CN114997777A - Vehicle movement feature identification method based on track information - Google Patents
Vehicle movement feature identification method based on track information Download PDFInfo
- Publication number
- CN114997777A CN114997777A CN202210584713.1A CN202210584713A CN114997777A CN 114997777 A CN114997777 A CN 114997777A CN 202210584713 A CN202210584713 A CN 202210584713A CN 114997777 A CN114997777 A CN 114997777A
- Authority
- CN
- China
- Prior art keywords
- track
- parking
- suspected
- std
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0833—Tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Abstract
The invention relates to a vehicle movement characteristic identification method based on track information, which is based on a distance threshold value D std On the basis of identifying all suspected parking track points and driving track points contained in the vehicle track data, a plurality of adjacent suspected parking track points are classified into the same suspected parking track segment K, and the parking stability S of the vehicle corresponding to each suspected parking track segment K is depended on k Each suspected parking track segment K is further judged to identify a long-time parking track segment and a short-time parking track segment, so that the identification efficiency and the identification accuracy can be effectively improved, and reliable data support is provided for the follow-up analysis of the running state of the vehicle in a certain time period and the running characteristics of freight vehicles in the area.
Description
Technical Field
The invention relates to the technical field of vehicle running state identification, in particular to a vehicle moving characteristic identification method based on track information.
Background
Along with the development of socio-economic, the urban logistics industry is rapidly developed, the development of information technology promotes a large amount of freight vehicle GPS track data, and the large amount of vehicle track data provides effective data support for data analysts. In the prior art, researches on vehicle trajectory data mainly include vehicle trajectory clustering, trajectory anomaly point detection, trajectory classification and the like, wherein the trajectory classification is to abstract a trajectory model by counting and analyzing space-time characteristics among different trajectories of the trajectory data, and use the trajectory model as a classifier to classify the trajectory of a target vehicle.
The track data of the freight vehicle in a certain time period generally consists of a series of track points arranged according to a time sequence, and each track point corresponds to track data for describing the space-time motion state of the freight vehicle in a certain geographic space range and time period, for example, a record is uploaded by a general freight vehicle at intervals of 30s to serve as the track data of one track point. The track data of the track points generally comprise vehicle identifications (carID), track point recording or occurring time (t) and longitude and latitude coordinates (P) of the track points so as to visually show the geographical positions of a certain vehicle at a certain time.
In general, the original vehicle GPS track data usually does not include parking information, and therefore the parking behavior of the vehicle in the actual running process cannot be directly and effectively identified from the original vehicle GPS track data. Therefore, the chinese patent with the publication number CN111340427B and the name of "a method for identifying the running state of a truck based on track data" discloses a method for identifying the running state of a truck based on the track data of the truck, which mainly obtains a distance difference and a staying time difference between two adjacent track points through calculation in the stage of identifying the track points, and compares the distance difference and the staying time difference with a preset distance threshold and a preset time threshold respectively, thereby identifying the staying track points and the running track points in the track data. However, the track points are often identified in such a way, so that certain ambiguity exists, the identification accuracy is not high, and the error is large.
Disclosure of Invention
The invention aims to provide a vehicle movement characteristic identification method based on track information, which is used for solving the technical problems of low accuracy and large error in the prior art when vehicle track points are identified.
The purpose of the invention is realized by the following technical scheme:
a vehicle movement feature identification method based on track information comprises the following steps:
s1, obtaining track data of a vehicle in a certain time period, wherein the track data comprises a plurality of track points P which are arranged in sequence according to a time sequence i Wherein, i is 1, 2, 3;
s2, setting a distance threshold value D std Sequentially calculating the distance difference Delta D between two adjacent track points i，i+1 The distance difference Delta D between two adjacent track points i，i+1 And a distance threshold D std Comparing to identify suspected parking track points and driving track points in the track data, marking the driving track points as 0 and the suspected parking track points as 1;
s3, classifying a plurality of adjacent suspected parking track points into the same suspected parking track segment K, wherein K is 1, 2 and 3;
s4, setting a parking stability threshold S std Calculating the parking stability S of each suspected parking track segment K k Sequentially setting the parking stability S of each suspected parking track segment K k And a parking stability threshold S std Comparing;
if S k ≥S std Classifying the suspected parking track segment K into a long-time parking track segment, and marking all suspected parking track points contained in the suspected parking track segment K as long-time parking track points;
if S k ＜S std And classifying the suspected parking track segment K into a transient parking track segment, and marking all suspected parking track points contained in the suspected parking track segment K as transient parking track points.
