclosure, the first computing unit further includes a fourth acquiring unit, a third computing unit, and a twelfth processing unit, which specifically include:

[0138] A fourth acquisition unit is used to obtain aging damage aging factors of at least five floating object risk sources;

[0139] a third calculation unit, configured to calculate the material damage aging intensity corresponding to the floating object risk source based on at least five of the risk source aging damage aging factors;

[0140] The twelfth processing unit is configured to construct a floating object risk source damage aging time series model based on the material damage aging intensity corresponding to the floating object risk source.

[0141] It should be noted that, regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0142] Example 3:

[0143] Corresponding to the above method embodiment, this embodiment further provides a railway perimeter floating object risk source assessment device. The railway perimeter floating object risk source assessment device described below and the railway perimeter floating object risk source assessment method described above can refer to each other.

[0144] Figure 3 FIG. 8 is a block diagram of a railway perimeter floating debris risk source assessment device 800 according to an exemplary embodiment. Figure 3 As shown, the railway perimeter floating debris risk source assessment device 800 may include: a processor 801 , a memory 802 , and may further include one or more of a multimedia component 803 , an I / O interface 804 , and a communication component 805 .

[0145] Processor 801 is used to control the overall operation of the railway perimeter floating debris risk source assessment device 800 to complete all or part of the steps in the railway perimeter floating debris risk source assessment method described above. Memory 802 is used to store various types of data to support the operation of the railway perimeter floating debris risk source assessment device 800. This data may include, for example, instructions for any application or method operating on the railway perimeter floating debris risk source assessment device 800, as well as application-related data such as contact information, sent and received messages, images, audio, and video. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as a keyboard, mouse, and buttons. These buttons can be virtual or physical. Communication component 805 enables wired or wireless communication between the railway perimeter floating debris risk source assessment device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof, can include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0146] In an exemplary embodiment, the railway perimeter floating object risk source assessment device 800 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-mentioned railway perimeter floating object risk source assessment method.

[0147] In another exemplary embodiment, a computer-readable storage medium containing program instructions is also provided. When executed by a processor, these program instructions implement the steps of the aforementioned railway perimeter floating debris risk source assessment method. For example, the computer-readable storage medium may be the aforementioned memory 802 containing the program instructions. These program instructions may be executed by the processor 801 of the railway perimeter floating debris risk source assessment device 800 to implement the aforementioned railway perimeter floating debris risk source assessment method.

[0148] Example 4:

[0149] Corresponding to the above method embodiment, this embodiment further provides a readable storage medium. The readable storage medium described below and the railway perimeter floating object risk source assessment method described above can refer to each other.

[0150] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the railway perimeter floating object risk source assessment method of the above method embodiment.

[0151] The readable storage medium may specifically be any readable storage medium that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0152] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

[0153] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for assessing risk sources of floating debris around railway perimeters, characterized in that: include: Acquiring a hyperspectral remote sensing image to be evaluated, wherein the hyperspectral remote sensing image includes a hyperspectral remote sensing image of a railway perimeter; Identifying risk sources of floating objects around the railway based on the hyperspectral remote sensing image to be assessed, and obtaining an identification result; determining first information according to the identification result, the first information including the distance between the risk source of the floating object to be assessed and the railway safety clearance; Dividing the risk area of ​​the railway perimeter according to the railway safety clearance to obtain the divided risk area; Acquiring second information, where the second information includes an ambient wind speed corresponding to a floating debris risk source to be assessed; Calculating the probability of a floating object risk source invading the divided risk area based on the first information and the second information to obtain an assessment result, wherein the assessment result includes a hazard level of the floating object risk source; Determining the first information according to the recognition result includes: Determine the center point of the floating object risk source map according to the identification result; Obtain the coordinate data information of the railway line; Generating a railway line centerline according to the coordinate data information of the railway line; Generating railway safety clearances according to preset line rules and the railway line centerline; The vertical distance between the railway safety clearance and the center point of the floating object risk source pattern is calculated to obtain first information.

2. The railway perimeter floating debris risk source assessment method according to claim 1 is characterized in that: Identify the risk sources of floating objects around the railway based on the hyperspectral remote sensing image to be assessed, and obtain identification results, including: Performing feature extraction on the hyperspectral remote sensing image to be evaluated to obtain feature information corresponding to each floating object risk source; Constructing a semantic feature label for each floating object risk source based on the feature information corresponding to each floating object risk source; Constructing a floating debris risk source identification model based on a deep learning algorithm and semantic feature labels of each floating debris risk source; The hyperspectral remote sensing image to be evaluated is sent to the floating object risk source identification model to obtain the identification result.

3. The railway perimeter floating debris risk source assessment method according to claim 1 is characterized in that: The risk areas of the railway perimeter are divided according to the railway safety clearance, and the divided risk areas include: Acquiring third information, the third information including a limit drift distance corresponding to a historical extreme wind field; determining radius information according to the third information and a preset safety factor; Dividing the railway perimeter according to the radius information and the railway safety clearance to obtain a safe area and a risk area; Acquire fourth information, the fourth information including the maximum value of the average wind speed information and the instantaneous peak wind speed information within a preset time; The risk areas are divided according to the fourth information.

4. The railway perimeter floating debris risk source assessment method according to claim 1 is characterized in that: Calculating the probability of a floating object risk source invading the divided risk area based on the first information and the second information includes: Calculate the critical wind speed corresponding to the floating debris risk source to be assessed based on the damage aging time series model of the floating debris risk source to obtain the fifth information; Calculating the drift distance corresponding to the risk source of the floating object to be assessed based on the motion trajectory model to obtain sixth information; Determining whether the first information is less than or equal to the sixth information is recorded as a first event; Determining whether the second information is greater than or equal to the fifth information is recorded as a second event; The hazard level of the floating object risk source is evaluated according to the probability of occurrence of the first event and the second event.

5. A railway perimeter floating debris risk source assessment device, characterized in that: include: A first acquisition module is configured to acquire a hyperspectral remote sensing image to be evaluated, wherein the hyperspectral remote sensing image includes a hyperspectral remote sensing image of a railway perimeter; A first processing module is configured to identify risk sources of floating objects around the railway according to the hyperspectral remote sensing image to be evaluated, and obtain an identification result; a second processing module, configured to determine first information based on the identification result, wherein the first information includes a distance between a floating object risk source to be assessed and a railway safety clearance; A third processing module is used to divide the risk area of ​​the railway perimeter according to the railway safety clearance to obtain the divided risk area; A second acquisition module is configured to acquire second information, wherein the second information includes an ambient wind speed corresponding to a floating object risk source to be assessed; a fourth processing module, configured to calculate the probability of a floating object risk source invading the divided risk area based on the first information and the second information, and obtain an assessment result, wherein the assessment result includes a hazard level of the floating object risk source; Wherein, the second processing module includes: a fifth processing unit, configured to determine a center point of a floating object risk source pattern according to the identification result; A first acquiring unit, configured to acquire coordinate data information of a railway line; a sixth processing unit, configured to generate a railway line centerline according to the coordinate data information of the railway line; a seventh processing unit, configured to generate a railway safety clearance according to a preset line rule and the center line of the railway line; The eighth processing unit is configured to calculate a vertical distance between the railway safety clearance and a center point of the floating object risk source pattern to obtain first information.

6. The railway perimeter floating object risk source assessment device according to claim 5, characterized in that: The first processing module includes: A first processing unit is configured to extract features from the hyperspectral remote sensing image to be evaluated to obtain feature information corresponding to each floating object risk source; A second processing unit is configured to construct a semantic feature label for each floating object risk source based on feature information corresponding to each floating object risk source; a third processing unit, configured to construct a floating object risk source identification model based on a deep learning algorithm and a semantic feature label of each floating object risk source; The fourth processing unit is configured to send the hyperspectral remote sensing image to be evaluated to the floating object risk source identification model to obtain the identification result.

7. The railway perimeter floating debris risk source assessment device according to claim 5, characterized in that: The third processing module includes: A second acquiring unit is configured to acquire third information, wherein the third information includes a limit drift distance corresponding to a historical extreme wind field; a ninth processing unit, configured to determine radius information according to the third information and a preset safety factor; a tenth processing unit, configured to divide the railway perimeter according to the radius information and the railway safety clearance to obtain a safe area and a risk area; a third acquiring unit, configured to acquire fourth information, wherein the fourth information includes a maximum value of the average wind speed information and instantaneous peak wind speed information within a preset time; An eleventh processing unit is configured to divide the risk area according to the fourth information.

8. The railway perimeter floating debris risk source assessment device according to claim 5, characterized in that: The fourth processing module includes: The first calculation unit is configured to calculate a critical wind speed corresponding to a floating debris risk source to be assessed based on a floating debris risk source damage aging time series model to obtain fifth information; a second calculation unit, configured to calculate a drift distance corresponding to a risk source of floating objects to be assessed based on the motion trajectory model to obtain sixth information; A first judging unit, configured to judge whether the first information is less than or equal to the sixth information as a first event; A second judging unit, configured to judge whether the second information is greater than or equal to the fifth information as a second event; An evaluation unit is configured to evaluate the danger level of the floating object risk source according to the probability of occurrence of the first event and the second event.

Images