阅读说明：本技术 轨迹去噪的处理方法、装置以及电子设备 (Track denoising processing method and device and electronic equipment ) 是由 石传基 于 2018-07-20 设计创作，主要内容包括：本发明实施例提供一种轨迹去噪的处理方法、装置以及电子设备,其中,方法包括：获取轨迹点数据,并采用滑动窗口按时间顺序多次滑动以对轨迹点进行划分；根据每次被划分到所述滑动窗口中的轨迹点的特征,调整去噪算法中的参数值；采用每次调整后的所述去噪算法对当次被划分到所述滑动窗口中的轨迹点进行去噪处理,保留非噪声轨迹点。本发明实施例的方案,能够提高从轨迹点中去除噪声点的准确率,使得去噪后的轨迹更贴近真实轨迹。(The embodiment of the invention provides track denoising processing methods and devices and electronic equipment, wherein the method comprises the steps of obtaining track point data, adopting a sliding window to slide for multiple times according to a time sequence to divide the track points, adjusting parameter values in a denoising algorithm according to the characteristics of the track points divided into the sliding window every time, adopting the denoising algorithm adjusted every time to denoise the track points divided into the sliding window every time, and keeping non-noise track points.)

1, track denoising processing method, comprising:

obtaining track point data, and adopting a sliding window to slide for multiple times according to the time sequence so as to divide the track points;

adjusting parameter values in a denoising algorithm according to the characteristics of the track points divided into the sliding window each time;

and denoising the track points which are divided into the sliding window at the current time by adopting the denoising algorithm after each adjustment, and reserving non-noise track points.

2. The method of claim 1, wherein the denoising algorithm comprises a Dbscan clustering algorithm;

the adjusting the parameter values in the denoising algorithm according to the characteristics of the track points divided into the sliding window each time comprises:

and adjusting the clustering radius and/or the minimum clustering number in the Dbscan clustering algorithm according to the characteristics of the track points which are divided into the sliding window each time.

3. The method of claim 2, wherein the features of the trace points comprise: interval time between adjacent track points and track scene speed;

the adjusting the clustering radius in the Dbscan clustering algorithm according to the characteristics of the track points divided into the sliding window each time includes:

calculating scene distance between the adjacent track points according to the interval time between the adjacent track points and the track scene speed;

and adjusting the clustering radius according to the scene distance between the adjacent track points.

4. The method of claim 2, wherein the features of the trace points comprise: actual distance between adjacent trace points;

the adjusting the clustering radius in the Dbscan clustering algorithm according to the characteristics of the track points divided into the sliding window each time includes:

and adjusting the clustering radius according to the actual distance between the adjacent track points.

5. The method of claim 2, wherein the features of the trace points comprise: the number of tracking points;

the adjusting the minimum number of clusters in the Dbscan clustering algorithm according to the characteristics of the track points divided into the sliding window each time comprises:

adjusting the minimum number of clusters to any number that is greater than half and less than the total number of the trace points in the sliding window.

6. The method of claim 1, further comprising:

calculating the center position of the initial track point which is divided into the sliding window and reserved;

if the distance between the starting track point and the central position is smaller than the preset distance, the starting track point is reserved, otherwise, the position drift of the starting track point is determined, and the starting track point is removed.

7. The method of any of , wherein the method further comprises:

and dynamically adjusting the size of the sliding window according to the time sequence.

8, track denoising processing device, comprising:

the data acquisition module is used for acquiring track point data and adopting a sliding window to slide for multiple times according to the time sequence so as to divide the track points;

the parameter adjusting module is used for adjusting parameter values in a denoising algorithm according to the characteristics of the track points divided into the sliding window each time;

and the data denoising module is used for denoising the track points which are divided into the sliding window at the current time by adopting the denoising algorithm after each adjustment, and reserving non-noise track points.

9. The apparatus of claim 8, wherein the denoising algorithm comprises a Dbscan clustering algorithm;

and the parameter adjusting module is used for adjusting the clustering radius and/or the minimum clustering number in the Dbscan clustering algorithm according to the characteristics of the track points which are divided into the sliding window each time.

10. The apparatus of claim 9, wherein the features of the trace points comprise: interval time between adjacent track points and track scene speed;

the parameter adjustment module comprises:

the distance calculation unit is used for calculating the scene distance between the adjacent track points according to the interval time between the adjacent track points and the track scene speed;

and the radius adjusting unit is used for adjusting the clustering radius according to the scene distance between the adjacent track points.

