CN103093624B - 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
- CN103093624B CN103093624B CN201310007674.XA CN201310007674A CN103093624B CN 103093624 B CN103093624 B CN 103093624B CN 201310007674 A CN201310007674 A CN 201310007674A CN 103093624 B CN103093624 B CN 103093624B
- 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.)
- Active
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a signalized intersection non-motor vehicle illegal cross-street behavior automatic judging method which comprises the following steps: (1) two cameras are set up in a pedestrian crossing and near range of the pedestrian crossing, relative parameters are arranged according to recorded videos; (2) a signalized intersection non-motor vehicle illegal cross-street behavior binary logit prediction model is built according to discrete choice analysis method, a parameter progressive method is adopted to demarcate the binary logit prediction model, and the demarcation result is shown in the description; and (3) the parameter data are inputted in the binary logit prediction model and therefore signalized intersection non-motor vehicle illegal cross-street behaviors are obtained, when P is larger than 0.5, a non-motor crosses the street illegally; when P is smaller than 0.5, the non-motor does not cross the street illegally. The signalized intersection non-motor vehicle illegal cross-street behavior automatic judging method reduces artificial participation, improves judging speed, and enables the judging to be correct and fair, and meanwhile, provides theoretical foundation for intersection transformation through the factors which obviously influence signalized non-motor vehicle illegal cross-street behavior, and has practical engineering applying value.
Description
Technical field
The present invention relates to a kind of signalized intersections bicycle and cross street behavior automatic distinguishing method in violation of rules and regulations, be specifically related to a kind of binary logit model that uses and carry out signalized intersections bicycle violation street behavior automatic distinguishing method excessively, 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, the preferred traffic instrument of especially domestic city resident short distance trip.The normal property sent out of bicycle accident and the seriousness of damage sequence, make bicycle accident become the feature of Chinese transportation accident, and become the difficult point of Chinese transportation and traffic hazard.2010, national bicycle accident 8745, cause 1462 people dead, 9483 people were injured, and direct property loss reaches 1,137 ten thousand yuans.Statistics shows, most of bicycle accident is crossed in violation of rules and regulations street due to it and caused, and thus studies how to determine that street behavior crossed by bicycle be have far reaching.
At present, the research of crossing street behavior for bicycle is less, and relevant research mainly concentrates on pedestrian's street crossing behavior.Existing research is mainly for the personal attribute of pedestrian, and the information such as Social Characteristics and family's characteristic are carried out qualitative analysis thus determined street Behavior preference.The research only having bicycle few in number to cross street behavior is also determine that it crosses street behavior based on information such as analysis age, sex, bicycle kinds, does not relate to crossing characteristic and the traffic environment that street crossed by bicycle.Thus existing method comprehensively can not cross the factor of street behavior by analyzing influence bicycle, and engineering practice can not be instructed to cross street behavior in violation of rules and regulations to reduce non-maneuver.
Summary of the invention
Goal of the invention: the object of the invention is to for the deficiencies in the prior art, provides a kind of accuracy of judgement, reduces manually participation, the signalized intersections bicycle of engineering practice can be instructed to cross street behavior automatic distinguishing method in violation of rules and regulations.
Technical scheme: a kind of signalized intersections bicycle of the present invention crosses street behavior automatic distinguishing method in violation of rules and regulations, it is characterized in that, carries out as follows:
(1) in signalized intersections crossing and environs thereof, set up two video cameras, First camera pedestal is located at the concealed location at crossing place, for taking bicycle characteristic and crossing street behavior; Second camera pedestal is located at the eminence of signalized intersections, overlooks shooting road traffic flow and crossing characteristic;
By the video of admission, correlation parameter is arranged, the parameter of arrangement comprises driver's sex, driver's age, whether driver helmets, whether bicycle is manned, whether bicycle type, intersection shape, crossing inlet road have median strip, whether crossing inlet road form of fracture, crossing inlet road to have 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 being gone to judge above-mentioned parameter by viewing video by people, then keeping a record.
(2) according to discrete choice analysis method, set up signalized intersections bicycle and cross street behavior binary logit forecast model in violation of rules and regulations, and adopt parameter progressive method to demarcate binary logit forecast model, calibration result is:
Wherein, x
1represent sex (1 man, 0 female), x
2represent the age (1 is young, and in 2 middle ages, 3 is old); x
3represent bicycle car type (1 battery-operated motor cycle, 2 electric bicycles, 3 bicycles); x
4represent crossing inlet road and whether have median strip (1 has, 2 nothings); x
5represent crossing inlet road form of fracture (1 single carriageway road, 2 Liang Fu roads, 3 triple carriageway roads); x
6represent crossing inlet road and whether have current vehicle (1 has, 2 nothings); x
7represent bicycle signal lamp form (1 numeric type; 2 flicker types).
