CN109344426B - Data processing method and device and server - Google Patents

Abstract

The invention discloses a data processing method, a data processing device and a server, wherein the method comprises the following steps: determining an initial fitting track of a data sampling point to be fitted, and taking the initial fitting track as a fitting track to be corrected; calculating a first fitting error of the fitting track to be corrected based on a preset fitting error cost function; carrying out track form disturbance processing on the fitting track to be corrected; calculating a second fitting error of the disturbed fitting track based on a preset fitting error cost function; judging whether the second fitting error is smaller than the first fitting error; when the judgment result is yes, taking the second fitting error as a first fitting error of the disturbed fitting track, and taking the disturbed fitting track as the fitting track to be corrected to execute track form disturbance processing until the current disturbance frequency reaches a preset disturbance frequency; and taking the fitting track reaching the preset disturbance times as a target fitting track of the data sampling point to be fitted.

Description

Data processing method and device and server

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a data processing method, an apparatus, and a server.

Background

At present, the track modeling has wide requirements in the fields of navigation electronic maps, motion simulation and the like. Specifically, data needs to be collected in track modeling (image information obtained by using a navigation electronic map and aerial photography of a street view collection vehicle or an unmanned aerial vehicle can be used as collected data), data points needing to be fitted with tracks are extracted from the collected data through characteristics, and fitting is carried out according to the data points.

In the prior art, a deterministic fitting algorithm based on the least square method is often used, and specifically, taking the commonly used fitting of the interpolation of the third-order B-spline as an example, the method may include: and uniformly resampling all the data sampling points according to the point intervals according to the lengths among the data sampling points to obtain uniform resampled data points. Control points are then determined from the resampled data points based on a least squares method (the number of control points is typically no more than half the number of all data points). Finally, a trajectory fitting is performed based on the determined control points. The existing method for performing track fitting of data points based on the least square method is sensitive to noise and damage of collected data, and track deformation and jitter occur, so that the track error of the determined data sampling points is large. Therefore, there is a need to provide a more reliable solution.

Disclosure of Invention

The invention provides a data processing method, a data processing device and a server, which can improve the accuracy of a fitting track of a data sampling point.

In a first aspect, the present invention provides a data processing method, including:

determining an initial fitting track of a data sampling point to be fitted, and taking the initial fitting track as a fitting track to be corrected;

calculating a first fitting error of the fitting track to be corrected based on a preset fitting error cost function, wherein the preset fitting error cost function represents the difference between the fitting track and an actual track corresponding to a data sampling point covered by the fitting track;

performing track form disturbance processing on the fitting track to be corrected to obtain a disturbed fitting track;

calculating a second fitting error of the disturbed fitting track based on a preset fitting error cost function;

judging whether the second fitting error is smaller than the first fitting error;

when the judgment result is yes, taking the second fitting error as a first fitting error of the disturbed fitting track, taking the disturbed fitting track as a fitting track to be corrected, and executing track form disturbance processing until the frequency of current track form disturbance processing reaches a preset disturbance frequency;

and taking the fitting track reaching the preset disturbance times as a target fitting track of the data sampling point to be fitted.

A second aspect provides a data processing apparatus, the apparatus comprising:

the device comprises a to-be-corrected fitting track determining module, a to-be-corrected fitting track determining module and a to-be-corrected fitting track determining module, wherein the to-be-corrected fitting track determining module is used for determining an initial fitting track of a to-be-fitted data sampling point and taking the initial fitting track as the to-be-corrected fitting track;

the first fitting error calculation module is used for calculating a first fitting error of the fitting track to be corrected based on a preset fitting error cost function, and the preset fitting error cost function represents the difference between the fitting track and an actual track corresponding to a data sampling point covered by the fitting track;

the track form disturbance processing module is used for carrying out track form disturbance processing on the fitting track to be corrected to obtain a disturbed fitting track;

the second fitting error calculation module is used for calculating a second fitting error of the disturbed fitting track based on a preset fitting error cost function;

the first judging module is used for judging whether the second fitting error is smaller than the first fitting error;

the first data processing module is used for taking the second fitting error as a first fitting error of the disturbed fitting track and taking the disturbed fitting track as a fitting track to be corrected to execute track form disturbance processing when the judgment result of the first judging module is yes, and the frequency of the current track form disturbance processing reaches a preset disturbance frequency;

and the fitting track determining module is used for taking the fitting track reaching the preset disturbance times as a target fitting track of the data sampling point to be fitted.

A third aspect provides a data processing server comprising a processor and a memory, the memory having stored therein at least one instruction, at least one program, set of codes, or set of instructions, which is loaded and executed by the processor to implement the data processing method according to the first aspect.

A fourth aspect provides a computer readable storage medium having stored therein at least one instruction, at least one program, set of codes, or set of instructions, which is loaded and executed by a processor to implement the data processing method according to the first aspect.

The data processing method, the data processing device and the server have the following technical effects:

the method can continuously adjust the fitting track by performing track form disturbance processing on the to-be-fitted track of the to-be-fitted data sampling point, meanwhile, in the track form disturbance processing process, the fitting error of the to-be-corrected fitting track after the current track form disturbance processing is continuously calculated through a preset fitting error cost function representing the difference between the fitting track and the actual track corresponding to the data sampling point covered by the fitting track, when the fitting error is reduced, the current track form disturbance processing is received, the difference between the to-be-corrected fitting track and the real fitting error of the fitting data sampling point is continuously reduced, and the accuracy of the fitting track of the data sampling point is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a schematic flow chart of a data processing method according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart illustrating the fitting degree of a fitting track to data sampling points within a range covered by the fitting track according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a first extended region of a multi-segment fitted polyline trace and a second extended region of a multi-segment sampled polyline trace provided by the present invention;

FIG. 4 is a schematic diagram of a trajectory splitting process performed on a fitted trajectory according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a trajectory merging process performed on a fitted trajectory according to an embodiment of the present invention;

fig. 6 is a schematic diagram of moving a connection point between adjacent piecewise fitting tracks in the fitting track to be corrected to obtain the disturbed fitting track according to the embodiment of the present invention;

fig. 7 is a schematic diagram of laterally moving control points of each segment of the piecewise fitting trajectory in the fitting trajectory to be corrected to obtain the disturbed fitting trajectory according to the embodiment of the present invention;

fig. 8 is a schematic diagram of longitudinally moving control points of each segment of the piecewise fitting trajectory in the fitting trajectory to be corrected to obtain the disturbed fitting trajectory according to the embodiment of the present invention;

FIG. 9 is a flow chart illustrating another data processing method according to an embodiment of the present invention;

FIG. 10 is a flow chart illustrating another data processing method according to an embodiment of the present invention;

FIG. 11 is a block diagram of a data processing apparatus according to an embodiment of the present invention;

fig. 12 is a schematic structural diagram of a server according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

While specific embodiments of the data processing method of the present invention are described below, fig. 1 is a flow chart of a data processing method provided by embodiments of the present invention, and the present specification provides the method operation steps as described in the embodiments or the flow chart, but may include more or less operation steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In practice, the system or server product may be implemented in a sequential or parallel manner (e.g., parallel processor or multi-threaded environment) according to the embodiments or methods shown in the figures. Specifically, as shown in fig. 1, the method may include:

s101: and determining an initial fitting track of the data sampling points to be fitted, and taking the initial fitting track as a fitting track to be corrected.

In this embodiment of the present specification, the sampling points of the data to be fitted may include sampling points of an object to be subjected to trajectory fitting, and specifically, the sampling points of the data to be fitted may include data points of the object extracted from image information including the object to be subjected to trajectory fitting.

In practical applications, the shapes of objects are various, and an object often needs multiple segments of tracks to describe the shape, for example, a road may include multiple curved tracks. Accordingly, the initial fitting trajectory of the data sampling points to be fitted in the embodiments of the present specification may include multiple interconnected trajectories. The plurality of sections of interconnected tracks can be tracks with the same length or tracks with different lengths. Specifically, determining the initial fitting trajectory of the data sampling points to be fitted in the embodiment of the present specification may include, but is not limited to, determining the initial fitting trajectory of the data sampling points to be fitted by using a randomized segmented bezier curve.

S103: and calculating a first fitting error of the fitting track to be corrected based on a preset fitting error cost function.

In practical application, a certain difference often exists between a fitting track and an actual track of an object, and in the embodiment of the present specification, a first fitting error of the fitting track to be corrected may be calculated based on a preset fitting error cost function. In this embodiment of the present description, the preset fitting error cost function may represent a difference between a fitting track and an actual track corresponding to a data sampling point covered by the fitting track. Specifically, when the difference between the fitting track and the actual track corresponding to the data sampling point covered by the fitting track is larger, the value of the preset fitting error cost function is larger; on the contrary, when the difference between the fitting track and the actual track corresponding to the data sampling point covered by the fitting track is smaller, the value of the preset fitting error cost function is smaller.

In a specific embodiment, the preset fitting error cost function may include at least one of the following fitting error influence factors:

1) and fitting degree of the fitting track and the data sampling points in the range covered by the fitting track.

In this embodiment of the present specification, the fitting degree of the fitting track and the data sampling points within the range covered by the fitting track may include a numerical value representing the fitting degree of the fitting track and the data sampling points within the range covered by the fitting track. Specifically, as shown in fig. 2, the fitting degree of the fitting track to the data sampling points within the range covered by the fitting track is determined by the following method:

s201: and performing broken line processing on the fitting track to obtain a plurality of sections of fitting broken line tracks.

S203: establishing a multi-section sampling broken line track based on the data sampling points in the coverage range of the fitting track;

s205: and determining a first expansion area of the multi-segment fitting broken line track and a second expansion area of the multi-segment sampling broken line track.

In this embodiment of the present specification, the first expansion area of the multi-segment fitted polygonal line trajectory may include an area corresponding to a first preset length expanded to two sides with each polygonal line in the multi-segment fitted polygonal line trajectory as a center; the second expansion area of the multi-segment sampling broken line track may include an area corresponding to a second preset length expanded to both sides with each broken line in the multi-segment sampling broken line track as a center.

In this embodiment of the present description, the first preset length and the second preset length may be set in combination with practical applications, so as to ensure that the first extension area and the second extension area coincide with each other. Typically, the first predetermined length is equal to the second predetermined length.

Specifically, as shown in fig. 3, fig. 3 is a schematic diagram of a first extended region of a multi-segment fitted polyline track and a second extended region of a multi-segment sampled polyline track provided by the present invention, where amulti-segment polyline 301 is a polyline in the multi-segment fitted polyline track, and amulti-segment polyline 302 is a polyline in the multi-segment sampled polyline track. Correspondingly, the area corresponding to the first preset length expanded to the two sides by taking themulti-segment folding line 301 as the center is a first expandedarea 3011; a region corresponding to the first preset length expanded to both sides with the multi-segmentbroken line 302 as the center is a second expandedregion 3021.

S207: and calculating the coincidence degree of the first extension area and the second extension area.

In this specification, the overlapping degree of the first extension region and the second extension region may include a ratio of an area of an overlapping region of the first extension region and the second extension region to an average value of the areas of the first extension region and the second extension region.

S209: and calculating the ratio of the length of the fitting track to the maximum allowable fitting track length.

In the embodiment of the present specification, the maximum allowable fitting track length may be set in combination with an actual length of an actual application fitting track, and the maximum allowable fitting track length fitting track is proportional to a difference between actual tracks corresponding to data sampling points covered by the fitting track.

S211: and calculating the product between the contact ratio and the ratio, and taking a negative numerical value of the product as the contact ratio of the fitting track and the data sampling points in the range covered by the fitting track.

In the embodiment of the specification, the contact ratio and the ratio between the length of the fitting track and the length of the maximum allowable fitting track are all in inverse proportion to the difference between the fitting track and the actual track corresponding to the data sampling point covered by the fitting track, that is, the contact ratio is increased, and the ratio between the length of the fitting track and the length of the maximum allowable fitting track is increased, so that the difference between the fitting track and the actual track corresponding to the data sampling point covered by the fitting track is reduced; on the contrary, the smaller the contact ratio and the ratio between the length of the fitting track and the length of the maximum allowable fitting track are, the larger the difference between the fitting track and the actual track corresponding to the data sampling point covered by the fitting track is. Therefore, in the embodiment of the present specification, the product obtained by multiplying the product between the contact ratio and the specific value by negative one is used as the fitting degree of the fitting track and the data sampling point within the range covered by the fitting track, so that the fitting degree of the fitting track and the data sampling point within the range covered by the fitting track can be ensured to be in direct proportion to the difference between the fitting track and the actual track corresponding to the data sampling point covered by the fitting track.

2) The tangent angle jump of the adjacent curves in the fitting track at the connection position exceeds the maximum allowable angle jump number.

Specifically, in the embodiment of the present specification, the number of the maximum allowable angle jumps may be set in combination with an actual application, and generally, the number of the maximum allowable angle jumps is inversely proportional to a difference between a corresponding fitting track and an actual track corresponding to a data sampling point covered by the fitting track.

3) The curvature jumps of adjacent curves in the fitted trajectory at the junction exceed the maximum allowed number of curvature jumps.

Specifically, in the embodiment of the present specification, the number of maximum allowed curvature jumps may be set in combination with an actual application, and generally, the number of maximum allowed curvature jumps is inversely proportional to a difference between a corresponding fitting track and an actual track corresponding to a data sampling point covered by the fitting track.

4) The number of curves in the fitted trajectory whose curve length exceeds the maximum allowable length.

Specifically, in the embodiment of the present specification, the maximum allowable length may be set in combination with an actual application, and generally, the maximum allowable length is inversely proportional to a difference between a corresponding fitting track and an actual track corresponding to a data sampling point covered by the fitting track.

In addition, it should be noted that a value of any one of the fitting error influencing factors is directly proportional to a value of the preset fitting error cost function.

In a specific embodiment, when the preset fitting error cost function includes one fitting error influence factor, the preset fitting error cost function may be a function including the fitting error influence factor.

In another specific embodiment, when the preset fitting error cost function includes a plurality of fitting error influence factors, the preset fitting error cost function may include determining in the following manner:

obtaining weight coefficients of the plurality of fitting error influence factors;

and performing weighted calculation on the fitting error influence factors based on the weight coefficients of the fitting error influence factors to obtain the preset fitting error cost function.

Specifically, the weight coefficient of each fitting error influence factor represents the influence degree of the fitting error influence factor on the difference between the fitting track and the actual track corresponding to the data sampling point covered by the fitting track.

Correspondingly, when a first fitting error of the fitting track to be corrected needs to be calculated based on a preset fitting error cost function, a fitting error influence factor included in the preset fitting error cost function corresponding to the initial fitting track can be calculated, and then the initial fitting error of the initial fitting track is calculated based on the preset fitting error cost function.

S105: and carrying out track form disturbance processing on the fitting track to be corrected to obtain a disturbed fitting track.

Specifically, in this embodiment of the present specification, the performing trajectory shape disturbance processing on the fitting trajectory to be corrected to obtain a disturbed fitting trajectory may include adopting any one of the following manners:

1) and carrying out track splitting processing on each section of the fitting track in the fitting track to be corrected to obtain the disturbed fitting track.

Specifically, as shown in fig. 4, fig. 4 is a schematic diagram of performing trajectory splitting processing on a fitting trajectory according to an embodiment of the present invention, and specifically, a fitting estimation of a certain segment is divided into two segments to implement split operation split.

2) And carrying out track merging processing on adjacent segmented fitting tracks in the fitting tracks to be corrected to obtain the disturbed fitting tracks.

Specifically, as shown in fig. 5, fig. 5 is a schematic diagram of performing a trajectory merging process on a fitting trajectory according to an embodiment of the present invention. Specifically, two adjacent piecewise fitting tracks are combined into one fitting track, so that the merge operation merge is realized.

3) And moving a connecting point between adjacent piecewise fitting tracks in the fitting track to be corrected to obtain the disturbed fitting track.

Specifically, as shown in fig. 6, fig. 6 is a schematic diagram of moving a connection point between adjacent piecewise fitting tracks in the fitting track to be corrected to obtain the disturbed fitting track according to the embodiment of the present invention. Specifically, the connectingpoint 600 between two adjacent piecewise fitting tracks is moved, so that the moving operation slide of the connecting point between the adjacent piecewise fitting tracks in the fitting track to be corrected is realized.

4) And transversely moving the control point of each section of the piecewise fitting track in the fitting track to be corrected to obtain the disturbed fitting track.

Specifically, as shown in fig. 7, fig. 7 is a schematic diagram of laterally moving a control point of each segment of the piecewise fitting trajectory in the fitting trajectory to be corrected to obtain the disturbed fitting trajectory according to the embodiment of the present invention. Specifically, thecontrol point 700 of each segment of the piecewise fitting track is moved transversely, so that the horizontal movement operation of the control point of each segment of the piecewise fitting track in the fitting track to be corrected is realized.

5) And longitudinally moving the control point of each section of the piecewise fitting track in the fitting track to be corrected to obtain the disturbed fitting track.

Specifically, as shown in fig. 8, fig. 8 is a schematic diagram of longitudinally moving control points of each segment of the piecewise fitting trajectory in the fitting trajectory to be corrected to obtain the disturbed fitting trajectory according to the embodiment of the present invention. Specifically, thecontrol point 800 of each segment of the piecewise fitting trajectory is longitudinally moved, so that the vertical move operation of the control point of each segment of the piecewise fitting trajectory in the fitting trajectory to be corrected is achieved.

S107: and calculating a second fitting error of the disturbed fitting track based on a preset fitting error cost function.

In the embodiment of the present specification, the step of calculating the second fitting error of the disturbed fitting track based on the preset fitting error cost function may refer to the above-mentioned related step of determining the initial fitting error of the initial fitting track, and is not described herein again.

In addition, in this embodiment of the present specification, the first fitting error may include a fitting error of a fitting trajectory before the current trajectory shape disturbance processing of the fitting trajectory to be corrected, which currently needs to be subjected to the trajectory shape disturbance processing. Correspondingly, the second fitting error may include a fitting error of the fitting track to be corrected, which currently needs to be subjected to the track morphology disturbance processing, after the current track morphology disturbance processing.

S109: and judging whether the second fitting error is smaller than the first fitting error.

In this embodiment, determining whether the second fitting error is smaller than the first fitting error may be determined by comparing the magnitude of the second fitting error with the magnitude of the first fitting error.

In other embodiments, determining whether the second fitting error is less than the first fitting error may be determined by calculating whether an exponential function with a base natural constant e (the exponent is the difference between the second fitting error minus the first fitting error) is greater than or equal to 1. Specifically, when an exponential function (an exponent is a difference between a second fitting error and a first fitting error) with a natural constant e as a base is greater than or equal to 1, the second fitting error is greater than or equal to the first fitting error; conversely, when an exponential function with the natural constant e as the base (the exponent is the difference between the second fitting error minus the first fitting error) is less than 1, the second fitting error is less than the first fitting error.

S111: and when the judgment result is yes, taking the second fitting error as a first fitting error of the disturbed fitting track, taking the disturbed fitting track as a fitting track to be corrected to execute track form disturbance processing until the frequency of the current track form disturbance processing reaches a preset disturbance frequency.

Specifically, the step of executing the trajectory form disturbance processing after the second fitting error is used as the first fitting error of the disturbed fitting trajectory, and the disturbed fitting trajectory is used as the fitting trajectory to be corrected, where the number of times of the current trajectory form disturbance processing reaches the preset disturbance number may include:

judging whether the frequency of the current track form disturbance processing is less than a preset disturbance frequency or not;

and when judging that the number of times of the current track form disturbance processing is smaller than the preset disturbance number of times, executing a track form disturbance processing step on the current fitting track to be corrected.

Otherwise, when the number of current track form disturbance processing is determined to be greater than or equal to the preset disturbance number, step S113 is executed.

Specifically, the preset disturbance times may include disturbance iteration times determined based on a convergence rate of the preset fitting error cost function. Specifically, a fitting track can be obtained to perform iterative processing of track form disturbance, the convergence rate of the preset fitting error cost function is determined according to the variation amplitude of the first fitting error and the second fitting error calculated by the preset fitting error cost function during iterative processing, when the convergence rate reaches the preset convergence rate, iteration can be stopped, the current iteration number can be used as the iteration number of the preset fitting error cost function, and correspondingly, the iteration number of the preset fitting error cost function can be used as the preset disturbance number.

S113: and taking the fitting track reaching the preset disturbance times as a target fitting track of the data sampling point to be fitted.

According to the technical scheme provided by the embodiment of the specification, the trajectory form disturbance processing is carried out on the trajectory to be fitted of the data sampling point to be fitted to continuously adjust the fitting trajectory, meanwhile, in the trajectory form disturbance processing process, the fitting error of the fitting trajectory to be corrected after the current trajectory form disturbance processing is continuously calculated through the preset fitting error cost function representing the difference between the fitting trajectory and the actual trajectory corresponding to the data sampling point covered by the fitting trajectory, when the fitting error is reduced, the current trajectory form disturbance processing is received, the difference between the fitting trajectory to be corrected and the actual fitting error of the fitting data sampling point is continuously reduced, and the accuracy of the fitting trajectory of the data sampling point is improved.

While another embodiment of the data processing method of the present invention is described below, fig. 9 is a flow chart of another data processing method provided by the embodiment of the present invention, and the present specification provides the method operation steps as described in the embodiment or the flow chart, but may include more or less operation steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In practice, the system or server product may be implemented in a sequential or parallel manner (e.g., parallel processor or multi-threaded environment) according to the embodiments or methods shown in the figures. Specifically, as shown in fig. 9, the method may include:

s901: and determining an initial fitting track of the data sampling points to be fitted, and taking the initial fitting track as a fitting track to be corrected.

S903: and calculating a first fitting error of the fitting track to be corrected based on a preset fitting error cost function, wherein the preset fitting error cost function represents the difference between the fitting track and an actual track corresponding to the data sampling point covered by the fitting track.

S905: and carrying out track form disturbance processing on the fitting track to be corrected to obtain a disturbed fitting track.

S907: and calculating a second fitting error of the disturbed fitting track based on a preset fitting error cost function.

S909: and judging whether the second fitting error is smaller than the first fitting error.

S911: and when the judgment result is yes, taking the second fitting error as a first fitting error of the disturbed fitting track, taking the disturbed fitting track as a fitting track to be corrected to execute track form disturbance processing until the frequency of the current track form disturbance processing reaches a preset disturbance frequency.

S913: and when the judgment result is negative, judging whether to accept the current track form disturbance processing based on a preset probability algorithm.

In an embodiment of the present specification, the determining whether to accept the current trajectory form disturbance processing based on the preset probability algorithm may include:

randomly generating a random number between 0 and 1;

judging whether the random number is larger than or equal to an exponential function taking a natural constant e as a base and taking a difference value obtained by subtracting the first fitting error from the second fitting error as an exponent;

and when the random number is judged to be larger than or equal to an exponential function taking a natural constant e as a base and a difference value obtained by subtracting the first fitting error from the second fitting error as an exponent, determining to accept the current track form disturbance processing.

And when the random number is judged to be smaller than an exponential function taking the natural constant e as the base and the difference value of the second fitting error minus the first fitting error as an exponent, determining to reject the current track form disturbance processing.

S915: and when judging that the current track form disturbance processing is rejected, executing track form disturbance processing on the current fitting track to be corrected until the frequency of the current track form disturbance processing reaches the preset disturbance frequency.

In this embodiment of the present description, when it is determined that the current trajectory form disturbance processing is rejected, executing the trajectory form disturbance processing until the number of times of the current trajectory form disturbance processing reaches the preset disturbance number may include:

judging whether the frequency of the current track form disturbance processing is less than a preset disturbance frequency or not;

and when judging that the current track form disturbance processing times are smaller than the preset disturbance times, executing a track form disturbance processing step on the current fitting track to be corrected.

Otherwise, when the number of current track form disturbance processing is determined to be greater than or equal to the preset disturbance number, step S917 is executed.

S917: and taking the fitting track reaching the preset disturbance times as a target fitting track of the data sampling point to be fitted.

In other embodiments, as shown in fig. 10, the method may further include:

s919: and when judging that the current track form disturbance processing is accepted, taking the second fitting error as a first fitting error of the disturbed fitting track, and taking the disturbed fitting track as a fitting track to be corrected to execute track form disturbance processing until the frequency of the current track form disturbance processing reaches a preset disturbance frequency.

According to the technical scheme provided by the embodiment of the specification, the trajectory form disturbance processing is carried out on the trajectory to be fitted of the data sampling point to be fitted to continuously adjust the fitting trajectory, meanwhile, in the trajectory form disturbance processing process, the fitting error of the current trajectory form to be corrected after the disturbance processing is carried out is continuously calculated through the preset fitting error cost function representing the difference between the fitting trajectory and the actual trajectory corresponding to the data sampling point covered by the fitting trajectory, and when the fitting error is reduced, the current trajectory form disturbance processing is received; when the fitting error is increased, rejecting the current track form disturbance processing based on a preset probability algorithm, and continuously performing the track form disturbance processing of the current fitting track to be corrected before reaching the preset disturbance times; the difference between the fitting track to be corrected and the real fitting error of the fitting data sampling point is continuously reduced, and the accuracy of the fitting track of the data sampling point is greatly improved.

An embodiment of the present invention further provides a data processing apparatus, as shown in fig. 11, the apparatus includes:

the to-be-corrected fittingtrack determining module 1101 may be configured to determine an initial fitting track of a to-be-fitted data sampling point, and use the initial fitting track as the to-be-corrected fitting track;

the first fittingerror calculating module 1102 may be configured to calculate a first fitting error of the fitting track to be corrected based on a preset fitting error cost function, where the preset fitting error cost function represents a difference between the fitting track and an actual track corresponding to a data sampling point covered by the fitting track;

the trajectory formdisturbance processing module 1103 may be configured to perform trajectory form disturbance processing on the fitting trajectory to be corrected to obtain a disturbed fitting trajectory;

a second fittingerror calculation module 1104, configured to calculate a second fitting error of the disturbed fitting trajectory based on a preset fitting error cost function;

a first determiningmodule 1105, configured to determine whether the second fitting error is smaller than the first fitting error;

the firstdata processing module 1106 may be configured to, when the result of the determination by the first determining module is yes, use the second fitting error as the first fitting error of the disturbed fitting track, use the disturbed fitting track as the fitting track to be corrected to execute track form disturbance processing, until the number of times of current track form disturbance processing reaches a preset disturbance number;

the fittingtrack determining module 1107 may be configured to use the fitting track when the preset disturbance frequency is reached as the target fitting track of the data sampling point to be fitted.

In another embodiment, the apparatus may further include:

the second judgment module is used for judging whether to accept the current track form disturbance processing based on a preset probability algorithm when the judgment result of the first judgment module is negative;

and the second data processing module is used for executing track form disturbance processing on the current fitting track to be corrected when the second judging module judges that the current track form disturbance processing is rejected until the frequency of the current track form disturbance processing reaches the preset disturbance frequency.

In another embodiment, the apparatus further comprises:

and the third data processing module is used for taking the second fitting error as the first fitting error of the disturbed fitting track and taking the disturbed fitting track as the fitting track to be corrected to execute track form disturbance processing when the second judging module judges that the current track form disturbance processing is accepted, until the frequency of the current track form disturbance processing reaches the preset disturbance frequency.

In another embodiment, the preset fitting error cost function includes at least one of the following fitting error impact factors:

the fitting degree of the fitting track and the data sampling points in the range covered by the fitting track;

the tangent angle jump of the adjacent curves in the fitting track at the connection position exceeds the maximum allowable angle jump number;

the curvature jump of the adjacent curves in the fitting track at the connection position exceeds the maximum allowable curvature jump number;

the number of curves in the fitted trajectory whose curve length exceeds the maximum allowable length.

In another embodiment, when the preset fitting error cost function includes one fitting error influence factor, the preset fitting error cost function includes determining by using the following units:

and the cost function determining unit is used for taking the fitting error influence factor as the preset fitting error cost function.

In another embodiment, when the preset fitting error cost function includes a plurality of fitting error influence factors, the preset fitting error cost function includes determining by using:

a weight coefficient unit for obtaining weight coefficients of the plurality of fitting error influence factors;

the weighting calculation unit is used for carrying out weighting calculation on the fitting error influence factors based on the weighting coefficients of the fitting error influence factors to obtain the preset fitting error cost function;

and the weight coefficient of each fitting error influence factor represents the influence degree of the fitting error influence factor on the difference between the fitting track and the actual track corresponding to the data sampling point covered by the fitting track.

In another embodiment, the fitting degree of the fitted track to the data sampling points within the range covered by the fitted track includes determining by using the following units:

the broken line processing unit is used for carrying out broken line processing on the fitting track to obtain a plurality of sections of fitting broken line tracks;

the multi-segment sampling broken line track establishing unit is used for establishing a multi-segment sampling broken line track based on the data sampling points in the coverage range of the fitting track;

an extended region determining unit, configured to determine a first extended region of the multi-segment fitted polyline trajectory and a second extended region of the multi-segment sampled polyline trajectory;

a coincidence degree calculation unit for calculating a coincidence degree of the first extension region and the second extension region;

the length ratio calculation unit is used for calculating the ratio between the fitting track length and the maximum allowable fitting track length;

a product calculation unit for calculating a product between the contact ratio and the ratio;

and the fitting degree determining unit is used for taking the value obtained after the product is negative as the fitting degree of the fitting track and the data sampling points in the range covered by the fitting track.

In another embodiment, the trajectory shape perturbation processing module includes:

the track splitting processing unit is used for carrying out track splitting processing on each section of fitting track in the fitting track to be corrected to obtain the disturbed fitting track;

or the like, or, alternatively,

the track merging processing unit is used for carrying out track merging processing on adjacent segmented fitting tracks in the fitting tracks to be corrected to obtain the disturbed fitting tracks;

or the like, or, alternatively,

the connecting point moving unit is used for moving connecting points between adjacent segmented fitting tracks in the fitting tracks to be corrected to obtain the disturbed fitting tracks;

or the like, or a combination thereof,

the transverse moving unit is used for transversely moving the control point of each section of the piecewise fitting track in the fitting track to be corrected to obtain the disturbed fitting track;

or the like, or, alternatively,

and the longitudinal moving unit is used for longitudinally moving the control point of each section of the piecewise fitting track in the fitting track to be corrected to obtain the disturbed fitting track.