11. The apparatus of claim 9, wherein the features of the trace points comprise: actual distance between adjacent trace points;

and the parameter adjusting module is used for adjusting the clustering radius according to the actual distance between the adjacent track points.

12. The apparatus of claim 9, wherein the features of the trace points comprise: the number of tracking points;

the parameter adjusting module is used for adjusting the minimum clustering number to any number which is greater than half of the number of the track points in the sliding window and less than the total number.

13. The apparatus of claim 8, further comprising:

the center calculation module is used for calculating the center position of the initial track point which is divided into the sliding window and reserved;

and the drift detection module is used for reserving the initial track point if the distance between the initial track point and the central position is less than a preset distance, otherwise, determining the position drift of the initial track point, and removing the initial track point.

14. The apparatus of any one of claims 8-13, , further comprising:

and the window adjusting module is used for dynamically adjusting the size of the sliding window according to the time sequence.

15, an electronic device, comprising:

a memory for storing a program;

a processor, coupled to the memory, for executing the program for:

obtaining track point data, and adopting a sliding window to slide for multiple times according to the time sequence so as to divide the track points;

adjusting parameter values in a denoising algorithm according to the characteristics of the track points divided into the sliding window each time;

and denoising the track points which are divided into the sliding window at the current time by adopting the denoising algorithm after each adjustment, and reserving non-noise track points.

Technical Field

The present application relates to the field of computer technologies, and in particular, to a processing method and apparatus for removing noise in tracks, and an electronic device.

Background

In the existing real-time cleaning algorithm or technical scheme of the GPS track, the track denoising processing which is usually adopted mainly utilizes various spatial clustering algorithms or filtering algorithms.

The clustering algorithm comprises a grid clustering method, a K median clustering method and the like, and is mainly used for separating normal track points and noise points through the space aggregation of the track points, but the time dimension characteristic of the track is not considered generally, or the performance of the clustering algorithm is too low to meet the requirement of online real-time performance;

the filtering and denoising mainly comprises mean filtering, median filtering and the like, and the main idea is to replace suspicious noise points with fixed point mean values or median values before and after track points (usually, speed is calculated through track points before and after a time sequence, and speed abnormal points are judged to be suspicious noise points).

In addition, the real-time track processing scheme usually does not consider the characteristic that the starting point is easy to drift when the GPS track is in cold start too much, and direct denoising processing may not completely solve the special drift of the starting point, because there are no other points in front of the starting point for judging the speed and the like to be used as denoising references.

Disclosure of Invention

The invention provides track denoising processing methods and devices and electronic equipment, which can improve the accuracy of removing noise points from track points and enable denoised tracks to be closer to real tracks.

In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:

, providing track denoising processing methods, including:

obtaining track point data, and adopting a sliding window to slide for multiple times according to the time sequence so as to divide the track points;

adjusting parameter values in a denoising algorithm according to the characteristics of the track points divided into the sliding window each time;

and denoising the track points which are divided into the sliding window at the current time by adopting the denoising algorithm after each adjustment, and reserving non-noise track points.

In a second aspect, there are kinds of processing apparatus for denoising trajectory, including:

the data acquisition module is used for acquiring track point data and adopting a sliding window to slide for multiple times according to the time sequence so as to divide the track points;

the parameter adjusting module is used for adjusting parameter values in a denoising algorithm according to the characteristics of the track points divided into the sliding window each time;

and the data denoising module is used for denoising the track points which are divided into the sliding window at the current time by adopting the denoising algorithm after each adjustment, and reserving non-noise track points.

In a third aspect, electronic devices are provided, comprising:

a memory for storing a program;

a processor, coupled to the memory, for executing the program for:

obtaining track point data, and adopting a sliding window to slide for multiple times according to the time sequence so as to divide the track points;

adjusting parameter values in a denoising algorithm according to the characteristics of the track points divided into the sliding window each time;

and denoising the track points which are divided into the sliding window at the current time by adopting the denoising algorithm after each adjustment, and reserving non-noise track points.

The invention provides track denoising processing methods, devices and electronic equipment, wherein after track point data to be processed are obtained, a sliding window is adopted to slide for multiple times according to a time sequence to divide track points, then parameter values in a denoising algorithm are adjusted according to the characteristics of the track points divided into the sliding window every time, the denoising algorithm after each parameter adjustment is utilized to denoise the track points divided into the sliding window every time, and non-noise track points are reserved.

