CN115792989B - Positioning method and system for electric bicycle - Google Patents
Positioning method and system for electric bicycle Download PDFInfo
- Publication number
- CN115792989B CN115792989B CN202310053751.9A CN202310053751A CN115792989B CN 115792989 B CN115792989 B CN 115792989B CN 202310053751 A CN202310053751 A CN 202310053751A CN 115792989 B CN115792989 B CN 115792989B
- Authority
- CN
- China
- Prior art keywords
- data
- positioning
- electric bicycle
- state
- acquiring
- 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 38
- 238000004891 communication Methods 0.000 claims abstract description 60
- 230000002159 abnormal effect Effects 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims description 98
- 239000013598 vector Substances 0.000 claims description 24
- 230000004927 fusion Effects 0.000 claims description 18
- 238000013507 mapping Methods 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 230000001133 acceleration Effects 0.000 claims description 5
- 230000004931 aggregating effect Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a positioning method and a system for an electric bicycle, comprising the following steps: acquiring satellite positioning data, base station communication data and IMU data of a target electric bicycle to form self-state data of the electric bicycle; according to the self state data, the initial positioning of the target electric bicycle is obtained, the self state data of other electric bicycles in a preset range are obtained for time synchronization, the self state data of the electric bicycles successfully matched in the time synchronization in the preset range are mapped to the same positioning space for auxiliary positioning, the positioning information and relative observation data of the other electric bicycles are used for positioning compensation of the target electric bicycle, a final positioning result is obtained, and the abnormal safety condition of track information analysis is obtained. The invention realizes high-precision positioning of the electric bicycle, and safety analysis is carried out through the motion trail and the running state of the electric bicycle, so that the travel safety of a user is improved, and meanwhile, the property loss is effectively avoided.
Description
Technical Field
The invention relates to the technical field of vehicle positioning, in particular to a method and a system for positioning an electric bicycle.
Background
The electric bicycle is the most common convenient transportation tool in life, and the electric bicycle becomes the first-choice transportation tool for people to go out in short distance by virtue of the advantages of small size, convenience, flexibility and easy learning. In addition, with the continuous development and perfection of satellite technology, satellite technology has been widely used in the fields of geographic information acquisition, cargo transportation, vehicle monitoring, etc. Today, the information age has come, and under the conditions that satellite technology is continuously perfected, 5G networks are commonly used and Geographic Information System (GIS) technology is gradually mature, the existing vehicle monitoring system is rapidly developed. At present, the number of electric bicycles is rapidly increased, and the traffic safety problem is also accompanied. Therefore, under the digital environment of rapid increase of vehicles and developed communication, how to realize high-precision positioning monitoring of the electric bicycle and construct a complete electric bicycle positioning management system are one of the problems which are particularly urgent to be solved.
Disclosure of Invention
In order to solve at least one of the above technical problems, the present invention provides a method and a system for positioning an electric bicycle.
The first aspect of the present invention provides a positioning method for an electric bicycle, comprising:
acquiring satellite positioning data, base station communication data and IMU data of a target electric bicycle, and carrying out data fusion on the satellite positioning data, the base station communication data and the IMU data to acquire self-state data of the target electric bicycle;
Acquiring initial positioning of a target electric bicycle according to the self-state data, acquiring self-state data of other electric bicycles in a preset range according to an initial positioning result, performing time synchronization, and mapping the self-state data of the electric bicycles successfully matched in the time synchronization in the preset range to the same positioning space;
performing auxiliary positioning on the target electric bicycle in the same positioning space, and performing positioning compensation on an initial positioning result of the target electric bicycle through positioning information and relative observation data of other electric bicycles to obtain a final positioning result;
track information is obtained according to real-time position information of a target electric bicycle, abnormal safety conditions are analyzed through the track information, and the track information and the abnormal safety conditions are visually displayed according to a preset mode.
In this scheme, carry out data fusion with satellite positioning data, basic station communication data and IMU data and acquire target electric bicycle's self state data, specifically do:
acquiring current satellite signal strength and base station communication time delay, and judging whether the satellite signal strength and the base station communication time delay are larger than a preset communication strength standard or not;
if the data are larger than the target electric bicycle, acquiring the data with high communication intensity for preferential positioning, and if the data are smaller than the target electric bicycle, acquiring the IMU data for preferential positioning;
Acquiring the priority of target electric bicycle positioning data under a current time stamp, acquiring data weight information through the priority, determining preferred positioning data according to the priority, and fusing and positioning other data with the preferred positioning data through the weight information;
and acquiring position information, speed information and acceleration information of the target electric bicycle according to the fused positioning data, and generating self state data.
In this scheme, through weight information fuses the location with other data and preferred location data, specifically:
carrying out data fusion by a volume Kalman filtering algorithm according to satellite positioning data, base station communication data and IMU data matching data weight information of the current time stamp;
acquiring a current satellite positioning observation matrix, a base station communication observation matrix and an IMU observation matrix, and acquiring an initial state of the current timestamp target electric bicycle according to the observation matrix;
acquiring an observation matrix and an observation noise covariance matrix of preferred positioning data to carry out preferred positioning, determining a preferred state of a target electric bicycle, and carrying out state prediction according to the preferred state;
acquiring an observation matrix and an observation noise covariance matrix of the second positioning data according to the priority order, and carrying out state correction by combining weight information to acquire a posterior state and a state error covariance matrix corresponding to the second positioning data;
And correcting again according to the weight information of the observation matrix and the observation noise covariance matrix set of the third positioning data to obtain a final state and a final state error covariance matrix, and extracting the position information of the current timestamp of the target electric bicycle.
