JP2021152906A - Method, device, appliance and storage medium for predicting vehicle locus - Google Patents

Abstract

To provide a method, a device, an appliance and a storage medium for predicting a vehicle locus, that are capable of improving accuracy and efficiency of vehicle locus prediction and reducing a cost.SOLUTION: A plurality of first historical position points in a first historical travelling time zone of a current vehicle are acquired, and the plurality of first historical position points are fitted to acquire a first fitting result; and a current position point of the current vehicle is acquired, and a travelling locus of the current vehicle is predicted based on the current position point and the first fitting result. The first history position point is acquired, the first fitting result is acquired; and the traveling locus of the current vehicle is predicted based on the current position point and the first fitting result.SELECTED DRAWING: Figure 1

Description

The present application relates to the field of computer technology, particularly to the field of vehicle safety technology, and specifically to vehicle trajectory prediction methods, devices, devices and storage media.

With the rapid development of the traffic industry, the number of vehicles on the road has increased dramatically, the traffic safety situation has become more severe, and drivers estimate the possibility of collision based on the trajectory of the vehicle while driving. It is difficult to do and poses a great threat to the personal safety of drivers and passengers.

Currently, when predicting a vehicle's travel trajectory, it is mainly predicted based on parameters such as the vehicle's handle, wheelbase and tread, or the distance and speed with the vehicle in front are detected using radar. Estimate the collision time.

However, the cost of radar is relatively high, and prediction based on vehicle parameters increases the dependence of the prediction process on the vehicle signal, the accuracy of the prediction result is low, and the prediction efficiency is not high.

The embodiments of the present application provide vehicle trajectory prediction methods, devices, devices and storage media to improve the accuracy and efficiency of vehicle trajectory prediction and reduce costs.

In the first aspect, the embodiments of the present application disclose a method of predicting a vehicle locus, which method is described as.
A step of acquiring a plurality of first historical position points in the first historical travel time zone of the current vehicle, fitting the plurality of first historical position points, and acquiring the first fitting result.
It includes a step of acquiring the current position point of the current vehicle and predicting the traveling locus of the current vehicle based on the current position point and the first fitting result.

In one embodiment of the above application, a plurality of first historical position points are fitted to obtain a first fitting result, and the current vehicle traveling locus is obtained based on the current position point and the first fitting result. Since the prediction does not need to depend on the signal of the vehicle, it has an advantage or a beneficial effect of reducing the prediction cost and improving the efficiency and accuracy of the trajectory prediction.

In addition, the vehicle trajectory prediction method according to the above embodiment of the present application may further have the following additional technical features.

Selectably, the first historical travel time zone is the historical travel time zone closest to the current time.
The length of time corresponding to the first historical travel time zone is larger than the preset time length threshold value, and / or the travel distance corresponding to the first historical travel time zone is the preset distance. Is greater than the threshold of.

One embodiment in the above application has an advantage or a beneficial effect of avoiding calculation of another invalid historical travel time zone and improving calculation accuracy and calculation efficiency by partitioning the range of the first historical travel time zone. Has.

The step of fitting the plurality of first historical position points and acquiring the first fitting result can be selected.
Steps to determine the first fitting equation used for fitting,
For each first historical position point, a step of determining at least one deformation equation corresponding to the first fitting equation based on a first preset transformation factor.
A step of determining the value of the unknown coefficient of the first fitting equation based on the coordinate value of each first historical position point and each of the above deformation equations.
A step of updating the first fitting equation using the value of the unknown coefficient and obtaining the first fitting result is included.

In one embodiment of the above application, the first fitting equation is transformed based on the first preset transformation factor, the unknown coefficient of the first fitting equation is determined based on the transformation equation, and the first fitting equation is determined. It has the advantage or beneficial effect of realizing the determination of the fitting equation and improving the calculation accuracy of the first fitting equation.

Selectably, the first preset transformation factor is the sequence number of the current first historical position point, the course angle corresponding to the current first historical position point, and the first historical position point. Includes at least one of the total number, the variance of the coordinate values in the first coordinate axis direction of each first historical position point, and the variance of the coordinate values in the second coordinate axis direction of each first historical position point. ..

In one embodiment of the above application, the expressive power and calculation accuracy of the first fitting equation can be improved by determining the first preset deformation factor based on the information of the first historical position point. It has the advantage or beneficial effect of being able to.

The step of predicting the traveling locus of the current vehicle based on the current position point and the first fitting result can be selected.
The step of determining the radius of curvature corresponding to the current position point based on the first fitting result,
This includes a step of determining a locus arc based on the current position point and the radius of curvature, and using the locus arc as the predicted running locus of the current vehicle.

One embodiment in the above application has an advantage or a beneficial effect of improving the prediction accuracy of the traveling locus of the vehicle by determining the traveling locus of the vehicle based on the radius of curvature.

Selectably, after the step of predicting the running locus of the current vehicle based on the current position point and the first fitting result, the method
A step of acquiring the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the second historical travel time zone, and
A step of fitting the distance to the current vehicle at each time and obtaining a second fitting result.
Based on the second fitting result, a step of determining the current distance and the current speed of the vehicle in front and the current vehicle, and
Further including a step of determining the collision time between the preceding vehicle and the current vehicle based on the current distance and the current speed, and determining whether or not to issue an early collision warning based on the collision time. ..

In one embodiment of the above application, the distance between the vehicle in front and the current vehicle at each time in the second historical travel time zone is fitted to determine the second fitting result, and the second fitting result is determined based on the second fitting result. By determining the current distance and current speed between the vehicle in front and the current vehicle, the accuracy and efficiency of calculating the current distance and current speed between the vehicle in front and the current vehicle can be improved, and in addition, collision prediction can be performed. It has the advantage or beneficial effect of improving accuracy.

The step of optionally fitting the distance to the current vehicle at each time and obtaining a second fitting result is:
Steps to determine the second fitting equation used for fitting,
For each time, a step of determining at least one transformation equation corresponding to the second fitting equation based on a second preset transformation factor.
A step of determining the value of the unknown coefficient of the second fitting equation based on the distance of the vehicle in front to the current vehicle at each time and each deformation equation corresponding to the second fitting equation.
A step of updating the second fitting equation with the value of the unknown coefficient of the second fitting equation and obtaining the second fitting result is included.

In one embodiment of the above application, the second fitting equation is modified based on the second preset transformation factor, the unknown coefficient of the second fitting equation is determined based on the transformation equation, and the second fitting is performed. It has the advantage or beneficial effect of realizing the determination of the equation and improving the calculation accuracy of the second fitting equation.

Selectable, the second preset transformation factor is
It includes at least one of a sequence number of the current time, a total number of times, a variance of each time, and a variance of the distance of the vehicle in front to the current vehicle at each time.

One embodiment in the above application has the advantage or beneficial effect of improving the expressiveness and calculation accuracy of the second fitting equation based on the second preset transformation factor.

Selectably, the method is performed prior to the step of acquiring the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the second historical travel time zone.
Determines whether the current distance between the vehicle in front of the current vehicle and the predicted travel locus of the current vehicle is within a preset range, and if so, a second historical travel time. It further includes a step of triggering the execution of an operation to obtain the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the band.

In one embodiment of the above application, it is first determined whether or not the current distance between the vehicle in front and the traveling locus of the current vehicle is within a preset range, and if so, a collision prediction operation. By doing so, it has the advantage or beneficial effect of improving prediction accuracy, avoiding errors due to excessive computational pressure, reducing invalid early warnings, and improving the user experience.

Selectably, the step of acquiring the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the second historical travel time zone is
A step of acquiring an image taken by the image pickup device of the current vehicle at each time of the second historical driving time zone, and
A step of determining the position information of the vehicle in front of the current vehicle at each time by performing image recognition on each of the images, and
It includes a step of determining the distance of the vehicle in front to the current vehicle at each time based on the position information of the vehicle in front at each time and the internal and external parameters of the imaging device.

In one embodiment of the above application, the position information of the vehicle in front at each time is acquired by image recognition, and the distance of the vehicle in front to the current vehicle at each time is determined based on the parameters of the calibrated imaging device. This has the advantage or beneficial effect of solving the problem of high cost due to the use of the radar system in the prior art and improving the usage experience.

Selectably, the internal parameters include the light center and the ratio of focal length to pixel size.
The external parameters include the posture angle of the imaging device and the height of the imaging device from the ground.

One embodiment in the above application has the advantage or beneficial effect of improving the efficiency of calculating the position of the vehicle in front and the distance to the current vehicle and accurately recording the sequence number of the position and distance of the vehicle in front.

In the second aspect, the embodiments of the present application disclose a vehicle trajectory prediction device, which is a device.
A first for acquiring a plurality of first historical position points in a first historical travel time zone of a current vehicle, fitting the plurality of first historical position points, and acquiring a first fitting result. Fitting result acquisition module and
It includes a travel locus prediction module for acquiring the current position point of the current vehicle and predicting the travel locus of the current vehicle based on the current position point and the first fitting result.

In a third aspect, the embodiments of the present application disclose electronic devices.
With at least one processor
Includes a memory communicatively connected to the at least one processor.
The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle trajectory prediction method of the present application. Will be done.

In a fourth aspect, an embodiment of the present application discloses a non-temporary computer-readable storage medium in which a computer instruction is stored, and the computer instruction is a method of predicting a vehicle trajectory of the present application to the computer. To execute.
In a fifth aspect, an embodiment of the present application discloses a computer program, which causes the computer to execute the method of predicting a vehicle trajectory of the present application.

In one embodiment of the above application, the first historical position point is fitted, the first fitting result is acquired, and the traveling locus of the current vehicle is predicted based on the current position point and the first fitting result. This has the advantage or beneficial effect of reducing the prediction cost and improving the efficiency and accuracy of trajectory prediction because it does not need to depend on the vehicle signal.

Other effects of the above selectable embodiments will be described below with reference to specific examples.

The drawings are used to better understand the proposed technology and are not intended to limit the application.
It is a schematic flowchart of the vehicle locus prediction method which concerns on 1st Example of this application. It is a schematic flowchart of the vehicle locus prediction method which concerns on the 2nd Example of this application. It is the schematic of the preset range which concerns on the 2nd Example of this application. It is a schematic flowchart of the trajectory prediction and the collision warning which concerns on the 2nd Example of this application. It is a schematic structural drawing of the vehicle locus prediction device which concerns on 3rd Example of this application. It is a block diagram of the electronic device for realizing the method of predicting the vehicle locus according to the Example of this application.

Hereinafter, exemplary examples of the present application are described in combination with the drawings, which include various details of the examples of the present application for ease of understanding, which are merely exemplary. Should be considered. Accordingly, one of ordinary skill in the art can make various changes and amendments to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and brevity, the following description omits the description of well-known functions and structures.

1st Example FIG. 1 is a schematic flowchart of a vehicle trajectory prediction method provided by the first embodiment of the present application, and the present embodiment is used when predicting the trajectory of a traveling vehicle. The method can be performed by a vehicle trajectory predictor, which can be implemented in software and / or hardware and can be integrated into an electronic device, which may be a device such as an in-vehicle terminal. As shown in FIG. 1, the vehicle trajectory prediction method provided by this embodiment can include S110 and S120.

S110, a plurality of first history position points in the first history travel time zone of the current vehicle are acquired, and the plurality of first history position points are fitted to obtain the first fitting result.

Here, by fusing the output results of GPS (Global Positioning System) and IMU (Inertial Measurement Unit), a plurality of vehicles traveled in the current vehicle during the first historical travel time zone. It is possible to acquire the position points of the above and determine the plurality of position points as the first history position points.

In this embodiment, the first historical travel time zone is selectably the historical travel time zone closest to the current time, and the length of time corresponding to the first historical travel time zone is preset. The travel distance corresponding to the first historical travel time zone is larger than the preset distance threshold. For example, when the preset time length threshold is 10 s and the preset distance threshold is 60 m, the position point of the current vehicle at each time of 11 seconds before the current time is set to the first position. The current position point of the vehicle at each time in the time zone before the current time when the mileage is 65 m is acquired as the first historical position point, or the current position point of the vehicle is acquired as the first historical position point. The current position point of the vehicle at each time of 15 seconds before the time of is acquired as the first historical position point, and the mileage of the vehicle exceeds 60 m in this 15 s.

Specifically, the current vehicle may travel within a plurality of time zones, and the historical travel time zone closest to the current time is the first historical travel time zone. For example, the current time is 15:40 on March 13th, and the current vehicle history travel time zone is from 17:20 to 17:40 on March 12th and 9:30 to 10:20 on March 13th. When is included, the first historical travel time zone is the time zone of 9:30 to 10:20 on March 13. The time length threshold and / or the distance threshold can be preset, and the first historical travel time zone confirmation requirement is that the corresponding time length is greater than the preset time length threshold. If the length of time corresponding to the historical travel time zone is equal to or less than a preset time length threshold value, the historical travel time zone is not the first historical travel time zone. The first requirement for confirming the historical travel time zone may be that the corresponding mileage is larger than the preset distance threshold value, and the mileage in the historical travel time zone is equal to or less than the preset distance threshold value. , The historical travel time zone is not the first historical travel time zone. For example, the preset time length threshold is 15 minutes, the current time is 15:40 on March 13th, and the current vehicle history travel time zone is 17:20 on March 12th. When ~ 17:40 and 9:30 to 9:40 on March 13 are included, the first historical travel time zone is the time zone from 17:20 to 17:40 on March 12. The beneficial effect of such a setting is to avoid the calculation of other invalid historical travel time zones by partitioning the range of the first historical travel time zone, and to improve the calculation accuracy and the calculation efficiency.

In this embodiment, the steps of selectively fitting a plurality of first historical position points and obtaining the first fitting result include a step of determining a first fitting equation used for fitting and each of the steps. A step of determining at least one deformation equation corresponding to the first fitting equation based on a first preset transformation factor for the first historical position point, and the coordinates of each first historical position point. The step of determining the value of the unknown coefficient of the first fitting equation based on the value and each transformation equation, and updating the first fitting equation using the value of the unknown coefficient to obtain the first fitting result. Including steps and.

Specifically, after acquiring a plurality of first history position points, the plurality of first history position points are fitted. The first history position point can be expressed as (x, y, θ), where x represents the coordinate value of the current first history position point in the first coordinate axis direction, and y is the current first history position point. The coordinate value of the history position point 1 in the second coordinate axis direction is represented, θ represents the course angle of the current first history position point, and x and y both represent the position information of the current vehicle. First, the first fitting equation used for fitting is determined, and here, in the first fitting equation, the coordinate value in the first coordinate axis direction of the first historical position point is set as an independent variable, and the first fitting equation is determined. The coordinate value in the second coordinate axis direction of the history position point is used as the dependent variable. The current position of the current vehicle can be the coordinate origin, the first coordinate axis direction is the x-axis direction, the x-axis direction is the direction perpendicular to the central axis of the current vehicle, and the second coordinate axis direction is. In the y-axis direction, the y-axis direction is the direction of the central axis of the current vehicle. The first fitting equation is determined based on the values of X and y, and the first fitting equation may be a quadratic equation or a higher order equation. For example, considering the stability and expressiveness of the equation, the first fitting equation may be determined as a cubic equation and is expressed as y = ax ³ + bx ² + cx + d, where a, b, c and d is an unknown coefficient.

として決定すると、第１の変形方程式は

として表されることができ、ここで、ｉは、現在の第１の履歴位置点の順序番号であり、Ｎは、第１の履歴位置点の数であり、ｘ_ｉは、現在の第１の履歴位置点の第１の座標軸方向の座標値であり、ｙ_ｉは、現在の第１の履歴位置点の第２の座標軸方向の座標値であり、σ２ｐは、ｘ_ｉの分散である。第１の変形方程式に基づいて第２の変形方程式を決定することができ、例えば、第１の変形方程式に対して一次導関数を行い、第２の変形方程式は

として表されることができ、ここで、σ２θは、ｙ_ｉの分散である。各第１の履歴位置点の座標値及び各変形方程式を決定し、各第１の履歴位置点の座標値を各変形方程式に代入して、第１のフィッティング方程式の未知係数の値を算出することができる。未知係数の値を第１のフィッティング方程式に追加し、第１のフィッティング方程式を更新し、第１のフィッティング結果を取得する。第１のフィッティング方程式をフィッティングする際に、第１の履歴位置点の順序番号の最初の位置に低い重みを使用でき、後の順序番号の第１の履歴位置点に使用される重みは高くなることができ、ＴＴＣ（Ｔｉｍｅ−Ｔｏ−Ｃｏｌｌｉｓｉｏｎ、衝突時間）推定の安定性及び予測精度を向上させる。このような設定の有益な効果は、第１のフィッティング方程式を変形して、変形方程式を取得することにより、第１のフィッティング結果がより正確になり、車両軌跡予測の精度を向上させることである。 A first preset transformation factor is preset, the first fitting equation is transformed based on the first preset transformation factor, and at least one transformation equation for each first historical position point is obtained. do. The weighting of the deformation equation can be determined based on the first preset transformation factor to obtain the weighted equation for least squares fitting. For example, the first preset transformation factor

The first transformation equation is

Where i is the sequence number of the current first history position point, N is the number of first history position points, and x _i is the current first history position point. Is the coordinate value of the historical position point in the first coordinate axis direction, y _i is the coordinate value of the current first historical position point in the second coordinate axis direction, and σ2p is the dispersion of _{x i.} The second deformation equation can be determined based on the first deformation equation, for example, a linear derivative is performed on the first deformation equation, and the second deformation equation is

Where σ 2 θ is the variance of _{y i.} The coordinate value of each first historical position point and each deformation equation are determined, and the coordinate value of each first history position point is substituted into each deformation equation to calculate the value of the unknown coefficient of the first fitting equation. be able to. The value of the unknown coefficient is added to the first fitting equation, the first fitting equation is updated, and the first fitting result is obtained. When fitting the first fitting equation, a lower weight can be used for the first position of the sequence number of the first history position point, and a higher weight is used for the first history position point of the later sequence number. It can improve the stability and prediction accuracy of TTC (Time-To-Collision, collision time) estimation. The beneficial effect of such a setting is that by transforming the first fitting equation to obtain the deformation equation, the first fitting result becomes more accurate and the accuracy of vehicle trajectory prediction is improved. ..

In this embodiment, the first preset transformation factor is selectively the sequence number of the current first historical position point, the course angle corresponding to the current first historical position point, and the first. Of the total number of historical position points, the variance of the coordinate values of each first historical position point in the first coordinate axis direction, and the variance of the coordinate values of each first historical position point in the second coordinate axis direction. Includes at least one.

には、現在の第１の履歴位置点の順序番号、第１の履歴位置点の総数及び各第１の履歴位置点の第１の座標軸方向の座標値の分散が使用される。ここで、分散の値は、予め設定されてもよいし、第１の履歴位置点のシーケンスを二次差分した後、差分結果の二乗和の平均値を算出してもよい。このような設定の有益な効果は、第１のフィッティング方程式の未知係数の正確性を向上させ、さらに、第１のフィッティング方程式の表現能力及び計算精度を向上させることである。 Specifically, the first preset transformation factor can be determined based on one or more pieces of information about the first historical position point, for example, the first preset transformation factor.

Is used for the sequence number of the current first historical position point, the total number of the first historical position points, and the variance of the coordinate values of each first historical position point in the first coordinate axis direction. Here, the value of the variance may be set in advance, or the average value of the sum of squares of the difference results may be calculated after the sequence of the first history position points is secondarily differentiated. The beneficial effect of such a setting is to improve the accuracy of the unknown coefficients of the first fitting equation, and further to improve the expressiveness and calculation accuracy of the first fitting equation.

S120, the current position point of the current vehicle is acquired, and the traveling locus of the current vehicle is predicted based on the current position point and the first fitting result.

Here, the current vehicle is in a running state, and the current position point of the current vehicle can be acquired based on the output results of GPS and IMU, and the current position point can be acquired (x ₀ , It is represented by y _0).

In this embodiment, the step of selectively predicting the current vehicle trajectory based on the current position point and the first fitting result corresponds to the current position point based on the first fitting result. It includes a step of determining the radius of curvature and a step of determining a locus arc based on the current position point and radius of curvature and using the locus arc as the predicted current vehicle travel locus.

Specifically, the radius of curvature R is acquired based on the first fitting result, an _{arc is created at (x 0} , y ₀ ) with R as the radius, the locus arc line is acquired, and the locus arc line is obtained. Is the predicted running locus of the current vehicle. A beneficial effect of such a setting is to improve the prediction accuracy and efficiency of the vehicle's travel locus by determining the vehicle's travel locus based on the radius of curvature and the current position point.

In one embodiment of the above application, the first historical position point is fitted, the first fitting result is acquired, and the traveling locus of the current vehicle is predicted based on the current position point and the first fitting result. This has the advantage or beneficial effect of reducing the prediction cost and improving the efficiency and accuracy of trajectory prediction because it does not need to depend on the vehicle signal.

Second Example FIG. 2 is a schematic flowchart of a vehicle trajectory prediction method provided by the second embodiment of the present application, which is optimized based on the above embodiment and is in motion. Used to give early collision warnings to a vehicle, the method can be performed by a vehicle trajectory predictor, which can be implemented in software and / or hardware and integrated into electronic devices such as in-vehicle terminals. .. As shown in FIG. 2, the vehicle trajectory prediction method provided by this embodiment includes S210 to S260.

S210, a plurality of first history position points in the first history travel time zone of the current vehicle are acquired, and the plurality of first history position points are fitted to obtain the first fitting result.

S220, the current position point of the current vehicle is acquired, and the traveling locus of the current vehicle is predicted based on the current position point and the first fitting result.

S230, Acquires the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the second historical travel time zone.

Here, the second historical travel time zone may be a preset time zone. For example, when the second historical travel time zone is preset as 3 seconds, the time is 3 seconds before the current time. The distance of the vehicle in front of the current vehicle to the current vehicle at each time of the band may be acquired, and a plurality of vehicles may be in front of the vehicle.

In this embodiment, optionally, the step of acquiring the distance of the vehicle in front of the current vehicle to the current vehicle at each time in the second historical travel time zone is currently at each time in the second historical travel time zone. A step of acquiring an image taken by the image pickup device of the vehicle, a step of determining the position information of the vehicle in front of the current vehicle at each time by performing image recognition for each image, and a step of each of the vehicles in front. It includes a step of determining the distance of the vehicle in front to the current vehicle at each time based on the position information at the time and the internal and external parameters of the imaging device.

Specifically, an image of the vehicle in front can be taken by an imaging device attached to the current vehicle, and images at each time of the second historical traveling time zone of the vehicle in front can be acquired. Image recognition is performed on each captured image to determine the position information at each time of the second historical traveling time zone of the vehicle in front of the current vehicle, and this position information is used in the corresponding image. It can include the position information of the detection frame of the vehicle in front.

Before determining the distance of the vehicle in front to the current vehicle at each time, the internal parameters of the imaging device can be preset in the system and the external parameters can be calibrated online. The external parameter calibration method first detects an adjacent preset number of lanes in a continuous multi-frame image of the current vehicle and calculates the fitting parameters corresponding to each lane in the image of each frame. Subsequently, the external parameters of the image pickup device may be calibrated based on the fitting parameters corresponding to each lane in each frame image and the predetermined internal parameters of the image pickup device. After determining the internal and external parameters of the image pickup device, the distance of the vehicle ahead to the current vehicle at each time is determined based on the position information of the vehicle in front at each time and the internal and external parameters of the image pickup device. .. The beneficial effect of such a setting is that image recognition acquires position information of the vehicle in front at each time and determines the distance of the vehicle in front to the current vehicle at each time based on the parameters of the calibrated imaging device. By doing so, the problem of high cost due to determining the state of the vehicle in front using the radar system in the prior art is solved, and the price / performance ratio is improved.

In this embodiment, the method is optionally performed before the step of obtaining the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the second historical travel time zone. Determines whether the current distance to the predicted current vehicle's travel locus is within a preset range, and if so, the current vehicle at each time in the second historical travel time zone. It further includes a step that triggers the execution of an operation to obtain the distance of the vehicle in front of the current vehicle with respect to.

