CN116977943A - Road element identification method, device, electronic equipment and computer storage medium - Google Patents
Road element identification method, device, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN116977943A CN116977943A CN202211713760.8A CN202211713760A CN116977943A CN 116977943 A CN116977943 A CN 116977943A CN 202211713760 A CN202211713760 A CN 202211713760A CN 116977943 A CN116977943 A CN 116977943A
- Authority
- CN
- China
- Prior art keywords
- road
- point
- track
- vehicle
- data
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 230000006399 behavior Effects 0.000 claims description 38
- 230000001133 acceleration Effects 0.000 claims description 34
- 230000008859 change Effects 0.000 claims description 29
- 238000012876 topography Methods 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 14
- 230000028838 turning behavior Effects 0.000 claims description 13
- 230000001174 ascending effect Effects 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 12
- 230000000670 limiting effect Effects 0.000 claims description 10
- 230000003247 decreasing effect Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 14
- 230000008569 process Effects 0.000 description 20
- 238000001514 detection method Methods 0.000 description 18
- 230000006870 function Effects 0.000 description 12
- 238000009499 grossing Methods 0.000 description 10
- 230000000007 visual effect Effects 0.000 description 10
- 238000013473 artificial intelligence Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the application discloses a method, a device, electronic equipment and a computer storage medium for identifying road elements, wherein the method comprises the following steps: acquiring track data generated when a vehicle runs on a road; determining candidate positioning points with road elements in the road according to the track data; acquiring the position of a candidate positioning point corresponding to each piece of track data in a road and the attribute of the road; calculating the target score of the road according to the position of the candidate positioning point corresponding to each piece of track data in the road and combining the attribute of each piece of track data and the attribute of the road; and according to the size of the target score, if the target score is larger than a preset threshold value, determining that the road has road elements and the target position of the road elements in the road. The application can rapidly and accurately identify the information of the road elements in a low-cost and low-calculation resource consumption mode, and can be applied to the fields including but not limited to maps, navigation, intelligent transportation, automatic driving and the like.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and apparatus for identifying a road element, a computer device, and a readable storage medium.
Background
The information of the road elements is important information of the road, such as the positions and the number of electronic eyes and traffic signs, and the like, the information of the road elements can be acquired by two modes of manual acquisition and visual equipment acquisition at present, and then the information of the road elements is provided for electronic map developers or travel crowds, so that traffic safety and travel convenience are improved.
However, manual collection requires more manpower, and the collection process is time-consuming and inefficient. The input cost of vision equipment collection is too high, still can receive the influence of factors such as scene, weather condition are shot on the spot, also need staff to intervene and calibrate, detect work such as after the collection is accomplished for the holistic accuracy of collection information and efficiency are not high.
Disclosure of Invention
The embodiment of the application provides a method, a device, a system, electronic equipment and a computer storage medium for identifying road elements, which can quickly and accurately identify the information of the road elements under the conditions of low cost and low calculation resource consumption.
An embodiment of the present application provides a method for identifying a road element, where the method includes:
acquiring track data generated when a vehicle runs on a road, wherein the track data at least comprises the speed of the vehicle, and the track data is acquired by continuously positioning the vehicle;
Determining candidate positioning points of a road element in the road according to the track data, wherein the candidate positioning points represent the settable positions of the road element in the road, and each candidate positioning point corresponds to each track data;
acquiring the position of a candidate positioning point corresponding to each piece of track data in the road and the attribute of the road, wherein the attribute of the road is related to the topography of the road;
calculating a target score of the road according to the position of the candidate positioning point corresponding to each piece of track data in the road and combining the track data with the attribute of the road, wherein the target score represents the probability that the road element exists in the road in a true mode;
and according to the size of the target score, if the target score is larger than a preset threshold value, determining that the road has the road element and the target position of the road element in the road.
Accordingly, a second aspect of an embodiment of the present application provides an apparatus for identifying a road element, the apparatus including:
a track data acquisition unit configured to acquire track data generated when a vehicle travels on a road, wherein the track data includes at least a speed of the vehicle, the track data being acquired by continuously positioning the vehicle;
A candidate anchor point determining unit configured to determine, according to the track data, candidate anchor points where a road element exists in the road, wherein the candidate anchor points characterize positions where the road element can be set in the road, and each of the candidate anchor points corresponds to each of the track data;
a road data obtaining unit, configured to obtain a position of a candidate positioning point corresponding to each piece of track data in the road, and an attribute of the road, where the attribute of the road is related to a topography of the road;
a target score calculating unit, configured to calculate a target score of the road according to the position of the candidate positioning point corresponding to each piece of track data in the road, in combination with each piece of track data and the attribute of the road, where the target score represents the probability that the road element actually exists in the road;
and the road element positioning unit is used for determining that the road has the road element and the target position of the road element in the road according to the target score if the target score is larger than a preset threshold value.
Optionally, the target score calculating unit further includes:
An initial score calculation subunit, configured to calculate an initial score of the road according to the position of the candidate positioning point in the road, where the initial score characterizes a probability that the road element actually exists in the road;
and the target score calculating subunit is used for calculating the target score of the road according to each piece of track data and each initial score corresponding to each piece of track data and the attribute of the road, wherein the accuracy of the target score is higher than that of the initial score.
Optionally, the trajectory data includes a plurality of trajectory points of the vehicle at different moments in time, and the initial score calculating subunit includes:
a first point score obtaining subunit, configured to obtain a first point score of the candidate positioning point;
a first point score generating subunit, configured to calculate a second point score of each track point according to the first point score, and generate a point score set corresponding to the track data;
the matching result obtaining subunit is used for obtaining the matching result of each track point and the road where the track point is located;
and the initial score determining subunit is used for determining the initial score of the road from the point score set according to the matching result, wherein the initial score is the maximum value of the point scores of the plurality of track points corresponding to the road.
Optionally, the first point score generating subunit is further specifically configured to:
acquiring a distance interval or a time interval between each track point and the candidate positioning point;
and according to the sequence of the distance interval or the time interval from small to large, taking the first point score as a reference, sequentially matching the second point scores which are gradually decreased one by one for each track point.
Optionally, the target score calculating unit includes:
a target score zeroing subunit, configured to determine the target score as zero if the speed of the vehicle in the track data meets a first preset condition, or if the attribute of the road meets a second preset condition;
and the target score calculating subunit is used for calculating the average value after summing each initial score if the target score is not zero, so as to obtain the target score.
Optionally, the target score zeroing subunit is further specifically configured to:
acquiring a first speed of each vehicle running on the road;
sorting each first speed according to the first speed, and screening out target speeds in a target sorting interval from the sorted first speeds;
And if the ratio between the target speed and the limiting speed of the road meets a preset value interval, determining the target score as zero.
Optionally, the target score zeroing subunit is further specifically configured to:
acquiring preset road topography of deceleration behaviors of a plurality of vehicles;
and if the road has the preset road topography or the road is positioned in the preset range of the preset road topography, determining the target score as zero.
Optionally, the apparatus further comprises:
a data calculation unit for calculating corner data and uphill data of the vehicle according to the trajectory data;
and the initial score zeroing unit is used for determining the initial score to be zero if the turning behavior of the vehicle is met based on the corner data or the uphill behavior of the vehicle is met by the uphill data.
Optionally, the trajectory data includes a plurality of trajectory points of the vehicle at different moments, and the data calculation unit includes:
the corner value calculating subunit is used for obtaining the corner value corresponding to each track point of the vehicle;
and the front-rear corner value calculating subunit is used for calculating a front corner value and a rear corner value of the vehicle at each track point according to each corner value, wherein the front corner value is the difference between the corner value of the vehicle at the current track point and the corner value of the track point which is positioned in front of the current track point and is preset in number intervals, and the rear corner value is the difference between the corner value of the current track point and the corner value of the track point which is positioned behind the current track point and is preset in number intervals.
And the turning behavior determination subunit is used for determining that the turning behavior of the vehicle exists if the track points of which the front turning angle value and the rear turning angle value are both larger than a first preset threshold value exist.