The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 is a schematic diagram of processing logic for track denoising according to an embodiment of the present invention;

FIG. 2 is a diagram of a track denoising processing system according to an embodiment of the present invention;

FIG. 3 is a flowchart of a track denoising processing method according to an embodiment of the present invention;

FIG. 4 is a flowchart of a track denoising processing method according to an embodiment of the present invention;

FIG. 5 is a flow chart of a parameter adjustment method according to an embodiment of the present invention;

FIG. 6 is a flowchart illustrating a parameter adjustment method according to a second embodiment of the present invention;

FIG. 7 is a flow chart of a parameter adjustment method according to an embodiment of the present invention;

FIG. 8 is a flowchart of a method for filtering out start trace points according to an embodiment of the present invention;

FIG. 9 is a diagram illustrating a structure of a track denoising processing apparatus according to an embodiment of the present invention;

FIG. 10 is a second block diagram of a track denoising processing apparatus according to an embodiment of the present invention;

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

FIG. 12 is a fourth block diagram of a track denoising processing apparatus according to an embodiment of the present invention;

fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Firstly, after track point data to be denoised are obtained, a sliding window is adopted to slide for a plurality of times according to the time sequence generated by the track points to divide the track points, the repeated track points do not exist between the track points in two adjacent windows divided by the sliding window, and the track points extracted by the sliding window each time need to be processed by two steps:

, extracting feature data of track points in the current sliding window, such as the number of the track points, the interval time between two adjacent track points, the actual distance, the track scene speed and other features, and then adjusting parameters of the denoising algorithm adopted at the current time based on the features, so that the adjusted denoising algorithm is more suitable for denoising the track point data divided into the sliding window at the current time, and obtaining the track points closer to the actual situation.

And secondly, denoising the track point data which is divided into the sliding window at the current time by using the denoising algorithm after the parameter value is adjusted, and reserving the non-noise track points.

In a practical application scenario, the type of denoising algorithm may not be limited to various spatial clustering algorithms or filtering algorithms. It should be emphasized that the core of the present solution is not limited to the specific algorithm content of the denoising algorithm, but in the process of processing the track points by using the denoising algorithm, the parameter values in the denoising algorithm adopted at the present time are dynamically adjusted according to the spatial distribution characteristics of the track points in different time periods (sliding windows), so that the present solution is more suitable for denoising the data of the track points divided into the sliding windows at the present time, and the track points closer to the actual situation are obtained.

In addition, the size of the adopted sliding window (the number of track points in the window) can be adjusted according to the time sequence or the characteristics of the track points in different spatial ranges, so that the whole denoising process is more flexible in data processing.

Based on the schematic processing logic diagram of track denoising shown in fig. 1, fig. 2 is a structural diagram of a processing system for track denoising provided in the embodiment of the present invention. As shown in fig. 2, the system includes: a terminal device 210, a track denoising processing device 220; wherein:

the terminal device 210 may be a portable terminal device such as a mobile phone, a palm computer, a wearable device, etc. having positioning and navigation functions, and is configured to acquire the position of the device, i.e., the track point, in real time, and upload the position to the track denoising processing device 220 for denoising.

And the track denoising processing device 220 is used for denoising the track point data uploaded by the terminal device 210, reserving non-noise track points, and transmitting the reserved track points to the terminal device 210 for track display.

In an actual application scenario, the terminal device 210 may be a standardized concept, and the essence of the terminal device may include a plurality of specific terminal devices, and the terminal device for monitoring the operation track and the terminal device for displaying the operation track may not be limited to terminal devices.

The track denoising processing device 220 may specifically include:

the data acquisition module is used for acquiring track point data and adopting a sliding window to slide for multiple times according to the time sequence so as to divide the track points;

the parameter adjusting module is used for adjusting parameter values in the denoising algorithm according to the characteristics of the track points divided into the sliding window each time;

and the data denoising module is used for denoising the track points which are divided into the sliding window at the current time by adopting the denoising algorithm after each adjustment, and reserving the non-noise track points.

The trace point data to be processed acquired by the data acquisition module may be trace points acquired and uploaded by the terminal device 210 in real time, or may be trace points generated historically. In order to facilitate data processing, the obtained track points can be repeatedly slid according to the time sequence by adopting a sliding window to divide the track points, so that the track points are divided into a plurality of groups of track point data in the sliding window at different time points. The characteristics of the track points contained in each sliding window after the sliding window is divided are utilized, the parameter values in the denoising algorithm are adjusted, so that the adjusted denoising algorithm is more suitable for denoising the track point data divided into the sliding window at the current time, and the track points closer to the actual condition are obtained. And finally, the data denoising module denoises the track points contained in the current divided sliding window by adopting the adjusted denoising algorithm, reserves the non-noise track points, and transmits the non-noise track points to the terminal equipment 210 for display.

Further , the denoising algorithm may include a Dbscan clustering algorithm;

correspondingly, the parameter adjusting module is used for adjusting the clustering radius and/or the clustering minimum number in the Dbscan clustering algorithm according to the characteristics of the track points which are divided into the sliding window each time.

The Dbscan clustering algorithm is taken as an example of a denoising algorithm, the Dbscan clustering algorithm is a typical density-based spatial clustering algorithm and comprises two important parameters, namely a clustering radius and a clustering minimum number, the parameter values of the two parameters directly influence a clustering result, the characteristics of track points can change along with time and space in the track forming process, if a simple system adopts the same clustering parameter value, the clustering effect can be influenced, and the final denoising effect is reduced.

, the characteristics of the track points include the interval time between adjacent track points and the track scene speed;

accordingly, the parameter adjustment module may include:

the distance calculation unit is used for calculating the scene distance between the adjacent track points according to the interval time between the adjacent track points and the track scene speed;

and the radius adjusting unit is used for adjusting the clustering radius according to the scene distance between the adjacent track points.

Specifically, the positioning data of the moving track is sampled periodically, so that the interval time between each two adjacent track points is the same, that is, the data sampling period; the track scene speed refers to track speeds in different service scenes, such as a track speed of a pedestrian, a track speed of a bicycle, a track speed of an electric vehicle, a track speed of a motor vehicle and the like. And calculating the scene distance between the adjacent track points according to the interval time between the adjacent track points and the track scene speed, wherein the scene distance is not the actual distance between the track points but the estimated distance under the same track scene. The actual distance between every two adjacent track points can be roughly estimated according to the scene distance, so that the clustering radius of the Dbscan clustering algorithm can be flexibly adjusted.

, the characteristics of the trace points may include actual distance between adjacent trace points;

correspondingly, the parameter adjusting module can be used for adjusting the clustering radius according to the actual distance between the adjacent track points.

Specifically, after data of the track points are obtained, the actual distance between two adjacent track points is calculated, and then the clustering radius of the Dbscan clustering algorithm is adjusted according to the actual distance.

, the trace points can also include the number of trace points;

correspondingly, the parameter adjusting module is further configured to adjust the minimum number of clusters to any number that is greater than half the number of track points in the sliding window and less than the total number.

Specifically, in order to ensure that clustering clusters are obtained after each clustering calculation in the sliding window, the clustering radius of the Dbscan clustering algorithm can be adjusted to any number which is more than half number and less than the total number of the track points in the sliding window, so that the calculation difficulty is simplified.

, the track denoising processing device may further include:

the center calculating module is used for calculating the center position of the initial track point which is divided into the sliding window and reserved;

and the drift detection module is used for reserving the initial track point if the distance between the initial track point and the central position is less than the preset distance, otherwise, determining the position drift of the initial track point, and removing the initial track point.

Specifically, in order to detect whether the initial track point in the track point data drifts, the center position of the track point which is initially divided into the sliding window and is retained after being processed by the denoising algorithm may be calculated, for example, the center position is directly calculated by using the core point clustered by the Dbscan clustering algorithm, or the center position is calculated by using algorithms such as median filtering for the track point retained after being processed by the denoising algorithm. After the central position is obtained, whether the distance between the initial track point and the central position is smaller than a preset distance or not is judged, if the distance is smaller than the preset distance, the track point is normally sampled and does not drift, the initial track point is reserved, and otherwise, the initial track point is determined to drift, and the initial track point is removed.

, the track denoising processing device may further include:

and the window adjusting module is used for dynamically adjusting the size of the sliding window according to the time sequence.

In order to fully reflect the characteristics of the track points in different time periods and different space regions, the size of the sliding window can be dynamically adjusted by referring to the distribution characteristics of the track points in time and space, so that the diversity of data processing modes is improved, and the denoising effect of the track point data is optimized.

The technical solution of the present application is further illustrated by a plurality of examples.