Specifically, after determining the traveling locus of the current vehicle, the route of the traveling locus is set as the center line, and the route is expanded to both sides of the traveling locus at a preset angle, and the vehicle in front of the current vehicle is preset. Get the range. Calculate the current distance between the vehicle in front and the current vehicle's trajectory, and explain that if this current distance is within a preset range, the vehicle in front and the current vehicle may collide. It is necessary to acquire the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the second historical traveling time zone. For example, the range on both sides of the current vehicle's travel locus is expanded by 5 ° to calculate the current distance between the vehicle in front and the current vehicle's travel locus, and this current distance is less than (2 + ytan5). In this case, there is a risk that the vehicle in front and the current vehicle collide with each other, where y is the y-axis coordinate value of the vehicle in front. FIG. 3 is a schematic view of a preset range. The solid line in the figure represents the predicted trajectory of the current vehicle, the dotted line is the boundary of the expanded preset range, and when the vehicle in front is located within the preset range, the second historical travel time Calculate the distance of the vehicle in front to the current vehicle at each time in the band. The beneficial effect of such a setting is to first determine if the current distance between the vehicle ahead and the current vehicle's trajectory is within a preset range, and if so, collision prediction. By performing this operation, the prediction accuracy is improved, errors due to excessive calculation pressure are avoided, invalid early warnings are reduced, and the user experience is improved.

In this embodiment, optionally, the internal parameters include the light center and the ratio of the focal length to the pixel size, and the external parameters include the attitude angle of the imaging device and the height of the imaging device from the ground.

Specifically, it determines the internal parameters of the imaging device, calibrates the external parameters, improves the efficiency of calculating the position and distance of the vehicle in front with respect to the current vehicle, and accurately records the sequence number of the position and distance of the vehicle in front. do.

S240, the distance to the current vehicle at each time is fitted to obtain the second fitting result.

Here, the position information at each time of the second historical traveling time zone of the vehicle in front is determined based on the imaging device, and the distance to the current vehicle at each time is acquired. The second fitting result is acquired based on the distance to the current vehicle at each time.

In this embodiment, the steps of optionally fitting the distance to the current vehicle at each time and obtaining the second fitting result are the step of determining the second fitting equation used for the fitting and each of them. A step of determining at least one transformation equation corresponding to the second fitting equation based on a second preset transformation factor with respect to the time, and the distance of the vehicle in front to the current vehicle at each time and the second. Update the second fitting equation with the steps to determine the value of the unknown coefficient of the second fitting equation and the value of the unknown coefficient of the second fitting equation based on each transformation equation corresponding to the fitting equation of And includes a step of obtaining a second fitting result.

であってもよく、第２のフィッティング方程式の変形方程式は

として表されることができ、ここで、jは現在の時刻の順序番号であり、Ｍは時刻の総数であり、ｔ_jはｊ番目の時刻であり、ｄ_jはｊ番目の時刻における現在の車両に対する前方車両の距離であり、σ２Ｔはｔ_jの分散である。第２のフィッティング方程式の変形方程式に基づいて他の変形方程式を取得することも可能であり、例えば、第２のフィッティング方程式の変形方程式に対して一次導関数を行うことができる。各第２の履歴位置点の座標値及び各変形方程式に基づいて、各時刻の時点及び現在の車両に対する前方車両の距離を各変形方程式に代入して、第２のフィッティング方程式の未知係数の値を算出することができる。未知係数の値を第２のフィッティング方程式に追加し、第２のフィッティング方程式を更新し、第２のフィッティング結果を取得する。第２のフィッティング方程式をフィッティングする際に、第２の履歴位置点の順序番号の最初の位置に低い重みを使用でき、後の順序番号の第２の履歴位置点に使用される重みは高くなることができ、ＴＴＣ推定の安定性及び予測精度を向上させる。このような設定の有益な効果は、第２の予め設定された変形因数に基づいて第２のフィッティング方程式を変形し、変形方程式に基づいて第２のフィッティング方程式の未知係数を決定することにより、未知係数の計算精度を向上させ、第２のフィッティング方程式を決定することを実現し、さらに、車両軌跡予測の精度を向上させることである。 Specifically, the position information and each time information at each time in the second historical travel time zone can be represented as the second historical position point, and the second historical position point can be represented as (t, d). .. t is each time in the second historical travel time zone, and d is the distance of the vehicle ahead to the current vehicle at each time in the second historical travel time zone. The time corresponding to the second historical position point is an independent variable, that is, the coordinate value t in the first coordinate axis direction, and the distance of the second historical position point with respect to the current vehicle is the dependent variable, that is, the coordinates in the second coordinate axis direction. The value d determines a second fitting equation used for fitting. The second fitting equation may be a quadratic or higher order equation, for example, d = et ² + ft + g, where e, f and g are unknown coefficients of the second fitting equation. A second preset transformation factor is preset and the second fitting equation is transformed based on the second preset transformation factor to obtain at least one weighted transformation equation for least squares fitting. get. For example, the second preset transformation factor is

The transformation equation of the second fitting equation may be

Where j is the sequence number of the current time, M is the total number of times, t _j is the jth time, and d _j is the current time at the jth time. It is the distance of the vehicle in front with respect to the vehicle, and σ2T is the variance of _{t j.} It is also possible to obtain other deformation equations based on the deformation equation of the second fitting equation, for example, a linear derivative can be performed on the deformation equation of the second fitting equation. Based on the coordinate values of each second historical position point and each deformation equation, the value of the unknown coefficient of the second fitting equation is substituted by substituting the distance of the vehicle in front with respect to the time point and the current vehicle into each deformation equation. Can be calculated. The value of the unknown coefficient is added to the second fitting equation, the second fitting equation is updated, and the second fitting result is obtained. When fitting the second fitting equation, a lower weight can be used for the first position of the sequence number of the second history position point, and a higher weight is used for the second history position point of the later sequence number. It can improve the stability and prediction accuracy of TTC estimation. The beneficial effect of such a setting is by transforming the second fitting equation based on a second preset transformation factor and determining the unknown coefficients of the second fitting equation based on the transformation equation. It is to improve the calculation accuracy of the unknown coefficient, to determine the second fitting equation, and further to improve the accuracy of vehicle trajectory prediction.

In this embodiment, the second preset transformation factor, optionally, is the sequence number of the current time, the total number of times, the variance of each time, and the distance of the vehicle in front to the current vehicle at each time. Includes at least one of the variances of.

S250, the current distance and the current speed between the vehicle in front and the current vehicle are determined based on the second fitting result.

Here, after determining the second fitting result, the current time t ₀ is substituted into the second fitting equation to calculate the current distance between the current vehicle and the vehicle ahead at _{t 0 time.} A first-order derivative is applied to the second fitting result, and t ₀ is substituted into the derivative equation to obtain the current speed of the vehicle in front at _{t 0 time.}

Based on S260, the current distance and the current speed, the collision time between the vehicle in front and the current vehicle is determined, and whether or not to issue an early collision warning is determined based on the collision time.

Here, after determining the current distance and the current speed between the vehicle in front and the current vehicle, the collision time between the vehicle in front and the current vehicle is calculated based on the speed equation. If the time threshold can be set in advance and the collision time is less than the time threshold, there is a high possibility that the vehicle in front and the current vehicle will collide, and warning information is transmitted to the current vehicle, and the warning information is a voice reminder. , Vibration reminder and visual reminder. FIG. 4 is a schematic flowchart of trajectory prediction and collision warning. A fusion positioning module that includes GPS, IMU, and CAN buses acquires a plurality of first historical position points of the current vehicle and the current position of the current vehicle in the first historical travel time zone, and obtains the current position of the current vehicle with respect to the current vehicle. To predict the trajectory. The camera's external parameters are calibrated online, tracking and detecting at least one vehicle in front of the current vehicle based on the camera's internal and external parameters, and the vehicle in front is preset to the current vehicle's trajectory. Determines whether or not it is within range, makes a TTC estimate if the vehicle in front is within a preset range of the current vehicle's travel trajectory, and warns if the collision time is less than the time threshold. The system sends warning information. By using TTC estimation, cost is effectively reduced and the price / performance ratio of early warning is improved.

In one embodiment of the above application, the first historical position point is acquired, the first fitting result is acquired, and the traveling locus of the current vehicle is predicted based on the current position point and the first fitting result. As a result, it is not necessary to depend on the signal of the vehicle, so that the prediction cost is reduced and the efficiency and accuracy of trajectory prediction are improved. The current distance and the current speed between the vehicle in front and the current vehicle by determining the second fitting result based on the distance between the vehicle in front and the current vehicle at each time of the second historical travel time zone. It has the advantage or beneficial effect of improving the computational efficiency of the vehicle, reducing invalid collision early warnings, and improving the accuracy of collision prediction.

Third Example FIG. 5 is a schematic structural diagram of the vehicle locus prediction device provided by the third embodiment of the present application, and implements the vehicle locus prediction method provided by the embodiment of the present application. It can have functional modules and beneficial effects that correspond to the implementation of the method. As shown in FIG. 5, the device 500 is
A first for acquiring a plurality of first historical position points in a first historical travel time zone of a current vehicle, fitting a plurality of first historical position points, and acquiring a first fitting result. Fitting result acquisition module 501 and
It includes a travel locus prediction module 502 for acquiring the current position point of the current vehicle and predicting the travel locus of the current vehicle based on the current position point and the first fitting result.

Selectably, the first historical travel time zone is the historical travel time zone closest to the current time, and
The length of time corresponding to the first historical travel time zone is larger than the preset time length threshold value, and / or the travel distance corresponding to the first historical travel time zone is the preset distance. Is greater than the threshold of.

Selectably, the first fitting result acquisition module 501
A first fitting equation determination unit for determining the first fitting equation used for fitting, and a first fitting equation determination unit.
For each first historical position point, a deformation equation determination unit for determining at least one deformation equation corresponding to the first fitting equation based on a first preset transformation factor.
An unknown coefficient determination unit for determining the value of the unknown coefficient of the first fitting equation based on the coordinate value of each first historical position point and each deformation equation.
It includes a first fitting result acquisition unit for updating the first fitting equation with the value of the unknown coefficient and acquiring the first fitting result.

Selectable, the first preset transformation factor is
The sequence number of the current first history position point, the course angle corresponding to the current first history position point, the total number of the first history position points, and the first coordinate axis of each first history position point. It includes at least one of a variance of the coordinate values in the direction and a variance of the coordinate values in the second coordinate axis direction of each first historical position point.

Selectable, the travel locus prediction module 502
A radius of curvature determination unit for determining the radius of curvature corresponding to the current position point based on the first fitting result,
The locus arc line determination unit for determining the locus arc line based on the current position point and the radius of curvature and making the locus arc line the predicted running locus of the current vehicle is included.

Selectable, the device
A distance acquisition module for acquiring the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the second historical travel time zone, and
A second fitting result acquisition module for fitting the distance to the current vehicle at each time and acquiring a second fitting result,
A current speed determination module for determining the current distance and current speed between the vehicle in front and the current vehicle based on the second fitting result, and
A collision early warning determination module for determining the collision time between the vehicle in front and the current vehicle based on the current distance and the current speed, and determining whether or not to issue an early collision warning based on the collision time. Including further.

Selectable, the second fitting result acquisition module, specifically,
Determine the second fitting equation used for fitting,
For each time, at least one transformation equation corresponding to the second fitting equation is determined based on the second preset transformation factor.
Based on the distance of the vehicle in front to the current vehicle at each time and each deformation equation corresponding to the second fitting equation, the value of the unknown coefficient of the second fitting equation is determined.
The value of the unknown coefficient of the second fitting equation is used to update the second fitting equation and obtain the second fitting result.

Selectable, the second preset transformation factor is
Includes at least one of the sequence number of the current time, the total number of times, the variance of each time, and the variance of the distance of the vehicle in front to the current vehicle at each time.

Selectable, the device
Determines if the current distance between the vehicle in front of the current vehicle and the predicted travel trajectory of the current vehicle is within a preset range, and if so, in the second historical travel time zone. It further includes a preset range determination module for triggering the execution of an operation to obtain the distance of the vehicle in front of the current vehicle to the current vehicle at each time.

Selectable, distance acquisition module, specifically,
The image taken by the image pickup device of the current vehicle is acquired at each time of the second historical driving time zone, and the image is acquired.
By performing image recognition for each image, the position information of the vehicle in front of the current vehicle at each time is determined.
The distance of the vehicle in front to the current vehicle at each time is determined based on the position information of the vehicle in front at each time and the internal and external parameters of the imaging device.

Selectably, the internal parameters include the light center and the ratio of focal length to pixel size.
External parameters include the attitude angle of the imaging device and the height of the imaging device from the ground.

In one embodiment of the above application, the first historical position point is acquired, the first fitting result is acquired, and the traveling locus of the current vehicle is predicted based on the current position point and the first fitting result. This has the advantage or beneficial effect of reducing the prediction cost and improving the efficiency and accuracy of trajectory prediction because it does not need to depend on the vehicle signal.

According to the embodiments of the present application, the present application further provides electronic devices and readable storage media.
According to an embodiment of the present application, the present application provides a computer program, which causes a computer to execute the vehicle trajectory prediction method provided by the present application.

As shown in FIG. 6, it is a block diagram of an electronic device of a method of predicting a vehicle locus according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices such as personal digital processors, mobile phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the description and / or the required realization of this application.

As shown in FIG. 6, the electronic device includes one or more processors 601 and memory 602, and an interface for connecting each component including a high-speed interface and a low-speed interface. The components are interconnected by different buses and can be mounted on a common motherboard or otherwise mounted as needed. The processor can process instructions executed within the electronic device, and the instructions are stored in memory to display GUI graphic information on an external input / output device (eg, a display device coupled to an interface). Contains instructions stored in or in memory. In other embodiments, a plurality of processors and / or a plurality of buses can be used together with a plurality of memories, if desired. Similarly, a plurality of electronic devices can be connected, and each electronic device can provide some necessary operations (for example, a server array, a group of blade servers, or a multiprocessor system). .. In FIG. 6, one processor 601 is taken as an example.

Memory 602 is a non-temporary computer-readable storage medium provided by this application. Here, the memory stores instructions that can be executed by at least one processor so that at least one processor executes the vehicle trajectory prediction method provided by the present application. The non-temporary computer-readable storage medium of the present application stores computer instructions for causing the computer to execute the vehicle trajectory prediction method provided by the present application.

The memory 602 is a non-temporary computer-readable storage medium, such as a program instruction / module corresponding to the vehicle trajectory prediction method in the embodiment of the present application, a non-temporary software program, a non-temporary computer. Store executable programs and modules. Processor 601 executes various functional applications and data processing of the server by executing non-temporary software programs, instructions and modules stored in memory 602, i.e. the vehicle trajectory in the embodiment of the above method. Realize the prediction method of.

The memory 602 can include a storage program area and a storage data area, where the storage program area can store an operating system, an application program required for at least one function, and the storage data area is a storage data area. It is possible to store data created by using an electronic device for predicting a vehicle trajectory. The memory 602 can also include fast random access memory and can further include non-temporary memory, eg, at least one magnetic disk storage device, flash memory device, or other non-temporary solid. It is a state storage device. In some embodiments, the memory 602 can selectively include memory configured remotely with respect to the processor 601 and these remote memories can be used in electronic devices for vehicle trajectory prediction methods via a network. Can be connected. Examples of the above networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device of the vehicle trajectory prediction method may further include an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603, and the output device 604 can be connected via a bus or other method, and in FIG. 6, the connection via the bus is taken as an example.

The input device 603 can receive the input numerical or character information and generate a key signal input relating to user setting and function control of the electronic device of the vehicle trajectory prediction method, for example, a touch screen, a key pad, a mouse. , Trackpads, touchpads, pointing sticks, one or more mouse buttons, trackballs, joysticks and other input devices. The output device 604 can include a display device, an auxiliary lighting device (eg, LED), a tactile feedback device (eg, a vibration motor), and the like. The display device can include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch screen.

Various embodiments of the systems and techniques described herein include digital electronic circuit systems, integrated circuit systems, application specific ASICs (ASICs), computer hardware, firmware, software, and / or them. It can be realized by the combination of. These various embodiments may be implemented in one or more computer programs, the one or more computer programs being executed and / or interpreted in a programmable system including at least one programmable processor. The programmable processor may be a dedicated or general purpose programmable processor, receiving data and instructions from a storage system, at least one input device, and at least one output device, and delivering the data and instructions to the storage system. It can be transmitted to the at least one input device and the at least one output device.

These computing programs (also called programs, software, software applications, or code) can include programmable processor machine instructions, high-level process and / or object-oriented programming languages, and / or assembly / machine languages. You can implement these computing programs at. As used herein, the terms "machine readable medium" and "computer readable medium" are any computer program products, devices for providing machine instructions and / or data to programmable processors. And / or devices (eg, magnetic disks, optical disks, memories, programmable logic devices (PLDs)), including machine-readable media that receive machine instructions, which are machine-readable signals. The term "machine readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

To provide interaction with the user, the systems and techniques described herein can be implemented on a computer, which computer is a display device for displaying information to the user (eg, a CRT (cathode line tube)). ) Or LCD (liquid crystal display) monitor) and a keyboard and pointing device (eg, mouse or trackball), the user can provide input to the computer by the keyboard and the pointing device. Other types of devices can also provide interaction with the user, eg, the feedback provided to the user is any form of sensing feedback (eg, visual feedback, auditory feedback, or tactile feedback). It is also possible to receive input from the user in any form (including acoustic input, voice input, and tactile input).

The systems and techniques described herein are computing systems that include back-end components (eg, data servers), or computing systems that include middleware components (eg, application servers), or computing that includes front-end components. A system (eg, a user computer having a graphical user interface or web browser, and the user interacts with embodiments of the system and technology described herein by the graphical user interface or web browser), or such back. It can be implemented in computing systems that include any combination of end components, middleware components, and front end components. The components of the system can be interconnected by digital data communication of any form or medium (eg, a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

A computer system can include a client and a server. Clients and servers are generally separated from each other and typically interact over a communication network. A client-server relationship is created by a computer program that runs on the corresponding computer and has a client-server relationship with each other.

According to the technical proposal of the embodiment of the present application, the first historical position point is acquired, the first fitting result is acquired, and the current vehicle travels based on the current position point and the first fitting result. By predicting the trajectory, it is not necessary to depend on the signal of the vehicle, so that the prediction cost is reduced and the efficiency and accuracy of the trajectory prediction are improved.

Steps can be rearranged, added, or deleted using the various forms of flow shown above. For example, the steps described in this application may be performed in parallel, sequentially, or in a different order, but the techniques disclosed in this application. As long as the proposal can achieve the desired result, it is not limited herein.

The specific embodiments described above do not limit the scope of protection of the present application. One of ordinary skill in the art can make various modifications, combinations, subcombinations, and alternatives based on design requirements and other factors. Any amendments, equivalent substitutions, and improvements made within the spirit and principles of this application should all be within the scope of this application's protection.

Claims (15)

It is a method of predicting the vehicle trajectory,
A step of acquiring a plurality of first historical position points in the first historical travel time zone of the current vehicle, fitting the plurality of first historical position points, and acquiring the first fitting result.
A step of acquiring the current position point of the current vehicle and predicting the traveling locus of the current vehicle based on the current position point and the first fitting result is included.
A method of predicting a vehicle trajectory, which is characterized in that. The first historical travel time zone is the historical travel time zone closest to the current time.
The length of time corresponding to the first historical travel time zone is larger than the preset time length threshold value, and / or the travel distance corresponding to the first historical travel time zone is the preset distance. Greater than the threshold of
The method according to claim 1. The step of fitting the plurality of first historical position points and acquiring the first fitting result is
Steps to determine the first fitting equation used for fitting,
For each first historical position point, a step of determining at least one deformation equation corresponding to the first fitting equation based on a first preset transformation factor.
A step of determining the value of the unknown coefficient of the first fitting equation based on the coordinate value of each first historical position point and each of the above deformation equations.
A step of updating the first fitting equation using the value of the unknown coefficient and obtaining the first fitting result, and the like.
The method according to claim 1. The first preset transformation factor is
The sequence number of the current first history position point, the course angle corresponding to the current first history position point, the total number of the first history position points, and the first coordinate axis of each first history position point. Includes at least one of the variance of the coordinate values in the direction and the variance of the coordinate values in the second coordinate axis direction of each first historical position point.
The method according to claim 3, wherein the method is characterized by the above. The step of predicting the traveling locus of the current vehicle based on the current position point and the first fitting result is
The step of determining the radius of curvature corresponding to the current position point based on the first fitting result,
A step of determining a locus arc based on the current position point and the radius of curvature and using the locus arc as the predicted running locus of the current vehicle is included.
The method according to claim 3, wherein the method is characterized by the above. After the step of predicting the running locus of the current vehicle based on the current position point and the first fitting result,
A step of acquiring the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the second historical travel time zone, and
A step of fitting the distance to the current vehicle at each time and obtaining a second fitting result.
Based on the second fitting result, a step of determining the current distance and the current speed of the vehicle in front and the current vehicle, and
Further including a step of determining the collision time between the preceding vehicle and the current vehicle based on the current distance and the current speed, and determining whether or not to issue an early collision warning based on the collision time. ,
The method according to any one of claims 1 to 5. The step of fitting the distance to the current vehicle at each time and obtaining the second fitting result is
Steps to determine the second fitting equation used for fitting,
For each time, a step of determining at least one transformation equation corresponding to the second fitting equation based on a second preset transformation factor.
A step of determining the value of the unknown coefficient of the second fitting equation based on the distance of the vehicle in front to the current vehicle at each time and each deformation equation corresponding to the second fitting equation.
Including a step of updating the second fitting equation with the value of the unknown coefficient of the second fitting equation and obtaining the second fitting result.
The method according to claim 6, wherein the method is characterized by the above. The second preset transformation factor is
Includes at least one of the sequence number of the current time, the total number of times, the variance of each time, and the variance of the distance of the vehicle in front to the current vehicle at each time.
The method according to claim 7, wherein the method is characterized by the above. Before the step of acquiring the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the second historical travel time zone,
Determines whether the current distance between the vehicle in front of the current vehicle and the predicted travel locus of the current vehicle is within a preset range, and if so, a second historical travel time. It further comprises a step of triggering the execution of an operation to obtain the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the band.
The method according to claim 6, wherein the method is characterized by the above. The step of acquiring the distance of the vehicle in front of the current vehicle to the current vehicle at each time of the second historical travel time zone is
A step of acquiring an image taken by the image pickup device of the current vehicle at each time of the second historical driving time zone, and
A step of determining the position information of the vehicle in front of the current vehicle at each time by performing image recognition on each of the images, and
Includes a step of determining the distance of the vehicle in front to the current vehicle at each time based on the position information of the vehicle in front at each time and the internal and external parameters of the imaging device.
The method according to claim 6, wherein the method is characterized by the above. The internal parameters include the center of light and the ratio of focal length to pixel size.
The external parameters include the posture angle of the image pickup device and the height of the image pickup device from the ground.
10. The method of claim 10. It is a vehicle trajectory prediction device
A first for acquiring a plurality of first historical position points in a first historical travel time zone of a current vehicle, fitting the plurality of first historical position points, and acquiring a first fitting result. Fitting result acquisition module and
Includes a travel locus prediction module for acquiring the current position point of the current vehicle and predicting the travel locus of the current vehicle based on the current position point and the first fitting result.
A vehicle trajectory prediction device characterized by this. With at least one processor
Includes a memory communicatively connected to the at least one processor.
Instructions that can be executed by the at least one processor are stored in the memory so that the at least one processor can execute the vehicle trajectory prediction method according to any one of claims 1 to 11. , Executed by said at least one processor,
An electronic device characterized by that. A non-temporary computer-readable storage medium that stores computer instructions.
The computer instruction causes the computer to execute the vehicle trajectory prediction method according to any one of claims 1 to 11.
A non-temporary computer-readable storage medium characterized by that. It ’s a computer program,
The computer program causes a computer to execute the vehicle trajectory prediction method according to any one of claims 1 to 11.
A computer program characterized by that.

Images