CN110211386B - Non-parameter inspection-based highway vehicle type classification method - Google Patents
Non-parameter inspection-based highway vehicle type classification method Download PDFInfo
- Publication number
- CN110211386B CN110211386B CN201910430406.6A CN201910430406A CN110211386B CN 110211386 B CN110211386 B CN 110211386B CN 201910430406 A CN201910430406 A CN 201910430406A CN 110211386 B CN110211386 B CN 110211386B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- types
- vehicle type
- classification
- inspection
- 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
-
- 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
- G08G1/015—Detecting movement of traffic to be counted or controlled with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
Abstract
The invention discloses a non-parameter inspection-based highway vehicle type classification method, which comprises 3 stages and 8 steps. Firstly, collecting parameters of common vehicle types on the highway, and providing a standard for preliminary vehicle type division according to the principle of distinguishing passenger cars and trucks and classifying as detailed as possible; secondly, observing the traffic flow of the highway, extracting indexes such as speed, headway, tailstock interval and the like, carrying out nonparametric inspection on the preliminarily divided vehicle types, analyzing inspection results, and excluding the indexes unsuitable for being used as vehicle type classification indexes; and finally, further analyzing the K-S detection result for the index which can be used as the vehicle type classification index, merging the vehicle types meeting the condition, and considering whether further merging is needed or not according to the result to obtain the final vehicle type classification scheme. The invention considers the difference of vehicles in the moving process, and the proposed vehicle type classification method can provide a basis for making a lane division scheme of the highway and improve the safety and efficiency of highway operation.
Description
Technical Field
The invention belongs to the technical field of highway lane management, and particularly relates to a highway vehicle type classification method based on non-parameter inspection.
Background
With the social and economic development and the accelerated urbanization process, in recent years, the expressway in China develops rapidly, the vehicle passing mileage of the expressway increases year by year, and a plurality of expressways are successively reconstructed and expanded. The types of vehicles running on the expressway are complex, and various types of vehicles have differences in size, power performance, passenger carrying capacity and the like. In order to promote safe and efficient driving of vehicles, a certain lane division strategy is often adopted for the expressway, the right of way of different vehicle types in each lane is limited, and vehicle type classification is a precondition for lane division.
The road engineering technical standard (JTGB01-2014) established by the road department in China divides automobiles into 4 types of passenger cars, medium-sized cars, large-sized cars and automobile trains, and provides conversion coefficients of different vehicle types for traffic volume analysis; the automobile is divided into 11 categories, namely passenger automobiles, cargo automobiles and special operating vehicles 3 by motor vehicle type terms and definitions (GA802-2014) set by a traffic police department and used for road traffic management. The classification of the vehicle types by different departments has different purposes, so that the classification standards are different, and the classification detail degree is also inconsistent. At present, vehicle type classification standards for lane division are not formulated in China, lanes are divided into small lanes and large lanes by part of highways, lanes are divided into passenger lanes and goods lanes by part of highways, and different vehicle type classification methods for lane division on different highways are different.
When the method is used for lane division, the vehicle type classification mainly considers the differences of the power performance and the driving behaviors of different vehicle types, the classification standard is popular and easy to understand, the driver and a manager can conveniently master the classification standard, the difficulty of vehicle identification and supervision is reduced, and the number of vehicle type categories is not too large. Therefore, a method for classifying vehicle types on the highway needs to be researched, vehicle type classification standards for lane division are formulated, and the running safety and efficiency of the highway are improved.
Disclosure of Invention
In order to solve the problems, the invention discloses a non-parameter inspection-based highway vehicle type classification method, which uses non-parameter inspection of two groups of independent samples for vehicle type classification research, analyzes the difference of the operating characteristics of different types of vehicles, formulates the proportion selection principle of classification indexes, provides the merging criterion of vehicle type classification, and has more reasonable classification results.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a non-parameter inspection-based highway vehicle type classification method comprises the following steps:
(1) preliminary classification of vehicle types
Step 1: collecting parameters of common vehicle types of the expressway, including size, vehicle body structure, rated passenger capacity, whole vehicle weight, rated load capacity, maximum vehicle speed and the like;
step 2: according to the principle of distinguishing passenger cars and trucks and classifying the cars as detailed as possible, the standard of vehicle type preliminary classification is provided. Passenger cars are classified mainly according to the number of seats, and trucks are classified mainly according to the total mass (the sum of the vehicle's dead weight and the rated load).
