CN110288823A - A kind of break in traffic rules and regulations erroneous judgement recognition methods based on naive Bayesian network - Google Patents
A kind of break in traffic rules and regulations erroneous judgement recognition methods based on naive Bayesian network Download PDFInfo
- Publication number
- CN110288823A CN110288823A CN201910392002.2A CN201910392002A CN110288823A CN 110288823 A CN110288823 A CN 110288823A CN 201910392002 A CN201910392002 A CN 201910392002A CN 110288823 A CN110288823 A CN 110288823A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- regulations
- traffic
- node
- 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
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
-
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention discloses one of break in traffic rules and regulations field and judges recognition methods by accident based on the break in traffic rules and regulations of naive Bayesian network, from vehicle and traffic information of the collection violation vehicle in traffic administration system database before and after the moment violating the regulations in a period of time, establish primary data training set, it constructs naive Bayesian network violation vehicle and judges identification model by accident, determine conditional probability distribution；Then the vehicle and traffic information in current slot are obtained, input of the vehicle and traffic information that will acquire as model obtains posterior probability, finally differentiates whether vehicle breaks rules and regulations really；The present invention is by naive Bayesian network model use into vehicle violation erroneous judgement identification, it is after electronic police determines vehicle violation, again to its progress depth recognition whether violating the regulations, the current traffic information of violation vehicle is considered not only, the traffic information being additionally contemplates that within the scope of front and back a period of time at moment violating the regulations simultaneously has higher accuracy for erroneous judgement identification violating the regulations.
Description
Technical field
The present invention relates to the recognition methods that break in traffic rules and regulations technical field more particularly to break in traffic rules and regulations are judged by accident.
Background technique
To maintain city vehicle management order, the installation equipment such as electronic monitoring are managed that play must to urban highway traffic
Indispensable effect, advocating for intelligent transportation also allow the equipment of urban traffic intersection electronic police to increase therewith.Electronic police is
It is a kind of to capture traffic offence or traffic accident using automatic detection and measuring technique, the information of acquisition is passed back public affairs using network
Peace department is analyzed and processed, and punishes as evidence to troublemaker, is occurred with reducing accident, auxiliary traffic police's work.
But electronic police is machine after all, inevitably has " accidental injury ", so as to cause the erroneous judgement to vehicle violation, and road conditions are complicated more
Become, such as carries out an urgent task that special car, signal lamp failure are violating the regulations, avoid failure or accident vehicle to avoid 119, emergency tender
And break rules and regulations, traffic lights and live traffic police command inconsistent, vehicle that situation violating the regulations when deck, is caused to be can be with
Application to set aside record violating the regulations, for another example more complicated road conditions, are the special car for avoiding carrying out an urgent task at red light crossing, lead
Causing front, continuously more vehicles make a dash across the red light or crimping is violating the regulations, and the vehicle nearest apart from special car is in manual examination and verification link
It easily identifies as that can be recorded so that application to set aside is violating the regulations, and apart from the more difficult identification of the farther away vehicle of special car, to cause
Erroneous judgement violating the regulations, and in manual examination and verification link, since workload is huge, may occur due to human factor or objective factor interference
Quality problems, resulting illegal activities erroneous judgement, misjudgement.
Problem is judged by accident for break in traffic rules and regulations, is disclosed in the document that Chinese Patent Application No. is CN201110123733.0
A kind of violation vehicle detection method of violation vehicle detection device of the application based on video identification can detect vehicle malice simultaneously
It jumps a queue, the break in traffic rules and regulations behavior in solid line lane change and continuous change two or more lane, avoids the erroneous judgement to normal lane change behavior, but
It is that this method can not solve erroneous judgement violating the regulations under a variety of special road conditions set forth above.
Bayesian theory is the important tool for handling unascertained information.As a kind of uncertain inference based on probability
Method, Bayesian network have obtained important application in the intellectualizing system of processing uncertain information, have been successfully used to
The fields such as medical diagnosis, statistical decision, expert system.These are successfully applied, and having fully demonstrated Bayesian networks technique is one
The strong reasoning method under uncertainty of kind.Naive Bayesian method is point independently assumed based on Bayes' theorem and characteristic condition
Class method.Naive Bayesian network model is presently the most one of extensive disaggregated model, it is one and includes a root node,
The tree-shaped Bayesian network of multiple leaf nodes.Bayesian network is applied to break in traffic rules and regulations field not yet at present.
Summary of the invention
Object of the present invention is to provide one for the erroneous judgement problem violating the regulations under a variety of special road conditions existing in the prior art
Break in traffic rules and regulations of the kind based on naive Bayesian network judges recognition methods by accident, works as using violation vehicle and in front and back a period of time violating the regulations
The algorithm that the information data and Bayesian network model of the preceding all vehicles in section provide is known to whether violation vehicle is judged by accident
Not, and according to traffic administration institute's lane database face data train come Probability Point, differentiate violation vehicle whether break rules and regulations really.
The present invention achieves the above technical objects by the following technical means: the following steps are included:
Step 1: from collecting violation vehicle in traffic administration system database before and after the moment violating the regulations for a period of time
Whether violation vehicle avoids special car information A in interior vehicle and traffic information, including front and back a period of time segmentk, traffic
Signal lamp whether fault message Bk, whether avoid disabled vehicle or roadblock information Ck, traffic lights and live traffic police commander whether one
Write breath Dk, license plate whether applied information EkAnd vehicle whether violation information Gk, GkInclude the certain violation information G of vehicle1With
Vehicle is erroneous judgement information G2；
Step 2: primary data training set is established according to all information in step 1, building naive Bayesian network is disobeyed
Chapter vehicle judges identification model by accident, including vehicle node G whether violating the regulations, whether avoids special car node A, traffic lights
Malfunctioning node B, whether avoid disabled vehicle or roadblock node C, traffic lights and live traffic police commander whether consistent node D, vehicle
Whether board is applied node E；
Step 3: the conditional probability distribution P (A of egress A and node G is determinedk|Gk), the conditional probability of node B and node G
It is distributed P (Bk|Gk), the conditional probability distribution P (C of node C and node Gk|Gk), the conditional probability distribution P (D of node D and node Gk|
Gk), the conditional probability distribution P (E of node E and node Gk|Gk), the prior probability distribution P of node Gf(Gk)；Node G includes G1With,
G2, prior probability PfIt (G) include Pf(G1) and Pf(G2), conditional probability distribution P (Ak|Gk) it include P (Ak|G1) and P (Ak|G2), item
Part probability distribution P (Bk|Gk) it include P (Bk|G1) and P (Bk|G2), conditional probability distribution P (Ck|Gk) it include P (Ck|G1) and P (Ck|
G2), conditional probability distribution P (Dk|Gk) it include P (Dk|G1) and P (Dk|G2), conditional probability distribution P (Ek|Gk) it include P (Ek|G1) and
P(Ek|G2)；
Step 4: acquiring the vehicle and road conditions image information before and after the moment violating the regulations, obtain vehicle in current slot and
Traffic information, the vehicle and traffic information that will acquire are as the naive Bayesian network violation vehicle erroneous judgement identification model
Input obtains the probability distribution P (A for whether avoiding special car node Ak), traffic lights whether the probability of malfunctioning node B point
Cloth P (Bk), whether avoid disabled vehicle or the probability distribution P (C of roadblock node Ck), traffic lights and live traffic police commander whether
Probability distribution P (the D of consistent node Dk), license plate whether applied the probability distribution P (E of node Ek)；Calculate whether vehicle breaks rules and regulations
The Posterior probability distribution P of node Gu(G1) and Pu(G2), Pu(G1) it is the posterior probability that vehicle is broken rules and regulations really, Pu(G2) it is vehicle violating the regulations
It is the posterior probability of erroneous judgement；
Step 5: compare Pu(G1) and Pu(G2) size, if Pu(G1)≥Pu(G2), then violation vehicle is judged to disobeying really
Chapter；If Pu(G1)<Pu(G2), then determine this violation vehicle for erroneous judgement.
The present invention by adopting the above technical scheme after beneficial effect be:
(1) present invention by naive Bayesian network model use into vehicle violation erroneous judgement identification, is sentenced in electronic police
After determining vehicle violation, again to its progress depth recognition whether violating the regulations, the current traffic information of violation vehicle is considered not only, together
When be additionally contemplates that traffic information before and after moment violating the regulations within the scope of a period of time, there is higher standard for erroneous judgement identification violating the regulations
Exactness.
(2) present invention largely reduces the erroneous judgement to break in traffic rules and regulations, alleviates the work of manual examination and verification link worker
It measures, improves work efficiency.
Detailed description of the invention
Fig. 1 is the Establishing process figure of naive Bayesian network violation vehicle erroneous judgement identification model.
Fig. 2 is the violation vehicle erroneous judgement identification model based on Bayesian network.
Fig. 3 is the flow chart of the break in traffic rules and regulations erroneous judgement recognition methods based on Fig. 2 institute representation model.
Specific embodiment
Implement as shown in Figure 1, the present invention is divided into two stages, the first stage is to establish simplicity based on naive Bayesian network
Bayesian network violation vehicle judges identification model by accident, and second stage is whether to judge progress by accident to break in traffic rules and regulations by the model of foundation
Erroneous judgement identification, specifically:
Referring to Fig. 1, the first stage establishes the specific steps of naive Bayesian network violation vehicle erroneous judgement identification model such as
Under:
Step 1: one section of the front and back at violation vehicle moment violating the regulations is collected from existing traffic administration system database
Vehicle and traffic information in time carry out collating sort to collected information.Be in the present invention collect front and back 10 seconds in
Vehicle and traffic information.Specifically include whether violation vehicle in front and back a period of time segment avoids special car information Ak, traffic
Signal lamp whether fault message Bk, whether avoid disabled vehicle or roadblock information Ck, traffic lights and live traffic police commander whether one
Write breath Dk, license plate whether applied information EkAnd vehicle whether violation information Gk。
To information above collating sort, erroneous judgement information below is further set out:
GkInclude { G1,G2},G1Indicate the certain violation information of vehicle, G2Indicate that vehicle is erroneous judgement information.
AkInclude { A1,A2,A3, A1It indicates that special car information is not present；A2There are special cars for expression, and with vehicle violating the regulations
Distance is greater than the information of 5m；A3Indicate that special car and violation vehicle distance are less than the information of 5m.
BkInclude { B1,B2, B1Indicate traffic lights normal information；B2Traffic signal light fault information.
CkInclude { C1,C2,C3},C1It indicates that disabled vehicle or roadblock information is not present；C2There are disabled vehicle or roadblocks for expression, and
It is greater than the information of 5m with violation vehicle distance；C3Indicate the information for being less than 5m with violation vehicle distance.
DkInclude { D1,D2,D3},D1Traffic police's command information is not present in the scene of expression；D2Indicate signal lamp and traffic police commander one
Write breath；D3Indicate that signal lamp and traffic police command inconsistent information.
EkInclude { E1,E2},E1Indicate that violation vehicle color is write with shape and actual vehicle one corresponding to its license plate number
Breath, E2Indicate inconsistent information.
Wherein, told violation vehicle 10 seconds vehicles and traffic information A before and after the moment violating the regulationsk、Bk、Ck、Dk、EkData are all
It is to be obtained from picture captured by electronic police using image processing techniques.
Step 2: the primary data training set in this period is established according to the information data that step 1 obtains, herein
Training dataset is known as primary data training set, as shown in table 1.Specifically include in each time slice vehicle whether violation information
Gk={ G1, G2}={ 1,2 }, if evacuation special car information Ak={ A1, A2, A3}={ 1,2,3 }, traffic lights whether therefore
Hinder information Bk={ B1, B2}={ 1,2 }, if evacuation disabled vehicle or roadblock information Ck={ C1, C2, C3}={ 1,2,3 }, traffic letter
Signal lamp and live traffic police commander whether consistent information Dk={ D1, D2, D3}={ 1,2 }, whether license plate is applied information Ek={ E1,
E2}={ 1,2 }.
Primary data training set when table 1 in interruption
| Gk | Ak | Bk | Ck | Dk | Ek |
| 1 | 1 | 1 | 1 | 1 | 1 |
| 1 | 1 | 1 | 1 | 1 | 2 |
| 1 | 1 | 1 | 1 | 2 | 1 |
| … | … | … | … | … | … |
。
Step 3: the naive Bayesian network violation vehicle in building current slot judges identification model by accident, such as Fig. 2 institute
Show, model specifically include vehicle node G whether violating the regulations, whether avoid special car node A, traffic lights whether malfunctioning node
B, whether avoid disabled vehicle or roadblock node C, traffic lights and live traffic police commander whether consistent node D, license plate whether by
Apply node E.
Using parametric learning method, parameter learning is carried out based on the primary data training set established in step 2, obtains net
The conditional probability distribution of network node, specifically include whether avoid special car node A and vehicle node G whether violating the regulations condition it is general
Rate is distributed P (Ak/G k ), traffic lights whether the conditional probability distribution P (B of malfunctioning node B and vehicle node G whether violating the regulationsk/
Gk), whether avoid the conditional probability distribution P (C of disabled vehicle or roadblock node C and vehicle node G whether violating the regulationsk/Gk), traffic letter
Signal lamp and live traffic police commander whether the conditional probability distribution P (D of consistent node D and vehicle node G whether violating the regulationsk/Gk), license plate
Whether the conditional probability distribution P (E of node E and vehicle whether violating the regulations node G is appliedk/Gk), the elder generation of vehicle node G whether violating the regulations
Test probability distribution Pf(Gk), vehicle node G whether violating the regulations includes two kinds of result { G1, G2, then prior probability Pf(G) 2 are specifically included
It is a, respectively Pf(G1) and Pf(G2).Similarly, conditional probability distribution P (Ak/G k ) specifically include 2, respectively P (Ak/G1) and P
(Ak/G2)；Conditional probability distribution P (Bk/Gk) it include P (Bk/G1) and P (Bk/G2)；Conditional probability distribution P (Ck/Gk) it include P (Ck/
G1) and P (Ck/G2)；Conditional probability distribution P (Dk/Gk) it include P (Dk/G1) and P (Dk/G2)；Conditional probability distribution P (Ek/Gk) include
P(Ek/G1) and P (Ek/G2)。
Second stage is identified using the identification model that the first stage establishes to whether break in traffic rules and regulations is judged by accident, specific to walk
It is rapid as follows:
Step 1: acquiring the vehicle and road conditions image information before and after the moment violating the regulations, and when sampling is 20 seconds a length of, and utilizes image
Processing technique obtains information of vehicles and traffic information parameter in current slot, specifically includes and whether avoids special car information
Ak, traffic lights whether fault message Bk, if evacuation disabled vehicle or roadblock information Ck, traffic lights refer to live traffic police
Wave whether consistent information Dk, whether license plate applied information Ek。
Step 2: input of the information of vehicles and traffic information that will acquire as identification model, it is special whether acquisition avoids
Probability distribution P (the A of vehicle node Ak), traffic lights whether the probability distribution P (B of malfunctioning node Bk), whether avoid disabled vehicle
Or the probability distribution P (C of roadblock node Ck), traffic lights and live traffic police commander whether the probability distribution P of consistent node D
(Dk), whether license plate is applied the probability distribution P (E of node Ek).In conjunction with the prior probability distribution P of vehicle node G whether violating the regulationsf
(Gk) Posterior probability distribution of vehicle node G whether violating the regulations is calculated:
Wherein, subscript u indicates that affiliated probability distribution is Posterior probability distribution, and subscript f indicates that affiliated probability distribution is priori
Probability distribution, Pu(G1) indicate the posterior probability that vehicle is broken rules and regulations really, Pu(G2) indicate that violation vehicle is the posterior probability of erroneous judgement.
To the result of vehicle violation erroneous judgement identification in the period are as follows:
Compare Pu(G1) and Pu(G2) size, if Pu(G1)≥Pu(G2), i.e., the posterior probability that vehicle is broken rules and regulations really be greater than or
Person is equal to the posterior probability that violation vehicle is erroneous judgement, then this violation vehicle is determined as really violating the regulations；If Pu(G1)<Pu(G2), i.e. vehicle
Posterior probability violating the regulations is less than the posterior probability that violation vehicle is erroneous judgement, then determines this violation vehicle for erroneous judgement.
Step 3: result identified above is uploaded, and is uploaded typing violation systems for certain violation vehicle and is handled, right
In erroneous judgement vehicle not typing violation systems.
The embodiment is a preferred embodiment of the present invention, but present invention is not limited to the embodiments described above, not
In the case where substantive content of the invention, any conspicuous improvement that those skilled in the art can make, replacement
Or modification all belongs to the scope of protection of the present invention.
Claims (6)
1. a kind of break in traffic rules and regulations based on naive Bayesian network judges recognition methods by accident, it is characterized in that the following steps are included:
Step 1: from collecting violation vehicle in traffic administration system database before and after the moment violating the regulations in a period of time
Whether violation vehicle avoids special car information A in vehicle and traffic information, including front and back a period of time segmentk, traffic signals
Lamp whether fault message Bk, whether avoid disabled vehicle or roadblock information Ck, whether traffic lights and live traffic police commander one write
Cease Dk, license plate whether applied information EkAnd vehicle whether violation information Gk, GkInclude the certain violation information G of vehicle1And vehicle
It is erroneous judgement information G2；
Step 2: primary data training set, building naive Bayesian network vehicle violating the regulations are established according to all information in step 1
Erroneous judgement identification model, including vehicle node G whether violating the regulations, whether avoid special car node A, traffic lights whether failure
Node B, whether avoid disabled vehicle or roadblock node C, whether consistent node D, license plate are by traffic lights and live traffic police commander
It is no to be applied node E；
Step 3: the conditional probability distribution P (A of egress A and node G is determinedk|Gk), the conditional probability distribution of node B and node G
P(Bk|Gk), the conditional probability distribution P (C of node C and node Gk|Gk), the conditional probability distribution P (D of node D and node Gk|Gk)、
Conditional probability distribution P (the E of node E and node Gk|Gk), the prior probability distribution P of node Gf(Gk)；Node G includes G1With G2,
Prior probability PfIt (G) include Pf(G1) and Pf(G2), conditional probability distribution P (Ak|Gk) it include P (Ak|G1) and P (Ak|G2), condition is general
Rate is distributed P (Bk|Gk) it include P (Bk|G1) and P (Bk|G2), conditional probability distribution P (Ck|Gk) it include P (Ck|G1) and P (Ck|G2),
Conditional probability distribution P (Dk|Gk) it include P (Dk|G1) and P (Dk|G2), conditional probability distribution P (Ek|Gk) it include P (Ek|G1) and P (Ek
|G2)；
Step 4: acquiring the vehicle and road conditions image information before and after breaking rules and regulations the moment, obtains vehicle and road conditions in current slot
Information, the vehicle and traffic information that will acquire are defeated as the naive Bayesian network violation vehicle erroneous judgement identification model
Enter, the probability distribution P (A for whether avoiding special car node A obtainedk), traffic lights whether the probability distribution of malfunctioning node B
P(Bk), whether avoid disabled vehicle or the probability distribution P (C of roadblock node Ck), traffic lights and live traffic police commander whether one
Cause the probability distribution P (D of node Dk), license plate whether applied the probability distribution P (E of node Ek)；Calculate vehicle section whether violating the regulations
The Posterior probability distribution P of point Gu(G1) and Pu(G2), Pu(G1) it is the posterior probability that vehicle is broken rules and regulations really, Pu(G2) it is violation vehicle
It is the posterior probability of erroneous judgement；
Step 5: compare Pu(G1) and Pu(G2) size, if Pu(G1)≥Pu(G2), then violation vehicle is determined as really violating the regulations；If
Pu(G1)<Pu(G2), then determine this violation vehicle for erroneous judgement.
2. a kind of break in traffic rules and regulations based on naive Bayesian network according to claim 1 judges recognition methods, feature by accident
It is: in step 4,
Subscript u indicates that affiliated probability distribution is Posterior probability distribution, and subscript f indicates that affiliated probability distribution is prior probability distribution.
3. a kind of break in traffic rules and regulations based on naive Bayesian network according to claim 1 judges recognition methods, feature by accident
It is: in step 1, setting: AkInclude { A1,A2,A3, A1It indicates that special car information, A is not present2Expression there are special car and
It is greater than the information of 5m, A with violation vehicle distance3Indicate that special car and violation vehicle distance are less than the information of 5m；BkInclude { B1,
B2, B1Indicate traffic lights normal information, B2Traffic signal light fault information；CkInclude { C1,C2,C3},C1Expression is not present
Disabled vehicle or roadblock information, C2Indicate the information for being greater than 5m there are disabled vehicle or roadblock and with violation vehicle distance；C3It indicates and disobeys
Chapter vehicle distances are less than the information of 5m；DkInclude { D1,D2,D3},D1Traffic police's command information, D is not present in the scene of expression2Indicate signal
Lamp and traffic police command consistent information, D3Indicate that signal lamp and traffic police command inconsistent information；EkInclude { E1,E2},E1Indicate violating the regulations
Actual vehicle consistent information corresponding to vehicle color and shape and its license plate number, E2Indicate inconsistent information.
4. a kind of break in traffic rules and regulations based on naive Bayesian network according to claim 1 judges recognition methods, feature by accident
It is: in step 4, acquires 20 seconds a length of when the sampling of the vehicle before and after the moment violating the regulations and road conditions image information, utilize image procossing
Technology obtains the vehicle and traffic information in current slot.
5. a kind of break in traffic rules and regulations based on naive Bayesian network according to claim 1 judges recognition methods, feature by accident
It is: in step 5, certain violation vehicle upload typing violation systems is handled, system violating the regulations for erroneous judgement vehicle not typing
System.
6. a kind of break in traffic rules and regulations based on naive Bayesian network according to claim 1 judges recognition methods, feature by accident
It is: in step 1, from the vehicle collected in traffic administration system database in the front and back 10 seconds that violation vehicle breaks rules and regulations the moment
And traffic information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910392002.2A CN110288823B (en) | 2019-05-13 | 2019-05-13 | Traffic violation misjudgment identification method based on naive Bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910392002.2A CN110288823B (en) | 2019-05-13 | 2019-05-13 | Traffic violation misjudgment identification method based on naive Bayesian network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110288823A true CN110288823A (en) | 2019-09-27 |
| CN110288823B CN110288823B (en) | 2021-08-03 |
Family
ID=68001535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910392002.2A Active CN110288823B (en) | 2019-05-13 | 2019-05-13 | Traffic violation misjudgment identification method based on naive Bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288823B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992703A (en) * | 2019-12-03 | 2020-04-10 | 浙江大华技术股份有限公司 | Traffic violation determination method and device |
| CN112185113A (en) * | 2020-09-28 | 2021-01-05 | 江西玉祥智能装备制造有限公司 | Urban intelligent traffic control system |
| CN113538909A (en) * | 2021-07-13 | 2021-10-22 | 公安部道路交通安全研究中心 | Traffic incident prediction method and device for automatic driving vehicle |
| CN114446045A (en) * | 2021-09-14 | 2022-05-06 | 武汉长江通信智联技术有限公司 | Method for studying and judging illegal transportation behaviors of vehicles on highway in epidemic situation period |
| CN116978231A (en) * | 2023-09-05 | 2023-10-31 | 云南省交通投资建设集团有限公司 | Road section emergency traffic situation influence evaluation analysis model and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000031707A1 (en) * | 1998-11-23 | 2000-06-02 | Nestor, Inc. | Non-violation event filtering for a traffic light violation detection system |
| JP2013214143A (en) * | 2012-03-30 | 2013-10-17 | Fujitsu Ltd | Vehicle abnormality management device, vehicle abnormality management system, vehicle abnormality management method, and program |
| CN103942533A (en) * | 2014-03-24 | 2014-07-23 | 河海大学常州校区 | Urban traffic illegal behavior detection method based on video monitoring system |
| CN104182618A (en) * | 2014-08-06 | 2014-12-03 | 西安电子科技大学 | Rear-end early warning method based on Bayesian network |
-
2019
- 2019-05-13 CN CN201910392002.2A patent/CN110288823B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000031707A1 (en) * | 1998-11-23 | 2000-06-02 | Nestor, Inc. | Non-violation event filtering for a traffic light violation detection system |
| JP2013214143A (en) * | 2012-03-30 | 2013-10-17 | Fujitsu Ltd | Vehicle abnormality management device, vehicle abnormality management system, vehicle abnormality management method, and program |
| CN103942533A (en) * | 2014-03-24 | 2014-07-23 | 河海大学常州校区 | Urban traffic illegal behavior detection method based on video monitoring system |
| CN104182618A (en) * | 2014-08-06 | 2014-12-03 | 西安电子科技大学 | Rear-end early warning method based on Bayesian network |
| CN104182618B (en) * | 2014-08-06 | 2017-06-30 | 西安电子科技大学 | A kind of method for early warning that knocks into the back based on Bayesian network |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992703A (en) * | 2019-12-03 | 2020-04-10 | 浙江大华技术股份有限公司 | Traffic violation determination method and device |
| CN112185113A (en) * | 2020-09-28 | 2021-01-05 | 江西玉祥智能装备制造有限公司 | Urban intelligent traffic control system |
| CN113538909A (en) * | 2021-07-13 | 2021-10-22 | 公安部道路交通安全研究中心 | Traffic incident prediction method and device for automatic driving vehicle |
| CN114446045A (en) * | 2021-09-14 | 2022-05-06 | 武汉长江通信智联技术有限公司 | Method for studying and judging illegal transportation behaviors of vehicles on highway in epidemic situation period |
| CN116978231A (en) * | 2023-09-05 | 2023-10-31 | 云南省交通投资建设集团有限公司 | Road section emergency traffic situation influence evaluation analysis model and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110288823B (en) | 2021-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288823A (en) | A kind of break in traffic rules and regulations erroneous judgement recognition methods based on naive Bayesian network | |
| US11380105B2 (en) | Identification and classification of traffic conflicts | |
| WO2019153193A1 (en) | Taxi operation monitoring method, device, storage medium, and system | |
| CN107204114A (en) | A kind of recognition methods of vehicle abnormality behavior and device | |
| KR102453627B1 (en) | Deep Learning based Traffic Flow Analysis Method and System | |
| CN111564015B (en) | Method and device for monitoring perimeter intrusion of rail transit | |
| CN105788269A (en) | Unmanned aerial vehicle-based abnormal traffic identification method | |
| CN110895662A (en) | Vehicle overload alarm method and device, electronic equipment and storage medium | |
| CN111680613B (en) | Method for detecting falling behavior of escalator passengers in real time | |
| CN105608906A (en) | System for monitoring illegal emergency lane occupancy of expressway motor vehicles and implementation method | |
| CN106548629A (en) | Traffic violation detection method and system based on data fusion | |
| CN103700220A (en) | Fatigue driving monitoring device | |
| CN111754786A (en) | System for identifying traffic vehicle passing events on highway | |
| CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
| CN116168356B (en) | Vehicle damage judging method based on computer vision | |
| CN111524350A (en) | Method, system, terminal device and medium for detecting abnormal driving condition of vehicle and road cooperation | |
| KR102311805B1 (en) | Method for video monitoring for vehicle and human auto detection based on deep learning and Data transmission method using the same | |
| CN105608422A (en) | Intelligent monitoring detection method for overloading of passenger car | |
| Ki et al. | Method for automatic detection of traffic incidents using neural networks and traffic data | |
| Wang et al. | Vision-based highway traffic accident detection | |
| CN117876966A (en) | Intelligent traffic security monitoring system and method based on AI analysis | |
| CN112633163B (en) | Detection method for realizing illegal operation vehicle detection based on machine learning algorithm | |
| DE112021005269T5 (en) | Risk management device, risk management method, and risk management system | |
| CN114049614A (en) | Subway train emergency braking anti-collision control method | |
| CN110060452A (en) | The alarming method for power and device in vehicles while passing place |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220811 Address after: 230000 Room 203, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee after: Hefei Jiuzhou Longteng scientific and technological achievement transformation Co.,Ltd. Address before: Zhenjiang City, Jiangsu Province, 212013 Jingkou District Road No. 301 Patentee before: JIANGSU University |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221019 Address after: No. 664, Nanqiao North Road, Langya District, Chuzhou, Anhui Province, 239000 Patentee after: Chuzhou Shuntong Transportation Facilities Co.,Ltd. Address before: 230000 Room 203, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee before: Hefei Jiuzhou Longteng scientific and technological achievement transformation Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: No. 664, Nanqiao North Road, Langya District, Chuzhou, Anhui Province, 239000 Patentee after: Anhui Boxing Ruixun Intelligent Technology Co.,Ltd. Address before: No. 664, Nanqiao North Road, Langya District, Chuzhou, Anhui Province, 239000 Patentee before: Chuzhou Shuntong Transportation Facilities Co.,Ltd. |