(3) supplemental characteristic that in the supplemental characteristic arranged in step (1), in extraction step (2), forecast model needs, and by the binary logit forecast model in data input step (2), obtain signalized intersections bicycle and cross street behavior in violation of rules and regulations, as P>0.5, bicycle crosses street in violation of rules and regulations; As P<0.5, bicycle does not cross street in violation of rules and regulations.
Carrying out demarcating to binary logit forecast model in step (2) adopts the Analysis module of SPSS19.0 system to carry out, the supplemental characteristic likely affecting model obtained in step (1) is analyzed, by " parameter go forward one by one method ", effective Selecting parameter is out included in model, 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 multiple functional module, and the present invention's utilization Analysis module wherein realizes the parameter calibration that street behavior binary logit forecast model crossed in violation of rules and regulations by signalized intersections bicycle, and fitting result shows, and models fitting goodness is remarkable.
After setting up signalized intersections bicycle violation mistake street behavior binary logit forecast model in step (2), carried out the precision test of model by the measured data of check groups.Street behavior crossed in violation of rules and regulations by the signalized intersections bicycle of model prediction, and mistake street Deviant behavior is less in violation of rules and regulations with signalized intersections bicycle in measured data, proves applicability and the validity of model.Choose the checking that 1131, Nanjing bicycle carries out model, the prediction accuracy that model crosses street in violation of rules and regulations to bicycle is 82.8%, prediction accuracy bicycle not being crossed in violation of rules and regulations to street is 78.7%, aggregate prediction precision is 81.9%, the difference of predicted value and measured value is very little, thus demonstrates the validity of forecast model and the ubiquity of application.
Beneficial effect: a kind of signalized intersections bicycle of the present invention crosses street behavior automatic distinguishing method in violation of rules and regulations, by gathering the data of intersection in the method for intersection erection video camera, after correlation parameter is arranged, input binary logit forecast model, street is crossed to signalized intersections place bicycle and whether makes quick judgement in violation of rules and regulations, reduce artificial participation, improve judgement speed, make accuracy of judgement just; Meanwhile, also cross the factor of street behavior in violation of rules and regulations by appreciable impact signal bicycle in model, for crossing transformation provides theoretical foundation, there is actual engineering application and be worth.
Accompanying drawing explanation
Fig. 1 is the process flow diagram that street behavior automatic distinguishing method crossed in violation of rules and regulations by signalized intersections bicycle of the present invention;
Fig. 2 is the logical diagram that in the inventive method, street behavioral data crossed by collection signal crossing bicycle;
Fig. 3 is the process flow diagram of the method for building up of binary logit forecast model in the inventive method.
Embodiment
Below technical solution of the present invention is described in detail, but protection scope of the present invention is not limited to described embodiment.
Embodiment: a kind of signalized intersections bicycle of the present invention crosses street behavior automatic distinguishing method in violation of rules and regulations, and its process flow diagram as shown in Figure 1, carries out as follows:
(1) in signalized intersections crossing and environs thereof, set up two video cameras, First camera pedestal is located at the concealed location at crossing place, for taking bicycle characteristic and crossing street behavior; Second camera pedestal is located at the eminence of signalized intersections, overlooks shooting road traffic flow and crossing characteristic.
By the video of admission, correlation parameter is arranged, the parameter logistics figure arranged as shown in Figure 2, comprises driver's sex, driver's age, whether driver helmets, whether bicycle is manned, whether bicycle type, intersection shape, crossing inlet road have median strip, whether crossing inlet road form of fracture, crossing inlet road to have 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 being gone to judge above-mentioned parameter by viewing video by people, then keeping a record.
(2) according to discrete choice analysis method, set up signalized intersections bicycle and cross street behavior binary logit forecast model in violation of rules and regulations, set up the process flow diagram of binary logit forecast model method as shown in Figure 3, and adopt parameter progressive method to demarcate binary logit forecast model, calibration result is:
Wherein, x
1represent sex (1 man, 0 female), x
2represent the age (1 is young, and in 2 middle ages, 3 is old); x
3represent bicycle car type (1 battery-operated motor cycle, 2 electric bicycles, 3 bicycles); x
4represent crossing inlet road and whether have median strip (1 has, 2 nothings); x
5represent crossing inlet road form of fracture (1 single carriageway road, 2 Liang Fu roads, 3 triple carriageway roads); x
6represent crossing inlet road and whether have current vehicle (1 has, 2 nothings); x
7represent bicycle signal lamp form (1 numeric type; 2 flicker types).
Carrying out demarcating to binary logit forecast model adopts the Analysis module of SPSS19.0 system to carry out, the supplemental characteristic likely affecting model obtained in step (1) is analyzed, by " parameter go forward one by one method ", effective Selecting parameter is out included in model, 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 multiple functional module, and the present invention's utilization Analysis module wherein realizes the parameter calibration that street behavior binary logit forecast model crossed in violation of rules and regulations by signalized intersections bicycle, and fitting result shows, and models fitting goodness is remarkable.
After setting up signalized intersections bicycle violation mistake street behavior binary logit forecast model, carried out the precision test of model by the measured data of check groups.Street behavior crossed in violation of rules and regulations by the signalized intersections bicycle of model prediction, and mistake street Deviant behavior is less in violation of rules and regulations with signalized intersections bicycle in measured data, proves applicability and the validity of model.Choose the checking that 1131, Nanjing bicycle carries out model, the prediction accuracy that model crosses street in violation of rules and regulations to bicycle is 82.8%, prediction accuracy bicycle not being crossed in violation of rules and regulations to street is 78.7%, aggregate prediction precision is 81.9%, the difference of predicted value and measured value is very little, thus demonstrates the validity of forecast model and the ubiquity of application.
(3) supplemental characteristic that in the supplemental characteristic arranged in step (1), in extraction step (2), forecast model needs, and by the binary logit forecast model in data input step (2), obtain signalized intersections bicycle and cross street behavior in violation of rules and regulations, as P>0.5, bicycle crosses street in violation of rules and regulations; As P<0.5, bicycle does not cross street in violation of rules and regulations.
Apply method of the present invention, 10 groups of bicycle data are obtained by the collection of bicycle data video, and data are inputed in binary logit forecast model and carry out bicycle and cross street behavior and predict, and will predict the outcome and cross street behavior with reality and compare, result is as shown in table 1:
Table 1:
The determination that street behavior crossed by signalized intersections bicycle is most important to raising intersection traffic safety, street behavior binary logit forecast model is crossed in violation of rules and regulations based on signalized intersections bicycle, by information input models such as bicycle characteristic and crossing geometrical properties, street behavior can be crossed in violation of rules and regulations to signalized intersections bicycle and make quick judgement.In addition, also cross the factor of street behavior by appreciable impact signal bicycle in model in violation of rules and regulations, carry out crossing transformation, there is actual engineering application and be worth.As shown in the Examples, that crosses street behavior to 10 groups of bicycles predicts the outcome that to cross street behavior with reality consistent, and what describe the inventive method implements validity.
As mentioned above, although represented with reference to specific preferred embodiment and described the present invention, it shall not be construed as the restriction to the present invention self.Under the spirit and scope of the present invention prerequisite not departing from claims definition, various change can be made in the form and details to it.
Claims (3)
1. signalized intersections bicycle crosses a street behavior automatic distinguishing method in violation of rules and regulations, it is characterized in that, carries out as follows:
(1) in signalized intersections crossing and environs thereof, set up two video cameras, First camera pedestal is located at the concealed location at crossing place, for taking bicycle characteristic and crossing street behavior; Second camera pedestal is located at the eminence of signalized intersections, overlooks shooting road traffic flow and crossing characteristic;
By the video of admission, correlation parameter is arranged, the parameter of arrangement comprises driver's sex, driver's age, whether driver helmets, whether bicycle is manned, whether bicycle type, intersection shape, crossing inlet road have median strip, whether crossing inlet road form of fracture, crossing inlet road to have in current vehicle, bicycle signal lamp form, 5min motor vehicle number in bicycle number and 5min;
(2) according to discrete choice analysis method, set up signalized intersections bicycle and cross street behavior binary logit forecast model in violation of rules and regulations, and adopt parameter progressive method to demarcate binary logit forecast model, calibration result is:
Wherein, x
1for driver's sex, x
2for driver's age, x
3for bicycle type, x
4for whether crossing inlet road has median strip, x
5for crossing inlet road form of fracture, x
6for whether crossing inlet road has current vehicle, x
7for bicycle signal lamp form;
(3) supplemental characteristic that in the supplemental characteristic arranged in step (1), in extraction step (2), forecast model needs, and by the binary logit forecast model in data input step (2), obtain signalized intersections bicycle and cross street behavior in violation of rules and regulations, as P>0.5, bicycle crosses street in violation of rules and regulations; As P<0.5, bicycle does not cross street in violation of rules and regulations.
2. a kind of signalized intersections bicycle according to claim 1 crosses street behavior automatic distinguishing method in violation of rules and regulations, it is characterized in that, carries out demarcating adopting the Analysis module of SPSS19.0 system to carry out in step (2) to binary logit forecast model.
3. a kind of signalized intersections bicycle according to claim 1 crosses street behavior automatic distinguishing method in violation of rules and regulations, it is characterized in that, after setting up signalized intersections bicycle violation mistake street behavior binary logit forecast model in step (2), carried out the precision test of model by the measured data of check groups.
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 CN103093624A (en) | 2013-05-08 |
| CN103093624B true CN103093624B (en) | 2015-04-15 |
Family
ID=48206145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310007674.XA Active 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) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200668B (en) * | 2014-07-28 | 2017-07-11 | 四川大学 | A kind of motorcycle based on graphical analysis is not helmeted violation event detection method |
| CN110516518A (en) * | 2018-05-22 | 2019-11-29 | 杭州海康威视数字技术股份有限公司 | A kind of illegal manned detection method of non-motor vehicle, device and electronic equipment |
| 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 |
| 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 |
| CN117480540A (en) * | 2021-09-24 | 2024-01-30 | 英特尔公司 | Infrastructure dynamic control for vulnerable users |
| 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 |
-
2013
- 2013-01-09 CN CN201310007674.XA patent/CN103093624B/en active Active
Non-Patent Citations (4)
| Title |
|---|
| 信号交叉口人行横道处的行人可接受间隙研究;孙智勇等;《公路交通科技》;20041130;第21卷(第11期);第102~104、113页 * |
| 城市四支信号交叉口行人交通特性及违法分析;张壮;《中国优秀硕士学位论文全文数据库 工程科技II辑》;20101015(第10期);第C034-290页 * |
| 无信号控制交叉口行人过街间隙选择模型研究;朱芳芳;《交通信息与安全》;20111231;第29卷(第2期);第36~39、43页 * |
| 行人过街设施选择偏好的非集计模型;熊辉等;《北京理工大学学报》;20080131;第28卷(第1期);第37~40页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103093624A (en) | 2013-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103093624B (en) | Signalized intersection non-motor vehicle illegal cross-street behavior automatic judging method | |
| Pai et al. | Cyclists’ red-light running behaviours: An examination of risk-taking, opportunistic, and law-obeying behaviours | |
| Miranda-Moreno et al. | Disaggregate exposure measures and injury frequency models of cyclist safety at signalized intersections | |
| CN108230676A (en) | A kind of intersection pedestrian's street crossing methods of risk assessment based on track data | |
| CN104294720A (en) | Method for evaluating safety of expressway design scheme | |
| CN113066287B (en) | Active prevention and control method and system for highway traffic accident site risks | |
| CN109887283A (en) | A kind of congestion in road prediction technique, system and device based on bayonet data | |
| Nolan et al. | Are bicycle lanes effective? The relationship between passing distance and road characteristics | |
| CN112101670A (en) | Data processing method and device, electronic equipment and readable storage medium | |
| CN114550445B (en) | Urban area traffic safety state assessment method and device | |
| Chen et al. | Lane-based Distance-Velocity model for evaluating pedestrian-vehicle interaction at non-signalized locations | |
| Yanfeng et al. | Characteristic analysis of pedestrian violation crossing behavior based on logistics model | |
| CN116153108A (en) | Method for evaluating safety influence of illumination on intersection by using random forest model | |
| Yu et al. | Using 3D mobile mapping to evaluate intersection design through drivers’ visual perception | |
| Liang et al. | Analyzing bicycle level of service using virtual reality and deep learning technologies | |
| Zhai et al. | Comparative analysis of drive-cycles, speed limit violations, and emissions in two cities: Toronto and Beijing | |
| CN105118310A (en) | Video-based single-point self-optimization signal control method and device | |
| Li et al. | Incorporating traffic control and safety hardware performance functions into risk-based highway safety analysis | |
| Ghadirzadeh et al. | Analysing pedestrian–vehicle conflict behaviours at urban pedestrian crossings | |
| Ehsani Sohi et al. | Effects of roadway and traffic characteristics on accidents frequency at city entrance zone | |
| CN105096586A (en) | Plain area freeway accident prediction method based on traffic flow characteristic parameters | |
| Hu et al. | GIS-based road safety evaluation model for cyclist in campus of Higher Education Mega Center | |
| Lin et al. | Naturalistic Bicycling Behavior Pilot Study. | |
| Ma et al. | Personal Characteristics of e‐Bike Riders and Illegal Lane Occupation Behavior | |
| Shams Esfandabadi | Safety effectiveness of adding by-pass lanes at unsignalized rural intersections in Kansas |
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 |