CN117974724A - Digital mapping method and device for vehicle, electronic equipment and storage medium - Google Patents
Digital mapping method and device for vehicle, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117974724A CN117974724A CN202311841728.2A CN202311841728A CN117974724A CN 117974724 A CN117974724 A CN 117974724A CN 202311841728 A CN202311841728 A CN 202311841728A CN 117974724 A CN117974724 A CN 117974724A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- current state
- estimated value
- digital mapping
- video image
- 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
- 238000013507 mapping Methods 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000005259 measurement Methods 0.000 claims abstract description 55
- 238000005457 optimization Methods 0.000 claims abstract description 33
- 238000001914 filtration Methods 0.000 claims abstract description 25
- 238000012937 correction Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 52
- 230000008569 process Effects 0.000 claims description 31
- 239000013598 vector Substances 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000007704 transition Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 238000009499 grossing Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 10
- 230000000007 visual effect Effects 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 5
- 230000008447 perception Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
Landscapes
- Navigation (AREA)
Abstract
The application relates to a digital mapping method, a digital mapping device, electronic equipment and a storage medium of a vehicle, wherein the method comprises the following steps: acquiring a motion video image of a vehicle, and acquiring a vehicle kinematic model according to the motion video image; solving the front wheel corner of the vehicle at each moment according to the vehicle kinematic model and the position information of the vehicle; based on the prior estimated value of the current state of the vehicle obtained through prediction and the posterior estimated value of the current state of the vehicle obtained through correction, kalman filtering optimization data are generated, and the digital mapping of the vehicle in the information space is optimized according to the Kalman filtering optimization data and the front wheel steering angle of the vehicle at each moment, so that a final digital mapping result is obtained. Therefore, the problems that in the related technology, the sensing visual field of the vehicle-mounted end sensor is limited, the measurement stability is poor, the accuracy of digital mapping is reduced, the real-time performance of a method based on high-precision map making is poor, the accuracy of map data is low due to delay in updating the high-precision map and the like are solved.
Description
Technical Field
The present application relates to the field of digital mapping technologies, and in particular, to a digital mapping method and apparatus for a vehicle, an electronic device, and a storage medium.
Background
Intelligent network-connected automobiles become a strategic direction of global automobile industry development, and the physical space and the information space of people, automobiles, roads and clouds are integrated through new generation information and communication technology, so that an automobile-road-cloud integrated system for realizing safe, energy-saving, comfortable and efficient operation of the intelligent network-connected automobile traffic system is generated based on system collaborative sensing, decision and control. The mapping of entities, vehicles, participants, and infrastructure in traffic to information (Cyber) space forms a cloud-controlled platform that provides service support for applications such as road network real-time traffic situation awareness, traffic flow statistics, traffic congestion analysis, digital twinning, etc., based on vehicle end, road side, and other dynamic traffic data. The accuracy of real-time digital mapping of road vehicles in a traffic environment on a cloud control platform is important for industrial application in a vehicle-road cloud integrated system, and the mapping principle from the physical world to the information world is shown in fig. 1.
In the related art, the real-time digital mapping modeling of the road vehicle on the cloud control platform is mainly performed by two methods, namely, a multi-mode sensor fusion-based method and a high-precision map-based method. The digital mapping method based on the multi-mode sensor fusion mainly uses various sensors carried on the vehicle, such as cameras, laser radars, millimeter wave radars, GNSS (Global Navigation SATELLITE SYSTEM ) and the like, and obtains comprehensive environmental information by fusing the data of the sensors; such a method based on high-precision map production focuses on constructing a map of high precision in advance and then updating map information in real time by an on-vehicle sensor, and such a map generally contains detailed road structures, intersection information, traffic signs, and the like. The vehicle can accurately position itself by comparing with the maps, and update map data in real time to adapt to environmental changes.
However, in the related art, the vehicle-mounted end sensor has limited sensing field of view, poor measurement stability, reduced accuracy of digital mapping, and poor real-time performance of the method based on high-precision map making, low accuracy of map data due to delay in updating the high-precision map, reduced accuracy and reliability of road vehicle positioning, and urgent improvement is needed.
Disclosure of Invention
The application provides a digital mapping method, a device, electronic equipment and a storage medium for a vehicle, which are used for solving the problems that in the related technology, a vehicle-mounted end sensor has limited perception field, poor measurement stability, reduced digital mapping accuracy, and a method based on high-precision map making has poor real-time performance, and the update of a high-precision map causes low map data accuracy due to delay, and reduced road vehicle positioning accuracy and reliability.
An embodiment of a first aspect of the present application provides a digital mapping method for a vehicle, including the steps of: acquiring a motion video image of a vehicle, and acquiring a vehicle kinematic model according to the motion video image; solving the front wheel corner of the vehicle at each moment according to the vehicle kinematic model and the position information of the vehicle; and generating Kalman filtering optimization data based on the prior estimated value of the predicted vehicle current state and the posterior estimated value of the corrected vehicle current state, and optimizing the digital mapping of the vehicle in an information space according to the Kalman filtering optimization data and the front wheel steering angle of the vehicle at each moment to obtain a final digital mapping result.
Optionally, in one embodiment of the present application, the capturing a motion video image of a vehicle and obtaining a vehicle kinematic model according to the motion video image includes: acquiring a moving video image of the vehicle based on at least one road side device; and taking the motion video image as a two-dimensional plane coordinate system to construct the vehicle kinematic model and the measurement model according to the two-dimensional plane coordinate system.
Optionally, in one embodiment of the present application, the state equation and the observation equation of the vehicle are:
wherein X (k) is the real state of the vehicle at the moment k, A is a state transition matrix, W (k) is process noise, Z (k) is an observation vector, H is a measurement model matrix, and V (k) is Gaussian white noise on corresponding measurement longitude and latitude.
Optionally, in one embodiment of the present application, the solving the front wheel corner of the vehicle at each time according to the vehicle kinematic model and the position information of the vehicle includes: extracting time sequence data from the position information of the vehicle, obtaining a time sequence signal according to the time sequence data, and smoothing noise in the time sequence signal to obtain smoothed data; and carrying out differential calculation on the position information of two adjacent time points based on the smooth data to obtain a vector included angle, and reversely pushing the front wheel corner of the vehicle at each time according to the vector included angle.
Optionally, in one embodiment of the present application, the generating the kalman filter optimization data based on the a priori estimated value of the current state of the vehicle obtained by prediction and the posterior estimated value of the current state of the vehicle obtained by correction includes: establishing a priori estimate of the current state of the vehicle by using a preset time update equation, and predicting to obtain a priori estimate of the current state of the vehicle; establishing a posterior estimation of the current state by using a priori estimated value of a preset measurement update equation and a measured variable, and correcting to obtain the posterior estimated value of the current state of the vehicle; and obtaining the Kalman filtering optimization data according to the prior estimated value and the posterior estimated value.
Optionally, in one embodiment of the present application, the preset time update equation is:
X(k|k-1)＝AX(k-1|k-1)+W(k-1)
P(k|k-1)＝AP(k-1|k-1)AT+Q(k-1)，
wherein X (k|k-1) is the prior estimated value of the Kalman filter at the moment k to the current state of the vehicle, X (k-1|k-1) is the posterior estimated value of the Kalman filter at the moment k-1 to the current state of the vehicle, P (k|k-1) is the prior estimated error covariance matrix, Q is the covariance matrix of process noise, R is the covariance matrix of measurement noise, and A is the state transition matrix.
Optionally, in an embodiment of the present application, the preset measurement update equation is:
X(k|k)＝X(k|k-1)+K(k)[Z(k)-HX(k|k-1)]
P(k|k)＝[I-K(k)H]P(k|k-1)
K(k)＝P(k|k-1)HT[HP(k|k-1)HT+R(k)]-1，
Wherein X (K-1) is an a priori estimate of the vehicle motion state by the kalman filter at time K, X (K-K) is the a priori estimate of the state at time K, P (K-1) is the a priori estimate error covariance matrix, P (K-K) is the a priori estimate error covariance matrix, I is an identity matrix, K (K) is a kalman gain or mixing factor, Z (K) is an observation vector, and H is a measurement model matrix.
An embodiment of a second aspect of the present application provides a digital mapping apparatus for a vehicle, including: the acquisition module is used for acquiring a motion video image of the vehicle and acquiring a vehicle kinematic model according to the motion video image; the solving module is used for solving the front wheel corner of the vehicle at each moment according to the vehicle kinematic model and the position information of the vehicle; and the mapping module is used for generating Kalman filtering optimization data based on the prior estimated value of the predicted current state of the vehicle and the posterior estimated value of the corrected current state of the vehicle, and optimizing the digital mapping of the vehicle in the information space according to the Kalman filtering optimization data and the front wheel steering angle of the vehicle at each moment to obtain a final digital mapping result.
Optionally, in one embodiment of the present application, the acquiring module includes: an acquisition unit configured to acquire a moving video image of the vehicle based on at least one roadside apparatus; and a construction unit for taking the motion video image as a two-dimensional plane coordinate system to construct the vehicle kinematic model and the measurement model according to the two-dimensional plane coordinate system.
Optionally, in one embodiment of the present application, the state equation and the observation equation of the vehicle are:
wherein X (k) is the real state of the vehicle at the moment k, A is a state transition matrix, W (k) is process noise, Z (k) is an observation vector, H is a measurement model matrix, and V (k) is Gaussian white noise on corresponding measurement longitude and latitude.
Optionally, in one embodiment of the present application, the solving module includes: an extraction unit, configured to extract time-series data from position information of the vehicle, obtain a time-series signal according to the time-series data, and perform smoothing processing on noise in the time-series signal to obtain smoothed data; and the calculating unit is used for carrying out differential calculation on the position information of two adjacent time points based on the smooth data to obtain a vector included angle, and reversely pushing the front wheel corner of the vehicle at each time according to the vector included angle.
Optionally, in one embodiment of the present application, the mapping module includes: the prediction unit is used for establishing prior estimation of the current state of the vehicle by using a preset time update equation, and predicting to obtain a prior estimation value of the current state of the vehicle; the correction unit is used for establishing posterior estimation of the current state by using a priori estimated value of a preset measurement update equation and a measured variable, and correcting the posterior estimation to obtain a posterior estimated value of the current state of the vehicle; and the generating unit is used for obtaining the Kalman filtering optimization data according to the prior estimated value and the posterior estimated value.
Optionally, in one embodiment of the present application, the preset time update equation is:
X(k|k-1)＝AX(k-1|k-1)+W(k-1)
P(k|k-1)＝AP(k-1|k-1)AT+Q(k-1)，
wherein X (k|k-1) is the prior estimated value of the Kalman filter at the moment k to the current state of the vehicle, X (k-1|k-1) is the posterior estimated value of the Kalman filter at the moment k-1 to the current state of the vehicle, P (k|k-1) is the prior estimated error covariance matrix, Q is the covariance matrix of process noise, R is the covariance matrix of measurement noise, and A is the state transition matrix.
Optionally, in an embodiment of the present application, the preset measurement update equation is:
X(k|k)＝X(k|k-1)+K(k)[Z(k)-HX(k|k-1)]
P(k|k)＝[I-K(k)H]P(k|k-1)
K(k)＝P(k|k-1)HT[HP(k|k-1)HT+R(k)]-1，
Wherein X (K-1) is an a priori estimate of the vehicle motion state by the kalman filter at time K, X (K-K) is the a priori estimate of the state at time K, P (K-1) is the a priori estimate error covariance matrix, P (K-K) is the a priori estimate error covariance matrix, I is an identity matrix, K (K) is a kalman gain or mixing factor, Z (K) is an observation vector, and H is a measurement model matrix.
An embodiment of a third aspect of the present application provides an electronic device, including: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to realize the digital mapping method of the vehicle according to the embodiment.
A fourth aspect of the present application provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements a digital mapping method for a vehicle as above.
The embodiment of the application can utilize the data obtained by the road side sensing equipment in real time to carry out digital mapping of the road vehicle on the cloud control platform, solves the front wheel steering angle value based on the road side sensing information and the vehicle kinematic model, combines Kalman filtering to optimize the mapping accuracy of the vehicle on the cloud, not only avoids high cost of high-precision map making investment, but also overcomes the dilemma that the front wheel steering angle data cannot be directly obtained due to incomplete sensing data types, provides more accurate state information in digital vehicle track mapping, and provides technical support for realizing accurate mapping and positioning of the vehicle on the cloud information world. Therefore, the problems that in the related technology, the sensing visual field of the vehicle-mounted end sensor is limited, the measurement stability is poor, the accuracy of digital mapping is reduced, the real-time performance of a method based on high-precision map making is poor, the accuracy of map data is low due to delay in updating of the high-precision map, the accuracy and reliability of road vehicle positioning are reduced, and the like are solved.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a schematic diagram of a mapping from the physical world to the real world in the related art;
FIG. 2 is a flow chart of a method for digitally mapping a vehicle according to an embodiment of the present application;
FIG. 3 is a Kalman filter optimization data flow chart of a digital mapping method of a vehicle according to one embodiment of the application;
fig. 4 is a schematic structural diagram of a digital mapping device of a vehicle according to an embodiment of the present application;
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.
The following describes a digital mapping method, a digital mapping device, an electronic device and a storage medium of a vehicle according to an embodiment of the present application with reference to the accompanying drawings. Aiming at the problems that in the related technology mentioned in the background technology, a vehicle-mounted end sensor has limited perception field, poor measurement stability, reduced digital mapping accuracy, and a method based on high-precision map production has poor real-time performance, and map data is low in accuracy due to delay caused by updating of a high-precision map, and reduced accuracy and reliability of road vehicle positioning are solved. Therefore, the problems that in the related technology, the sensing visual field of the vehicle-mounted end sensor is limited, the measurement stability is poor, the accuracy of digital mapping is reduced, the real-time performance of a method based on high-precision map making is poor, the accuracy of map data is low due to delay in updating of the high-precision map, the accuracy and reliability of road vehicle positioning are reduced, and the like are solved.
Specifically, fig. 2 is a flow chart of a digital mapping method of a vehicle according to an embodiment of the present application.
As shown in fig. 2, the digital mapping method of the vehicle includes the steps of:
in step S201, a motion video image of a vehicle is acquired, and a vehicle kinematic model is obtained from the motion video image.
In the actual execution process, the embodiment of the application can acquire the motion video image of the vehicle in real time by utilizing the road side sensor, and obtain the vehicle kinematic model according to the motion video image, thereby being convenient for solving the front wheel steering angle value subsequently.
The application can acquire the motion video image of the vehicle, obtain the vehicle kinematic model, provide support for acquiring the front wheel steering angle value of the vehicle, overcome the dilemma that the front wheel steering angle data cannot be directly acquired due to the insufficiency of the sensing data type, and provide more accurate state information in the digital vehicle track mapping.
Optionally, in one embodiment of the present application, acquiring a motion video image of a vehicle, and obtaining a vehicle kinematic model according to the motion video image includes: acquiring a moving video image of a vehicle based on at least one road side device; the motion video image is used as a two-dimensional planar coordinate system to construct a vehicle kinematic model and a measurement model according to the two-dimensional planar coordinate system.
It will be appreciated that at least one of the roadside devices in embodiments of the present application may be, but is not limited to, a roadside sensor, typically mounted in a fixed location, that is easier to achieve accurate spatial positioning relative to an onboard sensor; and the road side sensor can be deployed at a key position of an intersection, a road section or a city street, provides global and comprehensive environment perception, can cover a wider area compared with the vehicle-mounted sensor, and is beneficial to improving the accuracy of digital mapping.
In an actual implementation process, the embodiment of the application can acquire a moving video image of a vehicle based on at least one road side device, such as a road side sensor, take the moving video image as a two-dimensional plane coordinate system, and take the center point of a vehicle identification rectangular frame as an analysis object to construct a vehicle kinematic model and a measurement model of the vehicle in the running process.
The embodiment of the application can construct a vehicle kinematic model and a measurement model of the vehicle in the running process, thereby further providing support for the follow-up solving of the front wheel corner value, avoiding the high cost of high-precision map making investment and overcoming the dilemma that the front wheel corner data can not be directly acquired.
Optionally, in one embodiment of the present application, the state equation and the observation equation of the vehicle are:
Wherein X (k) is the real state of the vehicle at the moment k, A is a state transition matrix, W (k) is process noise, Z (k) is an observation vector, H is a measurement model matrix, and V (k) is Gaussian white noise on the corresponding measurement longitude and latitude.
In the actual implementation process, the embodiment of the application can be implemented through the state equation and the observation equation of the vehicle:
wherein Z (k) is an observation vector, namely the vehicle position acquired by the road side sensor, and the observation vector only comprises longitude and latitude coordinates of a central point of the target vehicle position.
The calculation accuracy is improved, and the running state of the vehicle is analyzed in a targeted manner, so that more accurate state information is provided in the digital vehicle track map.
In step S202, the front wheel turning angle of the vehicle at each time is solved based on the vehicle kinematic model and the position information of the vehicle.
In the actual execution process, the embodiment of the application can solve the front wheel corner of the vehicle at each moment according to the vehicle kinematic model and the position information of the vehicle obtained by real-time sensing through a dynamic front wheel corner solving algorithm, and provides a basis for the follow-up optimization of the mapping accuracy of the vehicle at the cloud.
The embodiment of the application can solve the front wheel corner of the vehicle at each moment, optimize the vehicle track mapping effect in the cloud control platform, improve the accuracy and reliability of road vehicle positioning, solve the unavoidable position errors and errors in the perception information transmitted by each node at the road side and other problems, thereby optimizing the target track of the road vehicle spliced in the information space, ensuring that the target track is presented more continuously and smoothly, and conforming to the reality logic.
Optionally, in one embodiment of the present application, solving the front wheel corner of the vehicle at each time according to the vehicle kinematic model and the position information of the vehicle includes: extracting time sequence data from the position information of the vehicle, obtaining a time sequence signal according to the time sequence data, and performing smoothing treatment on noise in the time sequence signal to obtain smoothed data; and carrying out differential calculation on the position information of two adjacent time points based on the smooth data to obtain a vector included angle, and reversely pushing the front wheel corner of the vehicle at each time according to the vector included angle.
As a possible implementation manner, the embodiment of the present application may extract the required time-series data from the acquired vehicle position information, ensure consistency and continuity of the data, smooth noise in the time-series signal by using a moving average filter (moving AVERAGE FILTER), make the data more approximate to a smooth state, reduce errors in a subsequent calculation process, and perform differential calculation on the filtered vehicle position information at each time and two adjacent time points, where the three points may be denoted as P1 (x_j, y_j), P2 (x_k, y_k), and P3 (x_l, y_l). Calculating the position vectors of points P1 to P2 and points P2 to P3, respectivelyAnd/>The included angle of the two vectors is calculated to reversely deduce the front wheel angle of the vehicle at each moment, so that the front wheel angle of the vehicle at each moment is reversely deduced to serve as the control input of Kalman filtering.
The embodiment of the application can reversely push the front wheel corner of the vehicle at each moment according to the vector included angle, thereby further providing a basis for the follow-up optimization of the mapping accuracy of the vehicle at the cloud end, further improving the positioning accuracy and reliability of the road vehicle, and solving the problems of unavoidable position errors, errors and the like in the perception information transmitted by each node at the road side.
In step S203, based on the prior estimated value of the predicted current state of the vehicle and the posterior estimated value of the corrected current state of the vehicle, kalman filter optimization data is generated, and the digital mapping of the vehicle in the information space is optimized according to the kalman filter optimization data and the front wheel steering angle of the vehicle at each moment, so as to obtain a final digital mapping result.
