Multi-source data fused motor vehicle passing influence assessment method under waterlogging

Abstract

The invention provides a multi-source data fused motor vehicle passing influence assessment method under waterlogging, and the method comprises the steps: obtaining social media data, remote sensing image data and road network data of waterlogging, the social media data comprising a waterlogging image and a waterlogging description text of a motor vehicle; constructing disaster geographic information data and a corresponding disaster buffer area based on the waterlogging image and the waterlogging description text; determining an urban inundation area from the remote sensing image data, and marking a road network intersected with the urban inundation area as a wading road section according to the road network data; and carrying out spatial superposition on the disaster geographic information data and the disaster buffer area with the wading road section to obtain a waterlogging influence range map and a motor vehicle traffic condition map. Through the method and the device, the defect that detailed guidance cannot be made for passing of motor vehicles due to the fact that the flooding degree is difficult to describe specifically when the inundation area of the waterlogging city is identified in the prior art is overcome.

Description

Technical Field

[0001] The present invention relates to the field of traffic technology, and in particular to a method for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data. Background Art

[0002] With the acceleration of urbanization, the impervious area in cities has increased significantly. In addition, the intensification of abnormal climate change has led to frequent extreme weather events, such as continuous heavy rains, resulting in an increasing frequency and severity of urban waterlogging. Urban waterlogging has a particularly serious impact on motor vehicle traffic. In the existing technology, ground monitoring methods based on space-based remote sensing can help quickly identify urban flooded areas, thereby assisting in assessing the impact on urban traffic. However, the relevant method has a major limitation, that is, it is difficult to describe the degree of flooding in detail, making it impossible to provide detailed guidance for motor vehicle traffic. Summary of the invention

[0003] The present invention provides a method for evaluating the impact of urban flooding on motor vehicle traffic by integrating multi-source data, so as to solve the defect in the prior art that it is difficult to specifically describe the degree of flooding when identifying urban flooding areas, resulting in inability to provide detailed guidance for motor vehicle traffic.

[0004] The present invention provides a method for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data, and the method comprises the following steps: Obtaining social media data, remote sensing image data, and road network data of waterlogging, wherein the social media data includes waterlogging images of motor vehicles and waterlogging description text; Based on the waterlogging image and the waterlogging description text, construct disaster geographic information data and a corresponding disaster buffer zone; Determine the urban flooded area from the remote sensing image data, and mark the road network intersecting the urban flooded area as a flooded road section according to the road network data; The disaster geographic information data and the disaster buffer zone are spatially superimposed with the water-related road section to obtain a waterlogging impact range map and a motor vehicle traffic status map.

[0005] In some embodiments, constructing disaster geographic information data and a corresponding disaster buffer zone based on the waterlogging image and the waterlogging description text includes: Extracting waterlogging geographical location information from the waterlogging description text; Identifying the flooded position of the motor vehicle in the waterlogging image to obtain water depth determination information based on the motor vehicle; Constructing disaster geographic information data according to the waterlogging geographic location information and the water depth judgment information; The vector point in the disaster geographic information data is taken as the disaster center, and the area within a preset length range of the disaster center is determined as the corresponding disaster buffer zone.

[0006] In some embodiments, the identifying the flooded position of the motor vehicle in the waterlogging image to obtain water depth determination information based on the motor vehicle includes: Performing wheel semantic segmentation processing on the motor vehicle in the waterlogging image to obtain a wheel mask file corresponding to the motor vehicle; The flood position detection result of the wheel contour is determined according to the wheel mask file, and the water depth is judged on the flood position detection result to obtain water depth judgment information based on the motor vehicle.

[0007] In some embodiments, determining the flooded position detection result of the wheel contour according to the wheel mask file includes: Calling the DBSCAN algorithm to separate the wheels of the motor vehicle in the wheel mask file to obtain a plurality of wheel masks, and performing edge detection on the wheel masks to obtain a pixel coordinate sequence of the wheel contour; Extracting a lower edge coordinate sequence from the pixel coordinate sequence, and fitting a wading line of the wheel based on the lower edge coordinate sequence; calculating a secant length between an intersection point of the wading line and the wheel profile; The longest line of the wheel profile is determined, and the ratio of the length of the cut line to the length of the longest line is used as the position detection result of the wheel profile.

[0008] In some embodiments, determining the longest line of the wheel profile comprises: constructing a moving straight line, the slope of the moving straight line being the same as the slope of the wading line; While keeping the slope of the moving straight line unchanged, changing the intercept value of the moving straight line so that the moving straight line traverses the entire wheel profile; During the traversal of the moving straight line, the length of the secant between the intersection of the moving straight line and the wheel contour is calculated, and the secant with the largest secant length is taken as the longest line of the wheel contour.

[0009] In some embodiments, the performing water depth judgment on the wheel profile information determination result to obtain water depth judgment information based on the motor vehicle includes: When the ratio of the length of the secant line between the intersection of the wading line and the wheel contour to the length of the longest line is less than a ratio threshold, determining that the center line of the wheel of the motor vehicle is above the water level; When the ratio of the length of the secant line between the intersection of the wading line and the wheel contour to the length of the longest line is greater than a ratio threshold, it is determined that the wheel centerline of the motor vehicle is below the water level.

[0010] The present invention also provides a device for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data, and the device includes the following modules: An acquisition module, used to acquire social media data, remote sensing image data and road network data of waterlogging, wherein the social media data includes waterlogging images of motor vehicles and waterlogging description text; A construction module, used to construct disaster geographic information data and a corresponding disaster buffer zone based on the waterlogging image and the waterlogging description text; A marking module, used for determining the urban flooded area from the remote sensing image data, and marking the road network intersecting with the urban flooded area as a flooded road section according to the road network data; The superposition module is used to spatially superimpose the disaster geographic information data and the disaster buffer zone with the flooded road section to obtain a map of the affected area of ​​the waterlogging and a map of the motor vehicle traffic conditions. The present invention also 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 method for evaluating the impact of motor vehicle traffic under flooding by fusing multi-source data as described in any one of the above-mentioned methods is implemented.

[0011] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for evaluating the impact of motor vehicle traffic under flooding by fusing multi-source data as described in any one of the above methods.

[0012] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for evaluating the impact of motor vehicle traffic under flooding by fusing multi-source data.

[0013] The method for evaluating the impact of motor vehicle traffic under waterlogging by integrating multi-source data provided by the present invention, at a microscopic perspective, uses waterlogging social media data to extract data information of waterlogging images and description texts to determine the buffer zone as the traffic condition of the disaster area. In addition, combined with multi-source data such as remote sensing image data and road network data, it is possible to quickly and macroscopically understand the urban flooding situation and provide macroscopic decisions for urban road network traffic. Finally, a waterlogging impact range map and a motor vehicle traffic status map are constructed in combination with the flooded sections of the road network, to achieve an accurate assessment of the impact of motor vehicle traffic under waterlogging, and provide auxiliary guidance for the traffic of motor vehicles under waterlogging. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced one by one below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 It is a flow chart of the method for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data provided by the present invention.

[0016] Figure 2 It is a schematic diagram of the principle of the method for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data provided by the present invention.

[0017] Figure 3 It is a schematic diagram of vehicle flooding position identification provided by the present invention.

[0018] Figure 4 It is a schematic diagram of data coordinates for water depth judgment provided by the present invention.

[0019] Figure 5 It is a visualization diagram of the waterlogging impact range map and the motor vehicle traffic status map provided by the present invention.

[0020] Figure 6 It is a schematic diagram of the structure of the device for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data provided by the present invention.

[0021] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] The method for evaluating the impact of motor vehicle traffic under waterlogging by integrating multi-source data provided by the present invention can be applied to a map system (hereinafter referred to as the map system) that monitors waterlogging disasters, so the execution subject of the method is the server or terminal of the map system. After the method is deployed on the corresponding system server or terminal, when the map system monitors the occurrence of waterlogging disasters, the social media data, remote sensing image data and road network data of waterlogging are obtained in real time through the method, and the impact of motor vehicle traffic under waterlogging is evaluated. Finally, a map of the waterlogging impact range and a map of motor vehicle traffic conditions are constructed, and visualized on the interface of the map system for reference and decision-making by disaster workers.

[0024] The following describes the impact assessment method of motor vehicle traffic under flooding by integrating multi-source data of the present invention with reference to the accompanying drawings. Figure 1 This is one of the flow charts of the method for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data provided by the present invention. Figure 1 As shown, the method includes the following steps 101 to 104, which are described in detail below.

[0025] Step 101: Acquire social media data, remote sensing image data, and road network data of waterlogging, wherein the social media data includes waterlogging images of motor vehicles and waterlogging description text.

[0026] Here, in the map system for monitoring waterlogging disasters, when waterlogging disasters are detected, social media data, remote sensing image data and road network data of waterlogging are obtained. Social media data include waterlogging images of motor vehicles and waterlogging description text. Social media data of waterlogging can be downloaded from social media platforms on the Internet after searching, including waterlogging images of motor vehicles and waterlogging description text, that is, the status map of motor vehicles in the flood. The waterlogging description text describes some information such as the time, location, and scope of the waterlogging disaster.

[0027] Remote sensing image data can be downloaded and obtained through satellite maps of the mapping system or data collected using mapping software (such as Google Maps) and other platforms, while road network data can also be directly obtained based on the functions of the mapping system or using other mapping software.

[0028] Step 102: construct disaster geographic information data and corresponding disaster buffer zones based on the waterlogging images and waterlogging description texts.

[0029] After obtaining the relevant data through step 101, the media social data therein can be used to detect the water depth position information of the motor vehicle in the flood, and to supplement the perception of the flooding degree of the local area of ​​the disaster from a microscopic scale. Based on the waterlogging image of the motor vehicle and the waterlogging description text, the disaster geographic information data and the corresponding disaster buffer zone are constructed, and the detected water depth position information is used to determine the traffic conditions of the motor vehicle, which is described in detail below.

[0030] like Figure 2 As shown, for the text data in the social media data, that is, the waterlogging description text, the waterlogging geographical location information is extracted from the waterlogging description text. Because the waterlogging description text records the location or geographical location where the waterlogging disaster occurred, the geographical location can be directly extracted from the text data to obtain the corresponding geographical code as the waterlogging geographical location information.

[0031] For the image data in social media data, that is, the waterlogged images of motor vehicles (i.e., flooded images), the vehicle flooded position is identified for the motor vehicle in the waterlogged images, and the water depth judgment information based on the motor vehicle is obtained. The water depth judgment information is used to determine whether the motor vehicle can pass in the flood and leave the flooded section. This process is divided into two stages: wheel semantic segmentation and wheel flooded position detection.

[0032] The first stage is to perform semantic segmentation of the wheels of motor vehicles in the waterlogged images and obtain the wheel mask file corresponding to the motor vehicle. In the wheel mask text, the pixel mask value belonging to the vehicle is set to 1, and the background mask value is set to 0, so that the water depth position can be better identified based on the wheels without being affected by the image background.

[0033] The second stage is to determine the flooded position detection result of the wheel contour according to the wheel mask file, and to judge the water depth of the flooded position detection result, and obtain the water depth judgment information based on the motor vehicle as the motor vehicle passage information. Here, from the perspective of the wheel contour, it is judged whether the wading line of the wheel exceeds the center line of the wheel, so as to judge the feasibility of the motor vehicle passing the wading section, and lay the foundation for the subsequent determination of the motor vehicle passage route planning.

[0034] The following describes the process of determining the position detection result of the wheel contour based on the wheel mask file. First, in the waterlogging image of a motor vehicle, there may be multiple tires on the wheels of the motor vehicle. When judging whether the wheel can pass through the wading section, only one of the tires needs to be judged. Therefore, the embodiment of the present invention calls the DBSCAN algorithm to separate the wheels of the motor vehicle in the wheel mask file to obtain multiple wheel masks, that is, to separate the wheel mask of one tire for subsequent processing.

[0035] The next step is to detect the wheel contour. Here, the edge detection algorithm is called again to perform edge detection on the wheel mask to obtain the pixel coordinate sequence of the wheel contour, which is recorded as .

[0036] like Figure 3 As shown in Figure 1, since the bottom part of the wheel is in the flood, it is necessary to determine the wading line of the wheel. Extract the lower edge coordinate sequence from , and based on the lower edge coordinate sequence The wheel wading line is obtained by fitting. Due to the shooting angle of the flood image of the motor vehicle and the movement of the flood water flow, the lower edge of the vehicle contour (flood surface) is not necessarily a clear straight line. Therefore, it is necessary to use the lower edge coordinate sequence , use the straight line fitting algorithm to approximate a fitting straight line , so that the lower edge coordinate sequence Each coordinate in the fit line should fall as much as possible on the fit line , this fitting is directly used as the wading line of the wheel.

[0037] like Figure 3 As shown, in the embodiment of the present invention, this fitting straight line is defined as The slope is k (k>0), and the intercept is , so there is This fitted straight line There must be two intersection points with the wheel contour, so the wading line is calculated next The length of the secant line between the intersection point with the wheel profile is denoted by .

[0038] Finally determine the longest line of the wheel profile , wading line Length of the secant line between the intersection points with the wheel profile The closer to this longest line , the probability that the vehicle can pass through the flooded section is lower, and vice versa. With the longest line The ratio of the lengths of the wheel profile is used as the flooded position detection result of the wheel profile, which is used to subsequently determine the water depth judgment information.

[0039] The embodiment of the present invention estimates the wading line of the wheel profile by modeling the wheel tire of the motor vehicle, and then compares it with the longest line of the wheel profile, thereby achieving accurate detection of the flooded position information of the motor vehicle in the flood, and ensuring the accuracy of subsequent judgment on whether the motor vehicle can pass through the wading section.

[0040] To determine whether a motor vehicle can pass through a flooded section, it is mainly necessary to achieve the longest line of the wheel contour. The following describes how to determine the longest line of the wheel profile. process.

[0041] like Figure 3 As shown, first construct the moving straight line , randomly construct a moving straight line on the vehicle contour, because the longest line finally determined needs to be the same length as the secant line For comparison, the secant length is based on the wading line (i.e. the fitted straight line ), so the moving straight line must be ensured during construction The slope and wading line The slope k is the same, so we have Then keep moving in a straight line When the slope k remains unchanged, change the intercept value of the moving straight line , so that the moving straight line Traverse the entire wheel profile.

[0042] In moving straight line During the traversal, calculate the moving straight line The longest secant length between the intersection points with the wheel contour is taken as the longest line of the wheel contour. The moving straight line must have two intersection points with the wheel contour during the moving process, so the secant length between the two intersection points can be calculated. The length of the secant line between the two intersection points will change gradually, and a maximum value will be calculated eventually. This maximum value is the longest secant line length, which can be used as the longest line of the wheel profile. .

[0043] In the embodiment of the present invention, when determining the longest line of the wheel contour, a moving straight line with the same slope as the wading line is set, and the longest line of the wheel contour is determined by translating the moving straight line, thereby eliminating the error caused by the change of the shooting angle and ensuring that the longest line is determined. The longest line of the wheel contour, which is closest to the actual one, is used as the criterion for judging the water-crossing sections for motor vehicles, which also ensures the accuracy of the judgment criterion.

[0044] Through the above steps, the second stage of determining the wheel contour flooding position detection result according to the wheel mask file is completed, and finally the secant line length is obtained. With the longest line The length ratio is used as the flood position detection result. Next, the water depth is judged on the flood position detection result to obtain the water depth judgment information based on the motor vehicle.

[0045] Here, when judging the water depth, the detection result of the flooded position is compared with the preset proportional threshold, that is, the length of the secant line With the longest line The ratio of the length of the wading line is compared with the preset ratio threshold. Length of the secant line between the intersection points with the wheel profile , and the longest line When the ratio of the lengths of is less than the ratio threshold, the secant length Less than the longest line The length of the cleavage line indicates that the wading line of the motor vehicle is lower than the center line of the wheel. It can be determined that the center line of the wheel of the motor vehicle is higher than the water level. At this time, the motor vehicle can pass through the wading section. The proportional threshold is used to measure the length of the cleavage line. With the longest line The length approximation can be reasonably preset according to the actual situation, for example, set to 0.95. If the ratio of the two is less than 0.95, it means that the secant length Less than the longest line Length.

[0046] like Figure 4 As shown, move the straight line The intercept value Rang b (that is, ) changes continuously, calculate the moving straight line The length of the secant line between the intersection points with the wheel contour is Fit. When the secant line length Fit reaches a maximum value, this maximum value is the longest secant line length Max, which can be used as the longest line of the wheel contour. . And when the wading line The length of the secant line between the intersection point with the wheel contour is Fit (i.e. ) does not exceed the longest line Max (that is, ) in length, it means that motor vehicles can pass through the flooded section.

[0047] When the wading line Length of the secant line between the intersection points with the wheel profile , and the longest line When the ratio of the lengths of is greater than the ratio threshold, the secant length Approximately equal to or equal to the longest line The length of the secant line indicates that the wading line of the motor vehicle is higher than the center line of the wheel. It can be determined that the center line of the wheel of the motor vehicle is lower than the water level. At this time, the motor vehicle cannot pass the wading section. Here, if the ratio of the two is greater than the ratio threshold of 0.95, then it can be considered that the secant line length Approximately equal to the longest line Length.

[0048] Therefore, the water depth judgment information of the motor vehicle is determined based on the waterlogging image of the motor vehicle, indicating whether the motor vehicle can pass through the wading section. Next, based on the waterlogging geographical location information and water depth judgment information, disaster geographical information data is constructed. This disaster geographical information data is used to indicate which geographical locations where disasters occur can allow motor vehicles to pass through the wading section.

[0049] like Figure 2 As shown, the corresponding disaster geographic information data is constructed based on the water depth judgment information obtained by geocoding and vehicle submerged position detection. This information data is mapped to the map system as vector points. Each vector point represents the geographical location where the disaster occurred and the motor vehicle can pass the wading section. Then, the vector point in the disaster geographic information data is used as the disaster center, and the area within the preset distance range of the disaster center is determined as the corresponding disaster buffer zone. The preset distance can be set to 500 meters, so that the area range where the motor vehicle can pass the wading section can be determined from the map as a disaster buffer zone.

[0050] The embodiment of the present invention extracts data information of waterlogging images and description texts through waterlogging social media data to determine a buffer zone as a passage condition in the disaster area, thereby achieving an accurate assessment of the impact of waterlogging disasters from the micro perspective of motor vehicle wading, and facilitating the formulation of motor vehicle passage plans.

[0051] Step 103: extract the urban flooded area from the remote sensing image data, and mark the road network intersecting with the urban flooded area as a flooded road section according to the road network data.

[0052] Next, from the perspective of the map system, it is necessary to understand the urban flooding situation from a macro perspective and provide macro decisions on urban road network traffic. Therefore, the embodiment of the present invention also obtains remote sensing image data, and extracts the urban flooding area from the remote sensing image data, that is, determines the disaster scope of urban waterlogging. Then, according to the road network data, the road network intersecting with the urban flooding area is marked as a flooded road section.

[0053] like Figure 2 As shown, multi-temporal remote sensing data flooded area extraction is performed on remote sensing image data to determine the specific urban flooded area. Combined with the road network data, the road network intersecting with the urban flooded area can be marked as a flooded section. By marking the corresponding flooded sections on the map road network, the urban flooding situation and the flood-affected area can be quickly understood from a macro perspective, which is convenient for providing macro decisions on urban road network traffic.

[0054] Step 104: spatially overlay the disaster geographic information data and the disaster buffer zone with the flooded road section to obtain a waterlogging impact range map and a motor vehicle traffic status map.

[0055] Through step 102 and step 103, the scope of waterlogging disaster impact is evaluated from micro and macro perspectives respectively. Finally, the disaster geographic information data and the disaster buffer zone are spatially superimposed with the flooded road section to obtain a waterlogging impact scope map and a motor vehicle traffic status map.

[0056] Spatial superposition can be achieved by calling the map synthesis function of the map system. In the geographical location map of the flood-stricken area displayed on the map system interface, the disaster geographic information data and the disaster buffer zone are marked separately, and the corresponding social media data (including the flood images of motor vehicles and the flood geographical location information extracted from the flood description text) are added. Since there is also a traffic road network on the map, the corresponding road network data is displayed, so the wading road sections marked according to the remote sensing image data can also be displayed on the road network of the map. This realizes the combination of macro and micro. Through the spatial superposition of the above information and the annotation of the map, the map of the flood-affected area and the motor vehicle traffic status map are finally obtained, and visualized in real time on the map system interface.

[0057] If disaster prevention decisions need to be made, they need to be made in combination with the waterlogging impact map and the motor vehicle traffic status map. Therefore, in the map system, the waterlogging impact map and the motor vehicle traffic status map can be superimposed together for visualization. The visualization results can be as follows: Figure 5 As shown, Figure 5 The visualization results of the map of the scope of urban flooding and the map of motor vehicle traffic conditions are displayed. Among them, the blue area in the figure is the natural water body before the disaster, and the brown area is the urban flooded area determined from the remote sensing image data. The green line represents the road network data, and the purple line represents the flooded road section marked as the urban flooded area in combination with the road network data. The flooded road section indicates the road section affected by the urban flooded area, but there is no social media data to further explain the road conditions. Therefore, motor vehicles need to be vigilant when traveling. The yellow line is the road section affected by the urban flooded area, and there is social media data to further explain the traffic conditions of the road section. It can be judged based on the social media data that motor vehicles can pass through the flooded road section, which is a passable road section. As shown in the following figure, Figure 5 As shown in the figure, the flooding degree of these road sections is relatively small (the flooding depth is below the center line of the vehicle wheels), and vehicles can slow down and safely pass through the flooded sections. And the social media data corresponding to points c and d ( Figure 5 The images of motor vehicle flooding (c and d on the right) provide further evidence, confirming that the wheels of the motor vehicle are above the water level. The red line is the road section with severe flooding as shown by social media data, such as Figure 3As shown in the a and b points, the water depth in these road sections exceeds the center line of the motor vehicle wheels (threatening the motor vehicle exhaust pipe), that is, the motor vehicle is lower than the water level, and the motor vehicle cannot pass through such a flooded road section at all. In addition, the social media data corresponding to a and b points ( Figure 5 The images of motor vehicle flooding shown in a and b on the lower side provide further evidence, confirming that the wheels of the motor vehicle were above the water level.

[0058] In this way, disaster workers can make corresponding disaster prevention decisions based on the visualized map of the impact area of ​​urban flooding and the motor vehicle traffic status map on the map system, and guide motor vehicles to pass through passable flooded sections or disaster buffer zones in the road network data.

[0059] The embodiment of the present invention uses waterlogging social media data to extract waterlogging images and description text data information to determine the buffer zone as the traffic condition of the disaster area. In addition, combined with remote sensing image data and road network data and other multi-source data, it can quickly and macroscopically understand the urban flooding situation and provide macroscopic decisions for urban road network traffic. Finally, the waterlogging impact range map and motor vehicle traffic status map are constructed in combination with the flooded sections of the road network to achieve an accurate assessment of the impact of motor vehicle traffic under waterlogging and provide auxiliary guidance for the traffic of motor vehicles under waterlogging.

[0060] The following is a description of the motor vehicle traffic impact assessment device for urban flooding that integrates multi-source data provided by the present invention. The motor vehicle traffic impact assessment device for urban flooding that integrates multi-source data described below and the motor vehicle traffic impact assessment method for urban flooding that integrates multi-source data described above can refer to each other.

[0061] like Figure 6 As shown, the motor vehicle traffic impact assessment device under waterlogging that integrates multi-source data includes the following modules: an acquisition module 601, a construction module 602, a marking module 603, and an overlay module 604. Specifically, the acquisition module 601 is used to acquire social media data, remote sensing image data, and road network data of waterlogging, wherein the social media data includes waterlogging images of motor vehicles and waterlogging description texts; the construction module 602 is used to construct disaster geographic information data and corresponding disaster buffer zones based on the waterlogging images and waterlogging description texts; the marking module 603 is used to determine the urban flooding area from the remote sensing image data, and mark the road network intersecting the urban flooding area as a flooded road section according to the road network data; the overlay module 604 is used to spatially overlay the disaster geographic information data and the disaster buffer zone with the flooded road section to obtain a waterlogging impact range map and a motor vehicle traffic status map.

[0062] It should be noted that the beneficial effects of the motor vehicle traffic impact assessment device under urban flooding that integrates multi-source data and the motor vehicle traffic impact assessment method under urban flooding that integrates multi-source data mentioned above can correspond to each other, so the beneficial effects of the motor vehicle traffic impact assessment device under urban flooding that integrates multi-source data will not be repeated here.

[0063] Figure 7 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the method for evaluating the impact of motor vehicle traffic under waterlogging by integrating multi-source data, the method comprising: obtaining social media data, remote sensing image data and road network data of waterlogging, wherein the social media data includes waterlogging images of motor vehicles and waterlogging description text; constructing disaster geographic information data and corresponding disaster buffer zones based on the waterlogging images and waterlogging description text; determining the urban flooded area from the remote sensing image data, and marking the road network intersecting the urban flooded area as a flooded road section according to the road network data; spatially superimposing the disaster geographic information data and the disaster buffer zone with the flooded road section to obtain a waterlogging impact range map and a motor vehicle traffic status map.

[0064] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0065] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for evaluating the impact of motor vehicle traffic under urban flooding by integrating multi-source data provided by the above-mentioned methods, and the method includes: obtaining social media data, remote sensing image data and road network data of urban flooding, and the social media data includes urban flooding images of motor vehicles and urban flooding description text; based on the urban flooding images and the urban flooding description text, constructing disaster geographic information data and corresponding disaster buffer zones; determining the urban flooding area from the remote sensing image data, and marking the road network intersecting with the urban flooding area as a flooded road section according to the road network data; spatially superimposing the disaster geographic information data and the disaster buffer zone with the flooded road section to obtain an urban flooding impact range map and a motor vehicle traffic status map.

[0066] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the method for evaluating the impact of urban flooding on motor vehicle traffic by integrating multi-source data provided by the above-mentioned methods, the method comprising: obtaining social media data, remote sensing image data and road network data of urban flooding, the social media data comprising urban flooding images of motor vehicles and urban flooding description text; constructing disaster geographic information data and a corresponding disaster buffer zone based on the urban flooding images and the urban flooding description text; determining an urban flooded area from the remote sensing image data, and marking a road network intersecting the urban flooded area as a flooded section according to the road network data; spatially superimposing the disaster geographic information data and the disaster buffer zone with the flooded section to obtain an urban flooding impact range map and a motor vehicle traffic status map.

[0067] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0068] 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 ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has 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 described 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 present invention.

Claims

1. A method for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data, characterized in that: The method comprises: Obtaining social media data, remote sensing image data, and road network data of waterlogging, wherein the social media data includes waterlogging images of motor vehicles and waterlogging description text; Based on the waterlogging image and the waterlogging description text, construct disaster geographic information data and a corresponding disaster buffer zone; Determine the urban flooded area from the remote sensing image data, and mark the road network intersecting the urban flooded area as a flooded road section according to the road network data; The disaster geographic information data and the disaster buffer zone are spatially superimposed with the water-related road section to obtain a waterlogging impact range map and a motor vehicle traffic status map.

2. The method for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data according to claim 1 is characterized in that: The constructing disaster geographic information data and a corresponding disaster buffer zone based on the waterlogging image and the waterlogging description text includes: Extracting waterlogging geographical location information from the waterlogging description text; Identifying the flooded position of the motor vehicle in the waterlogging image to obtain water depth determination information based on the motor vehicle; Constructing disaster geographic information data according to the waterlogging geographic location information and the water depth judgment information; The vector point in the disaster geographic information data is taken as the disaster center, and the area within a preset length range of the disaster center is determined as the corresponding disaster buffer zone.

3. The method for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data according to claim 2 is characterized in that: The step of identifying the flooded position of the motor vehicle in the waterlogging image to obtain water depth determination information based on the motor vehicle includes: Performing wheel semantic segmentation processing on the motor vehicle in the waterlogging image to obtain a wheel mask file corresponding to the motor vehicle; The flood position detection result of the wheel contour is determined according to the wheel mask file, and the water depth is judged on the flood position detection result to obtain water depth judgment information based on the motor vehicle.

4. The method for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data according to claim 3 is characterized in that: The step of determining the flooded position detection result of the wheel contour according to the wheel mask file comprises: Calling the DBSCAN algorithm to separate the wheels of the motor vehicle in the wheel mask file to obtain a plurality of wheel masks, and performing edge detection on the wheel masks to obtain a pixel coordinate sequence of the wheel contour; Extracting a lower edge coordinate sequence from the pixel coordinate sequence, and fitting a wading line of the wheel based on the lower edge coordinate sequence; calculating a secant length between an intersection point of the wading line and the wheel profile; The longest line of the wheel profile is determined, and the ratio of the length of the cut line to the length of the longest line is used as the position detection result of the wheel profile.

5. The method for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data according to claim 4 is characterized in that: Determining the longest line of the wheel profile comprises: constructing a moving straight line, the slope of the moving straight line being the same as the slope of the wading line; While keeping the slope of the moving straight line unchanged, changing the intercept value of the moving straight line so that the moving straight line traverses the entire wheel profile; During the traversal of the moving straight line, the length of the secant between the intersection of the moving straight line and the wheel contour is calculated, and the secant with the largest secant length is taken as the longest line of the wheel contour.

6. The method for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data according to claim 3 is characterized in that: The step of performing water depth determination on the position detection result to obtain water depth determination information of the motor vehicle includes: When the ratio of the length of the secant line between the intersection of the wading line and the wheel contour to the length of the longest line is less than a ratio threshold, determining that the center line of the wheel of the motor vehicle is above the water level; When the ratio of the length of the secant line between the intersection of the wading line and the wheel contour to the length of the longest line is greater than a ratio threshold, it is determined that the wheel centerline of the motor vehicle is below the water level.

7. A device for evaluating the impact of motor vehicle traffic under flooding by integrating multi-source data, characterized in that: The device comprises: An acquisition module, used to acquire social media data, remote sensing image data and road network data of waterlogging, wherein the social media data includes waterlogging images of motor vehicles and waterlogging description text; A construction module, used to construct disaster geographic information data and a corresponding disaster buffer zone based on the waterlogging image and the waterlogging description text; A marking module, used to determine the urban flooded area from the remote sensing image data, and mark the road network intersecting the urban flooded area as a flooded road section according to the road network data; The superposition module is used to spatially superimpose the disaster geographic information data and the disaster buffer zone with the water-related road section to obtain a map of the affected area of ​​waterlogging and a map of motor vehicle traffic conditions.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, it implements the method for evaluating the impact of motor vehicle traffic under urban flooding by fusing multi-source data as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the method for evaluating the impact of motor vehicle traffic under flooding by fusing multi-source data as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the method for evaluating the impact of motor vehicle traffic under flooding by fusing multi-source data as described in any one of claims 1 to 6.

Images