In this scheme, acquire the self state data of other electric bicycle in the scope of predetermineeing according to initial location result and carry out the time synchronization, specifically do:
acquiring other electric bicycles which accord with the authentication standard in a preset area of the current position of the target electric bicycle according to the big data retrieval, and acquiring self state data of the other electric bicycles;
carrying out data standardization processing on self-state data of other electric bicycles, acquiring a public time point from self-state data of other electric bicycles after the standardization processing, synchronizing the data to the public time point and carrying out data alignment on the target electric bicycle and other electric bicycles;
and acquiring self state data sets of other electric bicycles with successful data alignment, and mapping the self state data sets of the other electric bicycles to a low-dimensional vector space.
In this scheme, through the location information of other electric bicycle and relative observation data to the initial location result of target electric bicycle carry out the location compensation, obtain final location result, specifically do:
Constructing a corresponding state sequence according to self state information of the target electric bicycle and other electric bicycles in a preset area, carrying out vectorization representation and matching with ID information of the electric bicycles;
constructing a global coordinate system, and calculating vector difference values of a state sequence of a target electric bicycle and state sequence vectors of other electric bicycles in the same direction to obtain a relative state sequence vector;
aggregating the relative state sequence vectors to obtain a relative observation data set of other electric bicycles of the target electric bicycle in a preset area;
forming an auxiliary positioning sequence by the relative observation data set and the self state data, constructing an auxiliary positioning model based on an LSTM network, and carrying out initialization training;
and importing the auxiliary positioning sequence into the auxiliary positioning model to obtain an auxiliary positioning result, and performing positioning compensation on the initial positioning result through the auxiliary positioning result to improve the positioning accuracy.
In the scheme, the abnormal safety condition is analyzed through track information, and the method specifically comprises the following steps:
acquiring historical track information of a target electric bicycle within preset time, cleaning the historical track information, dividing the cleaned historical track information, judging stay point information in each track according to speed information of the target electric bicycle, and generating a stay point data set;
Performing cluster analysis according to the stay point data set to obtain a preferable stay point of the target user, and selecting an initial cluster center in the stay point data set;
in the first place
In the iteration, euclidean distance from each stay point to a clustering center point is obtained, and the stay points are attributed to the clustering center closest to the stay points to form a clustering result;
after all the stay points in the stay point data set are clustered, carrying out stay time weighting on the stay points, and then solving the mean value of each class cluster in the clustering result to serve as a new clustering center;
when the standard measure function meets the preset standard or the iteration number is greater than or equal to the maximum iteration number, ending clustering, and obtaining a final clustering result as a preferential stay place, otherwise, enabling the iteration number to be equal to or greater than the maximum iteration number
Continuing iterative clustering;
acquiring a preferential running track of a target user according to path information among preferential stay points, and acquiring preferential data of the target user by combining the preferential running track with a preferential running period in preset time;
and comparing the similarity between the current track information of the target electric bicycle and the preference data of the target user, carrying out key monitoring on the travel corresponding to the current track information when the similarity deviation is larger than a preset deviation threshold value, and generating safety abnormality early warning when the stay time of the target electric bicycle at a non-preference stay place is larger than a preset time threshold value.
The second aspect of the present invention also provides an electric bicycle positioning system, comprising: the electric bicycle positioning method comprises a memory and a processor, wherein the memory comprises an electric bicycle positioning method program, and the electric bicycle positioning method program realizes the following steps when being executed by the processor:
acquiring satellite positioning data, base station communication data and IMU data of a target electric bicycle, and carrying out data fusion on the satellite positioning data, the base station communication data and the IMU data to acquire self-state data of the target electric bicycle;
acquiring initial positioning of a target electric bicycle according to the self-state data, acquiring self-state data of other electric bicycles in a preset range according to an initial positioning result, performing time synchronization, and mapping the self-state data of the electric bicycles successfully matched in the time synchronization in the preset range to the same positioning space;
performing auxiliary positioning on the target electric bicycle in the same positioning space, and performing positioning compensation on an initial positioning result of the target electric bicycle through positioning information and relative observation data of other electric bicycles to obtain a final positioning result;
track information is obtained according to real-time position information of a target electric bicycle, abnormal safety conditions are analyzed through the track information, and the track information and the abnormal safety conditions are visually displayed according to a preset mode.
The invention discloses a positioning method and a system for an electric bicycle, comprising the following steps: acquiring satellite positioning data, base station communication data and IMU data of a target electric bicycle to form self-state data of the electric bicycle; the method comprises the steps of performing initial positioning of a target electric bicycle according to self state data, obtaining self state data of other electric bicycles in a preset range, performing time synchronization, obtaining self state data of the electric bicycles successfully matched in time synchronization in the preset range, mapping the self state data to the same positioning space, performing auxiliary positioning, performing positioning compensation on initial positioning results of the target electric bicycle through positioning information and relative observation data of the other electric bicycles, and obtaining final positioning results; track information is acquired, and abnormal safety conditions are analyzed through the track information. The invention realizes high-precision positioning of the electric bicycle, and safety analysis is carried out through the motion trail and the running state of the electric bicycle, so that the travel safety of a user is improved, and meanwhile, the property loss is effectively avoided.
Drawings
FIG. 1 is a flowchart showing a method for positioning an electric bicycle according to the present invention;
FIG. 2 is a flow chart of a method of fusion positioning according to the positioning data priority of the present invention;
FIG. 3 is a flowchart showing a method of performing positioning compensation on an initial positioning result of a target electric bicycle according to the present invention;
fig. 4 shows a block diagram of an electric bicycle positioning system of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flowchart of a positioning method of an electric bicycle according to the present invention.
As shown in fig. 1, a first aspect of the present invention provides a positioning method for an electric bicycle, including:
s102, acquiring satellite positioning data, base station communication data and IMU data of a target electric bicycle, and carrying out data fusion on the satellite positioning data, the base station communication data and the IMU data to acquire self-state data of the target electric bicycle;
S104, acquiring initial positioning of a target electric bicycle according to the self-state data, acquiring self-state data of other electric bicycles in a preset range according to an initial positioning result, performing time synchronization, and mapping the self-state data of the electric bicycles successfully matched in the time synchronization in the preset range to the same positioning space;
s106, performing auxiliary positioning on the target electric bicycle in the same positioning space, and performing positioning compensation on an initial positioning result of the target electric bicycle through positioning information and relative observation data of other electric bicycles to obtain a final positioning result;
s108, track information is obtained according to the real-time position information of the target electric bicycle, abnormal safety conditions are analyzed through the track information, and the track information and the abnormal safety conditions are visually displayed according to a preset mode.
It should be noted that, the current satellite signal strength and the base station communication time delay are obtained, and whether the satellite signal strength and the base station communication time delay are greater than a preset communication strength standard is judged; if the satellite signals are larger than the ground section, the space section and the user section, acquiring data with high communication intensity for preferential positioning, wherein the satellite positioning can be realized through positioning systems such as GPS (global positioning system), beidou satellite, GLONASS, galileo and the like, satellite signals are received based on a ranging principle, ranging information is obtained, and position coordinate information is calculated according to the ranging information, ephemeris information and errors; the base station communication positioning realizes positioning by measuring the receiving intensity of signals between the electric bicycle and the base station or measuring the distance or time difference between each base station signal and the electric bicycle; if the acquired IMU data of the target electric bicycle are smaller than the acquired IMU data, the IMU data are preferentially positioned, the IMU positioning acquires a posture matrix of the electric bicycle through an IMU built-in the electric bicycle, and the posture matrix is resolved to acquire current speed and position information; acquiring the priority of target electric bicycle positioning data under a current time stamp, acquiring data weight information through the priority, determining preferred positioning data according to the priority, and fusing and positioning other data with the preferred positioning data through the weight information; and acquiring the position information, the speed information and the acceleration information of the target electric bicycle according to the fused positioning data, and generating self state data.
FIG. 2 is a flow chart of a method of fusion positioning according to the present invention.
According to the embodiment of the invention, other data and preferred positioning data are fused and positioned through the weight information, specifically:
s202, carrying out data fusion by a volume Kalman filtering algorithm according to satellite positioning data, base station communication data and IMU data matching data weight information of a current time stamp;
s204, acquiring a current satellite positioning observation matrix, a base station communication observation matrix and an IMU observation matrix, and acquiring an initial state of the current timestamp target electric bicycle according to the observation matrix;
s206, acquiring an observation matrix and an observation noise covariance matrix of the preferred positioning data to carry out preferred positioning, determining a preferred state of a target electric bicycle, and carrying out state prediction according to the preferred state;
s208, acquiring an observation matrix and an observation noise covariance matrix of the second positioning data according to the priority order, and carrying out state correction by combining weight information to acquire a posterior state and a state error covariance matrix corresponding to the second positioning data;
s210, correcting again according to the weight information of the observation matrix and the observation noise covariance matrix set of the third positioning data, obtaining a final state and a final state error covariance matrix, and extracting the position information of the current timestamp of the target electric bicycle.
It should be noted that, according to the priority, the preferred positioning data and the subsequent positioning correction data of the electric bicycle are obtained, for example, in a preferred embodiment, the priority of the communication intensity of the current timestamp obtains the satellite positioning dataAs the preferred positioning data, constructing an observation equation based on satellite signal data
Wherein->
The satellite positioning is +.>
Observed state value of time +.>
Observation matrix corresponding to the satellite positioning data, < ->
Indicating the target electric bicycle is +.>
State initial value of time->
Indicating the target electric bicycle is +.>
Observation noise at the moment; time according to the preferred state of the current timestamp +.>
The state of (3) is predicted, specifically:
wherein,,
indicating the target electric bicycle is at time +.>
Status of->
A state transition matrix is represented and is used to represent,
indicating the target electric bicycle is at time +.>
Posterior state of->
Indicating the target electric bicycle is at time +.>
Error covariance matrix of>
Indicating the target electric bicycle is at time +.>
Error covariance matrix of>
Representing a process noise covariance matrix,>
representing a matrix transpose;
acquiring an observation matrix and an observation noise covariance matrix of base station communication data and IMU data according to the priority order, and carrying out state correction by combining weight information, wherein the method specifically comprises the following steps:
Wherein,,
kalman gain matrix representing time i, < ->
An observation matrix representing the second positioning data and the third positioning data in the priority, in this embodiment a base station communication observation matrix when n is 2, an IMU observation matrix when n is 3,
an observed noise covariance matrix representing the second positioning data and the third positioning data in the priority, in this embodiment the base station communication observed noise covariance matrix when n is 2, the IMU observed noise covariance matrix when n is 3, ">
Indicating the corresponding posterior states of the second positioning data and the third positioning data in the priority, +.>
Representing the corresponding observations, in this embodiment the base station communication observations when n is 2, the IMU observations when n is 3, +.>
Indicating the target electric bicycle is at time +.>
Error covariance matrix of (a);
through the final posterior matrix
Error covariance matrix->
As a final result of the positioning.
It is to be noted that, according to the big data retrieval, other electric bicycles which accord with the authentication standard in the preset area of the current position of the target electric bicycle are obtained, and the self state data of the other electric bicycles are obtained; carrying out data standardization processing on self-state data of other electric bicycles, acquiring a public time point from self-state data of other electric bicycles after the standardization processing, synchronizing the data to the public time point and carrying out data alignment on the target electric bicycle and other electric bicycles; and acquiring self state data sets of other electric bicycles with successful data alignment, and mapping the self state data sets of the other electric bicycles to a low-dimensional vector space.
Fig. 3 shows a flowchart of a method for performing positioning compensation on an initial positioning result of a target electric bicycle.
According to the embodiment of the invention, the initial positioning result of the target electric bicycle is subjected to positioning compensation through the positioning information and relative observation data of other electric bicycles, and the final positioning result is obtained, specifically:
s302, constructing a corresponding state sequence according to self state information of a target electric bicycle and other electric bicycles in a preset area, performing vectorization representation and matching with ID information of the electric bicycles;
s304, constructing a global coordinate system, and calculating vector difference values of a state sequence of the target electric bicycle and state sequence vectors of other electric bicycles in the same direction to obtain a relative state sequence vector;
s306, aggregating the relative state sequence vectors to obtain a relative observation data set of other electric bicycles of the target electric bicycle in a preset area;
s308, forming an auxiliary positioning sequence by the relative observation data set and the self state data, constructing an auxiliary positioning model based on an LSTM network, and carrying out initialization training;
s310, importing the auxiliary positioning sequence into the auxiliary positioning model to obtain an auxiliary positioning result, and performing positioning compensation on the initial positioning result through the auxiliary positioning result to improve positioning accuracy.
It should be noted that, a global coordinate system is constructed by selecting a fixed object within a preset range, the positioning information of the state information of the target electric bicycle is transformed into the global coordinate system, and the auxiliary positioning of the target electric bicycle is performed in the global coordinate system. The LSTM unit structure mainly controls the transmission state through a forgetting gate, a memory gate and an output gate, finally converts the output dimension into the time step number of the preset time through a full connection layer, the output layer positions information after the preset time, and takes an auxiliary positioning sequence as the input of the LSTM network, so that the relation between other electric bicycles and the target electric bicycle can be found in the training process of the neural network, the anti-interference capability of the system is improved, and the analysis robustness of the neural network is further enhanced.
It should be noted that, analysis of abnormal safety conditions through track information specifically includes:
acquiring historical track information of a target electric bicycle within preset time, cleaning the historical track information, dividing the cleaned historical track information, judging stay point information in each track according to speed information of the target electric bicycle, and generating a stay point data set;
Performing cluster analysis according to the stay point data set to obtain a preferable stay point of the target user, and selecting an initial cluster center in the stay point data set;
in the first place
In the iteration, euclidean distance from each stay point to a clustering center point is obtained, and the stay points are attributed to the clustering center closest to the stay points to form a clustering result;
after all the stay points in the stay point data set are clustered, clustering results are obtained
The mean value of each cluster of the class +.>
Is provided with->
Is->
Total number of samples of the cluster of individual classes, +.>
Is the->
The method for solving the clustering center points of the samples specifically comprises the following steps: />
；/>
When standard measure function
Maximum number of iterations->
If->
Or the number of iterations is equal to or greater than%>
Ending the clustering, obtaining a final clustering result as a preferential stay place, otherwise, making the iteration times
Continuing iterative clustering;
acquiring a preferential running track of a target user according to path information among preferential stay points, and acquiring preferential data of the target user by combining the preferential running track with a preferential running period in preset time;
and comparing the similarity between the current track information of the target electric bicycle and the preference data of the target user, carrying out key monitoring on the travel corresponding to the current track information when the similarity deviation is larger than a preset deviation threshold value, and generating safety abnormality early warning when the stay time of the target electric bicycle at a non-preference stay place is larger than a preset time threshold value.
According to the embodiment of the invention, the congestion degree of the non-motor vehicle in the city range is obtained and predicted according to the track information of the electric bicycle, specifically:
clustering analysis is carried out on a preset road within a preset range according to the history track information based on time factors through the history track information of the authorized electric bicycle within the preset range, so that thermodynamic visible views of the electric bicycle in each time period are obtained;
analyzing the crowding degree of the future journey of the user according to the thermodynamic visual view and the preference data of the user, and sending the crowding degree to the user in a preset mode;
in addition, riding safety characteristic data of the target user are extracted through preference data of the target user, the riding safety characteristic data and the standard data of the traffic regulations are compared and analyzed to obtain data deviation, and when the data deviation is larger than a preset deviation threshold value, riding safety early warning data of the target object are obtained;
and acquiring a path point with safety precaution of a target user in the historical track information according to the riding safety precaution data, and transmitting the path point according to a preset mode by combining the corresponding riding safety precaution data.
Fig. 4 shows a block diagram of an electric bicycle positioning system of the present invention.
The second aspect of the present invention also provides an electric bicycle positioning system 4, comprising: the memory 41 and the processor 42, wherein the memory comprises an electric bicycle positioning method program, and the electric bicycle positioning method program realizes the following steps when being executed by the processor:
acquiring satellite positioning data, base station communication data and IMU data of a target electric bicycle, and carrying out data fusion on the satellite positioning data, the base station communication data and the IMU data to acquire self-state data of the target electric bicycle;
acquiring initial positioning of a target electric bicycle according to the self-state data, acquiring self-state data of other electric bicycles in a preset range according to an initial positioning result, performing time synchronization, and mapping the self-state data of the electric bicycles successfully matched in the time synchronization in the preset range to the same positioning space;
performing auxiliary positioning on the target electric bicycle in the same positioning space, and performing positioning compensation on an initial positioning result of the target electric bicycle through positioning information and relative observation data of other electric bicycles to obtain a final positioning result;
track information is obtained according to real-time position information of a target electric bicycle, abnormal safety conditions are analyzed through the track information, and the track information and the abnormal safety conditions are visually displayed according to a preset mode.
It should be noted that, the current satellite signal strength and the base station communication time delay are obtained, and whether the satellite signal strength and the base station communication time delay are greater than a preset communication strength standard is judged; if the satellite signals are larger than the ground section, the space section and the user section, acquiring data with high communication intensity for preferential positioning, wherein the satellite positioning can be realized through positioning systems such as GPS (global positioning system), beidou satellite, GLONASS, galileo and the like, satellite signals are received based on a ranging principle, ranging information is obtained, and position coordinate information is calculated according to the ranging information, ephemeris information and errors; the base station communication positioning realizes positioning by measuring the receiving intensity of signals between the electric bicycle and the base station or measuring the distance or time difference between each base station signal and the electric bicycle; if the acquired IMU data of the target electric bicycle are smaller than the acquired IMU data, the IMU data are preferentially positioned, the IMU positioning acquires a posture matrix of the electric bicycle through an IMU built-in the electric bicycle, and the posture matrix is resolved to acquire current speed and position information; acquiring the priority of target electric bicycle positioning data under a current time stamp, acquiring data weight information through the priority, determining preferred positioning data according to the priority, and fusing and positioning other data with the preferred positioning data through the weight information; and acquiring the position information, the speed information and the acceleration information of the target electric bicycle according to the fused positioning data, and generating self state data.
According to the embodiment of the invention, other data and preferred positioning data are fused and positioned through the weight information, specifically:
carrying out data fusion by a volume Kalman filtering algorithm according to satellite positioning data, base station communication data and IMU data matching data weight information of the current time stamp;
acquiring a current satellite positioning observation matrix, a base station communication observation matrix and an IMU observation matrix, and acquiring an initial state of the current timestamp target electric bicycle according to the observation matrix;
acquiring an observation matrix and an observation noise covariance matrix of preferred positioning data to carry out preferred positioning, determining a preferred state of a target electric bicycle, and carrying out state prediction according to the preferred state;
acquiring an observation matrix and an observation noise covariance matrix of the second positioning data according to the priority order, and carrying out state correction by combining weight information to acquire a posterior state and a state error covariance matrix corresponding to the second positioning data;
and correcting again according to the weight information of the observation matrix and the observation noise covariance matrix set of the third positioning data to obtain a final state and a final state error covariance matrix, and extracting the position information of the current timestamp of the target electric bicycle.
It should be noted that, the preferred positioning data and the subsequent positioning correction data of the electric bicycle are obtained according to the priority, for example, in a preferred embodiment, the priority of the communication intensity of the current timestamp obtains satellite positioning data as the preferred positioning data, and an observation equation is constructed according to the satellite signal data
Wherein->
The satellite positioning is +.>
Observed state value of time +.>
Representation guardObservation matrix corresponding to star positioning data, +.>
Indicating the target electric bicycle is +.>
State initial value of time->
Indicating the target electric bicycle is +.>
Observation noise at the moment; time according to the preferred state of the current timestamp +.>
The state of (3) is predicted, specifically:
wherein,,
indicating the target electric bicycle is at time +.>
Status of->
A state transition matrix is represented and is used to represent,
indicating the target electric bicycle is at time +.>
Posterior state of->
Indicating the target electric bicycle is at time +.>
Error covariance matrix of>
Indicating the target electric bicycle is at time +.>
Error covariance matrix of>
Representing a process noise covariance matrix,>
representing a matrix transpose;
acquiring an observation matrix and an observation noise covariance matrix of base station communication data and IMU data according to the priority order, and carrying out state correction by combining weight information, wherein the method specifically comprises the following steps:
Wherein,,
kalman gain matrix representing time i, < ->
An observation matrix representing the second positioning data and the third positioning data in the priority, in this embodiment a base station communication observation matrix when n is 2, an IMU observation matrix when n is 3,
an observed noise covariance matrix representing the second positioning data and the third positioning data in the priority, in this embodiment the base station communication observed noise covariance matrix when n is 2, the IMU observed noise covariance matrix when n is 3, ">
Indicating the corresponding posterior states of the second positioning data and the third positioning data in the priority, +.>
Representing the corresponding observations, in this embodiment the base station communication observations when n is 2, the IMU observations when n is 3, +.>
Indicating the target electric bicycle is at time +.>
Error covariance matrix of (a);
through the final posterior matrix
Error covariance matrix->
As a final result of the positioning.
It is to be noted that, according to the big data retrieval, other electric bicycles which accord with the authentication standard in the preset area of the current position of the target electric bicycle are obtained, and the self state data of the other electric bicycles are obtained; carrying out data standardization processing on self-state data of other electric bicycles, acquiring a public time point from self-state data of other electric bicycles after the standardization processing, synchronizing the data to the public time point and carrying out data alignment on the target electric bicycle and other electric bicycles; and acquiring self state data sets of other electric bicycles with successful data alignment, and mapping the self state data sets of the other electric bicycles to a low-dimensional vector space.
According to the embodiment of the invention, the initial positioning result of the target electric bicycle is subjected to positioning compensation through the positioning information and relative observation data of other electric bicycles, and the final positioning result is obtained, specifically:
constructing a corresponding state sequence according to self state information of the target electric bicycle and other electric bicycles in a preset area, carrying out vectorization representation and matching with ID information of the electric bicycles;
constructing a global coordinate system, and calculating vector difference values of a state sequence of a target electric bicycle and state sequence vectors of other electric bicycles in the same direction to obtain a relative state sequence vector;
aggregating the relative state sequence vectors to obtain a relative observation data set of other electric bicycles of the target electric bicycle in a preset area;
forming an auxiliary positioning sequence by the relative observation data set and the self state data, constructing an auxiliary positioning model based on an LSTM network, and carrying out initialization training;
and importing the auxiliary positioning sequence into the auxiliary positioning model to obtain an auxiliary positioning result, and performing positioning compensation on the initial positioning result through the auxiliary positioning result to improve the positioning accuracy.
It should be noted that, a global coordinate system is constructed by selecting a fixed object within a preset range, the positioning information of the state information of the target electric bicycle is transformed into the global coordinate system, and the auxiliary positioning of the target electric bicycle is performed in the global coordinate system. The LSTM unit structure mainly controls the transmission state through a forgetting gate, a memory gate and an output gate, finally converts the output dimension into the time step number of the preset time through a full connection layer, the output layer positions information after the preset time, and takes an auxiliary positioning sequence as the input of the LSTM network, so that the relation between other electric bicycles and the target electric bicycle can be found in the training process of the neural network, the anti-interference capability of the system is improved, and the analysis robustness of the neural network is further enhanced.
It should be noted that, analysis of abnormal safety conditions through track information specifically includes:
acquiring historical track information of a target electric bicycle within preset time, cleaning the historical track information, dividing the cleaned historical track information, judging stay point information in each track according to speed information of the target electric bicycle, and generating a stay point data set;
Performing cluster analysis according to the stay point data set to obtain a preferable stay point of the target user, and selecting an initial cluster center in the stay point data set;
in the first place
In the iteration, euclidean distance from each stay point to a clustering center point is obtained, and the stay points are attributed to the clustering center closest to the stay points to form a clustering result;
after all the stay points in the stay point data set are clustered, clustering results are obtained
The mean value of each cluster of the class +.>
Is provided with->
Is->
Total number of samples of the cluster of individual classes, +.>
Is the->
The method for solving the clustering center points of the samples specifically comprises the following steps: />
；
When standard measure function
Maximum number of iterations->
If->
Or the number of iterations is equal to or greater than%>
Ending the clustering, obtaining a final clustering result as a preferential stay place, otherwise, making the iteration times
Continuing iterative clustering;
acquiring a preferential running track of a target user according to path information among preferential stay points, and acquiring preferential data of the target user by combining the preferential running track with a preferential running period in preset time;
and comparing the similarity between the current track information of the target electric bicycle and the preference data of the target user, carrying out key monitoring on the travel corresponding to the current track information when the similarity deviation is larger than a preset deviation threshold value, and generating safety abnormality early warning when the stay time of the target electric bicycle at a non-preference stay place is larger than a preset time threshold value.
The third aspect of the present invention also provides a computer-readable storage medium, in which an electric bicycle positioning method program is included, which when executed by a processor, implements the steps of an electric bicycle positioning method as described in any one of the above.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (4)
1. The electric bicycle positioning method is characterized by comprising the following steps of:
acquiring satellite positioning data, base station communication data and IMU data of a target electric bicycle, and carrying out data fusion on the satellite positioning data, the base station communication data and the IMU data to acquire self-state data of the target electric bicycle;
acquiring initial positioning of a target electric bicycle according to the self-state data, acquiring self-state data of other electric bicycles in a preset range according to an initial positioning result, performing time synchronization, and mapping the self-state data of the electric bicycles successfully matched in the time synchronization in the preset range to the same positioning space;
performing auxiliary positioning on the target electric bicycle in the same positioning space, and performing positioning compensation on an initial positioning result of the target electric bicycle through positioning information and relative observation data of other electric bicycles to obtain a final positioning result;
Acquiring track information according to real-time position information of a target electric bicycle, analyzing abnormal safety conditions through the track information, and visually displaying the track information and the abnormal safety conditions according to a preset mode;
the satellite positioning data, the base station communication data and the IMU data are subjected to data fusion to obtain the self-state data of the target electric bicycle, and the method specifically comprises the following steps:
acquiring current satellite signal strength and base station communication time delay, and judging whether the satellite signal strength and the base station communication time delay are larger than a preset communication strength standard or not;
if the data are larger than the target electric bicycle, acquiring the data with high communication intensity for preferential positioning, and if the data are smaller than the target electric bicycle, acquiring the IMU data for preferential positioning;
acquiring the priority of target electric bicycle positioning data under a current time stamp, acquiring data weight information through the priority, determining preferred positioning data according to the priority, and fusing and positioning other data with the preferred positioning data through the weight information;
acquiring position information, speed information and acceleration information of a target electric bicycle according to the fusion positioning data, and generating self state data;
and fusing and positioning other data and the preferred positioning data through the weight information, wherein the method specifically comprises the following steps:
Carrying out data fusion by a volume Kalman filtering algorithm according to satellite positioning data, base station communication data and IMU data matching data weight information of the current time stamp;
acquiring a current satellite positioning observation matrix, a base station communication observation matrix and an IMU observation matrix, and acquiring an initial state of the current timestamp target electric bicycle according to the observation matrix;
acquiring an observation matrix and an observation noise covariance matrix of preferred positioning data to carry out preferred positioning, determining a preferred state of a target electric bicycle, and carrying out state prediction according to the preferred state;
acquiring an observation matrix and an observation noise covariance matrix of the second positioning data according to the priority order, and carrying out state correction by combining weight information to acquire a posterior state and a state error covariance matrix corresponding to the second positioning data;
correcting again according to the weight information of the observation matrix and the observation noise covariance matrix set of the third positioning data to obtain a final state and a final state error covariance matrix, and extracting the position information of the current timestamp of the target electric bicycle;
the initial positioning result of the target electric bicycle is subjected to positioning compensation through positioning information and relative observation data of other electric bicycles, and a final positioning result is obtained, specifically:
Constructing a corresponding state sequence according to self state information of the target electric bicycle and other electric bicycles in a preset area, carrying out vectorization representation and matching with ID information of the electric bicycles;
constructing a global coordinate system, and calculating vector difference values of a state sequence of a target electric bicycle and state sequence vectors of other electric bicycles in the same direction to obtain a relative state sequence vector;
aggregating the relative state sequence vectors to obtain a relative observation data set of other electric bicycles of the target electric bicycle in a preset area;
forming an auxiliary positioning sequence by the relative observation data set and the self state data, constructing an auxiliary positioning model based on an LSTM network, and carrying out initialization training;
and importing the auxiliary positioning sequence into the auxiliary positioning model to obtain an auxiliary positioning result, and performing positioning compensation on the initial positioning result through the auxiliary positioning result to improve the positioning accuracy.
2. The positioning method of an electric bicycle according to claim 1, wherein the time synchronization is performed by acquiring self-state data of other electric bicycles within a preset range according to an initial positioning result, specifically:
Acquiring other electric bicycles which accord with the authentication standard in a preset area of the current position of the target electric bicycle according to the big data retrieval, and acquiring self state data of the other electric bicycles;
carrying out data standardization processing on self-state data of other electric bicycles, acquiring a public time point from self-state data of other electric bicycles after the standardization processing, synchronizing the data to the public time point and carrying out data alignment on the target electric bicycle and other electric bicycles;
and acquiring self state data sets of other electric bicycles with successful data alignment, and mapping the self state data sets of the other electric bicycles to a low-dimensional vector space.
3. The positioning method of an electric bicycle according to claim 1, wherein the analysis of abnormal safety conditions by track information is specifically:
acquiring historical track information of a target electric bicycle within preset time, cleaning the historical track information, dividing the cleaned historical track information, judging stay point information in each track according to speed information of the target electric bicycle, and generating a stay point data set;
Performing cluster analysis according to the stay point data set to obtain a preferable stay point of the target user, and selecting an initial cluster center in the stay point data set;
in the first place
In the iteration, euclidean distance from each stay point to a clustering center point is obtained, and the stay points are attributed to the clustering center closest to the stay points to form a clustering result;
after all the stay points in the stay point data set are clustered, carrying out stay time weighting on the stay points, and then solving the mean value of each class cluster in the clustering result to serve as a new clustering center;
when the standard measure function meets the preset standard or the iteration number is greater than or equal to the maximum iteration number, ending clustering, and obtaining a final clustering result as a preferential stay place, otherwise, enabling the iteration number to be equal to or greater than the maximum iteration number
Continuing iterative clustering;
acquiring a preferential running track of a target user according to path information among preferential stay points, and acquiring preferential data of the target user by combining the preferential running track with a preferential running period in preset time;
and comparing the similarity between the current track information of the target electric bicycle and the preference data of the target user, carrying out key monitoring on the travel corresponding to the current track information when the similarity deviation is larger than a preset deviation threshold value, and generating safety abnormality early warning when the stay time of the target electric bicycle at a non-preference stay place is larger than a preset time threshold value.
4. An electric bicycle positioning system, characterized in that it comprises: the electric bicycle positioning method comprises a memory and a processor, wherein the memory comprises an electric bicycle positioning method program, and the electric bicycle positioning method program realizes the following steps when being executed by the processor:
acquiring satellite positioning data, base station communication data and IMU data of a target electric bicycle, and carrying out data fusion on the satellite positioning data, the base station communication data and the IMU data to acquire self-state data of the target electric bicycle;
acquiring initial positioning of a target electric bicycle according to the self-state data, acquiring self-state data of other electric bicycles in a preset range according to an initial positioning result, performing time synchronization, and mapping the self-state data of the electric bicycles successfully matched in the time synchronization in the preset range to the same positioning space;
performing auxiliary positioning on the target electric bicycle in the same positioning space, and performing positioning compensation on an initial positioning result of the target electric bicycle through positioning information and relative observation data of other electric bicycles to obtain a final positioning result;
acquiring track information according to real-time position information of a target electric bicycle, analyzing abnormal safety conditions through the track information, and visually displaying the track information and the abnormal safety conditions according to a preset mode;
The satellite positioning data, the base station communication data and the IMU data are subjected to data fusion to obtain the self-state data of the target electric bicycle, and the method specifically comprises the following steps:
acquiring current satellite signal strength and base station communication time delay, and judging whether the satellite signal strength and the base station communication time delay are larger than a preset communication strength standard or not;
if the data are larger than the target electric bicycle, acquiring the data with high communication intensity for preferential positioning, and if the data are smaller than the target electric bicycle, acquiring the IMU data for preferential positioning;
acquiring the priority of target electric bicycle positioning data under a current time stamp, acquiring data weight information through the priority, determining preferred positioning data according to the priority, and fusing and positioning other data with the preferred positioning data through the weight information;
acquiring position information, speed information and acceleration information of a target electric bicycle according to the fusion positioning data, and generating self state data;
and fusing and positioning other data and the preferred positioning data through the weight information, wherein the method specifically comprises the following steps:
carrying out data fusion by a volume Kalman filtering algorithm according to satellite positioning data, base station communication data and IMU data matching data weight information of the current time stamp;
Acquiring a current satellite positioning observation matrix, a base station communication observation matrix and an IMU observation matrix, and acquiring an initial state of the current timestamp target electric bicycle according to the observation matrix;
acquiring an observation matrix and an observation noise covariance matrix of preferred positioning data to carry out preferred positioning, determining a preferred state of a target electric bicycle, and carrying out state prediction according to the preferred state;
acquiring an observation matrix and an observation noise covariance matrix of the second positioning data according to the priority order, and carrying out state correction by combining weight information to acquire a posterior state and a state error covariance matrix corresponding to the second positioning data;
correcting again according to the weight information of the observation matrix and the observation noise covariance matrix set of the third positioning data to obtain a final state and a final state error covariance matrix, and extracting the position information of the current timestamp of the target electric bicycle;
the initial positioning result of the target electric bicycle is subjected to positioning compensation through positioning information and relative observation data of other electric bicycles, and a final positioning result is obtained, specifically:
constructing a corresponding state sequence according to self state information of the target electric bicycle and other electric bicycles in a preset area, carrying out vectorization representation and matching with ID information of the electric bicycles;
Constructing a global coordinate system, and calculating vector difference values of a state sequence of a target electric bicycle and state sequence vectors of other electric bicycles in the same direction to obtain a relative state sequence vector;
aggregating the relative state sequence vectors to obtain a relative observation data set of other electric bicycles of the target electric bicycle in a preset area;
forming an auxiliary positioning sequence by the relative observation data set and the self state data, constructing an auxiliary positioning model based on an LSTM network, and carrying out initialization training;
and importing the auxiliary positioning sequence into the auxiliary positioning model to obtain an auxiliary positioning result, and performing positioning compensation on the initial positioning result through the auxiliary positioning result to improve the positioning accuracy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310053751.9A CN115792989B (en) | 2023-02-03 | 2023-02-03 | Positioning method and system for electric bicycle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310053751.9A CN115792989B (en) | 2023-02-03 | 2023-02-03 | Positioning method and system for electric bicycle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115792989A CN115792989A (en) | 2023-03-14 |
| CN115792989B true CN115792989B (en) | 2023-05-09 |
Family
ID=85429656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310053751.9A Active CN115792989B (en) | 2023-02-03 | 2023-02-03 | Positioning method and system for electric bicycle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115792989B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007105294A1 (en) * | 2006-03-13 | 2007-09-20 | Churyo Engineering Co., Ltd. | Vehicle traveling locus measuring device |
| CN104076382B (en) * | 2014-07-22 | 2016-11-23 | 中国石油大学(华东) | A kind of vehicle seamless positioning method based on Multi-source Information Fusion |
| CN108037483A (en) * | 2017-12-07 | 2018-05-15 | 北京搜狐新媒体信息技术有限公司 | A kind of vehicle positioning method, device and vehicle radio station system |
| CN108535753A (en) * | 2018-03-30 | 2018-09-14 | 北京百度网讯科技有限公司 | Vehicle positioning method, device and equipment |
| CN110349372B (en) * | 2019-06-10 | 2021-11-19 | 智慧华川养老(北京)有限公司 | Method and device for early warning abnormal activities of family aged care personnel |
| CN112946713B (en) * | 2021-02-05 | 2023-09-15 | 北京森云科技有限公司 | Indoor positioning method, equipment and system |
| CN113155123B (en) * | 2021-04-01 | 2022-09-27 | 北京大学 | Multi-intelligent-vehicle cooperative localization tracking method and device based on data sharing |
| CN113847914B (en) * | 2021-09-22 | 2024-03-26 | 中国第一汽车股份有限公司 | Vehicle positioning method and device, electronic equipment and storage medium |
| CN115575995A (en) * | 2022-07-01 | 2023-01-06 | 武汉小安信息科技有限公司 | Positioning method, positioning device, electronic equipment and storage medium |
-
2023
- 2023-02-03 CN CN202310053751.9A patent/CN115792989B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115792989A (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106205114B (en) | A kind of Freeway Conditions information real time acquiring method based on data fusion | |
| CN113155173B (en) | Perception performance evaluation method and device, electronic device and storage medium | |
| CN109741483B (en) | Automobile collision detection method based on Internet of vehicles platform | |
| CN107255825B (en) | Signal classification method and device and satellite signal detection equipment | |
| CN111383362B (en) | Safety monitoring method and device | |
| CN110807930A (en) | Dangerous vehicle early warning method and device | |
| CN109084797B (en) | Navigation path recommendation method and device | |
| CN110472999B (en) | Passenger flow mode analysis method and device based on subway and shared bicycle data | |
| US10629073B2 (en) | Method, device and system for wrong-way driver detection | |
| CN112380448A (en) | Vehicle data processing method and device, computer equipment and storage medium | |
| CN111222381A (en) | User travel mode identification method and device, electronic equipment and storage medium | |
| CN116472562A (en) | Mobile device and system for automatic trip familiarity recognition and corresponding methods | |
| CN112465041A (en) | AIS data quality evaluation method based on analytic hierarchy process | |
| CN112214677B (en) | Point of interest recommendation method and device, electronic equipment and storage medium | |
| CN116184442A (en) | Track, clock correction evaluation method and device, equipment and storage medium | |
| CN112381126A (en) | Indoor and outdoor scene recognition method and device, electronic equipment and storage medium | |
| WO2021150166A1 (en) | Determining a route between an origin and a destination | |
| Parada et al. | Machine learning-based trajectory prediction for vru collision avoidance in v2x environments | |
| CN115792989B (en) | Positioning method and system for electric bicycle | |
| CN110793531B (en) | Road matching method and device and readable storage medium | |
| CN112489495B (en) | Vehicle early warning method and device, electronic equipment and storage medium | |
| CN109657556B (en) | Method and system for classifying road and surrounding ground objects thereof | |
| CN108520044B (en) | Least square method path prediction algorithm based on axiality thought | |
| CN114872718A (en) | Vehicle trajectory prediction method, vehicle trajectory prediction device, computer equipment and storage medium | |
| Gundlegård et al. | Integrated tracking and route classification for travel time estimation based on cellular network signalling data |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhang Hong Inventor after: Dai Jiaxi Inventor after: Wen Weiwei Inventor after: Huang Zongwang Inventor after: Huang Peng Inventor before: Zhang Hong Inventor before: Dai Jiaxi Inventor before: Wen Weiwei Inventor before: Huang Zhongwang Inventor before: Huang Peng |