Optionally, in step S4, the parking stability S of the suspected parking trajectory segment K k Calculated by the following formula:
wherein, T k Is a suspected parking track segmentCumulative residence time of K, D k And the accumulated driving distance of the suspected parking track fragment K is obtained.
Optionally, the method further comprises the steps of:
s5, setting a threshold Din of transfer distance in the field std Calculating the driving distance D between two adjacent suspected parking track segments K k ， k+1 Driving distance delta D between two adjacent suspected parking track segments K k，k+1 Threshold value Din of transfer distance from field std A comparison is made to identify an intra-field transition track segment.
Further, in step S5, the driving distance Δ D between two adjacent suspected parking trajectory segments K k，k+1 The sum of the driving distances of all suspected parking track points and all driving track points between two adjacent suspected parking track segments K is obtained;
at this time, if Δ D k，k+1 ≥Din std Classifying all suspected parking track points and all driving track points between two adjacent suspected parking track segments K into the same non-in-field transfer track segment;
if Δ D k，k+1 ＜Din std And classifying all the suspected parking track points and all the driving track points between two adjacent suspected parking track segments K into the same in-field transfer track segment.
Optionally, step S2 specifically includes:
s21, a first track point P in the track data is processed 1 As a calculation starting point, marking the calculation starting point as a suspected parking track point, and marking the suspected parking track point as 1;
s22, sequentially calculating two adjacent track points P i And P i+1 Distance difference Δ D therebetween i，i+1 If Δ D i，i+1 ＜D std Then point of track P i+1 Marking as a suspected parking track point, if delta D i，i+1 ≥D std Then point of track P i+1 And recording as a driving track point.
Further, the distance difference Δ D between two adjacent track points i，i+1 Calculating by adopting a hemiversine formula, specifically:
wherein, R is the radius of the earth,
the longitude of the track point is shown, and the lambda is the latitude of the track point.
Optionally, a distance threshold D std The setting range of (1) is: d is more than 0km std ＜1km。
Further, the intra-field transfer distance threshold Din std The setting range of (1) is: din is less than 0km std ＜2km。
The technical scheme of the embodiment of the invention at least has the following advantages and beneficial effects:
1. the invention provides a vehicle movement characteristic identification method based on a distance threshold value D std On the basis of identifying all suspected parking track points and driving track points contained in the vehicle track data, a plurality of adjacent suspected parking track points are classified into the same suspected parking track segment K, and the parking stability S of the vehicle corresponding to each suspected parking track segment K is depended on k Each suspected parking track segment K is further judged to identify a long-time parking track segment and a short-time parking track segment, so that the identification efficiency and the identification accuracy can be effectively improved, and reliable data support is provided for the follow-up analysis of the running state of the vehicle in a certain time period and the running characteristics of freight vehicles in the area.
2. The vehicle movement characteristic identification method provided by the invention is characterized in that on the basis of identifying the running track points, the long-time parking track points and the short-time parking track points in the vehicle track data, the running distance D between two adjacent suspected parking track segments K is calculated k，k+1 And will travel a distance D k，k+1 Threshold value Din of transfer distance from field std The comparison can effectively and accurately identify the in-field transfer track segment, thereby judging whether the parking behavior of the vehicle is the parking generated when the in-field transfer occursThe behavior provides reliable data support.
Drawings
Fig. 1 is a flowchart of a vehicle movement feature identification method according to embodiment 1 of the present invention;
fig. 2 is a schematic diagram of identification of suspected parking track points provided in embodiment 1 of the present invention;
fig. 3 is a flowchart illustrating a process of determining a suspected parking track segment according to embodiment 1 of the present invention;
fig. 4 is a flowchart illustrating identification of intrafield transition trace segments according to embodiment 2 of the present invention.
Detailed Description
Example 1
Referring to fig. 1 to 3, the present embodiment provides a method for identifying vehicle movement characteristics based on track information, including the following steps:
s1, obtaining track data of a vehicle in a certain time period, wherein the track data comprises a plurality of track points P which are arranged in sequence according to a time sequence i Wherein i is 1, 2, 3. It is understood that the trajectory data of the vehicle in a certain period of time may be the trajectory data of the vehicle in 24 hours a day, or the trajectory data of the vehicle in a certain period of time, in this case, P 1 Data representing the first point in the vehicle trajectory data, P 2 And data representing the second track point in the vehicle track data, and so on.
It should be noted that, in consideration of the fact that the original trajectory data of the vehicle often has certain repeated data, abnormal data and missing data, before the feature recognition is performed on the trajectory data of the vehicle, a series of trajectory data of the vehicle within a certain time period should be preprocessed, so as to further improve the accuracy when the feature recognition is performed by using the trajectory data of the vehicle. The vehicle trajectory data preprocessing comprises the steps of repeated value processing, missing value processing, abnormal value processing and the like.
S2, after track data of the vehicle within a certain time period are obtained, a distance threshold value D is set std Sequentially calculating the distance difference Delta D between two adjacent track points i，i+1 The distance difference Delta D between two adjacent track points i，i+1 And a distance threshold D std And comparing to identify a suspected parking track point and a driving track point in the track data, and marking the driving track point as 0 and the suspected parking track point as 1.
It is understood that the distance threshold D in the present embodiment is different depending on the running condition of different vehicles std The distance threshold D is set as an adjustable parameter, and can be set according to actual conditions in actual implementation, for example, the distance threshold D of the embodiment std The setting range of (1) is: d is more than 0km std ＜1km。
In this embodiment, in combination with the schematic diagram of identifying the suspected parking track points and the driving track points shown in fig. 2, the distance difference Δ D between two adjacent track points is calculated in step S2 i，i+1 And by a distance difference DeltaD i，i+1 The process of identifying suspected parking track points and driving track points in the track data specifically comprises the following steps:
s21, a first track point P in the track data is processed 1 As a calculation starting point, marking the calculation starting point as a suspected parking track point, and marking the calculation starting point as 1;
s22, sequentially calculating two adjacent track points P i And P i+1 Distance difference Δ D between i，i+1 If Δ D i，i+1 ＜D std Description of the points of the vehicle from track P i To point of track P i+1 The distance traveled in this process is less than a distance threshold D std Then point of track P i+1 Marking as a suspected parking track point and marking as 1; on the contrary, if Δ D i，i+1 ≥D std Description of the points of the vehicle from track P i To point of track P i+1 The distance traveled in the process is greater than a distance threshold D std Then point of track P i+1 Marked as a driving track point and marked as 0.
And repeating the operation until all track points in the vehicle track data are identified so as to identify all suspected parking track points and all driving track points.
It should be noted that the distance difference Δ D between two adjacent track points i，i+1 The calculation can be performed by adopting a hemiversine formula, which specifically comprises the following steps:
wherein, R is the radius of the earth,
and the longitude of the track point, and the latitude of the track point.
And S3, after all suspected parking track points and all driving track points contained in the vehicle track data are to be identified, in order to improve the efficiency of subsequently identifying long-time parking track points and short-time parking track points, classifying a plurality of adjacent suspected parking track points into the same suspected parking track segment K, wherein K is 1, 2 and 3, and is used for representing the second suspected parking track segment. For example, with continued reference to FIG. 2, if P 1 And P 2 If all are suspected parking track points, P is calculated 1 And P 2 Classifying the parking track segment into the same suspected parking track segment K, wherein the K is 1, and the first suspected parking track segment is represented; if P 3 、P 4 And P 5 All are running track points, then P 3 、P 4 And P 5 Classifying the same driving track segment; if P 6 、P 7 、P 8 And P 9 If all are suspected parking track points, P is calculated 6 、P 7 、P 8 And P 9 The same suspected parking track segment K is classified, and K is 2, which represents the second suspected parking track segment. And repeating the steps until all the suspected parking track points contained in the vehicle track data are classified into a plurality of different suspected parking track segments K.
S4, after all suspected parking track fragments K are identified, based on the fact that the vehicles are parked in the interval range corresponding to the suspected parking track fragments K for a certain duration and have certain stability in time, the parking stability S of the vehicle corresponding to each suspected parking track fragment K is further analyzed k Can effectively judgeThe suspected parking track fragment K belongs to a long-time parking track fragment or a short-time parking track fragment, and meanwhile, the parking stability S of the vehicle is obtained k As the basis of judging whether the suspected parking track fragment K belongs to the long-time parking track fragment or the short-time parking track fragment, the accuracy in recognition can be effectively improved, and therefore the long-time parking track point and the short-time parking track point in the vehicle track data can be recognized more accurately.
Specifically, the parking stability threshold S is set first std Wherein the parking stability threshold S std And the adjustable parameter is also set, and can be set according to the actual situation in the actual implementation process. Next, with reference to the flow chart of the suspected parking trajectory segments shown in fig. 3, the parking stability S of each suspected parking trajectory segment K is calculated k Sequentially comparing the parking stability S of each suspected parking trajectory segment K k And a parking stability threshold S std Comparing;
at this time, if S k ≥S std Classifying the suspected parking track segment K into a long-time parking track segment, marking all suspected parking track points contained in the suspected parking track segment K as long-time parking track points, and indicating that the parking behaviors of the vehicle at the track points belong to long-time parking behaviors, such as parking behaviors of a driver during rest or goods loading and unloading;
on the contrary, if S k ＜S std The suspected parking track segment K is classified as a temporary parking track segment, and all suspected parking track points contained in the suspected parking track segment K are recorded as temporary parking track points, which indicates that the parking behavior of the vehicle at the track points belongs to a short-time parking behavior in the driving process, such as waiting for a traffic light or parking behavior during refueling.
And repeating the operation until all the suspected parking track segments K are judged.
In this embodiment, the parking stability S of the suspected parking trajectory segment K in step S4 is k Calculated by the following formula:
wherein, T k The accumulated staying time of the suspected parking track segment K, D k And the accumulated driving distance is the accumulated driving distance of the suspected parking track fragment K. It can be understood that, based on that all track points in the vehicle track data are arranged in sequence according to time sequence, the accumulated staying time T of the vehicle corresponding to the suspected parking track segment K can be calculated by obtaining the time when the first suspected parking track point in the suspected parking track segment K is located and the time when the last suspected parking track point is located k (ii) a Similarly, by obtaining the driving distance between all the suspected parking track points of the suspected parking track segment K, the accumulated driving distance D of the vehicle corresponding to the suspected parking track segment K can be calculated k 。
Therefore, the vehicle movement feature identification method provided by the embodiment is based on the distance threshold value D std On the basis of identifying all suspected parking track points and driving track points contained in the vehicle track data, a plurality of adjacent suspected parking track points are classified into the same suspected parking track segment K, and the parking stability S of the vehicle corresponding to each suspected parking track segment K is depended on k Each suspected parking track segment K is further judged to identify a long-time parking track segment and a short-time parking track segment, so that the identification efficiency and the identification accuracy can be effectively improved, and reliable data support is provided for the follow-up analysis of the running state of the vehicle in a certain time period and the running characteristics of freight vehicles in the area.
Example 2
Considering that it is often analyzed whether the vehicle belongs to an on-site transition (i.e., moves within a specific work area, for example, moves within a factory area) when analyzing the running state of the vehicle in a normal situation, in example 1, on the basis of identifying a travel track point, a long-time parking track point, and a short-time parking track point included in the vehicle trajectory data, a step of determining whether the vehicle belongs to the on-site transition is further added, which specifically includes:
s5, setting a threshold Din of transfer distance in the field std Calculating the driving distance D between two adjacent suspected parking track segments K k ， k+1 Driving distance delta D between two adjacent suspected parking track segments K k，k+1 Threshold value Din of transfer distance from field std A comparison is made to identify an intra-field transition track segment. It is understood that the intra-field transfer distance threshold Din of the present embodiment std Also set as an adjustable parameter, which can be set according to actual conditions in practical implementation, for example, considering that the distance traveled by a general freight vehicle when performing on-site transfer is often not greater than 2km, the on-site transfer distance threshold Din in this embodiment std The setting range of (1) is: din is less than 0km std ＜2km。
Specifically, in step S5, the driving distance Δ D between two adjacent suspected parking trajectory sections K is determined k，k+1 The sum of the driving distances of all suspected parking track points and all driving track points between two adjacent suspected parking track segments K is obtained;
at this time, if Δ D k，k+1 ≥Din std And classifying all suspected parking track points and all driving track points between two adjacent suspected parking track segments K into the same non-intra-field transfer track segment, and indicating that the parking behaviors corresponding to all suspected parking track points contained in the two adjacent suspected parking track segments K are not the parking behaviors when the intra-field transfer is performed.
If Δ D k，k+1 ＜Din std And classifying all the suspected parking track points and all the driving track points between the two adjacent suspected parking track segments K into the same in-field transfer track segment, and showing that the parking behaviors corresponding to all the suspected parking track points contained in the two adjacent suspected parking track segments K are the parking behaviors when the in-field transfer is carried out.
Therefore, the vehicle movement feature identification method provided by the embodiment identifies the driving track points, the long-time parking track points and the vehicle movement feature identification method in the vehicle track dataOn the basis of the short parking track points, the driving distance D between two adjacent suspected parking track segments K is calculated k，k+1 And will travel a distance D k，k+1 Threshold value Din of transfer distance from field std And comparing, and effectively and accurately identifying the in-field transfer track segment, thereby providing reliable data support for judging whether the parking behavior of the vehicle is the parking behavior generated during in-field transfer.
In addition, it should be noted that the vehicle movement characteristic identification method provided in this embodiment is applicable to identifying trajectory data of other similar vehicles in addition to identifying trajectory data of freight vehicles, for example, the method provided in this embodiment may also be used to identify trajectory data of passenger vehicles such as taxis or long-and-short-distance passenger cars, so as to analyze the operation state of the passenger vehicles within a certain period of time and the operation characteristics of the passenger vehicles within a certain area.
The present invention has been described in terms of the preferred embodiment, and it is not intended to be limited to the embodiment. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A vehicle movement feature identification method based on track information is characterized by comprising the following steps:
s1, obtaining track data of a vehicle in a certain time period, wherein the track data comprises a plurality of track points P which are arranged in sequence according to a time sequence i Wherein, i is 1, 2, 3;
s2, setting a distance threshold value D std Sequentially calculating the distance difference Delta D between two adjacent track points i，i+1 The distance difference Delta D between two adjacent track points i，i+1 And a distance threshold D std Comparing to identify suspected parking track points and driving track points in the track data, marking the driving track points as 0 and the suspected parking track points as 1;
s3, classifying a plurality of adjacent suspected parking track points into the same suspected parking track segment K, wherein K is 1, 2 and 3;
s4, setting a parking stability threshold S std Calculating the parking stability S of each suspected parking track segment K k Sequentially setting the parking stability S of each suspected parking track segment K k And a parking stability threshold S std Comparing;
if S k ≥S std Classifying the suspected parking track segment K into a long-time parking track segment, and marking all suspected parking track points contained in the suspected parking track segment K as long-time parking track points;
if S k ＜S std And classifying the suspected parking track segment K into a short parking track segment, and recording all suspected parking track points contained in the suspected parking track segment K as short parking track points.
2. The method for recognizing vehicle movement characteristics based on trajectory information according to claim 1, wherein in step S4, the parking stability S of the suspected parking trajectory segment K k Calculated by the following formula:
wherein, T k The accumulated staying time of the suspected parking track segment K, D k And the accumulated driving distance of the suspected parking track fragment K is obtained.
3. The method for recognizing the moving features of the vehicle based on the trajectory information as claimed in claim 1, further comprising the steps of:
s5, setting a threshold Din of transfer distance in the field std Calculating the driving distance D between two adjacent suspected parking track segments K k ， k+1 Driving distance delta D between two adjacent suspected parking track segments K k，k+1 Threshold of transfer distance from fieldDin std A comparison is made to identify an intra-field transition track segment.
4. The method according to claim 3, wherein in step S5, the distance Δ D between two adjacent suspected parking track segments K is determined k，k+1 The sum of the driving distances of all suspected parking track points and all driving track points between two adjacent suspected parking track segments K is obtained;
at this time, if Δ D k，k+1 ≥Din std Classifying all suspected parking track points and all driving track points between two adjacent suspected parking track segments K into the same non-in-field transfer track segment;
if Δ D k，k+1 ＜Din std And classifying all the suspected parking track points and all the driving track points between two adjacent suspected parking track segments K into the same in-field transfer track segment.
5. The method for recognizing the moving characteristics of the vehicle based on the trajectory information as claimed in claim 1, wherein the step S2 specifically includes:
s21, a first track point P in the track data is subjected to 1 As a calculation starting point, marking the calculation starting point as a suspected parking track point, and marking the calculation starting point as 1;
s22, sequentially calculating two adjacent track points P i And P i+1 Distance difference Δ D between i，i+1 If Δ D i，i+1 ＜D std Then point of track P i+1 Marking as a suspected parking track point if delta D i，i+1 ≥D std Then point of track P i+1 And recording as a driving track point.
6. The trajectory-information-based vehicle movement feature recognition method according to claim 5, wherein a distance difference Δ D between two adjacent trajectory points i，i+1 Calculating by adopting a hemiversine formula, specifically:
wherein, R is the radius of the earth,
the longitude of the track point is shown, and the lambda is the latitude of the track point.
7. The method according to claim 1, wherein the distance threshold D is a distance threshold std The setting range of (1) is: d is less than 0km std ＜1km。
8. The trajectory information-based vehicle movement feature recognition method according to claim 3, wherein the intra-field transfer distance threshold Din std The setting range of (1) is: din is less than 0km std ＜2km。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210584713.1A CN114997777A (en) | 2022-05-27 | 2022-05-27 | Vehicle movement feature identification method based on track information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210584713.1A CN114997777A (en) | 2022-05-27 | 2022-05-27 | Vehicle movement feature identification method based on track information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114997777A true CN114997777A (en) | 2022-09-02 |
Family
ID=83028529
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210584713.1A Pending CN114997777A (en) | 2022-05-27 | 2022-05-27 | Vehicle movement feature identification method based on track information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114997777A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115964545A (en) * | 2023-03-16 | 2023-04-14 | 四川国蓝中天环境科技集团有限公司 | Method for deducing pollution point location based on slag transport vehicle track point |
| CN115994324A (en) * | 2023-03-13 | 2023-04-21 | 浙江口碑网络技术有限公司 | Data processing method and device |
-
2022
- 2022-05-27 CN CN202210584713.1A patent/CN114997777A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115994324A (en) * | 2023-03-13 | 2023-04-21 | 浙江口碑网络技术有限公司 | Data processing method and device |
| CN115994324B (en) * | 2023-03-13 | 2023-07-18 | 浙江口碑网络技术有限公司 | Data processing method and device |
| CN115964545A (en) * | 2023-03-16 | 2023-04-14 | 四川国蓝中天环境科技集团有限公司 | Method for deducing pollution point location based on slag transport vehicle track point |
| CN115964545B (en) * | 2023-03-16 | 2023-05-30 | 四川国蓝中天环境科技集团有限公司 | Method for deducing pollution point location based on slag transport vehicle track point |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114997777A (en) | Vehicle movement feature identification method based on track information | |
| US9508257B2 (en) | Road detection logic | |
| CN111340427B (en) | Freight car running state identification method based on track data | |
| CN111554100B (en) | Expressway lane guiding method and device considering carbon emission of motor vehicle | |
| US11640560B2 (en) | Automated training data quality process | |
| CN109523787B (en) | Fatigue driving analysis method based on vehicle passing track | |
| US10444027B2 (en) | Parking lot entrance recognition method and system | |
| CN107590999B (en) | Traffic state discrimination method based on checkpoint data | |
| Borkar et al. | An efficient method to generate ground truth for evaluating lane detection systems | |
| CN111598347B (en) | Ultra-long travel segmentation optimization method for road transport vehicle | |
| CN111144485A (en) | Vehicle accident judgment method and system based on xgboost classification algorithm | |
| CN109493606B (en) | Method and system for identifying illegal parking vehicles on expressway | |
| CN114999181B (en) | Highway vehicle speed abnormality identification method based on ETC system data | |
| CN113127466A (en) | Vehicle track data preprocessing method and computer storage medium | |
| CN108665084B (en) | Method and system for predicting driving risk | |
| JP2019505892A (en) | Method and apparatus for predicting road conditions based on big data | |
| CN110097074B (en) | Vehicle track compression method based on sequence similarity | |
| CN108760239B (en) | Vehicle recognition device detection method and system | |
| CN116631187A (en) | Intelligent acquisition and analysis system for case on-site investigation information | |
| CN107622667B (en) | Method and system for detecting altered license plate number | |
| CN116168541A (en) | Data processing system for acquiring road traffic state | |
| CN114091581A (en) | Vehicle operation behavior type identification method based on sparse track | |
| CN114298634A (en) | Resident point identification method and device, electronic equipment and machine-readable storage medium | |
| CN114407661A (en) | Data-driven electric vehicle energy consumption prediction method, system, device and medium | |
| CN109448377B (en) | Method for evaluating vehicle driving safety by using satellite positioning data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |