Mapping method and device for viaduct area and vehicle positioning method and device thereof

Abstract

The application discloses a method and device for mapping an overpass area and a vehicle positioning method and device thereof. The method comprises the following steps: acquiring mapping data of the overpass area sent by a vehicle terminal, wherein the mapping data comprises road images of the overpass area, inertial navigation positioning data and a navigation route corresponding to the overpass area; based on the inertial navigation positioning data, extracting features of the road images of the overpass area by using a preset feature extraction model to obtain feature data of the overpass area; based on the navigation route, matching the feature data of the overpass area by using a preset feature matching strategy; and constructing a feature map of the overpass area according to the feature matching result. The application collects sufficient feature data for the overpass area, and realizes self-labeling of the feature data based on a navigation route provided by a map navigation tool of the vehicle terminal. The feature map of the overpass area constructed in this way can provide effective support for subsequent vehicle positioning in the overpass area, and guarantee the travel experience of users.

Description

Technical Field

[0001] This application relates to the field of mapping and positioning technology for elevated bridge areas, and in particular to a mapping method and apparatus for elevated bridge areas, and a vehicle positioning method and apparatus thereof. Background Technology

[0002] Most vehicles are equipped with cameras and map navigation software, but due to limitations in onboard computing power, they generally lack high-precision maps. When these vehicles enter elevated highway areas, GPS (Global Positioning System) positioning can deviate due to obstructions from the elevated highway and the influence of nearby tall buildings, especially in parallel elevated highway areas, where it cannot accurately determine whether it is on or below the elevated highway. Therefore, accurate identification of elevated highways can help vehicles promptly detect deviations during driving, allowing them to quickly find the correct route.

[0003] For the identification and positioning of elevated bridge areas, existing solutions mainly use image recognition classification to determine whether a vehicle is on or under the elevated bridge. However, this identification method is bound to have false positives, and its output result is either on or under the elevated bridge. The output result of this classification model is not interpretable. Moreover, in many cities, there are situations where vehicles are already on the bridge, but there is still a bridge above the vehicles, such as elevated bridges for oncoming traffic. Obviously, this solution cannot provide accurate identification results.

[0004] In addition, existing solutions use accelerometers and gyroscopes in an IMU (Inertial Measurement Unit) to calculate the vehicle's uphill and downhill status, but IMU data contains noise and causes cumulative errors, especially on gentle slopes, making it impossible to accurately distinguish.

[0005] Therefore, the above scheme has a high false detection rate for identifying and locating elevated bridge areas. Once a false detection occurs and causes the map to deviate, it will affect the user's travel experience. Summary of the Invention

[0006] This application provides a mapping method and apparatus for elevated bridge areas, as well as a vehicle positioning method and apparatus thereon, to improve the accuracy of vehicle positioning in elevated bridge areas.

[0007] The embodiments of this application adopt the following technical solutions:

[0008] In a first aspect, embodiments of this application provide a mapping method for an elevated bridge area, wherein the mapping method for the elevated bridge area includes:

[0009] Acquire mapping data of the elevated bridge area sent by the vehicle terminal. The mapping data of the elevated bridge area includes road images of the elevated bridge area, inertial navigation positioning data, and the navigation route of the vehicle terminal in the elevated bridge area.

[0010] Based on the inertial navigation positioning data of the elevated bridge area, feature extraction is performed on the road image of the elevated bridge area using a preset feature extraction model to obtain feature data of the elevated bridge area.

[0011] Based on the navigation route of the vehicle in the elevated bridge area, the feature data of the elevated bridge area is matched using a preset feature matching strategy to obtain the feature matching result of the elevated bridge area.

[0012] A feature map of the elevated bridge area is constructed based on the feature matching results of the elevated bridge area.

[0013] Optionally, the step of extracting features from the road image of the elevated bridge area using a preset feature extraction model based on the inertial navigation positioning data of the elevated bridge area to obtain the feature data of the elevated bridge area includes:

[0014] Based on the road images and inertial navigation positioning data of the elevated bridge area, key frame images of the elevated bridge area are determined;

[0015] The keyframe images of the elevated bridge area are used to extract features using a preset feature extraction model to obtain keyframe feature data of the elevated bridge area.

[0016] Optionally, the step of matching the feature data of the elevated bridge area based on the navigation route corresponding to the elevated bridge area by the vehicle terminal and using a preset feature matching strategy to obtain the feature matching result of the elevated bridge area includes:

[0017] Based on the navigation route of the vehicle in the elevated bridge area, determine whether the amount of feature data of the elevated bridge area meets the preset mapping conditions.

[0018] If the amount of feature data in the elevated bridge area meets the preset mapping conditions, the feature data in the elevated bridge area is matched using the preset feature matching strategy to obtain the feature matching result of the elevated bridge area.

[0019] Optionally, the mapping data for the elevated bridge area also includes intersection markers corresponding to the elevated bridge area. The step of matching the feature data of the elevated bridge area using a preset feature matching strategy based on the navigation route corresponding to the elevated bridge area from the vehicle's navigation system, to obtain the feature matching result for the elevated bridge area, includes:

[0020] Based on the navigation route of the vehicle in the elevated bridge area, the feature data type corresponding to the feature data of the elevated bridge area is determined. The feature data type includes bridge feature data and under-bridge feature data.

[0021] Determine the correspondence between the feature data of the elevated bridge area, the type of feature data, and the intersection identifiers corresponding to the elevated bridge area;

[0022] Based on the correspondence between the feature data of the elevated bridge area, the feature data type, and the intersection identifiers corresponding to the elevated bridge area, the feature data of the elevated bridge area is matched using the preset feature matching strategy to obtain the feature matching result of the elevated bridge area.

[0023] Optionally, the bridge feature data and the under-bridge feature data each include multiple sets. The matching of the feature data of the elevated bridge area based on the correspondence between the feature data of the elevated bridge area, the feature data type, and the intersection identifiers corresponding to the elevated bridge area, using the preset feature matching strategy, to obtain the feature matching result of the elevated bridge area includes:

[0024] Perform feature matching between any two sets of bridge feature data to obtain the bridge feature matching results;

[0025] Perform feature matching between any two sets of under-bridge feature data to obtain the under-bridge feature matching results;

[0026] If the feature matching results on the bridge meet the preset feature matching requirements on the bridge, and the feature matching results under the bridge meet the preset feature matching requirements under the bridge, the feature matching results of the viaduct area are determined based on the feature matching results on the bridge and the feature matching results under the bridge.

[0027] Optionally, constructing a feature map of the elevated bridge area based on the feature matching results of the elevated bridge area includes:

[0028] Based on the feature matching results of the elevated bridge area, the successfully matched feature data are determined;

[0029] Determine the location of the elevated bridge area corresponding to the successfully matched feature data, and filter the successfully matched feature data according to the location of the elevated bridge area corresponding to the successfully matched feature data to obtain the filtered feature data;

[0030] A feature map of the elevated bridge area is constructed based on the filtered feature data.

[0031] Secondly, embodiments of this application also provide a vehicle positioning method for an elevated bridge area, wherein the vehicle positioning method for an elevated bridge area includes:

[0032] The vehicle receives a feature map acquisition request for the elevated bridge area sent by the vehicle terminal. The feature map acquisition request for the elevated bridge area includes the intersection identifiers corresponding to the elevated bridge area.

[0033] Based on the intersection signs corresponding to the elevated bridge area, determine the feature map of the corresponding elevated bridge area;

[0034] The current road image sent by the vehicle is acquired, and the current road image is extracted using a preset feature extraction model to obtain the feature data of the current road image.

[0035] The feature data of the current road image is matched with the feature map of the elevated bridge area to obtain the vehicle positioning result of the elevated bridge area;

[0036] The feature map of the elevated bridge area is constructed based on any of the aforementioned mapping methods for elevated bridge areas.

[0037] Optionally, after obtaining the vehicle location result for the elevated bridge area based on the feature data of the current road image and the feature map of the elevated bridge area, the method further includes:

[0038] Obtain the navigation route from the vehicle.

[0039] Compare the vehicle location results in the elevated bridge area with the navigation route;

[0040] The comparison results will determine whether the vehicle's navigation route needs to be replanned.

[0041] Thirdly, embodiments of this application also provide a mapping device for an elevated bridge area, wherein the mapping device for the elevated bridge area includes:

[0042] The first acquisition unit is used to acquire mapping data of the elevated bridge area sent by the vehicle terminal. The mapping data of the elevated bridge area includes road images of the elevated bridge area, inertial navigation positioning data, and the navigation route of the vehicle terminal in the elevated bridge area.

[0043] The first feature extraction unit is used to extract features from the road image of the elevated bridge area based on the inertial navigation positioning data of the elevated bridge area and using a preset feature extraction model to obtain the feature data of the elevated bridge area.

[0044] The first matching unit is used to match the feature data of the elevated bridge area based on the navigation route corresponding to the vehicle terminal in the elevated bridge area using a preset feature matching strategy, so as to obtain the feature matching result of the elevated bridge area.

[0045] The construction unit is used to construct a feature map of the elevated bridge area based on the feature matching results of the elevated bridge area.

[0046] Fourthly, embodiments of this application also provide a vehicle positioning device for an elevated bridge area, wherein the mapping device for the elevated bridge area includes:

[0047] The second acquisition unit is used to acquire a feature map acquisition request for the elevated bridge area sent by the vehicle terminal. The feature map acquisition request for the elevated bridge area includes the intersection identifiers corresponding to the elevated bridge area.

[0048] The first determining unit is used to determine the feature map of the corresponding elevated bridge area based on the intersection signage of the elevated bridge area.

[0049] The second feature extraction unit is used to acquire the current road image sent by the vehicle terminal, and to extract features from the current road image using a preset feature extraction model to obtain feature data of the current road image.

[0050] The second matching unit is used to match the feature data of the current road image with the feature map of the overpass area to obtain the vehicle positioning result of the overpass area.

[0051] The feature map of the elevated bridge area is constructed based on the aforementioned mapping device for the elevated bridge area.

[0052] Fifthly, embodiments of this application also provide an electronic device, including:

[0053] Processor; and

[0054] A memory is configured to store computer-executable instructions, which, when executed, cause the processor to perform any of the aforementioned mapping methods for the viaduct area.

[0055] Sixthly, embodiments of this application also provide a computer-readable storage medium storing one or more programs that, when executed by an electronic device including multiple applications, cause the electronic device to perform any of the aforementioned mapping methods for viaduct areas.

[0056] The above-mentioned technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: The mapping method for elevated bridge areas in the embodiments of this application first acquires the mapping data of the elevated bridge area sent by the vehicle terminal. The mapping data of the elevated bridge area includes road images of the elevated bridge area, inertial navigation positioning data, and the navigation route corresponding to the vehicle terminal in the elevated bridge area. Then, based on the road images and inertial navigation positioning data of the elevated bridge area, feature extraction is performed using a preset feature extraction model to obtain feature data of the elevated bridge area. Afterwards, based on the navigation route corresponding to the vehicle terminal in the elevated bridge area, the feature data of the elevated bridge area is matched using a preset feature matching strategy to obtain the feature matching result of the elevated bridge area. Finally, a feature map of the elevated bridge area is constructed based on the feature matching result of the elevated bridge area. The mapping method for elevated bridge areas in the embodiments of this application collects sufficient feature data for the elevated bridge area and realizes self-annotation of feature data based on the navigation route provided by the map navigation tool provided by the vehicle terminal. The feature map of the elevated bridge area constructed in this way can provide effective support for subsequent vehicle positioning in the elevated bridge area, ensuring that users have a more intelligent travel experience. Attached Figure Description

[0057] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0058] Figure 1 This is a flowchart illustrating a mapping method for an elevated bridge area according to an embodiment of this application.

[0059] Figure 2 This is a schematic diagram illustrating the extraction of keyframe images from an elevated bridge area according to an embodiment of this application.

[0060] Figure 3 This is a flowchart illustrating a vehicle positioning method for an elevated bridge area according to an embodiment of this application.

[0061] Figure 4 This is a flowchart illustrating the feature map construction and localization process for an elevated bridge area in an embodiment of this application.

