WO2022233099A1 - Networked adas-based method for investigating spatial-temporal characteristics of road area traffic violation behavior - Google Patents

Abstract

Disclosed in the present invention is a networked ADAS-based method for investigating spatial-temporal characteristics of a road area traffic violation behavior, comprising: acquiring forward vehicle traffic violation behavior information perceived by all networked ADAS vehicles in an urban road traffic system during a traveling process; encoding the traffic violation behavior information, and packaging the traffic violation behavior information into structured data; uploading the structured data to a traffic data cloud platform, matching each traffic violation behavior with a road segment in a road of a selected area according to time information and longitude and latitude information, and outputting a traffic violation behavior spatial-temporal distribution diagram in each time period; performing statistical analysis on a road traffic violation behavior spatial-temporal state, and obtaining the occurrence frequency of traffic violation behaviors of each road segment; and performing clustering analysis on a road traffic violation behavior spatial-temporal distribution state to obtain an aggregation road segment and an aggregation time period of the traffic violation behaviors. The present invention can accurately and timely reflect the characteristics of traffic violation behaviors, and has a certain meaning for improving the road risk prevention and control level.

Description

A method for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS technical field

The invention relates to the fields of traffic safety and intelligent traffic, in particular to a method for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS.

Background technique

Road traffic accidents occur frequently in my country, and the fatality rate of road traffic accidents remains high. In recent years, with the rapid development of electronic industry and IT industry, more and more road traffic monitoring and management based on image processing have been applied to road traffic safety research.

According to statistics, more than 70% of the roads in my country are equipped with surveillance cameras. Based on the recording and monitoring of illegal behavior of road traffic vehicles based on surveillance cameras, image processing and pattern recognition methods can be used to identify lane lines, signal lights, and signs in the road traffic environment. Lines, etc., according to the trajectory characteristics of the vehicle and the motion state of the vehicle to determine the movement pattern of the vehicle, to provide strong evidence for the collection of traffic violations. However, in the case that some roadside cameras cannot be covered or the cameras cannot be photographed due to the obstruction of road traffic, traffic accident perpetrators often have a speculative mentality, which brings certain difficulties to the detection of the accident. In addition, the electronic police installed by the traffic control department can only cover a small area or very few road sections, and can only collect illegal evidence in a specific area, but cannot cover the entire road network.

At present, ADAS with rich functions and strong environmental awareness has been widely used in cars and commercial vehicles, which makes it possible for ADAS to obtain a large amount of traffic violation data. However, at present, the data collected by ADAS is mostly used offline, and effective data has not been uploaded online, so it is impossible to comprehensively collect traffic violations. In view of the current situation, the traffic data collected by a large number of vehicles equipped with ADAS can provide sufficient data sources for the investigation of traffic violations after network integration and analysis. Make full use of existing resources to provide support for the prevention and control of regional traffic accident risks.

SUMMARY OF THE INVENTION

The main purpose of the present invention is to provide a method for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS, which can quickly understand the state of the distribution of violations and provide support for road traffic risk prevention and control.

The technical scheme adopted in the present invention is:

Provided is a method for investigating spatiotemporal characteristics of road traffic violations based on networked ADAS, including the following steps:

S1. Obtain information on traffic violations of forward vehicles perceived by all networked ADAS vehicles in the urban road traffic system during driving;

S2. Encode the obtained traffic violation information, determine the time when the traffic violation occurred and the location of the illegal vehicle at that moment, and package the traffic violation code, violation time, and longitude and latitude of the illegal vehicle into structured data;

S3. Upload the structured data to the traffic data cloud platform, match the traffic violations on the road sections in the selected area according to the time information and latitude and longitude information, and output the time-space distribution map of the traffic violations in each time period;

S4. Statistically analyze the spatiotemporal state of road traffic violations to obtain the occurrence frequency of traffic violations in each road section; perform cluster analysis on the spatiotemporal distribution state of road traffic violations to obtain the aggregated road sections and aggregation periods of traffic violations.

Following the above technical solutions, the information on vehicle traffic violations includes illegal parking, illegal lane change, speeding, illegal U-turn/left turn, driving on the line, wrong-way traffic, pedestrian crossing the road, and driving/vehicle running a red light.

In connection with the above technical solution, in step S1, the urban road traffic system performs lane line recognition, vehicle feature recognition, vehicle motion trajectory recognition, and signal lights by positioning and image recognition methods according to the forward road traffic video collected by the networked ADAS vehicle through the video capture camera. Recognition, road sign and marking recognition, and then based on the identified basic road information and forward vehicle information, the machine learning algorithm is used to identify the traffic violations of forward vehicles.

Connect the above-mentioned technical scheme, the concrete method of step S3 is:

Taking the principle of adjacent intersections as one section, the urban area is divided into n sections, and the longitude and latitude information L _n , B _n at the center point O of each intersection is collected, and the actual distance between the two intersections is the section length. , and number the road segments as 1, 2...n in sequence, where n is a natural number;

Taking the structured data of an illegal act as a data point, according to the collected latitude and longitude coordinates, the data points are matched to each target road section in the city map, and the spatiotemporal distribution map of traffic illegal acts is obtained.

Connect the above technical scheme, the concrete method of step S4 is:

After matching the distribution of traffic violations on the target road section, firstly collect statistics on the traffic violations on the road section, and record the frequency of various violations in the target time period; The spatial clustering is based on the latitude and longitude location distribution of traffic violations, and the time clustering is based on the distribution of traffic violations on the time axis. The resulting spatiotemporal clustering centers are the aggregation points of traffic violations in time and space.

In connection with the above technical solution, in step S4, the time information recorded in the structured data of traffic violations is integrated, and divided into day, night, or interested time periods of morning peak and evening peak according to the time stamp, and then the latitude and longitude are used. The information associates traffic violations with the corresponding road sections in the selected road area, and obtains the distribution and aggregation of traffic violations on the corresponding road sections within a specific time period through statistical and cluster analysis. identify the situation.

The present invention also provides a system for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS, including:

The information acquisition module is used to acquire the traffic violation information of forward vehicles sensed by all connected ADAS vehicles in the urban road traffic system;

The encoding module is used to encode the obtained traffic violation information, determine the time when the traffic violation occurred and the location of the illegal vehicle at that moment, and package the traffic violation code, violation time, and longitude and latitude of the illegal vehicle into structured data;

The matching module is used to upload the structured data to the traffic data cloud platform, match the traffic violations on the road sections in the selected area according to the time information and latitude and longitude information, and output the time-space distribution map of the traffic violations in each time period;

The analysis module is used to perform statistical analysis on the spatiotemporal state of road traffic violations to obtain the frequency of occurrence of traffic violations in each road section; perform cluster analysis on the spatiotemporal distribution of road traffic violations to obtain the aggregated road sections and aggregated time periods of traffic violations.

Connected to the above technical solutions, the matching module is specifically used for:

Taking the principle of adjacent intersections as one section, the urban area is divided into n sections, and the longitude and latitude information L _n , B _n at the center point O of each intersection is collected, and the actual distance between the two intersections is the section length. , and number the road segments as 1, 2...n in sequence, where n is a natural number;

The structured data of one illegal act is taken as a data point, and the data points are matched to each target road section in the city map according to the collected latitude and longitude coordinates, and the spatiotemporal distribution map of traffic illegal acts is obtained.

Connected to the above technical solutions, the analysis module is specifically used for:

After matching the distribution of traffic violations on the target road section, firstly collect statistics on the traffic violations on the road section, and record the frequency of various violations in the target time period; The spatial clustering is based on the latitude and longitude location distribution of traffic violations, and the time clustering is based on the distribution of traffic violations on the time axis. The resulting spatiotemporal clustering centers are the aggregation points of traffic violations in time and space.

The present invention also provides a computer storage medium, which can be executed by a processor and stores a computer program in the computer program.

The beneficial effects of the present invention are: the present invention can measure the required information by using the networked ADAS vehicle, does not need to arrange a detector, and reduces a large number of roadside equipment requirements. In addition, the present invention uses networked ADAS to identify and count traffic violations in the road area, and can further analyze and obtain the gathering sections and time periods for illegal acts, which can accurately and real-time reflect the characteristics of traffic violations, and has a certain significance for improving the level of road risk prevention and control. .

Description of drawings

The present invention will be further described below in conjunction with the accompanying drawings and embodiments, in which:

1 is a flowchart of a method for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS according to an embodiment of the present invention;

2 is a flowchart of a method for investigating spatiotemporal characteristics of road traffic violations based on networked ADAS according to another embodiment of the present invention;

Figure 3a is a schematic diagram of driving on the line with the monitoring record of some illegal behaviors of the vehicle ahead;

Figure 3b is a schematic diagram of the illegal U-turn in the monitoring record of some illegal behaviors of the vehicle ahead;

4 is a schematic diagram of a method for dividing a road segment;

Figure 5 is a schematic diagram of the spatial distribution characteristics of traffic violations;

6 is a schematic structural diagram of a system for investigating spatiotemporal characteristics of road traffic violations based on a networked ADAS according to an embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

The main idea of the present invention is: the first step is to use the built-in image processing algorithm in ADAS (Advanced Driver Assistant System, ADAS) to extract and analyze the forward video information recorded by the vehicle camera during the driving process of the vehicle, and identify the illegal behavior of the vehicle ahead, And encode the traffic violations collected by ADAS. The second step is to package and upload the code of vehicle violations collected by a large number of connected ADAS vehicles, the corresponding time information and the location information obtained by GPS to the traffic data cloud platform, and then use the map matching algorithm to match the collected road traffic violations. to the regional road. The third step is to perform preliminary statistics on different road sections, time periods, and illegal acts based on the illegal behavior data in the traffic data cloud platform, and perform cluster analysis on the spatiotemporal distribution of the obtained road traffic violations. Aggregate road segments and aggregate time periods.

As shown in FIG. 1 , a method for identifying and counting the spatiotemporal characteristics of road traffic violations based on networked ADAS according to an embodiment of the present invention includes the steps:

S101. Obtain information on traffic violations of forward vehicles sensed by all networked ADAS vehicles in the urban road traffic system during driving;

S102. Encode the obtained traffic violation information, determine the time when the traffic violation occurred and the location of the violating vehicle at that moment, and package the traffic violation code, violation time, and longitude and latitude of the violating vehicle into structured data;

S103, uploading the structured data to the traffic data cloud platform, matching traffic violations on the road sections in the selected area according to time information and longitude and latitude information, and outputting a time-space distribution map of traffic violations in each time period;

S104. Statistically analyze the spatiotemporal state of road traffic violations to obtain the occurrence frequency of traffic violations in each road section; perform cluster analysis on the spatiotemporal distribution state of road traffic violations to obtain aggregated road sections and aggregation periods of traffic violations.

As shown in Figure 2, another embodiment of the present invention is based on a method for identifying and counting the spatiotemporal characteristics of road traffic violations based on networked ADAS, the method comprising:

S1. _The ADAS vehicle records real-time video information of forward traffic operating conditions during driving, and analyzes the recorded video with the help of a recognition processor module integrated in the video camera, and perceives and collects traffic violations of forward vehicles.

Information on traffic violations of forward vehicles, including illegal parking, illegal lane change, speeding, illegal U-turn/left turn, driving on the line, wrong-way traffic, pedestrian crossing the road, driving/vehicle running a red light, etc.

It should be noted that the traffic violation identification and collection system of the present invention includes a video capture camera, a positioning module, an identification processor module, and a video capture camera.

In addition to conventional monitoring functions, the video capture camera also has built-in image processing algorithms, which can intelligently identify vehicles ahead, lane lines, roadside signs (such as no parking, no U-turn, etc.), markings (dotted and solid lines, grid lines, etc.) and Traffic lights, etc.

The positioning module adopts high-precision navigation devices such as GPS and Beidou, which can obtain the accurate latitude and longitude information and accurate time information of the driving recorder. Combined with the shooting range of the camera, it can more accurately judge the location information and accurate time information of the illegal behavior of the vehicle ahead.

The recognition processor module is built in the video capture camera, and the functions implemented by the camera depend on the algorithms built into the processor. The recognition processing module is based on an embedded system and is used to process the information collected by the video camera, and to The location information stored by the location module. Identify the processor module as the core of the system. This module is based on an embedded system and integrates various image recognition algorithms, including lane line recognition, vehicle feature recognition, vehicle motion trajectory recognition, signal light recognition, and road sign marking recognition.

As shown in Figure 3a, the processor can detect the relative position of the vehicle ahead and the lane line, and the system will automatically trigger when it finds the vehicle in front of the line pressing behavior to store and capture data; the built-in chip of the processor can intelligently identify each As shown in Figure 3b, the processor recognizes the "No U-turn" sign ahead, and at the same time recognizes that the vehicle has a U-turn motion pattern according to the trajectory of the vehicle ahead. At this time, the system also starts automatically and begins to record the vehicle ahead. illegal behavior.

S3. Code the obtained traffic violations, determine the time when the traffic violations occurred and the location _of the violation vehicles at the time, and package the traffic violation codes, violation time, and latitude and longitude of the violation vehicles into structured data.

It should be noted that the code of each traffic violation is unique. After ADAS recognizes the violation of the vehicle ahead, it can more accurately judge the violation of the vehicle ahead by combining the video capture camera and the high-precision navigation system in the positioning module. location information and accurate time information. The code of traffic violations, the time of occurrence of traffic violations and the location of traffic violations are combined into complete structured data, and the data is transmitted to the traffic data cloud platform using the in-vehicle network.

S3. Upload the structured data collected by all connected ADAS vehicles to the traffic data cloud platform, match the traffic violations _on the road sections in the selected area according to the time information and latitude and longitude information, and output the traffic violations in each time period Behavioral spatiotemporal distribution map.

Specifically, the regional roads are selected, and the regional roads are divided into different sections, and the obtained structured data of traffic violations is matched in the map by using the map matching algorithm, and is associated with the sections in the selected regional roads.

It should be noted that, as shown in FIG. 4 , the urban area can be divided into n road sections by adopting the principle that adjacent intersections are one section, and the longitude and latitude information L _o and _La at the center point O of each intersection are collected, The actual distance between two intersections is the segment length. Then the road segments are numbered as 1, 2...n in sequence, and the four corner points of each road segment represent the range of the road segment; among them:

Road _Loc ={(L _o1 ,L _a1 ,),(L _o2 ,L _a2 ),...,(L _on ,L _an )}.

On this basis, road segment matching is performed on the structured data of traffic violations uploaded to the data cloud platform to obtain the spatiotemporal distribution characteristics of traffic violations.

Match:{(lon _i ,lat _i )∈Road _Loc ,T _i ∈T _seg ,i=1,…,n}

The structured data of an illegal act can also be used as a data point, and the data points are matched to each target road section in the ArcGIS city map according to the collected latitude and longitude coordinates, and the spatiotemporal distribution map of traffic violations can be obtained, as shown in Figure 5.

S4 _. Statistically analyze the spatiotemporal state of road traffic violations, obtain the occurrence frequency of traffic violations in each road section, perform cluster analysis on the spatiotemporal distribution state of road traffic violations, and obtain the aggregated road sections and aggregation time periods of the traffic violations.

It should be noted that: after matching the distribution of traffic violations on the target road section, first make statistics on the traffic violations on the road section, record the frequency of various violations in the target time period, and use the traffic violations on different road sections in the morning peak time period as the number of violations. An example of the frequency of behavior:

road section	1	2	3	...	n
The number of trips on the line	x 1	x 2	x 3	...	x n

Number of illegal U-turns	y 1	y 2	y 3	...	y n
Speeding times	z 1	z 2	z 3	...	z n
Number of illegal parking	m 1	m 2	m 3	...	m 4
...	...	...	...	...	...
Number of driving/vehicle running red lights	n 1	n 2	n 3	...	n 4

Then perform spatiotemporal clustering on the traffic violations matched on the road sections. The spatial clustering is based on the longitude and latitude location distribution of the traffic violations, and the time clustering is based on the distribution of the traffic violations on the time axis. The number of clusters is determined according to the clustering effect. The obtained cluster centers are the aggregation points of traffic violations in time and space.

As shown in Figure 6, the embodiment of the present invention is based on a networked ADAS system for investigating the spatiotemporal characteristics of road traffic violations, including:

The information acquisition module is used to acquire the traffic violation information of forward vehicles sensed by all connected ADAS vehicles in the urban road traffic system;

The encoding module is used to encode the obtained traffic violation information, determine the time when the traffic violation occurred and the location of the illegal vehicle at that moment, and package the traffic violation code, violation time, and longitude and latitude of the illegal vehicle into structured data;

The matching module is used to upload the structured data to the traffic data cloud platform, match the traffic violations on the road sections in the selected area according to the time information and latitude and longitude information, and output the time-space distribution map of the traffic violations in each time period;

The analysis module is used to perform statistical analysis on the spatiotemporal state of road traffic violations to obtain the frequency of occurrence of traffic violations in each road section; perform cluster analysis on the spatiotemporal distribution of road traffic violations to obtain the aggregated road sections and aggregated time periods of traffic violations.

Further, the matching module is specifically used for:

Taking the principle of adjacent intersections as one section, the urban area is divided into n sections, and the longitude and latitude information L _n , B _n at the center point O of each intersection is collected, and the actual distance between the two intersections is the section length. , and number the road segments as 1, 2...n in sequence, where n is a natural number;

The structured data of one illegal act is taken as a data point, and the data points are matched to each target road section in the city map according to the collected latitude and longitude coordinates, and the spatiotemporal distribution map of traffic illegal acts is obtained.

Further, the analysis module is specifically used for:

After matching the distribution of traffic violations on the target road section, firstly collect statistics on the traffic violations on the road section, and record the frequency of various violations in the target time period; The spatial clustering is based on the latitude and longitude location distribution of traffic violations, and the time clustering is based on the distribution of traffic violations on the time axis. The resulting spatiotemporal clustering centers are the aggregation points of traffic violations in time and space.

The above-mentioned system for investigating spatiotemporal characteristics of road traffic violations based on networked ADAS is mainly used to realize the method for investigating spatiotemporal characteristics of roadway traffic violations based on networked ADAS in the above embodiment, and the template implementation method has the same functions, which will not be repeated here.

The present invention also provides a computer storage medium, which can be executed by a processor, and stores a computer program in the computer program.

To sum up, the present invention has the following advantages:

(1) The required information can be measured by using ADAS vehicles, and there is no need to deploy detectors, reducing the demand for a large number of roadside equipment;

(2) Wide coverage and high data accuracy. Compared with the existing illegal behavior collection technology, the use of ADAS vehicle identification and statistics on traffic violations can make up for the insufficient coverage of road facilities, and more objectively and directly reflect the distribution of road traffic violations. .

(3) Strong applicability, the method proposed by the present invention is suitable for most cities, the detection equipment is not easily affected by the environment, weather, etc., and the measurement accuracy is high;

(4) In line with the development trend of the future transportation field, ADAS vehicles are the development direction of the future automobile industry, and also cater to the trend of intelligent transportation development.

It should be understood that, for those skilled in the art, improvements or changes can be made according to the above description, and all these improvements and changes should fall within the protection scope of the appended claims of the present invention.

Claims (10)

1. A method for investigating spatiotemporal characteristics of road traffic violations based on networked ADAS, comprising the following steps:

   S1. Obtain information on traffic violations of forward vehicles perceived by all networked ADAS vehicles in the urban road traffic system during driving;

   S2. Encode the obtained traffic violation information, determine the time when the traffic violation occurred and the location of the illegal vehicle at that moment, and package the traffic violation code, violation time, and longitude and latitude of the illegal vehicle into structured data;

   S3. Upload the structured data to the traffic data cloud platform, match the traffic violations on the road sections in the selected area according to the time information and latitude and longitude information, and output the time-space distribution map of the traffic violations in each time period;

   S4. Statistically analyze the spatiotemporal state of road traffic violations to obtain the occurrence frequency of traffic violations in each road section; perform cluster analysis on the spatiotemporal distribution state of road traffic violations to obtain the aggregated road sections and aggregation periods of traffic violations.
2. The method for investigating spatiotemporal characteristics of road traffic violations based on networked ADAS according to claim 1, wherein the information on vehicle traffic violations includes illegal parking, illegal lane changing, speeding, illegal U-turn/left-turn, and driving under line , vehicles in the wrong direction, pedestrians crossing the road, driving/vehicles running red lights.
3. The method for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS according to claim 1, wherein, in step S1, the urban road traffic system is based on the forward road traffic video collected by the networked ADAS vehicle through the video collection camera, through the Positioning and image recognition methods are used for lane line recognition, vehicle feature recognition, vehicle motion trajectory recognition, signal light recognition, and road sign marking recognition, and then based on the recognized basic road information and forward vehicle information, machine learning algorithms are used to identify forward vehicle traffic. illegal act.
4. The method for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS according to claim 1, is characterized in that, the concrete method of step S3 is:

   Taking the principle of adjacent intersections as one section, the urban area is divided into n sections, and the longitude and latitude information L _n , B _n at the center point O of each intersection is collected, and the actual distance between the two intersections is the section length. , and number the road segments as 1, 2...n in sequence, where n is a natural number;

   Taking the structured data of an illegal act as a data point, according to the collected latitude and longitude coordinates, the data points are matched to each target road section in the city map, and the spatiotemporal distribution map of traffic illegal acts is obtained.
5. The method for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS according to claim 1, is characterized in that, the concrete method of step S4 is:

   After matching the distribution of traffic violations on the target road section, firstly collect statistics on the traffic violations on the road section, and record the frequency of various violations in the target time period; The spatial clustering is based on the latitude and longitude location distribution of traffic violations, and the time clustering is based on the distribution of traffic violations on the time axis. The resulting spatiotemporal clustering centers are the aggregation points of traffic violations in time and space.
6. The method for investigating spatiotemporal characteristics of road traffic violations based on networked ADAS according to claim 1, wherein in step S4, the time information recorded in the structured data of traffic violations is integrated, and divided into Day, night, or the time period of interest in the morning peak and evening peak, and then use the latitude and longitude information to associate traffic violations with the corresponding road sections in the selected road area, and obtain the corresponding road sections in a specific time period through statistical and cluster analysis. The distribution and aggregation of traffic violations within the city are used to identify the occurrence of violations on different road sections in different time periods.
7. A system for investigating spatiotemporal characteristics of road traffic violations based on networked ADAS, comprising:

   The information acquisition module is used to acquire the traffic violation information of forward vehicles sensed by all connected ADAS vehicles in the urban road traffic system;

   The encoding module is used to encode the obtained traffic violation information, determine the time when the traffic violation occurred and the location of the illegal vehicle at that moment, and package the traffic violation code, violation time, and longitude and latitude of the illegal vehicle into structured data;

   The matching module is used to upload the structured data to the traffic data cloud platform, match the traffic violations on the road sections in the selected area according to the time information and latitude and longitude information, and output the time-space distribution map of the traffic violations in each time period;

   The analysis module is used to perform statistical analysis on the spatiotemporal state of road traffic violations to obtain the occurrence frequency of traffic violations in each road section; perform cluster analysis on the spatiotemporal distribution of road traffic violations to obtain the aggregated road sections and aggregation periods of traffic violations.
8. The system for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS according to claim 7, is characterized in that, the matching module is specifically used for:

   Taking the principle of adjacent intersections as one section, the urban area is divided into n sections, and the longitude and latitude information L _n , B _n at the center point O of each intersection is collected, and the actual distance between the two intersections is the section length. , and number the road segments as 1, 2...n in sequence, where n is a natural number;

   The structured data of one illegal act is taken as a data point, and the data points are matched to each target road section in the city map according to the collected latitude and longitude coordinates, and the spatiotemporal distribution map of traffic illegal acts is obtained.
9. The method for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS according to claim 7, is characterized in that, the analysis module is specifically used for:

   After matching the distribution of traffic violations on the target road section, firstly collect statistics on the traffic violations on the road section, and record the frequency of various violations in the target time period; The spatial clustering is based on the longitude and latitude location distribution of traffic violations, and the time clustering is based on the distribution of traffic violations on the time axis. The resulting spatiotemporal clustering centers are the aggregation points of traffic violations in time and space.
10. A computer storage medium, characterized in that, a computer program executable by a processor is stored therein, and the computer program executes the spatiotemporal characteristics of investigating road traffic violations based on networked ADAS according to any one of claims 1-6 Methods.

Images