The vehicle model preliminary classification criteria are shown in table 1:
TABLE 1 preliminary vehicle type division table
Note: the trucks comprise railing type, van type, bin grid type, self-unloading type and the like; the special vehicles comprise oil tank trucks, concrete mixer trucks and the like.
(2) Vehicle type classification index comparison and selection
And step 3: and observing the traffic flow of the highway, selecting a certain section, and extracting parameters such as the type (primarily divided according to the type), size, speed, headway, tailstock interval and the like of each vehicle when the vehicle passes through the section. The observation duration is determined according to the number of observation samples, and each vehicle type is ensured to extract enough sample amount.
The rear-to-rear distance is defined as the road space occupied by the moving vehicle, i.e. the space occupied by the vehicle body itself plus the space between the front and rear of the vehicle, as shown in fig. 1. The vehicle always keeps a certain distance from the front vehicle in the moving process, and the distance reflects the consideration of a driver on driving safety and is related to the speed and the deceleration performance of the vehicle. The method for calculating the vehicle tail distance comprises the following steps:
Dn＝Sn-Ln+1+Ln
Sn＝Vn·hn
in the formula, DnIndicating the vehicle rear spacing of the nth vehicle, SnIndicates the headway distance of the nth vehicle, LnIndicates the body length, L, of the nth vehiclen+1Denotes a vehicle body length, V, of an n +1 th vehicle (preceding vehicle)nRepresenting the speed of the nth vehicle, hnThe headway of the nth vehicle from the preceding vehicle is shown.
And 4, step 4: selecting 1 index (speed, headway, tailstock distance and the like) as a test variable, and performing Kolmogorov-Smirnov Z test (K-S test) on the preliminarily divided vehicle types.
The Kolmogorov-Smirnov Z test is a nonparametric test method used to infer whether there is a significant difference in the distribution from two populations by analyzing two independent sets of samples with little knowledge of the population distribution. The method for testing two groups of independent samples by K-S is as follows: mixing and arranging the two groups of samples in ascending order, respectively calculating the accumulative frequency and the accumulative frequency of the two groups of sample ranks, calculating the difference of the two groups of accumulative frequencies to obtain the difference value sequence and the D statistic of the ranks, calculating the probability p value of the statistic, comparing the p value with the significance level alpha (taking 0.05), and judging whether to accept the zero hypothesis or reject the zero hypothesis. Since the zero hypothesis is that the distributions of the two populations from the two independent samples have no significant difference, the zero hypothesis is rejected when the p value is less than the significance level, that is, the two vehicle models are considered to have significant difference.
And 5: and analyzing the inspection result, and if the following conditions occur, determining that the index is not suitable as the vehicle type classification index:
the differences between a certain vehicle type and all other vehicle types are not obvious;
in the category of passenger cars or trucks, a certain car type has a significant difference from an adjacent car type, but the difference from a non-adjacent car type is not significant (the adjacent car type refers to a car type with an adjacent position in the preliminary division of the car type, for example, a small-sized passenger car and a medium-sized passenger car are adjacent car types, the medium-sized truck and a heavy truck are adjacent car types, but an extra-large-sized passenger car and a micro truck are not adjacent car types).
Step 6: replacing other indexes (speed, headway, tailstock interval and the like) as inspection variables, repeating the step 4 and the step 5, and eliminating the indexes which are not suitable as vehicle type classification indexes.
(3) Further classification of vehicle type
And 7: and further analyzing the K-S inspection result between every two vehicle types for the index which can be used as the vehicle type classification index. The analysis method comprises the following steps: if the difference situation of two vehicle types and all other vehicle types is completely the same, the two vehicle types can be combined into one type.
And 8: on the basis of the classification result, if the vehicle types are further combined (such as the number of classes needs to be reduced), combining samples of partial vehicle types into a new vehicle type is tried, and K-S inspection is conducted again between every two different vehicle types. And analyzing the test result according to the method in the step 7 to obtain a final vehicle type classification scheme.
The invention has the beneficial effects that:
the existing expressway vehicle type classification method mainly focuses on static characteristics of vehicles according to the sizes, wheelbases, passenger capacities or mass capacities of the vehicles, and the static characteristics of the vehicles are not considered sufficiently. Vehicle type classification standards are proposed by different departments in China, but due to different purposes, classification methods and classification detail degrees are different. Meanwhile, the vehicle type classification standard for lane division is not established in China, and the vehicle type classification standards of different highways are different. The invention provides a non-parameter inspection-based highway vehicle type classification method, which comprises the steps of selecting indexes of vehicle speed, headway, tail space and the like which reflect vehicle running characteristics, analyzing the difference of each vehicle type and other vehicle types in the motion process, and enabling the vehicle type classification result to guide the practice of highway lane division. The invention can provide a vehicle type classification basis for formulating a lane division scheme of the highway so as to separate vehicles with larger differences of vehicle performance and running characteristics and improve the running safety and efficiency of the highway.
Drawings
Figure 1 is a flow chart of vehicle type classification according to the invention,
FIG. 2 is a schematic view of the rear spacing of a vehicle.
Detailed Description
The present invention will be further illustrated with reference to the accompanying drawings and specific embodiments, which are to be understood as merely illustrative of the invention and not as limiting the scope of the invention.
In order to manage lanes, the vehicle types of a certain eight-lane highway in China are classified.
(1) Preliminary classification of vehicle types
Step 1: collecting parameters of common vehicle types of the expressway, including size, vehicle body structure, rated passenger capacity, whole vehicle weight, rated load capacity, maximum vehicle speed and the like. Some models are shown in table 2:
TABLE 2 common model parameters for expressway
Step 2: according to the principle of distinguishing passenger cars and trucks and classifying the cars as detailed as possible, the standard of vehicle type preliminary classification is provided. Passenger cars are classified mainly according to the number of seats, and trucks are classified mainly according to the total mass (the sum of the vehicle's dead weight and the rated load).
The vehicle model preliminary classification criteria are shown in table 1.
(2) Vehicle type classification index comparison and selection
And step 3: and observing the traffic flow of the highway, selecting a certain section, and extracting parameters such as the type (primarily divided according to the type), size, speed, headway, tailstock interval and the like of each vehicle when the vehicle passes through the section. The observation duration is determined according to the number of observation samples, and each vehicle type is ensured to extract enough sample amount.
And observing a certain section of the highway, wherein the observation time is 50 minutes, and 3896 samples are obtained, wherein 3428 minibuses, 38 medium buses, 14 large buses, 91 extra large buses, 68 minivans, 48 light vans, 59 medium vans and 149 heavy vans are used.
And 4, step 4: selecting 1 index (speed, headway, tailstock distance and the like) as a test variable, and performing Kolmogorov-Smirnov Z test (K-S test) on the preliminarily divided vehicle types.
And 5: and analyzing the inspection result, and if the following conditions occur, determining that the index is not suitable as the vehicle type classification index:
the differences between a certain vehicle type and all other vehicle types are not obvious;
in the category of passenger cars or trucks, a certain car type has a significant difference from an adjacent car type, but the difference from a non-adjacent car type is not significant (the adjacent car type refers to a car type with an adjacent position in the preliminary division of the car type, for example, a small-sized passenger car and a medium-sized passenger car are adjacent car types, the medium-sized truck and a heavy truck are adjacent car types, but an extra-large-sized passenger car and a micro truck are not adjacent car types).
Step 6: and (5) replacing other indexes as test variables, repeating the step 4 and the step 5, and eliminating the indexes which are not suitable as vehicle type classification indexes.
The results with speed as the check variable are shown in table 3. In order to make the comparison between different vehicle types more intuitive, the test results are summarized in table 4, and obviously, the table is symmetrical along the diagonal line, and the difference between each vehicle type and the table is not obvious. As can be seen from table 4, the differences between the medium passenger car and the large passenger car and all the vehicle types are not significant, and therefore the speed is considered to be unsuitable as the vehicle type classification index in this example. The reason for this may be that the vehicle is limited to run when the traffic flow density is high, the speed difference between different vehicle types is not obvious, and the reason may be related to the small sample size of medium-sized passenger cars and large-sized passenger cars.
