CN115326081A

CN115326081A - Map matching method, map matching device, computer equipment and storage medium

Info

Publication number: CN115326081A
Application number: CN202110505468.6A
Authority: CN
Inventors: 张然; 刘新宇; 黄翔宇; 傅建雄; 周浩
Original assignee: Beijing Wanji Technology Co Ltd
Current assignee: Beijing Wanji Technology Co Ltd
Priority date: 2021-05-10
Filing date: 2021-05-10
Publication date: 2022-11-11

Abstract

The application relates to a map matching method, a map matching device, a computer device and a storage medium, wherein the evaluation matching probability of a vehicle position and at least one candidate road section in a target map searching range is obtained according to the distance between the vehicle position and the last observation point of a vehicle and the precision factor of a navigation device; determining the state matching probability of each candidate road section and the vehicle position according to the evaluation matching probability of each candidate road section, the state transition probability from the history matching road section of the previous observation point to each candidate road section and the history state matching probability of the history matching road section of the previous observation point; and then determining a target matching road section of the driving path of the vehicle in the map according to the state matching probability of each candidate road section and the position of the vehicle. The method eliminates errors caused by instability of navigation equipment in the process of map matching, so that the final map matching result is more accurate.

Description

Map matching method, map matching device, computer equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of intelligent travel, in particular to a map matching method, a map matching device, computer equipment and a storage medium.

Background

With the development of science and technology and society, the problem of road traffic safety and the problem of traffic efficiency become increasingly prominent, and V2X is increasingly popularized as a system scheme in vehicle-road cooperation.

Map matching is gaining more and more attention as a basic support function of V2X, and map matching in V2X is one item: and carrying out road section matching according to the GPS information and the map information of the vehicle to obtain the node information of the road section where the vehicle is located. Specifically, map matching is performed according to information such as longitude, latitude, course angle, speed and the like in the vehicle GPS, and information such as upstream and downstream node relation, node longitude, node latitude and the like of a plurality of nodes in map information is matched, so that a unique matching road section of the vehicle in the map is obtained.

However, in practical applications, the GPS information is not stable enough, resulting in the map matching method being not accurate enough.

Disclosure of Invention

In view of the above, it is necessary to provide a map matching method, apparatus, computer device and storage medium, which can improve the accuracy of the final map matching result.

In a first aspect, an embodiment of the present application provides a map matching method, where the method includes:

obtaining the evaluation matching probability of the vehicle position and at least one candidate road section in the target map searching range according to the distance between the vehicle position and the last observation point of the vehicle and the precision factor of the navigation equipment;

determining the state matching probability of each candidate road section and the vehicle position according to the evaluation matching probability of each candidate road section, the state transition probability from the history matching road section of the previous observation point to each candidate road section and the history state matching probability of the history matching road section of the previous observation point;

and determining a target matching road section of the driving path of the vehicle in the map according to the state matching probability of each candidate road section and the position of the vehicle.

In one embodiment, the obtaining an estimated matching probability between the vehicle position and at least one candidate road segment in the target map search range according to the distance between the vehicle position and the last observation point and the navigation device precision factor includes:

acquiring distribution information of the distance between the vehicle position and the last observation point, and regularizing a precision factor of the navigation equipment;

and determining the evaluation matching probability of each candidate road section according to the distribution information of the distance between the vehicle position and the last observation point and the navigation equipment precision factor after regularization processing.

In one embodiment, the method further comprises:

obtaining a map network topological relation between a history matching road section of a previous observation point and each candidate road section;

and determining the state transition probability from the history matching road section of the previous observation point to each candidate road section according to the topological relation of the map network.

In one embodiment, the determining the state transition probability from the history matching road segment of the previous observation point to each candidate road segment according to the map network topology relationship includes:

for any candidate segment:

if the map network topological relation is that the candidate road section is the same road section of the history matching road section, determining that the transition probability is a preset first value;

and if the map network topological relation is that the candidate road section is the next road section of the history matching road section, determining that the transition probability is a preset second value.

In one embodiment, the method further comprises:

acquiring initial state matching probability values of initial candidate road sections in a search range from an initial observation point of a vehicle to a target map;

and determining the historical state matching probability of the historical matching road section of the previous observation point according to the initial state matching probability value.

In one embodiment, the obtaining of the initial state matching probability value of each candidate road segment in the search range from the initial observation point to the target map includes:

determining a projection point proportion evaluation value of each initial candidate road section according to proportion information of projection points of the initial observation points in each initial candidate road section;

determining a distance evaluation value of each initial candidate road section according to the distance information from the initial observation point to each initial candidate road section;

determining an included angle evaluation value of each initial candidate road section according to included angle information from the driving direction of the initial observation point to the direction of each initial candidate road section;

and determining the initial state matching probability value of each initial candidate road section according to the projection point proportion evaluation value, the distance evaluation value and the included angle evaluation value of each initial candidate road section.

In one embodiment, the determining the historical state matching probability of the historical matching road segment of the previous observation point according to the initial state matching probability value includes:

and taking the state matching probability values of all candidate road sections of the initial observation point as initial values, sequentially determining the historical state matching probability of the historical matching road section of the next observation point according to the observation point sequence of the driving path of the vehicle until the previous observation point of the vehicle position is determined, and obtaining the historical state matching probability of the historical matching road section of the previous observation point.

In one embodiment, the determining the target matching section of the driving path of the vehicle in the map according to the state matching probability of each candidate section and the vehicle position includes:

and determining the candidate road section corresponding to the maximum state matching probability value and a sequence road section formed by the historical track of the vehicle as a target matching road section of the driving path of the vehicle in the map.

In a second aspect, an embodiment of the present application provides a map matching apparatus, including:

the acquisition module is used for acquiring the evaluation matching probability of the vehicle position and at least one candidate road section in the target map search range according to the distance between the vehicle position and the last observation point of the vehicle and the navigation equipment precision factor;

the determining module is used for determining the state matching probability of each candidate road section and the vehicle position according to the evaluation matching probability of each candidate road section, the state transition probability from the history matching road section of the previous observation point to each candidate road section and the history state matching probability of the history matching road section of the previous observation point;

and the matching module is used for determining a target matching road section of the driving path of the vehicle in the map according to the state matching probability of each candidate road section and the position of the vehicle.

In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the method steps of any one of the foregoing first aspects when executing the computer program.

In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method steps of any one of the embodiments in the first aspect.

According to the map matching method, the map matching device, the computer equipment and the storage medium, the evaluation matching probability of at least one candidate road section in the search range of the target map and the vehicle position is obtained according to the distance between the vehicle position and the last observation point of the vehicle and the precision factor of the navigation equipment; determining the state matching probability of each candidate road section and the vehicle position according to the evaluation matching probability of each candidate road section, the state transition probability from the history matching road section of the previous observation point to each candidate road section and the history state matching probability of the history matching road section of the previous observation point; and then determining a target matching road section of the driving path of the vehicle in the map according to the state matching probability of each candidate road section and the position of the vehicle. In the method, the estimated matching probability of each candidate road section is determined by combining the navigation equipment precision factor HDOP and the distance between the vehicle position and the last observation point of the vehicle, so that the influence caused by the HDOP is considered in the map matching process, namely, the error caused by the instability of the navigation equipment is eliminated in the map matching process, and the final map matching result is more accurate.

Drawings

FIG. 1 is a diagram of an application environment of a map matching method provided in an embodiment;

FIG. 2 is a flow diagram illustrating a method for map matching in one embodiment;

FIG. 3 is a schematic flow chart diagram of a map matching method in accordance with another embodiment;

FIG. 4 is a schematic flow chart diagram of a map matching method in accordance with another embodiment;

FIG. 5 is a schematic flow chart diagram of a map matching method in accordance with another embodiment;

FIG. 6 is a flow chart illustrating a method for map matching in accordance with another embodiment;

FIG. 7 is a schematic representation of a projected relationship of a path and a vehicle location provided in one embodiment;

FIG. 8 is a flow diagram of a method of map matching provided in one embodiment;

FIG. 9 is a block diagram of a map matching apparatus provided in an embodiment;

FIG. 10 is a diagram showing an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The map matching method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the processor in the computer device is configured to provide computing and control capabilities; the memory comprises a nonvolatile storage medium and an internal memory; the non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and a computer program in the nonvolatile storage medium; the database of the computer device is used for storing relevant data in the map matching process. The network interface of the computer device is used for communicating with other external devices through network connection. The computer device may be installed in a vehicle, and may be, but is not limited to, a vehicle-mounted navigation device or a personal computer, a notebook computer, a smart phone, a tablet computer, a portable wearable device, etc. with a built-in vehicle-mounted navigator. Of course, the computer device can also be a server, which performs map matching by wired or wireless communication with the navigation device in the vehicle.

The following detailed description will specifically explain how the technical solutions of the present application and the technical solutions of the present application solve the above technical problems by embodiments and with reference to the accompanying drawings. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. In the following description, a map matching method provided in an embodiment of the present application is described with an execution subject being a computer device. In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments.

In an embodiment, as shown in fig. 2, a map matching method is provided, and this embodiment relates to a specific process that, in combination with a distance between a current position of a vehicle and a previous observation point and an accuracy factor of a navigation device on the vehicle, an estimated matching probability of a candidate road segment can be obtained, and based on the estimated matching probability, a state transition probability of each candidate road segment observed last, and a historical state matching probability of the previous observation point, a state matching probability of each candidate road segment and a vehicle position can be determined, and a target matching road segment is finally determined; this embodiment comprises the steps of:

and S101, acquiring the evaluation matching probability of the vehicle position and at least one candidate road section in the target map searching range according to the distance between the vehicle position and the last observation point of the vehicle and the precision factor of the navigation equipment.

The vehicle position is a current position point of the vehicle, and specific information of the current position point can be determined through a navigation device in the vehicle, for example, longitude, latitude and heading angle information of the vehicle are acquired through a GPS navigator.

The current time point corresponding to the current position point can be regarded as a current observation point, and the last observation point is the time point of the last road section matching of the vehicle. For the last observation point, the road segment matching has been completed, and the navigation device can also acquire the position information of the vehicle at the last observation point, so that the position of the vehicle at the last observation point is known. Then, the distance between the current position point of the vehicle and the position of the vehicle at the last observation point can be determined. Therefore, the distance between the vehicle position (current observation point) and the last observation point (vehicle position) substantially reflects the change between the two GPS sampling points.

In general, in the practical application of map matching, the acquired GPS information is not stable enough due to hardware problems or algorithm problems, so that a plurality of vehicle location points need to be integrated to determine the final matching result. And since there must be some relationship between the information in the time series, i.e., the GPS-determined vehicle location points in the series, the relationship between each location point is related to the horizontal component precision (HDOP) of the GPS. The HDOP is an open root number value of a sum of squared errors such as latitude and longitude. The size of the HDOP value is positively correlated with the error of GPS positioning, the larger the HDOP value is, the larger the positioning error of the GPS is, and the lower the positioning accuracy of the GPS is, so that the HDOP of the GPS for a period of time can influence the final matching result. Based on this, the embodiment of the application determines the estimated matching probability of the vehicle position and each candidate road segment by combining the distance between the vehicle position and the last observation point of the vehicle and the precision factor of the navigation device, so that the estimated matching probability of each candidate road segment and the vehicle position can be more accurate. The estimated matching probability is the probability that each candidate road segment preliminarily estimated matches the vehicle position.

Each candidate link refers to a link in a target map search range, the target map search range refers to a possible range of the current driving path of the vehicle in the map, that is, any link in the target map search range is likely to be a matching link of the current driving path of the vehicle. The target map search range is predetermined, for example, a current preliminary position of the vehicle is determined in advance according to historical travel data (including, but not limited to, a track, travel time, form speed, and the like) of the vehicle in combination with a current travel time of the vehicle, and then the target map search range is determined in the map according to the preliminary position. The determining mode of the target map searching range is not limited in the embodiment of the application; or, according to the position of the GPS positioning of the vehicle, a range is determined with the position as the center of a circle, and the range may be used as the target map search range.

For any candidate road segment, for example, the estimated matching probability of the candidate road segment and the vehicle position can be determined through a preset neural network model, that is, the distance between the vehicle position and the last observation point and the precision factor of the navigation device are used as input data and input into the trained neural network model, and the obtained output is the estimated matching probability of the candidate road segment and the vehicle position. Alternatively, the estimated matching probability of the candidate link to the vehicle position may be determined by summing the difference between the distance from the vehicle position to the last observation point and the distance from the vehicle position to the candidate link, and the precision factor of the navigation device. The embodiments of the present application do not limit this. The precision factor of the navigation equipment can be directly acquired from the navigation equipment.

S102, determining the state matching probability of each candidate road section and the vehicle position according to the evaluation matching probability of each candidate road section, the state transition probability from the history matching road section of the previous observation point to each candidate road section and the history state matching probability of the history matching road section of the previous observation point.

After the evaluation matching probability of each candidate road section is obtained, the state transition probability from the history matching road section of the previous observation point to each candidate road section and the history state matching probability of the history matching road section of the previous observation point need to be further obtained.

In map matching, the state at time T and the state at time T +1 are associated with each other, for example, the positions of the preceding and following times are necessarily related to the speed, which conforms to the basic characteristics of the hidden markov model. For the initial positioning results at different moments, the initial positioning result at the previous moment is converted from a certain state to a certain state of the initial positioning result at the next moment, and the probability is the state transition probability from the history matching road section at the previous observation point to each candidate road section. Therefore, the state transition probability is determined from the state relation dimension between adjacent observation points, and can reflect the possibility that each candidate road segment is the target matching road segment.

The history matching section of the last observation point refers to the final matching section I which is matched last time _F Therefore, the history state matching probability of the history matching section means that the final matching section I is not determined in the last map matching _F Time, road section I _F The state match probability. Road section I _F Has not determined I _F When the final matching road section is obtained, the dimension representing the road section I from the state information (such as distance, included angle, projection information and the like) is _F Is the probability value of the final matching road segment.

For example, when determining the state matching probability of each candidate link and the vehicle position based on the estimated matching probability of each candidate link, the state transition probability of the history matching link of the previous observation point to each candidate link, and the history state matching probability of the history matching link of the previous observation point, the product of the three may be used as the state matching probability of each candidate link and the vehicle position, or the sum or weighted sum of the three may be used as the state matching probability of each candidate link and the vehicle position, and the like, which is not limited in the embodiment of the present application.

For example, take the product as an example, let P be _N (seg _i ) Representing the state matching probability of the candidate link i at the vehicle position (current observation point); p _N-1 (seg _i ) Representing the history state matching probability of the history matching road section i (final matching road section) at the last observation point; p _topo (seg _i ) A state transition probability representing a candidate link i that transitions from the history matching link of the last observation point to the vehicle position (current observation point); p _cvt (seg _i ) The estimated matching probability of the candidate road section i representing the vehicle position; then P is _N (seg _i )＝P _N-1 (seg _i )·P _topo (seg _i )·P _cvt (seg _i )。

And S103, determining a target matching road section of the driving path of the vehicle in the map according to the state matching probability of each candidate road section and the position of the vehicle.

After the state matching probability of each candidate road section and the position of the vehicle is determined, the target matching road section of the driving path of the vehicle in the map is determined based on the state matching probability.

In one embodiment, the candidate road section corresponding to the maximum state matching probability value and the sequence road section formed by the historical track of the vehicle are determined as the target matching road section of the driving path of the vehicle in the map.

And after all the candidate road sections are traversed, searching the candidate road section with the maximum state matching probability value, then searching the candidate road section corresponding to the maximum state matching probability value as the road section which is most matched with the current observation point, and then determining the candidate road section corresponding to the maximum state matching probability value and a sequence road section formed by history tracks matched with the history tracks to be the target matching road section of the driving path of the vehicle in the map. In other words, from the initial observation point to the current observation point, the candidate link with the highest state matching probability value at each observation point is the target candidate link corresponding to the observation point, so that the link formed by corresponding each observation point to the determined target candidate link can be called the target matching link of the driving path of the vehicle in the map.

The embodiment of the application provides a map matching method, which comprises the steps of obtaining the evaluation matching probability of at least one candidate road section in the search range of a vehicle position and a target map according to the distance between the vehicle position and the last observation point of a vehicle and the precision factor of navigation equipment; determining the state matching probability of each candidate road section and the vehicle position according to the evaluation matching probability of each candidate road section, the state transition probability from the history matching road section of the previous observation point to each candidate road section and the history state matching probability of the history matching road section of the previous observation point; and then determining a target matching road section of the driving path of the vehicle in the map according to the state matching probability of each candidate road section and the position of the vehicle. In the method, the estimated matching probability of each candidate road section is determined by combining the navigation equipment precision factor HDOP and the distance between the vehicle position and the last observation point of the vehicle, so that the influence caused by the HDOP is considered in the map matching process, namely, the error caused by the instability of the navigation equipment is eliminated in the map matching process, and the final map matching result is more accurate.

Based on the above embodiments, an example of the determination process of the estimated matching probability of each candidate link is provided below. As shown in fig. 3, in one embodiment, the embodiment comprises:

s201, obtaining distribution information of the distance between the vehicle position and the last observation point, and conducting regularization processing on the precision factor of the navigation equipment.

The distribution information of the distance from the vehicle position to the last observation point may be a gaussian distribution (normal distribution) or the like. For example, the difference between the distance of the vehicle position to the last observation point and the distance of the vehicle position to the candidate road segment establishes a gaussian distribution:

d _I distance of vehicle position to last observation point, d _i For the distance from the vehicle position to the candidate road section i, μ is an expected value of the distribution, and is usually 0, and σ is a standard deviation parameter, which determines the amplitude of the distribution, and is usually 4.07.

And after the accuracy factor of the navigation equipment is acquired, the navigation equipment is subjected to regularization processing so as to reduce errors. For example,

where γ is a regularization parameter, typically taking a value of 2 to 6, which is used for controlBalance relationships among two different targets, i.e., a target for balance fitting training and a target for keeping parameter values small.

S202, determining the evaluation matching probability of each candidate road section according to the distribution information of the distance between the vehicle position and the last observation point and the navigation equipment precision factor after regularization processing.

And determining the sum of the distribution information of the distance between the vehicle position and the last observation point and the regularized precision factor of the navigation equipment as the evaluation matching probability of the determined candidate road section. For example, the estimated matching probability of the candidate link i is represented as P _cvt (seg _i ) And then:

in the embodiment, the distribution information of the distance between the vehicle position and the last observation point is obtained, the navigation equipment accuracy factor is subjected to regularization, and then the estimated matching probability of each candidate road section is determined according to the distribution information of the distance between the vehicle position and the last observation point and the regularized navigation equipment accuracy factor, so that the estimated matching probability of the candidate road section is determined according to the HDOP and the distance, namely the influence of the HDOP on the candidate road section as a final target matching road section is considered, and when the HDOP is considered, the regularization is performed on the candidate road section, so that the measurement error is reduced, and the accuracy of the estimated matching probability is improved.

The probability of the above state transition probability and the history state matching probability is explained by the embodiment below. In an embodiment, an implementation of determining a state transition probability of a history matching road segment of a last observation point to each candidate road segment is provided, as shown in fig. 4, the embodiment includes:

s301, obtaining the map network topological relation between the history matching road section of the last observation point and each candidate road section.

The map network topology relationship is a connection relationship between roads in the map, such as the trend of each road, the intersection point with other roads, the distance, the physical space distribution, and other information. Here, the topological relation between the history matching road section determined by the last observation point and each candidate road section of the current observation point is referred to. For example, if the history matching section is an AB section, and each candidate section of the current observation point includes a CD section and an EF section, the topological relationship between the history matching section and each candidate section may be that the CD section is a downstream section of the AB section, the EF section is an upstream section of the AB section, and so on. Besides the upstream and downstream road segments, the current road segment may also be a current road segment belonging to a history matching road segment, and a lane on the current road segment, for example, the current lane, another lane, and the like.

Specifically, the map network topological relation between the history matching road section and each candidate road section can be determined according to the road relation stored in the electronic map and the self positions of the history matching road section and the candidate road section in the map.

S302, according to the topological relation of the map network, determining the state transition probability from the history matching road section of the previous observation point to each candidate road section.

After the map network topological relation between the history matching road section of the previous observation point and each candidate road section is determined, the state transition probability from the history matching road section of the previous observation point to each candidate road section is determined by combining the map network topological relation.

In one embodiment, taking any candidate segment as an example, the map-to-map network topology relationship includes: two relations that the candidate road section is the same road section of the history matching road section and the candidate road section is the next road section of the history matching road section are taken as examples for explanation. Then, according to the map network topology relationship, the method for determining the state transition probability from the history matching road section of the previous observation point to each candidate road section comprises the following steps:

if the map network topological relation is that the candidate road section is the same road section of the history matching road section, determining that the transition probability is a preset first value; and if the map network topological relation is that the candidate road section is the next road section of the history matching road section, determining that the transition probability is a preset second value.

For the same road section of which the candidate road section is the history matching road section, the history matching road section which is successfully matched with the previous observation point is the same road section, namely the vehicle does not drive out of the driving road section of the previous observation point at present; and the candidate road section is the next road section of the history matching road section, which indicates that the vehicle has driven out from the history matching road section of the last observation point and reaches the downstream road section.

Exemplarily, let P _topo (seg _i ) Representing the state transition probability of the candidate road section I, and I represents the history matching road section

It can be determined that if the candidate road segment is the same road segment as the history matching road segment, the transition probability is determined to be a preset first value, namely 0.5; if the candidate road section is the next road section of the history matching road section, determining that the transition probability is a preset second value, namely 0.2; and if the topological relation between the candidate road section and the historical matching road section is not the two, the transition probability is determined to be 0, and the candidate road section i is represented as the target matching road section which cannot be the current observation point.

In this embodiment, a map network topology relationship between the history matching road section of the previous observation point and each candidate road section is obtained, and according to the map network topology relationship, a state transition probability from the history matching road section of the previous observation point to each candidate road section is determined. Because the topological relation of the map network reflects the position relation among the road sections, the state transition probability is determined according to the geographic position, so that the probability of the state transition can more accurately reflect the possibility that each candidate road section is a target matching road section.

In another embodiment, an implementation is provided for determining a history state matching summary of history matching road segments of a previous observation point, as shown in fig. 5, which includes the following steps:

s401, acquiring initial state matching probability values of initial candidate road sections from an initial observation point of a vehicle to a target map searching range.

The initial observation point is the moment when map matching is performed at the beginning, and each initial candidate road section has an initial state matching probability value at the initial observation point. For example, there are three road segments I1, I2, I3 in the target map search range, which are initial candidate road segments of the initial observation point, and the initial position of the vehicle (the position corresponding to the initial observation point) can also be located to specific position information by the navigation device, so that according to the initial position of the vehicle and the road segment information (e.g., direction, position, etc.) of the initial candidate road segments I1, I2, I3, a matching degree of the initial candidate road segments I1, I2, I3 with the initial position of the vehicle can be determined, and this matching degree can be regarded as the initial state probability value of the initial candidate road segments I1, I2, I3.

S402, determining the historical state matching probability of the historical matching road section of the previous observation point according to the initial state matching probability value.

And determining the historical state probability value of the historical matching road section of the last observation point based on the determined initial state matching probability value of each initial candidate road section. The last observation point is defined relative to the current observation point, e.g., the initial observation point is T0, the current observation point is Tn, then the last observation point is Tn-1, and assuming n =5, the last observation point is T4. Therefore, after the initial state matching probability value of the initial candidate road section of the initial observation point T0 is determined, the state matching probability of each candidate road section of the previous observation point T4 can be determined by sequentially determining the next observation point.

Optionally, determining a historical state matching probability of the historical matching road segment of the last observation point according to the initial state matching probability value includes: and taking the state matching probability value of each candidate road section of the initial observation point as an initial value, sequentially determining the historical state matching probability of the historical matching road section of the next observation point according to the sequence of the observation points of the driving path of the vehicle until the previous observation point of the vehicle position is determined, and obtaining the historical state matching probability of the historical matching road section of the previous observation point.

Setting P1 (Tn observation point state matching probability) = P2 (Tn-1 observation point state matching probability) × P3 (transition state probability of Tn-1 observation point transferring to Tn observation point) × P4 (estimated matching probability of Tn observation point);

when n =1, the initial state matching probability value P2 of the initial candidate segment of the initial observation point T0, the transition state probability P3 from the initial observation point T0 to the T1 observation point, and the estimated matching probability P4 of the T1 observation point are sequentially substituted into the formula to determine the state matching probability P1 of the T1 observation point. By analogy, the state matching probability P1 of the T2 observation point can be determined, and until the state matching probability of the T4 observation point is determined, the state matching probability of the last observation point is obtained, namely the historical state matching probability of the historical matching road section. It should be noted that, during calculation, the route sections are used as units for calculation, each observation point has at least one candidate route section, and then the state matching probability is naturally the state matching probability value of each candidate route section.

In the embodiment, the initial state matching probability value of each initial candidate road section in the search range from the initial observation point of the vehicle to the target map is obtained, and then the historical state matching probability of the historical matching road section of the previous observation point is determined according to the initial state matching probability value; and sequentially calculating the history matching road sections in the last observation point of the current observation point from the initial observation point as a starting point, wherein adjacent observation points are mutually linked, so that the history state matching probability of the history matching road sections of the last observation point is more accurate.

As shown in fig. 6, in an embodiment, the process of obtaining the initial state matching probability value of each candidate road segment in the initial observation point to target map search range includes:

s501, determining a projection point proportion evaluation value of each initial candidate road section according to proportion information of projection points of the initial observation points in each initial candidate road section.

The proportion information refers to the proportion of the position of the vehicle in the whole road section, so the form of the proportion information can be percentage, proportion and the like, and the embodiment of the application does not limit the proportion. Therefore, the proportion information of the projected points of the positions of the vehicles of the initial observation points in each initial candidate road section refers to the percentage R of the projected points of the positions of the vehicles of the initial observation points in the road section; for example, if a road segment is 10 meters long and the projection point of the vehicle position at the initial observation point is 5 meters in the road segment, the proportion information is 50%. After the proportion information is determined, the proportion information can be directly determined as the projection point proportion evaluation value of any road section i.

In addition, the projection point of the position of the vehicle (in this embodiment, the vehicle position refers to the position of the vehicle at the initial observation point, and will not be described repeatedly) may fall outside the road section, for example, please refer to fig. 7, where P is the position of the vehicle, and P' is the projection point of the vehicle on the road section AB. For this case, the projected point scale evaluation value of each initial candidate link may be determined from the projected line segment information. Specifically, in fig. 7, BP 'is a projection line segment, if P' is in the line segment AB, the length of the projection line segment takes a positive value, otherwise, the length takes a negative value, and the connection line between the projection point and the nearest point on AB when outside the line segment is the projection line segment.

Let projection line segment information be R _i Then, then

Based on the formula, the projection line segment information R of any road segment i in the initial candidate road segments can be determined _i Determining projected line segment information R of the initial candidate links _i Middle maximum value R _max Projecting line segment information R of any road section i _i With a maximum value R _max As the projection information of any road section i

Then

Determines projection information

Then, the projection information can be directly projected

Determining an evaluation value for the ratio of projected points for any section i, i.e.

And S502, determining a distance evaluation value of each initial candidate road section according to the distance information from the initial observation point to each initial candidate road section.

The distance information may be that the distance information from the vehicle to each initial candidate road section is a vertical distance d from the vehicle to each initial candidate road section; for example, if the point where the vehicle is located is P and the link is L, the distance information is the vertical distance from the point P to the link L. Alternatively, the algorithm for obtaining the distance information from the vehicle to each initial candidate link may be any one of algorithms that use an euclidean distance, a chebyshev distance, a manhattan distance, a fretscher distance, a hausdov distance, a hamming distance, an LCS distance, and a DTW distance, which is not limited in this embodiment of the present application.

As an example, there is provided a manner of determining a distance evaluation value for each initial candidate link as follows: if the current position of the vehicle is P and any historical position of the vehicle is Q, QP is the driving direction of the vehicle. A. B is a path point on any initial candidate road section, and the direction of the path point is from A to B; p' is the projection of P on AB; p '= A + (B-A) × t, where t is the ratio of AP' to AB length, and the calculation formulase:Sub>A is

Determining the distance D from the vehicle P to the road section AB according to P' and P _i Wherein D is _i ＝|P-P _i ' where the subscript i is the reference number of any road segment, such as road segment AB.

According to the method, the distance D from the vehicle to each initial candidate road section is calculated _i Then, the minimum distance D of the distances from the vehicle to all road sections is determined _min Distance information of vehicle to road section i

Is calculated by the formula

In the formula, G is a log model adjustable parameter, and is usually 10 according to V2X communication distance limitation.

Determine the vehicleDistance information to road section i

Then, the distance estimation value of any link i is the distance estimation value

S503, determining an included angle evaluation value of each initial candidate road section according to included angle information from the driving direction of the initial observation point to the direction of each initial candidate road section.

The included angle information may reflect a positional relationship between the vehicle and each of the initial candidate road segments. The included angle information refers to an included angle a between the vehicle driving direction and the road section direction. The method for obtaining the information of the included angle between the vehicle and each initial candidate road section may be determined by a neural network model or a geometric algorithm, for example, if the information is determined by the neural network model, a neural network model needs to be trained in advance, and the input of the neural network model is the current position of the vehicle, the driving direction of the vehicle, and the coordinate position of the initial candidate road section; and outputting the information which is the included angle information between the vehicle and each initial candidate road section.

Optionally, one embodiment of obtaining information of an included angle between the vehicle and each initial candidate road segment includes: acquiring a supplementary angle value of the included angle of each initial candidate road section according to the included angle formed by the current position of the vehicle and each initial candidate road section; and determining the ratio of the angle compensation value of the included angle of each initial candidate road section to the maximum angle compensation value in the angle compensation values of the included angles as the included angle information of the vehicle and each initial candidate road section.

The included angle formed by the current position of the vehicle and each initial candidate road section refers to ^ PAB in a triangle formed by a line segment formed by the current position point P of the vehicle and two end points AB of any initial candidate road section with the value of i _i May be H' _i Is represented by, i.e. H' _i Is the angle formed by the vehicle P and the road section AB. According to the included angle, the angle value of the supplementary angle of the included angle needs to be obtained, and then the angle of the supplementary angle of the included angle formed by the vehicle and the vehicle needs to be obtained for each initial candidate road sectionThe value is obtained.

Let H _i To complement the angle formed by the vehicle and the road section AB, then H _i ＝180-H′ _i . Wherein an included angle H 'formed by the vehicle P and the road section AB' _i The calculation can be made based on the angle formed by the road section AB and the due north direction and the angle (heading angle) formed by the vehicle and the due north direction.

Specifically, it is provided

Is road section AB and true north direction

The included angle formed is Veh which is the included angle formed by the vehicle and the due north direction, wherein, the included angle is obtained

The cos value of (c) is:

then the user can either, for example,

that is, if

The difference with < Veh is more than 180 degrees, and an included angle H 'formed by the vehicle P and the road section AB' _i Is 360 degrees minus

Difference with < Veh, otherwise, included angle H formed by vehicle P and road section AB' _i Is composed of

The difference from ≈ Veh.

After the angle-complementing angle value of the included angle of each initial candidate road section is determined, the ratio of the angle-complementing angle value of the included angle of each initial candidate road section to the maximum angle-complementing angle value of all the initial candidate road sections is determined as the information of the included angle between the vehicle and each initial candidate road section.

E.g. H _i Supplementary angle size H of included angle formed by vehicle and initial candidate road section i _max Being the largest angle among the angles in all initial candidate segments,

is the included angle information of the initial candidate road section i, then

Similarly, for any road section i in each initial candidate road section, the included angle information can be calculated in the way, so that the included angle information between the vehicle and each initial candidate road section is obtained.

Determining included angle information of any road section i

Then, the included angle information can be directly used

Determined as an estimate of the angle of any road section i, i.e.

Since the included angle information itself may also reflect the position relationship between the vehicle and each initial candidate link, the accuracy of the matching evaluation value of each initial candidate link may be greatly increased by using the included angle information as one of the factors of the matching evaluation value of each initial candidate link in the embodiment of the present application.

In addition, since the diagonal information may also reflect the distance between the vehicle and each initial candidate link, the diagonal information may also be used as one of the factors of the matching evaluation value of each initial candidate link in the embodiment of the present application, and the accuracy of the matching evaluation value of each initial candidate link may be greatly increased.

For example, the diagonal angle value of each initial candidate road segment may be obtained according to the diagonal angle formed by the current position of the vehicle and each initial candidate road segment; determining the ratio of the diagonal angle value of each initial candidate road section to the maximum diagonal angle value in each diagonal angle value as the diagonal information of the vehicle and each initial candidate road section; the diagonal information of the vehicle and each initial candidate link is determined as a diagonal evaluation value for each initial candidate link.

The opposite angle formed by the current position of the vehicle and each initial candidate road section is equivalent to the opposite angle of a triangular central line formed by points and lines, for example, the current position of the vehicle is point P, any initial candidate road section is two end points a and B of i, then the opposite angle of the road section AB in a triangle formed by the two end points a and B of the road section i and the vehicle point P is ═ APB _i 。

Exemplarily, taking an initial candidate road segment i as an example, acquiring @ APB _i Angle value A of _i Can be determined according to cos ([ angle ] APB) _i ) Is determined wherein

Then

Wherein rad To deg represents arccos (cos (. Unders. APB) _i ) Conversion into corresponding values in angle as a measure unit, namely calculation of arccos (cos (& lt APB) _i ))*180/π。

After the diagonal angle value of each initial candidate road segment is determined, the ratio between the diagonal angle value of each initial candidate road segment and the maximum diagonal angle value in all the initial candidate road segments is determined as the diagonal information of the vehicle and each initial candidate road segment. For example, A _i Magnitude of diagonal angle value of initial candidate link i, A _max For the largest diagonal angle value among all initial candidate segments,

diagonal information representing the initial candidate link i, then

Determining diagonal information of any road section i

Then, the opposite angle information can be directly used

Determined as a diagonal evaluation value of any link i, i.e.

S504, determining an initial state matching probability value of each initial candidate road section according to the projection point proportion evaluation value, the distance evaluation value and the included angle evaluation value of each initial candidate road section.

After the projection point proportion evaluation value, the distance evaluation value and the included angle evaluation value of each initial candidate road section are determined, the initial state matching probability value of each initial candidate road section can be determined according to the projection point proportion evaluation value, the distance evaluation value and the included angle evaluation value of each initial candidate road section.

Let initial state match probability value denote P _cond (d _i ,A _i ,R _i |Seg _i ) I is any initial candidate segment, then P _cond (d _i ,A _i ,R _i |Seg _i )＝E(d _i |Seg _i )+E(H _i |Seg _i )+E(R _i |Seg _i ). Of course, if the diagonal evaluation value E (a) is also obtained as described above _i |Seg _i ) Then E (A) may also be added to the initial state matching probability value _i |Seg _i ) This is not limited in the embodiments of the present application.

In the embodiment of the application, the ratio evaluation value of the projection point of each initial candidate road section, the distance evaluation value of each initial candidate road section and the included angle evaluation value of each initial candidate road section are determined; and then determining the initial state matching probability of each initial candidate road section according to the projection point proportion evaluation value, the distance evaluation value and the included angle evaluation value of each initial candidate road section, and accurately estimating the probability value that each initial candidate road section is possibly a target matching road section by evaluating the initial state matching probability of each initial candidate road section, so that the finally determined initial state matching probability of each initial candidate road section is more accurate.

As shown in fig. 8, in one embodiment, there is also provided a map matching method, including:

s1, acquiring distribution information of the distance between the position of the vehicle and the last observation point, and regularizing a precision factor of the navigation equipment.

And S2, determining the evaluation matching probability of each candidate road section according to the distribution information of the distance between the vehicle position and the last observation point and the navigation equipment precision factor after regularization processing.

And S3, acquiring the map network topological relation between the history matching road section of the previous observation point and each candidate road section.

S4, for any candidate road section, if the map network topological relation is that the candidate road section is the same road section of the history matching road section, determining that the transition probability is a preset first value; and if the map network topological relation is that the candidate road section is the next road section of the history matching road section, determining that the transition probability is a preset second value.

S5, determining a projection point proportion evaluation value of each initial candidate road section according to proportion information of projection points of the initial observation points in each initial candidate road section; determining a distance evaluation value of each initial candidate road section according to the distance information from the initial observation point to each initial candidate road section; and determining an included angle evaluation value of each initial candidate road section according to the included angle information from the driving direction of the initial observation point to the direction of each initial candidate road section.

And S6, determining the initial state matching probability value of each initial candidate road section according to the projection point proportion evaluation value, the distance evaluation value and the included angle evaluation value of each initial candidate road section.

And S7, taking the state matching probability value of each candidate road section of the initial observation point as an initial value, sequentially determining the historical state matching probability of the historical matching road section of the next observation point according to the observation point sequence of the driving path of the vehicle until the previous observation point of the vehicle position is determined, and obtaining the historical state matching probability of the historical matching road section of the previous observation point.

And S8, determining the state matching probability of each candidate road section and the vehicle position according to the evaluation matching probability of each candidate road section, the state transition probability from the history matching road section of the previous observation point to each candidate road section and the history state matching probability of the history matching road section of the previous observation point.

And S9, determining the candidate road section corresponding to the maximum state matching probability value and a sequence road section formed by the historical track of the vehicle as a target matching road section of the driving path of the vehicle in the map.

In this embodiment, the implementation principle and technical effect of each step are similar to those of the above method embodiment, and are not described herein again.

It should be understood that, although the steps in the flowcharts of the above embodiments are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.

In one embodiment, as shown in fig. 9, there is provided a map matching apparatus, including: the device comprises an acquisition module 10, a determination module 11 and a matching module 12, wherein:

the acquisition module 10 is configured to acquire an estimated matching probability of the vehicle position and at least one candidate road segment in a target map search range according to a distance between the vehicle position and a last observation point of the vehicle and a precision factor of the navigation device;

the determining module 11 is configured to determine the state matching probability of each candidate road segment and the vehicle position according to the evaluation matching probability of each candidate road segment, the state transition probability from the history matching road segment of the previous observation point to each candidate road segment, and the history state matching probability of the history matching road segment of the previous observation point;

and the matching module 12 is used for determining a target matching road section of the driving path of the vehicle in the map according to the state matching probability of each candidate road section and the position of the vehicle.

In one embodiment, the obtaining module 10 includes:

the processing unit is used for acquiring the distribution information of the distance between the vehicle position and the last observation point and regularizing the precision factor of the navigation equipment;

and the determining unit is used for determining the evaluation matching probability of each candidate road section according to the distribution information of the distance between the vehicle position and the last observation point and the navigation equipment precision factor after the regularization processing.

In one embodiment, the apparatus further comprises:

the relation determining module is used for acquiring a map network topological relation between the history matching road section of the previous observation point and each candidate road section;

and the probability determining module is used for determining the state transition probability from the history matching road section of the previous observation point to each candidate road section according to the topological relation of the map network.

In an embodiment, the probability determining module is specifically configured to: for any candidate segment:

In one embodiment, the apparatus further comprises:

the initial probability acquisition module is used for acquiring initial state matching probability values of initial candidate road sections from an initial observation point of a vehicle to a target map search range;

and the matching probability determining module is used for determining the historical state matching probability of the historical matching road section of the previous observation point according to the initial state matching probability value.

In one embodiment, the initial probability obtaining module includes:

the first evaluation value unit is used for determining the projection point proportion evaluation value of each initial candidate road section according to the proportion information of the projection point of the initial observation point in each initial candidate road section;

the second evaluation value unit is used for determining the distance evaluation value of each initial candidate road section according to the distance information from the initial observation point to each initial candidate road section;

the third evaluation value unit is used for determining the evaluation value of the included angle of each initial candidate road section according to the information of the included angle from the driving direction of the initial observation point to the direction of each initial candidate road section;

and the initial probability determining unit is used for determining the initial state matching probability value of each initial candidate road section according to the projection point proportion evaluation value, the distance evaluation value and the included angle evaluation value of each initial candidate road section.

In an embodiment, the matching probability determination module is specifically configured to sequentially determine the historical state matching probability of the historical matching road segment of the next observation point according to the observation point sequence of the driving path of the vehicle by using the state matching probability value of each candidate road segment of the initial observation point as an initial value until the previous observation point of the vehicle position is determined, and obtain the historical state matching probability of the historical matching road segment of the previous observation point.

In one embodiment, the matching module 12 is specifically configured to determine the candidate link corresponding to the maximum state matching probability value and a sequence link formed by the historical track of the vehicle as a target matching link of the driving path of the vehicle in the map.

For the specific definition of the map matching device, reference may be made to the above definition of the map matching method, which is not described herein again. The various modules in the map matching apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for communicating with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a map matching method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:

The implementation principle and technical effect of the computer device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, performs the steps of:

The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A map matching method, the method comprising:

acquiring the evaluation matching probability of the vehicle position and at least one candidate road section in the target map searching range according to the distance between the vehicle position and the last observation point of the vehicle and the navigation equipment precision factor;

and determining a target matching road section of the driving path of the vehicle in a map according to the state matching probability of each candidate road section and the position of the vehicle.

2. The method according to claim 1, wherein the obtaining an estimated matching probability between the vehicle position and at least one candidate road segment in a target map search range according to the distance between the vehicle position and a last observation point and a navigation device precision factor comprises:

acquiring distribution information of the distance between the vehicle position and the last observation point, and regularizing the precision factor of the navigation equipment;

3. The method according to claim 1 or 2, characterized in that the method further comprises:

obtaining a map network topological relation between the history matching road section of the last observation point and each candidate road section;

4. The method of claim 3, wherein determining the state transition probability of the historically matched segment of the previous observation point to each of the candidate segments according to the map network topology relationship comprises:

for any candidate segment:

5. The method according to claim 1 or 2, characterized in that the method further comprises:

acquiring initial state matching probability values from an initial observation point of a vehicle to each initial candidate road section in the target map searching range;

6. The method of claim 5, wherein the obtaining initial state matching probability values of the initial observation point to the candidate road segments in the target map search range comprises:

7. The method of claim 5, wherein the determining the historical state matching probability of the historical matching segment of the previous observation point according to the initial state matching probability value comprises:

and taking the state matching probability value of each candidate road section of the initial observation point as an initial value, and sequentially determining the historical state matching probability of the historical matching road section of the next observation point according to the observation point sequence of the driving path of the vehicle until the previous observation point of the vehicle position is determined, so as to obtain the historical state matching probability of the historical matching road section of the previous observation point.

8. The method according to claim 1 or 2, wherein the determining of the target matching section of the driving path of the vehicle in the map according to the state matching probability of each candidate section and the vehicle position comprises:

and determining the candidate road section corresponding to the maximum state matching probability value and a sequence road section formed by the historical track of the vehicle as a target matching road section of the driving path of the vehicle in a map.

9. A map matching apparatus, characterized in that the apparatus comprises:

the acquisition module is used for acquiring the evaluation matching probability of the vehicle position and at least one candidate road section in a target map search range according to the distance between the vehicle position and the last observation point of the vehicle and the navigation equipment precision factor;

and the matching module is used for determining a target matching road section of the driving path of the vehicle in a map according to the state matching probability of each candidate road section and the position of the vehicle.

10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 8 are implemented by the processor when executing the computer program.

11. A storage medium on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.