CN114781791A - High-speed service area risk identification method based on holographic sensing data - Google Patents
High-speed service area risk identification method based on holographic sensing data Download PDFInfo
- Publication number
- CN114781791A CN114781791A CN202210236418.7A CN202210236418A CN114781791A CN 114781791 A CN114781791 A CN 114781791A CN 202210236418 A CN202210236418 A CN 202210236418A CN 114781791 A CN114781791 A CN 114781791A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- speed
- risk
- pedestrian
- predicted
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims abstract description 61
- 239000011159 matrix material Substances 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 4
- 230000003068 static effect Effects 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000007726 management method Methods 0.000 description 6
- 230000003993 interaction Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention relates to a holographic sensing data-based high-speed service area risk identification method, which comprises the following steps: acquiring holographic sensing data collected by sensing equipment of a high-speed service area to be identified; dividing the high-speed service area into a plurality of functional areas, dividing each functional area into a plurality of grids, and determining the time period length of risk identification and early warning; acquiring a pedestrian risk index of each grid of each functional area and determining a pedestrian risk evaluation threshold; acquiring the current vehicle risk index of each grid of each functional area and determining the current vehicle risk evaluation threshold; obtaining a predicted vehicle risk index of each grid of each functional area and confirming a predicted vehicle risk evaluation threshold; and judging whether the risk indexes of the grids are larger than the corresponding evaluation threshold values or not, if so, judging that the grids have risks. Compared with the prior art, the method and the system have the advantages that the risk of different areas can be quantitatively analyzed, and different grades of risks of the service areas can be comprehensively and effectively identified and early warned.
Description
Technical Field
The invention relates to the field of risk identification, in particular to a high-speed service area risk identification method based on holographic sensing data.
Background
The expressway service area is also called an expressway service station, is an important supporting facility of the expressway, and is a place for providing services such as catering, rest, shopping, entertainment, parking, refueling, vehicle maintenance and the like for the expressway drivers and conductors. In a highway service area, passenger and cargo vehicles, dangerous transport vehicles and pedestrians are interwoven, large-scale equipment such as gas stations and charging stations also have the hidden dangers of flammability and explosiveness, and the high-speed service area has the complex traffic safety hidden dangers under the coupling of various complex factors. The real-time risk and the potential risk of the high-speed service area are identified and early warned on line, so that the operating efficiency of the service area can be effectively improved, the potential safety hazard is reduced, and the intelligent operation management of the highway is served.
In the prior art, a simple video camera is mostly arranged at key points of a part of service areas to carry out manual monitoring and management. Single-point sensing often faces a plurality of problems, such as insufficient sensing range, easy obstruction of sensing visual field due to self visual angle, credible judgment of data interaction, and the like, and the problems become bottlenecks that restrict single-point sensing capability and precision. In addition, the risk level in the scene is judged in real time through vision by manpower, so that the time and labor are consumed, the efficiency is extremely low, the full-scene and multi-target danger degree cannot be identified and early warned in time, and the risk in a period of time in the future cannot be effectively estimated so as to cope in advance.
Holographic sensing data is generally acquired through ubiquitous sensing equipment, such as a video camera and a millimeter wave radar, can be customized and installed at each point position of a high-speed service area, can be acquired under a full-scene sensing visual field in a 'Shangdi view angle' mode, and is transmitted to a service area data management cloud platform through a powerful computational edge computing unit and a 5G communication technology, so that massive and real-time holographic sensing data of the high-speed service area acquired in real time can be analyzed and decided, rapid risk identification and timely early warning are realized, and a solid data base is provided for management of the high-speed service area.
At present, the research on risk identification and early warning of a high-speed service area is rare, functional characteristics of each area of the high-speed service area are different, human-human, human-vehicle and vehicle-vehicle interaction risks in different degrees exist, and serious safety accidents and economic losses can be caused after collision.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a high-speed service area risk identification method based on holographic sensing data.
The purpose of the invention can be realized by the following technical scheme:
a high-speed service area risk identification method based on holographic sensing data comprises the following steps:
s1: acquiring holographic sensing data collected by sensing equipment of a high-speed service area to be identified;
s2: dividing the high-speed service area into a plurality of functional areas, dividing each functional area into a plurality of grids, and determining the time period length of risk identification and early warning;
s3: acquiring a pedestrian risk index of each grid of each functional area according to the holographic sensing data and determining a pedestrian risk evaluation threshold;
s4: acquiring the current vehicle risk index of each grid of each functional area according to the holographic sensing data and determining the current vehicle risk evaluation threshold;
s5: obtaining a predicted vehicle risk index of each grid of each functional area according to the holographic sensing data and confirming a predicted vehicle risk evaluation threshold;
s6: and judging whether the risk indexes of the grids in different functional areas are larger than the corresponding evaluation threshold values, if so, judging that the grids have risks.
Preferably, the step S2 specifically includes
S21: dividing high-speed service area into N function areas according to service function { Z1,Z2,...Zn},ZnIs the nth functional area;
s22: dividing each functional area into a plurality of grids with the size Xm square;
s23: determining a time period length t of risk identification and early warning updaten。
Preferably, the step S3 specifically includes:
s31: according to the acquired holographic sensing data, the top t is screened out by utilizing the timestamp and the target typenThe data row of which the target type is a pedestrian in the second;
s32: calculating the pedestrian density D of each grid of each functional area and obtaining the corresponding pedestrian risk index Rhh:
wherein ,NpThe number of pedestrians sensed in the grid is obtained, and X is the side length of the grid;
s33: and determining a pedestrian risk evaluation threshold matrix.
Preferably, the pedestrian risk evaluation threshold matrix is:
Preferably, the step S4 specifically includes:
s41: calculating the current human-vehicle risk index of each grid of each functional area:
wherein ,(xi,yi) As coordinates of the pedestrian i, viIs the speed of pedestrian i, (x)j,yj) Is the center point coordinate of the vehicle j, vjSpeed of vehicle j, αiIs the included angle alpha between the speed of the pedestrian i and the connecting direction of the central points of the pedestrian and the vehiclejIs the included angle between the speed of the vehicle j and the direction of the connecting line of the central points of the man and the vehicle, ajIs the width of the vehicle j, bjIs the length of the vehicle j, tijTime of collision of pedestrian i with vehicle j, dijIs the distance, Δ d, of the pedestrian i from the body of the vehicle jjThe distance from the central point of the vehicle j to the vehicle body;
s42: calculating the current car risk index of each grid of each functional area:
wherein ,(xh,yh) Is the coordinate of the center point of the vehicle h, vhIs the speed of the vehicle h, (x)j,yj) Is the center point coordinate of the vehicle j, vjSpeed of vehicle j, αhIs the angle between the speed of the vehicle i and the direction of the connecting line of the central points of the two vehicles, alphajIs the angle between the speed of the vehicle j and the direction of the line connecting the central points of the two vehicles, ahWidth of vehicle h, bhIs the length of the vehicle h, ajIs the width of the vehicle j, bjIs the length of the vehicle j, thjThe time of collision of vehicle h with vehicle j, dhjIs the distance between the body of vehicle h and the body of vehicle j, Δ dhDistance of vehicle h from center point to body, Δ djThe distance from the central point of the vehicle j to the vehicle body;
s43: and determining a current pedestrian and vehicle risk evaluation threshold matrix and a current vehicle and vehicle risk evaluation threshold matrix.
Preferably, the current human-vehicle risk evaluation threshold matrix is:
the current car risk evaluation threshold matrix is as follows:
wherein ,and the current vehicle risk evaluation threshold value is the current vehicle risk evaluation threshold value of the nth functional area.
Preferably, the step S5 specifically includes:
s51: and (3) predicting the coordinates (x ', y ') and the speed v ' of the pedestrian and the vehicle at the next stage:
in the formula ,tnFor the period division length, p is the number of periods before prediction, (x)t-n,yt-n) The sensing coordinate value of the vehicle or the pedestrian in the nth time period before the t time period,the value of the vehicle or pedestrian perception speed is the nth time period before the t time period;
s52: calculating next-stage prediction human-vehicle risk index R'hv
wherein ,(x′i,y′i) Center point coordinates, v ', predicted for the next period of pedestrian i'iSpeed predicted for pedestrian i next period, (x'j,y'j) Predicted center point coordinate, v 'for the next time period of vehicle j'jPredicted speed, α, for the next period of vehicle jiIs the angle between the speed of the pedestrian i and the direction of the connecting line of the central points of the two vehicles, alphajIs the angle between the speed of the vehicle j and the direction of the connecting line of the central points of the two vehicles, ajIs the width of the vehicle j, bjIs j length, t 'of vehicle'ijIs a predicted value d 'of the collision time of the pedestrian i and the vehicle j in the next period'ijIs the predicted value of the distance between the pedestrian i and the vehicle body of the vehicle j at the next stage, delta djThe distance from the central point of the vehicle j to the vehicle body;
s53: calculating predicted vehicle risk index R 'predicted by next stage'vv:
wherein ,(x'h,y'h) Predicted center point coordinate, v 'for the next period of vehicle h'hIs the predicted speed for the next period of vehicle h, (x'j,y'j) Predicted center point coordinate, v 'for the next time period of vehicle j'jPredicted speed, α, for the next period of vehicle jhIs the angle between the h speed of the vehicle and the direction of the connecting line of the central points of the two vehicles, alphajIs the angle between the speed of the vehicle j and the direction of the connecting line of the central points of the two vehicles, ahWidth of vehicle h, bhIs the length of the vehicle h, ajIs the width of the vehicle j, bjIs j length, t 'of vehicle'hjIs a predicted value d 'of the collision time of the vehicle h and the vehicle j in the next period'hjIs the predicted value of the distance between the vehicle h and the vehicle body of the vehicle j, delta dhDistance, Δ d, from the center point of the vehicle h to the bodyjThe distance from the central point of the vehicle j to the vehicle body;
s54: and determining a predicted pedestrian and vehicle risk evaluation threshold matrix and a predicted vehicle and vehicle risk evaluation threshold matrix.
Preferably, the predicted human-vehicle risk evaluation threshold matrix is as follows:
Preferably, the sensing device can acquire holographic sensing data of all objects in a high-speed service area to be identified, the holographic sensing data has a full-scene sensing view field, and real-time information of all dynamic and static participating objects in the service area can be acquired; fields of the collected data include, but are not limited to, time stamp, target ID, target type, target speed, target coordinates, target length, target width.
Preferably, the sensing device is a millimeter wave radar or a high definition camera or a laser radar.
Compared with the prior art, the invention has the following advantages:
(1) based on holographic sensing data, the method can effectively perform regional division on the high-speed service area, timely analyze and acquire pedestrian risks, human-vehicle risks and vehicle-vehicle risks in different regions, effectively realize quantitative risk identification of the high-speed service area by setting different risk index thresholds, realize holographic sensing and effective identification, and comprehensively guarantee the safety level of the high-speed service area;
(2) the method and the device realize quantitative identification and prediction of the risk of the high-speed service area, design and calculate various risk indexes and risk prediction indexes in the area based on the motion characteristics of the objects participating in the high-speed service area, can effectively identify the risk of the high-speed service area, improve identification accuracy and identification efficiency, and further improve the safety level of the high-speed service area.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a functional area division diagram of a high speed service area to be identified according to the present invention;
FIG. 3 is a schematic illustration of a pedestrian risk index distribution of the present invention;
FIG. 4 is a calculation illustration of a human-vehicle risk index;
fig. 5 is a calculation illustration of the car risk index.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. Note that the following description of the embodiments is merely a substantial example, and the present invention is not intended to be limited to the application or the use thereof, and is not limited to the following embodiments.
Examples
A high-speed service area risk identification method based on holographic sensing data is disclosed, and as shown in FIG. 1, the method comprises the following steps:
s1: and acquiring holographic sensing data collected by sensing equipment of the high-speed service area to be identified.
The sensing equipment can acquire holographic sensing data of all objects in a high-speed service area to be identified, the holographic sensing data has a full-scene sensing visual field and can acquire real-time information of all dynamic and static participating objects in the service area; fields of the collected data include, but are not limited to, time stamp, target ID, target type, target speed, target coordinates, target length, target width.
The sensing equipment is ubiquitous sensing equipment such as a millimeter wave radar, a high-definition camera and a laser radar, and target detection of all objects in the service area is achieved. The ubiquitous sensing equipment is arranged in each area in the service area, and the time service server is used for carrying out unified time service on all the ubiquitous sensing equipment to complete time synchronization.
S2: dividing the high-speed service area into a plurality of functional areas, dividing each functional area into a plurality of grids, and determining the period length of risk identification and early warning.
Step S2 specifically includes
S21: as shown in FIG. 2, the high-speed service area is divided into N functional areas { Z } according to service functions1,Z2,...Zn},ZnThe functional area is an nth functional area, and comprises a refueling area, a passenger car area and the like;
s22: dividing each functional region into a plurality of grids with the size Xm square;
s23: determining a time period length t of risk identification and early warning updatenThe subsequent risk identification results are updated and predicted according to the time interval.
S3: considering that a trampling accident is easy to happen when the density of people is too high, the pedestrian risk index in the area can be judged by utilizing the density D of the pedestrians in the grids, the pedestrian risk index of each grid of each functional area is obtained according to the holographic sensing data, and the pedestrian risk evaluation threshold is determined.
Step S3 specifically includes:
s31: according to the acquired holographic sensing data, the top t is screened out by utilizing the timestamp and the target typenThe target type in the second is a data row of a pedestrian;
s32: as shown in fig. 3, which is a schematic diagram of pedestrian density, for each grid in the region, the number of pedestrians falling in the corresponding grid region is calculated, and the magnitude D of the corresponding pedestrian density is calculated to obtain the corresponding pedestrian risk index Rhh:
wherein ,NpThe number of pedestrians sensed in the grid is obtained, and X is the side length of the grid;
s33: determining a pedestrian risk evaluation threshold matrix:
wherein ,a pedestrian risk index threshold value representing the nth functional zone. The pedestrian risk evaluation threshold value of each functional area is according toThe pedestrian risk evaluation threshold value preset in the functional area can be determined according to historical high-risk pedestrian density, can also be determined according to the pedestrian density threshold value of the top 10 percentile, and can also be determined according to the urban population density specification.
S4: in order to monitor potential human-vehicle and vehicle-vehicle collision accidents in the region, the risk level in the region can be evaluated by calculating the collision time between pedestrians and vehicles and between vehicles, the current vehicle risk index of each grid of each functional region is obtained according to the holographic sensing data, and the current vehicle risk evaluation threshold is determined.
Step S4 specifically includes:
s41: as shown in fig. 4, according to the acquired holographic sensing data, the first t in each area grid is screened out by using the timestamp and the target typenThe type in seconds is the data row of the pedestrian and the vehicle. The collision time between each vehicle and the pedestrian can be solved by using the position coordinates, the vehicle size and the speed of each vehicle and the pedestrian. The size of the pedestrian is negligible, and the current pedestrian and vehicle risk index of each grid of each functional area is calculated:
on the basis, the human-vehicle interaction risk index R in each grid can be obtained by utilizing the human-vehicle collision time in each gridhvThe evaluation is carried out in such a way that,
wherein ,(xi,yi) As coordinates of the pedestrian i, viIs the speed of pedestrian i, (x)j,yj) As the center point coordinate of vehicle j, vjSpeed of vehicle j, αiIs the included angle alpha between the speed of the pedestrian i and the connecting direction of the central points of the pedestrian and the vehiclejIs the included angle between the speed of the vehicle j and the direction of the connecting line of the central points of the pedestrian and the vehicle, ajIs the width of the vehicle j, bjIs the length of the vehicle j, tijTime of collision of pedestrian i with vehicle j, dijIs the distance of the pedestrian i from the body of the vehicle j, Δ djThe distance from the central point of the vehicle j to the vehicle body;
s42: as shown in fig. 5, according to the acquired holographic sensing data, the first t in each area grid is screened out by using the timestamp and the target typenThe type in seconds is the data row of the vehicle. By using the position coordinates, the vehicle sizes and the speed of each vehicle, the collision time between the vehicles can be solved, and the collision time t between the corresponding vehicle h and the vehicle jij
On the basis, the interaction risk index R of the vehicles in each grid can be obtained by utilizing the collision time of the vehicles in each gridvvThe evaluation is carried out in such a way that,
wherein ,(xh,yh) Is the coordinate of the center point of the vehicle h, vhIs the speed of the vehicle h, (x)j,yj) As the center point coordinate of vehicle j, vjSpeed of vehicle j, αhIs the angle between the speed of vehicle i and the direction of the line connecting the center points of the two vehicles, alphajIs the angle between the speed of the vehicle j and the direction of the connecting line of the central points of the two vehicles, ahWidth of vehicle h, bhIs the length of the vehicle h, ajIs the width of the vehicle j, bjIs the length of the vehicle j, thjTime of collision of vehicle h with vehicle j, dhjIs the distance between the body of vehicle h and the body of vehicle j, Δ dhDistance of vehicle h from center point to body, Δ djThe distance from the central point of the vehicle j to the vehicle body;
s43: and determining a current pedestrian and vehicle risk evaluation threshold matrix and a current vehicle and vehicle risk evaluation threshold matrix.
The current pedestrian and vehicle risk evaluation threshold matrix is as follows:
wherein ,the current human-vehicle risk evaluation threshold value is the current human-vehicle risk evaluation threshold value of the nth functional area;
the current car risk evaluation threshold matrix is as follows:
wherein ,and the current vehicle risk evaluation threshold value is the current vehicle risk evaluation threshold value of the nth functional area.
The current human-vehicle risk evaluation threshold value and the current vehicle-vehicle risk evaluation threshold value are both preset threshold values, the determining method can be determined through regional properties and safety requirements, and the two threshold values are less than or equal to 5 s.
S5: in order to improve the response speed to the potential accidents in the area, the safety risk level in the area in the next period can be calculated and judged by further predicting the motion tracks of pedestrians and vehicles. And obtaining the predicted vehicle risk index of each grid of each functional area according to the holographic sensing data and confirming the predicted vehicle risk evaluation threshold.
Step S5 specifically includes:
s51: and screening out the coordinate and speed sensing result of each pedestrian or vehicle in the previous p time periods by utilizing fields such as a timestamp, a target type, a target ID and the like in each area grid according to the acquired holographic sensing data. Therefore, the vehicle motion in a short period can be regarded as uniform acceleration linear motion, and a least square algorithm is utilized to fit a kinematic equation, so that the coordinates and the speed of the corresponding pedestrian and vehicle in the next period can be predicted. For the vehicle or the pedestrian, predicting the coordinates (x ', y ') and the speed v ' of the pedestrian and the vehicle at the next stage:
in the formula ,tnDivide the length for a period, p is the number of periods before prediction, (x)t-n,yt-n) The sensing coordinate value of the vehicle or the pedestrian in the nth time period before the t time period,the sensing speed value of the vehicle or the pedestrian is the nth time period before the t time period;
s52: furthermore, by utilizing the predicted coordinates and predicted speed of the pedestrians and vehicles in each regional grid, the collision time of the pedestrians and the vehicles and the vehicle-vehicle collision time in the next time interval can be calculatedThe collision time is calculated, and then the next-stage prediction human-vehicle risk index R 'is calculated'hv
wherein ,(x′i,y′i) Center point coordinates, v ', predicted for the next period of pedestrian i'iSpeed predicted for pedestrian i next period, (x'j,y'j) Center point coordinates, v ', predicted for the next period of vehicle j'jPredicted speed, α, for the next period of vehicle jiThe included angle alpha between the speed of the pedestrian i and the direction of the connecting line of the central points of the two vehiclesjIs the angle between the speed of the vehicle j and the direction of the connecting line of the central points of the two vehicles, ajIs the width of the vehicle j, bjIs j length, t 'of vehicle'ijIs a predicted value d 'of the collision time of the pedestrian i and the vehicle j in the next period'ijIs the predicted value of the distance between the pedestrian i and the vehicle body of the vehicle j at the next stage, delta djThe distance from the central point of the vehicle j to the vehicle body;
s53: calculating predicted vehicle risk index R 'predicted by next stage'vv:
wherein ,(x'h,y'h) Predicted center point coordinate, v 'for the next period of vehicle h'hIs the predicted speed for the next period of vehicle h, (x'j,y'j) Predicted center point coordinate, v 'for the next time period of vehicle j'jPredicted speed, α, for the next period of vehicle jhIs the angle between the h speed of the vehicle and the direction of the line connecting the center points of the two vehicles, alphajIs the angle between the speed of the vehicle j and the direction of the connecting line of the central points of the two vehicles, ahWidth of vehicle h, bhIs the length of the vehicle h, ajIs the width of the vehicle j, bjIs j length, t 'of vehicle'hjIs a predicted value d 'of the collision time of the vehicle h and the vehicle j in the next period'hjIs a predicted value of the distance between the vehicle h and the vehicle body of the vehicle j at the next stage, delta dhDistance, Δ d, from the center point of the vehicle h to the bodyjThe distance from the central point of the vehicle j to the vehicle body;
s54: and determining a predicted human-vehicle risk evaluation threshold matrix and a predicted vehicle-vehicle risk evaluation threshold matrix.
The forecast human and vehicle risk evaluation threshold matrix is as follows:
Method for determining predicted human-vehicle risk index threshold value and predicted vehicle-vehicle risk index threshold value the method for determining the risk threshold value can be determined by regional properties and safety requirements, is less than or equal to 5s and can be slightly higher than the human-vehicle risk evaluation threshold value and the vehicle-vehicle risk evaluation threshold value in the current time period.
S6: and judging whether the risk indexes of the grids in different functional areas are larger than the corresponding evaluation threshold values, if so, judging that the grids have risks.
Step S6 is to determine whether there is a grid pedestrian risk indicator R in a certain functional areahhIf the grid is larger than the corresponding threshold value, judging that the grid of the functional area has risks, and evacuating the managing personnel to avoid accidents; when a grid people and vehicles risk index R exists in a certain functional areahvOr car risk index RvvIf the grid is larger than the corresponding threshold value, judging that the grid of the functional area has risks, and performing intervention by a manager to avoid accidents; when grid prediction human-vehicle risk index R 'exists in certain area'hvOr predicting a car risk indicator R'vvIf the grid is larger than the corresponding threshold value, the grid of the functional area is judged to have risks, and managers should intervene to reduce the safety risks of the area.
The invention also provides a management module which can display the calculation results of each grid index in different areas and provide guidance for management personnel to carry out traffic risk management.
The above embodiments are merely examples and do not limit the scope of the present invention. These embodiments may be implemented in other various manners, and various omissions, substitutions, and changes may be made without departing from the technical spirit of the present invention.
Claims (10)
1. A high-speed service area risk identification method based on holographic sensing data is characterized by comprising the following steps:
s1: acquiring holographic sensing data collected by sensing equipment in a high-speed service area to be identified;
s2: dividing the high-speed service area into a plurality of functional areas, dividing each functional area into a plurality of grids, and determining the time period length of risk identification and early warning;
s3: acquiring a pedestrian risk index of each grid of each functional area according to the holographic sensing data and determining a pedestrian risk evaluation threshold;
s4: acquiring current vehicle risk indexes of grids of each functional area according to the holographic sensing data and determining a current vehicle risk evaluation threshold;
s5: obtaining a predicted vehicle risk index of each grid of each functional area according to the holographic sensing data and confirming a predicted vehicle risk evaluation threshold;
s6: and judging whether the risk indexes of the grids in different functional areas are larger than the corresponding evaluation threshold values, if so, judging that the grids have risks.
2. The holographic sensing data-based high-speed service area risk identification method according to claim 1, wherein the step S2 specifically comprises:
s21: dividing high-speed service area into N function areas according to service function { Z1,Z2,...Zn},ZnIs the nth functional area;
s22: dividing each functional area into a plurality of grids with the size of X m × X m squares;
s23: determining a time period length t of risk identification and early warning updaten。
3. The holographic sensing data-based high-speed service area risk identification method according to claim 1, wherein the step S3 specifically comprises:
s31: according to the collectionHolographic sensing data, and screening out the top t by using a timestamp and a target typenThe data row of which the target type is a pedestrian in the second;
s32: calculating the pedestrian density D of each grid of each functional area and obtaining the corresponding pedestrian risk index Rhh:
wherein ,NpThe number of pedestrians sensed in the grid is obtained, and X is the side length of the grid;
s33: and determining a pedestrian risk evaluation threshold matrix.
5. The holographic sensing data-based high-speed service area risk identification method according to claim 1, wherein the step S4 specifically comprises:
s41: calculating the current human-vehicle risk index of each grid of each functional area:
wherein ,(xi,yi) As coordinates of the pedestrian i, viIs the speed of pedestrian i, (x)j,yj) As the center point coordinate of vehicle j, vjSpeed of vehicle j, αiThe included angle alpha between the speed of the pedestrian i and the direction of the connecting line of the central points of the pedestrian and the vehiclejIs the included angle between the speed of the vehicle j and the direction of the connecting line of the central points of the man and the vehicle, ajIs the width of the vehicle j, bjIs the length of the vehicle j, tijTime of collision of pedestrian i with vehicle j, dijIs the distance, Δ d, of the pedestrian i from the body of the vehicle jjThe distance from the central point of the vehicle j to the vehicle body;
s42: calculating the current car risk index of each grid of each functional area:
wherein ,(xh,yh) As coordinates of the center point of the vehicle h, vhSpeed of vehicle h, (x)j,yj) As the center point coordinate of vehicle j, vjSpeed of vehicle j, αhIs the angle between the speed of vehicle i and the direction of the line connecting the center points of the two vehicles, alphajIs the angle between the speed of the vehicle j and the direction of the connecting line of the central points of the two vehicles, ahWidth of vehicle h, bhIs the length of the vehicle h, ajIs the width of the vehicle j, bjIs the length of the vehicle j, thjTime of collision of vehicle h with vehicle j, dhjIs the distance between the body of vehicle h and the body of vehicle j, Δ dhDistance of vehicle h from center point to body, Δ djThe distance from the central point of the vehicle j to the vehicle body;
s43: and determining a current human-vehicle risk evaluation threshold matrix and a current vehicle-vehicle risk evaluation threshold matrix.
6. The holographic sensing data-based high-speed service area risk identification method according to claim 5, wherein the current human-vehicle risk evaluation threshold matrix is:
wherein ,the current human-vehicle risk evaluation threshold value is the current human-vehicle risk evaluation threshold value of the nth functional area;
the current vehicle risk evaluation threshold matrix is as follows:
7. The holographic sensing data-based high-speed service area risk identification method according to claim 1, wherein the step S5 specifically comprises:
s51: and (3) predicting the coordinates (x ', y ') and the speed v ' of the pedestrian and the vehicle at the next stage:
in the formula ,tnDivide the length for a period, p is the number of periods before prediction, (x)t-n,yt-n) The perception coordinate value of the vehicle or the pedestrian in the nth time period before the t time period,the sensing speed value of the vehicle or the pedestrian is the nth time period before the t time period;
s52: calculating next-stage prediction human-vehicle risk index R'hv
wherein ,(x'i,y'i) Center point coordinates, v ', predicted for the next period of pedestrian i'iIs the predicted speed for the next time period of pedestrian i, (x'j,y'j) Predicted center point coordinate, v 'for the next time period of vehicle j'jPredicted speed, α, for the next period of vehicle jiIs the angle between the speed of the pedestrian i and the direction of the connecting line of the central points of the two vehicles, alphajIs the angle between the speed of the vehicle j and the direction of the line connecting the central points of the two vehicles, ajIs the width of the vehicle j, bjIs vehicle j length, t'ijFor the predicted value of the time of collision of the pedestrian i with the vehicle j in the next time period, di'jIs the predicted value of the distance between the pedestrian i and the vehicle body of the vehicle j at the next stage, delta djThe distance from the central point of the vehicle j to the vehicle body;
s53: calculating predicted vehicle risk index R 'predicted by next stage'vv:
wherein ,(x'h,y'h) Center point coordinates, v ', predicted for the next period of vehicle h'hIs the predicted speed for the next period of vehicle h, (x'j,y'j) Predicted center point coordinate, v 'for the next time period of vehicle j'jPredicted speed, α, for the next period of vehicle jhIs the angle between the h speed of the vehicle and the direction of the line connecting the center points of the two vehicles, alphajIs the angle between the speed of the vehicle j and the direction of the line connecting the central points of the two vehicles, ahWidth of vehicle h, bhIs the length of the vehicle h, ajIs the width of the vehicle j, bjIs j length, t 'of vehicle'hjIs a predicted value d 'of the collision time of the vehicle h and the vehicle j in the next period'hjIs a predicted value of the distance between the vehicle h and the vehicle body of the vehicle j at the next stage, delta dhDistance of vehicle h from center point to body, Δ djThe distance from the central point of the vehicle j to the vehicle body;
s54: and determining a predicted pedestrian and vehicle risk evaluation threshold matrix and a predicted vehicle and vehicle risk evaluation threshold matrix.
8. The holographic sensing data-based high-speed service area risk identification method according to claim 7, wherein the predicted human-vehicle risk evaluation threshold matrix is as follows:
9. The method for identifying the risk of the high-speed service area based on the holographic sensing data as claimed in claim 1, wherein the sensing device is capable of acquiring the holographic sensing data of all objects in the high-speed service area to be identified, the holographic sensing data has a full-scene sensing view and is capable of acquiring real-time information of all dynamic and static participating objects in the service area; fields of the collected data include, but are not limited to, time stamp, target ID, target type, target speed, target coordinates, target length, target width.
10. The holographic sensing data based high-speed service area risk identification method as claimed in claim 9, wherein the sensing device is a millimeter wave radar, a high definition camera or a laser radar.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210236418.7A CN114781791B (en) | 2022-03-11 | 2022-03-11 | High-speed service area risk identification method based on holographic perception data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210236418.7A CN114781791B (en) | 2022-03-11 | 2022-03-11 | High-speed service area risk identification method based on holographic perception data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114781791A true CN114781791A (en) | 2022-07-22 |
CN114781791B CN114781791B (en) | 2023-09-29 |
Family
ID=82423674
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210236418.7A Active CN114781791B (en) | 2022-03-11 | 2022-03-11 | High-speed service area risk identification method based on holographic perception data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114781791B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106652556A (en) * | 2015-10-28 | 2017-05-10 | 中国移动通信集团公司 | Human-vehicle anti-collision method and apparatus |
CN107862437A (en) * | 2017-10-16 | 2018-03-30 | 中国人民公安大学 | The public domain crowd massing method for early warning and system assessed based on risk probability |
CN111260915A (en) * | 2020-01-22 | 2020-06-09 | 长安大学 | Early warning reminding method for pedestrian stay in expressway traffic abnormal area |
CN111311093A (en) * | 2020-02-13 | 2020-06-19 | 中交第一公路勘察设计研究院有限公司 | Road intersection risk assessment and early warning method based on driver physiological data |
CN111429754A (en) * | 2020-03-13 | 2020-07-17 | 南京航空航天大学 | Vehicle collision avoidance track risk assessment method under pedestrian crossing working condition |
CN111462488A (en) * | 2020-04-01 | 2020-07-28 | 北京工业大学 | Intersection safety risk assessment method based on deep convolutional neural network and intersection behavior characteristic model |
CN111815986A (en) * | 2020-09-02 | 2020-10-23 | 深圳市城市交通规划设计研究中心股份有限公司 | Traffic accident early warning method and device, terminal equipment and storage medium |
CN112349100A (en) * | 2020-11-09 | 2021-02-09 | 紫清智行科技(北京)有限公司 | Multi-view driving risk assessment method and device based on internet environment |
CN112550284A (en) * | 2020-11-16 | 2021-03-26 | 东南大学 | Self-adaptive cruise driving risk assessment method under vehicle-road coupling effect |
CN113112809A (en) * | 2021-04-23 | 2021-07-13 | 武汉理工大学 | Intersection traffic safety risk evaluation system based on holographic sensing |
CN113272195A (en) * | 2019-12-16 | 2021-08-17 | 驭势科技(北京)有限公司 | Control system and control method for intelligent networked vehicle |
-
2022
- 2022-03-11 CN CN202210236418.7A patent/CN114781791B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106652556A (en) * | 2015-10-28 | 2017-05-10 | 中国移动通信集团公司 | Human-vehicle anti-collision method and apparatus |
CN107862437A (en) * | 2017-10-16 | 2018-03-30 | 中国人民公安大学 | The public domain crowd massing method for early warning and system assessed based on risk probability |
CN113272195A (en) * | 2019-12-16 | 2021-08-17 | 驭势科技(北京)有限公司 | Control system and control method for intelligent networked vehicle |
CN111260915A (en) * | 2020-01-22 | 2020-06-09 | 长安大学 | Early warning reminding method for pedestrian stay in expressway traffic abnormal area |
CN111311093A (en) * | 2020-02-13 | 2020-06-19 | 中交第一公路勘察设计研究院有限公司 | Road intersection risk assessment and early warning method based on driver physiological data |
CN111429754A (en) * | 2020-03-13 | 2020-07-17 | 南京航空航天大学 | Vehicle collision avoidance track risk assessment method under pedestrian crossing working condition |
CN111462488A (en) * | 2020-04-01 | 2020-07-28 | 北京工业大学 | Intersection safety risk assessment method based on deep convolutional neural network and intersection behavior characteristic model |
CN111815986A (en) * | 2020-09-02 | 2020-10-23 | 深圳市城市交通规划设计研究中心股份有限公司 | Traffic accident early warning method and device, terminal equipment and storage medium |
CN112349100A (en) * | 2020-11-09 | 2021-02-09 | 紫清智行科技(北京)有限公司 | Multi-view driving risk assessment method and device based on internet environment |
CN112550284A (en) * | 2020-11-16 | 2021-03-26 | 东南大学 | Self-adaptive cruise driving risk assessment method under vehicle-road coupling effect |
CN113112809A (en) * | 2021-04-23 | 2021-07-13 | 武汉理工大学 | Intersection traffic safety risk evaluation system based on holographic sensing |
Non-Patent Citations (3)
Title |
---|
YUCHUAN DU等: "Stochastic choice simulation approach for regional traffic volume estimation", 《SECOND INTERNATIONAL CONFERENCE ON TRANSPORTATION ENGINEERING》, pages 512 - 525 * |
刘金: "基于人车环境动态数据协同推演的汽车驾驶倾向性特征提取及辨识", 《中国优秀硕士学位论文全文数据库工程科技II辑》, no. 4, pages 1 - 121 * |
杜豫川 等: "路侧感知车辆轨迹数据质量智能评估方法", 《中国公路学报》, vol. 34, no. 7, pages 164 - 176 * |
Also Published As
Publication number | Publication date |
---|---|
CN114781791B (en) | 2023-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11380105B2 (en) | Identification and classification of traffic conflicts | |
Oh et al. | A method for identifying rear-end collision risks using inductive loop detectors | |
CN110807930B (en) | Dangerous vehicle early warning method and device | |
JP6045846B2 (en) | Traffic accident occurrence prediction device, method and program | |
CN116957345B (en) | Data processing method for unmanned system | |
CN111460920A (en) | Target tracking and segmenting system for complex scene of airport | |
JP4580995B2 (en) | Road traffic control system | |
Deng | Anomaly detection of highway vehicle trajectory under the internet of things converged with 5g technology | |
CN115578850A (en) | Urban traffic intelligent control method and system based on traffic informatization | |
Worrall et al. | Improving vehicle safety using context based detection of risk | |
Fu et al. | Spatial analysis of taxi speeding event using GPS trajectory data | |
Chen et al. | A Novel Background Filtering Method with Automatic Parameter Adjustment for Real-Time Roadside LiDAR Sensing System | |
CN116682264B (en) | Active safety prevention and control system for port vehicle | |
CN114781791B (en) | High-speed service area risk identification method based on holographic perception data | |
Zuo et al. | Determination of bus crowding coefficient based on passenger flow forecasting | |
CN117022323A (en) | Intelligent driving vehicle behavior analysis and prediction system and method | |
CN114724356B (en) | GIS expressway accident early warning method and system based on meteorological data integration | |
CN113256014B (en) | Intelligent detection system for 5G communication engineering | |
Subirats et al. | A new road safety indicator based on vehicle trajectory analysis | |
JP4128962B2 (en) | Road traffic control system | |
Kaur et al. | RFID based Intelligent Transport System with RSU Communication for Emergency Vehicles in Urbanization | |
Yun et al. | A before-and-after study of a collision risk detecting and warning system on local roads | |
Wang et al. | Automatic freeway incident detection for free flow conditions: a vehicle reidentification based approach using image data from sparsely distributed video cameras | |
Yang et al. | Vehicle collision prediction based on support vector data description | |
Fazekas et al. | Statistical analysis of data describing the relationship between driver, truck and characteristics of the road |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |