Public transport early warning method and system based on internet of things

Abstract

The application discloses a public traffic early warning method and system based on the Internet of Things, which comprises the following steps: obtaining a face image of a vehicle driver through an imaging device, obtaining a driving state of the driver according to the face image, and assigning and outputting the driving state of the driver; selecting vehicles in a certain vehicle driving section for triangular fitting to obtain a position set of all triangular regions in the vehicle driving section, and taking three vehicles as three vertices of a triangle for each triangular region; obtaining a driving risk of each triangular region in a certain vehicle driving section, and obtaining regional risk prompt information; and generating driving prompt information according to the regional risk prompt information, and sending the driving prompt information to vehicle drivers in the corresponding region. The application can quantize and visually process the driving risk of vehicles in a region in combination with the quantized driving state of the driver, so that the purpose of global and accurate early warning is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of public transportation, in particular to a public transportation early warning method and system based on Internet of Things. BACKGROUND

[0002] In the prior art, there are technical solutions for traffic safety monitoring of vehicles driving on the road by using Internet of Things devices such as laser radar and industrial cameras.

[0003] However, in the above-mentioned technology, the driving behavior of a single target vehicle is generally evaluated for risk and the driver of the vehicle is reminded how to avoid risks, but such evaluation and reminders cannot be transmitted to other vehicles driving on the road.

[0004] There are many vehicles driving on the road at the same time, and the occurrence of some traffic accidents, such as rear-end collisions, is not determined by the driving behavior of a single target vehicle, but is often related to multiple vehicles, and after a traffic accident occurs, vehicles within a certain range will be affected, but the impact is large or small depending on the distance from the event point.

[0005] Therefore, the current method of risk assessment and early warning for a single target vehicle cannot provide corresponding early warning prompts to other vehicles that may be affected, and thus cannot achieve global and accurate early warning for all drivers of vehicles driving in the area. SUMMARY

[0006] In view of the deficiencies of the prior art, the present application aims to provide a public transportation early warning method and system based on Internet of Things, which can quantitatively process the driving risk of three vehicles in the same triangular area by combining the quantitative driving state of the driver, in order to achieve global and accurate early warning.

[0007] The present application provides a public transportation early warning method based on Internet of Things, which comprises:

[0008] acquiring a facial image of a vehicle driver by an imaging device, and acquiring the driving state of the driver according to the facial image, and assigning and outputting the driving state of the driver;

[0009] selecting vehicles in a vehicle driving section for triangular fitting to obtain a position set of all triangular areas in the vehicle driving section, and each triangular area taking three vehicles as three vertices of a triangle;

[0010] acquiring a driving risk value of each triangular area in a vehicle driving section;

[0011] obtaining regional risk prompt information according to the driving risk value of each triangular area;

[0012] It also generates driving tips based on regional risk warnings and sends them to drivers of vehicles within the corresponding region.

[0013] Preferably, the imaging device includes a camera installed inside the vehicle.

[0014] Preferably, assigning values ​​to the driver's driving status includes assigning different values ​​to different driving statuses, and different values ​​represent whether the driver has committed a violation of driving rules and the severity of the violation.

[0015] Preferably, selecting vehicles within a specific road segment for triangulation fitting to obtain the set of locations of all triangular regions within that road segment includes the following steps:

[0016] Establish a three-dimensional coordinate system on the map with latitude and longitude as the x and y axes and time as the z axis, and obtain the P value of each vehicle at time Z based on the positioning device. i Longitude X i Latitude Y i ;

[0017] At the current moment, select any vehicle P within a certain road segment. i As the central vehicle P io Central vehicle P io Coordinates are marked as P io (X io Y io Z io ), with the center's vehicle P io Define a predetermined range with center R and radius R, and obtain the total number T of vehicles within this predetermined range and the set of position coordinates R of all vehicles. i ;

[0018] The following formula is used to obtain the value of the vehicle P within the predetermined range and at the center. io The set of locations Oi for all relevant triangular regions:

[0019]

[0020] Where E is an identity matrix with T rows and T columns; the value of i ranges from 0 to T; This indicates that within the predetermined range, excluding the central vehicle P io In addition, any two vehicles can be randomly selected to interact with the central vehicle P. io Perform triangle fitting to obtain the values ​​of the two vehicles and the central vehicle P. io A triangular region with three vertices;

[0021] repeating the above steps to obtain a corresponding set of positions of the triangular regions with each vehicle as the center vehicle in a certain vehicle driving section;

[0022] performing data cleaning on all the obtained sets of positions of the triangular regions to remove repeated triangular regions to finally obtain a set of positions of all the triangular regions in a certain vehicle driving section.

[0023] Preferably, the radius R is 2-5 kilometers.

[0024] Preferably, the driving risk value of each triangular region in a certain vehicle driving section is obtained according to the following formula:

[0025]

[0026] wherein p is the current traffic density of the certain vehicle driving section; V i is the current driving speed of the center vehicle corresponding to the current triangular region; L i is the current driving direction vector of the center vehicle corresponding to the current triangular region; M i is the set of driving states of the three vehicle drivers in the current triangular region.

[0027] Preferably, the driving risk value of each triangular region is subjected to data visualization processing, and the region risk prompt information is obtained according to the driving risk value after the visualization processing.

[0028] Preferably, different triangular regions are marked with different colors according to the driving risk value.

[0029] Also provided is a public transportation early warning system, comprising:

[0030] an imaging device installed in a vehicle for obtaining a facial image of a vehicle driver;

[0031] a state obtaining unit connected to the imaging device for obtaining the driving state of the driver according to the facial image;

[0032] an assignment unit connected to the state obtaining unit for assigning and outputting the driving state of the driver;

[0033] a triangular fitting unit for selecting vehicles in a certain vehicle driving section to perform triangular fitting to obtain a set of positions of all the triangular regions in the vehicle driving section;

[0034] a risk value calculation unit for obtaining a driving risk value of each triangular region in a certain vehicle driving section.

[0035] Preferably, the public transport early warning system further comprises a visualization unit connected to the risk value calculation unit, configured to perform data visualization processing on the driving risk value of each triangular region, and obtain regional risk prompt information according to the driving risk value after the visualization processing;

[0036] and an early warning unit configured to generate driving prompt information according to the regional risk prompt information and send the driving prompt information to the drivers of the vehicles in the corresponding triangular region.

[0037] The present application has at least the following technical effects or advantages:

[0038] The present application firstly quantifies the driving state of the driver as a reference factor for the subsequent driving risk value, and further includes three vehicles in the same triangular region in the calculation of the driving risk value, so as to quantify and visualize the driving risk, and to achieve the purpose of global and accurate early warning by obtaining the regional driving risk value to warn and remind all vehicles in a certain region. In the embodiment, the triangular fitting method can greatly improve the running speed of the program, solve the delay problem of the real-time program, improve the accuracy of subsequent calculation, and realize more accurate regional positioning. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0040] Figure 1 The step flow chart of the public transport early warning method based on the Internet of Things of the present application;

[0041] Figure 2 The three-dimensional coordinate diagram of different time in the embodiment of the present application;

[0042] Figure 3 The schematic diagram of obtaining the triangular region by triangular fitting in the embodiment of the present application;

[0043] Figure 4 The schematic diagram of marking different triangular regions with different colors in the embodiment of the present application;

[0044] Figure 5 The structural schematic diagram of the public transport early warning system of the present application. DETAILED DESCRIPTION

[0045] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0046] Example 1:

[0047] like Figure 1 As shown in the figure, this embodiment provides a public transportation early warning method based on the Internet of Things, which includes the following steps:

[0048] S1. Acquire a facial image of the vehicle driver through an imaging device, obtain the driver's driving state based on the facial image, and assign and output the driver's driving state m.

[0049] Specifically, the imaging device includes a camera installed in the vehicle to ensure that it can capture the driver's facial image. The driver's driving state includes normal driving, closing eyes, yawning, holding a mobile phone and making or receiving calls, etc. Assigning values ​​to the driver's driving state m includes assigning different values ​​to different driving states m, and different values ​​represent whether the driver has committed a violation of driving rules and the severity of the violation.

[0050] For example, the driving status m can be assigned a value in the range of 0-10. The higher the value of m, the better the current driving status of the driver (e.g., m=10 means that the driver's driving behavior is completely normal and there is no violation of driving rules). The lower the value of m, the worse the current driving status of the driver (e.g., m=0 means that the driver closes his eyes while driving, which is the most serious violation of driving rules; m=2 means that the driver holds a mobile phone and makes or receives calls while driving, which is a relatively serious violation of driving rules).

[0051] S2. Select vehicles within a certain road segment and perform triangulation fitting to obtain the location set of all triangular regions within the road segment, with each triangular region having three vehicles as the three vertices of the triangle.

[0052] Specifically, step S2 includes the following steps:

[0053] S21, such as Figure 2 As shown, a three-dimensional coordinate system is established on the map with latitude and longitude as the xy-axis and time as the z-axis. The position P of each vehicle at time Z is obtained using a positioning device (such as GPS, BeiDou, or other positioning systems). i Longitude X i Latitude Y i ;

[0054] The location information of all vehicles within a certain road segment P at different times (e.g., 8:00, 12:00, 20:00, etc.) is marked on a three-dimensional coordinate axis, and the coordinates of the location of each vehicle Pi are marked as P. i (Xi, Yi, Zi);

[0055] S22, such as Figure 3 As shown, at the current time (e.g., 20:00), any vehicle P is selected within a certain road segment P. i As the central vehicle P io Central vehicle P io Coordinates are marked as P io (X io Y io Z io ), with the center's vehicle P io Define a predetermined range P1 with R as the center and R as the radius, where R can be determined based on traffic flow, such as 2-5 kilometers;

[0056] And obtain the total number of vehicles T within the predetermined range P1 and the set of location coordinates R of all vehicles. i ;

[0057] S23. According to formula (1), obtain the distance between the predetermined range P1 and the center vehicle P. io The set of locations Oi for all relevant triangular regions:

[0058]

[0059] Where E is the T-row, T-column identity matrix, expressed in the following form:

[0060]

[0061] The value of i ranges from 0 to T; This indicates that within the predetermined range P1, excluding the central vehicle P... io In addition, any two vehicles can be randomly selected to interact with the central vehicle P. io Perform triangle fitting to obtain a triangle with respect to the two vehicles and the central vehicle P. io A triangular region with three vertices;

[0062] For example, such as Figure 3 As shown, within the predetermined range P1, excluding the central vehicle P io In addition, any two vehicles P can be selected. i1 P i2 With the central vehicle P io Perform triangle fitting to obtain a vehicle P centered at the triangle. io Vehicle P i1 P i2A triangle region T1 with three vertices, and similarly, a triangle region T2 with three vertices, or a triangle region T3 with three vertices, all of which are centered at the vehicle P io , the vehicle P i2 , P i3 , the vehicle P io , the vehicle P i1 , P i3 A triangle region T3 with three vertices, the three triangle regions T1, T2, T3 are all centered at the vehicle P io , all of which are centered at the vehicle P

[0063] S24, repeating S22-S23 to obtain a set of positions of the corresponding triangle region obtained when each vehicle is taken as the center vehicle in a vehicle driving section P;

[0064] S25, performing data cleaning on the set of positions of all the triangle regions obtained in step S24 to remove duplicate triangle regions, to finally obtain a set of positions O of all the triangle regions in a vehicle driving section P, and the set of positions O is expressed as formula (2):

[0065] O =∑O i (2);

[0066] All the vehicles driving in a vehicle driving section P will form a driving network, and it is too simple to evaluate the relationship between only two vehicles and it is too complex to evaluate the relationship between four vehicles. Therefore, the embodiment selects three vehicles and explores the relationship between the three vehicles through triangle fitting;

[0067] The reason is that three vehicles can form a triangle region, i.e., three points are the minimum number of points to form a region, and the triangle structure is the most stable, so when triangle fitting is adopted, the position relationship calculation of the vehicles will not cause calculation redundancy; and because the number of vehicles involved in the triangle region is the least, the structural relationship is simple, compared with the polygon fitting and the circle fitting in the prior art, it only needs to calculate the relationship between two vehicles three times, which can greatly improve the running speed of the program and solve the delay problem of the real-time program; secondly, triangle fitting can realize more accurate region positioning, compared with polygon fitting and circle fitting, the error of triangle fitting can be ignored, thereby helping to improve the accuracy of subsequent calculation;

[0068] S3, obtaining the driving risk value F of each triangle region in a vehicle driving section according to formula (3):

[0069]

[0070] Where ρ is the current traffic flow density of a certain road segment P; Vi is the current driving speed of the central vehicle corresponding to the current triangular region; Li is the current driving direction vector of the central vehicle corresponding to the current triangular region; Mi is the set of driving states m of the three drivers of the current triangular region, denoted as Mi{m1, m2, m3}.

[0071] Existing technologies mostly assess the risk of driving behavior of a single vehicle without considering the relationship between the vehicle and other vehicles and the possible mutual influence. This embodiment, however, takes into account all three vehicles in the same triangular area, and uses the regional driving risk value to provide early warnings to all vehicles in a certain area, so as to achieve the purpose of global and accurate early warning.

[0072] S4. Visualize the driving risk value F of each triangular region, and obtain regional risk warning information based on the visualized driving risk value F (the regional risk warning information can be presented in one or a combination of images, text, audio, numbers, etc.), for example, Figure 4 As shown, based on the driving risk value F, different triangular areas are marked with different colors to complete the visualization process. This includes indicating the degree of driving risk in different triangular areas, such as red for high-risk areas, orange for medium-risk areas, and green for low-risk areas. Furthermore, regional risk warning information is generated based on the visualized driving risk value F. For example, if a certain area has a large proportion of red triangular areas, then that area is marked as a "high-risk area," and if a certain area has a large proportion of green triangular areas, then that area is marked as a "low-risk area," and so on. The above data visualization results and regional risk warning information can be sent to the traffic control center or to the driver's smartphone, tablet, and other wearable devices to enable timely monitoring of driving risks in different areas.

[0073] S5, generates driving warning information based on regional risk warning information (the driving warning information includes text and / or graphics and / or sound), and sends it to the drivers of vehicles in the corresponding area, such as sending a red alert to drivers of vehicles in dangerous areas, using physical means such as lights or music to remind drivers to drive slowly; sending a yellow alert to drivers of vehicles in medium-risk areas, reminding drivers to drive slowly, etc.

[0074] Therefore, in this embodiment, the driver's driving state is first assigned a value to quantify it, so as to serve as a reference factor for the subsequent driving risk value F. Compared with the prior art, which only qualitatively assesses the driver's driving state and then provides a warning based on the qualitative result (such as issuing a warning message when it is determined that the driver is yawning), this embodiment can combine the quantified driving state to provide more accurate warning information and avoid misjudgment.

[0075] Furthermore, this application includes all three vehicles within the same triangular area in the calculation of driving risk value, so as to provide early warning reminders to all vehicles in a certain area by obtaining regional driving risk value, so as to achieve the purpose of global and accurate early warning; at the same time, the triangle fitting method in this embodiment can greatly improve the running speed of the program compared with polygon fitting and circle fitting, solve the problem of real-time program delay, and improve the accuracy of subsequent calculations, so as to achieve more accurate regional positioning.

[0076] Example 2:

[0077] This embodiment provides a public transportation early warning system that implements the public transportation early warning method described in Embodiment 1, such as... Figure 5 As shown, it includes:

[0078] Imaging device 1, which is installed inside the vehicle, is used to acquire facial images of the vehicle driver;

[0079] The status acquisition unit 2 is connected to the imaging device 1 and is used to acquire the driver's driving status based on the facial image;

[0080] Assignment unit 3, which is connected to the state acquisition unit 2, is used to assign and output the driving state m of the driver;

[0081] Triangle fitting unit 4 is used to select vehicles in a certain vehicle driving segment for triangle fitting to obtain the location set of all triangular regions in the vehicle driving segment. See step S2 for specific steps.

[0082] Risk value calculation unit 5 is used to obtain the driving risk value F of each triangular area within a certain vehicle driving segment. For specific steps, please refer to step S3.

[0083] The visualization unit 6 is connected to the risk value calculation unit 5 and is used to perform data visualization processing on the driving risk value F of each triangular area, and to obtain regional risk warning information based on the visualized driving risk value F. For specific steps, please refer to step S4.

[0084] And a warning unit 7, which is used to generate driving warning information based on regional risk warning information and send it to the drivers of vehicles within the corresponding triangular area.

[0085] In summary, this invention first quantifies and assigns values ​​to the driver's driving status as a reference factor for subsequent driving risk values, which can provide more accurate early warning information and avoid misjudgment.

[0086] Furthermore, this invention incorporates all three vehicles within the same triangular area into the calculation of driving risk values ​​to quantify and visualize driving risks. By acquiring regional driving risk values, it provides early warnings to all vehicles within a specific area, achieving a global and precise early warning system. Simultaneously, compared to polygonal or circle fitting, the triangle fitting method in this embodiment significantly improves program speed, resolves real-time program latency issues, and enhances the accuracy of subsequent calculations, resulting in more precise regional positioning.

[0087] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A public transportation early warning method based on the Internet of Things, characterized in that, include: The driver's facial image is acquired through an imaging device, and the driver's driving state is obtained based on the facial image. The driver's driving state is then assigned a value and output. Triangulation fitting is performed on vehicles within a certain road segment to obtain the location set of all triangular regions within that road segment, with each triangular region having three vehicles as the three vertices of the triangle. Obtain the driving risk value of each triangular region within a given road segment; Based on the driving risk value of each triangular area, regional risk warning information is obtained; And generate driving tips based on regional risk warnings and send them to drivers of vehicles within the corresponding region; The process of selecting vehicles within a specific road segment for triangulation fitting to obtain the set of locations of all triangular regions within that segment includes the following steps: Establish a three-dimensional coordinate system on the map with latitude and longitude as the x and y axes and time as the z axis, and obtain the P value of each vehicle at time Z based on the positioning device. i Longitude X i Latitude Y i ; At the current moment, select any vehicle P within a certain road segment. i As the central vehicle P io Central vehicle P io Coordinates are marked as P io (X io Y io Z io ), with the center's vehicle P io Define a predetermined range with center R and radius R, and obtain the total number T of vehicles within this predetermined range and the set of position coordinates R of all vehicles. i ; The following formula is used to obtain the value of the vehicle P within the predetermined range and at the center. io The set of locations Oi for all relevant triangular regions: Where E is an identity matrix with T rows and T columns; the value of i ranges from 0 to T; This indicates that within the predetermined range, excluding the central vehicle P io In addition, any two vehicles can be randomly selected to interact with the central vehicle P. io Perform triangle fitting to obtain the values ​​of the two vehicles and the central vehicle P. io A triangular region with three vertices; Repeat the above steps to obtain the set of locations of the corresponding triangular regions within a certain vehicle travel segment, with each vehicle as the center vehicle. Data cleaning is performed on the obtained set of locations of all triangular regions to remove duplicate triangular regions, so as to finally obtain the set of locations of all triangular regions within a certain vehicle travel segment O; The driving risk value for each triangular region within a given road segment is obtained using the following formula: Where ρ is the current traffic flow density of a certain road segment; V i L represents the current speed of the central vehicle corresponding to the current triangular region. i M is the current driving direction vector of the central vehicle corresponding to the current triangular region; i This is the set of driving states of the drivers of the three vehicles within the current triangular region.

2. The public transportation early warning method as described in claim 1, characterized in that, The imaging device includes a camera installed inside the vehicle.

3. The public transportation early warning method as described in claim 1, characterized in that, Assigning values ​​to the driver's driving status includes assigning different values ​​to different driving statuses, and different values ​​represent whether the driver has committed a violation of driving rules and the severity of the violation.

4. The public transportation early warning method as described in claim 1, characterized in that, The radius R is 2-5 kilometers.

5. The public transportation early warning method as described in claim 1, characterized in that, The driving risk value of each triangular area is visualized, and regional risk warning information is obtained based on the visualized driving risk value.

6. The public transportation early warning method as described in claim 5, characterized in that, Based on the driving risk value, different triangular areas are marked with different colors.

7. A public transportation early warning system for implementing the Internet of Things-based public transportation early warning method of claim 1, characterized in that, include: Imaging equipment, installed inside a vehicle, is used to acquire facial images of the vehicle's driver; A status acquisition unit, which is connected to the imaging device, is used to acquire the driver's driving status based on the facial image; The assignment unit, which is connected to the state acquisition unit, is used to assign and output the driver's driving state. The triangulation unit is used to select vehicles within a certain road segment to perform triangulation to obtain the location set of all triangular regions within that road segment. The risk value calculation unit is used to obtain the driving risk value of each triangular area within a certain vehicle driving segment.

8. The public transportation early warning system as described in claim 7, characterized in that, The public transportation early warning system also includes: a visualization unit, which is connected to the risk value calculation unit, used to visualize the driving risk value of each triangular area, and obtain regional risk warning information based on the visualized driving risk value; And a warning unit, which generates driving warning information based on regional risk warning information and sends it to the drivers of vehicles within the corresponding triangular area.

Images