CN111914691B - Rail transit vehicle positioning method and system - Google Patents
Rail transit vehicle positioning method and system Download PDFInfo
- Publication number
- CN111914691B CN111914691B CN202010680791.2A CN202010680791A CN111914691B CN 111914691 B CN111914691 B CN 111914691B CN 202010680791 A CN202010680791 A CN 202010680791A CN 111914691 B CN111914691 B CN 111914691B
- Authority
- CN
- China
- Prior art keywords
- train
- station
- platform
- parking
- matching
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000005516 engineering process Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 238000007499 fusion processing Methods 0.000 claims 1
- 230000004807 localization Effects 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 10
- 238000009434 installation Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 230000010354 integration Effects 0.000 description 4
- 230000004927 fusion Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 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
- 230000008447 perception Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L25/00—Recording or indicating positions or identities of vehicles or trains or setting of track apparatus
- B61L25/02—Indicating or recording positions or identities of vehicles or trains
- B61L25/026—Relative localisation, e.g. using odometer
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
-
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Mechanical Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The embodiment of the invention provides a rail transit vehicle positioning method and a rail transit vehicle positioning system, comprising the following steps: acquiring real-time speed information of a train, and calculating the driving mileage of the train and the parking distance of the train each time according to the real-time speed information; performing station interval matching by using the parking interval to obtain a station interval matching result; acquiring a platform image of a train when the train stops each time, identifying the platform image based on a neural network identification technology, and acquiring a platform identification result; determining an accurate stopping platform of the train according to the station spacing matching result and the station identification result; and determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform. The rail transit vehicle positioning method and system provided by the embodiment of the invention can finish the positioning of the train on the rail line with meter-level precision only through the platform image and the vehicle speed information, and the installation and maintenance cost is low.
Description
Technical Field
The invention relates to the technical field of rail transit, in particular to a rail transit vehicle positioning method and system.
Background
Whether accurate vehicle position information can be acquired is significant for acquiring the perception environment information of the train, and the method comprises the following steps: the position of the train in the map is found through positioning, and the environment information of the sensing capability of the remote overtaking sensor can be obtained from the map.
Currently, the main current vehicle positioning methods include the following: the vehicle positioning is realized through satellite positioning systems (Global Positioning System, GPS for short), beidou and other satellite navigation systems; by establishing a high-precision point cloud map, the high-precision point cloud map is continuously matched with the point cloud in the map in the running process of the vehicle, so that the positioning of the vehicle is realized; an RFID beacon is installed on a vehicle running line in advance, the vehicle detects the beacon in real time, and the vehicle is positioned according to information provided by the beacon.
For a metro vehicle, most of the time the vehicle is driven in a tunnel environment, the vehicle cannot acquire satellite signals such as GPS and the like, and therefore positioning cannot be achieved through a satellite navigation system. The process of establishing the high-precision point cloud map is complex, the high-cost laser radar is relied on, real-time point cloud matching is needed in the running process of the train, the requirement on the computing capacity of a vehicle-mounted system is high, in addition, the environment characteristics are few, and the point cloud matching difficulty is high in a tunnel scene. The RFID beacons which are arranged on the track line in advance are adopted for positioning, a large number of beacons are required to be arranged on the track line to ensure positioning accuracy, detection equipment which is in close contact with the RFID beacons is required to be arranged on the vehicle, and the installation and maintenance costs of the hardware facilities are high.
In view of the drawbacks of the prior art, there is a need to provide a new rail transit vehicle positioning method to improve positioning accuracy and adaptability and reduce installation and maintenance costs of hardware facilities.
Disclosure of Invention
The embodiment of the invention provides a rail transit vehicle positioning method and system, which are used for solving the defects of higher installation and maintenance cost and low positioning precision of hardware facilities in the prior art.
In a first aspect, an embodiment of the present invention provides a method for positioning a rail transit vehicle, which mainly includes: acquiring real-time speed information of a train, and calculating the driving mileage of the train and the parking distance of the train each time according to the real-time speed information; performing station interval matching by using the parking interval to obtain a station interval matching result; acquiring a platform image of a train when the train stops each time, identifying the platform image based on a neural network identification technology, and acquiring a platform identification result; determining an accurate stopping platform of the train according to the station spacing matching result and the station identification result; and determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform.
Alternatively, the calculating the driving distance of the train and the parking distance of each train according to the real-time vehicle speed information mainly includes: respectively acquiring real-time vehicle speed information of the train in a time period from start to stop; integrating the real-time vehicle speed information in each time period to obtain the parking distance of the train each time; and accumulating the parking intervals of the trains each time to obtain the driving mileage of the trains.
Alternatively, the step of performing step-to-step distance matching by using the parking distance to obtain a step-to-step distance matching result mainly includes: sequentially matching the stopping distance of each train with the station distance on the train running line; if the continuous K1 parking intervals are matched with the continuous K1 station intervals, setting the station interval matching result as successful; if the continuous K1 parking intervals are not matched with the continuous K1 station intervals, setting the station interval matching result as failure; k1 is the number of parking intervals, and K1 is more than or equal to 2.
Optionally, before the step of using the parking space for step space matching, the method further comprises: selecting the longest line in the train running lines, and generating a first inter-station distance list according to the inter-station distances on the longest line; respectively extending the line which is not covered by the longest line in the train running line forwards and backwards by two inter-station distances to generate a second inter-station distance list; in the second inter-station distance list, combining inter-station distances with overlapping heads and tails to generate a third inter-station distance list; constructing a total station spacing list by the first station spacing list and the third station spacing list; the parking space of each train is matched with the station space on the train running line in sequence, and specifically, the parking space of each train is matched with the total station space list in sequence.
Optionally, the identifying the station image based on the neural network identification technology to obtain a station identification result mainly includes:
after each arrival of a train, acquiring platform images of a platform where the train is located, and sequentially arranging all the platform images according to an acquisition sequence to construct a platform image set; taking each platform image as the input of a platform identification network model in sequence, acquiring a target identification result output by the platform identification network model and corresponding to the input platform image, and constructing a target identification result set; if the continuous K2 target recognition results exist in the target recognition result set and are larger than a preset threshold, setting the station recognition result as successful; if the continuous K2 target recognition results are not in the target recognition result set and are larger than a preset threshold, setting the station recognition result as failure; k2 is the number of target recognition results, and K2 is more than or equal to 2.
Alternatively, before each station image is sequentially taken as an input of a station identification network model, the method may further include, before obtaining a target identification result corresponding to the input station image output by the station identification network model: collecting images of each platform under different weather conditions and different light conditions as training samples, and constructing a training sample set by taking an identification result corresponding to each training sample as a label; and performing iterative training on the platform identification network model by using the training sample set.
Optionally, determining the accurate stop platform of the train according to the matching result of the distance between the stations and the identification result of the platform mainly comprises the following steps: if the platform identification result is successful, determining an accurate stopping platform of the train directly according to the platform identification result; if the station identification result is failure and the station spacing matching result is successful, determining an accurate stop station of the train according to the station spacing matching result; if the station identification result is failure and the station spacing matching result is failure, the current station identification fails, and the collection of the station spacing matching result and the station identification result is continued until an accurate stop station of the train is obtained.
Alternatively, determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform mainly includes: after the accurate stopping platform of the train is obtained, determining the current positioning of the train; and determining the positioning information of the train on the running route of the train by taking the current positioning as a starting point and the running mileage of the train as a moving distance.
In a second aspect, an embodiment of the present invention further provides a rail transit vehicle positioning system, including a vehicle speed calculation unit, a station distance matching unit, a station identification unit, a station positioning unit, and a train positioning unit, where:
The vehicle speed calculation unit is used for acquiring real-time vehicle speed information of the train and calculating the driving mileage of the train and the parking distance of the train each time according to the real-time vehicle speed information; the inter-station distance matching unit is used for performing inter-station distance matching by using the parking distance to obtain an inter-station distance matching result; the platform identification unit is used for acquiring a platform image of the train when the train stops each time, identifying the platform image based on a neural network identification technology and acquiring a platform identification result; the station positioning unit is used for determining an accurate stop station of the train according to the station spacing matching result and the station identification result; and the train positioning unit is used for determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform.
In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the rail transit vehicle positioning method as described in any one of the above when the processor executes the program.
In a fourth aspect, embodiments of the present invention also provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a rail transit vehicle positioning method as described in any of the above.
The rail transit vehicle positioning method and system provided by the embodiment of the invention can finish the positioning of the train on the rail line with meter-level precision only through the platform image and the vehicle speed information, and the installation and maintenance cost is low.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a rail transit vehicle positioning method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of another rail transit vehicle positioning method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a train route according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a first inter-station distance list provided in an embodiment of the present invention;
fig. 5 is a schematic diagram of a second inter-station distance list provided in an embodiment of the present invention;
fig. 6 is a schematic diagram of construction of a third inter-station distance list according to an embodiment of the present invention;
FIG. 7 is a schematic flow chart of determining an accurate stop platform of a train according to a station distance matching result and a station identification result according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a rail transit vehicle positioning system according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to effectively overcome the defects of high installation and maintenance cost of hardware facilities and influence on positioning accuracy due to environmental interference in the prior art when a train is positioned, the embodiment of the invention provides a low-cost rail transit vehicle positioning method, as shown in fig. 1, which comprises the following steps:
Step S1: acquiring real-time speed information of a train, and calculating the driving mileage of the train and the parking interval of the train each time according to the real-time speed information;
step S2: performing station interval matching by using the parking interval to obtain a station interval matching result;
step S3: acquiring a platform image of a train when the train stops each time, identifying the platform image based on a neural network identification technology, and acquiring a platform identification result;
step S4: determining an accurate stopping platform of the train according to the station spacing matching result and the platform identification result;
step S5: and determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform.
In general, the technical scheme of the application can realize the positioning of the train only by acquiring the platform image shot after the train enters each platform and combining the speed information. The specific positioning step comprises the following steps:
firstly, the collection and storage of the real-time speed information of the train can be realized by utilizing a wheel speed meter or a millimeter wave radar or a laser radar arranged on the train, and the embodiment of the invention does not specifically limit the speed acquisition mode.
Further, since the movement distance in a period of time can be obtained by integrating the speed in the period of time, in the embodiment of the invention, the parking space of each train can be obtained by integrating the real-time vehicle speed information. Each parking space is the time when the train is parked at the last speed of 0, namely the starting point of integration is the last parking position of the train, and the end point of integration is the current position. In the embodiment of the invention, the real-time vehicle speed information can be subjected to sectional integration, so that a plurality of parking spaces which are sequentially arranged in sequence are obtained.
Further, the driving mileage of the train in any time period can be determined in an accumulation mode.
Further, in the embodiment of the present invention, matching of sequential inter-station distances may be performed each time a train is stopped, and the specific operation method thereof includes: and matching the parking space with the actual station space on the line by using the parking space of the last several times so as to determine the station information corresponding to the current parking position. For example, the obtained parking intervals (for example, parking intervals between four stations) are sequentially matched with the actual station intervals on the line, and if the obtained parking intervals exactly match with the four station intervals in the actual station intervals, it can be determined that the four stations correspond to the four stations in the actual station intervals. It should be noted that, in the actual matching process, the number of parking spaces for matching may be appropriately increased to increase the accuracy of detection, and the embodiment of the present invention is not specifically limited to the specific number of matching.
Optionally, in the embodiment of the present invention, after matching is completed, when the stored total mileage exceeds a certain threshold, a deletion operation may be performed on the earliest recorded parking space, so as to ensure a lower system memory occupation.
Further, after each arrival of the train, the image of the station is acquired by using a camera preset on the train, and the image is identified by using a neural network model which is trained in advance, so as to determine the name of the station as a station identification result. Or, the neural network model is utilized to identify the input station image so as to identify the corresponding relation between the current station and the station on the line map, such as the matching degree, as the station identification result.
And then, fusing the station spacing matching result and the station identification result which are acquired at the same time, and determining an accurate stop station of the train. For example: if the current station where the train is located is obtained to be matched with the F station on the train driving line according to the station spacing matching result, and the station identification result also shows that the matching degree of the current station and the F station is greater than a preset threshold (for example, 95%), the current station can be determined to be the F station.
And finally, determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform. For example: if the current station is determined to be the F station, the real-time positioning information of the train can be determined on the running line of the train at any time according to the running mileage of the train after the train starts from the F station.
According to the rail transit vehicle positioning method provided by the embodiment of the invention, the platform identification result and the station spacing matching result are respectively determined by collecting the platform image and the real-time vehicle speed information of the train when the train is parked each time, and the two results are fused to determine the parking platform of the train, so that the real-time positioning of the train is performed by combining the platform information and the driving mileage information of the train, the positioning of the train on the rail line in meter-level precision can be completed through the platform image and the vehicle speed information, and the installation and maintenance cost is low.
Based on the content of the above embodiment, as an optional embodiment, the calculating the driving mileage of the train and the parking space of the train according to the real-time vehicle speed information mainly includes, but is not limited to, the following steps: respectively acquiring real-time vehicle speed information of the train in a time period from start to stop; integrating the real-time vehicle speed information in each time period to obtain the parking distance of the train each time; and accumulating the parking intervals of the trains each time to obtain the driving mileage of the trains.
Specifically, in the embodiment of the present invention, the real-time vehicle speed information may be measured by a millimeter wave radar, a laser radar, a wheel speed meter, or the like provided on the train and stored in the vehicle-mounted computer. After each train enters a station, the station spacing calculation and matching can be performed after each stop. The real-time vehicle speed information of the train in the time period from start to stop can be integrated sequentially, and the driving distance in the time period can be obtained. According to the method, real-time vehicle speed information can be divided into continuous driving sections according to the speed of 0, and then each parking distance can be obtained.
If the historical driving mileage of the train needs to be obtained, only the starting platform and the target platform need to be obtained, the driving mileage from the starting point to the target platform can be obtained by accumulating the parking intervals. Further, if the current driving mileage of the train needs to be calculated, the current departure platform can be obtained, and then the current driving mileage of the train can be calculated and obtained by combining with an on-board odometer.
According to the rail transit vehicle positioning method provided by the embodiment of the invention, the driving distance of the train and the stopping distance of the train each time can be obtained only according to the speed information, the current platform of the train can be deduced through the matching of the station distance, and then the driving distance of the train is combined, so that the accurate positioning of the train is realized. By adopting the method, other hardware facilities are not required to be installed, the input of external signals such as GPS is not relied on, the high reliability of train positioning information is ensured, and the consumption of manpower and material resources is reduced.
Based on the content of the foregoing embodiment, as an alternative embodiment, as shown in part in fig. 2, the foregoing performing inter-station distance matching using parking distance, and obtaining an inter-station distance matching result may include the following steps:
Sequentially matching the stopping distance of each train with a station distance list on a train running line; if the continuous K1 parking intervals are matched with the continuous K1 station intervals, setting the station interval matching result as successful; if the continuous K1 parking intervals are not matched with the continuous K1 station intervals, setting the station interval matching result as failure; k1 is the number of parking intervals, and K1 is more than or equal to 2.
The inter-station distance matching can be performed at each parking time, and the specific operation method can be as follows: according to the real-time vehicle speed information, calculating each parking distance; then, the last parking distance is matched with an actual station distance list on a train driving line, so that station information corresponding to the current parking position is determined.
Fig. 3 is a schematic diagram of a train driving route according to an embodiment of the present invention, taking the driving route shown in fig. 3 as an example, assuming that 3 parking spaces in succession are exactly matched with 1-2-3 station spaces on the route by calculation, it can be explained that the 3 parking spaces have a relatively large probability of 1-2-3 station spaces. Therefore, the successful matching result of the inter-station distance can be determined, and the station where the train is currently located can be positioned according to the successful matching result. If the above-mentioned 3 continuous parking spaces are matched with all the distances between stations in the driving line shown in fig. 3, if there is no continuous 3 distances between stations matched with the distances between stations, it is indicated that the distance between stations matching result is set to fail, and the matching can be performed by using other continuous parking spaces.
According to the rail transit vehicle positioning method provided by the embodiment of the invention, the positioning of the station where the train is currently positioned is realized by matching the plurality of continuous train lifting distances with the station distance list on the train driving line, the input of external signals such as GPS is not relied on, the high reliability of train positioning information is ensured, and other hardware facilities are required to be installed, so that the installation and maintenance cost is greatly reduced.
Based on the content of the above embodiment, as an alternative embodiment, before the matching of the inter-stop distance by using the inter-stop distance, the method further includes: selecting the longest line in the train running lines, and generating a first inter-station distance list according to the inter-station distances on the longest line; respectively extending the line which is not covered by the longest line in the train running line forwards and backwards by two inter-station distances to generate a second inter-station distance list; in the second inter-station distance list, combining inter-station distances with overlapping heads and tails to generate a third inter-station distance list; constructing a total station spacing list by the first station spacing list and the third station spacing list; the stopping distance of each train is matched with the station distance on the train running line in sequence, and specifically, the stopping distance of each train is matched with the total station distance list in sequence.
In an actual running route of a train, there may be a branch route and an advanced turn-back area and a plurality of turn-back points in the running route of the train, as in the route shown in fig. 3, the inter-station distances 3, 4, 5 are three consecutive stations, 3, 17, 18 are also three consecutive stations, A1, A2, 1 are three consecutive stations, and B1, B2, 1 are also three consecutive stations. Thus, one inter-site distance list cannot cover all three consecutive inter-site distances. Therefore, in the embodiment of the invention, a plurality of inter-station distance lists are designed to be assembled into a total inter-station distance list, and parking distances and the total inter-station distance list are matched in sequence.
The manufacturing method of the inter-station distance list can be as follows:
first, the longest one of the loops or unidirectional paths is selected and a first inter-station distance list is generated using the inter-station distances thereof, as shown in fig. 4.
Then, each uncovered line is extended back and forth by two inter-station distances, and a second inter-station distance list is generated, as shown in fig. 5. Wherein the light boxes represent lines not covered by the longest line in the previous step, and the dark boxes represent two inter-station distances extending the uncovered line forward and backward.
Further, the second inter-station distance list generated by construction is simplified, which comprises the following steps: the overlapping end-to-end inter-site distance lists are combined to remove redundancy, resulting in a third inter-site distance list as shown in fig. 6. Where inter-site distance 15 and inter-site distance 2 represent the overlapping inter-site distances in the previous step, i.e., the second inter-site distance list.
And finally, combining the third station spacing list obtained in a simplified way with the first station spacing list to form a complete station spacing list, namely obtaining a total station spacing list.
Because the inter-station distance matching needs to consider the matching condition of inter-station distances (preferably more than 2 inter-station distances) of continuous multiple stations, for complex lines, bifurcation intersections exist in the lines, and the first two inter-station distances of a certain inter-station distance have multiple conditions, the accuracy of matching is effectively improved by constructing a total inter-station distance list containing all driving conditions in advance in the embodiment of the invention.
It should be noted that, according to the rail transit vehicle positioning method provided by the embodiment of the invention, the accurate stop platform determination of the train can be realized by independently using the station spacing matching method, and only a proper number of continuous stop spacing and a total station spacing list are selected for matching when the platform matching is carried out. Alternatively, in the case that the matching result is successful, other continuous parking intervals may be extracted and matched with the total station interval list again for verification, which is not particularly limited in the embodiment of the present invention.
Based on the foregoing embodiments, as an alternative embodiment, as shown in fig. 2, the identifying, based on the neural network identification technology, the station image, and obtaining the station identification result, includes: after each arrival of a train, acquiring platform images of a platform where the train is located, and sequentially arranging all the platform images according to an acquisition sequence to construct a platform image set; taking each platform image as the input of a platform identification network model in sequence, acquiring a target identification result output by the platform identification network model and corresponding to the input platform image, and constructing a target identification result set; if the continuous K2 target recognition results exist in the target recognition result set and are larger than a preset threshold, setting the station recognition result as successful; if the continuous K2 target recognition results are not in the target recognition result set and are larger than a preset threshold, setting the station recognition result as failure; k2 is the number of target recognition results, and K2 is more than or equal to 2.
Specifically, the embodiment of the invention also provides an image recognition technology, which is used for positioning the current accurate stopping platform of the train through a platform recognition method, mainly comprising the steps of recognizing the corresponding relation between the current platform and the platform on the line map through the image of the platform by using a trained deep learning model so as to obtain the position of the train when stopping.
The whole method flow for identifying by using the platform image comprises the following steps: the process of acquiring station images and computing network models (i.e., station identification process).
Wherein, since the purpose of station identification is to find the correspondence between the current station and the stations on the line map, the selected neural network type can adopt a classification network, such as ResNet, mobileNet
Because the platform image is identified, the platform identification is only needed when the train stops each time. The stopping time of the train at the station is generally 20 seconds or more, so the recognition speed of the station recognition network is low, so long as the result can be recognized during stopping.
The output result of the station identification network is the normalized matching probability of the current station and each station on the whole train operation line, and in order to ensure the reliability of the identification result, the station identification is considered successful only when the maximum matching probability is greater than a preset threshold (e.g. 0.9) for K2 times (e.g. 3 times) continuously.
It should be noted that, when the accurate stop platform of the train is determined according to the platform recognition result alone, the accurate stop platform is easily limited by light and shooting angle, and an incorrect recognition result is easily obtained, so that the positioning accuracy of the train is affected.
According to the method and the device for positioning the train, the accurate stopping platform of the train is comprehensively deduced according to the platform identification result of deep learning and the result obtained by matching the distance between the stations, and then the positioning information of the train is finally determined according to the driving mileage of the train from the accurate stopping platform, so that the positioning accuracy of the train is effectively improved, other hardware facilities are not required to be preset in the positioning process, and the cost of equipment purchase and maintenance is reduced.
Based on the foregoing embodiment, as an alternative embodiment, before each station image is sequentially taken as an input of a station identification network model, the method further includes, before obtaining a target identification result corresponding to the input station image output by the station identification network model: collecting images of each platform under different weather conditions and different light conditions as training samples, and constructing a training sample set by taking an identification result corresponding to each training sample as a label; and performing iterative training on the platform identification network model by using the training sample set.
In order to ensure the reliability and precision of the utilized platform recognition network model, in the process of collecting training set data, platform images under different weather conditions and different light conditions are fully collected to serve as input of model training, and meanwhile, corresponding recognition labels are set for each sample image for training. Alternatively, the input data of the model training may be a platform image captured by the vehicle-mounted camera when each platform is parked; the label of each image is the name or ID of the respective station. In order to ensure the reliability of the platform identification network, the platform images under different weather conditions and different light conditions should be fully acquired in the process of acquiring the training set data.
Based on the content of the foregoing embodiment, as an optional embodiment, the determining an accurate stopping station of the train according to the station distance matching result and the station identification result may include: if the platform identification result is successful, determining an accurate stopping platform of the train directly according to the platform identification result; if the station identification result is failure and the station spacing matching result is successful, determining an accurate stop station of the train according to the station spacing matching result; if the station identification result is failure and the station spacing matching result is failure, the current station identification fails, and the collection of the station spacing matching result and the station identification result is continued until an accurate stop station of the train is obtained.
Specifically, as shown in fig. 7, the embodiment of the invention provides a method for determining an accurate stop platform of a train by combining a platform identification result and a station spacing matching result, and the results of two algorithms are required to be chosen and removed under the condition of consistency or inconsistency due to the platform identification result and the station spacing matching result. The specific fusion scheme for station identification and station spacing matching is as follows:
1) If the station identification result is successful
In the embodiment of the invention, the filtering condition that the continuous multiple times of identification is successful is added, so that the false identification rate of the station identification is very low, and if the station identification is successful, the station identification result is believed to be correct, so that the accurate stop station of the train is directly determined according to the station identification result.
2) If the station identification result is failure, but the station spacing matching result of the continuous multiple stations is successful.
If the station identification fails (tail end operation or light is bad), but the number of successful stations matched with the continuous parking space exceeds K2 (such as 3), the accurate parking station of the train is determined according to the station space matching result.
3) If the station identification result is failure and the station spacing matching result is failure
If the station identification fails and the number of successful stations of the continuous matching of the station spacing is less than 3 stations, the current station identification fails.
According to the rail transit vehicle positioning method provided by the embodiment of the invention, the specific fusion of the station identification and the station spacing matching is effectively realized by determining the fusion strategy which takes the station identification as a main part and takes the station spacing matching as an auxiliary part, so that the accuracy of positioning the current stop station of the train is effectively improved, and the accuracy of train positioning is improved.
Based on the foregoing embodiment, as an optional embodiment, the determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform may specifically include:
after the accurate stopping platform of the train is obtained, determining the current positioning of the train; and determining the positioning information of the train on the running route of the train by taking the current positioning as a starting point and the running mileage of the train as a moving distance.
According to the rail transit vehicle positioning method provided by the embodiment of the invention, after the information of the train stopping platform is obtained, the current positioning information of the train is known, and after the train starts, the running mileage of the train is calculated by taking the platform as a starting point, so that the real-time positioning information of the train can be obtained.
The embodiment of the invention also provides a rail transit vehicle positioning system, as shown in fig. 8, which comprises, but is not limited to, a vehicle speed operation unit 1, a station distance matching unit 2, a station identification unit 3, a station positioning unit 4 and a train positioning unit 5, wherein: the vehicle speed operation unit 1 is mainly used for acquiring real-time vehicle speed information of a train and calculating the driving mileage of the train and the parking distance of the train each time according to the real-time vehicle speed information; the inter-station distance matching unit 2 is mainly used for performing inter-station distance matching by using parking distance to obtain an inter-station distance matching result; the platform identification unit 3 is mainly used for acquiring a platform image of a train when the train stops each time, and identifying the platform image based on a neural network identification technology to acquire a platform identification result; the station positioning unit 4 is mainly used for determining an accurate stop station of the train according to the station spacing matching result and the station identification result; the train positioning unit 5 is mainly used for determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform.
Specifically, in the rail transit vehicle positioning system provided by the embodiment of the invention, real-time speed information of a train is acquired through the speed operation unit 1, and after the driving mileage of the train and the parking distance of each time of the train are determined through integration and accumulation operation, the parking distance of each time of the train is input into the inter-station distance matching unit 2 to complete inter-station distance matching. The platform identification unit 3 collects the platform image when each time of parking, and inputs the platform image into a pre-trained neural network model to perform platform identification. Then, the accurate stopping platform of the train is determined by the platform positioning unit 4 according to the operation results of the platform spacing matching unit 2 and the platform identification unit 3. Finally, the train positioning unit 5 combines the running mileage of the train calculated in the vehicle speed calculation unit 1 according to the calculation result of the platform positioning unit 4, so that the accurate positioning of the train can be realized.
According to the rail transit vehicle positioning system provided by the embodiment of the invention, the platform identification result and the station spacing matching result are respectively determined by collecting the platform image and the real-time vehicle speed information of the train when the train is parked each time, and the two results are fused to determine the parking platform of the train, so that the real-time positioning of the train is performed by combining the platform information and the driving mileage information of the train, the positioning of the train on the rail line in meter-level precision can be completed through the platform image and the vehicle speed information, and the installation and maintenance cost is low.
It should be noted that, when the rail transit vehicle positioning system provided by the embodiment of the present invention is specifically executed, the rail transit vehicle positioning method described in any one of the above embodiments may be operated, and this embodiment will not be described in detail.
Fig. 9 illustrates a physical schematic diagram of an electronic device, as shown in fig. 9, which may include: processor 910, communication interface (Communications Interface), memory 930, and communication bus 940, wherein processor 910, communication interface 920, and memory 930 communicate with each other via communication bus 940. The processor 910 may invoke logic instructions in the memory 930 to perform a rail transit vehicle positioning method comprising: acquiring real-time speed information of a train, and calculating the driving mileage of the train and the parking distance of the train each time according to the real-time speed information; performing station interval matching by using the parking interval to obtain a station interval matching result; acquiring a platform image of a train when the train stops each time, identifying the platform image based on a neural network identification technology, and acquiring a platform identification result; determining an accurate stopping platform of the train according to the station spacing matching result and the station identification result; and determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform.
Further, the logic instructions in the memory 930 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, embodiments of the present invention also provide a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method for locating a rail transit vehicle provided by the above method embodiments, the method comprising: acquiring real-time speed information of a train, and calculating the driving mileage of the train and the parking distance of the train each time according to the real-time speed information; performing station interval matching by using the parking interval to obtain a station interval matching result; acquiring a platform image of a train when the train stops each time, identifying the platform image based on a neural network identification technology, and acquiring a platform identification result; determining an accurate stopping platform of the train according to the station spacing matching result and the station identification result; and determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform.
In yet another aspect, embodiments of the present invention further provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the method for positioning rail transit vehicles provided by the above embodiments, the method comprising: acquiring real-time speed information of a train, and calculating the driving mileage of the train and the parking distance of the train each time according to the real-time speed information; performing station interval matching by using the parking interval to obtain a station interval matching result; acquiring a platform image of a train when the train stops each time, identifying the platform image based on a neural network identification technology, and acquiring a platform identification result; determining an accurate stopping platform of the train according to the station spacing matching result and the station identification result; and determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A rail transit vehicle positioning method, comprising:
acquiring real-time speed information of a train, and calculating the driving mileage of the train and the parking interval of the train each time according to the real-time speed information;
performing inter-station distance matching by using the parking distance to obtain an inter-station distance matching result; the station spacing matching is performed during each stop; the step of utilizing the parking space to carry out station space matching and obtaining the station space matching result comprises the following steps: matching the parking space of the last several times with an actual station space list on a train driving line to determine station information corresponding to the current parking position; if the continuous K1 parking intervals are matched with the continuous K1 station intervals, setting the station interval matching result as successful; if the continuous K1 parking intervals are not matched with the continuous K1 station intervals, setting the station interval matching result as failure; k1 is the number of parking intervals, and K1 is more than or equal to 2;
acquiring a platform image of a train when the train is stopped each time, and identifying the platform image based on a neural network identification technology to acquire a platform identification result;
determining an accurate stopping platform of the train according to the station spacing matching result and the platform identification result;
Determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform;
the step of determining the accurate stop platform of the train according to the station spacing matching result and the platform identification result comprises the following steps: the station spacing matching result and the station identification result which are acquired at the same time are fused, and an accurate stop station of the train is determined;
the step of determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform comprises the following steps: after the accurate stopping platform of the train is obtained, determining the current positioning of the train; and determining the positioning information of the train on the running route of the train by taking the current positioning as a starting point and the running mileage of the train as a moving distance.
2. The method for locating a rail transit vehicle according to claim 1, wherein calculating a driving distance of the train and a parking distance of the train each time based on the real-time vehicle speed information comprises:
respectively acquiring real-time vehicle speed information of the train in a time period from start to stop;
integrating the real-time vehicle speed information in each time period to obtain the parking distance of the train each time;
And accumulating the parking intervals of the trains each time to obtain the driving mileage of the trains.
3. The rail transit vehicle positioning method according to claim 1, characterized by further comprising, before the inter-stop distance matching using the parking distance:
selecting a longest line in train running lines, and generating a first station spacing list according to the station spacing on the longest line;
respectively extending two inter-station distances forwards and backwards on a line which is not covered by the longest line in the train running line, and generating a second inter-station distance list;
in the second inter-station distance list, combining inter-station distances with overlapping heads and tails to generate a third inter-station distance list;
constructing a total station spacing list from the first station spacing list and the third station spacing list;
the parking space of each train is matched with the station space on the train running line in sequence, and particularly the parking space of each train is matched with the total station space list in sequence.
4. The method for locating a rail transit vehicle according to claim 1, wherein the identifying the platform image based on the neural network identification technology, and obtaining the platform identification result, comprises:
After each arrival of a train, acquiring platform images of a platform where the train is located, and sequentially arranging all the platform images according to an acquisition sequence to construct a platform image set;
taking each platform image as the input of a platform identification network model, acquiring a target identification result output by the platform identification network model and corresponding to the input platform image, and constructing a target identification result set;
if the continuous K2 target recognition results exist in the target recognition result set and are larger than a preset threshold, setting the station recognition result as successful;
if the continuous K2 target recognition results are not in the target recognition result set and are larger than a preset threshold, setting the station recognition result as failure;
k2 is the number of target recognition results, and K2 is more than or equal to 2.
5. The method according to claim 4, wherein before sequentially taking each of the station images as an input of a station identification network model, obtaining a target identification result corresponding to the input station image output by the station identification network model, further comprising:
collecting images of each platform under different weather conditions and different light conditions as training samples, and constructing a training sample set by taking an identification result corresponding to each training sample as a label;
And performing iterative training on the platform identification network model by using the training sample set.
6. The method for locating a rail transit vehicle according to claim 1, wherein said determining an exact stop station of a train based on said station pitch matching result and said station identification result comprises:
if the platform identification result is successful, determining an accurate stopping platform of the train directly according to the platform identification result;
if the station identification result is failure and the station spacing matching result is successful, determining an accurate stop station of the train according to the station spacing matching result;
if the station identification result is failure and the station spacing matching result is failure, the current station identification fails, and the collection of the station spacing matching result and the station identification result is continued until an accurate stop station of the train is obtained.
7. The method for locating a rail transit vehicle as claimed in claim 1, wherein the determining the locating information of the train according to the driving mileage of the train from the accurate stopping station comprises:
after the accurate stopping platform of the train is obtained, determining the current positioning of the train;
And determining the positioning information of the train on the running route of the train by taking the current positioning as a starting point and the running mileage of the train as a moving distance.
8. A rail transit vehicle positioning system, comprising:
the vehicle speed calculation unit is used for acquiring real-time vehicle speed information of the train and calculating the driving mileage of the train and the parking distance of the train each time according to the real-time vehicle speed information;
the inter-station distance matching unit is used for performing inter-station distance matching by utilizing the parking distance to obtain an inter-station distance matching result; the station spacing matching is performed during each stop; the station spacing matching unit is specifically used for matching the nearest parking spacing with an actual station spacing list on a train driving line so as to determine station information corresponding to the current parking position; if the continuous K1 parking intervals are matched with the continuous K1 station intervals, setting the station interval matching result as successful; if the continuous K1 parking intervals are not matched with the continuous K1 station intervals, setting the station interval matching result as failure; k1 is the number of parking intervals, and K1 is more than or equal to 2;
the platform identification unit is used for acquiring a platform image of the train when the train stops each time, and identifying the platform image based on a neural network identification technology to acquire a platform identification result;
The station positioning unit is used for determining an accurate stop station of the train according to the station spacing matching result and the station identification result; the station positioning unit is specifically used for carrying out fusion processing on station spacing matching results and station identification results which are acquired at the same time, and determining an accurate stop station of the train;
the train positioning unit is used for determining the positioning information of the train according to the driving mileage of the train from the accurate stopping platform; the train positioning unit is specifically used for determining the current positioning of the train after acquiring the accurate stopping platform of the train; and determining the positioning information of the train on the running route of the train by taking the current positioning as a starting point and the running mileage of the train as a moving distance.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the rail transit vehicle localization method according to any one of claims 1 to 7 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010680791.2A CN111914691B (en) | 2020-07-15 | 2020-07-15 | Rail transit vehicle positioning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010680791.2A CN111914691B (en) | 2020-07-15 | 2020-07-15 | Rail transit vehicle positioning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111914691A CN111914691A (en) | 2020-11-10 |
| CN111914691B true CN111914691B (en) | 2024-03-19 |
Family
ID=73281019
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010680791.2A Active CN111914691B (en) | 2020-07-15 | 2020-07-15 | Rail transit vehicle positioning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111914691B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4067202A1 (en) * | 2021-03-31 | 2022-10-05 | Siemens Mobility GmbH | Method and assembly for locating a track-bound vehicle in a route network following start-up of the vehicle |
| CN115447639B (en) * | 2022-09-22 | 2024-01-02 | 中车成都机车车辆有限公司 | Parking precision testing method, device, equipment and readable storage medium |
| CN115527199B (en) * | 2022-10-31 | 2023-05-12 | 通号万全信号设备有限公司 | Rail transit train positioning method, device, medium and electronic equipment |
| CN116985872B (en) * | 2023-09-25 | 2024-03-26 | 今创集团股份有限公司 | High-speed rail stop position detection method, platform screen door control method and system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5987378A (en) * | 1996-10-24 | 1999-11-16 | Trimble Navigation Limited | Vehicle tracker mileage-time monitor and calibrator |
| CN102495963A (en) * | 2011-12-06 | 2012-06-13 | 苏州大学 | Train operation simulation quick calculation method and system |
| CN102717817A (en) * | 2012-06-27 | 2012-10-10 | 李志恒 | System and method for publishing information at high speed railway platform |
| CN103295413A (en) * | 2013-05-30 | 2013-09-11 | 天脉聚源(北京)传媒科技有限公司 | Public transport vehicle information display system and method |
| CN105882684A (en) * | 2016-05-18 | 2016-08-24 | 唐智科技湖南发展有限公司 | Method for deciding urban rail transit kilometer posts |
| CN106710218A (en) * | 2017-03-09 | 2017-05-24 | 北京公共交通控股（集团）有限公司 | Method for predicting arrival time of bus |
| JP2018179572A (en) * | 2017-04-05 | 2018-11-15 | 日鉄住金レールウェイテクノス株式会社 | Railway vehicle travelling route identification method |
| EP3456606A1 (en) * | 2017-09-15 | 2019-03-20 | Aktiebolaget SKF | Position determination method and system |
| CN110196065A (en) * | 2019-06-04 | 2019-09-03 | 北京磁浮交通发展有限公司 | A kind of speed measuring and calculating of magnetic suspension train and Method for Calculate Mileage and system |
| WO2020020298A1 (en) * | 2018-07-26 | 2020-01-30 | 比亚迪股份有限公司 | Unmanned vehicle control method and apparatus |
| WO2020083103A1 (en) * | 2018-10-24 | 2020-04-30 | 中车株洲电力机车研究所有限公司 | Vehicle positioning method based on deep neural network image recognition |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6754444B2 (en) * | 2016-11-29 | 2020-09-09 | 三菱重工機械システム株式会社 | Map matching device, map matching system, map matching method and program |
-
2020
- 2020-07-15 CN CN202010680791.2A patent/CN111914691B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5987378A (en) * | 1996-10-24 | 1999-11-16 | Trimble Navigation Limited | Vehicle tracker mileage-time monitor and calibrator |
| CN102495963A (en) * | 2011-12-06 | 2012-06-13 | 苏州大学 | Train operation simulation quick calculation method and system |
| CN102717817A (en) * | 2012-06-27 | 2012-10-10 | 李志恒 | System and method for publishing information at high speed railway platform |
| CN103295413A (en) * | 2013-05-30 | 2013-09-11 | 天脉聚源(北京)传媒科技有限公司 | Public transport vehicle information display system and method |
| CN105882684A (en) * | 2016-05-18 | 2016-08-24 | 唐智科技湖南发展有限公司 | Method for deciding urban rail transit kilometer posts |
| CN106710218A (en) * | 2017-03-09 | 2017-05-24 | 北京公共交通控股（集团）有限公司 | Method for predicting arrival time of bus |
| JP2018179572A (en) * | 2017-04-05 | 2018-11-15 | 日鉄住金レールウェイテクノス株式会社 | Railway vehicle travelling route identification method |
| EP3456606A1 (en) * | 2017-09-15 | 2019-03-20 | Aktiebolaget SKF | Position determination method and system |
| WO2020020298A1 (en) * | 2018-07-26 | 2020-01-30 | 比亚迪股份有限公司 | Unmanned vehicle control method and apparatus |
| WO2020083103A1 (en) * | 2018-10-24 | 2020-04-30 | 中车株洲电力机车研究所有限公司 | Vehicle positioning method based on deep neural network image recognition |
| CN110196065A (en) * | 2019-06-04 | 2019-09-03 | 北京磁浮交通发展有限公司 | A kind of speed measuring and calculating of magnetic suspension train and Method for Calculate Mileage and system |
Non-Patent Citations (5)
| Title |
|---|
| Dilution of Precision in Three Dimensional Angle-of-Arrival Positioning Systems;Qiang Wang等;Journal of Electrical Engineering & Technology;第14卷;2583–2593 * |
| Map matching for low-sampling-rate GPS trajectories by exploring real-time moving directions;Yu-Ling Hsueh等;Information Sciences;第433–434卷;55-69 * |
| 基于道岔曲线信息的列车定位方法研究;王剑 等;交通运输系统工程与信息;第10卷(第02期);64-69 * |
| 应用智能公交和路网数据的城市公交站点出行计算模型与评价;李佳怡;中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑(第（2018）01期);C034-463 * |
| 铁路货车运行里程统计系统设计与应用;钱琳 等;中国智能交通协会.第十四届中国智能交通年会论文集;655-663 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111914691A (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111914691B (en) | Rail transit vehicle positioning method and system | |
| CN109484435B (en) | Train positioning method and device suitable for intelligent rail transit detection system | |
| CN109084786B (en) | Map data processing method | |
| CN112286206B (en) | Automatic driving simulation method, system, equipment, readable storage medium and platform | |
| CN107792077A (en) | For confirming that road section is appropriate for the method and system that autonomous vehicle drives | |
| CN105676251A (en) | Vehicle passenger identification | |
| CN111742326A (en) | Lane line detection method, electronic device, and storage medium | |
| CN105336166A (en) | Traffic characteristic parameter extraction method based on vehicle Bluetooth | |
| CN111224710A (en) | Virtual transponder capturing method and system based on satellite space distribution inspection | |
| CN106463050A (en) | Method for processing measurement data of a vehicle in order to determine the start of a search for a parking space and computer program product | |
| CN115148031B (en) | Multi-sensor high-precision positioning method for parking lot inspection vehicle | |
| CN111539305B (en) | Map construction method and system, vehicle and storage medium | |
| CN113834489A (en) | Navigation path planning method and device | |
| CN113963550A (en) | Ambiguous path identification method and device and electronic equipment | |
| US20220266856A1 (en) | Platform for perception system development for automated driving systems | |
| CN113808414B (en) | Road load determination method, device and storage medium | |
| CN112633812B (en) | Track segmentation method, device, equipment and storage medium for freight vehicle | |
| CN112085034A (en) | Rail transit train positioning method and system based on machine vision | |
| CN117612127A (en) | Scene generation method and device, storage medium and electronic equipment | |
| CN106803353A (en) | Method and onboard system for determining the transformation rule of traffic lights | |
| CN114563007B (en) | Obstacle motion state prediction method, obstacle motion state prediction device, electronic device, and storage medium | |
| US11983918B2 (en) | Platform for perception system development for automated driving system | |
| US20230236020A1 (en) | System and Method for Map Matching GNSS Positions of a Vehicle | |
| Roth et al. | An open data set for rail vehicle positioning experiments | |
| CN115667849A (en) | Method for determining a starting position of a vehicle |
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 |