Optionally, the track data includes a plurality of track points of the vehicle at different moments, and a height value corresponding to each track point, and the data calculating unit includes:
a height change value obtaining subunit, configured to obtain, according to the height value of each track point, a height change value of the height value of the current track point and the height value of the last track point;
a track point group determining subunit, configured to determine at least one group of first track points and second track points from each track point according to the altitude change value, where the first track points are starting points where the vehicle has a suspected uphill behavior, and the second track points are ending points where the vehicle has the suspected uphill behavior;
and if the difference value between the height change value of the first track point and the height change value of the second track point is larger than a second preset threshold value, determining that the vehicle has the ascending behavior.
Optionally, the trajectory data includes a plurality of trajectory points of the vehicle at different moments, and a speed corresponding to each of the trajectory points, and the candidate positioning point determining unit includes:
The acceleration determining subunit is used for determining the acceleration of each track point according to the track points and the corresponding speed of each track point;
a deceleration point determining subunit, configured to determine, according to the acceleration of each track point, a deceleration start point indicating that the vehicle starts decelerating, and a deceleration end point indicating that the vehicle ends decelerating, where the deceleration start points and the deceleration end points are in one-to-one correspondence;
and the candidate positioning point determining subunit is used for calculating a speed difference between the speed of the deceleration starting point and the speed of the deceleration ending point, and determining the deceleration ending point as the candidate positioning point if the speed difference is larger than a second preset threshold value.
Optionally, the apparatus further comprises:
an initial track data acquisition unit, configured to acquire initial track data, where the initial track data is vehicle running data of the vehicle at each fixed interval unit;
and the initial track data processing unit is used for processing the initial track data to obtain track data meeting the track screening conditions.
An electronic device provided in a third aspect of an embodiment of the present application includes:
A processor and a storage medium;
the processor is used for realizing each instruction;
the storage medium is for storing a plurality of instructions for loading and executing by the processor the road element identification method described above.
The fourth aspect of the embodiment of the present application further provides a computer readable storage medium, where a plurality of instructions are stored, where the instructions are adapted to be loaded by a processor to perform the steps in any of the road element identification methods provided by the embodiments of the present application.
The fifth aspect of the embodiments of the present application further provides a computer program product, which includes a computer program or instructions, which when executed by a processor, implement the method for identifying any road element provided by the embodiments of the present application.
Therefore, the application obtains the track data of the vehicle by acquiring the historical driving data and the real-time driving data generated when the vehicle runs on the road, and identifies and detects the information such as the position, the number and the like of the road elements existing on different roads according to the track data. The whole road element identification and detection process does not need manual intervention and is not influenced by visual factors such as road environment, weather conditions and the like, so that the information of the road elements in different roads can be rapidly and accurately obtained on the premise of not needing visual equipment and manual detection and acquisition, the accuracy and the efficiency of the road element identification and detection are obviously improved, and the cost of the road element identification and detection can be reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1a is an application scenario schematic diagram of a data classification system according to an embodiment of the present application;
fig. 1b is a flow chart of a method for identifying road elements according to an embodiment of the present application;
fig. 1c is another flow chart of a method for identifying road elements according to an embodiment of the present application;
fig. 1d is another flow chart of the method for identifying road elements according to the embodiment of the present application;
FIG. 2a is a schematic diagram of display trajectory data according to an embodiment of the present application;
FIG. 2b is a schematic illustration of calculating a first point score and a second point score provided by an embodiment of the present application;
fig. 3 is a schematic structural diagram of a road element identification device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which 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 those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
Artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use the knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision.
Computer Vision (CV) is a science of studying how to "look" a machine, and more specifically, to replace a human eye with a camera and a Computer to perform machine Vision such as recognition and measurement on a target, and further perform graphic processing to make the Computer process an image more suitable for human eye observation or transmission to an instrument for detection. As a scientific discipline, computer vision research-related theory and technology has attempted to build artificial intelligence systems that can acquire information from images or multidimensional data. Computer vision techniques typically include image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content/behavior recognition, three-dimensional object reconstruction, 3D techniques, virtual reality, augmented reality, synchronous positioning, and map construction, among others, as well as common biometric recognition techniques such as face recognition, fingerprint recognition, and others.
Machine Learning (ML) is a multi-domain interdisciplinary, involving multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, etc. It is specially studied how a computer simulates or implements learning behavior of a human to acquire new knowledge or skills, and reorganizes existing knowledge structures to continuously improve own performance. Machine learning is the core of artificial intelligence, a fundamental approach to letting computers have intelligence, which is applied throughout various areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, confidence networks, reinforcement learning, transfer learning, induction learning, teaching learning, and the like.
The method for identifying road elements of the present application is related to techniques in the fields of machine learning and computer vision of artificial intelligence, for example, vehicle images or roads may be detected by a convolutional neural network model to obtain trajectory data of a vehicle or road attributes of the road, etc., which will be specifically discussed in the embodiments.
The road element identification method of the application can be integrated in a road element identification system, the road element identification system can be integrated in one or more computer devices, the computer devices can comprise terminals or servers, etc., wherein the servers can be independent physical servers, can be server clusters or distributed systems formed by a plurality of physical servers, and can be cloud servers for providing cloud computing services. The terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a smart home, a wearable electronic device, a vehicle-mounted computer, a vehicle-mounted smart terminal, etc. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the present application is not limited herein.
Referring to fig. 1a, the road element identification system may comprise a road element identification device, wherein the road element identification device may acquire track data generated when a vehicle travels on a road, wherein the track data at least comprises a speed of the vehicle, and the track data is acquired by continuously positioning the vehicle; determining candidate positioning points of a road element in the road according to the track data, wherein the candidate positioning points represent the settable positions of the road element in the road, and each candidate positioning point corresponds to each track data; acquiring the position of a candidate positioning point corresponding to each piece of track data in the road and the attribute of the road, wherein the attribute of the road is related to the topography of the road; calculating a target score of the road according to the position of the candidate positioning point corresponding to each piece of track data in the road and combining the track data with the attribute of the road, wherein the target score represents the probability that the road element exists in the road in a true mode; and according to the size of the target score, if the target score is larger than a preset threshold value, determining that the road has the road element and the target position of the road element in the road.
It should be noted that, the schematic view of the scene of the road element recognition system shown in fig. 1a is only an example, and the road element recognition system and the scene described in the embodiments of the present application are for more clearly describing the technical solution of the embodiments of the present application, and do not constitute a limitation on the technical solution provided by the embodiments of the present application, and as a person of ordinary skill in the art can know that, along with the evolution of the road element recognition device and the appearance of the new service scene, the technical solution provided by the embodiments of the present application is equally applicable to similar technical problems.
The road element of the present application generally refers to an electronic eye having a speed limiting function, or a traffic sign, such as a speed limiting electronic eye, a speed limiting traffic sign, or the like. The method of the application is used for obtaining the information of the road elements, such as the position and the number of the speed-limiting electronic eyes, so as to remind the user and the vehicle to reduce the speed in advance in the navigation and road-finding processes, thereby guaranteeing the travel safety and the smoothness of the user.
The following will describe in detail. The following description of the embodiments is not intended to limit the preferred embodiments.
Referring to fig. 1b and fig. 1d, in this embodiment, a method for identifying a road element is provided and applied to a data sorting end, as shown in fig. 1b, a specific flow of the method for identifying a road element may be as follows:
Step 101, track data generated when a vehicle runs on a road is acquired.
Wherein the trajectory data includes at least a speed of the vehicle, the trajectory data being obtained by continuously locating the vehicle. For example, trajectory data may include, but is not limited to, speed, trajectory, time of day, duration, location, mileage, latitude and longitude, altitude, corner value, etc. of the vehicle. In some embodiments, the trajectory data of the vehicle may be acquired by a device or application having a positioning function. The trajectory data may be acquired, for example, by a vehicle recorder, an in-vehicle device, a navigation device, a map application app, etc.
In some embodiments, the trajectory data may include a plurality of trajectory points of the vehicle at different times, and a corresponding speed for each trajectory point. Referring to fig. 2a, fig. 2a is a schematic diagram showing track data according to an embodiment of the present application. As shown in fig. 2a, after the track data of the vehicle is acquired, the track of the vehicle, and a plurality of track points constituting the track, may be acquired from the track data. The track may be a path traveled by the vehicle, and the track point may be a plurality of coordinate points constituting the track.
In some embodiments, the track point of the vehicle may be determined in units of a fixed time interval, for example, starting from a position where the vehicle starts traveling, and the coordinate point corresponding to each time the vehicle travels for 1 second or 2 seconds is the track point of the vehicle. In some embodiments, the track point of the vehicle may be determined in units of a fixed distance interval, for example, the track point of the vehicle may be determined from a position where the vehicle starts traveling, and the coordinate point corresponding to each time the vehicle travels 5 meters or 10 meters. The present embodiment is not limited as to the determination manner of the track point.
In some embodiments, each item of track data may be data generated by the vehicle at each track point. As shown in fig. 2a, track data of a track point 1 where a vehicle is located at a time of 15 hours, 00 minutes and 30 seconds are displayed, and the vehicle travels at a speed of 70km/h, a mileage of 500m, a height of 10m, a rotation angle value of 360 degrees, longitude and latitude of 104.06 degrees, and north latitude of 30.67 degrees.
Step 102, determining candidate positioning points with road elements in the road according to the track data,
wherein the candidate anchor points characterize positions in the road where road elements can be set, each candidate anchor point corresponding to the each piece of trajectory data. In some embodiments, candidate anchor points for road elements in the corresponding road may be determined from the trajectory data. The candidate locating point refers to a candidate position in the road where a road element may exist. Specifically, the acceleration of the vehicle at each track point may be calculated according to the speed of the vehicle in the track data, and further at least one candidate positioning point may be determined from a plurality of track points according to the change condition of the acceleration.
Optionally, step 102 may include:
determining the acceleration of each track point according to the track points and the corresponding speed of each track point;
according to the acceleration of each track point, determining a deceleration starting point for indicating the vehicle to start decelerating and a deceleration ending point for indicating the vehicle to end decelerating, wherein the deceleration starting points and the deceleration ending points are in one-to-one correspondence;
and calculating a speed difference between the speed of the deceleration starting point and the speed of the deceleration ending point, and determining the deceleration ending point as the candidate positioning point if the speed difference is larger than a second preset threshold value.
In some embodiments, to improve the accuracy of the acceleration calculation, the speed of the vehicle at each track point may be smoothed first. The formula of the speed smoothing process can be expressed as:
where v (t) is the speed of the vehicle at the current time t, v (t-1) is the speed of the vehicle at the time t-1 immediately before the current time, v (t+1) is the speed of the vehicle at the time t+1 immediately after the current time, and v' () is the speed of the current time t after the smoothing process.
It will be appreciated that the speed of the vehicle at each locus point is smoothed by calculating an average value of the sum of speeds at times adjacent to and before the current time. After the speed is smoothed, the speed of each track point can be more reasonable, and the acceleration of the vehicle can be calculated more conveniently according to the smoothed speed data.
The calculation formula of the acceleration of the vehicle at each track point can be expressed as follows:
where a (t) is the acceleration of the vehicle at the current time t, v' (t-1) is the speed of the vehicle at the previous time after the smoothing process, and Δt is the time difference between the current time and the previous time.
It will be appreciated that after the acceleration of the vehicle at each locus point is calculated by the above formula, the change in the value of each acceleration can be observed to determine the acceleration of the vehicle while driving. For example, when the acceleration is greater than zero, acceleration is smaller than zero, acceleration is decreasing, acceleration is always greater than zero, a change value is gradually decreasing, acceleration is slowing, acceleration is always greater than zero, a change value is gradually increasing, acceleration is increasing, and the like.
It will be appreciated that in a typical traffic scenario, when a vehicle passes over a road where the road element of the present application is present, it undergoes a deceleration phase to smoothly pass over the road element segment due to the speed limiting properties of the road element, and correspondingly, after passing over the road element, it undergoes an acceleration phase to reach the previous travel speed. Therefore, at least one group of deceleration starting points indicating that the vehicle starts decelerating and deceleration ending points indicating that the vehicle ends decelerating can be screened out by changing the acceleration of the vehicle at each track point.
Wherein the initial point of deceleration is acceleration of 0m/s or more 2 Transition to less than 0m/s 2 For example, track point 1 has an acceleration of 1m/s 2 Acceleration of the track point 2 is-1 m/s 2 The trajectory point 2 can be determined as a deceleration start point. Wherein the deceleration end point is that the acceleration is less than or equal to 0m/s 2 Transition to greater than 0m/s 2 The acceleration of the track point 3 is-1 m/s 2 Acceleration of the locus point 4 is 1m/s 2 The locus point 4 can be determined as a deceleration termination point.
In some embodiments, a speed difference between the speed of the deceleration start point and the speed of the deceleration end point may be calculated, and if the speed difference is greater than a second preset threshold, the deceleration end point is determined as a candidate anchor point. It will be appreciated that although the start and end points of deceleration indicate that the vehicle has undergone a course of travel that begins to decelerate and ends to decelerate, there is also a small magnitude deceleration behavior in which the user drives the vehicle unaffected by the road element, for example a small magnitude deceleration behavior in which the speed of the vehicle is decelerated from 70km/h to 69km/h, so that the above deceleration behavior with a lesser degree of deceleration may not be the result of the speed limit prompting function of the road element.
From the above, after the deceleration starting point and the deceleration ending point are determined, the speed difference between the speeds corresponding to the two track points may be further calculated, for example, when the speed difference is greater than a second preset threshold, for example, the second preset threshold is 3km/h, 4km/h, or the like, it may be reflected that the deceleration behavior from the deceleration starting point to the deceleration ending point is a large-scale deceleration behavior with a large deceleration degree, and then the position corresponding to the deceleration ending point is determined as a candidate positioning point where a road element may exist, so that reliability and accuracy of determining the candidate positioning point may be improved.
In some embodiments, instead of determining the candidate positioning points in the above manner, the starting track point and the ending track point of the deceleration behavior of the vehicle may be determined by combining track data with a related machine learning algorithm, a simulated annealing algorithm, and the like, so as to further determine the candidate positioning points, and the determination algorithm of the candidate positioning points is not limited in this embodiment.
Optionally, before step 102, the present application may further include:
acquiring initial track data, wherein the initial track data is vehicle running data of the vehicle at each fixed interval unit;
and processing the initial track data to obtain track data meeting the track screening conditions.
The initial trajectory may be vehicle travel data of the vehicle at each fixed interval unit. Such as raw untreated travel data of the vehicle at each fixed time interval or each fixed distance interval.
In some embodiments, the initial trajectory data may be screened by trajectory screening conditions. In some embodiments, the trajectory filtering condition may include filtering out trajectory points having a speed greater than a certain threshold, for example, trajectory points having a speed greater than 10km/h may be filtered out. In some embodiments, the track screening condition may include screening track data having a number of out-track points greater than a threshold, e.g., track data having a number of out-track points greater than 100 may be screened.
In some embodiments, to ensure the continuity of the distribution of the track points in the track data, two track points with larger interval units may be cut, and the two track points may be respectively cut into different track data. For example, two trajectory points with a time interval of more than 3 seconds or a distance interval of more than 30 meters may be cut into different trajectory data.
In some embodiments, in order to improve the efficiency of calculating the road target score subsequently, the road with the length greater than 100 meters may be cut into a plurality of sections of roads with the length less than 100 meters, the cutting mode may be set according to the preset length, the intersection position, the preset position or other road cutting requirements, and the cutting mode of the longer road is not limited in this embodiment.
From the above, the application can effectively collect the running data of the vehicle at each track point through the track data of the running of the vehicle, and can rapidly and accurately predict the candidate positioning points based on the track data to represent the possible positions and the possible quantity of the road elements, so that the probability, the positions and the possible quantity of the road elements actually existing on the road can be further calculated according to the candidate positioning points without the help of visual equipment and manual collection and without being influenced by the field environment and weather conditions.
And 102, calculating a target score of the road according to the position of the candidate positioning point corresponding to each piece of track data in the road and combining the track data and the attribute of the road.
Optionally, step 102 may include:
calculating an initial score of the road according to the position of the candidate locating point in the road;
and calculating a target score of the road according to the track data and the initial score corresponding to the track data and the attribute of the road.
The target score and the initial score can represent the probability of the real existence of the road element in the road, and the accuracy of the target score is higher than that of the initial score. Wherein the initial score may be represented by a number, e.g., 1, 2, 3, etc. The value of the initial score may be proportional to the probability that a road element is actually present in the road, e.g., a road with an initial score of 5 has a greater probability that a road with an initial score of 4 is present.
Optionally, before the step of calculating the initial score of the road according to the position of the candidate positioning point in the road, the present application may further include:
Calculating the corner data and the uphill data of the vehicle according to the track data;
and if the turning behavior of the vehicle is met based on the rotation angle data or the uphill behavior of the vehicle is met by the uphill data, determining the initial score as zero.
It will be appreciated that vehicles typically slow down through a turn or uphill road segment as they travel. Therefore, in the above case, even if there is no road element that limits the vehicle speed on the road, the vehicle has a deceleration behavior such that the initial score is determined to be zero when it is determined that there is no road element corresponding to the road where the vehicle has a cornering behavior and an uphill behavior.
Optionally, the step of calculating the rotation angle data of the vehicle according to the trajectory data includes:
acquiring a corner value corresponding to each track point of the vehicle;
calculating a front corner value and a rear corner value of the vehicle at each track point according to each corner value, wherein the front corner value is the difference between the corner value of the vehicle at the current track point and the corner value of the track point which is positioned in front of the current track point and is preset in number, and the rear corner value is the difference between the corner value of the current track point and the corner value of the track point which is positioned behind the current track point and is preset in number;
And if the track points with the front rotation angle value and the rear rotation angle value which are both larger than the first preset threshold value exist, determining that the turning behavior of the vehicle exists.
Wherein the trajectory data may comprise a plurality of trajectory points of the vehicle at different moments in time. It will be appreciated that the vehicle may have a corresponding angle of rotation at each locus, which may be 0 ° or 360 ° when the vehicle is travelling in a straight line, and may vary, for example, by 1 °, 2 °, 359 ° when the vehicle is turning.
In some embodiments, the rotation angle value of each track point may be smoothed by referring to a method of smoothing the speed, and the specific formula is as follows:
wherein c (t) is the rotation angle value of the vehicle at the current time t, c (t-1) is the rotation angle value of the vehicle at the time t-1 which is the last time of the current time, c (t+1) is the rotation angle value of the vehicle at the time t+1 which is the next time of the current time, and c' () is the rotation angle value of the current time t after the smoothing treatment.
It can be seen that the rotation angle value of the vehicle at each track point is smoothed by calculating an average value of the sum of rotation angle values at the times adjacent to the current time and before and after the current time. After the corner value is subjected to smoothing treatment, the corner value of each track point can be more reasonable, and whether the vehicle turns or not can be calculated more conveniently according to the smoothed corner value data.
In some embodiments, the front-facing angle value and the rear-facing angle value of the vehicle may be calculated by the following formulas:
c f (t)=|c′(t)-c′(t-x)|
c b ()=|c′(t)-′(t+x)|
wherein c f (t) is the front rotation angle value of the current time t, c b () For the post-rotation angle value of the current time t, x is a preset number of intervals, for example, x is 5, t-x is a time spaced forward by 5 from the current time, and t+x is a time spaced backward by 5 from the current time.
It can be appreciated that in the driving process of the vehicle, the vehicle may have normal smaller rotation angle value variation when no turning behavior exists due to factors such as driving habits of users, flatness of the road surface and the like. Therefore, the change of the corner value of the vehicle at a period of time before and after the current time can be judged through the formula, if the front corner value and the rear corner value are both changed by more than a first preset threshold value, the vehicle is indicated to have a great probability of actually having turning behaviors in a period of time before and after, for example, the first preset threshold value can be 10 degrees, 20 degrees, 30 degrees and the like, the value of x is 5, the first preset threshold value is 30 degrees, the turning behaviors of the vehicle with the corner value more than 30 degrees in 5 seconds before and after the current time are indicated, and the initial score of the road corresponding to the track data can be further judged to be zero.
Optionally, the step of "track data, calculating the uphill data of the vehicle" may include:
according to the height value of each track point, obtaining the height change value of the height value of the current track point and the height value of the last track point;
determining at least one group of first track points and second track points from each track point according to the height change value, wherein the first track points are starting points of suspected ascending behaviors of the vehicle, and the second track points are ending points of the suspected ascending behaviors of the vehicle;
and if the difference value between the height change value of the first track point and the height change value of the second track point is larger than a second preset threshold value, determining that the vehicle has the ascending behavior.
The track data may include a plurality of track points of the vehicle at different moments, and a height value corresponding to each track point.
In some embodiments, the height value of each track point may be smoothed by referring to the manner of smoothing the speed and the rotation angle values, and the specific formula is as follows:
where h (t) is the height value of the vehicle at the current time t, h (t-1) is the height value of the vehicle at the time t-1 immediately before the current time, h (+1) is the height value of the vehicle at the time t+1 immediately after the current time, and h' () is the height value of the current time t after the smoothing process.
It can be seen that the height value of the vehicle at each track point is smoothed by calculating an average value of the sum of the height values at the times adjacent to the current time and before and after the current time. After the height value is smoothed, the height value of each track point can be more reasonable, and whether the vehicle has an ascending behavior can be calculated more conveniently according to the smoothed height value data.
The above algorithm for smoothing the speed, the rotation angle value, and the altitude value of the vehicle is not limited to the calculation of the average value, but may be performed by, for example, calculating the median value, filtering the maximum and minimum values, and filtering the algorithm to smooth the above data, which is not limited to this embodiment.
In some embodiments, the altitude change value of the vehicle at the current time may be calculated by the following formula:
△h′(t)=h′(t)-h′(t-1)
wherein h' (+1) is the height value after smoothing processing at the previous time of the current time.
Further, after calculating the height change value of each track point through the above formula, the height change values of all track points may be traversed, and at least one set of start points, such as a first track point, suspected of ascending behavior and end points, such as a second track point, suspected of ascending behavior are determined.
It can be understood that, similar to the change of the corner value, the vehicle may have a smaller height value change value when the vehicle does not have an uphill behavior due to factors such as driving habits of users and road surface flatness during running, so that it can be determined whether the difference value between the height change values of the first track point and the second track point is greater than a second preset threshold value. For example, the second preset threshold may be 10 meters, if the difference between the height value of the second track point and the height value of the first track point is greater than 10 meters, the height value from the first track point to the second track point is increased by 10 meters, so that the existence of a high probability indicates that the vehicle climbs upwards by more than 10 meters, and the vehicle has an ascending behavior.
Wherein the trajectory data may comprise a plurality of trajectory points of the vehicle at different moments in time.
Alternatively, the step of "calculating an initial score of the road from the position of the candidate anchor point in the road" may include:
acquiring a first point score of the candidate positioning point;
calculating a second point position score of each track point according to the first point position score, and generating a point position score set corresponding to the track data;
Obtaining a matching result of each track point and the road where the track point is located;
and determining an initial score of the road from the point score set according to the matching result, wherein the initial score is the maximum value of point scores of a plurality of track points corresponding to the road.
In some embodiments, the initial score may be expressed as:
wherein P is i Is the ith track point; l (L) j For the jth road, the road is provided with a road map,scoring the point position corresponding to the ith track point,/-for>Initial scoring for the jth road.
It will be understood that, since the track data is the track collected from the beginning to the end of the vehicle, and the application cuts the road with a length greater than 100 meters, so that a segment of track data may correspond to multiple roads, different track points may be attributed to different roads, for example, track point 1, track point 2 and track point 3 may correspond to one road, and track point 4, track point 5 and track point 6 may correspond to another road. Therefore, the maximum value of the point position scores of the corresponding track points in different roads can be determined as the initial score of the road.
Optionally, the step of calculating a second point score for each of the track points according to the first point score may include:
Acquiring a distance interval or a time interval between each track point and the candidate positioning point;
and according to the sequence of the distance interval or the time interval from small to large, taking the first point score as a reference, sequentially matching the second point scores which are gradually decreased one by one for each track point.
Referring to fig. 2b, fig. 2b is a schematic diagram illustrating calculation of a first point score and a second point score according to an embodiment of the present application.
In some embodiments, when the initial score is not zero, the vehicle is not identified as having cornering and uphill behavior within a 100 meter heading, for example, within the candidate setpoint. The first point score may be used as a reference, and the second point scores that decrease one by one may be sequentially matched for each track point. It can be understood that the candidate positioning point is a deceleration ending point at which the vehicle stops accelerating and is ready to accelerate, so that the speed of the vehicle at the candidate positioning point is the lowest in the whole deceleration behavior, and the position of the candidate positioning point is considered to be the set position of the road element with a high probability, and the probability of existence of the road element is higher than that of other track points.
Thus, as shown in fig. 2b, the first point bit score of the candidate anchor point may be set to be higher than the point scores of the other track points, such that the second point scores of the other track points may decrease one by one with the order of the time interval or distance interval of the track point from the candidate anchor point from small to large. For example, assuming that the first point score of the candidate positioning point is 10 points, the second point scores of the track point a and the track point A1 which are spaced apart from the candidate positioning point by 5 meters may be 9 points, the second point scores of the track point B and the track point B1 which are spaced apart from the candidate positioning point by 10 meters may be reduced from 9 points to 8 points, and so on until the second point score of a certain track point is calculated to be zero. It should be noted that, the decreasing value of the second point score of each track point may be set according to the requirement, which is not limited in this embodiment.
Therefore, after the first point score of the candidate locating point is determined, the second point score of each track point can be rapidly and accurately calculated according to the distance interval or the time interval between other track points and the candidate locating point, so that the efficiency of calculating the target score of the road can be improved.
And 103, acquiring the position of the candidate positioning point corresponding to each piece of track data in the road and the attribute of the road.
Wherein the property of the road is related to the topography of the road. For example, the topography of the road may include intersections, uphill slopes, crosswalks, or the like.
And 104, calculating the target score of the road according to the position of the candidate positioning point corresponding to each piece of track data in the road and combining the track data and the attribute of the road.
Wherein the accuracy of the target score is higher than the initial score. It will be appreciated that since one track data corresponds to one vehicle traveling data on a road, there are a plurality of vehicles traveling on each road. Therefore, in order to improve the accuracy of calculating the road score, a plurality of pieces of track data can be fused, and the target score of the road can be calculated by the plurality of pieces of track data.
Optionally, the step of calculating the target score of the road according to the each track data and each initial score corresponding to the each track data and the attribute of the road, may include:
if the speed of the vehicle in the track data meets a first preset condition or if the attribute of the road meets a second preset condition, determining the target score as zero;
and if the target score is not zero, calculating the average value of the sum of the initial scores to obtain the target score.
It will be appreciated that under the first preset condition and the second preset condition, there may be a case where there is no road element in the road. Therefore, roads with track data meeting the first preset condition and attributes meeting the second preset condition can be eliminated, and roads with target scores which are not zero can be further calculated.
In some embodiments, the target score for a road may be expressed as:
wherein L is j For the jth road, the road is provided with a road map,is a road L j Is (are) initial scoring->Is a road L j Target score of initial score of ∈10->And (3) the initial score corresponding to the T-th track data, wherein T is the total number of the track data.
It will be appreciated that the average value of the initial scores of each track data corresponding to the road after summation can be calculated by the above formula, so as to be used as the target score of the current road.
Optionally, the step of determining the target score as zero if the speed of the vehicle in the trajectory data meets a first preset condition includes:
acquiring a first speed of each vehicle running on the road;
sorting each first speed according to the first speed, and screening out target speeds in a target sorting interval from the sorted first speeds;
and if the ratio between the target speed and the limiting speed of the road meets a preset value interval, determining the target score as zero.
In some embodiments, the average speed of the vehicle running on the road may be obtained according to the track data, and then the target speed in the target sorting interval may be screened out. By way of example, for example, the target rank interval ranks speeds at 5% to 6% of the first speed magnitude, for example, the target speed is 67km/h, assuming a defined speed of the link is 80km/h, the preset value interval is 0-90% and 110% -infinity, so that the ratio between the target speed and the limiting speed is 83.75%, the preset value interval is met, and the target score of the road can be determined to be zero.
It can be understood that if the road has road elements, vehicles which are favored to be in high-speed driving at each moment in the driving habit of the user can be eliminated, the speed with higher speed is selected from the target sorting interval, and whether the speed is in the reasonable speed reduction range of the road speed limit is judged. For example, a road with a limited speed of 80km/h, when a road element exists, a user has a high probability of decelerating the speed of the vehicle to a range of 10% of the limited speed, for example, 72-88 km/h, so that a preset value interval can be 0-90%, 110% - ++infinity outside the range of 10% of the limited speed, and if the ratio between the speed of the target sorting interval and the limited speed is in the preset value interval, the high probability of the vehicle is not influenced by the speed limit of the road element, and therefore the target score of the road can be determined to be zero.
Optionally, the step of determining the target score as zero if the attribute of the road meets a second preset condition includes:
acquiring preset road topography of deceleration behaviors of a plurality of vehicles;
and if the road has the preset road topography or the road is positioned in the preset range of the preset road topography, determining the target score as zero.
In some embodiments, the preset road topography may include intersections, uphill slopes, or crosswalks. It will be appreciated that there is a road with the above preset road topography, and even if there is no road element with the speed limit prompting function, the vehicle will also travel at a reduced speed, and therefore, the target score of the road within the preset range of the preset road topography may be determined to be zero, for example, the target score of the road 100 meters around the intersection may be 0.
Step 105, determining that the road has the road element and the target position of the road element in the road according to the target score if the target score is greater than a preset threshold.
It may be further understood that, since the initial scores calculated according to each track data are different, the values of the different initial scores may be different, so that the target scores of the road under a plurality of track data may be reflected by the sum average value of the initial scores, and the larger the target score, the larger the probability that the road has a road element is indicated. Thus the more initial scores that are added to the calculation, the more accurate the reflecting value of the target score. Therefore, in some embodiments, the target score with a value greater than the third threshold may be selected as a valid target score, for example, the third preset threshold may be 2, 3, 4, etc., so that the situation that the information for identifying the detected road element is inaccurate due to the fact that the value of the target score is too low can be avoided.
In some embodiments, the target position may be a distance center of the road, for example, seven points of the road may be set to 0 and the end point of the road may be set to 1 according to the length of the road, so that a position with a length of 0.5 in the road is the target position.
In some embodiments, the target location may also be the coordinates of a candidate anchor point or a locus point in the road where the point score is high. It will be appreciated that since the candidate anchor point or the locus point with a higher point score is a point with a higher probability of existence of the road element, the coordinates of the above point can be determined as the target position of the road element in the road.
Therefore, the application obtains the track data of the vehicle by acquiring the historical driving data and the real-time driving data generated when the vehicle runs on the road, and identifies and detects the information such as the position, the number and the like of the road elements existing on different roads according to the track data. The whole road element identification and detection process does not need manual intervention and is not influenced by visual factors such as road environment, weather conditions and the like, so that the information of the road elements in different roads can be rapidly and accurately obtained on the premise of not needing visual equipment and manual detection and acquisition, the accuracy and the efficiency of the road element identification and detection are obviously improved, and the cost of the road element identification and detection can be reduced.
The other specific flow of the above method for identifying road elements is as follows, referring to fig. 1c and fig. 1d, the method is applied to the data sorting end:
step 201, obtaining initial track data.
The initial trajectory data may refer to travel data generated during road travel of an unprocessed vehicle. Such as speed, mileage, altitude, etc. of the vehicle.
And 202, processing the initial track data to obtain track data.
The initial track data can be screened through track screening conditions to obtain track data meeting requirements, so that the efficiency and accuracy of calculating the road target score in the follow-up process are improved.
And 203, determining candidate positioning points of the road elements.
The candidate locating point may be a candidate location point in the road where a road element may exist.
Step 204, obtaining a first point score of the candidate positioning points.
The first bit score may be set to an arbitrary value, and the larger the corresponding value is, the greater the probability that the road exists the road element.
Step 205, calculating a second point score of each track point according to the first point score to obtain a point score set.
In some embodiments, the score may be based on the first bit
And 206, determining the initial score of the road from the point scoring set according to the matching result of the track points and the road.
Wherein the initial score may characterize the overall probability of the presence of a road element in the road.
Step 207, if the speed of the vehicle meets the first preset condition, or if the attribute of the road meets the second preset condition, determining the target score as zero.
Wherein the accuracy of the target score may be higher than the initial score.
And step 208, if the target score is not zero, calculating the average value of the sum of the initial scores to obtain the target score.
The target score can be comprehensively calculated in a mode of fusing a plurality of pieces of track data, so that the accuracy of calculating the target score is improved.
Step 209, determining that the road exists a road element and a target position of the road element in the road according to the target score.
Specifically, after determining the target score of each road, it may be determined that a road element exists on the road according to whether the target score is zero, and if the target score is not zero and is greater than a preset threshold, the target position of the road is determined as the position of the road element. For example, the target location may be the center of the road, the location of candidate anchor points in the road, etc.
The method described in the above embodiments will be described in further detail below.
As shown in fig. 3, a schematic structural diagram of a road element identification device provided in an embodiment of the present application is provided, where the device may be applied to a data sorting terminal, and the device includes:
a track data acquisition unit 301 configured to acquire track data generated when a vehicle travels on a road, wherein the track data includes at least a speed of the vehicle, the track data being acquired by continuously positioning the vehicle;
a candidate anchor point determining unit 302 configured to determine, according to the track data, candidate anchor points where a road element exists in the road, where the candidate anchor points characterize positions where the road element can be set in the road, and each of the candidate anchor points corresponds to each of the track data;
a road data obtaining unit 303, configured to obtain a position of a candidate positioning point corresponding to each piece of track data in the road, and an attribute of the road, where the attribute of the road is related to a topography of the road;
a target score calculating unit 304, configured to calculate a target score of the road according to the position of the candidate positioning point corresponding to each piece of track data in the road, in combination with the track data and the attribute of the road, where the target score characterizes the probability that the road element actually exists in the road;
A road element locating unit 305 for determining that the road has the road element and a target position of the road element in the road according to the target score.
Optionally, the target score calculating unit 304 further includes:
an initial score calculation subunit, configured to calculate an initial score of the road according to the position of the candidate positioning point in the road, where the initial score characterizes a probability that the road element actually exists in the road;
and the target score calculating subunit is used for calculating the target score of the road according to each piece of track data and each initial score corresponding to each piece of track data and the attribute of the road, wherein the accuracy of the target score is higher than that of the initial score.
Optionally, the trajectory data includes a plurality of trajectory points of the vehicle at different moments in time, and the initial score calculating subunit includes:
a first point score obtaining subunit, configured to obtain a first point score of the candidate positioning point;
a first point score generating subunit, configured to calculate a second point score of each track point according to the first point score, and generate a point score set corresponding to the track data;
The matching result obtaining subunit is used for obtaining the matching result of each track point and the road where the track point is located;
and the initial score determining subunit is used for determining the initial score of the road from the point score set according to the matching result, wherein the initial score is the maximum value of the point scores of the plurality of track points corresponding to the road.
Optionally, the first point score generating subunit is further specifically configured to:
acquiring a distance interval or a time interval between each track point and the candidate positioning point;
and according to the sequence of the distance interval or the time interval from small to large, taking the first point score as a reference, sequentially matching the second point scores which are gradually decreased one by one for each track point.
Optionally, the target score calculating unit 304 includes:
a target score zeroing subunit, configured to determine the target score as zero if the speed of the vehicle in the track data meets a first preset condition, or if the attribute of the road meets a second preset condition;
and the target score calculating subunit is used for calculating the average value after summing each initial score if the target score is not zero, so as to obtain the target score.
Optionally, the target score zeroing subunit is further specifically configured to:
acquiring a first speed of each vehicle running on the road;
sorting each first speed according to the first speed, and screening out target speeds in a target sorting interval from the sorted first speeds;
and if the ratio between the target speed and the limiting speed of the road meets a preset value interval, determining the target score as zero.
Optionally, the target score zeroing subunit is further specifically configured to:
acquiring preset road topography of deceleration behaviors of a plurality of vehicles;
and if the road has the preset road topography or the road is positioned in the preset range of the preset road topography, determining the target score as zero.
Optionally, the apparatus further comprises:
a data calculation unit for calculating corner data and uphill data of the vehicle according to the trajectory data;
and the initial score zeroing unit is used for determining the initial score to be zero if the turning behavior of the vehicle is met based on the corner data or the uphill behavior of the vehicle is met by the uphill data.
Optionally, the trajectory data includes a plurality of trajectory points of the vehicle at different moments, and the data calculation unit includes:
the corner value calculating subunit is used for obtaining the corner value corresponding to each track point of the vehicle;
and the front-rear corner value calculating subunit is used for calculating a front corner value and a rear corner value of the vehicle at each track point according to each corner value, wherein the front corner value is the difference between the corner value of the vehicle at the current track point and the corner value of the track point which is positioned in front of the current track point and is preset in number intervals, and the rear corner value is the difference between the corner value of the current track point and the corner value of the track point which is positioned behind the current track point and is preset in number intervals.
And the turning behavior determination subunit is used for determining that the turning behavior of the vehicle exists if the track points of which the front turning angle value and the rear turning angle value are both larger than a first preset threshold value exist.
Optionally, the track data includes a plurality of track points of the vehicle at different moments, and a height value corresponding to each track point, and the data calculating unit includes:
A height change value obtaining subunit, configured to obtain, according to the height value of each track point, a height change value of the height value of the current track point and the height value of the last track point;
a track point group determining subunit, configured to determine at least one group of first track points and second track points from each track point according to the altitude change value, where the first track points are starting points where the vehicle has a suspected uphill behavior, and the second track points are ending points where the vehicle has the suspected uphill behavior;
and if the difference value between the height change value of the first track point and the height change value of the second track point is larger than a second preset threshold value, determining that the vehicle has the ascending behavior.
Optionally, the trajectory data includes a plurality of trajectory points of the vehicle at different moments, and a speed corresponding to each of the trajectory points, and the candidate positioning point determining unit 302 includes:
the acceleration determining subunit is used for determining the acceleration of each track point according to the track points and the corresponding speed of each track point;
a deceleration point determining subunit, configured to determine, according to the acceleration of each track point, a deceleration start point indicating that the vehicle starts decelerating, and a deceleration end point indicating that the vehicle ends decelerating, where the deceleration start points and the deceleration end points are in one-to-one correspondence;
And the candidate positioning point determining subunit is used for calculating a speed difference between the speed of the deceleration starting point and the speed of the deceleration ending point, and determining the deceleration ending point as the candidate positioning point if the speed difference is larger than a second preset threshold value.
Optionally, the apparatus further comprises:
an initial track data acquisition unit, configured to acquire initial track data, where the initial track data is vehicle running data of the vehicle at each fixed interval unit;
and the initial track data processing unit is used for processing the initial track data to obtain track data meeting the track screening conditions.
In the present application, the candidate anchor point determination unit 302 may determine, from the trajectory data, candidate anchor points where a road element exists in the road, wherein the candidate anchor points characterize positions where the road element can be set in the road, each of the candidate anchor points corresponding to the each piece of trajectory data.
Therefore, the application obtains the track data of the vehicle by acquiring the historical driving data and the real-time driving data generated when the vehicle runs on the road, and identifies and detects the information such as the position, the number and the like of the road elements existing on different roads according to the track data. The whole road element identification and detection process does not need manual intervention and is not influenced by visual factors such as road environment, weather conditions and the like, so that the information of the road elements in different roads can be rapidly and accurately obtained on the premise of not needing visual equipment and manual detection and acquisition, the accuracy and the efficiency of the road element identification and detection are obviously improved, and the cost of the road element identification and detection can be reduced.
The embodiment of the application also provides electronic equipment which can be a terminal, a server and other equipment. As shown in fig. 4, a schematic structural diagram of an electronic device according to an embodiment of the present application is shown, specifically:
the electronic device may include one or more processing cores 'processors 401, one or more computer-readable storage media's memory 402, a power supply 403, an input unit 404, and a communication unit 405, among other components. Those skilled in the art will appreciate that the electronic device structure shown in fig. 4 does not create a limitation on the electronic device and may include more or fewer components than shown, or may combine certain components, or may be a different arrangement of components. Wherein:
the processor 401 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, and performs various functions of the electronic device and processes data by running or executing software programs and/or units stored in the memory 402, and calling data stored in the memory 402. In some embodiments, processor 401 may include one or more processing cores; in some embodiments, processor 401 may integrate an application processor that primarily processes operating systems, user interfaces, applications, and the like, with a modem processor that primarily processes wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 401.
The memory 402 may be used to store software programs and units, and the processor 401 executes various functional applications and data processing by running the software programs and units stored in the memory 402. The memory 402 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the electronic device, etc. In addition, memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.
The electronic device also includes a power supply 403 for powering the various components, and in some embodiments, the power supply 403 may be logically connected to the processor 401 by a power management system, such that charge, discharge, and power consumption management functions are performed by the power management system. The power supply 403 may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.
The electronic device may further comprise an input unit 404, which input unit 404 may be used for receiving input digital or character information and generating keyboard, mouse, joystick, optical or trackball signal inputs in connection with user settings and function control.
The electronic device may also include a communication unit 405, and in some embodiments the communication unit 405 may include a wireless unit, through which the electronic device may wirelessly transmit over a short distance, thereby providing wireless broadband internet access to the user. For example, the communication unit 405 may be used to assist a user in e-mail, browsing web pages, accessing streaming media, and the like.
Although not shown, the electronic device may further include a display unit or the like, which is not described herein. In particular, in this embodiment, the processor 401 in the electronic device loads executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 executes the application programs stored in the memory 402, so as to implement various functions as follows:
acquiring track data generated when a vehicle runs on a road, wherein the track data at least comprises the speed of the vehicle, and the track data is acquired by continuously positioning the vehicle;
Determining candidate positioning points of a road element in the road according to the track data, wherein the candidate positioning points represent the settable positions of the road element in the road, and each candidate positioning point corresponds to each track data;
acquiring the position of a candidate positioning point corresponding to each piece of track data in the road and the attribute of the road, wherein the attribute of the road is related to the topography of the road;
calculating a target score of the road according to the position of the candidate positioning point corresponding to each piece of track data in the road and combining the track data with the attribute of the road, wherein the target score represents the probability that the road element exists in the road in a true mode;
and according to the size of the target score, if the target score is larger than a preset threshold value, determining that the road has the road element and the target position of the road element in the road.
The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.
As can be seen from the above, the technical solution of the present application does not require a trusted third party to participate in the collection and management operation of the data to be classified, and by converting the data to be classified in each data terminal into a matrix required for classification calculation, and performing encryption, element position variation, random number addition and other processes on the matrix through different data terminals in the classification process, any data terminal cannot completely obtain and tamper with the data from other data terminals, thereby avoiding the leakage and tampering of the data to be classified, and improving the efficiency, accuracy and safety of data classification.
Therefore, the method for identifying the road elements can solve the technical problems that in the existing data classification process, a large amount of characteristic data of data to be classified need to be acquired from different data sources, so that the data is divulged and tampered, and a safe and reliable trusted third party is difficult to find, so that the efficiency, accuracy and safety of data classification are reduced.
To this end, an embodiment of the present application provides a computer readable storage medium having stored therein a plurality of instructions capable of being loaded by a processor to perform the steps of any one of the road element identification methods provided by the embodiment of the present application. For example, the instructions may perform the steps of:
acquiring track data generated when a vehicle runs on a road, wherein the track data at least comprises the speed of the vehicle, and the track data is acquired by continuously positioning the vehicle;
determining candidate positioning points of a road element in the road according to the track data, wherein the candidate positioning points represent the settable positions of the road element in the road, and each candidate positioning point corresponds to each track data;
Acquiring the position of a candidate positioning point corresponding to each piece of track data in the road and the attribute of the road, wherein the attribute of the road is related to the topography of the road;
calculating a target score of the road according to the position of the candidate positioning point corresponding to each piece of track data in the road and combining the track data with the attribute of the road, wherein the target score represents the probability that the road element exists in the road in a true mode;
and according to the size of the target score, if the target score is larger than a preset threshold value, determining that the road has the road element and the target position of the road element in the road.
Wherein the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
Therefore, the application obtains the track data of the vehicle by acquiring the historical driving data and the real-time driving data generated when the vehicle runs on the road, and identifies and detects the information such as the position, the number and the like of the road elements existing on different roads according to the track data. The whole road element identification and detection process does not need manual intervention and is not influenced by visual factors such as road environment, weather conditions and the like, so that the information of the road elements in different roads can be rapidly and accurately obtained on the premise of not needing visual equipment and manual detection and acquisition, the accuracy and the efficiency of the road element identification and detection are obviously improved, and the cost of the road element identification and detection can be reduced.
The steps in the method for identifying road elements provided by the embodiment of the present application can be executed by the instructions stored in the storage medium, so that the beneficial effects of the method for identifying road elements provided by the embodiment of the present application can be achieved, and detailed descriptions of the foregoing embodiments are omitted.
The above description of the method, the device, the system, the electronic device and the computer storage medium for identifying the road element provided by the embodiment of the present application is provided in detail, and specific examples are applied to illustrate the principle and the implementation of the present application, and the description of the above embodiment is only used to help understand the method and the core idea of the present application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, the present description should not be construed as limiting the present application.
Claims (16)
1. A method of identifying road elements, the method comprising:
acquiring track data generated when a vehicle runs on a road, wherein the track data at least comprises the speed of the vehicle, and the track data is acquired by continuously positioning the vehicle;
Determining candidate positioning points of a road element in the road according to the track data, wherein the candidate positioning points represent the settable positions of the road element in the road, and each candidate positioning point corresponds to each track data;
acquiring the position of a candidate positioning point corresponding to each piece of track data in the road and the attribute of the road, wherein the attribute of the road is related to the topography of the road;
calculating a target score of the road according to the position of the candidate positioning point corresponding to each piece of track data in the road and combining the track data with the attribute of the road, wherein the target score represents the probability that the road element exists in the road in a true mode;
and according to the size of the target score, if the target score is larger than a preset threshold value, determining that the road has the road element and the target position of the road element in the road.
2. The method for identifying road elements according to claim 1, wherein calculating the target score of the road according to the position of the candidate anchor point corresponding to each piece of track data in the road in combination with the each piece of track data and the attribute of the road comprises:
Calculating an initial score of the road according to the position of the candidate locating point in the road, wherein the initial score characterizes the probability that the road element exists in the road in real time;
and calculating a target score of the road according to each piece of track data and each initial score corresponding to each piece of track data and the attribute of the road, wherein the accuracy of the target score is higher than that of the initial score.
3. The method of identifying road elements of claim 2, wherein the trajectory data includes a plurality of trajectory points of the vehicle at different times, the calculating an initial score of the road based on the location of the candidate anchor point in the road, comprising:
acquiring a first point score of the candidate positioning point;
calculating a second point position score of each track point according to the first point position score, and generating a point position score set corresponding to the track data;
obtaining a matching result of each track point and the road where the track point is located;
and determining an initial score of the road from the point score set according to the matching result, wherein the initial score is the maximum value of point scores of a plurality of track points corresponding to the road.
4. A method of identifying road elements as claimed in claim 3 wherein said calculating a second point location score for each of said locus points based on said first point location scores comprises:
acquiring a distance interval or a time interval between each track point and the candidate positioning point;
and according to the sequence of the distance interval or the time interval from small to large, taking the first point score as a reference, sequentially matching the second point scores which are gradually decreased one by one for each track point.
5. The method for identifying road elements according to claim 2, wherein calculating the target score of the road based on the each track data and each initial score corresponding to the each track data in combination with the attribute of the road comprises:
if the speed of the vehicle in the track data meets a first preset condition or if the attribute of the road meets a second preset condition, determining the target score as zero;
and if the target score is not zero, calculating the average value of the sum of the initial scores to obtain the target score.
6. The method according to claim 5, wherein determining the target score as zero if the speed of the vehicle in the trajectory data satisfies a first preset condition, comprises:
Acquiring a first speed of each vehicle running on the road;
sorting each first speed according to the first speed, and screening out target speeds in a target sorting interval from the sorted first speeds;
and if the ratio between the target speed and the limiting speed of the road meets a preset value interval, determining the target score as zero.
7. The method according to claim 5, wherein determining the target score as zero if the attribute of the road satisfies a second preset condition, comprises:
acquiring preset road topography of deceleration behaviors of a plurality of vehicles;
and if the road has the preset road topography or the road is positioned in the preset range of the preset road topography, determining the target score as zero.
8. The method of identifying road elements of claim 2, wherein prior to calculating an initial score for the road based on the location of the candidate anchor point in the road, the method further comprises:
calculating the corner data and the uphill data of the vehicle according to the track data;
And if the turning behavior of the vehicle is met based on the rotation angle data or the uphill behavior of the vehicle is met by the uphill data, determining the initial score as zero.
9. The method according to claim 8, wherein the trajectory data includes a plurality of trajectory points of the vehicle at different timings, and the calculating the rotation angle data of the vehicle from the trajectory data includes:
acquiring a corner value corresponding to each track point of the vehicle;
calculating a front corner value and a rear corner value of the vehicle at each track point according to each corner value, wherein the front corner value is the difference between the corner value of the vehicle at the current track point and the corner value of the track point which is positioned in front of the current track point and is preset in number, and the rear corner value is the difference between the corner value of the current track point and the corner value of the track point which is positioned behind the current track point and is preset in number;
and if the track points with the front rotation angle value and the rear rotation angle value which are both larger than the first preset threshold value exist, determining that the turning behavior of the vehicle exists.
10. The method according to claim 8, wherein the trajectory data includes a plurality of trajectory points of the vehicle at different times, and a height value corresponding to each of the trajectory points, and the calculating the uphill data of the vehicle based on the trajectory data includes:
according to the height value of each track point, obtaining the height change value of the height value of the current track point and the height value of the last track point;
determining at least one group of first track points and second track points from each track point according to the height change value, wherein the first track points are starting points of suspected ascending behaviors of the vehicle, and the second track points are ending points of the suspected ascending behaviors of the vehicle;
and if the difference value between the height change value of the first track point and the height change value of the second track point is larger than a second preset threshold value, determining that the vehicle has the ascending behavior.
11. The method for identifying a road element according to claim 2, wherein the trajectory data includes a plurality of trajectory points of the vehicle at different times, and a speed corresponding to each of the trajectory points, and the determining, according to the trajectory data, candidate positioning points where the road element exists in the road includes:
Determining the acceleration of each track point according to the track points and the corresponding speed of each track point;
according to the acceleration of each track point, determining a deceleration starting point for indicating the vehicle to start decelerating and a deceleration ending point for indicating the vehicle to end decelerating, wherein the deceleration starting points and the deceleration ending points are in one-to-one correspondence;
and calculating a speed difference between the speed of the deceleration starting point and the speed of the deceleration ending point, and determining the deceleration ending point as the candidate positioning point if the speed difference is larger than a second preset threshold value.
12. The method of identifying road elements according to claim 2, wherein before determining, from the trajectory data, that there are candidate anchor points of a road element in the road, the method further comprises:
acquiring initial track data, wherein the initial track data is vehicle running data of the vehicle at each fixed interval unit;
and processing the initial track data to obtain track data meeting the track screening conditions.
13. A device for identifying road elements, the device comprising:
a track data acquisition unit configured to acquire track data generated when a vehicle travels on a road, wherein the track data includes at least a speed of the vehicle, the track data being acquired by continuously positioning the vehicle;
A candidate anchor point determining unit configured to determine, according to the track data, candidate anchor points where a road element exists in the road, wherein the candidate anchor points characterize positions where the road element can be set in the road, and each of the candidate anchor points corresponds to each of the track data;
a road data obtaining unit, configured to obtain a position of a candidate positioning point corresponding to each piece of track data in the road, and an attribute of the road, where the attribute of the road is related to a topography of the road;
a target score calculating unit, configured to calculate a target score of the road according to the position of the candidate positioning point corresponding to each piece of track data in the road, in combination with each piece of track data and the attribute of the road, where the target score represents the probability that the road element actually exists in the road;
and the road element positioning unit is used for determining that the road has the road element and the target position of the road element in the road according to the target score if the target score is larger than a preset threshold value.
14. An electronic device, comprising:
A processor and a storage medium;
the processor is used for realizing each instruction;
the storage medium is for storing a plurality of instructions for loading and executing by a processor the method of identifying road elements according to any one of claims 1 to 12.
15. A computer readable storage medium storing executable instructions which when executed by a processor implement the method of identifying road elements of any one of claims 1-12.
16. A computer program product comprising a computer program or instructions which, when executed by a processor, implements the method of identifying road elements according to any one of claims 1-12.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211713760.8A CN116977943A (en) | 2022-12-29 | 2022-12-29 | Road element identification method, device, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211713760.8A CN116977943A (en) | 2022-12-29 | 2022-12-29 | Road element identification method, device, electronic equipment and computer storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116977943A true CN116977943A (en) | 2023-10-31 |
Family
ID=88477272
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211713760.8A Pending CN116977943A (en) | 2022-12-29 | 2022-12-29 | Road element identification method, device, electronic equipment and computer storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116977943A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118097972A (en) * | 2024-04-26 | 2024-05-28 | 泰安九洲金城机械有限公司 | Track point optimization method and device for vehicle running track |
-
2022
- 2022-12-29 CN CN202211713760.8A patent/CN116977943A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118097972A (en) * | 2024-04-26 | 2024-05-28 | 泰安九洲金城机械有限公司 | Track point optimization method and device for vehicle running track |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110364008B (en) | Road condition determining method and device, computer equipment and storage medium | |
JP7351487B2 (en) | Intelligent navigation method and system based on topology map | |
CN105444770B (en) | Track level map generation and localization method based on smart mobile phone | |
CN102208013B (en) | Landscape coupling reference data generation system and position measuring system | |
CN105513354A (en) | Video-based urban road traffic jam detecting system | |
CN112249009B (en) | Vehicle speed control method, device and system and electronic equipment | |
CN113375689B (en) | Navigation method, navigation device, terminal and storage medium | |
CN116518960B (en) | Road network updating method, device, electronic equipment and storage medium | |
CN113762044A (en) | Road recognition method, road recognition device, computer equipment and storage medium | |
CN115203352B (en) | Lane level positioning method and device, computer equipment and storage medium | |
CN113033463A (en) | Deceleration strip detection method and device, electronic equipment and storage medium | |
CN113918615A (en) | Simulation-based driving experience data mining model construction method and system | |
CN116358584A (en) | Automatic driving vehicle path planning method, device, equipment and medium | |
CN116295496A (en) | Automatic driving vehicle path planning method, device, equipment and medium | |
CN113420692A (en) | Method, apparatus, device, medium, and program product for generating direction recognition model | |
CN116664873B (en) | Image information processing method, device and storage medium | |
CN116778347A (en) | Data updating method, device, electronic equipment and storage medium | |
CN115546743B (en) | Vehicle road cooperative control method, device, equipment and medium based on adhesion coefficient | |
CN113276860B (en) | Vehicle control method, device, electronic device, and storage medium | |
CN116977943A (en) | Road element identification method, device, electronic equipment and computer storage medium | |
CN113715817B (en) | Vehicle control method, vehicle control device, computer equipment and storage medium | |
CN116105712A (en) | Road map generation method, reinjection method, computer device and medium | |
CN114895274A (en) | Guardrail identification method | |
CN113705304A (en) | Image processing method and device, storage medium and computer equipment | |
CN113762030A (en) | Data processing method and device, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication |