CN112327337A - Intersection reconstruction method, device, equipment and storage medium - Google Patents
Intersection reconstruction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112327337A CN112327337A CN202011205254.9A CN202011205254A CN112327337A CN 112327337 A CN112327337 A CN 112327337A CN 202011205254 A CN202011205254 A CN 202011205254A CN 112327337 A CN112327337 A CN 112327337A
- Authority
- CN
- China
- Prior art keywords
- intersection
- access point
- information
- determining
- target area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000013136 deep learning model Methods 0.000 claims abstract description 23
- 238000010586 diagram Methods 0.000 claims description 81
- 238000001514 detection method Methods 0.000 claims description 41
- 238000013528 artificial neural network Methods 0.000 claims description 23
- 238000013527 convolutional neural network Methods 0.000 claims description 21
- 230000010365 information processing Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 abstract description 11
- 238000003709 image segmentation Methods 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 241000272183 Geococcyx californianus Species 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/393—Trajectory determination or predictive tracking, e.g. Kalman filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The embodiment of the disclosure provides a method, a device, equipment and a storage medium for reconstructing an intersection. The method comprises the following steps: acquiring track information corresponding to a road junction to be processed; determining the type and/or access point information of the intersection through a deep learning model according to the track information; and rebuilding the intersection according to the type and/or the access point information of the intersection. The embodiment of the disclosure can solve the problem that the intersection reconstructed by the prior art has a plurality of noise road sections or loses important topological communication, so that the accuracy of intersection reconstruction is low.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of maps, in particular to a method, a device, equipment and a storage medium for reconstructing intersections.
Background
With the continuous development of positioning technology and the continuous improvement of travel convenience, the application of the navigation function is more and more extensive. Accurate electronic maps play an important role in navigation applications, but the traditional way of drawing electronic maps by hand is very labor and material consuming and inefficient.
With the widespread use of Positioning sensors such as GPS (Global Positioning System), road network automation reconstruction technology (map inference) based on large-scale GPS track information will greatly reduce the manufacturing cost of electronic maps. The existing reconstruction technology usually processes the track information by a clustering method, thereby realizing the reconstruction of the intersection. However, intersections reconstructed by the method often do not conform to the real intersection structure, a plurality of noisy road sections exist or important topological communication is lost, and therefore the accuracy of intersection reconstruction is low.
Disclosure of Invention
The embodiment of the disclosure provides a method, a device, equipment and a storage medium for reconstructing an intersection, which can solve the problem that the accuracy of intersection reconstruction is low due to the fact that the intersection reconstructed by the prior art has a plurality of noisy road sections or loses important topological connectivity.
In a first aspect, an embodiment of the present disclosure provides an intersection reconstruction method, including: acquiring track information corresponding to a road junction to be processed; determining the type and/or access point information of the intersection through a deep learning model according to the track information; and rebuilding the intersection according to the type and/or the access point information of the intersection.
In a second aspect, an embodiment of the present disclosure provides an intersection reconstruction apparatus, including: the track information acquisition module is used for acquiring track information corresponding to the intersection to be processed; the track information processing module is used for determining the type and/or the access point information of the intersection through a deep learning model according to the track information; and the intersection reconstruction module is used for reconstructing the intersection according to the type and/or the access point information of the intersection.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of the first aspect.
In a fourth aspect, the present disclosure provides a computer-readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the method of the first aspect.
According to the intersection reconstruction method, the device, the equipment and the storage medium provided by the embodiment of the disclosure, the type and/or the access point information of the intersection are determined through the deep learning model according to the track information by acquiring the track information corresponding to the intersection to be processed, so that the topological communication of the intersection is ensured, then the intersection is reconstructed according to the type and/or the access point information of the intersection, a more real and accurate intersection topological structure is generated, and the accuracy of intersection reconstruction is improved.
Drawings
Fig. 1 is a schematic view of an application scenario of an intersection reconstruction method provided in the embodiment of the present disclosure;
fig. 2 is a schematic flow chart of an intersection reconstruction method provided in the embodiment of the present disclosure;
fig. 3 is a schematic flow chart of an intersection reconstruction method according to another embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a topological feature map provided in accordance with another embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an intersection reconstruction device provided in the embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
In the prior art, the existing reconstruction technology usually processes the track information by a clustering method, thereby realizing the reconstruction of the intersection. However, intersections reconstructed by the method often do not conform to the real intersection structure, a plurality of noisy road sections exist or important topological communication is lost, and therefore the accuracy of intersection reconstruction is low.
In order to solve the technical problems, the technical idea of the disclosure is to provide a multi-task deep learning framework, combine the CNN and the GCN to simultaneously learn the shape and topological characteristics of the intersection, predict the type and the entry/exit point of the intersection, and reconstruct the intersection based on the type and the entry/exit point of the intersection, so that the reconstructed intersection not only conforms to the actual intersection structure, but also ensures topological connectivity, and improves the accuracy of intersection reconstruction.
Fig. 1 is a schematic view of an application scenario of an intersection reconstruction method provided in the embodiment of the present disclosure. As shown in fig. 1, a track of a target area is first obtained, and a range frame where each intersection is located is determined according to the track. For each intersection, an original track (namely track information) is used as an input quantity, and a topological feature diagram is constructed through a Graph Convolutional neural Network (GCN). The topological characteristic diagram is subjected to Convolutional Neural Networks (CNN) to obtain the type of the intersection, and simultaneously, an access point is obtained through a target detection algorithm, wherein the target detection algorithm can be an improved one-dimensional target detection algorithm. According to the type and the access point of the intersection, the intersection can be rebuilt. The road junction reconstructed by the method conforms to the structure of the real road junction, a plurality of noise road sections do not exist or important topological communication is lost, and the accuracy of road junction reconstruction is improved.
In particular, the intersection reconstruction method provided by the present disclosure aims to solve the above technical problems of the prior art.
The following describes the technical solutions of the present disclosure and how to solve the above technical problems in specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present disclosure will be described below with reference to the accompanying drawings.
Fig. 2 is a schematic flow chart of an intersection reconstruction method provided in the embodiment of the present disclosure. The embodiment of the present disclosure provides an intersection reconstruction method for solving the above technical problems in the prior art, and the method specifically includes the following steps:
s201, obtaining track information corresponding to the intersection to be processed.
The execution main body of the embodiment of the disclosure can be a server, the server can acquire the track information of the GPS track through an acquisition device, and the track information can comprise the speed and the direction angle of the track point.
In practical application, road network reconstruction is carried out on which area, a GPS track of an actual road network corresponding to the area needs to be acquired, then a range frame where each intersection is located is identified for the area, and the area corresponding to each intersection in the electronic map is drawn or reconstructed according to track information for the range frame where each intersection is located.
Specifically, how to obtain the track information corresponding to the intersection to be processed can be realized through the following steps:
step a1, obtaining the track information corresponding to the target area to be reconstructed in the electronic map.
Step a2, determining a range frame where each intersection in the target area is located according to the track information corresponding to the target area.
Step a3, determining the track information corresponding to each intersection according to the range frame where each intersection is located.
Wherein the intersection to be processed is any intersection in the target area.
In the embodiment of the present disclosure, the acquisition of the track information corresponding to the intersection to be processed may be determined by intersection detection. In intersection detection, the whole intersection is divided into a road section and an intersection. The intersection detection can include two parts, namely, construction of a spatial trajectory characteristic diagram and detection of an intersection range frame by using an image target detection algorithm, such as an SSD algorithm.
Specifically, track information corresponding to a target area to be reconstructed in an electronic map is obtained by a GPS sensor, then a spatial track characteristic diagram is constructed based on the track information corresponding to the target area, a range frame where each intersection is located in the target area is detected based on the spatial track characteristic diagram, and then the track information of the range frame where each intersection to be processed is located, namely the track information corresponding to the intersection to be processed, is determined according to the track information. The intersection to be processed here is any intersection in the target area.
Optionally, how to determine the range frame where each intersection in the target area is located may be implemented by the following steps:
step b1, performing mesh division on the target area, and determining the two-dimensional space characteristics of the target area according to the track information in each mesh.
Step b2, determining a range frame where each intersection of the target area is located through a target detection algorithm according to the two-dimensional space characteristics of the target area.
In the embodiment of the present disclosure, the target area is subjected to grid division, for example, grid division is performed by (5m × 5m), the number of trace points of the GPS falling into each grid, an average direction angle, and an average speed are counted to form a two-dimensional spatial feature of the target area, then, according to the two-dimensional spatial feature of the target area, an SSD algorithm, that is, a target detection algorithm, is used to detect each intersection of the target area, and a range frame where each intersection of the target area is located is determined. The average direction angle here is an average value of the direction angles of the trace points of the GPS falling in each grid, and the average speed is an average value of the speeds of the trace points of the GPS falling in each grid.
After the target area is subjected to grid division, for the range frame where each determined intersection is located, the continuity information of the track can be determined through the track points of the GPS, for example, which grid enters and passes through which grid and which grid exits from which grid.
S202, determining the type and/or the access point information of the intersection through a deep learning model according to the track information.
In the embodiment of the disclosure, after the range frame where each intersection is located is obtained, for each intersection, classification and access points of the intersection can be predicted at the same time through a constructed multi-task deep learning network, that is, the type of the intersection is identified, and the access point position of the intersection is checked.
Specifically, a GCN model and a CNN model are trained, so that a graph convolution neural network and a convolution neural network simultaneously learn the type of the intersection and the topological characteristic graph to construct a multitask deep learning model. Wherein, the GCN models the track continuity characteristic, and the CNN carries out intersection classification prediction. The input quantity of the GCN model is track information of the intersection to be processed and track continuity information of the intersection to be processed, a topological characteristic diagram is output through GCN weighted modeling, then the topological characteristic diagram is used as the input quantity of the CNN model to classify the intersection to obtain the type of the intersection to be processed, an access point of the intersection to be processed is identified through a target detection algorithm, such as an improved one-dimensional target detection method, according to the topological characteristic diagram to obtain access point information, and the access point information can comprise position information of the intersection to be processed where each access point is located and whether the access point is a connected point or a non-connected point.
Optionally, determining the type and/or the access point information of the intersection through a deep learning model according to the track information may be implemented in the following manner: and according to the track information, constructing a topological characteristic diagram of the intersection through a deep learning model, and determining the type and/or access point information of the intersection according to the topological characteristic diagram.
The topological characteristic diagram can be constructed through a diagram convolution neural network according to the track information; the type of intersection and/or access point information can be determined from the topological profile.
Specifically, for intersection classification, a complete continuous GPS track can be used to construct an intersection topological feature map, and a GCN is used to model track continuity features, wherein the GCN is used to learn topological connectivity differences of intersections. And the CNN is combined to carry out classification prediction on the intersections, and the CNN learns the form difference, so that the topological connectivity of the intersections can be identified in the task of classifying the intersections.
And aiming at the access point detection, determining access point information of the road junction through a target detection algorithm according to the topological characteristic diagram. The realization mode is as follows: and detecting the outermost layer grid of the intersection through a target detection algorithm according to the topological characteristic diagram, and determining the access point information of the intersection.
And the access point information comprises the position and connectivity of the access point of the intersection.
Specifically, an object detection algorithm is used for the outermost grid based on the topological feature diagram, image segmentation is carried out in a sliding window mode, and the positions of the entrance and exit points of the intersection and the connectivity of the entrance and exit points are predicted.
S203, reconstructing the intersection according to the type and/or the access point information of the intersection.
In the embodiment of the disclosure, the actual intersection structure can be determined according to the type of the intersection and the continuity information of the track, so as to realize intersection reconstruction; the actual intersection structure can be determined according to the positions of the access points of the intersection and the connectivity of the access points and the continuity information of the track, so that intersection reconstruction is realized; the actual intersection structure can be determined by combining the types of the intersections and the positions of the access points, so that the intersection reconstruction is realized.
Specifically, referring to fig. 3, fig. 3 is a schematic flow chart of an intersection reconstruction method according to another embodiment of the present disclosure. The embodiment of the present disclosure explains S203 in detail on the basis of the above-described embodiment. Reconstructing the intersection according to the type and/or the access point information of the intersection may include:
s301, obtaining an intersection template corresponding to the type of the intersection.
In the embodiment of the present disclosure, the intersection template used can be determined according to the type of the intersection, and the intersection template herein can include templates corresponding to various types of intersections, that is, one type of intersection corresponds to one intersection template. Types of intersections can include T-shaped, Y-shaped, cross-shaped, X-shaped, offset, circular, and the like.
S302, determining the corresponding relation between the access point of the intersection and the access point of the intersection template according to the access point information of the intersection.
In this embodiment, the access point information of the intersection includes the position of the access point and the connectivity of the access point, and the position of the access point of the intersection template can be determined on the intersection template according to the connectivity of the access point, so as to form a corresponding relationship between the access point of the intersection and the access point of the intersection template.
S303, reconstructing the intersection according to the determined corresponding relation.
In the embodiment of the disclosure, the used intersection template can be determined according to the type of the intersection, then the entry and exit points of the intersection template and the detected entry and exit points are matched and correspond one by one, the corresponding relation is stretched, and the deformation is performed to obtain the final intersection reconstruction result, so as to realize the reconstruction of the intersection. The method solves the problems that in the prior art, a CNN method similar to image segmentation is used for extracting a road center line, the extracted road center line is represented by pixels, for example, the pixels can be represented as roads or non-roads, but road network topology cannot be constructed based on the pixels, intersection topology problems same as a track clustering method exist, namely, the intersection topology is not consistent with a real intersection structure, a lot of noise road sections exist or important topological communication is lost, and the like.
Meanwhile, different from the prior art that the track is converted into the thermodynamic diagram (because it is difficult to distinguish whether the intersection is connected or not connected through the thermodynamic diagram, such as a connected-T-shaped intersection or a non-connected-T-shaped intersection, the intersection reconstructed by the existing method has a topological connection error), the continuity information of the track is ignored, and the accuracy of identifying the topological connection of the intersection is low. According to the method, the type and/or the access point information of the intersection are determined through a deep learning model according to the track information, so that topological communication of the intersection is guaranteed, then the intersection is reconstructed according to the type and/or the access point information of the intersection, a more real and accurate intersection topological structure is generated, and the accuracy of intersection reconstruction is improved.
Optionally, the embodiment of the present disclosure explains in detail how to construct the topological feature diagram based on the above embodiment. According to the track information, a topological characteristic diagram of the intersection is constructed through a graph convolution neural network, and the method can be realized through the following steps:
and c1, determining the two-dimensional space characteristics of the intersection according to the track information of the intersection.
In the embodiment of the present disclosure, firstly, grid division is performed on the target region, for example, (5m × 5m) grid division is performed, and the number of trace points of the GPS falling into each grid, an average direction angle, and an average speed are counted; then, based on the determined range frame where each intersection is located, the grid information contained in the range frame where each intersection is located, such as the number of the divided grids of the intersection, the number of track points corresponding to each grid, the average direction angle and the average speed, is counted, and the two-dimensional space characteristics of the intersection are formed based on the grid information.
And c2, constructing a topological characteristic diagram of the intersection through a diagram convolution neural network according to the two-dimensional space characteristics of the intersection and the continuity of the track information in the intersection.
The intersection is divided into a plurality of grids, and the two-dimensional spatial characteristics of the intersection comprise at least one item of information of each grid in the intersection, wherein the information comprises: the number of trajectory information within the grid, the average direction angle, the average velocity.
In the embodiment of the disclosure, the two-dimensional spatial characteristics of the intersection and the continuity of the track information in the intersection are used as the input quantity of the trained graph convolution neural network, the topological connectivity difference of the intersection is learned through the graph convolution neural network, the track continuity characteristics of the intersection are output, and then the topological characteristic diagram is constructed. Referring to fig. 4, a partial mesh in the intersection is shown, wherein, taking mesh 8 as an example, a topological feature map of mesh 8 is passed through.
