Bridge collision warning method and system based on aerial photograph and storage medium

Abstract

The application discloses a bridge collision early warning method and system based on aerial photographs and a storage medium, and is applied to the technical field of bridge safety, can provide effective data support for bridge anti-collision early warning, and effectively improves the accuracy of bridge anti-collision early warning. The method comprises the following steps: acquiring a plurality of aerial photographs of a channel in a preset range of a target bridge; synthesizing the plurality of aerial photographs to obtain a complete channel map; determining whether the complete channel map meets a preset requirement, and slicing the complete channel map to obtain channel slice resources; wherein the preset requirement comprises that the complete channel map is complete in terms of water surface feature points; constructing a channel slice map according to the channel slice resources; and performing bridge collision risk judgment according to the channel slice map and real-time coordinate data of a ship, to obtain an early warning result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bridge safety, and in particular to a bridge collision early warning method and system based on aerial photographs and a storage medium. BACKGROUND

[0002] Waterway transportation has the advantages of low cost, small pollution, safety and economy, and thus becomes a relatively optimal transportation mode for goods transportation. In recent years, waterway transportation has developed rapidly, and more and more ships are sailing in river channels or shipping waters. With the increase in the number of sailing ships, ship-bridge collision events also occur frequently. In the related art, the collision risk of a ship is usually evaluated by manual operation, which is difficult to discover and effectively prevent the occurrence of ship-bridge collision accidents in time, and the collision risk of the ship and the bridge is relatively large. SUMMARY

[0003] To solve at least one of the above technical problems, the present application provides a bridge collision early warning method and system based on aerial photographs and a storage medium, which can provide effective data support for bridge collision early warning and effectively improve the accuracy of bridge collision early warning.

[0004] In one aspect, the present application provides a bridge collision early warning method based on aerial photographs, comprising the following steps:

[0005] Obtaining a plurality of aerial photographs of a channel in a preset range of a target bridge;

[0006] Synthesizing the plurality of aerial photographs to obtain a complete channel map;

[0007] Determining that the complete channel map meets a preset requirement, and slicing the complete channel map to obtain a channel slice resource; wherein the preset requirement includes complete water surface feature points of the complete channel map;

[0008] Constructing a channel slice map according to the channel slice resource;

[0009] Judging a bridge collision risk according to the channel slice map and real-time coordinate data of a ship to obtain a warning result.

[0010] According to the bridge collision early warning method based on aerial photographs, the following beneficial effects are achieved: the embodiment first acquires a plurality of aerial photographs in a preset range of a target bridge, and obtains a complete waterway map in the preset range of the target bridge in a manner of synthesizing the acquired plurality of aerial photographs. Then, after determining that the water surface feature points of the synthesized complete waterway map are complete, the complete waterway map is sliced to obtain waterway slice resources, and a waterway slice map is constructed according to the waterway slice resources, thereby effectively improving the accuracy of the waterway map and relieving the problem of a large early warning result error caused by a large error between the waterway map and the actual waterway. Then, the embodiment judges the collision risk between a ship and a bridge according to the waterway slice map and real-time coordinate data of the ship, and obtains an early warning result, thereby providing effective data support for bridge anti-collision early warning and effectively improving the accuracy of bridge anti-collision early warning.

[0011] According to some embodiments of the present application, the waterway in the preset range of the target bridge includes a preset upstream waterway, a preset downstream waterway and a preset waterway shore;

[0012] The acquiring of the plurality of aerial photographs of the waterway in the preset range of the target bridge includes:

[0013] The plurality of aerial photographs of the preset upstream waterway, the preset downstream waterway and the preset waterway shore of the target bridge are acquired by a drone.

[0014] According to some embodiments of the present application, during the execution of the step of determining that the complete waterway map meets the preset requirement and slicing the complete waterway map to obtain waterway slice resources, the method further includes:

[0015] Determining that the complete waterway map does not meet the preset requirement, and repairing the water surface feature points.

[0016] According to some embodiments of the present application, the repairing of the water surface feature points includes:

[0017] Converting the complete waterway map into a label image file format to obtain a label image file format waterway map;

[0018] Determining a feature missing area in the label image file format waterway map, to obtain the feature missing area;

[0019] Constructing a shape surface according to the feature missing area; wherein the shape surface wraps the feature missing area;

[0020] Converting the shape surface into a first label image file format image;

[0021] The first label image file format image is valued by a grid calculation function to obtain a second label image file format image;

[0022] The wave band number of the second label image file format image is determined to be the same as that of the label image file format channel chart, and the second label image file format image and the label image file format channel chart are inlaid to obtain a target channel chart.

[0023] According to some embodiments of the present application, the complete channel chart is sliced to obtain a channel slice resource, including:

[0024] The complete channel chart is pyramid-sliced by a network Mercator projection algorithm to obtain the channel slice resource.

[0025] According to some embodiments of the present application, the bridge collision risk is judged according to the channel slice map and real-time coordinate data of a ship to obtain a warning result, including:

[0026] The ship coordinate data of the ship is obtained in real time by a radar;

[0027] Channel coordinate data of the channel is obtained according to the channel slice map; wherein the ship coordinate data and the channel coordinate data are both longitude and latitude coordinate data;

[0028] The ship navigation state is judged according to the ship coordinate data and the channel coordinate data; wherein the ship navigation state includes ship yawing and normal ship navigation;

[0029] The collision risk of the ship and the target bridge is judged according to the ship navigation state to obtain the warning result.

[0030] According to some embodiments of the present application, before the step of constructing a channel slice map according to the channel slice resource is performed, the method further includes:

[0031] A map tile service is published according to the channel slice resource;

[0032] The channel slice map is constructed according to the channel slice resource, including:

[0033] The channel slice resource is obtained from the map tile service by a website request;

[0034] The channel slice resource is added to a tile layer to obtain a first layer;

[0035] The first layer and a map are constructed to obtain the channel slice map.

[0036] In another aspect, the embodiment of the present application also provides a bridge collision early warning system based on aerial photographs, comprising:

[0037] An acquisition module is configured to acquire a plurality of aerial photographs of a channel within a preset range of a target bridge;

[0038] A synthesis module is configured to synthesize the plurality of aerial photographs to obtain a complete channel map;

[0039] A slicing module is configured to determine that the complete channel map meets a preset requirement, and slice the complete channel map to obtain a channel slice resource; wherein the preset requirement comprises that a water surface feature point of the complete channel map is complete;

[0040] A construction module is configured to construct a channel slice map according to the channel slice resource;

[0041] An early warning module is configured to perform bridge collision risk judgment according to the channel slice map and real-time coordinate data of a ship, and obtain an early warning result.

[0042] In another aspect, the embodiment of the present application also provides a bridge collision early warning system based on aerial photographs, comprising:

[0043] At least one processor;

[0044] At least one memory is configured to store at least one program;

[0045] When the at least one program is executed by the at least one processor, the at least one processor is caused to implement the bridge collision early warning method based on aerial photographs as described in the above embodiment.

[0046] In another aspect, the embodiment of the present application also provides a computer storage medium, wherein a program executable by a processor is stored, and the program executable by the processor is used to implement the bridge collision early warning method based on aerial photographs when executed by the processor. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 is a flow chart of the bridge collision early warning method based on aerial photographs provided by the embodiment of the present application;

[0048] Figure 2 is a principle block diagram of the bridge collision early warning system based on aerial photographs provided by the embodiment of the present application. DETAILED DESCRIPTION

[0049] The embodiments described in the embodiments of the present application should not be regarded as limitations of the present application, and all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0050] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" can be the same subset or different subsets as each other and can be combined with each other, without conflict.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to be limiting of this application.

[0052] In recent years, with the maturation of satellite positioning systems, the improvement of electronic and radio control technology, and the emergence of multi-rotor unmanned aerial vehicle structures, the unmanned aerial vehicle industry has entered a rapid development stage. At present, unmanned aerial vehicles have become an important tool for commercial, government and consumer applications, and are widely used in construction, oil, agriculture and public utility fields. With the rapid development of water transportation, more and more ships sail in the river or shipping waters. And with the increase of sailing ships, ship and bridge collision accidents also occur frequently. In the related art, there is a lack of effective bridge active anti-collision early warning measures in the management process of the bridge, and the ship collision risk is usually judged by manual judgment, which has low accuracy of the judgment result and cannot complete the prompt warning work, so it is difficult to discover and effectively prevent the occurrence of ship-bridge collision accidents in time, and the collision risk of the ship and the bridge is large.

[0053] Based on this, one embodiment of the present application provides a bridge collision early warning method and system based on aerial photographs and a storage medium, which can provide effective data support for bridge anti-collision early warning and effectively improve the accuracy of bridge anti-collision early warning. Referring to Figure 1 The method of the embodiment of the present application includes but is not limited to steps S110, S120, S130, S140 and S150.

[0054] Specifically, the application process of the method of the embodiment of the present application includes but is not limited to the following steps:

[0055] S110: Obtain several aerial photographs of the waterway in the preset range of the target bridge.

[0056] S120: Synthesize the several aerial photographs to obtain a complete waterway map.

[0057] S130: Determine whether the complete waterway map meets the preset requirements, and slice the complete waterway map to obtain a waterway slice resource. The preset requirements include that the water surface feature points of the complete waterway map are complete.

[0058] S140: Construct a waterway slice map according to the waterway slice resource.

[0059] S150: judging the bridge collision risk according to the channel slice map and the real-time coordinate data of the ship, and obtaining a warning result.

[0060] In the working process of the embodiment, the embodiment first acquires a plurality of aerial photographs of the channel in the preset range of the target bridge. Specifically, the embodiment acquires a plurality of aerial photographs of the channel in the preset range around the target bridge. The plurality of acquired aerial photographs include complete feature information of the channel in the preset range of the target bridge, so as to restore the channel in the preset range of the target bridge by using the plurality of acquired aerial photographs. For example, a plurality of aerial photographs of a region with the target bridge as the center and a preset distance as the radius are acquired, and these aerial photographs cover the channel in the preset range of the target bridge. Further, the embodiment synthesizes the plurality of acquired aerial photographs to obtain a complete channel map. After acquiring the plurality of aerial photographs, the embodiment synthesizes the aerial photographs in the form of picture merging, thereby obtaining a complete map of the channel in the preset range of the target bridge, i.e., a complete channel map. For example, in some embodiments of the application, after acquiring the plurality of aerial photographs, the aerial photographs are synthesized into a complete picture by using the web version of Open Drone Map, thereby obtaining the complete channel map. Then, when it is determined that the synthesized complete channel map meets the preset requirements, the complete channel map is sliced to obtain channel slice resources. Specifically, the water feature points in the synthesized complete channel map need to be complete. Before slicing, the embodiment needs to determine whether there is a problem of missing water feature points in the synthesized complete channel map. When it is determined that the water feature points in the complete channel map are complete, the complete channel map is sliced, thereby effectively alleviating the problem of channel data loss caused by missing water feature points, and effectively improving the reliability of the channel data. Further, the embodiment constructs a channel slice map according to the channel slice resources. The embodiment constructs a channel slice map in the preset range of the target bridge by using the channel slice resources, so as to effectively improve the cache efficiency of the system by using the channel slice map. Then, the embodiment judges the bridge collision risk according to the channel slice map and the real-time coordinate data of the ship, and obtains a warning result. In the embodiment, the collision risk of the current ship and the target bridge is judged by constructing a channel slice map with high precision and combining the real-time coordinate data of the ship, thereby obtaining a warning result, providing effective data support for bridge anti-collision warning, and effectively improving the accuracy of bridge anti-collision warning.

[0061] In some embodiments of the application, the channel in the preset range of the target bridge includes a preset upstream channel, a preset downstream channel, and a preset channel bank. Acquiring a plurality of aerial photographs of the channel in the preset range of the target bridge includes but is not limited to:

[0062] The plurality of aerial photographs of the preset upstream channel, the preset downstream channel, and the preset channel bank of the target bridge are acquired by using a drone.

[0063] In the embodiment, the channel in the preset range of the target bridge includes a preset upstream channel of the target bridge, a preset downstream channel of the target bridge, and a preset channel bank. Specifically, the embodiment obtains aerial photographs of the channel in the preset range of the target bridge by using the unmanned aerial vehicle. The aerial photographs obtained in the embodiment include aerial photographs of the preset channel bank, the preset upstream channel, and the preset downstream channel. In the process of synthesizing the aerial photographs, it is necessary to ensure that the complete channel map contains complete feature data of the channel. If the data of the preset channel bank is missing in the obtained aerial photographs, the problem of missing part of the feature data of the channel may occur. In the embodiment, several aerial photographs of the preset upstream channel, the preset downstream channel, and the preset channel bank of the target bridge are obtained by using the unmanned aerial vehicle, so as to obtain a complete channel map containing complete information of the channel. For example, most of the coordinate systems used by map manufacturers at present are GCJ-02 coordinate systems converted from geodetic coordinate systems (WGS-84). The latitude and longitude coordinate data of the target ship obtained by the radar is also in the WGD-84 coordinate system, and needs to be converted before being judged, which introduces calculation errors in the conversion process. In the embodiment, the coordinate system of the unmanned aerial vehicle is set as the WSG-84 coordinate system, and the flight mode is set as the 2D aerial photograph mode. Then, the aerial flight area of the unmanned aerial vehicle is set, so that the unmanned aerial vehicle can obtain the aerial photographs of the preset upstream channel, the preset downstream channel, and the preset channel bank. After setting the flight area of the unmanned aerial vehicle, the distortion calibration of the camera is opened, and the relative height is set before the shooting operation.

[0064] In some embodiments of the application, in the process of performing the step of determining that the complete channel map meets the preset requirements and slicing the complete channel map to obtain a channel slice resource, the bridge collision warning method based on aerial photographs provided in the embodiment further includes but is not limited to:

[0065] determining that the complete channel map does not meet the preset requirements, and repairing the water feature points.

[0066] In the embodiment, when it is determined that the complete channel map does not meet the preset requirements, the water feature points are repaired. Specifically, after synthesizing the several aerial photographs, it is necessary to judge the synthesized complete channel map to determine whether the water feature points of the complete channel map are missing. When it is determined that the synthesized complete channel map does not meet the preset requirements, that is, the water feature points of the complete channel map are missing, the water feature points in the complete channel map need to be repaired to alleviate the problems of data missing in the channel slice map and inaccurate warning results caused by the missing water feature points in the complete channel map.

[0067] In some embodiments of the present application, the water surface feature points are repaired, including but not limited to:

[0068] The complete channel map is converted into a label image file format, and a label image file format channel map is obtained.

[0069] The area where the water surface feature points are missing in the label image file format channel map is determined, and a feature missing area is obtained.

[0070] A shape surface is constructed according to the feature missing area. The shape surface wraps the feature missing area.

[0071] The shape surface is converted into a first label image file format image.

[0072] The first label image file format image is valued by a grid calculation function, and a second label image file format image is obtained.

[0073] It is determined that the number of bands of the second label image file format image and the label image file format channel map is the same, and the second label image file format image and the label image file format channel map are inlaid to obtain a target channel map.

[0074] In the embodiment, the embodiment first converts the picture format of the complete waterway map with missing water surface feature points into a tag image file format (TIFF), to obtain a tag image file format waterway map. Then, the embodiment determines the location of the region with missing water surface feature points, i.e., the feature missing region, in the tag image file format waterway map. There can be multiple feature missing regions. Next, the embodiment constructs a shape surface according to the determined feature missing region. Specifically, the constructed shape surface in the embodiment wraps the feature missing region. When there are multiple feature missing regions, a corresponding shape surface is constructed for each feature missing region. It should be noted that in some embodiments of the application, the construction of the shape surface can be constructed manually or autonomously constructed through a deep learning algorithm. Further, the embodiment converts the constructed shape surface into a first tag image file format image, so that the format of the shape surface is consistent with the format of the tag image file format waterway map obtained after conversion. At the same time, the embodiment assigns values to the first tag image file format image through a grid calculation function to obtain a second tag image file format image. For example, the embodiment assigns values to the first tag image file format image through the Con method, to assign values by performing judgment condition evaluation on each input image source of the input grid, thereby obtaining a second tag image file format. Further, the embodiment determines that the number of bands of the second tag image file format image and the tag image file format waterway map is the same, and then mosaics the second tag image file format image and the tag image file format waterway map to obtain a target waterway map. Specifically, before mosaicking the second tag image file format image and the tag image file format waterway map, it is necessary to determine whether the number of bands of the two is consistent. When the number of bands of the second tag image file format image and the tag image file format waterway map is different, the mosaicking operation cannot be performed. The embodiment determines that the number of bands of the two is consistent, and then performs the mosaicking operation, thereby completing the repair of the water surface feature points. It should be noted that when it is determined that the number of bands of the two is inconsistent, the embodiment needs to adjust the number of bands of the second tag image file format image and the tag image file format waterway map. For example, the number of bands is cut through Composite bands, or the initial tag image file format waterway map is saved again, and the corresponding number of bands is selected when saving.

[0075] Exemplarily, in some embodiments of the present application, the missing water feature points are repaired by ArcGIS. After importing the label image file format channel map into ArcMap, the shp surface, i.e. shape surface, of the missing area of the water feature points in the label image file format channel map is manually drawn, and the drawn shp surface is converted into a corresponding tif image to obtain a first label image file format image. Then, the first label image file format image is valued by the Con method to obtain a second label image file format image. Then, the second label image file format image is inlaid with the label image file format channel map to obtain the repaired target channel map.

[0076] In some embodiments of the present application, the complete channel map is sliced to obtain channel slice resources, including but not limited to:

[0077] The complete channel map is pyramid-sliced by the network Mercator projection algorithm to obtain the channel slice resources.

[0078] In the specific embodiment, the complete channel map is pyramid-sliced by the network Mercator projection algorithm to obtain the channel slice resources. Specifically, the specific formula for pyramid slicing by the network Mercator projection algorithm in the embodiment is shown in the following formula (1) and formula (2):

[0079]

[0080]

[0081] wherein λ represents the longitude in radian, φ represents the geodetic latitude in radian, zoom level represents the zoom level, the minimum zoom level is 0, representing the zoom level when the whole earth is displayed, and pixels are the unit of pixels.

[0082] Exemplarily, in the embodiment, the tile size is usually 256*256 pixels, and the minimum level of the map is 0. When zoom level=0, the data in the longitude [-180°, 180°] and latitude [-85.051129°, 85.051129°] interval can be projected on a 256*256 pixel picture, and the map tile at a certain zoom level is composed of 4 tiles at the previous level, forming a tile pyramid. Among them, the zoom level resolution is linearly changed, while the resolution of the unmanned aerial vehicle aerial photograph is linearly changed with the height. Therefore, the zoom level and the unmanned aerial vehicle aerial photograph height are also linearly changed. The detection distance formula of the unmanned aerial vehicle at different heights is shown in the following formula (3):

[0083]

[0084] wherein h1, h2 are different flight heights of the UAV, x1, x2 are lateral detection distances of the UAV at different flight heights, h1 and x1 are perpendicular to each other to form a first triangle, h2 and x2 are perpendicular to each other to form a second triangle, the first triangle and the second triangle are in a similar triangle relationship.

[0085] Further, the formula of the zoom level that can be cut is shown as formula (4) below:

[0086]

[0087] wherein x represents the lateral resolution of the picture.

[0088] Correspondingly, when the picture lateral resolution of x1 is 1000 pixels, the relationship between the zoom level and the flight height of the UAV can be obtained as shown in formula (5) below:

[0089]

[0090] From the above formula (5), it can be seen that when the flight height h2 of the UAV increases, the level zoom level that can be cut also increases, and the flight height of the UAV and the zoom level are in a positive correlation relationship.

[0091] In some embodiments of the present application, the bridge collision risk is judged according to the channel slicing map and the real-time coordinate data of the ship, and the early warning result is obtained, including but not limited to:

[0092] The ship coordinate data of the ship is obtained in real time by radar.

[0093] The channel coordinate data of the channel is obtained according to the channel slicing map. The ship coordinate data and the channel coordinate data are both longitude and latitude coordinate data.

[0094] The ship navigation state is judged according to the ship coordinate data and the channel coordinate data. The ship navigation state includes ship yaw and normal ship navigation.

[0095] The collision risk of the ship and the target bridge is judged according to the ship navigation state, and the early warning result is obtained.

[0096] In the embodiment, the ship position coordinates are monitored in real time by the radar first, and the coordinate data of the ship, i.e., the ship coordinate data, is obtained. Then, the channel coordinate data of the channel is obtained according to the constructed channel slice map. In some embodiments of the application, the WMTS service conforming to the OGC standard is published after the slicing is completed. After the web page loads the WMTS service, the coordinates of each point in the constructed channel slice map can be obtained from the page, and the channel in the map is plotted in the channel slice map, and the corresponding channel coordinate data is obtained. The channel coordinate data and the ship coordinate data obtained by the radar are both longitude and latitude coordinate data. Then, the ship navigation state is determined according to the ship coordinate data and the channel coordinate data. Specifically, the ship coordinate data and the channel coordinate data obtained by the radar in real time are compared by a preset algorithm to determine the current navigation state of the ship. The ship navigation state includes ship yaw and normal ship navigation. Further, the collision risk of the ship and the bridge is determined according to the ship navigation state to obtain a warning result. It is easy to understand that when the ship is normally navigated, the collision risk of the ship and the bridge is small, and when the ship is yawed, the collision risk of the ship and the bridge is high. At the same time, when the ship is yawed, the angle of yaw and the current speed of the ship will affect the collision risk of the ship and the bridge. In some embodiments of the application, the collision risk coefficient of the ship and the bridge is obtained according to the yaw angle of the ship and the current speed of the ship, and the collision avoidance decision of the ship and the bridge is generated.

[0097] In some embodiments of the application, before the step of constructing the channel slice map according to the channel slice resource, the bridge collision warning method based on the aerial photograph provided by the embodiment further includes but is not limited to:

[0098] The map tile service is published according to the channel slice resource.

[0099] The channel slice map is constructed according to the channel slice resource, including but not limited to:

[0100] The channel slice resource is obtained from the map tile service by a web address request.

[0101] The channel slice resource is added to the tile layer to obtain a first layer.

[0102] The channel slice map is constructed according to the first layer and the map.

[0103] In the embodiment, the embodiment publishes a corresponding map tile service (Web Map Tile Service, WMTS) according to the channel slice resource before constructing the channel slice map, so that the system can directly access the corresponding channel slice resource through a web page. Then, the embodiment obtains the channel slice resource from the published map tile service through a website request, and adds the channel slice resource to the slice layer to construct a first layer. Further, the embodiment combines the first layer with corresponding map data to obtain the channel slice map. For example, in some embodiments of the application, the complete channel map is pyramid sliced by GeoServer to obtain the channel slice resource. At the same time, after the slicing is completed, the WMTS service conforming to the OGC (Open Geospatial Consortium) standard is published to load the map tile through OpenLayers. The WMTS component in OpenLayers requests the cache data of the WMTS service through the url, obtains the data of the channel slice resource, and adds the data to the layer Tile to obtain the corresponding tile layer, i.e., the first layer. Then, the first layer is added to the map, the tile layer is overlaid on the map to obtain the channel slice map, and the pyramid slicing data is realized in the page.

[0104] One embodiment of the application also provides a bridge collision early warning system based on aerial photographs, which comprises:

[0105] An acquisition module is configured to acquire a plurality of aerial photographs of a channel within a preset range of a target bridge.

[0106] A synthesis module is configured to synthesize the plurality of aerial photographs to obtain a complete channel map.

[0107] A slicing module is configured to determine whether the complete channel map meets a preset requirement, and slice the complete channel map to obtain channel slice resources. The preset requirement comprises that a water surface feature point of the complete channel map is complete.

[0108] A construction module is configured to construct a channel slice map according to the channel slice resources.

[0109] An early warning module is configured to determine a bridge collision risk according to the channel slice map and real-time coordinate data of a ship, and obtain an early warning result.

[0110] Reference Figure 2 One embodiment of the application also provides a bridge collision early warning system based on aerial photographs, which comprises:

[0111] At least one processor 210.

[0112] At least one memory 220 is configured to store at least one program.

[0113] When the at least one program is executed by the at least one processor 210, the at least one processor 210 implements the aerial photograph-based bridge collision warning method as described in the above embodiments.

[0114] One embodiment of the present application also provides a computer readable storage medium storing computer executable instructions, which are executed by one or more control processors, for example, to perform the steps described in the above embodiments.

[0115] Those skilled in the art can understand that all or some of the steps in the above disclosed method and system can be implemented as software, firmware, hardware and appropriate combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software can be distributed on a computer readable medium, which can include computer storage media (or non-transitory media) and communication media (or transitory media). As known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, it is known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.

[0116] The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the present application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the present application.

Claims

1. A bridge collision early warning method based on aerial photographs, characterized in that, Includes the following steps: Acquire several aerial photographs of the waterway within a preset range of the target bridge; The aforementioned aerial photographs are combined to obtain a complete waterway map; Once it is determined that the complete waterway map meets preset requirements, the complete waterway map is sliced ​​to obtain waterway slice resources; wherein, the preset requirements include that the water surface feature points of the complete waterway map are complete; Construct a waterway slice map based on the waterway slice resources; Based on the aforementioned waterway slice map and real-time coordinate data of ships, a bridge collision risk assessment is conducted to obtain early warning results; The method further includes the following steps in the process of determining that the complete waterway map meets preset requirements and slicing the complete waterway map to obtain waterway slice resources: If the complete waterway map does not meet the preset requirements, the water surface feature points are repaired. The repair of the water surface feature points includes: The complete waterway map is converted into a labeled image file format to obtain a waterway map in labeled image file format; The region where the water surface feature points are missing in the waterway map of the labeled image file format is determined to obtain the feature missing region; A shape surface is constructed based on the feature-missing region; wherein the shape surface encloses the feature-missing region; Convert the shape surface into an image in the first label image file format; The first tag image file format image is assigned a value by a raster calculation function to obtain the second tag image file format image; The second tag image file format image and the tag image file format waterway map are determined to have the same number of bands. The second tag image file format image and the tag image file format waterway map are then mosaicked to obtain the target waterway map. The step of assessing bridge collision risk based on the waterway slice map and real-time coordinate data of ships to obtain early warning results includes: The waterway coordinate data is obtained from the waterway slice map; wherein, both the ship coordinate data and the waterway coordinate data are latitude and longitude coordinate data; The ship's navigation status is determined based on the ship's coordinate data and the waterway coordinate data; wherein, the ship's navigation status includes ship yaw and ship normal navigation; The collision risk between the ship and the target bridge is determined based on the ship's navigation status, and the early warning result is obtained.

2. The bridge collision early warning method based on aerial photographs according to claim 1, characterized in that, The waterway within the preset range of the target bridge includes the preset upstream waterway, the preset downstream waterway, and the preset waterway bank; The acquisition of several aerial photographs of the waterway within a preset range of the target bridge includes: Several aerial photographs of the predetermined upstream channel, the predetermined downstream channel, and the shoreline of the predetermined channel, including the target bridge, were acquired using drones.

3. The bridge collision early warning method based on aerial photographs according to claim 1, characterized in that, The step of slicing the complete waterway map to obtain waterway slice resources includes: The complete waterway map is sliced ​​into pyramids using the network Mercator projection algorithm to obtain the waterway slice resources.

4. The bridge collision early warning method based on aerial photographs according to claim 1, characterized in that, Before performing the step of constructing a waterway tile map based on the waterway tile resources, the method further includes: Publish map tile services based on the aforementioned waterway slice resources; The step of constructing a waterway tile map based on the waterway tile resources includes: The waterway slice resource is obtained from the map tile service by requesting a URL; Add the waterway slice resources to the tile layer to obtain the first layer; The waterway slice map is constructed based on the first layer and the map.

5. A bridge collision early warning system based on aerial photographs, characterized in that, include: The acquisition module is used to acquire several aerial photographs of the waterway within a preset range of the target bridge; The compositing module is used to combine the several aerial photographs to obtain a complete airway map; The slicing module is used to determine whether the complete waterway map meets preset requirements, and to slice the complete waterway map to obtain waterway slice resources; wherein, the preset requirements include that the water surface feature points of the complete waterway map are complete; The construction module is used to construct a waterway slice map based on the waterway slice resources; The early warning module is used to assess the risk of bridge collision based on the waterway slice map and the real-time coordinate data of the ships, and to obtain an early warning result. The process of determining that the complete waterway map meets preset requirements and slicing the complete waterway map to obtain waterway slice resources further includes: If the complete waterway map does not meet the preset requirements, the water surface feature points are repaired. The repair of the water surface feature points includes: The complete waterway map is converted into a labeled image file format to obtain a waterway map in labeled image file format; The region where the water surface feature points are missing in the waterway map of the labeled image file format is determined to obtain the feature missing region; A shape surface is constructed based on the feature-missing region; wherein the shape surface encloses the feature-missing region; Convert the shape surface into an image in the first label image file format; The first tag image file format image is assigned a value by a raster calculation function to obtain the second tag image file format image; The second tag image file format image and the tag image file format waterway map are determined to have the same number of bands. The second tag image file format image and the tag image file format waterway map are then mosaicked to obtain the target waterway map. The step of assessing bridge collision risk based on the waterway slice map and real-time coordinate data of ships to obtain early warning results includes: The waterway coordinate data is obtained from the waterway slice map; wherein, both the ship coordinate data and the waterway coordinate data are latitude and longitude coordinate data; The ship's navigation status is determined based on the ship's coordinate data and the waterway coordinate data; wherein, the ship's navigation status includes ship yaw and ship normal navigation; The collision risk between the ship and the target bridge is determined based on the ship's navigation status, and the early warning result is obtained.

6. A bridge collision early warning system based on aerial photographs, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the bridge collision warning method based on aerial images as described in any one of claims 1 to 4.

7. A computer storage medium storing a processor-executable program, characterized in that, The program executable by the processor, when executed by the processor, is used to implement the bridge collision warning method based on aerial images as described in any one of claims 1 to 4.

Images