TABLE 3 table of speed non-parametric test results under preliminary division
Table 4 comparison table of speed non-parameter checking vehicle type under preliminary division
The pair of test results with headway as the test variable is shown in table 5. As can be seen from the table, the small-sized passenger car and the medium-sized passenger car are adjacent but have significant differences, and the small-sized passenger car and the large-sized passenger car are not adjacent but have insignificant differences, so that the head-end time interval is considered to be unsuitable as a vehicle type classification index under the data condition of the example. The reason for this may be that the large passenger car has a small sample size.
TABLE 5 locomotive headway non-parameter checking vehicle type comparison table under preliminary division
The test result pairs with the tail clearance as the test variable are shown in table 6. As can be seen from the table, there is no case where the index is rejected as the vehicle type classification index, and therefore the vehicle rear pitch can be used as the index of vehicle type classification.
Table 6 vehicle rear interval non-parameter checking vehicle type comparison table under preliminary division
(3) Further classification of vehicle type
And 7: and further analyzing the K-S inspection result between every two vehicle types for the index which can be used as the vehicle type classification index. The analysis method comprises the following steps: if the difference situation of two vehicle types and all other vehicle types is completely the same, the two vehicle types can be combined into one type.
As can be seen from table 6, the difference between the car rear distances of two different car models is not completely the same as that of the other car models, in other words, each car model is different. From the inspection result, a certain two vehicle types cannot be combined.
And 8: on the basis of the classification result, if the vehicle types are further combined (such as the number of classes needs to be reduced), combining samples of partial vehicle types into a new vehicle type is tried, and K-S inspection is conducted again between every two different vehicle types. And analyzing the test result according to the method in the step 7 to obtain a final vehicle type classification scheme.
When the eight-lane highway is used for lane management, vehicle type division is popular and easy to understand, drivers and managers can master conveniently, difficulty in vehicle identification and supervision is reduced, the number of vehicle types is not too large, and therefore partial vehicle types need to be merged. As can be seen from table 6, there is similarity in the differences between some models of vehicles and other models of vehicles, such as minivans and pickup vans, which differ only in the differences from oversize buses. Divide into other passenger cars except minibus into one kind, divide into one kind with other freight cars except heavy goods van, be about to 8 types of motorcycle types merge into 4 types: the first type: a small bus, 3428 total; the second category is 143 medium-sized passenger cars, large-sized passenger cars and extra-large-sized passenger cars; the third category, mini-trucks, light trucks, medium trucks, total 175; and a fourth category, heavy goods vehicles, 149 vehicles.
And performing K-S inspection on the combined vehicle models pairwise, wherein the inspection results are shown in a table 7. As can be seen from the table, the difference between the tail distances of the medium, large and extra-large buses and the tail distances of the small, light and medium trucks and other vehicle types are completely the same. From the inspection result, the vehicle types can be divided into 3 types, namely small passenger cars; medium, large and extra large passenger cars and small, light and medium trucks; heavy goods vehicles.
TABLE 7 comparison table for vehicle rear interval non-parameter inspection vehicle types after vehicle type combination
Because the passenger car and the truck have differences in the aspects of size, weight, power performance, driving behavior and the like, most of the highways in China implement a lane function division method for passenger-truck lane division driving, so that the middle, large and extra-large passenger cars and the small, light and medium-sized trucks are not combined, and finally the types of the passenger cars are divided into 4 types, namely small passenger cars, large and medium-sized passenger cars, medium and small trucks and large trucks. The classification criteria are shown in table 8:
TABLE 8 vehicle type Final Classification List
Claims (3)
1. A non-parameter inspection-based method for classifying vehicle types on a highway is characterized by comprising the following steps: the method comprises the following steps:
(1) preliminary classification of vehicle types
Step 1: collecting parameters of common vehicle types of the expressway, including size, vehicle body structure, rated passenger capacity, whole vehicle weight, rated load capacity and maximum vehicle speed;
step 2: according to the principle of distinguishing passenger cars and trucks and classifying the passenger cars as detailed as possible, the standard of primary classification of the car types is provided, the passenger cars are mainly classified according to seat numbers, and the trucks are classified according to the total mass;
(2) vehicle type classification index comparison and selection
And step 3: observing the traffic flow of the highway, selecting a certain section, and extracting parameters such as the type, the size, the speed, the head-time interval and the tail-end interval of each vehicle when the vehicles pass through the section; the observation duration is determined according to the number of observation samples, and sufficient sample amount is ensured to be extracted for each vehicle type;
the vehicle tail space is defined as the road space occupied by the moving vehicle, namely the space occupied by the vehicle body plus the space between the vehicle head and the front vehicle tail, the vehicle always keeps a certain distance from the front vehicle in the moving process, and the distance reflects the consideration of the driver on the driving safety and is related to the speed and the deceleration performance of the vehicle; the method for calculating the vehicle tail distance comprises the following steps:
Dn＝Sn-Ln+1+Ln
Sn＝Vn·hn
in the formula, DnIndicating the vehicle rear spacing of the nth vehicle, SnIndicates the headway distance of the nth vehicle, LnIndicates the body length, L, of the nth vehiclen+1Denotes the body length of the (n + 1) th vehicle, i.e., the body length of the preceding vehicle, VnRepresenting the speed of the nth vehicle, hnRepresenting the time headway of the nth vehicle and the previous vehicle;
and 4, step 4: selecting 1 index as a test variable, and performing K-S test on the preliminarily divided vehicle types;
and 5: and analyzing the inspection result, and if the following conditions occur, determining that the index is not suitable as the vehicle type classification index:
the differences between a certain vehicle type and all other vehicle types are not obvious;
in the category of passenger cars or trucks, a certain car type has significant difference with adjacent car types, but has insignificant difference with non-adjacent car types;
step 6: replacing other indexes as inspection variables, repeating the step 4 and the step 5, and removing the indexes which are not suitable as vehicle type classification indexes;
(3) further classification of vehicle type
And 7: further analyzing K-S inspection results between every two vehicle types for the indexes which can be used as vehicle type classification indexes; the analysis method comprises the following steps: if the difference conditions of the two vehicle types and all other vehicle types are completely the same, the two vehicle types are considered to be combined into one type;
and 8: on the basis of the classification result, when the number of categories needs to be reduced, combining samples of part of vehicle types into a new vehicle type, and performing K-S inspection on different vehicle types again; and analyzing the test result according to the method in the step 7 to obtain a final vehicle type classification scheme.
2. The non-parametric inspection-based classification method for vehicle types on highways according to claim 1, characterized in that: and 2, the total mass is the sum of the self weight of the vehicle and the rated load.
3. The non-parametric inspection-based classification method for vehicle types on highways according to claim 1, characterized in that: the K-S test described in step 4 is a nonparametric test method used to infer whether there is a significant difference in the distributions from two populations by analyzing two groups of independent samples, without knowing the population distributions; the method for testing two groups of independent samples by K-S is as follows: mixing and arranging the two groups of samples in ascending order, respectively calculating the accumulative frequency and the accumulative frequency of the two groups of sample ranks, calculating the difference of the two groups of accumulative frequencies to obtain the difference sequence and the D statistic of the ranks, calculating the probability p value of the statistic, comparing the p value with the significance level alpha, and judging whether to accept the zero hypothesis or reject the zero hypothesis; since the zero hypothesis is that the distributions of the two populations from the two independent samples have no significant difference, the zero hypothesis is rejected when the p value is less than the significance level, that is, the two vehicle models are considered to have significant difference.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910430406.6A CN110211386B (en) | 2019-05-22 | 2019-05-22 | Non-parameter inspection-based highway vehicle type classification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910430406.6A CN110211386B (en) | 2019-05-22 | 2019-05-22 | Non-parameter inspection-based highway vehicle type classification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110211386A CN110211386A (en) | 2019-09-06 |
| CN110211386B true CN110211386B (en) | 2021-03-23 |
Family
ID=67788097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910430406.6A Active CN110211386B (en) | 2019-05-22 | 2019-05-22 | Non-parameter inspection-based highway vehicle type classification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110211386B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113313946A (en) * | 2021-05-31 | 2021-08-27 | 长安大学 | Multi-lane highway passenger and truck cooperative control method, device and equipment |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2896070B1 (en) * | 2006-01-11 | 2008-02-15 | Commissariat Energie Atomique | MAGNETIC SYSTEM FOR CONTROLLING TRAFFIC |
| CN103164577B (en) * | 2013-03-12 | 2015-12-02 | 天津市市政工程设计研究院 | Determine the method for harbour bridge automobile load rated figure |
| CN103295079A (en) * | 2013-06-09 | 2013-09-11 | 国家电网公司 | Electric power multi-objective decision support method based on intelligent data mining model |
| US9483838B2 (en) * | 2014-04-24 | 2016-11-01 | Xerox Corporation | Method and system for automated sequencing of vehicles in side-by-side drive-thru configurations via appearance-based classification |
| CN104933284B (en) * | 2015-02-12 | 2016-07-06 | 长安大学 | The random wagon flow analogy method of a kind of highway bridge based on measured data |
| CN104732013B (en) * | 2015-02-12 | 2016-07-06 | 长安大学 | The vehicular load recognition methods by multi-girder bridge of a kind of bicycle |
| CN106650818B (en) * | 2016-12-30 | 2020-01-03 | 太原理工大学 | Resting state function magnetic resonance image data classification method based on high-order hyper-network |
| CN108417042A (en) * | 2017-09-18 | 2018-08-17 | 西安金路交通工程科技发展有限责任公司 | Car based on vehicle image and lorry sorting technique |
-
2019
- 2019-05-22 CN CN201910430406.6A patent/CN110211386B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| Analysis of vehicle headway distribution on multi-lane freeway considering car–truck interaction;Guo Xiucheng 等;《Advances In Mechanical Engineering》;20161231;1-12 * |
| 城市道路车辆分类及折算系数研究;景鹏 等;《城市交通》;20060331;61-64 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110211386A (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Berzi et al. | Development of driving cycles for electric vehicles in the context of the city of Florence | |
| CN107067722B (en) | Method for constructing vehicle running condition | |
| CN106203330A (en) | A kind of vehicle classification method based on convolutional neural networks | |
| CN108550263A (en) | A kind of traffic accidents genetic analysis method based on fault tree models | |
| CN113313946A (en) | Multi-lane highway passenger and truck cooperative control method, device and equipment | |
| CN111552926A (en) | Driving behavior evaluation method and system based on Internet of vehicles and storage medium | |
| CN110211386B (en) | Non-parameter inspection-based highway vehicle type classification method | |
| CN113920732B (en) | Road traffic accident risk early warning method for specific driving crowd | |
| CN102789690B (en) | Illegal vehicle identifying method and system | |
| CN113297795A (en) | Method for constructing running condition of pure electric vehicle | |
| Wang et al. | Development of a typical urban driving cycle for battery electric vehicles based on kernel principal component analysis and random forest | |
| CN113553548B (en) | Actual operation condition VSPBin dividing method based on Internet of vehicles big data | |
| d'Agostino et al. | Learning-based driving events classification | |
| CN113657432A (en) | Commercial vehicle driving behavior risk level identification method based on Internet of vehicles data | |
| CN116307699A (en) | Road hidden trouble point segment grading method, device and storage medium based on multi-source data | |
| CN115718886A (en) | Construction method and device for pure electric vehicle running condition | |
| CN115688003A (en) | Driver identification method and device, computer equipment and readable storage medium | |
| Ma et al. | Naturalistic driving behavior analysis under typical normal cut-in scenarios | |
| Hasan et al. | Severity analysis of heavy vehicle crashes using machine learning models: A case study in New Jersey | |
| Abdelwahab et al. | Investigating the effect of light truck vehicle percentages on head-on fatal traffic crashes | |
| CN116029624B (en) | Goods source place identification method integrating truck track and POI data | |
| Yuan et al. | Study of driving cycle of city tour bus based on coupled GA-K-means and HMM algorithms: a case study in Beijing | |
| CN116070731A (en) | Regional electric automobile load classification prediction method and system | |
| Xu et al. | Analysis on Influencing Factors of accidents at national and provincial road intersections based on random forest | |
| Zan et al. | Lane Change Intention Recognition for Human Driving Vehicles under Moving Bottleneck on Freeway |
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 |