Wherein, if one track passes through the grid 1 and the grid 8 in the GPS track, the topological features corresponding to the grids 1 to 8 in the topological feature diagram are 0.1; two tracks pass through the grid 2 and the grid 8 in the GPS track, and the topological features corresponding to 2 to 8 in the topological feature diagram are 0.2; two tracks pass through the grid 3 and the grid 8 in the GPS track, and the topological features corresponding to the 3 to 8 in the topological feature diagram are 0.2; if the GPS track passes through the grids 4 and 8 without the track, 4 to 8 in the topological feature diagram have no topological feature; if three tracks pass through the grids 5 and 8 in the GPS track, the topological features corresponding to the grids 5 to 8 in the topological feature diagram are 0.3; if the GPS track passes through the grids 6 and 8, the corresponding topological features of 6 to 8 in the topological feature map are 0.1; if the GPS track passes through the trackless tracks of the grids 7 and 8, no topological feature exists between 7 and 8 in the topological feature diagram; and if the GPS track passes through the grid 9 and the grid 8 without tracks, the topological characteristic is absent from 9 to 8 in the topological characteristic diagram, and so on, aiming at each grid, a topological characteristic diagram is formed, and further the topological characteristic diagram of the whole intersection is formed.
Then, based on the topological characteristic diagram of the whole intersection, for the detection of the access point of the intersection, the image segmentation is performed on the outermost points (taking fig. 4 as an example, such as 1, 2, 3, 6 and 8) through a sliding window by using an object detection method, and the positions of the access point and the access point of the intersection and the connectivity of the access point and the access point are predicted.
Optionally, after reconstructing each intersection of the target region, the road segments between each intersection of the target region may be determined according to the track information of the target region, so as to form a complete road network.
Specifically, according to the track information of the target area, road section connection between intersections is realized by using a RoadRunner method, and finally a complete road network is formed.
Therefore, the intersection and road network reconstruction framework based on deep learning is adopted in the method, intersection detection, intersection classification, entrance and exit point identification, intersection reconstruction and road section reconstruction are achieved, and a real and accurate road network structure with topological connectivity is formed.
Fig. 5 is a schematic structural diagram of an intersection reconstruction device according to an embodiment of the present disclosure. The intersection reconstruction device may specifically be the server in the above embodiment. The intersection reconstruction device provided in the embodiment of the present disclosure can execute the processing procedure provided in the embodiment of the intersection reconstruction method, and as shown in fig. 5, the intersection reconstruction device includes: a track information obtaining module 501, configured to obtain track information corresponding to a road junction to be processed; a track information processing module 502, configured to determine, according to the track information, a type and/or access point information of the intersection through a deep learning model; and an intersection rebuilding module 503, configured to rebuild the intersection according to the type of the intersection and/or the access point information.
The method and the device for reconstructing the intersection in the embodiment of the disclosure have the advantages that the configured track information acquisition module 501, the track information processing module 502 and the intersection reconstruction module 503 are used for determining the type and/or the access point information of the intersection through a deep learning model according to the track information by acquiring the track information corresponding to the intersection to be processed, so as to ensure the topological communication of the intersection, and then reconstructing the intersection according to the type and/or the access point information of the intersection, so that a more real and accurate intersection topological structure is generated, and the accuracy of intersection reconstruction is improved.
In the embodiment of the disclosure, the server may collect the track information of the GPS track through the collecting device, where the track information may include the speed and the direction angle of the track point.
Optionally, the track information obtaining module is specifically configured to: acquiring track information corresponding to a target area to be reconstructed in an electronic map; determining a range frame where each intersection in the target area is located according to the track information corresponding to the target area; determining track information corresponding to each intersection according to the range frame where each intersection is located; wherein the intersection to be processed is any intersection in the target area.
In the embodiment of the present disclosure, the acquisition of the track information corresponding to the intersection to be processed may be determined by intersection detection. In intersection detection, the whole intersection is divided into a road section and an intersection. The intersection detection can include two parts, namely, construction of a spatial trajectory characteristic diagram and detection of an intersection range frame by using an image target detection algorithm, such as an SSD algorithm.
Specifically, the track information acquisition module acquires track information corresponding to a target area to be reconstructed in an electronic map by using a GPS sensor, then constructs a spatial track characteristic diagram based on the track information corresponding to the target area, detects a range frame where each intersection is located in the target area based on the spatial track characteristic diagram, and then determines the track information of the range frame where each intersection to be processed is located, namely the track information corresponding to the intersection to be processed, according to the track information. The intersection to be processed here is any intersection in the target area.
Optionally, how to determine the range frame where each intersection in the target area is located may be implemented by the track information obtaining module; the track information acquisition module is further specifically configured to: performing grid division on the target area, and determining two-dimensional space characteristics of the target area according to track information in each grid; and determining a range frame where each intersection of the target area is located through a target detection algorithm according to the two-dimensional space characteristics of the target area.
In the embodiment of the present disclosure, the target area is first subjected to grid division, for example, grid division is performed by (5m × 5m), the number of trace points of the GPS falling in each grid, an average direction angle, and an average speed are counted to form a two-dimensional spatial feature of the target area, then, according to the two-dimensional spatial feature of the target area, an SSD algorithm, that is, a target detection algorithm, is used to detect each intersection of the target area, and a range frame where each intersection of the target area is located is determined. The average direction angle here is an average value of the direction angles of the trace points of the GPS falling in each grid, and the average speed is an average value of the speeds of the trace points of the GPS falling in each grid.
After the target area is subjected to grid division, for the range frame where each determined intersection is located, the continuity information of the track can be determined through the track points of the GPS, for example, which grid enters and passes through which grid and which grid exits from which grid.
Optionally, the deep learning model is obtained by simultaneously learning the type of the intersection and the topological feature map through a graph convolution neural network and a convolution neural network.
Optionally, the track information processing module is specifically configured to: and according to the track information, constructing a topological characteristic diagram of the intersection through a deep learning model, and determining the type and/or access point information of the intersection according to the topological characteristic diagram.
In the embodiment of the disclosure, after the range frame where each intersection is located is obtained, for each intersection, the track information processing module can predict the classification and the access point of the intersection at the same time through a constructed multi-task deep learning network, that is, identify the type of the intersection and check the access point position of the intersection.
Specifically, a GCN model and a CNN model are trained, so that a graph convolution neural network and a convolution neural network simultaneously learn the type of the intersection and the topological characteristic graph to construct a multitask deep learning model. Wherein, the GCN models the track continuity characteristic, and the CNN carries out intersection classification prediction. The input quantity of the GCN model is track information of the intersection to be processed and track continuity information of the intersection to be processed, a topological characteristic diagram is output through GCN weighted modeling, then the topological characteristic diagram is used as the input quantity of the CNN model to classify the intersections to obtain the types of the intersections to be processed, the access point of the intersection to be processed is identified through a target detection algorithm according to the topological characteristic diagram to obtain access point information, and the access point information can comprise position information of the intersection to be processed where each access point is located and whether the access point is a connected point or a non-connected point.
Optionally, the track information processing module is further specifically configured to: according to the track information, a topological characteristic diagram of the intersection is constructed through a graph convolution neural network; and determining the type and/or access point information of the intersection according to the topological characteristic diagram.
Optionally, the track information processing module is further specifically configured to: determining the type of the intersection through a convolutional neural network according to the topological characteristic diagram; and/or determining the access point information of the road junction through a target detection algorithm according to the topological characteristic diagram.
In the embodiment of the disclosure, the topological feature map can be constructed by a map convolution neural network according to the track information; the type of intersection and/or access point information can be determined from the topological profile.
Specifically, for intersection classification, a complete continuous GPS track can be used to construct an intersection topological feature map, and a GCN is used to model track continuity features, wherein the GCN is used to learn topological connectivity differences of intersections. And the CNN is combined to carry out classification prediction on the intersections, and the CNN learns the form difference, so that the topological connectivity of the intersections can be identified in the task of classifying the intersections.
Optionally, the track information processing module is further specifically configured to: detecting the outermost grid of the intersection through a target detection algorithm according to the topological characteristic diagram, and determining the access point information of the intersection; and the access point information comprises the position and connectivity of the access point of the intersection.
In the embodiment of the disclosure, for the point-in-and-out detection, the outermost grid of the intersection is detected by a target detection algorithm according to the topological characteristic diagram through a track information processing module root, and the point-in-and-out information of the intersection is determined.
And the access point information comprises the position and connectivity of the access point of the intersection.
Specifically, an object detection algorithm is used for the outermost grid based on the topological feature diagram, image segmentation is carried out in a sliding window mode, and the positions of the entrance and exit points of the intersection and the connectivity of the entrance and exit points are predicted.
Optionally, the track information processing module is further specifically configured to: determining two-dimensional space characteristics of the intersection according to the track information of the intersection; constructing a topological characteristic diagram of the intersection through a graph convolution neural network according to the two-dimensional space characteristics of the intersection and the continuity of track information in the intersection; the intersection is divided into a plurality of grids, and the two-dimensional spatial characteristics of the intersection comprise at least one item of information of each grid in the intersection, wherein the information comprises: the number of trajectory information within the grid, the average direction angle, the average velocity.
In the embodiment of the present disclosure, firstly, grid division is performed on the target region, for example, (5m × 5m) grid division is performed, and the number of trace points of the GPS falling into each grid, an average direction angle, and an average speed are counted; then, based on the determined range frame where each intersection is located, the grid information contained in the range frame where each intersection is located, such as the number of the divided grids of the intersection, the number of track points corresponding to each grid, the average direction angle and the average speed, is counted, and the two-dimensional space characteristics of the intersection are formed based on the grid information. The intersection is divided into a plurality of grids, and the two-dimensional spatial characteristics of the intersection comprise at least one item of information of each grid in the intersection, wherein the information comprises: the number of trajectory information within the grid, the average direction angle, the average velocity.
And taking the two-dimensional space characteristics of the intersection and the continuity of the track information in the intersection as input quantities of a trained graph convolution neural network, learning the topology communication difference of the intersection through the graph convolution neural network, outputting the track continuity characteristics of the intersection, and further constructing a topology characteristic graph. Referring to fig. 4, a partial mesh in the intersection is shown, wherein, taking mesh 8 as an example, a topological feature map of mesh 8 is passed through.
Wherein, if one track passes through the grid 1 and the grid 8 in the GPS track, the topological features corresponding to the grids 1 to 8 in the topological feature diagram are 0.1; two tracks pass through the grid 2 and the grid 8 in the GPS track, and the topological features corresponding to 2 to 8 in the topological feature diagram are 0.2; two tracks pass through the grid 3 and the grid 8 in the GPS track, and the topological features corresponding to the 3 to 8 in the topological feature diagram are 0.2; if the GPS track passes through the grids 4 and 8 without the track, 4 to 8 in the topological feature diagram have no topological feature; if three tracks pass through the grids 5 and 8 in the GPS track, the topological features corresponding to the grids 5 to 8 in the topological feature diagram are 0.3; if the GPS track passes through the grids 6 and 8, the corresponding topological features of 6 to 8 in the topological feature map are 0.1; if the GPS track passes through the trackless tracks of the grids 7 and 8, no topological feature exists between 7 and 8 in the topological feature diagram; and if the GPS track passes through the grid 9 and the grid 8 without tracks, the topological characteristic is absent from 9 to 8 in the topological characteristic diagram, and so on, aiming at each grid, a topological characteristic diagram is formed, and further the topological characteristic diagram of the whole intersection is formed.
Then, based on the topological characteristic diagram of the whole intersection, for the detection of the access point of the intersection, the image segmentation is performed on the outermost points (taking fig. 4 as an example, such as 1, 2, 3, 6 and 8) through a sliding window by using an object detection method, and the positions of the access point and the access point of the intersection and the connectivity of the access point and the access point are predicted.
Optionally, the intersection rebuilding module is specifically configured to: acquiring an intersection template corresponding to the type of the intersection; determining the corresponding relation between the access point of the intersection and the access point of the intersection template according to the access point information of the intersection; and rebuilding the intersection according to the determined corresponding relation.
In the embodiment of the disclosure, the intersection reconstruction module can determine the used intersection template according to the type of the intersection, then match and correspond the entry and exit points of the intersection template and the detected entry and exit points one by one, stretch the correspondence, deform to obtain the final intersection reconstruction result, and realize the reconstruction of the intersection, so that the deformable prior intersection template is used, the prior information of the intersection construction standard in reality is fully utilized, and compared with the method for directly reconstructing the intersection by track clustering and the like in the prior art, a more real and accurate intersection topological expression is generated. The method solves the problems that in the prior art, a CNN method similar to image segmentation is used for extracting a road center line, the extracted road center line is represented by pixels, for example, the pixels can be represented as roads or non-roads, but road network topology cannot be constructed based on the pixels, intersection topology problems same as a track clustering method exist, namely, the intersection topology is not consistent with a real intersection structure, a lot of noise road sections exist or important topological communication is lost, and the like.
Meanwhile, different from the prior art that the track is converted into the thermodynamic diagram (because it is difficult to distinguish whether the intersection is connected or not connected through the thermodynamic diagram, such as a connected-T-shaped intersection or a non-connected-T-shaped intersection, the intersection reconstructed by the existing method has a topological connection error), the continuity information of the track is ignored, and the accuracy of identifying the topological connection of the intersection is low. According to the method, the type and/or the access point information of the intersection are determined through a deep learning model according to the track information, so that topological communication of the intersection is guaranteed, then the intersection is reconstructed according to the type and/or the access point information of the intersection, a more real and accurate intersection topological structure is generated, and the accuracy of intersection reconstruction is improved.
Optionally, the apparatus further comprises: a road segment determination module; and the road section determining module is used for determining road sections among all intersections of the target area according to the track information of the target area after all intersections of the target area are reconstructed so as to form a complete road network.
Specifically, according to the track information of the target area, road section connection between intersections is realized by using a RoadRunner method, and finally a complete road network is formed.
The intersection reconstruction device in the embodiment shown in fig. 5 may be used to implement the technical solution of the method embodiment in the first aspect, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. The electronic device may specifically be the server in the above embodiment. The electronic device provided in the embodiment of the present disclosure may execute the processing procedure provided in the embodiment of the intersection reconstruction method, as shown in fig. 6, the electronic device 600 provided in this embodiment includes: at least one processor 601 and memory 602. The processor 601 and the memory 602 are connected by a bus 603.
In a specific implementation, at least one processor 601 executes computer-executable instructions stored by the memory 602 to cause the at least one processor 601 to perform the methods of the above-described method embodiments.
For a specific implementation process of the processor 601, reference may be made to the above method embodiments, which implement the principle and the technical effect similarly, and details of this embodiment are not described herein again.
In the embodiment shown in fig. 6, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The memory may comprise high speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present disclosure are not limited to only one bus or one type of bus.
In addition, the embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the intersection reconstruction method described in the foregoing embodiment.
The computer-readable storage medium may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (24)
1. An intersection reconstruction method, comprising:
acquiring track information corresponding to a road junction to be processed;
determining the type and/or access point information of the intersection through a deep learning model according to the track information;
and rebuilding the intersection according to the type and/or the access point information of the intersection.
2. The method of claim 1, wherein determining the type of the intersection and/or the access point information from the trajectory information via a deep learning model comprises:
and according to the track information, constructing a topological characteristic diagram of the intersection through a deep learning model, and determining the type and/or access point information of the intersection according to the topological characteristic diagram.
3. The method of claim 2, wherein constructing a topological feature map of the intersection through a deep learning model according to the trajectory information, and determining the type and/or access point information of the intersection according to the topological feature map comprises:
according to the track information, a topological characteristic diagram of the intersection is constructed through a graph convolution neural network;
and determining the type and/or access point information of the intersection according to the topological characteristic diagram.
4. The method of claim 3, wherein constructing the topological feature map of the intersection from the trajectory information via a graph convolution neural network comprises:
determining two-dimensional space characteristics of the intersection according to the track information of the intersection;
constructing a topological characteristic diagram of the intersection through a graph convolution neural network according to the two-dimensional space characteristics of the intersection and the continuity of track information in the intersection;
the intersection is divided into a plurality of grids, and the two-dimensional spatial characteristics of the intersection comprise at least one item of information of each grid in the intersection, wherein the information comprises: the number of trajectory information within the grid, the average direction angle, the average velocity.
5. The method of claim 4, wherein determining the type and/or access point information for the intersection from the topological feature map comprises:
determining the type of the intersection through a convolutional neural network according to the topological characteristic diagram; and/or the presence of a gas in the gas,
and determining the access point information of the road junction through a target detection algorithm according to the topological characteristic diagram.
6. The method of claim 5, wherein determining access point information for the access point by a target detection algorithm based on the topological profile comprises:
detecting the outermost grid of the intersection through a target detection algorithm according to the topological characteristic diagram, and determining the access point information of the intersection;
and the access point information comprises the position and connectivity of the access point of the intersection.
7. The method of claim 1, wherein reconstructing the intersection based on the type of intersection and/or access point information comprises:
acquiring an intersection template corresponding to the type of the intersection;
determining the corresponding relation between the access point of the intersection and the access point of the intersection template according to the access point information of the intersection;
and rebuilding the intersection according to the determined corresponding relation.
8. The method according to any one of claims 1 to 7, wherein obtaining track information corresponding to the intersection to be processed comprises:
acquiring track information corresponding to a target area to be reconstructed in an electronic map;
determining a range frame where each intersection in the target area is located according to the track information corresponding to the target area;
determining track information corresponding to each intersection according to the range frame where each intersection is located;
wherein the intersection to be processed is any intersection in the target area.
9. The method of claim 8, wherein determining a range frame in which each intersection in the target area is located according to the trajectory information of the target area comprises:
performing grid division on the target area, and determining two-dimensional space characteristics of the target area according to track information in each grid;
and determining a range frame where each intersection of the target area is located through a target detection algorithm according to the two-dimensional space characteristics of the target area.
10. The method of claim 8, further comprising:
and after reconstructing each intersection of the target area, determining road sections among the intersections of the target area according to the track information of the target area to form a complete road network.
11. The method of claim 5, wherein the deep learning model is obtained by simultaneously learning the type of the intersection and the topological feature map through a graph convolution neural network and a convolution neural network.
12. An intersection reconstruction device, comprising:
the track information acquisition module is used for acquiring track information corresponding to the intersection to be processed;
the track information processing module is used for determining the type and/or the access point information of the intersection through a deep learning model according to the track information;
and the intersection reconstruction module is used for reconstructing the intersection according to the type and/or the access point information of the intersection.
13. The apparatus according to claim 12, wherein the trajectory information processing module is specifically configured to:
and according to the track information, constructing a topological characteristic diagram of the intersection through a deep learning model, and determining the type and/or access point information of the intersection according to the topological characteristic diagram.
14. The apparatus of claim 13, wherein the trajectory information processing module is further specifically configured to:
according to the track information, a topological characteristic diagram of the intersection is constructed through a graph convolution neural network;
and determining the type and/or access point information of the intersection according to the topological characteristic diagram.
15. The apparatus of claim 14, wherein the trajectory information processing module is further specifically configured to:
determining two-dimensional space characteristics of the intersection according to the track information of the intersection;
constructing a topological characteristic diagram of the intersection through a graph convolution neural network according to the two-dimensional space characteristics of the intersection and the continuity of track information in the intersection;
the intersection is divided into a plurality of grids, and the two-dimensional spatial characteristics of the intersection comprise at least one item of information of each grid in the intersection, wherein the information comprises: the number of trajectory information within the grid, the average direction angle, the average velocity.
16. The apparatus of claim 15, wherein the trajectory information processing module is further specifically configured to:
determining the type of the intersection through a convolutional neural network according to the topological characteristic diagram; and/or the presence of a gas in the gas,
and determining the access point information of the road junction through a target detection algorithm according to the topological characteristic diagram.
17. The apparatus of claim 16, wherein the trajectory information processing module is further specifically configured to:
detecting the outermost grid of the intersection through a target detection algorithm according to the topological characteristic diagram, and determining the access point information of the intersection;
and the access point information comprises the position and connectivity of the access point of the intersection.
18. The apparatus of claim 12, wherein the intersection reconstruction module is specifically configured to:
acquiring an intersection template corresponding to the type of the intersection;
determining the corresponding relation between the access point of the intersection and the access point of the intersection template according to the access point information of the intersection;
and rebuilding the intersection according to the determined corresponding relation.
19. The apparatus according to any one of claims 12 to 18, wherein the trajectory information obtaining module is specifically configured to:
acquiring track information corresponding to a target area to be reconstructed in an electronic map;
determining a range frame where each intersection in the target area is located according to the track information corresponding to the target area;
determining track information corresponding to each intersection according to the range frame where each intersection is located;
wherein the intersection to be processed is any intersection in the target area.
20. The apparatus of claim 19, wherein the trajectory information obtaining module is further specifically configured to:
performing grid division on the target area, and determining two-dimensional space characteristics of the target area according to track information in each grid;
and determining a range frame where each intersection of the target area is located through a target detection algorithm according to the two-dimensional space characteristics of the target area.
21. The apparatus of claim 19, further comprising: a road segment determination module; and the road section determining module is used for determining road sections among all intersections of the target area according to the track information of the target area after all intersections of the target area are reconstructed so as to form a complete road network.
22. The apparatus of claim 16, wherein the deep learning model is obtained by simultaneously learning the type of intersection and the topological feature map through a convolutional neural network and a convolutional neural network.
23. An electronic device, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any of claims 1-11.
24. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011205254.9A CN112327337B (en) | 2020-11-02 | 2020-11-02 | Intersection reconstruction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011205254.9A CN112327337B (en) | 2020-11-02 | 2020-11-02 | Intersection reconstruction method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112327337A true CN112327337A (en) | 2021-02-05 |
| CN112327337B CN112327337B (en) | 2024-04-19 |
Family
ID=74324380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011205254.9A Active CN112327337B (en) | 2020-11-02 | 2020-11-02 | Intersection reconstruction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112327337B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114201997A (en) * | 2022-02-17 | 2022-03-18 | 深圳依时货拉拉科技有限公司 | Intersection turning recognition method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109084798A (en) * | 2018-08-29 | 2018-12-25 | 武汉环宇智行科技有限公司 | Network issues the paths planning method at the control point with road attribute |
| CN110634291A (en) * | 2019-09-17 | 2019-12-31 | 武汉中海庭数据技术有限公司 | High-precision map topology automatic construction method and system based on crowdsourcing data |
| CN110728735A (en) * | 2019-09-17 | 2020-01-24 | 武汉中海庭数据技术有限公司 | Road-level topological layer construction method and system |
| CN110827544A (en) * | 2019-11-11 | 2020-02-21 | 重庆邮电大学 | Short-term traffic flow control method based on graph convolution recurrent neural network |
| CN111095291A (en) * | 2018-02-27 | 2020-05-01 | 辉达公司 | Real-time detection of lanes and boundaries by autonomous vehicles |
| CN111243277A (en) * | 2020-03-09 | 2020-06-05 | 山东大学 | Commuting vehicle space-time trajectory reconstruction method and system based on license plate recognition data |
| CN111540198A (en) * | 2020-04-17 | 2020-08-14 | 浙江工业大学 | Urban traffic situation recognition method based on directed graph convolution neural network |
| CN111583652A (en) * | 2020-05-21 | 2020-08-25 | 北京易华录信息技术股份有限公司 | Topological modeling method and system for traffic network |
-
2020
- 2020-11-02 CN CN202011205254.9A patent/CN112327337B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111095291A (en) * | 2018-02-27 | 2020-05-01 | 辉达公司 | Real-time detection of lanes and boundaries by autonomous vehicles |
| CN109084798A (en) * | 2018-08-29 | 2018-12-25 | 武汉环宇智行科技有限公司 | Network issues the paths planning method at the control point with road attribute |
| CN110634291A (en) * | 2019-09-17 | 2019-12-31 | 武汉中海庭数据技术有限公司 | High-precision map topology automatic construction method and system based on crowdsourcing data |
| CN110728735A (en) * | 2019-09-17 | 2020-01-24 | 武汉中海庭数据技术有限公司 | Road-level topological layer construction method and system |
| CN110827544A (en) * | 2019-11-11 | 2020-02-21 | 重庆邮电大学 | Short-term traffic flow control method based on graph convolution recurrent neural network |
| CN111243277A (en) * | 2020-03-09 | 2020-06-05 | 山东大学 | Commuting vehicle space-time trajectory reconstruction method and system based on license plate recognition data |
| CN111540198A (en) * | 2020-04-17 | 2020-08-14 | 浙江工业大学 | Urban traffic situation recognition method based on directed graph convolution neural network |
| CN111583652A (en) * | 2020-05-21 | 2020-08-25 | 北京易华录信息技术股份有限公司 | Topological modeling method and system for traffic network |
Non-Patent Citations (2)
| Title |
|---|
| 徐建闽等: "基于梯度提升决策树的城市车辆路径链重构", 华南理工大学学报( 自然科学版), vol. 48, no. 7, pages 55 - 64 * |
| 谭康;刘建勋;廖祝华;: "一种基于GPS轨迹的道路拓扑生成方法", 计算机科学, no. 09, pages 37 - 40 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114201997A (en) * | 2022-02-17 | 2022-03-18 | 深圳依时货拉拉科技有限公司 | Intersection turning recognition method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112327337B (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112907491B (en) | Laser point cloud loop detection method and system suitable for underground roadway | |
| Li et al. | Cross-layer attention network for small object detection in remote sensing imagery | |
| CN111694917B (en) | Vehicle abnormal track detection and model training method and device | |
| CN108256431B (en) | Hand position identification method and device | |
| CN113780270B (en) | Target detection method and device | |
| CN113343985B (en) | License plate recognition method and device | |
| CN111353580B (en) | Training method of target detection network, electronic equipment and storage medium | |
| US20230401691A1 (en) | Image defect detection method, electronic device and readable storage medium | |
| CN114842439A (en) | Cross-perception-device vehicle identification method and device, electronic device and storage medium | |
| CN112651417B (en) | License plate recognition method, device, equipment and storage medium | |
| CN112327337A (en) | Intersection reconstruction method, device, equipment and storage medium | |
| CN117083621A (en) | Detector training method, device and storage medium | |
| Eftelioglu et al. | Ring-net: road inference from gps trajectories using a deep segmentation network | |
| CN114596702A (en) | Traffic state prediction model construction method and traffic state prediction method | |
| CN113256683A (en) | Target tracking method and related equipment | |
| CN112130137A (en) | Method and device for determining lane-level track and storage medium | |
| CN117689693A (en) | Abnormal local track detection method and device based on graph comparison self-supervision learning | |
| CN114141339B (en) | Pathological image classification method, device, equipment and storage medium for membranous nephropathy | |
| CN116682018A (en) | Vehicle track prediction method, device, system and storage medium | |
| CN114090560B (en) | Lane center line generation method, device, equipment and storage medium | |
| CN116826734A (en) | Photovoltaic power generation power prediction method and device based on multi-input model | |
| Yang et al. | An instance segmentation algorithm based on improved mask R-CNN | |
| CN112133100B (en) | Vehicle detection method based on R-CNN | |
| CN114896134A (en) | Metamorphic test method, device and equipment for target detection model | |
| Zou et al. | Inertia mutation energy model to extract roads by crowdsourcing trajectories |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |