CN111724590B - Highway abnormal event occurrence time estimation method based on travel time correction - Google Patents

Highway abnormal event occurrence time estimation method based on travel time correction Download PDF

Info

Publication number
CN111724590B
CN111724590B CN202010495068.7A CN202010495068A CN111724590B CN 111724590 B CN111724590 B CN 111724590B CN 202010495068 A CN202010495068 A CN 202010495068A CN 111724590 B CN111724590 B CN 111724590B
Authority
CN
China
Prior art keywords
time
occurrence
abnormal event
data
event
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.)
Active
Application number
CN202010495068.7A
Other languages
Chinese (zh)
Other versions
CN111724590A (en
Inventor
孙棣华
唐毅
王荣斌
吴霄
陈平
赵敏
蔡啸
李志晗
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Shouxun Technology Co ltd
Chongqing University
Original Assignee
Chongqing Shouxun Technology Co ltd
Chongqing University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Shouxun Technology Co ltd, Chongqing University filed Critical Chongqing Shouxun Technology Co ltd
Priority to CN202010495068.7A priority Critical patent/CN111724590B/en
Publication of CN111724590A publication Critical patent/CN111724590A/en
Application granted granted Critical
Publication of CN111724590B publication Critical patent/CN111724590B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a method for estimating the occurrence time of an abnormal event of a highway based on travel time correction, comprising the following steps of S1: extracting vehicle occupancy data of the abnormal event occurring road section, and performing smoothing processing; s2: detecting the occurrence time of the abnormal event by using an FCM algorithm; s3: acquiring average travel time between adjacent toll stations based on the charging data and the gate data; s4: judging the occurrence place of the abnormal event according to the data of the workshop appliances at the upstream and the downstream; s5: extracting the time required by the abnormal event from the accident occurrence point to the position of the downstream vehicle detector; s6: and correcting the occurrence time of the abnormal event. The invention estimates the travel time of the road section, obtains the time of the event occurrence to the upstream and downstream detectors by a series of calculation of the obtained travel time of the road section, then obtains the event detection time, and finally can finish the estimation of the actual occurrence time of the event by two times, thereby achieving the purpose of rapidly estimating the occurrence time of the event.

Description

Highway abnormal event occurrence time estimation method based on travel time correction
Technical Field
The invention relates to the field of traffic data analysis and processing, in particular to a method for estimating the occurrence time of an abnormal event on a highway based on travel time correction.
Background
In recent years, the number of vehicles owned by people is increased explosively, the increasing rate of the vehicles is far higher than the extending construction speed of a highway network, the phenomenon of road surface supersaturation is continuously increased, and the probability of abnormal events on the highway is greatly increased.
The vehicles in the highway run fast, and the road surface road is closed, and the trafficability of lane is big. In a high-speed kilometer, once an abnormal event occurs, such as a traffic accident, a road damage, or poor driving conditions caused by weather conditions, the consequences are very serious. Particularly, under the condition of bad weather (such as heavy fog, heavy rain and the like which affect the visibility of roads), the method is easy to cause chain car accidents or secondary accidents, and cause the harm to bad personnel and property. Meanwhile, in some mountain areas such as Chongqing and the like, due to special terrain, the occupation ratio of special road sections such as bridges, tunnels and the like in the expressway is high, and the special road sections have the characteristics of large influence, difficulty in eliminating and the like after traffic abnormality occurs. In order to overcome the problems, the information of the abnormal event must be detected in time, and only by obtaining the actual time and the influence degree of the abnormal event, the decision can be made by a traveler and a controller, so that the operation safety of the highway system is guaranteed.
However, in the actual field implementation, due to the influence of a certain hysteresis of the detection cycle time and the detection algorithm of the detection device, the detection time of many events has a certain delay with the real time of the event occurrence. However, because the cost of the detector is high, the installation of the vehicle detector is sparse, the distance is uneven, the detection range is small, and the difference between the detection time and the occurrence time is sometimes very large, which leads people to be unable to know when the event occurs, so that it is difficult to predict how the subsequent situation evolves. Therefore, it is very important to accurately and rapidly estimate the time of the event from the obtained information.
Disclosure of Invention
In view of this, the present invention provides a method for estimating the time of an abnormal event on a highway based on travel time correction, so as to achieve the purpose of rapidly estimating the time of the event, and have great significance.
The purpose of the invention is realized by the following technical scheme:
an estimation method of the occurrence time of an abnormal event of an expressway based on travel time correction,
s1: based on the vehicle detector, extracting vehicle occupancy data of the abnormal event occurrence road section, and performing smoothing processing;
s2: detecting occurrence time t of abnormal event by using FCM algorithmde；
S3: obtaining average travel time T between adjacent toll stations based on charging data and toll gate datai,i+1；
S4: judging the occurrence place of the abnormal event according to the data of the upstream workshop appliance and the downstream workshop appliance, wherein the occurrence place is the upstream or the downstream of the road section where the abnormal event is located;
s5: extracting the time T required by the abnormal event from the accident occurrence point to the position of the downstream vehicle detectoraf；
S6: correcting the occurrence time of the abnormal event to obtain the real time t of the abnormal eventoc。
Further, the S2 specifically includes:
s21: selecting the absolute difference of the occupancy rates of the upstream and downstream vehicles at each moment of the road section where the abnormal event is located; the ratio of the absolute difference between the upstream and downstream vehicle occupancy to the upstream occupancy; clustering the data set by using the three data of the downstream occupancy;
s22: dividing the data into two fuzzy groups, wherein the two fuzzy groups respectively represent the occurrence and non-occurrence of abnormal events and correspondingly generate clustering centers of the two fuzzy groups;
s23: and judging the data set to be judged by adopting the Euclidean distance according to the clustering center obtained by fuzzy clustering to obtain the data set and the corresponding judgment result, wherein the event is generated or not generated.
S24: when the event is judged to occur, the time in the smoothed vehicle data is acquired as the detected time tde。
Further, the S3 specifically includes:
s31: the detection period is set up, and the detection period,data matching is carried out by combining ramp charging data and checkpoint data, and travel time t of n vehicles in the detection period is obtainedi(i＝1,2,...,n)；
S32: acquiring the average travel time of the vehicle on the abnormal event occurrence road section based on S31;
s33: acquiring the average travel time from a toll station i to a gate and the average travel time from a toll station i +1 to the gate, and acquiring the travel time from the toll station i to the i + 1:
Figure BDA0002522485480000021
further, the method for correcting the occurrence time of the abnormal event comprises the following steps:
toc＝tde-Taf
wherein: t is tocThe actual occurrence time of the abnormal event.
The invention has the beneficial effects that:
the invention firstly estimates the travel time of the road section through the charging data, obtains the time of the event occurrence reaching the upstream and downstream detectors through a series of calculations of the obtained road section travel time, designs an event detection algorithm to obtain the event detection time, and finally can complete the estimation of the actual event occurrence time according to the two time, thereby achieving the purpose of rapidly estimating the event occurrence time and having very important significance.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings, in which:
FIG. 1 is a schematic diagram illustrating the process from occurrence to detection of an abnormal event;
FIG. 2 shows a schematic flow diagram of the present invention;
FIG. 3 shows a FCM-based event occurrence event detection flow diagram.
Detailed Description
Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be understood that the preferred embodiments are illustrative of the invention only and are not limiting upon the scope of the invention.
The embodiment provides a method for estimating the occurrence time of an abnormal event on a highway based on travel time correction, which is used for accurately and quickly estimating the occurrence time of the abnormal event, and specifically shown in fig. 1 and 2:
s1: according to the vehicle detector, vehicle occupancy data of the abnormal event occurrence road section is extracted, and smoothing processing is carried out, wherein the method specifically comprises the following steps:
s11: according to a vehicle detector of a road section on which an abnormal event occurs, collecting traffic flow data of the road section by taking every 5min as a period, wherein the traffic flow data mainly comprises vehicle occupancy, namely collecting the vehicle occupancy of the road section every 5 min;
s12: the vehicle occupancy data is smoothed, and in the present embodiment, a function of the vehicle occupancy with time is formed by using a difference method, and then vehicle occupancy data with a period of 1min is obtained, where 1min is 1 time in the following discussion.
S2: acquiring the occurrence time t of the abnormal event by utilizing the FCM algorithm for the processed vehicle occupancy datadeAs shown in fig. 3, in particular.
S21: extracting the absolute difference of the occupancy rates of the vehicles at the upper and lower reaches of each time of the road section where the abnormal event is located; the ratio of the absolute difference between the upstream and downstream vehicle occupancy to the upstream occupancy; a downstream occupancy;
s22: clustering the three groups of data into two fuzzy groups, wherein the two fuzzy groups respectively represent the occurrence and non-occurrence of abnormal events and correspondingly generate clustering centers of the two fuzzy groups;
the objective function of FMC is:
Figure BDA0002522485480000031
dij＝||ci-xi||
Figure BDA0002522485480000041
wherein:
cirepresenting the center of the i-th class of the fuzzy class;
c represents a common class c;
n represents a total of n data objects;
m is a weighting index satisfying m ∈ [1, ∞);
dijthe Euclidean distance from the jth data object to the ith cluster center;
uijand representing the membership size of the j-th data object belonging to the i-class.
And calculating and updating the clustering centers, and judging whether the iteration termination condition is met or not by respectively representing the occurrence and non-occurrence of the event by the two clustering centers until the iteration termination condition is met.
The iteration termination condition is as follows:
||J(t+1)-J(t)| | < epsilon or T ═ Tmax
Wherein:
J(t+1)the t +1 th objective function value;
J(t)the t-th objective function value;
epsilon is an iteration termination condition threshold;
Tmaxis the maximum number of iterations.
S23: minimizing the cost function of the dissimilarity index of the two fuzzy groups according to the Euclidean distance, wherein the Euclidean distance is expressed as:
Figure BDA0002522485480000042
wherein: x and y represent the objects of the two fuzzy groups, respectively;
xkand ykThe kth feature vector for two data objects;
p is the sum of the feature vectors of the data objects.
S24: through the steps, two fuzzy groups with the minimum value functions of two non-similarity indexes are obtained, the data set required to be judged is judged by the Euclidean distance according to the clustering center obtained by fuzzy clustering, the data set and the corresponding judgment result are obtained, and the event is generated or not generated.
S25: when the event is judged to occur, the time in the smoothed vehicle data is acquired as the detected time tde。
S3: obtaining average travel time T between adjacent toll stations based on charging data and toll gate datai,i+1The method specifically comprises the following steps:
s31: setting a detection period, wherein the detection period in the embodiment is 1h, and performing data matching by combining ramp charging data and gate data to obtain travel time t of n vehicles in the detection periodi(i＝1,2,...,n)；
S32: acquiring the average travel time of the vehicle on the abnormal event occurrence road section based on S31;
s33: acquiring the average travel time from a toll station i to a gate and the average travel time from a toll station i +1 to the gate, and acquiring the travel time from the toll station i to the i + 1:
Figure BDA0002522485480000051
s4: according to the data of the upstream workshop appliance and the downstream workshop appliance, judging the occurrence place of the abnormal event, wherein the occurrence place is the upstream or the downstream of the road section where the abnormal event is located, and the judging method comprises the following steps: in the case where the threshold value of the change in vehicle occupancy between adjacent times is set manually, it is possible to extract whether or not the time at which the change in vehicle occupancy of the upstream exceeds the threshold value is prior to the time at which the change in vehicle occupancy of the downstream exceeds the threshold value, based on the function of the change in vehicle occupancy with time obtained in S1, and if so, the point of occurrence of the abnormal event is upstream, and if not, the abnormal event occurs downstream.
S5: extracting the time T required by the abnormal event from the accident occurrence point to the position of the downstream vehicle detectorafSpecifically, the method comprises the following steps:
s51: according to the section Li,i+1Length l ofi,i+1And the average travel time T of the road sectioni,i+1Calculating the average travel speed V of the road sectioni,i+1：
Figure BDA0002522485480000052
S52: according to the average travel speed V of the road sectioni,i+1And the distance l between the accident occurrence point and the downstream vehicle detectordownCalculating the time T required for the vehicle to pass from the point of accident to the position of the downstream detectoraf：
Figure BDA0002522485480000053
S6: using the time T required for the vehicle to reach the position of the downstream detector from the point of accidentafCorrecting event detection event TtsEstimate the true time t of the event occurrenceoc：
toc＝tde-Taf
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.

Claims (2)

1. The method for estimating the occurrence time of the expressway abnormal event based on travel time correction is characterized by comprising the following steps of:
s1: based on the vehicle detector, extracting vehicle occupancy data of the abnormal event occurrence road section, and performing smoothing processing;
s2: detecting occurrence time t of abnormal event by using FCM algorithmdeThe method specifically comprises the following steps:
s21: selecting the absolute difference of the occupancy rates of the upstream and downstream vehicles at each moment of the road section where the abnormal event is located; the ratio of the absolute difference between the upstream and downstream vehicle occupancy to the upstream occupancy; clustering the data set by using the three data of the downstream occupancy;
s22: dividing the data into two fuzzy groups, wherein the two fuzzy groups respectively represent the occurrence and non-occurrence of abnormal events and correspondingly generate clustering centers of the two fuzzy groups;
s23: judging the data set to be judged by adopting the Euclidean distance according to the clustering center obtained by fuzzy clustering to obtain the data set and the corresponding judgment result, wherein the event occurs or does not occur;
s24: when the event is judged to occur, acquiring the time in the smoothed vehicle detector data as the detection time tde；
S3: obtaining average travel time T between adjacent toll stations based on charging data and toll gate datai,i+1；
S4: judging the occurrence place of the abnormal event according to the data of the upstream workshop appliance and the downstream workshop appliance, wherein the occurrence place is the upstream or the downstream of the road section where the abnormal event is located;
s5: extracting the time T required by the abnormal event from the accident occurrence point to the position of the downstream vehicle detectoraf；
S6: correcting the occurrence time of the abnormal event to obtain the real time t of the abnormal eventocThe method for correcting the occurrence time of the abnormal event comprises the following steps:
toc＝tde-Taf
wherein: t is tocThe actual occurrence time of the abnormal event.
2. The method for estimating the occurrence time of an abnormal highway event based on travel time correction according to claim 1, wherein: the S3 specifically includes:
s31: setting a detection period, carrying out data matching by combining ramp charging data and gate data, and obtaining the travel time t of n vehicles in the detection periodi(i＝1,2,...,n)；
S32: acquiring the average travel time of the vehicle on the abnormal event occurrence road section based on S31;
s33: acquiring the average travel time from a toll station i to a gate and the average travel time from a toll station i +1 to the gate, and acquiring the travel time from the toll station i to the i + 1:
Figure FDA0003528593400000011
CN202010495068.7A 2020-06-03 2020-06-03 Highway abnormal event occurrence time estimation method based on travel time correction Active CN111724590B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010495068.7A CN111724590B (en) 2020-06-03 2020-06-03 Highway abnormal event occurrence time estimation method based on travel time correction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010495068.7A CN111724590B (en) 2020-06-03 2020-06-03 Highway abnormal event occurrence time estimation method based on travel time correction

Publications (2)

Publication Number Publication Date
CN111724590A CN111724590A (en) 2020-09-29
CN111724590B true CN111724590B (en) 2022-04-15

Family

ID=72565691

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010495068.7A Active CN111724590B (en) 2020-06-03 2020-06-03 Highway abnormal event occurrence time estimation method based on travel time correction

Country Status (1)

Country Link
CN (1) CN111724590B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112530163B (en) * 2020-11-23 2022-03-01 腾讯科技（深圳）有限公司 Traffic accident prediction method, traffic accident prediction device, electronic device, and storage medium
CN112991724B (en) * 2021-02-09 2022-08-12 重庆大学 Method and device for estimating occurrence position and occurrence time of highway abnormal event
CN113345220B (en) * 2021-05-11 2022-08-16 山西省交通科技研发有限公司 Highway inspection vehicle tracking and prediction analysis system
CN115424432B (en) * 2022-07-22 2024-05-28 重庆大学 Upstream diversion method based on multisource data under expressway abnormal event

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3734594B2 (en) * 1997-05-16 2006-01-11 三菱電機株式会社 Abnormal event detection device and traffic flow measurement device
CN102419905B (en) * 2011-08-12 2013-07-31 北京航空航天大学 Traffic-wave theory-based traffic influence area determining method of expressway accidents
CN104408907B (en) * 2014-10-31 2016-07-13 重庆大学 There is the freeway traffic event Duration Prediction method of on-line optimization ability
CN107146409B (en) * 2017-06-01 2019-11-19 东方网力科技股份有限公司 The identification of equipment detection time exception and true time difference evaluation method in road network
CN108428341A (en) * 2018-05-14 2018-08-21 齐鲁交通发展集团有限公司青临分公司 A kind of emergency traffic management and dispatching method and system based on human-computer fusion
CN109754604B (en) * 2018-12-03 2021-01-26 江苏智运科技发展有限公司 Congestion area identification method based on traffic coil detection data quality control

Also Published As

Publication number Publication date
CN111724590A (en) 2020-09-29

Similar Documents

Publication Publication Date Title
CN111724590B (en) Highway abnormal event occurrence time estimation method based on travel time correction
CN112382095A (en) Urban expressway traffic state estimation method based on multi-source data fusion
CN102509291B (en) Pavement disease detecting and recognizing method based on wireless online video sensor
CN114863675B (en) Road police data fusion-based key vehicle position estimation and abnormality alarm method
CN103310199B (en) Based on the vehicle model recognition methods of high-definition remote sensing data
CN117057614B (en) Highway safe operation dynamic change prediction method and system based on remote sensing technology
CN109082984A (en) A kind of road abnormality detection model based on window division and dynamic time warping
CN111640304B (en) Automatic quantitative extraction method for traffic jam propagation characteristics of continuous flow traffic facility
CN111882858A (en) Method for predicting queuing length of expressway abnormal events based on multi-source data
CN103093625A (en) City road traffic condition real-time estimation method based on reliability verification
CN116168356A (en) Vehicle damage judging method based on computer vision
CN111724592A (en) Highway traffic jam detection method based on charging data and checkpoint data
CN109344903B (en) Urban road pavement fault real-time detection method based on vehicle-mounted sensing data
CN112927511A (en) Vehicle early warning method based on driver age and gender identification
CN113033363A (en) Vehicle dense target detection method based on deep learning
CN113256014B (en) Intelligent detection system for 5G communication engineering
CN111724591B (en) Three-dimensional McMaster method for detecting traffic jam of section of highway
CN112183597B (en) Unbalanced traffic accident severity analysis method based on spectral clustering
CN113722982A (en) Automobile sensor attack detection and defense method based on multi-model fusion
CN113887659A (en) Vehicle type classification algorithm based on naive Bayes
CN108288382B (en) Method for judging vehicle reliability based on belief double-base model
CN107730919B (en) Pedestrian signal control method based on mobile phone terminal
CN113920723B (en) Identification method for mountainous area expressway accident-prone road section
CN113380032B (en) Hierarchical clustering method-based highway congestion judgment method and device
Oh et al. Gaussian background mixture model based automatic incident detection system for real-time tracking

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