CN116311895A - Track prediction method and device and Internet of vehicles equipment - Google Patents

Track prediction method and device and Internet of vehicles equipment Download PDF

Info

Publication number
CN116311895A
CN116311895A CN202211724629.1A CN202211724629A CN116311895A CN 116311895 A CN116311895 A CN 116311895A CN 202211724629 A CN202211724629 A CN 202211724629A CN 116311895 A CN116311895 A CN 116311895A
Authority
CN
China
Prior art keywords
predicted position
predicted
lane
target object
running state
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.)
Pending
Application number
CN202211724629.1A
Other languages
Chinese (zh)
Inventor
许文龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
CICTCI Technology Co Ltd
Original Assignee
CICTCI Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by CICTCI Technology Co Ltd filed Critical CICTCI Technology Co Ltd
Priority to CN202211724629.1A priority Critical patent/CN116311895A/en
Publication of CN116311895A publication Critical patent/CN116311895A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • 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
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a track prediction method and device and Internet of vehicles equipment. The method comprises the following steps: under the condition that the position of a target object is detected to be lost, acquiring historical position coordinates and a running state of the target object before the position is lost; and predicting the track of the target object in the position losing period according to the lane boundary characteristics in the map, the historical position coordinates before the position losing and the running state. The method can utilize the shape high-precision map without topological relation to conduct track prediction.

Description

Track prediction method and device and Internet of vehicles equipment
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a track prediction method and apparatus, and an internet of vehicles device.
Background
The track prediction (Trajectory Prediction, TP) is an important functional module in the intelligent traffic and road cooperation field, and can conduct track prediction deduction aiming at targets which are missed to be detected and false to be detected by the sensor and the edge calculation unit, so that a target position with higher confidence coefficient is obtained, the authenticity and the integrity of traffic information flow are ensured, the target information identified by a road side end can be better provided for an intelligent traffic control platform and traffic participants, the power-assisted traffic safety is improved, and the research on an efficient and reliable track prediction method has great research significance.
The high-definition Map (HD Map) is a novel Map data format for intelligent traffic and automatic driving. The accuracy of traditional maps is typically on the order of meters or tens of meters, with excessive errors, which are not trusted for the intelligent traffic domain. Unlike conventional maps, the coordinate accuracy of high-precision maps can reach sub-meter to centimeter levels. Conventional navigation maps generally provide only road network structure information and rough geometric point positions, while high-precision maps contain, in addition to these information, lane information (lane line positions, types, lane directions, lane traffic restriction information, etc.), traffic sign information, and position information of traffic lights, overpasses, portal frames, etc. The advantages of the high-precision map can well provide a basis for judging the target intention and the subsequent trend in the prediction of the cooperative track of the vehicle and road, and more accurate and reliable prediction and deduction can be made.
ESRI shape (shp), or shape for short, is a more general open format of spatial data in the field of geographic information. The file format has become an open standard for the geographic information software community. shapefile is used to describe geometry objects: points, broken lines and polygons are a relatively common high-precision map format. shapefile is used as the existing geographic information software to support the most extensive data format, has the unique advantages of small file data size, high retrieval efficiency and the like, and is quite widely applied to high-precision maps stored in the shapefile format in practical application.
But simultaneously, because of the limitation of the shape file format, the map does not contain topology information, only single-shape elements are stored, no topology information is connected between road sections, the analysis efficiency is improved in the use process, and certain road information is lost. How to use a high-precision map without topological relation for track prediction is a urgent problem to be solved.
Disclosure of Invention
The invention provides a track prediction method, a track prediction device and Internet of vehicles equipment, which solve the problem that the track prediction cannot be carried out by using a high-precision map without topological relation in the prior art.
In a first aspect, an embodiment of the present invention provides a track prediction method, including:
under the condition that the position of a target object is detected to be lost, acquiring historical position coordinates and a running state of the target object before the position is lost;
and predicting the track of the target object in the position losing period according to the lane boundary characteristics in the map, the historical position coordinates before the position losing and the running state.
Optionally, predicting the track of the target object according to the lane boundary feature in the map, the historical position coordinates before the position is lost and the driving state includes:
determining a 1 st predicted position and a running state corresponding to the 1 st predicted position according to lane boundary characteristics in the map, historical position coordinates before the position is lost and the running state;
determining the (n+1) th predicted position of the target object and the running state corresponding to the (n+1) th predicted position according to the (n) th predicted position of the target object and the running state corresponding to the (n) th predicted position; n is more than or equal to 1 and is a positive integer;
and sequentially connecting the 1 st predicted position to the n th predicted position to generate a predicted track of the target object.
Optionally, the determining the 1 st predicted position and the running state corresponding to the 1 st predicted position according to the lane boundary feature in the map, the historical position coordinates before the position is lost and the running state includes:
generating a 1 st estimated position according to the historical position coordinates and the driving state before the position is lost;
determining a target lane where the target object is located according to the 1 st estimated position and the lane boundary characteristics;
determining a coordinate point set of a lane center line of the target lane according to the lane boundary characteristics of the target lane;
and determining the 1 st predicted position and the running state corresponding to the 1 st predicted position according to the 1 st predicted position and the coordinate point set.
Optionally, the determining the driving state corresponding to the n+1th predicted position and the n+1th predicted position of the target object according to the driving state corresponding to the n predicted position and the n predicted position of the target object includes:
generating an n+1th estimated position according to the nth predicted position of the target object and the running state corresponding to the nth predicted position;
determining a target lane where the target object is located according to the n+1th estimated position and the lane boundary characteristics;
determining a coordinate point set of a lane center line of the target lane according to the lane boundary characteristics of the target lane;
and determining the (n+1) th predicted position and a running state corresponding to the (n+1) th predicted position according to the (n+1) th predicted position and the coordinate point set.
Optionally, the determining, according to the n+1th predicted position and the coordinate point set, a running state corresponding to the n+1th predicted position and the n+1th predicted position includes:
determining a target coordinate point nearest to the (n+1) th estimated position from the coordinate point set;
and predicting the traveling state corresponding to the (n+1) th predicted position and the (n+1) th predicted position according to the target coordinate point and the (n+1) th predicted position.
Optionally, the predicting, according to the target coordinate point and the n+1th predicted position, a running state corresponding to the n+1th predicted position and the n+1th predicted position includes:
and predicting the running state corresponding to the (n+1) th predicted position and the (n+1) th predicted position of the target object by using the target coordinate point as a measured value and the (n+1) th predicted position as a predicted value through a linear Kalman filtering algorithm.
Optionally, the driving state includes: travel speed and heading angle.
In a second aspect, an embodiment of the present invention provides an internet of vehicles device, including: a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the trajectory prediction method according to the first aspect when the computer program is executed.
In a third aspect, an embodiment of the present invention provides a trajectory prediction apparatus, including:
the acquisition module is used for acquiring historical position coordinates and running states of the target object before the position loss under the condition that the position of the target object is detected to be lost;
and the prediction module is used for predicting the track of the target object in the position losing period according to the lane boundary characteristics in the map, the historical position coordinates before the position losing and the running state.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the trajectory prediction method according to the first aspect.
The technical scheme of the invention has the beneficial effects that:
in the scheme, under the condition that the position of the target object is detected to be lost, the historical position coordinates and the running state of the target object before the position is lost are obtained; and predicting the track of the target object in the position losing period according to the lane boundary characteristics in the map, the historical position coordinates before the position losing and the running state. By means of the method and the device, track prediction of the target object in the position loss period can be achieved by utilizing lane boundary characteristics, historical position coordinates before position loss and driving states in the map, and the problem that track prediction cannot be conducted by utilizing a high-precision map without topological relation in the prior art can be solved.
Drawings
FIG. 1 is a flow chart of a track prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic view of lane edge characteristics according to an embodiment of the present invention;
FIG. 3 is a schematic view of lane edge features and lane center lines according to an embodiment of the present invention;
FIG. 4 is a block diagram showing a track prediction apparatus according to an embodiment of the present invention;
fig. 5 shows a schematic hardware structure of an internet of vehicles device according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided merely to facilitate a thorough understanding of embodiments of the invention. It will therefore be apparent to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
In various embodiments of the present invention, it should be understood that the sequence numbers of the following processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
In addition, the terms "system" and "network" are often used interchangeably herein.
In the examples provided herein, it should be understood that "B corresponding to a" means that B is associated with a from which B may be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, and it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
First embodiment
As shown in fig. 1, an embodiment of the present invention provides a track prediction method, which specifically includes the following steps:
step 101: under the condition that the position of a target object is detected to be lost, acquiring historical position coordinates and a running state of the target object before the position is lost;
wherein, the driving state includes: travel speed and heading angle.
Step 102: and predicting the track of the target object in the position losing period according to the lane boundary characteristics in the map, the historical position coordinates before the position losing and the running state.
It should be noted that, the map used in the present application is a high-precision map file in shape format. The high-precision map file comprises file types such as Points, lines, outlines, and the files respectively correspond to geometric features of roads such as points, lines, planes and the like. The shape characteristics of each lane need to be obtained, the Polygen (polygonal) shape types contained in the lines file containing the road surface characteristics basically cover all map data information needed by the application, and the Point (Point) and Line (Line) shape information of the road is more unilateral, so that the application performs data analysis on the lines file, extracts lane edge characteristics of the whole map, and the lane edge characteristics can be understood as lane frames. As shown in fig. 2, which shows an effect diagram with lane edge features. The whole map consists of a plurality of sections of lane frames, each lane frame consists of a plurality of tens to hundreds of different side line scattered points of the section of lanes, and each scattered point has longitude and latitude information.
Although the lane frames have no topological relation, the position relation among the lane frames can be obtained through the scattered point coordinate information contained in the lane frames.
In the above embodiment, the track of the target object in the position loss period can be predicted by using the lane boundary characteristics in the map, the historical position coordinates before the position loss and the driving state, and the problem that the track prediction cannot be performed by using the high-precision map without topological relation in the prior art can be solved.
In an embodiment, in step 102, predicting the track of the target object according to the lane boundary feature in the map, the historical position coordinates before the position is lost, and the driving state includes:
determining a 1 st predicted position and a running state corresponding to the 1 st predicted position according to lane boundary characteristics in the map, historical position coordinates before the position is lost and the running state;
determining the (n+1) th predicted position of the target object and the running state corresponding to the (n+1) th predicted position according to the (n) th predicted position of the target object and the running state corresponding to the (n) th predicted position; n is more than or equal to 1 and is a positive integer;
and sequentially connecting the 1 st predicted position to the n th predicted position to generate a predicted track of the target object.
Wherein, the driving state includes: travel speed and heading angle.
In this embodiment, after determining the 1 st predicted position and the running state corresponding to the 1 st predicted position according to the lane boundary feature, the historical position coordinates before the position is lost, and the running state in the map, the next predicted position and the corresponding running state are predicted according to the previous predicted position and the corresponding running state, so as to obtain n predicted position points, where the n predicted position points are points on the predicted track.
In a specific embodiment, the determining the 1 st predicted position and the running state corresponding to the 1 st predicted position according to the lane boundary feature in the map, the historical position coordinates before the position is lost, and the running state includes:
generating a 1 st estimated position according to the historical position coordinates and the driving state before the position is lost;
determining a target lane where the target object is located according to the 1 st estimated position and the lane boundary characteristics;
determining a coordinate point set of a lane center line of the target lane according to the lane boundary characteristics of the target lane;
and determining the 1 st predicted position and the running state corresponding to the 1 st predicted position according to the 1 st predicted position and the coordinate point set.
Wherein, the driving state includes: travel speed and heading angle.
It should be noted that the 1 st estimated position is a preliminary estimated position, which is only used for determining the target lane where the target object is located, and is not a final estimated position.
In the specific implementation, the pre-aiming distance can be calculated according to the running speed in the running state, and the 1 st pre-aiming position can be obtained based on the course angle and the pre-aiming distance in the running state. Further, the lane boundary feature is regarded as a polygonal geometry composed of multiple points, and when the 1 st estimated position is located in the polygonal geometry composed of the lane boundary feature of the target lane, the target object is considered to be located in the target lane.
In specific implementation, the vehicle center line may be obtained by: and carrying out polygon solving on each section of independent lane frame (lane boundary characteristics) to obtain a lane center line. As shown in fig. 3, which shows an effect diagram of a lane center line of a partial lane frame, the lane center line is composed of scattered points. Points numbered 0 to 70 in fig. 3 are points in the coordinate point set of the lane center line, and two scattered points located at two sides of the center line are boundary feature points at two sides of the lane. The number of the lane center lines is the same as that of the lane frames, so that the lane frames and the lane center lines can be stored in a pairing mode, and when a target lane is positioned, the corresponding lane center line can be extracted according to the sequence number of the target lane.
In the embodiment, the 1 st estimated position is generated according to the historical position coordinates and the driving state before the position is lost, the target lane where the target object is located can be located according to the 1 st estimated position, and the 1 st estimated position and the corresponding driving state can be determined further based on the 1 st estimated position and the lane center line of the target lane. Because the lane center line can reflect the extending direction of the lane, the 1 st predicted position and the running state corresponding to the 1 st predicted position are determined based on the 1 st predicted position and the coordinate point set of the lane center line, the predicted position can be correctly kept in the lane, the target object can run along the trend of the lane center line, and the running position point of the target object in the target lane can be accurately predicted. Therefore, the embodiment can correlate the self state (position and running state) of the target object with the running traffic environment, and the traffic environment is used as a reference for track prediction, so that the predicted and deduced track is more accurate and reliable.
In a specific embodiment, the determining, according to the nth predicted position of the target object and the running state corresponding to the nth predicted position, the running state corresponding to the (n+1) th predicted position of the target object and the (n+1) th predicted position includes:
generating an n+1th estimated position according to the nth predicted position of the target object and the running state corresponding to the nth predicted position;
determining a target lane where the target object is located according to the n+1th estimated position and the lane boundary characteristics;
determining a coordinate point set of a lane center line of the target lane according to the lane boundary characteristics of the target lane;
and determining the (n+1) th predicted position and a running state corresponding to the (n+1) th predicted position according to the (n+1) th predicted position and the coordinate point set.
Wherein, the driving state includes: travel speed and heading angle.
In the specific implementation, the pre-aiming distance can be calculated according to the running speed in the running state, and the (n+1) th estimated position can be obtained based on the course angle and the pre-aiming distance in the running state. Further, the lane boundary feature is regarded as a polygonal geometry composed of multiple points, and when the n+1th estimated position is located in the polygonal geometry composed of the lane boundary features of the target lane, the target object is considered to be located in the target lane. When the target lane is positioned, the corresponding lane center line can be extracted according to the sequence number of the target lane.
In this embodiment, since the lane center line can reflect the extending direction of the lane, the travel state corresponding to the n-th predicted position and the n-th predicted position is determined based on the n+1-th predicted position and the coordinate point set of the lane center line, so that the predicted position can be correctly kept inside the lane, and the target object can travel along the direction of the lane center line, so that the travel track of the target object in the target lane can be predicted more accurately. Therefore, the embodiment can realize the association between the self state (position and running state) of the target object and the running traffic environment of the target object, and the traffic environment is used as a reference for track prediction, so that the predicted and deduced track is more accurate and reliable.
In a specific embodiment, the determining, according to the n+1th predicted position and the coordinate point set, a driving state corresponding to the n+1th predicted position and the n+1th predicted position includes:
determining a target coordinate point nearest to the (n+1) th estimated position from the coordinate point set;
and predicting the traveling state corresponding to the (n+1) th predicted position and the (n+1) th predicted position according to the target coordinate point and the (n+1) th predicted position.
Wherein, the driving state includes: travel speed and heading angle.
In this embodiment, according to the n+1th predicted position and the target coordinate point on the lane center line, which is closest to the n+1th predicted position, the n+1th predicted position is predicted, so that the predicted positions are arranged along the extending direction of the lane, and the driving track of the target object in the target lane can be predicted more accurately.
Moreover, the problem of no topological feature of the shape map can be well avoided by using the pre-aiming operation of the pre-estimated position, when the pre-estimated position is positioned at the edge of a certain lane frame shape, the next pre-estimated position is positioned in the next lane frame by using the pre-aiming mechanism, so that the next pre-estimated position can be subjected to subsequent prediction across the lane frame, and the predicted track can be continuously deduced, but is not limited to a certain single lane frame.
Specifically, predicting, according to the target coordinate point and the n+1th predicted position, a running state corresponding to the n+1th predicted position and the n+1th predicted position includes:
and predicting the running state corresponding to the (n+1) th predicted position and the (n+1) th predicted position of the target object by using the target coordinate point as a measured value and the (n+1) th predicted position as a predicted value through a linear Kalman filtering algorithm.
Wherein, the driving state includes: travel speed and heading angle.
Specifically, when the method is implemented, a target coordinate point is used as a measured value, the n+1th predicted position is used as a predicted value, a linear Kalman filtering algorithm is utilized to carry out Kalman prediction on the target coordinate point and the n+1th predicted position, and the expected n+1th predicted position, running speed, course angle and other information are obtained by adjusting the proportion of process noise and measurement noise.
In the above embodiment, the predicted positions of the subsequent states of all the missed targets are predicted by the cyclic iteration position prediction process, so as to obtain the predicted and deduced track. The self state of the target object can be associated with the traffic environment in which the target object runs, and the predicted and deduced track is more accurate and reliable by taking the traffic environment as a reference for track prediction.
In addition, compared with the traditional track prediction mode based on priori data, the track prediction result has higher confidence, and when special topography such as curves, tunnels and other non-long straight roads are encountered and signals are easy to lose, the prediction position can be correctly kept in the lane, so that a target object runs along the trend of the lane center line, and the track prediction precision under a specific scene is improved.
In addition, the high-precision map in the shape format is utilized, the map data format is fixed, the data volume is small, compared with other high-precision map formats with more traffic data such as topology information, the memory resources and operation resources required for calling the shape map are small, the algorithm speed is higher, and meanwhile the problem of actual deduction connection under the condition that each road section in the shape map has no topological relation is solved.
Second embodiment
As shown in fig. 4, an embodiment of the present invention provides a track detection apparatus 400, including:
the acquiring module 401 acquires a historical position coordinate and a running state of the target object before the position loss when the position of the target object is detected to be lost;
and a prediction module 402, configured to predict a track of the target object in a position loss period according to the lane boundary feature in the map, the historical position coordinates before the position loss, and the driving state.
Optionally, the prediction module 402 includes:
the first prediction submodule is used for determining a 1 st predicted position and a running state corresponding to the 1 st predicted position according to lane boundary characteristics in the map, historical position coordinates before the position is lost and the running state;
the second prediction sub-module is used for determining the (n+1) th predicted position of the target object and the running state corresponding to the (n+1) th predicted position according to the (n) th predicted position of the target object and the running state corresponding to the (n) th predicted position; n is more than or equal to 1 and is a positive integer;
and the third prediction sub-module is used for sequentially connecting the 1 st prediction position to the n th prediction position to generate a prediction track of the target object.
Optionally, the first prediction submodule includes:
the first prediction unit is used for generating a 1 st estimated position according to the historical position coordinates and the driving state before the position is lost;
the second prediction unit is used for determining a target lane where the target object is located according to the 1 st estimated position and the lane boundary characteristics;
the third prediction unit is used for determining a coordinate point set of a lane center line of the target lane according to the lane boundary characteristics of the target lane;
and the fourth prediction unit is used for determining the 1 st prediction position and the running state corresponding to the 1 st prediction position according to the 1 st prediction position and the coordinate point set.
Optionally, the second prediction submodule includes:
a fifth prediction unit, configured to generate an n+1th predicted position according to the nth predicted position of the target object and a running state corresponding to the nth predicted position;
a sixth prediction unit, configured to determine a target lane where the target object is located according to the n+1th estimated position and the lane boundary feature;
a seventh prediction unit, configured to determine a coordinate point set of a lane center line of the target lane according to the lane boundary characteristic of the target lane;
and the eighth prediction unit is used for determining the running state corresponding to the (n+1) th prediction position and the (n+1) th prediction position according to the (n+1) th prediction position and the coordinate point set.
Optionally, the eighth prediction unit is specifically configured to:
determining a target coordinate point nearest to the (n+1) th estimated position from the coordinate point set;
and predicting the traveling state corresponding to the (n+1) th predicted position and the (n+1) th predicted position according to the target coordinate point and the (n+1) th predicted position.
Optionally, the eighth prediction unit is specifically configured to, when predicting, according to the target coordinate point and the n+1th predicted position, a running state corresponding to the n+1th predicted position and the n+1th predicted position:
and predicting the running state corresponding to the (n+1) th predicted position and the (n+1) th predicted position of the target object by using the target coordinate point as a measured value and the (n+1) th predicted position as a predicted value through a linear Kalman filtering algorithm.
Optionally, the driving state includes: travel speed and heading angle.
The second embodiment of the present invention corresponds to the method of the first embodiment, and all the implementation means in the first embodiment are applicable to the embodiment of the track prediction device, so that the same technical effects can be achieved.
Third embodiment
In order to better achieve the above object, as shown in fig. 5, a fourth embodiment of the present invention further provides an internet of vehicles device, including:
a processor 500; and a memory 520 connected to the processor 500 through a bus interface, the memory 520 storing programs and data used by the processor 500 in performing operations, the processor 500 calling and executing the programs and data stored in the memory 1120.
Wherein the transceiver 510 is coupled to the bus interface for receiving and transmitting data under the control of the processor 500; the processor 500 is configured to read the program in the memory 520 to implement the following steps:
under the condition that the position of a target object is detected to be lost, acquiring historical position coordinates and a running state of the target object before the position is lost;
and predicting the track of the target object in the position losing period according to the lane boundary characteristics in the map, the historical position coordinates before the position losing and the running state.
Wherein in fig. 5, a bus architecture may comprise any number of interconnected buses and bridges, and in particular one or more processors represented by processor 500 and various circuits of memory represented by memory 520, linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., which are well known in the art and, therefore, will not be described further herein. The bus interface provides an interface. The transceiver 510 may be a number of elements, including a transmitter and a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The user interface 530 may also be an interface capable of interfacing with an inscribed desired device for a different terminal, including but not limited to a keypad, display, speaker, microphone, joystick, etc. The processor 500 is responsible for managing the bus architecture and general processing, and the memory 520 may store data used by the processor 500 in performing operations.
Optionally, the processor 500 is specifically configured to read the program in the memory 520 to implement the following steps:
determining a 1 st predicted position and a running state corresponding to the 1 st predicted position according to lane boundary characteristics in the map, historical position coordinates before the position is lost and the running state;
determining the (n+1) th predicted position of the target object and the running state corresponding to the (n+1) th predicted position according to the (n) th predicted position of the target object and the running state corresponding to the (n) th predicted position; n is more than or equal to 1 and is a positive integer;
and sequentially connecting the 1 st predicted position to the n th predicted position to generate a predicted track of the target object.
Optionally, the processor 500 is specifically configured to read the program in the memory 520 to implement the following steps:
generating a 1 st estimated position according to the historical position coordinates and the driving state before the position is lost;
determining a target lane where the target object is located according to the 1 st estimated position and the lane boundary characteristics;
determining a coordinate point set of a lane center line of the target lane according to the lane boundary characteristics of the target lane;
and determining the 1 st predicted position and the running state corresponding to the 1 st predicted position according to the 1 st predicted position and the coordinate point set.
Optionally, the processor 500 is specifically configured to read the program in the memory 520 to implement the following steps:
generating an n+1th estimated position according to the nth predicted position of the target object and the running state corresponding to the nth predicted position;
determining a target lane where the target object is located according to the n+1th estimated position and the lane boundary characteristics;
determining a coordinate point set of a lane center line of the target lane according to the lane boundary characteristics of the target lane;
and determining the (n+1) th predicted position and a running state corresponding to the (n+1) th predicted position according to the (n+1) th predicted position and the coordinate point set.
Optionally, the processor 500 is specifically configured to read the program in the memory 520 to implement the following steps:
determining a target coordinate point nearest to the (n+1) th estimated position from the coordinate point set;
and predicting the traveling state corresponding to the (n+1) th predicted position and the (n+1) th predicted position according to the target coordinate point and the (n+1) th predicted position.
Optionally, the processor 500 is specifically configured to read the program in the memory 520 to implement the following steps:
and predicting the running state corresponding to the (n+1) th predicted position and the (n+1) th predicted position of the target object by using the target coordinate point as a measured value and the (n+1) th predicted position as a predicted value through a linear Kalman filtering algorithm.
Optionally, the driving state includes: travel speed and heading angle.
According to the Internet of vehicles equipment provided by the invention, when the position of the target object is detected to be lost, the historical position coordinates and the running state of the target object before the position is lost are obtained; and predicting the track of the target object in the position losing period by utilizing the lane boundary characteristics, the historical position coordinates and the running state before the position losing in the map.
Those skilled in the art will appreciate that all or part of the steps of implementing the above-described embodiments may be implemented by hardware, or may be implemented by instructing the relevant hardware by a computer program comprising instructions for performing some or all of the steps of the above-described methods; and the computer program may be stored in a readable storage medium, which may be any form of storage medium.
In addition, a specific embodiment of the present invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method in the first embodiment described above. And the same technical effects can be achieved, and in order to avoid repetition, the description is omitted here.
Furthermore, it should be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. Also, the steps of performing the series of processes described above may naturally be performed in chronological order in the order of description, but are not necessarily performed in chronological order, and some steps may be performed in parallel or independently of each other. It will be appreciated by those of ordinary skill in the art that all or any of the steps or components of the methods and apparatus of the present invention may be implemented in hardware, firmware, software, or a combination thereof in any computing device (including processors, storage media, etc.) or network of computing devices, as would be apparent to one of ordinary skill in the art after reading this description of the invention.
The object of the invention can thus also be achieved by running a program or a set of programs on any computing device. The computing device may be a well-known general purpose device. The object of the invention can thus also be achieved by merely providing a program product containing program code for implementing said method or apparatus. That is, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. It is apparent that the storage medium may be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. The steps of executing the series of processes may naturally be executed in chronological order in the order described, but are not necessarily executed in chronological order. Some steps may be performed in parallel or independently of each other.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.

Claims (10)

1. A track prediction method, comprising:
under the condition that the position of a target object is detected to be lost, acquiring historical position coordinates and a running state of the target object before the position is lost;
and predicting the track of the target object in the position losing period according to the lane boundary characteristics in the map, the historical position coordinates before the position losing and the running state.
2. The trajectory prediction method according to claim 1, wherein predicting the trajectory of the target object based on lane boundary characteristics in a map, historical position coordinates before the position loss, and a traveling state, comprises:
determining a 1 st predicted position and a running state corresponding to the 1 st predicted position according to lane boundary characteristics in the map, historical position coordinates before the position is lost and the running state;
determining the (n+1) th predicted position of the target object and the running state corresponding to the (n+1) th predicted position according to the (n) th predicted position of the target object and the running state corresponding to the (n) th predicted position; n is more than or equal to 1 and is a positive integer;
and sequentially connecting the 1 st predicted position to the n th predicted position to generate a predicted track of the target object.
3. The trajectory prediction method according to claim 2, wherein the determining the 1 st predicted position and the running state corresponding to the 1 st predicted position according to the lane-side characteristic in the map, the history position coordinates before the position loss, and the running state includes:
generating a 1 st estimated position according to the historical position coordinates and the driving state before the position is lost;
determining a target lane where the target object is located according to the 1 st estimated position and the lane boundary characteristics;
determining a coordinate point set of a lane center line of the target lane according to the lane boundary characteristics of the target lane;
and determining the 1 st predicted position and the running state corresponding to the 1 st predicted position according to the 1 st predicted position and the coordinate point set.
4. The trajectory prediction method according to claim 2, wherein the determining the travel state corresponding to the n+1th predicted position and the n+1th predicted position of the target object according to the travel state corresponding to the n-th predicted position and the n predicted position of the target object includes:
generating an n+1th estimated position according to the nth predicted position of the target object and the running state corresponding to the nth predicted position;
determining a target lane where the target object is located according to the n+1th estimated position and the lane boundary characteristics;
determining a coordinate point set of a lane center line of the target lane according to the lane boundary characteristics of the target lane;
and determining the (n+1) th predicted position and a running state corresponding to the (n+1) th predicted position according to the (n+1) th predicted position and the coordinate point set.
5. The trajectory prediction method according to claim 4, wherein the determining, from the n+1th predicted position and the coordinate point set, a running state corresponding to the n+1th predicted position and the n+1th predicted position includes:
determining a target coordinate point nearest to the (n+1) th estimated position from the coordinate point set;
and predicting the traveling state corresponding to the (n+1) th predicted position and the (n+1) th predicted position according to the target coordinate point and the (n+1) th predicted position.
6. The trajectory prediction method according to claim 5, wherein predicting the travel state corresponding to the n+1th predicted position and the n+1th predicted position from the target coordinate point and the n+1th predicted position includes:
and predicting the running state corresponding to the (n+1) th predicted position and the (n+1) th predicted position of the target object by using the target coordinate point as a measured value and the (n+1) th predicted position as a predicted value through a linear Kalman filtering algorithm.
7. The trajectory prediction method according to any one of claims 1 to 6, characterized in that the running state includes: travel speed and heading angle.
8. An internet of vehicles device, comprising: transceiver, memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the trajectory prediction method according to any one of claims 1 to 7 when executing the computer program.
9. A trajectory prediction device, comprising:
the acquisition module is used for acquiring historical position coordinates and running states of the target object before the position loss under the condition that the position of the target object is detected to be lost;
and the prediction module is used for predicting the track of the target object in the position losing period according to the lane boundary characteristics in the map, the historical position coordinates before the position losing and the running state.
10. A computer readable storage medium having stored thereon a computer program, which when executed by a processor performs the steps of the trajectory prediction method according to any one of claims 1 to 7.
CN202211724629.1A 2022-12-30 2022-12-30 Track prediction method and device and Internet of vehicles equipment Pending CN116311895A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211724629.1A CN116311895A (en) 2022-12-30 2022-12-30 Track prediction method and device and Internet of vehicles equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211724629.1A CN116311895A (en) 2022-12-30 2022-12-30 Track prediction method and device and Internet of vehicles equipment

Publications (1)

Publication Number Publication Date
CN116311895A true CN116311895A (en) 2023-06-23

Family

ID=86815693

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211724629.1A Pending CN116311895A (en) 2022-12-30 2022-12-30 Track prediction method and device and Internet of vehicles equipment

Country Status (1)

Country Link
CN (1) CN116311895A (en)

Similar Documents

Publication Publication Date Title
CN110260870B (en) Map matching method, device, equipment and medium based on hidden Markov model
US9494694B1 (en) Method and apparatus of road location inference for moving object
CN109215372B (en) Road network information updating method, device and equipment
CN112212874B (en) Vehicle track prediction method and device, electronic equipment and computer readable medium
US20230070760A1 (en) Method for generating real-time relative map, intelligent driving device, and computer storage medium
CN110389995B (en) Lane information detection method, apparatus, device, and medium
CN114212110B (en) Obstacle trajectory prediction method and device, electronic equipment and storage medium
EP3023740B1 (en) Method, apparatus and computer program product for route matching
CN111829536B (en) Navigation map road network generation method and device, storage medium and electronic equipment
CN115585816B (en) Lane-level map matching method and device
CN113742437B (en) Map updating method, device, electronic equipment and storage medium
CN113050660B (en) Error compensation method, error compensation device, computer equipment and storage medium
CN112616118B (en) ETC portal determination method, device and storage medium for vehicles to pass through
Wu et al. A heuristic map-matching algorithm by using vector-based recognition
Karimi et al. A methodology for predicting performances of map-matching algorithms
CN111613052B (en) Traffic condition determining method and device, electronic equipment and storage medium
CN114705180B (en) Data correction method, device and equipment for high-precision map and storage medium
CN116311895A (en) Track prediction method and device and Internet of vehicles equipment
CN109270566A (en) Air navigation aid, navigation effect test method, device, equipment and medium
CN102045636A (en) Road condition navigation method, mobile terminal and road condition navigation server
CN113008246B (en) Map matching method and device
CN111288942B (en) Track transponder position measuring method and device and computer equipment
Yang et al. The research on real-time map-matching algorithm
CN112394371A (en) GPS analog signal generation method and device, electronic equipment and storage medium
CN112632150B (en) Method and device for determining turning point and electronic equipment

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