[0062] Figure 5 This is a schematic diagram of a mapping device for an elevated bridge area according to an embodiment of this application;

[0063] Figure 6 This is a schematic diagram of the structure of a vehicle positioning device in an elevated bridge area according to an embodiment of this application;

[0064] Figure 7 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0066] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0067] This application provides a mapping method for elevated bridge areas, such as... Figure 1 The diagram shows a flowchart of a mapping method for an elevated bridge area according to an embodiment of this application. The mapping method for the elevated bridge area includes at least the following steps S110 to S140:

[0068] Step S110: Obtain mapping data of the elevated bridge area sent by the vehicle terminal. The mapping data of the elevated bridge area includes road images of the elevated bridge area, inertial navigation positioning data, and the navigation route of the vehicle terminal in the elevated bridge area.

[0069] The mapping method for elevated bridge areas in this embodiment can be executed by the cloud. When constructing a map of the elevated bridge area, it is necessary to first acquire mapping data collected by vehicles. These vehicles can be any vehicle that will pass through the same elevated bridge area within a certain period and is capable of communicating with the cloud. Based on its GPS positioning and navigation route, the vehicle can determine whether it is about to arrive at the elevated bridge area. If it is about to arrive, it can first check the cloud to see if a complete feature map corresponding to that elevated bridge area already exists. If not, the subsequent mapping data collection and reporting process is triggered, thereby constructing or updating the feature map corresponding to the elevated bridge area. This data collected and reported by the vehicles is a crucial foundation for cloud-based mapping; that is, the mapping process in this embodiment can be implemented through a "crowdsourcing" approach, resulting in rich data and high collection efficiency. Of course, data can also be collected by a dedicated data collection vehicle; no specific limitation is made here.

[0070] "Elevated road area" can refer to the area formed from the intersection where one is about to enter the elevated road to the point after traveling a predetermined distance along the elevated road or under the bridge. For example, the area corresponding to the distance from 10 meters before the elevated road intersection to 200 meters after traveling along the elevated road or under the bridge can be considered the elevated road area. Of course, those skilled in the art can flexibly adjust the specific size of the elevated road area according to the actual scenario and needs, and no specific limitation is made here.

[0071] The mapping data collected by the vehicle-mounted terminal for the elevated bridge area mainly includes a series of road images of the elevated bridge area, corresponding inertial navigation positioning data, and the navigation route corresponding to the vehicle in the elevated bridge area. The vehicle-mounted terminal can start collecting road images by activating the front camera on the vehicle when it is about to reach the intersection of the elevated bridge, and stop collecting road images after driving a preset distance. During this process, the vehicle-mounted terminal's IMU is also outputting inertial navigation positioning data in real time, including acceleration and angular velocity. Based on its built-in map navigation software, the vehicle-mounted terminal can also obtain the corresponding navigation route when it is about to enter the elevated bridge area. All of this data can be sent to the cloud as the basis for subsequent mapping.

[0072] Step S120: Based on the inertial navigation positioning data of the elevated bridge area, feature extraction is performed on the road image of the elevated bridge area using a preset feature extraction model to obtain feature data of the elevated bridge area.

[0073] Inertial navigation positioning data can reflect the approximate driving status of a vehicle throughout the elevated bridge area. Although relying solely on the inertial navigation positioning data of the IMU for positioning when the GPS positioning signal is poor will result in a certain degree of cumulative error, this embodiment does not use inertial navigation positioning data to determine the uphill and downhill status of the vehicle. Instead, it uses a pre-set feature extraction model to extract features from the road image of the elevated bridge area based on the rough position information calculated from the inertial navigation positioning data, thereby obtaining the feature data of the elevated bridge area.

[0074] The aforementioned preset feature extraction model can be pre-trained based on existing deep learning models. The extracted feature data can specifically include the coordinates of feature points in the road image and the feature descriptor corresponding to each feature point.

[0075] Step S130: Based on the navigation route corresponding to the elevated bridge area by the vehicle, the feature data of the elevated bridge area is matched using a preset feature matching strategy to obtain the feature matching result of the elevated bridge area.

[0076] In most cases, vehicles will follow the navigation routes provided by map navigation software. Therefore, for the navigation routes in the elevated bridge area, it can reflect whether the vehicle is driving on the bridge or under the bridge when it arrives at the elevated bridge area. Therefore, the embodiments of this application can obtain sufficient feature data corresponding to the bridge and under the bridge areas based on the navigation routes corresponding to the elevated bridge area. Then, a preset feature matching strategy is used to perform feature matching on the feature data corresponding to the bridge and under the bridge areas respectively, so as to obtain feature data that correctly and fully represents the characteristics of the bridge and under the bridge areas.

[0077] Step S140: Construct a feature map of the elevated bridge area based on the feature matching results of the elevated bridge area.

[0078] The feature matching results for the elevated bridge area here are mainly feature data with obvious features and good matching effect. Based on these feature data, a feature map of the elevated bridge area can be constructed, thereby providing effective support for the accurate judgment of the position of vehicles that are about to drive into the elevated bridge area.

[0079] The mapping method for elevated bridge areas in this application collects sufficient feature data for the elevated bridge area and implements self-annotation of the feature data based on the navigation route provided by the vehicle's built-in map navigation tool. The feature map of the elevated bridge area constructed in this way can provide effective support for subsequent vehicle positioning in the elevated bridge area, ensuring that users have a more intelligent travel experience.

[0080] In some embodiments of this application, the step of extracting features from the road image of the elevated bridge area using a preset feature extraction model based on the inertial navigation positioning data of the elevated bridge area to obtain the feature data of the elevated bridge area includes: determining the key frame image of the elevated bridge area based on the road image and inertial navigation positioning data of the elevated bridge area; and extracting features from the key frame image of the elevated bridge area using a preset feature extraction model to obtain the key frame feature data of the elevated bridge area.

[0081] Since the road images of the elevated bridge area collected by the vehicle-mounted terminals are continuous multi-frame images over a certain distance, the amount of data collected by multiple vehicle-mounted terminals is often very large. In the actual localization process, it is often not necessary to use the feature data provided by the full amount of road images, which will also affect the efficiency of subsequent matching and localization. Based on this, the embodiments of this application can use a certain keyframe extraction strategy to extract keyframe images from the multi-frame road images of the elevated bridge area collected by each vehicle-mounted terminal for subsequent processing.

[0082] Since the number of road images and their corresponding features collected by each vehicle entering the viaduct area may not be completely consistent—for example, vehicle A might report 20 frames of road images from the viaduct area, while vehicle B might report 22 frames from the same viaduct area—selecting keyframes solely based on the inter-frame interval of the images is inaccurate. Therefore, this embodiment utilizes IMU inertial navigation positioning data to select keyframe images. For instance, the SLAM (Simultaneous Localization and Mapping) algorithm can be used to process the road images and corresponding IMU inertial navigation positioning data. A keyframe can be selected at regular intervals, such as 30 meters. This distance is determined by using the SLAM algorithm to locate the images and the IMU inertial navigation positioning data. Figure 2As shown, a schematic diagram of keyframe image extraction in an elevated bridge area is provided in an embodiment of this application. For all road images collected from entering the elevated bridge area to exiting the elevated bridge area, the above keyframe extraction method can extract keyframe images of 0, 1, 2, ..., n frames at a distance of 30m.

[0083] Finally, the key frame images of the viaduct area are extracted using a preset feature extraction model to obtain key frame feature data of the viaduct area. In order to improve the efficiency of subsequent feature matching, the extracted key frame feature data can be further thinned before being saved.

[0084] In some embodiments of this application, the step of matching feature data of the elevated bridge area based on the navigation route corresponding to the vehicle in the elevated bridge area using a preset feature matching strategy to obtain the feature matching result of the elevated bridge area includes: determining whether the amount of feature data of the elevated bridge area meets the preset mapping conditions based on the navigation route corresponding to the vehicle in the elevated bridge area; and if the amount of feature data of the elevated bridge area meets the preset mapping conditions, matching feature data of the elevated bridge area using the preset feature matching strategy to obtain the feature matching result of the elevated bridge area.

[0085] Since the collection and uploading of mapping data from the vehicle is a gradual process, and the mapping data is also gradually accumulated, the cloud can first determine whether the amount of mapping data for the elevated bridge area currently acquired meets the mapping requirements when constructing a specific feature map. That is, whether it can provide sufficient feature data for subsequent matching and positioning. Of course, the specific data volume requirement can be flexibly set according to the actual scenario and needs. For example, it can be set to consider the data volume sufficient to meet subsequent mapping requirements when 100 sets of mapping data for the elevated bridge area are acquired.

[0086] Furthermore, the data volume corresponding to the area above the bridge and the data volume corresponding to the area below the bridge can be further limited to meet certain requirements. Since the vehicle also reports the navigation route, assuming that the vehicle will normally travel according to the navigation route, it is possible to determine whether the road image collected by the vehicle is a road image of the area above the bridge or the road image of the area below the bridge. This allows for separate statistics on the data volume of the areas above and below the bridge, and ultimately, it is possible to determine whether the data volume meets the requirements for subsequent mapping.

[0087] In some embodiments of this application, the mapping data of the elevated bridge area further includes intersection markers corresponding to the elevated bridge area. The step of matching the feature data of the elevated bridge area using a preset feature matching strategy based on the navigation route corresponding to the elevated bridge area from the vehicle's navigation route in the elevated bridge area to obtain the feature matching result of the elevated bridge area includes: determining the feature data type corresponding to the feature data of the elevated bridge area based on the navigation route corresponding to the vehicle's navigation route in the elevated bridge area; the feature data type includes bridge-on-bridge feature data and bridge-off-bridge feature data; determining the correspondence between the feature data of the elevated bridge area, the feature data type, and the intersection markers corresponding to the elevated bridge area; and matching the feature data of the elevated bridge area using the preset feature matching strategy based on the correspondence between the feature data of the elevated bridge area, the feature data type, and the intersection markers corresponding to the elevated bridge area to obtain the feature matching result of the elevated bridge area.

[0088] Since the vehicle has a built-in map navigation tool, the map navigation tool will assign a globally unique identifier, such as a link ID, to each intersection in the overpass area. This identifier can uniquely represent the overpass area corresponding to the intersection, and therefore can be used as an index in the subsequent matching and positioning stage.

[0089] As mentioned earlier, based on the vehicle's navigation route in the elevated bridge area, it's possible to determine whether the feature data in the road images collected by the vehicle corresponds to feature data above or below the bridge, that is, to determine the feature data type corresponding to the elevated bridge area. Then, by combining this with the intersection markers corresponding to the elevated bridge area uploaded by the vehicle, a correspondence can be established between feature data, intersection markers, and feature data type (above / below the bridge). Based on this correspondence, subsequent feature matching operations can be performed.

[0090] In some embodiments of this application, the bridge feature data and the under-bridge feature data each include multiple sets. The step of matching the feature data of the elevated bridge area based on the correspondence between the feature data of the elevated bridge area, the feature data type, and the intersection identifiers corresponding to the elevated bridge area, and using the preset feature matching strategy to obtain the feature matching result of the elevated bridge area includes: performing feature matching between any two sets of bridge feature data to obtain a bridge feature matching result; performing feature matching between any two sets of under-bridge feature data to obtain an under-bridge feature matching result; and, if the bridge feature matching result meets the preset bridge feature matching requirements and the under-bridge feature matching result meets the preset under-bridge feature matching requirements, determining the feature matching result of the elevated bridge area based on the bridge feature matching result and the under-bridge feature matching result.

[0091] In this embodiment of the application, when matching feature data, the feature data of the area on the bridge and the feature data of the area under the bridge can be matched separately. For example, multiple sets of feature data of the area on the bridge can be matched pairwise to obtain successfully matched feature data of the area on the bridge. Similarly, multiple sets of feature data of the area under the bridge can be matched pairwise to obtain successfully matched feature data of the area under the bridge. Since each set of feature data contains feature data from multiple keyframe images, for example, the first set of feature data and the second set of feature data each contain 10 frames of feature data, when matching the two sets of feature data, the 10 frames of feature data in the two sets of data can be compared separately. When multiple frames of feature data in the two sets of data are successfully matched, that is, when the similarity is high, the two sets of feature data can be considered to be successfully matched. By analogy, the matching results of any two sets of feature data can be obtained.

[0092] The more feature data that is successfully matched, the more accurately the feature data can represent the characteristics of the location, and thus provide more accurate support for feature matching in the subsequent localization stage. Therefore, we can also constrain the amount of feature data that is successfully matched in the area above the bridge and the area below the bridge. For example, if there are 50 feature data in the area above the bridge and 40 of them are successfully matched, then we can consider that the feature matching result in the area above the bridge has met the requirements. Similarly, we can also set corresponding requirements for the area below the bridge.

[0093] The specific matching algorithm between feature data can be flexibly selected by combining existing technologies. For example, the SIFT (Scale-invariant feature transform) algorithm or the FAST (Features from accelerated segment test) algorithm can be used, and no specific limitation is made here.

[0094] Based on the above process, accurate feature data of the elevated bridge area can be obtained without manual annotation. By storing this feature data in the cloud, a high recognition accuracy can be achieved throughout the entire elevated bridge area.

[0095] In some embodiments of this application, constructing a feature map of the elevated bridge area based on the feature matching results of the elevated bridge area includes: determining successfully matched feature data based on the feature matching results of the elevated bridge area; determining the location of the elevated bridge area corresponding to the successfully matched feature data, and filtering the successfully matched feature data based on the location of the elevated bridge area corresponding to the successfully matched feature data to obtain filtered feature data; and constructing a feature map of the elevated bridge area based on the filtered feature data.

[0096] Since the successfully matched feature data often represents multiple frames of feature data for the same location point, that is, features collected and extracted from the same location, they have high feature similarity. For the subsequent matching and localization process, it is not necessary to use all the feature data corresponding to the same location point for matching. Therefore, the successfully matched feature data can be filtered according to the specific location of the overpass area corresponding to each successfully matched feature data, so that each location point has one or a few corresponding feature data, thereby improving the efficiency of subsequent feature matching.

[0097] This application also provides a vehicle positioning method for elevated bridge areas, such as... Figure 3 The diagram shows a flowchart of a vehicle positioning method for an elevated bridge area according to an embodiment of this application. The vehicle positioning method for an elevated bridge area includes at least the following steps S310 to S340:

[0098] Step S310: Obtain the feature map acquisition request for the elevated bridge area sent by the vehicle terminal. The feature map acquisition request for the elevated bridge area includes the intersection identifiers corresponding to the elevated bridge area.

[0099] In this embodiment of the application, when locating a vehicle in an elevated bridge area, it is necessary to first obtain a feature map acquisition request for the elevated bridge area sent by the vehicle. The request needs to carry the intersection identifier corresponding to the elevated bridge area, such as link ID. The link ID is a unique identifier that represents each elevated bridge area. Therefore, the vehicle needs to provide the intersection identifier to facilitate subsequent confirmation of which elevated bridge area the vehicle is about to enter.

[0100] Step S320: Determine the feature map of the corresponding elevated bridge area based on the intersection markers corresponding to the elevated bridge area.

[0101] Since each elevated bridge area is marked with a corresponding intersection icon during the feature map construction process, after receiving the feature map acquisition request from the vehicle, we can determine which elevated bridge area the vehicle is about to enter based on the intersection icon sent by the vehicle, and thus obtain the feature map corresponding to that elevated bridge area.

[0102] Step S330: Obtain the current road image sent by the vehicle terminal, and use a preset feature extraction model to extract features from the current road image to obtain feature data of the current road image.

[0103] Next, it is necessary to obtain the current road image sent by the vehicle. The current road image can refer to the image reported by the vehicle after it has entered the elevated bridge area and traveled a certain distance. For example, the road image collected after the vehicle has passed the intersection 50m away. The vehicle can roughly estimate the distance traveled in the elevated bridge area based on the GPS positioning data and the inertial navigation positioning data collected by the IMU, so as to determine whether it is necessary to collect the road image.

[0104] After obtaining the current road image, the preset feature extraction model trained based on deep learning can also be used to extract features from the current road image, thereby obtaining the feature data of the current road image.

[0105] Step S340: Match the feature data of the current road image with the feature map of the elevated bridge area to obtain the vehicle positioning result of the elevated bridge area; wherein, the feature map of the elevated bridge area is constructed based on any of the aforementioned mapping methods for the elevated bridge area.

[0106] The feature data of the current road image is matched one by one with the feature data of multiple frames contained in the feature map of the overpass area. The best matching frame is then determined based on the degree of matching. Since the feature data in the feature map is pre-labeled with the specific type of under-bridge / under-bridge area, it is possible to determine whether the vehicle is currently located on or under the overpass. The required degree of matching can be, for example, that the number of matching point pairs with feature data on the bridge is much greater than the number of matching point pairs with feature data under the bridge, or vice versa. The specific number requirement can be flexibly set according to actual needs, as long as the type of feature data in the current road image can be clearly distinguished. Of course, a minimum number of matching point pairs can also be limited, specifically by setting a preset minimum threshold, to further reduce the false detection rate.

[0107] Since the degree of feature matching is a specific and quantifiable indicator, the higher the degree of matching, the more likely it is that the two data points correspond to feature data at the same location, meaning they are more likely to belong to the same data type. Therefore, the feature matching results output by this application embodiment are interpretable and more credible and reliable than the classification results of "under the bridge" / "under the bridge" obtained based on image recognition models in existing solutions. Furthermore, since this application embodiment uses a feature matching method, it can still accurately identify complex elevated bridge scenarios, such as when a vehicle is already on the bridge but there is still a bridge above it.

[0108] It should be noted that the vehicle positioning method for the elevated bridge area described in this application embodiment can be executed in the cloud. The advantage of cloud execution is that it reduces the computing power requirements of the vehicle-side, because most vehicle-side devices may not yet have the computing power to meet the requirements of feature map matching. Therefore, cloud execution can be applied to more vehicle-side devices. Of course, if some vehicle-side devices have the corresponding computing power, they can also be executed by the vehicle-side. When executed by the vehicle-side, since the feature map data of the elevated bridge area is stored in the cloud, the vehicle-side device needs to first download the corresponding feature map of the elevated bridge area from the cloud, and then perform subsequent feature extraction, matching, and positioning operations on the vehicle-side. This can reduce the latency of vehicle positioning in the elevated bridge area and improve real-time performance.

[0109] In some embodiments of this application, after obtaining the vehicle positioning result of the elevated bridge area based on the feature data of the current road image and the feature map of the elevated bridge area, the method further includes: obtaining the navigation route of the vehicle; comparing the vehicle positioning result of the elevated bridge area with the navigation route; and determining whether the navigation route of the vehicle needs to be replanned based on the comparison result.

[0110] Because it is difficult to accurately identify the vehicle's position in the elevated bridge area, false detection may trigger deviation and require replanning of the navigation route. However, the embodiments of this application can obtain accurate positioning results in the elevated bridge area. By comparing the positioning results with the navigation route planning results, it is possible to more accurately determine whether the vehicle has deviated from its course, i.e. whether the route needs to be replanned.

[0111] For example, if feature matching identifies that the vehicle is currently traveling on a bridge, and the navigation route also corresponds to a route traveling on a bridge, then it verifies that the vehicle has not deviated from its course. This avoids the problem of the navigation route being incorrectly replanned due to positioning errors, thus ensuring that the vehicle travels along the correct route.

[0112] For ease of understanding of the various embodiments of this application, such as Figure 4 The diagram illustrates a flowchart of a feature map construction and localization process for an elevated bridge area, as described in this embodiment. For the mapping process, road images of the elevated bridge area are first acquired and features are extracted to obtain feature data for the elevated bridge area. Then, the feature data is self-labeled to obtain a feature map of the elevated bridge area. For the localization process, the elevated bridge area that the vehicle is about to enter is first determined, and the corresponding feature map data for that area is loaded. Then, the current road image collected by the vehicle is acquired and features are extracted to obtain feature data from the current road image. Finally, the feature data from the current road image is matched with the corresponding feature map data of the elevated bridge area to determine the vehicle's localization result in the elevated bridge area.

[0113] This application embodiment also provides a mapping device 500 for elevated bridge areas, such as... Figure 5 The diagram shows a schematic representation of a mapping device for an elevated bridge area according to an embodiment of this application. The mapping device 500 for the elevated bridge area includes: a first acquisition unit 510, a first feature extraction unit 520, a first matching unit 530, and a construction unit 540, wherein:

[0114] The first acquisition unit 510 is used to acquire mapping data of the elevated bridge area sent by the vehicle terminal. The mapping data of the elevated bridge area includes road images of the elevated bridge area, inertial navigation positioning data, and the navigation route of the vehicle terminal in the elevated bridge area.

[0115] The first feature extraction unit 520 is used to extract features from the road image of the elevated bridge area based on the inertial navigation positioning data of the elevated bridge area and using a preset feature extraction model to obtain feature data of the elevated bridge area.

[0116] The first matching unit 530 is used to match the feature data of the elevated bridge area based on the navigation route corresponding to the vehicle terminal in the elevated bridge area using a preset feature matching strategy, so as to obtain the feature matching result of the elevated bridge area.

[0117] The construction unit 540 is used to construct a feature map of the elevated bridge area based on the feature matching results of the elevated bridge area.

[0118] In some embodiments of this application, the first feature extraction unit 520 is specifically used to: determine the key frame image of the elevated bridge area based on the road image and inertial navigation positioning data of the elevated bridge area; and extract features from the key frame image of the elevated bridge area using a preset feature extraction model to obtain key frame feature data of the elevated bridge area.

[0119] In some embodiments of this application, the first matching unit 530 is specifically used to: determine whether the amount of feature data of the elevated bridge area meets the preset mapping conditions based on the navigation route corresponding to the elevated bridge area by the vehicle terminal; and when the amount of feature data of the elevated bridge area meets the preset mapping conditions, use the preset feature matching strategy to match the feature data of the elevated bridge area to obtain the feature matching result of the elevated bridge area.

[0120] In some embodiments of this application, the mapping data of the elevated bridge area further includes the intersection identifiers corresponding to the elevated bridge area. The first matching unit 530 is specifically used to: determine the feature data type corresponding to the feature data of the elevated bridge area based on the navigation route corresponding to the vehicle in the elevated bridge area, wherein the feature data type includes bridge feature data and under-bridge feature data; determine the correspondence between the feature data of the elevated bridge area, the feature data type, and the intersection identifiers corresponding to the elevated bridge area; and, based on the correspondence between the feature data of the elevated bridge area, the feature data type, and the intersection identifiers corresponding to the elevated bridge area, match the feature data of the elevated bridge area using the preset feature matching strategy to obtain the feature matching result of the elevated bridge area.

[0121] In some embodiments of this application, the bridge feature data and the under-bridge feature data each include multiple sets. The first matching unit 530 is specifically used to: perform feature matching between any two sets of bridge feature data to obtain a bridge feature matching result; perform feature matching between any two sets of under-bridge feature data to obtain an under-bridge feature matching result; and, when the bridge feature matching result meets the preset bridge feature matching requirements and the under-bridge feature matching result meets the preset under-bridge feature matching requirements, determine the feature matching result of the viaduct area based on the bridge feature matching result and the under-bridge feature matching result.

[0122] In some embodiments of this application, the construction unit 540 is specifically used to: determine successfully matched feature data based on the feature matching results of the elevated bridge area; determine the location of the elevated bridge area corresponding to the successfully matched feature data, and filter the successfully matched feature data according to the location of the elevated bridge area corresponding to the successfully matched feature data to obtain filtered feature data; and construct a feature map of the elevated bridge area based on the filtered feature data.

[0123] It is understood that the mapping device for the elevated bridge area described above can realize each step of the mapping method for the elevated bridge area provided in the foregoing embodiments. The relevant explanations of the mapping method for the elevated bridge area are applicable to the mapping device for the elevated bridge area, and will not be repeated here.

[0124] This application embodiment also provides a vehicle positioning device 600 for elevated bridge areas, such as... Figure 6 The diagram shows a structural schematic of a vehicle positioning device for an elevated bridge area according to an embodiment of this application. The mapping device 600 for the elevated bridge area includes: a second acquisition unit 610, a first determination unit 620, a second feature extraction unit 630, and a second matching unit 640, wherein:

[0125] The second acquisition unit 610 is used to acquire a feature map acquisition request for the elevated bridge area sent by the vehicle terminal. The feature map acquisition request for the elevated bridge area includes the intersection identifiers corresponding to the elevated bridge area.

[0126] The first determining unit 620 is used to determine the feature map of the corresponding elevated bridge area based on the intersection signage of the elevated bridge area.

[0127] The second feature extraction unit 630 is used to acquire the current road image sent by the vehicle terminal, and to extract features from the current road image using a preset feature extraction model to obtain feature data of the current road image.

[0128] The second matching unit 640 is used to match the feature data of the current road image with the feature map of the overpass area to obtain the vehicle positioning result of the overpass area.

[0129] The feature map of the elevated bridge area is constructed based on the aforementioned mapping device for the elevated bridge area.

[0130] In some embodiments of this application, the vehicle positioning device in the elevated bridge area further includes: a third acquisition unit for acquiring the navigation route of the vehicle; a comparison unit for comparing the vehicle positioning result in the elevated bridge area with the navigation route; and a second determination unit for determining whether the navigation route of the vehicle needs to be replanned based on the comparison result.

[0131] It is understood that the vehicle positioning device for the elevated bridge area described above can realize each step of the vehicle positioning method for the elevated bridge area provided in the foregoing embodiments. The relevant explanations of the vehicle positioning method for the elevated bridge area are applicable to the vehicle positioning device for the elevated bridge area, and will not be repeated here.

[0132] Figure 7 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 7 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0133] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0134] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0135] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a mapping device for the viaduct region at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0136] Acquire mapping data of the elevated bridge area sent by the vehicle terminal. The mapping data of the elevated bridge area includes road images of the elevated bridge area, inertial navigation positioning data, and the navigation route of the vehicle terminal in the elevated bridge area.

[0137] Based on the inertial navigation positioning data of the elevated bridge area, feature extraction is performed on the road image of the elevated bridge area using a preset feature extraction model to obtain feature data of the elevated bridge area.

[0138] Based on the navigation route of the vehicle in the elevated bridge area, the feature data of the elevated bridge area is matched using a preset feature matching strategy to obtain the feature matching result of the elevated bridge area.

[0139] A feature map of the elevated bridge area is constructed based on the feature matching results of the elevated bridge area.

[0140] The above is as stated in this application. Figure 1The mapping device for the elevated bridge area disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0141] The electronic device can also perform Figure 1 A method for implementing mapping equipment in elevated bridge areas, and realizing the mapping equipment in elevated bridge areas. Figure 1 The functions of the embodiments shown are not described in detail here.

[0142] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the mapping device for the elevated bridge area in the illustrated embodiment is specifically used to perform the following:

[0143] Acquire mapping data of the elevated bridge area sent by the vehicle terminal. The mapping data of the elevated bridge area includes road images of the elevated bridge area, inertial navigation positioning data, and the navigation route of the vehicle terminal in the elevated bridge area.

[0144] Based on the inertial navigation positioning data of the elevated bridge area, feature extraction is performed on the road image of the elevated bridge area using a preset feature extraction model to obtain feature data of the elevated bridge area.

[0145] Based on the navigation route of the vehicle in the elevated bridge area, the feature data of the elevated bridge area is matched using a preset feature matching strategy to obtain the feature matching result of the elevated bridge area.

[0146] A feature map of the elevated bridge area is constructed based on the feature matching results of the elevated bridge area.

[0147] It should be noted that the electronic device in this application embodiment can also be used to perform... Figure 6 The method for the vehicle positioning device in the elevated bridge area disclosed in the illustrated embodiment will not be described in detail here.

[0148] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0149] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0150] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0151] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0152] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0153] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0154] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0155] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0156] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0157] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A mapping method for an elevated bridge area, wherein, The mapping method for the elevated bridge area includes: Acquire mapping data of the elevated bridge area sent by the vehicle terminal. The mapping data of the elevated bridge area includes road images of the elevated bridge area, inertial navigation positioning data, and the navigation route of the vehicle terminal in the elevated bridge area. Based on the inertial navigation positioning data of the elevated bridge area, feature extraction is performed on the road image of the elevated bridge area using a preset feature extraction model to obtain feature data of the elevated bridge area. Based on the navigation route of the vehicle in the elevated bridge area, the feature data of the elevated bridge area is matched using a preset feature matching strategy to obtain the feature matching result of the elevated bridge area. A feature map of the elevated bridge area is constructed based on the feature matching results of the elevated bridge area. The mapping data for the elevated bridge area also includes the intersection markers corresponding to the elevated bridge area, which are used as indexes for the vehicle positioning stage of the elevated bridge area; The step of matching the feature data of the elevated bridge area based on the navigation route corresponding to the vehicle in the elevated bridge area using a preset feature matching strategy to obtain the feature matching result of the elevated bridge area includes: Based on the navigation route of the vehicle in the elevated bridge area, the feature data type corresponding to the feature data of the elevated bridge area is determined. The feature data type includes bridge feature data and under-bridge feature data. Determine the correspondence between the feature data of the elevated bridge area, the type of feature data, and the intersection identifiers corresponding to the elevated bridge area; Based on the correspondence between the feature data of the elevated bridge area, the feature data type, and the intersection identifiers corresponding to the elevated bridge area, the feature data of the elevated bridge area is matched using the preset feature matching strategy to obtain the feature matching result of the elevated bridge area. The bridge-on feature data and the bridge-under feature data each include multiple sets. Based on the correspondence between the feature data of the elevated bridge area, the feature data type, and the intersection identifiers corresponding to the elevated bridge area, the feature data of the elevated bridge area is matched using the preset feature matching strategy to obtain the feature matching result of the elevated bridge area, including: Perform feature matching between any two sets of bridge feature data to obtain the bridge feature matching results; Perform feature matching between any two sets of under-bridge feature data to obtain the under-bridge feature matching results; If the feature matching result on the bridge meets the preset feature matching requirements and the feature matching result under the bridge meets the preset feature matching requirements, the feature matching result of the viaduct area is determined based on the feature matching result on the bridge and the feature matching result under the bridge. Both the preset bridge feature matching requirements and the preset under-bridge feature matching requirements include the required amount of data for successfully matched feature data.

2. The mapping method for the elevated bridge area as described in claim 1, wherein, The inertial navigation positioning data based on the elevated bridge area, and the feature extraction of the road image of the elevated bridge area using a preset feature extraction model, yields the following feature data for the elevated bridge area: Based on the road images and inertial navigation positioning data of the elevated bridge area, key frame images of the elevated bridge area are determined; The keyframe images of the elevated bridge area are used to extract features using a preset feature extraction model to obtain keyframe feature data of the elevated bridge area.

3. The mapping method for the elevated bridge area as described in claim 1, wherein, The step of matching the feature data of the elevated bridge area based on the navigation route corresponding to the vehicle in the elevated bridge area using a preset feature matching strategy to obtain the feature matching result of the elevated bridge area includes: Based on the navigation route of the vehicle in the elevated bridge area, determine whether the amount of feature data of the elevated bridge area meets the preset mapping conditions. If the amount of feature data in the elevated bridge area meets the preset mapping conditions, the feature data in the elevated bridge area is matched using the preset feature matching strategy to obtain the feature matching result of the elevated bridge area.

4. The mapping method for the elevated bridge area as described in claim 1, wherein, The step of constructing a feature map of the elevated bridge area based on the feature matching results of the elevated bridge area includes: Based on the feature matching results of the elevated bridge area, the successfully matched feature data are determined; Determine the location of the elevated bridge area corresponding to the successfully matched feature data, and filter the successfully matched feature data according to the location of the elevated bridge area corresponding to the successfully matched feature data to obtain the filtered feature data; A feature map of the elevated bridge area is constructed based on the filtered feature data.

5. A vehicle positioning method for an elevated bridge area, wherein, The vehicle positioning method in the elevated bridge area includes: The vehicle receives a feature map acquisition request for the elevated bridge area sent by the vehicle terminal. The feature map acquisition request for the elevated bridge area includes the intersection identifiers corresponding to the elevated bridge area. Based on the intersection signs corresponding to the elevated bridge area, determine the feature map of the corresponding elevated bridge area; The current road image sent by the vehicle is acquired, and the current road image is extracted using a preset feature extraction model to obtain the feature data of the current road image. The feature data of the current road image is matched with the feature map of the elevated bridge area to obtain the vehicle positioning result of the elevated bridge area; The feature map of the elevated bridge area is constructed based on the mapping method of the elevated bridge area described in any one of claims 1 to 4.

6. The vehicle positioning method for the elevated bridge area as described in claim 5, wherein, After obtaining the vehicle location results for the elevated bridge area based on the feature data of the current road image and the feature map of the elevated bridge area, the method further includes: Obtain the navigation route from the vehicle. Compare the vehicle location results in the elevated bridge area with the navigation route; The comparison results will determine whether the vehicle's navigation route needs to be replanned.

7. A mapping device for an elevated bridge area, wherein, The mapping device for the elevated bridge area includes: The first acquisition unit is used to acquire mapping data of the elevated bridge area sent by the vehicle terminal. The mapping data of the elevated bridge area includes road images of the elevated bridge area, inertial navigation positioning data, and the navigation route of the vehicle terminal in the elevated bridge area. The first feature extraction unit is used to extract features from the road image of the elevated bridge area based on the inertial navigation positioning data of the elevated bridge area and using a preset feature extraction model to obtain feature data of the elevated bridge area. The first matching unit is used to match the feature data of the elevated bridge area based on the navigation route corresponding to the vehicle terminal in the elevated bridge area using a preset feature matching strategy, so as to obtain the feature matching result of the elevated bridge area. A construction unit is used to construct a feature map of the elevated bridge area based on the feature matching results of the elevated bridge area. The mapping data for the elevated bridge area also includes the intersection markers corresponding to the elevated bridge area, which are used as indexes for the vehicle positioning stage of the elevated bridge area; The first matching unit is specifically used for: Based on the navigation route of the vehicle in the elevated bridge area, the feature data type corresponding to the feature data of the elevated bridge area is determined. The feature data type includes bridge feature data and under-bridge feature data. Determine the correspondence between the feature data of the elevated bridge area, the type of feature data, and the intersection identifiers corresponding to the elevated bridge area; Based on the correspondence between the feature data of the elevated bridge area, the feature data type, and the intersection identifiers corresponding to the elevated bridge area, the feature data of the elevated bridge area is matched using the preset feature matching strategy to obtain the feature matching result of the elevated bridge area. The bridge feature data and the under-bridge feature data each comprise multiple sets, and the first matching unit is specifically used for: Perform feature matching between any two sets of bridge feature data to obtain the bridge feature matching results; Perform feature matching between any two sets of under-bridge feature data to obtain the under-bridge feature matching results; If the feature matching result on the bridge meets the preset feature matching requirements and the feature matching result under the bridge meets the preset feature matching requirements, the feature matching result of the viaduct area is determined based on the feature matching result on the bridge and the feature matching result under the bridge. Both the preset bridge feature matching requirements and the preset under-bridge feature matching requirements include the required amount of data for successfully matched feature data.

8. A vehicle positioning device for an elevated bridge area, wherein, The mapping device for the elevated bridge area includes: The second acquisition unit is used to acquire a feature map acquisition request for the elevated bridge area sent by the vehicle terminal. The feature map acquisition request for the elevated bridge area includes the intersection identifiers corresponding to the elevated bridge area. The first determining unit is used to determine the feature map of the corresponding elevated bridge area based on the intersection signage of the elevated bridge area. The second feature extraction unit is used to acquire the current road image sent by the vehicle terminal, and to extract features from the current road image using a preset feature extraction model to obtain feature data of the current road image. The second matching unit is used to match the feature data of the current road image with the feature map of the overpass area to obtain the vehicle positioning result of the overpass area. The feature map of the elevated bridge area is constructed based on the mapping device for the elevated bridge area as described in claim 7.

9. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform a mapping method for any of the viaduct areas described in claims 1 to 4, or a vehicle positioning method for any of the viaduct areas described in claims 5 to 6.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform a mapping method for any of the viaduct areas of claims 1 to 4, or a vehicle positioning method for any of the viaduct areas of claims 5 to 6.

Images