It will be appreciated that, based on the front wheel steering angle of the vehicle at each time, in combination with the data optimization capability of the kalman filter, a high-precision digital mapping of the road vehicle in the information space can be achieved, wherein the flow of the kalman filter optimization data is shown in fig. 3. The Kalman filter in the embodiment of the application comprises two main processes: prediction and correction.
In the actual execution process, the embodiment of the application can finish two processes of the Kalman filter, obtain Kalman filter optimization data according to the prior estimated value of the current state of the vehicle in the prediction process and the posterior estimated value of the current state of the vehicle in the correction process, take the front wheel steering angle of the vehicle at each moment as the control input of the Kalman filter, and optimize the digital mapping of the vehicle in the information space according to the Kalman filter optimization data and the front wheel steering angle of the vehicle at each moment to obtain the final digital mapping result.
The embodiment of the application can realize high-precision digital mapping of road vehicles in an information space by means of a dynamic front wheel steering angle estimation method and combining with the data optimization capability of Kalman filtering, thereby not only overcoming the dilemma that the front wheel steering angle data can not be directly acquired, but also providing more precise state information in digital vehicle track mapping and providing technical support for realizing accurate mapping and positioning of vehicles in the digital world.
Optionally, in one embodiment of the present application, generating the kalman filter optimization data based on the a priori estimate of the predicted current state of the vehicle and the posterior estimate of the corrected current state of the vehicle includes: establishing a priori estimate of the current state of the vehicle by using a preset time update equation, and predicting to obtain a priori estimate of the current state of the vehicle; establishing a posterior estimation of the current state by using a priori estimated value of a preset measurement update equation and a measured variable, and correcting to obtain a posterior estimated value of the current state of the vehicle; and according to the priori estimated value and the posterior estimated value, kalman filtering optimization data is obtained.
In the actual execution process, the embodiment of the application can utilize the preset time update equation to establish the prior estimation of the current state of the vehicle, and timely calculate the values of the current state variable and the error covariance estimation forward so as to construct the prior estimation value for the next time state, the correction process is responsible for feedback, the preset measurement update equation can be utilized to establish the improved posterior estimation of the current state on the basis of the prior estimation value and the measurement variable in the estimation process, and the posterior estimation value of the current state of the vehicle is obtained, and the Kalman filtering optimization data can be obtained according to the prior estimation value and the posterior estimation value, namely according to the prediction and correction processes.
According to the embodiment of the application, the prior estimation of the current state of the vehicle can be established by utilizing the preset time update equation, the prior estimation value of the preset measurement update equation and the measurement variable are utilized to establish the posterior estimation of the current state, the Kalman filtering optimization data is obtained, and the mapping accuracy of the vehicle in the cloud can be optimized by combining the Kalman filtering optimization data with the front wheel steering angle value.
It should be noted that the preset time update equation and the preset measurement update equation may be set by those skilled in the art according to actual situations, and are not particularly limited herein.
Optionally, in one embodiment of the present application, the preset time update equation is:
X(k|k-1)＝AX(k-1|k-1)+W(k-1)
P(k|k-1)＝AP(k-1|k-1)AT+Q(k-1)，
wherein X (k|k-1) is the prior estimated value of the Kalman filter at the moment k to the current state of the vehicle, X (k-1|k-1) is the posterior estimated value of the corresponding Kalman filter at the moment k-1 to the current state of the vehicle, P (k|k-1) is the prior estimated error covariance matrix, Q is the covariance matrix of process noise, R is the covariance matrix of measurement noise, and A is the state transition matrix.
Specifically, the embodiment of the application can update the equation according to the preset time of the discrete Kalman filtering:
X(k|k-1)＝AX(k-1|k-1)+W(k-1)
P(k|k-1)＝AP(k-1|k-1)AT+Q(k-1)，
wherein, Q is the covariance matrix of the process noise, which is estimated according to the actual operation process and is recorded as:
Q(k-1)＝E(W(k-1)W(k-1)T)，
the calculation accuracy is improved, so that more accurate mapping is obtained, and accurate mapping and positioning of the vehicle in the digital world are realized.
Optionally, in one embodiment of the present application, the preset measurement update equation is:
X(k|k)＝X(k|k-1)+K(k)[Z(k)-HX(k|k-1)]
P(k|k)＝[I-K(k)H]P(k|k-1)
K(k)＝P(k|k-1)HT[HP(k|k-1)HT+R(k)]-1，
wherein X (K-1) is the prior estimated value of the Kalman filter at the moment K to the motion state of the vehicle, X (K-K) is the posterior state estimated value at the moment K, P (K-1) is the prior estimated error covariance matrix, P (K-K) is the posterior estimated error covariance matrix, I is the identity matrix, K (K) is the Kalman gain or the mixing factor, Z (K) is the observation vector, and H is the measurement model matrix.
In the actual implementation process, the embodiment of the application can update the equation according to the preset measurement of the discrete Kalman filtering:
X(k|k)＝X(k|k-1)+K(k)[Z(k)-HX(k|k-1)]
P(k|k)＝[I-K(k)H]P(k|k-1)
K(k)＝P(k|k-1)HT[HP(k|k-1)HT+R(k)]-1，
wherein, R is a covariance matrix of measurement noise, which can be generally obtained according to data and actual measurement of a related measurement sensor such as a camera manufacturer, and is recorded as:
R(k)＝E(V(k)V(k)T)，
the calculation accuracy is further improved, the more accurate mapping is further obtained, and the accurate mapping and positioning of the vehicle in the digital world are realized.
According to the digital mapping method for the vehicle, which is provided by the embodiment of the application, the road vehicle can be digitally mapped on the cloud control platform by utilizing the data acquired by the road side sensing equipment in real time, the front wheel steering angle value is solved based on the road side sensing information and the vehicle kinematic model, and the mapping accuracy of the vehicle on the cloud is optimized by combining Kalman filtering, so that the high cost of high-precision map making investment is avoided, the dilemma that the front wheel steering angle data cannot be directly acquired due to incomplete sensing data types is overcome, more accurate state information is provided in the digital vehicle track mapping, and technical support is provided for realizing accurate mapping and positioning of the vehicle on the cloud information world. Therefore, the problems that in the related technology, the sensing visual field of the vehicle-mounted end sensor is limited, the measurement stability is poor, the accuracy of digital mapping is reduced, the real-time performance of a method based on high-precision map making is poor, the accuracy of map data is low due to delay in updating of the high-precision map, and the accuracy and reliability of road vehicle positioning are reduced are solved.
Next, a digital mapping device of a vehicle according to an embodiment of the present application will be described with reference to the accompanying drawings.
Fig. 4 is a schematic structural view of a digital mapping device of a vehicle according to an embodiment of the present application.
As shown in fig. 4, the digital mapping device 10 of the vehicle includes: an acquisition module 100, a solution module 200 and a mapping module 300.
Specifically, the acquiring module 100 is configured to acquire a motion video image of a vehicle, and obtain a kinematic model of the vehicle according to the motion video image.
The solving module 200 is configured to solve a front wheel corner of the vehicle at each moment according to the vehicle kinematic model and the position information of the vehicle.
The mapping module 300 is configured to generate kalman filter optimization data based on the prior estimated value of the predicted current state of the vehicle and the posterior estimated value of the corrected current state of the vehicle, and obtain a final digital mapping result according to the kalman filter optimization data and the digital mapping of the front wheel steering angle optimization vehicle in the information space at each moment.
Optionally, in one embodiment of the present application, the acquiring module 100 includes: an acquisition unit and a construction unit.
And the acquisition unit is used for acquiring the moving video image of the vehicle based on at least one road side device.
And a construction unit for taking the motion video image as a two-dimensional plane coordinate system to construct a vehicle kinematic model and a measurement model according to the two-dimensional plane coordinate system.
Optionally, in one embodiment of the present application, the state equation and the observation equation of the vehicle are:
Wherein X (k) is the real state of the vehicle at the moment k, A is a state transition matrix, W (k) is process noise, Z (k) is an observation vector, H is a measurement model matrix, and V (k) is Gaussian white noise on the corresponding measurement longitude and latitude.
Optionally, in one embodiment of the present application, the solving module 200 includes: an extraction unit and a calculation unit.
The extraction unit is used for extracting time sequence data from the position information of the vehicle, obtaining a time sequence signal according to the time sequence data, and smoothing noise in the time sequence signal to obtain smoothed data.
The calculation unit is used for carrying out differential calculation on the position information of two adjacent time points based on the smooth data to obtain a vector included angle, and reversely pushing the front wheel corner of the vehicle at each moment according to the vector included angle.
Optionally, in one embodiment of the present application, the mapping module 300 includes: prediction unit, correction unit and generation unit.
The prediction unit is used for establishing prior estimation of the current state of the vehicle by using a preset time update equation, and predicting to obtain a prior estimation value of the current state of the vehicle.
And the correction unit is used for establishing the posterior estimation of the current state by using the prior estimation value of the preset measurement update equation and the measurement variable, and correcting the posterior estimation to obtain the posterior estimation value of the current state of the vehicle.
And the generating unit is used for optimizing data according to the prior estimated value and the posterior estimated value by Kalman filtering.
Optionally, in one embodiment of the present application, the preset time update equation is:
X(k|k-1)＝AX(k-1|k-1)+W(k-1)
P(k|k-1)＝AP(k-1|k-1)AT+Q(k-1)，
wherein X (k|k-1) is the prior estimated value of the Kalman filter at the moment k to the current state of the vehicle, X (k-1|k-1) is the posterior estimated value of the corresponding Kalman filter at the moment k-1 to the current state of the vehicle, P (k|k-1) is the prior estimated error covariance matrix, Q is the covariance matrix of process noise, R is the covariance matrix of measurement noise, and A is the state transition matrix.
Optionally, in one embodiment of the present application, the preset measurement update equation is:
X(k|k)＝X(k|k-1)+K(k)[Z(k)-HX(k|k-1)]
P(k|k)＝[I-K(k)H]P(k|k-1)
K(k)＝P(k|k-1)HT[HP(k|k-1)HT+R(k)]-1，
wherein X (K-1) is the prior estimated value of the Kalman filter at the moment K to the motion state of the vehicle, X (K-K) is the posterior state estimated value at the moment K, P (K-1) is the prior estimated error covariance matrix, P (K-K) is the posterior estimated error covariance matrix, I is the identity matrix, K (K) is the Kalman gain or the mixing factor, Z (K) is the observation vector, and H is the measurement model matrix.
It should be noted that the foregoing explanation of the embodiment of the vehicle digital mapping method is also applicable to the vehicle digital mapping device of this embodiment, and will not be repeated herein.
According to the digital mapping device for the vehicle, which is provided by the embodiment of the application, the road vehicle can be digitally mapped on the cloud control platform by utilizing the data acquired by the road side sensing equipment in real time, the front wheel steering angle value is solved based on the road side sensing information and the vehicle kinematic model, and the mapping accuracy of the vehicle on the cloud is optimized by combining the Kalman filtering, so that the high cost of high-precision map making investment is avoided, the dilemma that the front wheel steering angle data cannot be directly acquired due to incomplete sensing data types is overcome, more accurate state information is provided in the digital vehicle track mapping, and technical support is provided for realizing accurate mapping and positioning of the vehicle on the cloud information world. Therefore, the problems that in the related technology, the sensing visual field of the vehicle-mounted end sensor is limited, the measurement stability is poor, the accuracy of digital mapping is reduced, the real-time performance of a method based on high-precision map making is poor, the accuracy of map data is low due to delay in updating of the high-precision map, and the accuracy and reliability of road vehicle positioning are reduced are solved.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:
Memory 501, processor 502, and a computer program stored on memory 501 and executable on processor 502.
The processor 502 implements the digital mapping method of the vehicle provided in the above embodiment when executing a program.
Further, the electronic device further includes:
a communication interface 503 for communication between the memory 501 and the processor 502.
Memory 501 for storing a computer program executable on processor 502.
The memory 501 may include high-speed RAM memory and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
If the memory 501, the processor 502, and the communication interface 503 are implemented independently, the communication interface 503, the memory 501, and the processor 502 may be connected to each other via a bus and perform communication with each other. The bus may be an industry standard architecture (Industry Standard Architecture, abbreviated ISA) bus, an external device interconnect (PERIPHERAL COMPONENT, abbreviated PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 5, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 501, the processor 502, and the communication interface 503 are integrated on a chip, the memory 501, the processor 502, and the communication interface 503 may perform communication with each other through internal interfaces.
The processor 502 may be a central processing unit (Central Processing Unit, abbreviated as CPU), or an Application SPECIFIC INTEGRATED Circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the application.
The present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the digital mapping method of a vehicle as above.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (10)
1. A digital mapping method of a vehicle, comprising the steps of:
Acquiring a motion video image of a vehicle, and acquiring a vehicle kinematic model according to the motion video image;
solving the front wheel corner of the vehicle at each moment according to the vehicle kinematic model and the position information of the vehicle; and
Based on the prior estimated value of the current state of the vehicle obtained through prediction and the posterior estimated value of the current state of the vehicle obtained through correction, kalman filtering optimization data are generated, and the digital mapping of the vehicle in an information space is optimized according to the Kalman filtering optimization data and the front wheel steering angle of the vehicle at each moment, so that a final digital mapping result is obtained.
2. The method of claim 1, wherein the acquiring a motion video image of the vehicle and deriving a vehicle kinematic model from the motion video image comprises:
acquiring a moving video image of the vehicle based on at least one road side device;
And taking the motion video image as a two-dimensional plane coordinate system to construct the vehicle kinematic model and the measurement model according to the two-dimensional plane coordinate system.
3. The method of claim 1, wherein the state equation and the observation equation of the vehicle are:
wherein X (k) is the real state of the vehicle at the moment k, A is a state transition matrix, W (k) is process noise, Z (k) is an observation vector, H is a measurement model matrix, and V (k) is Gaussian white noise on corresponding measurement longitude and latitude.
4. The method of claim 1, wherein said solving for the front wheel steering angle of the vehicle at each time based on the vehicle kinematic model and the vehicle position information comprises:
extracting time sequence data from the position information of the vehicle, obtaining a time sequence signal according to the time sequence data, and smoothing noise in the time sequence signal to obtain smoothed data;
And carrying out differential calculation on the position information of two adjacent time points based on the smooth data to obtain a vector included angle, and reversely pushing the front wheel corner of the vehicle at each time according to the vector included angle.
5. The method of claim 1, wherein the generating kalman filter optimization data based on the predicted a priori estimate of the current state of the vehicle and the corrected a posteriori estimate of the current state of the vehicle comprises:
establishing a priori estimate of the current state of the vehicle by using a preset time update equation, and predicting to obtain a priori estimate of the current state of the vehicle;
establishing a posterior estimation of the current state by using a priori estimated value of a preset measurement update equation and a measured variable, and correcting to obtain the posterior estimated value of the current state of the vehicle;
And obtaining the Kalman filtering optimization data according to the prior estimated value and the posterior estimated value.
6. The method of claim 5, wherein the predetermined time update equation is:
X(k|k-1)＝AX(k-1|k-1)+W(k-1)
P(k|k-1)＝AP(k-1|k-1)AT+Q(k-1)，
wherein X (k|k-1) is the prior estimated value of the Kalman filter at the moment k to the current state of the vehicle, X (k-1|k-1) is the posterior estimated value of the Kalman filter at the moment k-1 to the current state of the vehicle, P (k|k-1) is the prior estimated error covariance matrix, Q is the covariance matrix of process noise, R is the covariance matrix of measurement noise, and A is the state transition matrix.
7. The method of claim 5, wherein the predetermined measurement update equation is:
X(k|k)＝X(k|k-1)+K(k)[Z(k)-HX(k|k-1)]
P(k|k)＝[I-K(k)H]P(k|k-1)
K(k)＝P(k|k-1)HT[HP(k|k-1)HT+R(k)]-1，
Wherein X (K-1) is an a priori estimate of the vehicle motion state by the kalman filter at time K, X (K-K) is the a priori estimate of the state at time K, P (K-1) is the a priori estimate error covariance matrix, P (K-K) is the a priori estimate error covariance matrix, I is an identity matrix, K (K) is a kalman gain or mixing factor, Z (K) is an observation vector, and H is a measurement model matrix.
8. A digital mapping device of a vehicle, characterized by comprising:
the acquisition module is used for acquiring a motion video image of the vehicle and acquiring a vehicle kinematic model according to the motion video image;
The solving module is used for solving the front wheel corner of the vehicle at each moment according to the vehicle kinematic model and the position information of the vehicle; and
The mapping module is used for generating Kalman filtering optimization data based on the prior estimated value of the predicted vehicle current state and the posterior estimated value of the corrected vehicle current state, and optimizing the digital mapping of the vehicle in the information space according to the Kalman filtering optimization data and the front wheel steering angle of the vehicle at each moment to obtain a final digital mapping result.
9. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the digital mapping method of a vehicle as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor for implementing a digital mapping method of a vehicle according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311841728.2A CN117974724A (en) | 2023-12-28 | 2023-12-28 | Digital mapping method and device for vehicle, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311841728.2A CN117974724A (en) | 2023-12-28 | 2023-12-28 | Digital mapping method and device for vehicle, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117974724A true CN117974724A (en) | 2024-05-03 |
Family
ID=90846912
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311841728.2A Pending CN117974724A (en) | 2023-12-28 | 2023-12-28 | Digital mapping method and device for vehicle, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117974724A (en) |
-
2023
- 2023-12-28 CN CN202311841728.2A patent/CN117974724A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111442776B (en) | Method and equipment for sequential ground scene image projection synthesis and complex scene reconstruction | |
| CN110146869B (en) | Method and device for determining coordinate system conversion parameters, electronic equipment and storage medium | |
| CN104833370B (en) | System and method for mapping, positioning and pose correction | |
| CN107167826B (en) | Vehicle longitudinal positioning system and method based on variable grid image feature detection in automatic driving | |
| EP2053860A1 (en) | On-vehicle image processing device and its viewpoint conversion information generation method | |
| WO2018179616A1 (en) | Vehicle position deduction apparatus | |
| CN114323050B (en) | Vehicle positioning method and device and electronic equipment | |
| US20200353914A1 (en) | In-vehicle processing device and movement support system | |
| CN111522003B (en) | Vehicle positioning method and system, computer equipment, vehicle and storage medium | |
| CN110858405A (en) | Attitude estimation method, device and system of vehicle-mounted camera and electronic equipment | |
| CN111507130A (en) | Lane level positioning method and system, computer equipment, vehicle and storage medium | |
| CN114111775B (en) | Multi-sensor fusion positioning method and device, storage medium and electronic equipment | |
| JP6342104B1 (en) | Vehicle position estimation device | |
| US20220176989A1 (en) | High precision position estimation method through road shape classification-based map matching and autonomous vehicle thereof | |
| CN114485698B (en) | Intersection guide line generation method and system | |
| CN114264301A (en) | Vehicle-mounted multi-sensor fusion positioning method and device, chip and terminal | |
| CN115456898A (en) | Method and device for building image of parking lot, vehicle and storage medium | |
| CN111982132B (en) | Data processing method, device and storage medium | |
| CN114140533A (en) | Method and device for calibrating external parameters of camera | |
| CN113763504B (en) | Map updating method, system, vehicle-mounted terminal, server and storage medium | |
| US20210190509A1 (en) | Position estimating apparatus and position estimating method | |
| JP2018073275A (en) | Image recognition device | |
| Park et al. | Vehicle localization using an AVM camera for an automated urban driving | |
| CN111351497B (en) | Vehicle positioning method and device and map construction method and device | |
| CN111605481A (en) | Congestion car following system and terminal based on look around |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |