CN110288823B - Traffic violation misjudgment identification method based on naive Bayesian network - Google Patents
Traffic violation misjudgment identification method based on naive Bayesian network Download PDFInfo
- Publication number
- CN110288823B CN110288823B CN201910392002.2A CN201910392002A CN110288823B CN 110288823 B CN110288823 B CN 110288823B CN 201910392002 A CN201910392002 A CN 201910392002A CN 110288823 B CN110288823 B CN 110288823B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- violation
- information
- node
- traffic
- 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
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
-
- 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 invention discloses a traffic violation false judgment and identification method based on a naive Bayesian network in the field of traffic violation, which comprises the steps of collecting vehicle and road condition information of a violation vehicle in a period of time before and after a violation moment from a traffic vehicle management system database, establishing an initial data training set, constructing a naive Bayesian network violation vehicle false judgment and identification model, and determining conditional probability distribution; then obtaining the information of the vehicles and road conditions in the current time period, taking the obtained information of the vehicles and road conditions as the input of a model, obtaining posterior probability, and finally judging whether the vehicles indeed violate the regulations; the invention applies the naive Bayesian network model to the vehicle violation false judgment and identification, and carries out deep identification on whether the vehicle is violated once again after an electronic police judges the vehicle violation, thereby not only considering the current road condition information of the vehicle violating the regulations, but also considering the road condition information in a time range before and after the violation moment, and having higher accuracy for the violation false judgment and identification.
Description
Technical Field
The invention relates to the technical field of traffic violation, in particular to a traffic violation misjudgment identification method.
Background
In order to maintain the management order of urban vehicles, electronic monitoring equipment and the like are installed to play an indispensable role in managing urban road traffic, and the advocation of intelligent traffic also increases the equipment of electronic policemen at urban traffic intersections. The electronic police uses automatic detection and measurement technology to capture traffic violation or traffic accident, uses network to transmit the collected information back to public security department for analysis and processing, and uses this as evidence to punish the troublemaker so as to reduce accident and assist traffic police. However, the electronic police is a machine after all, so that 'false damage' is inevitable, misjudgment of vehicle violation is caused, the road condition is complex and variable, for example, in order to avoid special vehicles such as 119 emergency vehicles for executing emergency tasks, signal lamp failure violation, violation due to avoidance of failure or accident vehicles, inconsistent traffic signal lamps and field traffic police commands, fake license plates of vehicles and the like, violation conditions can be applied for canceling violation records, for example, more complex road conditions, in a red light intersection, in order to avoid special vehicles for executing emergency tasks, a plurality of continuous vehicles in front are caused to run red lights or violate regulations, vehicles closest to the special vehicles are easy to be identified in a manual auditing link as being capable of being applied for canceling the violation records, vehicles far away from the special vehicles are difficult to be identified, misjudgment of violation is caused, in the manual auditing link, due to huge workload, quality problems may occur due to interference of human factors or objective factors, and illegal behaviors are misjudged and misjudged accordingly.
Aiming at the problem of misjudgment of traffic violation, the document with the Chinese patent application number of CN201110123733.0 discloses a method for detecting the violation vehicle by applying a violation vehicle detection device based on video identification, which can simultaneously detect the traffic violation behaviors of vehicle malicious jamming, solid line lane change and continuous change of more than two lanes, and avoid misjudgment of normal lane change behaviors, but the method can not solve the misjudgment of the violation behaviors under various special road conditions.
Bayesian theory is an important tool for processing uncertainty information. As a probability-based uncertainty reasoning method, the Bayesian network has gained important application in an intelligent system for processing uncertain information, and has been successfully used in the fields of medical diagnosis, statistical decision, expert system, and the like. The successful application fully reflects that the Bayesian network technology is a powerful uncertainty reasoning method. The naive Bayes method is a classification method based on Bayes theorem and independent hypothesis of characteristic conditions. The naive bayesian network model is one of the most extensive classification models at present, and is a tree-like bayesian network including a root node and a plurality of leaf nodes. At present, the Bayesian network is not applied to the field of traffic violation.
Disclosure of Invention
The invention aims to solve the problem of misjudgment of the traffic violation under various special road conditions in the prior art, and provides a traffic violation misjudgment identification method based on a naive Bayes network.
The invention realizes the technical purpose by the following technical means: the method comprises the following steps:
the method comprises the following steps: collecting the information of the vehicles and road conditions of the violation vehicles in a period of time before and after the violation time from the database of the traffic vehicle management system, includingInformation A of whether the violation vehicle avoids the special vehicle within a period of timekInformation on whether traffic signal lamp is in fault BkInformation C of whether to avoid the fault vehicle or roadblockkInformation D whether the traffic signal lamp is consistent with the on-site traffic police commandkInformation E whether license plate is sleevedkAnd whether the vehicle violates the regulations information Gk，GkContaining information G about actual violation of vehicle1And vehicle is misjudgment information G2；
Step two: establishing an initial data training set according to all information in the first step, and constructing a naive Bayesian network violation vehicle misjudgment recognition model, wherein the model comprises whether a vehicle is a violation node G, whether a special vehicle node A is avoided, whether a traffic signal lamp is a fault node B, whether a fault vehicle or a roadblock node C is avoided, whether the traffic signal lamp is consistent with a field traffic police command node D, and whether a license plate is a node E for use;
step three: determining the conditional probability distribution P (A) of node A and node Gk|Gk) Conditional probability distribution P (B) of node B and node Gk|Gk) Conditional probability distribution P (C) of node C and node Gk|Gk) Conditional probability distribution P (D) of node D and node Gk|Gk) Conditional probability distribution P (E) for node E and node Gk|Gk) Prior probability distribution P of node Gf(Gk) (ii) a Node G includes G1And, G2Prior probability Pf(G) Including Pf(G1) And Pf(G2) Conditional probability distribution P (A)k|Gk) Comprising P (A)k|G1) And P (A)k|G2) Conditional probability distribution P (B)k|Gk) Comprising P (B)k|G1) And P (B)k|G2) Conditional probability distribution P (C)k|Gk) Comprising P (C)k|G1) And P (C)k|G2) Conditional probability distribution P (D)k|Gk) Comprising P (D)k|G1) And P (D)k|G2) Conditional probability distribution P (E)k|Gk) Comprising P (E)k|G1) And P (E)k|G2)；
Step four: acquiring image information of vehicles and road conditions before and after the violation moment, acquiring the information of the vehicles and the road conditions in the current time period, taking the acquired information of the vehicles and the road conditions as the input of the naive Bayesian network violation vehicle misjudgment identification model, and acquiring the probability distribution P (A) of whether to avoid a special vehicle node Ak) Probability distribution P of node B whether traffic signal lamp is faulty or not (B)k) Probability distribution P (C) of whether to avoid the fault vehicle or the road block node Ck) Probability distribution P (D) of node D whether traffic signal lamp is consistent with field traffic police commandk) Probability distribution P (E) of node E for determining whether license plate is sleevedk) (ii) a Calculating posterior probability distribution P of node G whether the vehicle violates regulationsu(G1) And Pu(G2)，Pu(G1) Is the posterior probability, P, of a true violation of the vehicleu(G2) The posterior probability that the violation vehicle is misjudged;
step five: comparison Pu(G1) And Pu(G2) If P is the size ofu(G1)≥Pu(G2) If yes, the vehicle is judged to be indeed violation; if Pu(G1)<Pu(G2) And judging the violation vehicle as misjudgment.
The invention adopts the technical scheme and has the beneficial effects that:
(1) the invention applies the naive Bayesian network model to the vehicle violation false judgment and identification, and carries out deep identification on whether the vehicle is violated once again after an electronic police judges the vehicle violation, thereby not only considering the current road condition information of the vehicle violating the regulations, but also considering the road condition information in a time range before and after the violation moment, and having higher accuracy for the violation false judgment and identification.
(2) The invention greatly reduces the misjudgment of traffic violation, lightens the workload of workers in the manual auditing link and improves the working efficiency.
Drawings
FIG. 1 is a flow chart of the establishment of a naive Bayesian network violation vehicle misjudgment identification model.
FIG. 2 is a Bayesian network based violation vehicle false positive identification model.
FIG. 3 is a flow chart of a traffic violation false positive identification method based on the model shown in FIG. 2.
Detailed Description
As shown in fig. 1, the invention is implemented in two stages, the first stage is to establish a naive bayes network violation vehicle misjudgment recognition model based on a naive bayes network, and the second stage is to misjudge and recognize whether the traffic violation misjudgment is carried out by the established model, specifically:
referring to fig. 1, in the first stage, the specific steps of establishing a naive bayesian network violation vehicle misjudgment identification model are as follows:
the method comprises the following steps: and collecting the vehicle and road condition information in a period of time before and after the violation time of the violation vehicle from the existing traffic vehicle management system database, and sorting and classifying the collected information. The invention collects the information of vehicles and road conditions within 10 seconds before and after the collection. Specifically comprises information A of whether the violation vehicle avoids the special vehicle within a period of timekInformation on whether traffic signal lamp is in fault BkInformation C of whether to avoid the fault vehicle or roadblockkInformation D whether the traffic signal lamp is consistent with the on-site traffic police commandkInformation E whether license plate is sleevedkAnd whether the vehicle violates the regulations information Gk。
The above information is sorted and classified, and the following misjudgment information is further set:
Gkcontaining { G1,G2},G1Information indicating a true violation of the vehicle, G2Indicating that the vehicle is misjudgment information.
AkContaining { A1,A2,A3}，A1Indicating that no special vehicle information exists; a. the2Information indicating that a special vehicle exists and the distance between the special vehicle and the violation vehicle is more than 5 m; a. the3Information indicating that the special vehicle is less than 5m away from the violation vehicle.
BkContaining { B1,B2}，B1Indicating normal information of the traffic signal lamp; b is2Traffic control systemSignal lamp fault information.
CkContaining { C1,C2,C3},C1Indicating the absence of faulty vehicle or roadblock information; c2Information indicating that a fault vehicle or a roadblock exists and the distance between the fault vehicle or the roadblock and the violation vehicle is more than 5 m; c3Information representing a distance of less than 5m from the violation vehicle.
DkContaining { D1,D2,D3},D1Indicating that no traffic police command information exists on site; d2Indicating the consistent information of the signal lamp and the traffic police; d3And indicating the inconsistent information of the signal lamp and the traffic police.
EkContaining { E1,E2},E1Representing the information that the color and the appearance of the violation vehicle are consistent with the actual vehicle corresponding to the license plate number, E2Indicating inconsistent information.
Wherein, the vehicle and road condition information A of the violation vehicle is 10 seconds before and after the violation momentk、Bk、Ck、Dk、EkThe data is obtained from pictures taken by the electronic police using image processing techniques.
Step two: and establishing an initial data training set in the time period according to the information data obtained in the step one, wherein the training data set is called the initial data training set, and is shown in table 1. Specifically comprises the information G whether the vehicle violates the regulations in each time segmentk＝{G1，G21, 2, whether to avoid special vehicle information Ak＝{A1，A2，A31, 2, 3, and whether the traffic signal lamp has fault information Bk＝{B1，B21, 2, whether to avoid the fault vehicle or the road block information Ck＝{C1，C2，C31, 2, 3, and information D of whether the traffic signal light is consistent with the command of the on-site traffic policek＝{D1，D2，D31, 2, and information E indicating whether the license plate is usedk＝{E1，E2}＝{1，2}。
TABLE 1 initial training set of data within time break
| 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 three: and constructing a naive Bayesian network violation vehicle misjudgment recognition model in the current time period, wherein the model specifically comprises whether a vehicle violates a node G, whether a special vehicle node A is avoided, whether a traffic signal lamp is in a fault node B, whether a fault vehicle or a roadblock node C is avoided, whether the traffic signal lamp is consistent with a field traffic police command node D, and whether a license plate is sleeved with a node E, as shown in FIG. 2.
Performing parameter learning based on the initial data training set established in the second step by using a parameter learning method to obtain conditional probability distribution of the network nodes, specifically including whether to avoid the special vehicle node A and whether to violate the vehicle node G (A)k/G k ) Conditional probability distribution P of node B whether traffic signal lamp is faulty and node G whether vehicle is violating regulationsk/Gk) Conditional probability distribution P (C) of whether to avoid fault vehicle or roadblock node C and whether vehicle violates regulation node Gk/Gk) Conditional probability distribution P (D) of node D whether traffic signal lamp is consistent with on-site traffic police command or not and node G whether vehicle is illegal or notk/Gk) Conditional probability distribution P (E) of node E whether license plate is used in a sleeving manner or not and node G whether vehicle breaks rules and regulations or notk/Gk) Prior probability distribution P of node G whether vehicle violates regulationsf(Gk) Whether the vehicle violation node G contains two results { G }1，G2H, then the prior probability Pf(G) Specifically comprises 2, Pf(G1) And Pf(G2). Similarly, the conditional probability distribution P (A)k/G k ) Specifically comprises 2, P (A)k/G1) And P (A)k/G2) (ii) a Conditional probability distribution P (B)k/Gk) Comprising P (B)k/G1) And P (B)k/G2) (ii) a Conditional probability distribution P (C)k/Gk) Comprising P (C)k/G1) And P (C)k/G2) (ii) a Conditional probability distribution P (D)k/Gk) Comprising P (D)k/G1) And P (D)k/G2) (ii) a Conditional probability distribution P (E)k/Gk) Comprising P (E)k/G1) And P (E)k/G2)。
And in the second stage, identifying whether the traffic violation misjudges or not by adopting the identification model established in the first stage, and specifically comprising the following steps:
the method comprises the following steps: acquiring image information of vehicles and road conditions before and after the violation moment, wherein the sampling time is 20 seconds, and acquiring vehicle information and road condition information parameters in the current time period by using an image processing technology, specifically including information A of whether to avoid special vehicleskInformation on whether traffic signal lamp is in fault BkInformation C of whether to avoid the faulty vehicle or roadblockkInformation D whether traffic signal lamp is consistent with on-site traffic police commandkInformation E whether license plate is coveredk。
Step two: the obtained vehicle information and road condition information are used as input of an identification model to obtain probability distribution P (A) of whether to avoid a special vehicle node Ak) Probability distribution P of whether traffic signal light is faulty or not node B (B)k) Probability distribution P (C) of whether to avoid the fault vehicle or the road block node Ck) Probability distribution P (D) of node D whether traffic signal light is consistent with on-site traffic police commandk) Probability distribution P (E) of node E for whether license plate is sleeved or notk). Prior probability distribution P of node G combined with whether vehicle violatesf(Gk) Calculating to obtain the posterior probability distribution of the vehicle violation node G:
wherein, subscript u represents that the probability distribution is posterior probability distribution, subscript f represents that the probability distribution is prior probability distribution, Pu(G1) Posterior probability, P, representing a true violation of the vehicleu(G2) Indicating the posterior probability that the offending vehicle is a false positive.
The result of misjudgment and identification of vehicle violation in the time period is as follows:
comparison Pu(G1) And Pu(G2) If P is the size ofu(G1)≥Pu(G2) If the posterior probability of the vehicle really breaking rules is larger than or equal to the posterior probability that the vehicle breaking rules is judged by mistake, the vehicle breaking rules is judged to be really breaking rules; if Pu(G1)<Pu(G2) And if the posterior probability of the vehicle violation is smaller than the posterior probability that the vehicle violation is judged to be misjudged, judging that the vehicle violation is misjudged.
Step three: and uploading the identification result, uploading the vehicle which really violates the regulations to be recorded into a violation system for processing, and not recording the vehicle which misjudges into the violation system.
The present invention is not limited to the above-described embodiments, and any obvious improvements, substitutions or modifications can be made by those skilled in the art without departing from the spirit of the present invention.
Claims (6)
1. A traffic violation misjudgment identification method based on a naive Bayesian network is characterized by comprising the following steps:
the method comprises the following steps: collecting the information of the vehicles and road conditions of the violation vehicles in a period of time before and after the violation time from the database of the traffic vehicle management system, wherein the information includes information A of whether the violation vehicles avoid special vehicles in the period of time before and afterkInformation on whether traffic signal lamp is in fault BkInformation C of whether to avoid the fault vehicle or roadblockkTraffic signal lamp andinformation D whether on-site traffic police commands are consistentkInformation E whether license plate is sleevedkAnd whether the vehicle violates the regulations information Gk，GkContaining information G about actual violation of vehicle1And vehicle is misjudgment information G2；
Step two: establishing an initial data training set according to all information in the first step, and constructing a naive Bayesian network violation vehicle misjudgment recognition model, wherein the model comprises whether a vehicle is a violation node G, whether a special vehicle node A is avoided, whether a traffic signal lamp is a fault node B, whether a fault vehicle or a roadblock node C is avoided, whether the traffic signal lamp is consistent with a field traffic police command node D, and whether a license plate is a node E for use;
step three: determining the conditional probability distribution P (A) of node A and node Gk|G k ) Conditional probability distribution P (B) of node B and node Gk|Gk) Conditional probability distribution P (C) of node C and node Gk|Gk) Conditional probability distribution P (D) of node D and node Gk|Gk) Conditional probability distribution P (E) for node E and node Gk|Gk) Prior probability distribution P of node Gf(Gk) (ii) a Node GkComprising G1And G2Prior probability Pf(G) Including Pf(G1) And Pf(G2) Conditional probability distribution P (A)k|G k ) Comprising P (A)k|G1) And P (A)k|G2) Conditional probability distribution P (B)k|Gk) Comprising P (B)k|G1) And P (B)k|G2) Conditional probability distribution P (C)k|Gk) Comprising P (C)k|G1) And P (C)k|G2) Conditional probability distribution P (D)k|Gk) Comprising P (D)k|G1) And P (D)k|G2) Conditional probability distribution P (E)k|Gk) Comprising P (E)k|G1) And P (E)k|G2)；
Step four: acquiring image information of vehicles and road conditions before and after the violation moment, acquiring the information of the vehicles and the road conditions in the current time period, and acquiring the acquired vehicles and road conditionsThe road condition information is used as the input of the misjudgment and identification model of the naive Bayesian network violation vehicle to obtain the probability distribution P (A) of whether to avoid the special vehicle node Ak) Probability distribution P of node B whether traffic signal lamp is faulty or not (B)k) Probability distribution P (C) of whether to avoid the fault vehicle or the road block node Ck) Probability distribution P (D) of node D whether traffic signal lamp is consistent with field traffic police commandk) Probability distribution P (E) of node E for determining whether license plate is sleevedk) (ii) a Calculating posterior probability distribution P of node G whether the vehicle violates regulationsu(G1) And Pu(G2)，Pu(G1) Is the posterior probability, P, of a true violation of the vehicleu(G2) The posterior probability that the violation vehicle is misjudged;
step five: comparison Pu(G1) And Pu(G2) If P is the size ofu(G1)≥Pu(G2) If yes, the vehicle is judged to be indeed violation; if Pu(G1)<Pu(G2) And judging the violation vehicle as misjudgment.
2. The traffic violation false positive identification method based on the naive Bayes network as claimed in claim 1, wherein the traffic violation false positive identification method comprises the following steps: in the fourth step of the method, the first step of the method,
the subscript u indicates that the assigned probability distribution is a posterior probability distribution, and the subscript f indicates that the assigned probability distribution is a prior probability distribution.
3. The traffic violation false positive identification method based on the naive Bayes network as claimed in claim 1, wherein the traffic violation false positive identification method comprises the following steps: in the first step, setting: a. thekIncluded{A1,A2,A3}，A1Indicating absence of special vehicle information, A2Information indicating the presence of a particular vehicle and a distance greater than 5m from the offending vehicle, A3Information indicating that the distance between the special vehicle and the violation vehicle is less than 5 m; b iskContaining { B1,B2}，B1Indicating normal information of traffic lights, B2Traffic signal lamp fault information; ckContaining { C1,C2,C3},C1Indicating absence of faulty vehicle or road-block information, C2Information indicating that a fault vehicle or a roadblock exists and the distance between the fault vehicle or the roadblock and the violation vehicle is more than 5 m; c3Information representing a distance of less than 5m from the violation vehicle; dkContaining { D1,D2,D3},D1Indicating absence of traffic police command information on site, D2Indicating the traffic light and traffic police command consistent information, D3Indicating inconsistent information between the signal lamp and the traffic police; ekContaining { E1,E2},E1Representing the information that the color and the appearance of the violation vehicle are consistent with the actual vehicle corresponding to the license plate number, E2Indicating inconsistent information.
4. The traffic violation false positive identification method based on the naive Bayes network as claimed in claim 1, wherein the traffic violation false positive identification method comprises the following steps: and in the fourth step, the sampling time for acquiring the image information of the vehicle and the road condition before and after the violation moment is 20 seconds, and the image processing technology is utilized to acquire the information of the vehicle and the road condition in the current time slot.
5. The traffic violation false positive identification method based on the naive Bayes network as claimed in claim 1, wherein the traffic violation false positive identification method comprises the following steps: and fifthly, uploading the vehicle which really violates the regulations to the violation system for processing, and not inputting the violation system for the misjudged vehicle.
6. The traffic violation false positive identification method based on the naive Bayes network as claimed in claim 1, wherein the traffic violation false positive identification method comprises the following steps: in the first step, vehicle and road condition information within 10 seconds before and after the violation time of the violation vehicle is collected from the traffic vehicle management system database.
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 CN110288823A (en) | 2019-09-27 |
| CN110288823B true 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) |
Families Citing this family (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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110288823A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288823B (en) | Traffic violation misjudgment identification method based on naive Bayesian network | |
| CN110969130B (en) | Driver dangerous action identification method and system based on YOLOV3 | |
| US8885929B2 (en) | Abnormal behavior detection system and method using automatic classification of multiple features | |
| CN102385705B (en) | Abnormal behavior detection system and method by utilizing automatic multi-feature clustering method | |
| CN104332052B (en) | Recognition method for automatic capture for pedestrian red light punishment | |
| CN107204114A (en) | A kind of recognition methods of vehicle abnormality behavior and device | |
| CN106373426A (en) | Computer vision-based parking space and illegal lane occupying parking monitoring method | |
| CN105788269A (en) | Unmanned aerial vehicle-based abnormal traffic identification method | |
| KR20100119476A (en) | An outomatic sensing system for traffic accident and method thereof | |
| CN109344886B (en) | Occlusion number plate distinguishing method based on convolutional neural network | |
| CN107644206A (en) | A kind of road abnormal behaviour action detection device | |
| CN111274886B (en) | Deep learning-based pedestrian red light running illegal behavior analysis method and system | |
| CN107346435A (en) | A kind of suspicion fake-licensed car catching method based on vehicle characteristics storehouse | |
| CN113269042B (en) | Intelligent traffic management method and system based on driving vehicle violation identification | |
| CN112883936A (en) | Method and system for detecting vehicle violation | |
| CN109034211A (en) | A kind of parking space state detection method based on machine learning | |
| CN117876966A (en) | Intelligent traffic security monitoring system and method based on AI analysis | |
| CN116168356A (en) | Vehicle damage judging method based on computer vision | |
| CN113673304B (en) | Vehicle-mounted expected functional safety hazard analysis and evaluation method based on scene semantic driving | |
| CN111860383B (en) | Group abnormal behavior identification method, device, equipment and storage medium | |
| CN113851001A (en) | Automatic auditing method, system, device and storage medium for multilane merging violation | |
| CN116993517A (en) | Vehicle insurance claim fraud identification method, device, equipment and storage medium | |
| CN115359658B (en) | Traffic event detection method, device, equipment, storage medium and program product | |
| CN111553199A (en) | Motor vehicle traffic violation automatic detection technology based on computer vision | |
| CN112633163B (en) | Detection method for realizing illegal operation vehicle detection based on machine learning algorithm |
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 |
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. |
|
| TR01 | Transfer of patent right | ||
| 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. |
|
| CP01 | Change in the name or title of a patent holder |