CN103093624A - Signalized intersection non-motor vehicle illegal cross-street behavior automatic judging method - Google Patents
Signalized intersection non-motor vehicle illegal cross-street behavior automatic judging method Download PDFInfo
- Publication number
- CN103093624A CN103093624A CN201310007674XA CN201310007674A CN103093624A CN 103093624 A CN103093624 A CN 103093624A CN 201310007674X A CN201310007674X A CN 201310007674XA CN 201310007674 A CN201310007674 A CN 201310007674A CN 103093624 A CN103093624 A CN 103093624A
- Authority
- CN
- China
- Prior art keywords
- bicycle
- street
- violation
- regulations
- rules
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 230000000153 supplemental effect Effects 0.000 claims description 8
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 230000000750 progressive effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000002360 preparation method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
本发明公开了一种信号交叉口非机动车违规过街行为自动判别方法，按如下步骤进行：（1）在信号交叉口人行横道及其附近范围内架设两台摄像机，通过录取的视频，对相关参数进行整理；（2）根据离散选择分析方法，建立信号交叉口非机动车违规过街行为二元logit预测模型，并采用参数递进方法对二元logit预测模型进行标定，标定结果为：（3）将参数数据输入二元logit预测模型中，得到信号交叉口非机动车违规过街行为，当P>0.5时，非机动车违规过街；当P<0.5时，非机动车不违规过街。本发明减少人为的参与，提高判断速度，使判断准确公正；同时，也可通过模型中显著影响信号非机动车违规过街行为的因素，为交叉口改造提供理论依据，具有实际的工程运用价值。
The invention discloses a method for automatically judging illegal crossing behavior of non-motor vehicles at signalized intersections. (2) According to the discrete choice analysis method, a binary logit prediction model of illegal crossing behavior of non-motorized vehicles at signalized intersections was established, and the binary logit prediction model was calibrated using the parameter progression method. The calibration results are: (3) Enter the parameter data into the binary logit prediction model to obtain the illegal crossing behavior of non-motorized vehicles at signalized intersections. When P>0.5, non-motorized vehicles cross the street illegally; when P<0.5, non-motorized vehicles do not cross the street illegally. The invention reduces human participation, improves the judgment speed, and makes the judgment accurate and fair; at the same time, it can also provide a theoretical basis for the reconstruction of the intersection through the factors in the model that significantly affect the illegal crossing behavior of signal non-motor vehicles, and has practical engineering application value.
Description
Technical field
The present invention relates to a kind of signalized intersections bicycle and cross in violation of rules and regulations street behavior automatic distinguishing method, be specifically related to a kind of utilization binary logit model and carry out the signalized intersections bicycle and cross in violation of rules and regulations street behavior automatic distinguishing method, belong to traffic administration and traffic safety technology field.
Background technology
Bicycle mainly comprises bicycle and electric bicycle, is the important mode of transportation in incity, China big city, especially the preferred traffic instrument of domestic city resident short distance trip.The normal property sent out of bicycle accident and the seriousness of damage sequence make the bicycle accident become the characteristics of Chinese transportation accident, and become the difficult point of Chinese transportation and traffic hazard.2010,8745 of national bicycle accidents caused 1462 people dead, and 9483 people are injured, and direct property loss reaches 1,137 ten thousand yuans.Statistics shows, most of bicycle accidents are crossed in violation of rules and regulations the street and caused due to it, thus research how to confirm bicycle to cross the street behavior be to have far reaching.
At present, the research of crossing the street behavior for bicycle is less, and relevant research mainly concentrates on the pedestrian's street crossing behavior.Existing research is mainly the personal attribute for the pedestrian, thereby the information such as Social Characteristics and family's characteristic are carried out qualitative analysis and determined street behavior preference.The research that only has bicycle few in number to cross the street behavior also is based on information such as analyzing age, sex, bicycle kind and determines that it crosses the street behavior, does not relate to crossing characteristic and traffic environment that bicycle is crossed the street.Thereby existing method can not analysis-by-synthesis affect the factor that bicycle is crossed the street behavior, can not instruct engineering practice to cross the street behavior to reduce non-motor-driven violation.
Summary of the invention
Goal of the invention: the object of the invention is to for the deficiencies in the prior art, a kind of accuracy of judgement is provided, reduces manually participation, can instructs the signalized intersections bicycle of engineering practice to cross in violation of rules and regulations street behavior automatic distinguishing method.
Technical scheme: a kind of signalized intersections bicycle of the present invention is crossed street behavior automatic distinguishing method in violation of rules and regulations, it is characterized in that, carries out as follows:
(1) set up two video cameras in signalized intersections crossing and environs thereof, the First camera pedestal is located at the concealed location at crossing place, is used for taking the bicycle characteristic and crosses the street behavior; Second camera pedestal is located at the eminence of signalized intersections, overlooks and takes road traffic flow and crossing characteristic;
Video by admission, correlation parameter is arranged, and the parameter of arrangement comprises whether driver's sex, driver's age, driver helmet, whether bicycle is manned, whether bicycle type, intersection shape, crossing inlet road has the median strip, whether crossing inlet road form of fracture, crossing inlet road has in current vehicle, bicycle signal lamp form, 5min motor vehicle number in bicycle number and 5min;
To the arrangement of related data by manually completing, namely by the people by watching video to remove to judge above-mentioned parameter, then keep a record.
(2) according to the discrete choice analysis method, to set up the signalized intersections bicycle and cross in violation of rules and regulations street behavior binary logit forecast model, and adopt the parameter progressive method that binary logit forecast model is demarcated, calibration result is:
Wherein, x
1Represent sex (1 man, 0 female), x
2Represent the age (1 youth, 2 middle ages, 3 old age); x
3Represent bicycle car type (1 battery-operated motor cycle, 2 electric bicycles, 3 bicycles); x
4Represent whether the crossing inlet road has median strip (1 has, 2 without); x
5Represent crossing inlet road form of fracture (1 single carriageway road, 2 two width roads, 3 triple carriageway roads); x
6Represent whether the crossing inlet road has current vehicle (1 has, 2 without); x
7Represent bicycle signal lamp form (1 numeric type; 2 flicker types).
(3) supplemental characteristic that in the supplemental characteristic that arranges in step (1), in extraction step (2), forecast model needs, and with the binary logit forecast model in data input step (2), obtain the signalized intersections bicycle and cross in violation of rules and regulations the street behavior, as P 0.5 the time, bicycle is crossed the street in violation of rules and regulations; When P＜0.5, bicycle is not crossed the street in violation of rules and regulations.
In step (2), binary logit forecast model being demarcated adopts the Analysis module of SPSS19.0 system to carry out, the supplemental characteristic that might affect model that obtains in step (1) is analyzed, effective parameter is chosen include in model by " parameter go forward one by one method ", and invalid parameter is cast out.SPSS19.0 is the business mathematics analysis software that American I BM company releases, and it integrates data preparation, analytic function.SPSS19.0 is combined by a plurality of functional modules, and utilization of the present invention Analysis module wherein realizes the signalized intersections bicycle parameter calibration of mistake street behavior binary logit forecast model in violation of rules and regulations, the fitting result demonstration, and the models fitting goodness is remarkable.
After setting up the signalized intersections bicycle in step (2) and crossing in violation of rules and regulations street behavior binary logit forecast model, carry out the precision test of model by the measured data of check group.The signalized intersections bicycle of model prediction is crossed in street behavior and measured data the signalized intersections bicycle in violation of rules and regulations, and mistake street behavior deviation is less in violation of rules and regulations, proves applicability and the validity of model.Choose 1131, Nanjing bicycle and carry out the checking of model, the prediction accuracy that model is crossed the street in violation of rules and regulations to bicycle is 82.8%, the prediction accuracy of bicycle not being crossed in violation of rules and regulations the street is 78.7%, the aggregate prediction precision is 81.9%, the difference of predicted value and measured value is very little, thereby has proved the validity of forecast model and the ubiquity of application.
Beneficial effect: a kind of signalized intersections bicycle of the present invention is crossed street behavior automatic distinguishing method in violation of rules and regulations, gather the data of intersection by the method for setting up video camera in the intersection, after correlation parameter is arranged, input binary logit forecast model, signalized intersections place bicycle is crossed the street whether make in violation of rules and regulations quick judgement, reduce artificial participation, improve judgement speed, make accuracy of judgement just; Simultaneously, also can cross in violation of rules and regulations the factor of street behavior by appreciable impact signal bicycle in model, for the crossing transformation provides theoretical foundation, have actual engineering application and be worth.
Description of drawings
Fig. 1 is that signalized intersections bicycle of the present invention is crossed the process flow diagram of street behavior automatic distinguishing method in violation of rules and regulations;
Fig. 2 is the logical diagram that in the inventive method, collection signal crossing bicycle is crossed the street behavioral data;
Fig. 3 is the process flow diagram of the method for building up of binary logit forecast model in the inventive method.
Embodiment
The below is elaborated to technical solution of the present invention, but protection scope of the present invention is not limited to described embodiment.
Embodiment: a kind of signalized intersections bicycle of the present invention is crossed street behavior automatic distinguishing method in violation of rules and regulations, and its process flow diagram carries out as shown in Figure 1 as follows:
(1) set up two video cameras in signalized intersections crossing and environs thereof, the First camera pedestal is located at the concealed location at crossing place, is used for taking the bicycle characteristic and crosses the street behavior; Second camera pedestal is located at the eminence of signalized intersections, overlooks and takes road traffic flow and crossing characteristic.
Video by admission, correlation parameter is arranged, the parameter logical diagram that arranges comprises whether driver's sex, driver's age, driver helmet, whether bicycle is manned, whether bicycle type, intersection shape, crossing inlet road has the median strip, whether crossing inlet road form of fracture, crossing inlet road has in current vehicle, bicycle signal lamp form, 5min motor vehicle number in bicycle number and 5min as shown in Figure 2.
To the arrangement of related data by manually completing, namely by the people by watching video to remove to judge above-mentioned parameter, then keep a record.
(2) according to the discrete choice analysis method, set up the signalized intersections bicycle and cross in violation of rules and regulations street behavior binary logit forecast model, set up the process flow diagram of binary logit forecast model method as shown in Figure 3, and adopt the parameter progressive method that binary logit forecast model is demarcated, calibration result is:
Wherein, x
1Represent sex (1 man, 0 female), x
2Represent the age (1 youth, 2 middle ages, 3 old age); x
3Represent bicycle car type (1 battery-operated motor cycle, 2 electric bicycles, 3 bicycles); x
4Represent whether the crossing inlet road has median strip (1 has, 2 without); x
5Represent crossing inlet road form of fracture (1 single carriageway road, 2 two width roads, 3 triple carriageway roads); x
6Represent whether the crossing inlet road has current vehicle (1 has, 2 without); x
7Represent bicycle signal lamp form (1 numeric type; 2 flicker types).
Binary logit forecast model is demarcated adopts the Analysis module of SPSS19.0 system to carry out, the supplemental characteristic that might affect model that obtains in step (1) is analyzed, effective parameter is chosen include in model by " parameter go forward one by one method ", and invalid parameter is cast out.SPSS19.0 is the business mathematics analysis software that American I BM company releases, and it integrates data preparation, analytic function.SPSS19.0 is combined by a plurality of functional modules, and utilization of the present invention Analysis module wherein realizes the signalized intersections bicycle parameter calibration of mistake street behavior binary logit forecast model in violation of rules and regulations, the fitting result demonstration, and the models fitting goodness is remarkable.
After setting up the signalized intersections bicycle and crossing in violation of rules and regulations street behavior binary logit forecast model, carry out the precision test of model by the measured data of check group.The signalized intersections bicycle of model prediction is crossed in street behavior and measured data the signalized intersections bicycle in violation of rules and regulations, and mistake street behavior deviation is less in violation of rules and regulations, proves applicability and the validity of model.Choose 1131, Nanjing bicycle and carry out the checking of model, the prediction accuracy that model is crossed the street in violation of rules and regulations to bicycle is 82.8%, the prediction accuracy of bicycle not being crossed in violation of rules and regulations the street is 78.7%, the aggregate prediction precision is 81.9%, the difference of predicted value and measured value is very little, thereby has proved the validity of forecast model and the ubiquity of application.
(3) supplemental characteristic that in the supplemental characteristic that arranges in step (1), in extraction step (2), forecast model needs, and with the binary logit forecast model in data input step (2), obtain the signalized intersections bicycle and cross in violation of rules and regulations the street behavior, as P 0.5 the time, bicycle is crossed the street in violation of rules and regulations; When P＜0.5, bicycle is not crossed the street in violation of rules and regulations.
Use method of the present invention, obtain 10 groups of bicycle data by the collection of bicycle data video, and data are inputed to carry out bicycle in binary logit forecast model and cross the street behavior and predict, and will predict the outcome and cross the street behavior with reality and compare, result is as shown in table 1:
Table 1:
The signalized intersections bicycle is crossed the definite most important to improving the crossing traffic safety of street behavior, cross in violation of rules and regulations street behavior binary logit forecast model based on the signalized intersections bicycle, with input information models such as bicycle characteristic and crossing geometrical properties, can cross in violation of rules and regulations the street behavior to the signalized intersections bicycle and make quick judgement.In addition, also can cross in violation of rules and regulations the factor of street behavior by appreciable impact signal bicycle in model, carry out the crossing transformation, have actual engineering application and be worth.As shown in the Examples, 10 groups of bicycles are crossed predicting the outcome of street behavior and to cross the street behavior consistent for reality, the enforcement validity of the inventive method has been described.
As mentioned above, although represented and explained the present invention with reference to specific preferred embodiment, it shall not be construed as the restriction to the present invention self.Under the spirit and scope of the present invention prerequisite that does not break away from the claims definition, can make in the form and details various variations to it.
Claims (3)
1. a signalized intersections bicycle is crossed street behavior automatic distinguishing method in violation of rules and regulations, it is characterized in that, carries out as follows:
(1) set up two video cameras in signalized intersections crossing and environs thereof, the First camera pedestal is located at the concealed location at crossing place, is used for taking the bicycle characteristic and crosses the street behavior; Second camera pedestal is located at the eminence of signalized intersections, overlooks and takes road traffic flow and crossing characteristic;
Video by admission, correlation parameter is arranged, and the parameter of arrangement comprises whether driver's sex, driver's age, driver helmet, whether bicycle is manned, whether bicycle type, intersection shape, crossing inlet road has the median strip, whether crossing inlet road form of fracture, crossing inlet road has in current vehicle, bicycle signal lamp form, 5min motor vehicle number in bicycle number and 5min;
(2) according to the discrete choice analysis method, to set up the signalized intersections bicycle and cross in violation of rules and regulations street behavior binary logit forecast model, and adopt the parameter progressive method that binary logit forecast model is demarcated, calibration result is:
Wherein, x
1Be driver's sex, x
2Be driver's age, x
3Be bicycle type, x
4For whether the crossing inlet road has median strip, x
5Be crossing inlet road form of fracture, x
6For whether the crossing inlet road has current vehicle, x
7Be bicycle signal lamp form;
(3) supplemental characteristic that in the supplemental characteristic that arranges in step (1), in extraction step (2), forecast model needs, and with the binary logit forecast model in data input step (2), obtain the signalized intersections bicycle and cross in violation of rules and regulations the street behavior, as P 0.5 the time, bicycle is crossed the street in violation of rules and regulations; When P＜0.5, bicycle is not crossed the street in violation of rules and regulations.
2. a kind of signalized intersections bicycle according to claim 1 is crossed street behavior automatic distinguishing method in violation of rules and regulations, it is characterized in that, in step (2), binary logit forecast model is demarcated and is adopted the Analysis module of SPSS19.0 system to carry out.
3. a kind of signalized intersections bicycle according to claim 1 is crossed street behavior automatic distinguishing method in violation of rules and regulations, it is characterized in that, after setting up the signalized intersections bicycle in step (2) and crossing in violation of rules and regulations street behavior binary logit forecast model, carry out the precision test of model by the measured data of check group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310007674.XA CN103093624B (en) | 2013-01-09 | 2013-01-09 | Signalized intersection non-motor vehicle illegal cross-street behavior automatic judging method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310007674.XA CN103093624B (en) | 2013-01-09 | 2013-01-09 | Signalized intersection non-motor vehicle illegal cross-street behavior automatic judging method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103093624A true CN103093624A (en) | 2013-05-08 |
| CN103093624B CN103093624B (en) | 2015-04-15 |
Family
ID=48206145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310007674.XA Expired - Fee Related CN103093624B (en) | 2013-01-09 | 2013-01-09 | Signalized intersection non-motor vehicle illegal cross-street behavior automatic judging method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103093624B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200668A (en) * | 2014-07-28 | 2014-12-10 | 四川大学 | Image-analysis-based detection method for helmet-free motorcycle driving violation event |
| WO2019223655A1 (en) * | 2018-05-22 | 2019-11-28 | 杭州海康威视数字技术股份有限公司 | Detection of non-motor vehicle carrying passenger |
| CN111708098A (en) * | 2020-06-18 | 2020-09-25 | 山西省交通科技研发有限公司 | Traffic safety device and safety detection method |
| CN112164232A (en) * | 2020-10-16 | 2021-01-01 | 腾讯科技（深圳）有限公司 | Control method and device of non-maneuvering object, electronic equipment and storage medium |
| CN115273456A (en) * | 2022-06-14 | 2022-11-01 | 北京车网科技发展有限公司 | Method and system for judging illegal driving of two-wheeled electric vehicle and storage medium |
| WO2023044722A1 (en) * | 2021-09-24 | 2023-03-30 | Intel Corporation | Dynamic control of infrastructure for vulnerable users |
-
2013
- 2013-01-09 CN CN201310007674.XA patent/CN103093624B/en not_active Expired - Fee Related
Non-Patent Citations (4)
| Title |
|---|
| 孙智勇等: "信号交叉口人行横道处的行人可接受间隙研究", 《公路交通科技》 * |
| 张壮: "城市四支信号交叉口行人交通特性及违法分析", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
| 朱芳芳: "无信号控制交叉口行人过街间隙选择模型研究", 《交通信息与安全》 * |
| 熊辉等: "行人过街设施选择偏好的非集计模型", 《北京理工大学学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200668A (en) * | 2014-07-28 | 2014-12-10 | 四川大学 | Image-analysis-based detection method for helmet-free motorcycle driving violation event |
| WO2019223655A1 (en) * | 2018-05-22 | 2019-11-28 | 杭州海康威视数字技术股份有限公司 | Detection of non-motor vehicle carrying passenger |
| CN111708098A (en) * | 2020-06-18 | 2020-09-25 | 山西省交通科技研发有限公司 | Traffic safety device and safety detection method |
| CN112164232A (en) * | 2020-10-16 | 2021-01-01 | 腾讯科技（深圳）有限公司 | Control method and device of non-maneuvering object, electronic equipment and storage medium |
| CN112164232B (en) * | 2020-10-16 | 2023-12-26 | 腾讯科技（深圳）有限公司 | Control method and device for non-motorized object, electronic equipment and storage medium |
| WO2023044722A1 (en) * | 2021-09-24 | 2023-03-30 | Intel Corporation | Dynamic control of infrastructure for vulnerable users |
| CN115273456A (en) * | 2022-06-14 | 2022-11-01 | 北京车网科技发展有限公司 | Method and system for judging illegal driving of two-wheeled electric vehicle and storage medium |
| CN115273456B (en) * | 2022-06-14 | 2023-08-29 | 北京车网科技发展有限公司 | Method, system and storage medium for judging illegal running of two-wheeled electric vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103093624B (en) | 2015-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104294720B (en) | A kind of Expressway Design solution security evaluation methodology | |
| Miranda-Moreno et al. | Disaggregate exposure measures and injury frequency models of cyclist safety at signalized intersections | |
| CN103093624A (en) | Signalized intersection non-motor vehicle illegal cross-street behavior automatic judging method | |
| CN103531031B (en) | A control method based on video detection and recognition in soft closed areas of urban traffic arteries to realize a green light passage | |
| Chen et al. | Built environment effects on bike crash frequency and risk in Beijing | |
| CN113066287B (en) | A method and system for active risk prevention and control of highway traffic accident scene | |
| CN106781499A (en) | A kind of transportation network efficiency rating system | |
| CN101465059A (en) | Early-warning system for inspecting and judging urban road traffic safety situation | |
| CN105678034A (en) | Pedestrian crossing time model and signalized intersection pedestrian crosswalk width optimizing method | |
| CN105469167A (en) | Traffic conflict prediction method based on space-time proximity | |
| CN105513362B (en) | A kind of bus platform adjacent area bus running state evaluation verification method | |
| Hawas | Simulation-based regression models to estimate bus routes and network travel times | |
| CN107240264A (en) | A kind of non-effective driving trace recognition methods of vehicle and urban road facility planing method | |
| Zhai et al. | Comparative analysis of drive-cycles, speed limit violations, and emissions in two cities: Toronto and Beijing | |
| Yu et al. | Using 3D mobile mapping to evaluate intersection design through drivers’ visual perception | |
| CN114550445B (en) | Urban area traffic safety state assessment method and device | |
| Liu et al. | Utilizing bicycle compatibility index and bicycle level of service for cycleway networks | |
| CN104392076B (en) | City road network pedestrian traffic accident black spot recognition method | |
| CN105427600A (en) | Road jam real time identification method and apparatus based on FCD | |
| CN102518054B (en) | Road deceleration marked line setting method based on actual deceleration effect | |
| CN111882190A (en) | A BIM-based visual distance evaluation method for interchangeable interchanges | |
| Yanfeng et al. | Characteristic analysis of pedestrian violation crossing behavior based on logistics model | |
| CN209560723U (en) | Vehicle speed measurement system based on interval speed measurement | |
| CN109887291B (en) | A method for determining demand for traffic light setting | |
| CN117058887B (en) | Urban traffic data acquisition method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150415 |