In another embodiment, the preset number of perturbations includes a number of perturbation iterations determined based on a convergence speed of the preset fitting error cost function.

The device and method embodiments in the device embodiment described are based on the same inventive concept.

An embodiment of the present invention provides a data processing server, where the data processing server includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the data processing method provided in the foregoing method embodiment.

The method provided by the embodiment of the invention can be executed in a mobile terminal, a computer terminal, a server or a similar operation device. Taking the example of the operation on a server, fig. 12 is a hardware structure block diagram of the server of the data processing method according to the embodiment of the present invention. As shown in fig. 12, theserver 1200 may have a large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 1210, amemory 1230 for storing data, and one ormore storage media 1220 for storingapplication programs 1223 ordata 1222. Further, thecentral processor 1210 may be configured to communicate with thestorage medium 1220, and execute a series of instruction operations in thestorage medium 1220 on theserver 1200. Theserver 1200 may also include one ormore power supplies 1260, one or more wired orwireless network interfaces 1250, one or more input-output interfaces 1240, and/or one ormore operating systems 1221.

The input/output interface 1240 may be used to accept or transmit data via a network. The specific example of the network described above may include a wireless network provided by a communication provider of theserver 1200. In one example, the input/output Interface 1240 includes a Network Interface Controller (NIC) that may be coupled to other Network devices via a base station to communicate with the internet. In one example, the input/output interface 1240 may be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.

It will be understood by those skilled in the art that the structure shown in fig. 12 is only an illustration and is not intended to limit the structure of the electronic device. For example,server 1200 may also include more or fewer components than shown in FIG. 12, or have a different configuration than shown in FIG. 12.

Embodiments of the present invention also provide a storage medium, which may be disposed in a server to store at least one instruction, at least one program, a code set, or a set of instructions related to implementing a data processing method in the method embodiments, where the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by the processor to implement the data processing method provided by the above method embodiments.

Alternatively, in this embodiment, the storage medium may be located in at least one network server of a plurality of network servers of a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

According to the embodiment of the data processing method, the data processing device or the data processing server, the fitting track is continuously adjusted through track form disturbance processing on the to-be-fitted track of the to-be-fitted data sampling point, meanwhile, in the track form disturbance processing process, the fitting error of the to-be-corrected fitting track after the current track form disturbance processing is continuously calculated through a preset fitting error cost function representing the difference between the fitting track and the actual track corresponding to the data sampling point covered by the fitting track, and when the fitting error is reduced, the current track form disturbance processing is received; when the fitting error is increased, rejecting the current track form disturbance processing based on a preset probability algorithm, and continuously performing the track form disturbance processing of the current fitting track to be corrected before reaching the preset disturbance times; the difference between the fitting track to be corrected and the real fitting error of the fitting data sampling point is continuously reduced, and the accuracy of the fitting track of the data sampling point is greatly improved.

It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device and server embodiments, since they are substantially similar to the method embodiments, the description is simple, and the relevant points can be referred to the partial description of the method embodiments.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.

Claims (10)

1. A method of data processing, the method comprising:

determining an initial fitting track of a data sampling point to be fitted, and taking the initial fitting track as a fitting track to be corrected, wherein the data sampling point to be fitted comprises data points of an object extracted from image information of the object containing the object needing track fitting;

calculating a first fitting error of the fitting track to be corrected based on a preset fitting error cost function, wherein the preset fitting error cost function represents the difference between the fitting track and an actual track corresponding to a data sampling point covered by the fitting track;

performing track form disturbance processing on the fitting track to be corrected to obtain a disturbed fitting track, wherein the track form disturbance processing comprises track splitting processing on each section of fitting track in the fitting track to be corrected, or track combining processing on adjacent section fitting tracks in the fitting track to be corrected, or moving processing on a connecting point between the adjacent section fitting tracks in the fitting track to be corrected; or, performing transverse movement processing on the control points of each section of the piecewise fitting track in the fitting track to be corrected, or performing longitudinal movement processing on the control points of each section of the piecewise fitting track in the fitting track to be corrected;

calculating a second fitting error of the disturbed fitting track based on a preset fitting error cost function;

judging whether the second fitting error is smaller than the first fitting error;

when the judgment result is yes, taking the second fitting error as a first fitting error of the disturbed fitting track, taking the disturbed fitting track as a fitting track to be corrected, and executing track form disturbance processing until the frequency of current track form disturbance processing reaches a preset disturbance frequency;

and taking the fitting track reaching the preset disturbance times as a target fitting track of the data sampling point to be fitted.

2. The method of claim 1, further comprising:

when the judgment result is negative, judging whether to accept the current track form disturbance processing based on a preset probability algorithm;

when the current track form disturbance processing is judged to be rejected, executing track form disturbance processing on the current fitting track to be corrected until the number of times of the current track form disturbance processing reaches a preset disturbance number, wherein the executing track form disturbance processing on the current fitting track to be corrected comprises performing track splitting processing on each section of fitting track in the current fitting track to be corrected, or combining the tracks of adjacent section fitting tracks in the current fitting track to be corrected, or moving the connecting points between the adjacent section fitting tracks in the current fitting track to be corrected; or, performing transverse movement processing on the control points of each segment of the segmented fitting track in the current fitting track to be corrected, or performing longitudinal movement processing on the control points of each segment of the segmented fitting track in the current fitting track to be corrected.

3. The method of claim 2, further comprising:

and when judging that the current track form disturbance processing is accepted, taking the second fitting error as a first fitting error of the disturbed fitting track, and taking the disturbed fitting track as a fitting track to be corrected to execute track form disturbance processing until the frequency of the current track form disturbance processing reaches a preset disturbance frequency.

4. The method according to any one of claims 1 to 3, wherein the predetermined fitting error cost function comprises at least one of the following fitting error impact factors:

the fitting degree of the fitting track and the data sampling points in the range covered by the fitting track;

the tangent angle jump of the adjacent curves in the fitting track at the connection position exceeds the maximum allowable angle jump number;

the curvature jump of the adjacent curves in the fitting track at the connection position exceeds the maximum allowable curvature jump number;

the number of curves in the fitted trajectory whose curve length exceeds the maximum allowable length.

5. The method of claim 4, wherein when the preset fitting error cost function comprises a plurality of fitting error impact factors, the preset fitting error cost function comprises determining by:

obtaining weight coefficients of the plurality of fitting error influence factors;

performing weighted calculation on the fitting error influence factors based on the weighting coefficients of the fitting error influence factors to obtain the preset fitting error cost function;

and the weight coefficient of each fitting error influence factor represents the influence degree of the fitting error influence factor on the difference between the fitting track and the actual track corresponding to the data sampling point covered by the fitting track.

6. The method of claim 4, wherein the degree of fit of the fitted trace to the data sample points within the range covered by the fitted trace is determined by:

performing broken line processing on the fitting track to obtain a plurality of sections of fitting broken line tracks;

establishing a multi-section sampling broken line track based on the data sampling points in the coverage range of the fitting track;

determining a first extension area of the multi-segment fitting broken line track and a second extension area of the multi-segment sampling broken line track, and calculating the contact ratio of the first extension area and the second extension area; calculating the ratio of the length of the fitting track to the length of the maximum allowable fitting track;

and calculating the product between the contact ratio and the ratio, and taking a negative numerical value of the product as the contact ratio of the fitting track and the data sampling points in the range covered by the fitting track.

7. The method according to any one of claims 1 to 3, wherein the predetermined number of perturbations comprises a number of perturbation iterations determined based on a convergence speed of the predetermined fitting error cost function.

8. A data processing apparatus, characterized in that the apparatus comprises:

the device comprises a to-be-corrected fitting track determining module, a to-be-corrected fitting track determining module and a to-be-corrected fitting track determining module, wherein the to-be-corrected fitting track determining module is used for determining an initial fitting track of a to-be-fitted data sampling point, the initial fitting track is used as the to-be-corrected fitting track, and the to-be-fitted data sampling point comprises a data point of an object extracted from image information containing the object needing track fitting;

the first fitting error calculation module is used for calculating a first fitting error of the fitting track to be corrected based on a preset fitting error cost function, and the preset fitting error cost function represents the difference between the fitting track and an actual track corresponding to a data sampling point covered by the fitting track;

the trajectory form disturbance processing module is used for performing trajectory form disturbance processing on the fitting trajectory to be corrected to obtain a disturbed fitting trajectory, wherein the trajectory form disturbance processing comprises trajectory splitting processing on each section of fitting trajectory in the fitting trajectory to be corrected, or trajectory combining processing on adjacent section fitting trajectories in the fitting trajectory to be corrected, or moving processing on connecting points between adjacent section fitting trajectories in the fitting trajectory to be corrected; or, performing transverse movement processing on the control points of each section of the piecewise fitting track in the fitting track to be corrected, or performing longitudinal movement processing on the control points of each section of the piecewise fitting track in the fitting track to be corrected;

the second fitting error calculation module is used for calculating a second fitting error of the disturbed fitting track based on a preset fitting error cost function;

the first judging module is used for judging whether the second fitting error is smaller than the first fitting error;

the first data processing module is used for taking the second fitting error as a first fitting error of the disturbed fitting track and taking the disturbed fitting track as a fitting track to be corrected to execute track form disturbance processing when the judgment result of the first judging module is yes, and the frequency of the current track form disturbance processing reaches a preset disturbance frequency;

and the fitting track determining module is used for taking the fitting track reaching the preset disturbance times as a target fitting track of the data sampling point to be fitted.

9. A data processing server, characterized in that the server comprises a processor and a memory, in which at least one instruction, at least one program, a set of codes, or a set of instructions is stored, which is loaded and executed by the processor to implement the data processing method according to any one of claims 1 to 7.

10. A computer readable storage medium having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement the data processing method according to any one of claims 1 to 7.

Images