CN114112435A - Intelligent internet vehicle-oriented in-loop scene oriented self-adaptive evaluation test method and system - Google Patents
Intelligent internet vehicle-oriented in-loop scene oriented self-adaptive evaluation test method and system Download PDFInfo
- Publication number
- CN114112435A CN114112435A CN202111435477.9A CN202111435477A CN114112435A CN 114112435 A CN114112435 A CN 114112435A CN 202111435477 A CN202111435477 A CN 202111435477A CN 114112435 A CN114112435 A CN 114112435A
- Authority
- CN
- China
- Prior art keywords
- risk
- scene
- vehicle
- oriented
- unit
- 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.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 32
- 238000010998 test method Methods 0.000 title claims description 6
- 238000012360 testing method Methods 0.000 claims abstract description 40
- 230000010485 coping Effects 0.000 claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000005259 measurement Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 12
- 230000004044 response Effects 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 abstract description 10
- 238000000034 method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an intelligent internet vehicle-oriented in-the-loop scene oriented self-adaptive evaluation testing method and system, which are applied to the technical field of intelligent internet vehicle simulation testing and comprise the following steps: a data acquisition step: extracting risk scene slices from the video data by using a deep neural network; a database establishing step: extracting traffic scene information from the risk scene slices, determining the scene risk level, and establishing a scene description file according to the scene risk level to form a risk scene library; and (3) an analysis step: and adjusting the risk coping capability estimators of the tested vehicle by using the risk scenes of different levels to obtain the final risk coping capability of the tested vehicle. The invention adjusts the subsequent scene according to the real-time test result of the vehicle, combines virtual and real tests, effectively reduces the test cost and improves the test safety and accuracy.
Description
Technical Field
The invention relates to the technical field of intelligent networking vehicle simulation tests, in particular to a method and a system for intelligent networking vehicle in-loop scene oriented self-adaptive evaluation testing.
Background
In the development process of the intelligent networked vehicle, the development and test of the intelligent networked vehicle are also developed from the initial model level (microcosmic, mesoscopic and macroscopic) to a more real and complex environment.
However, the driving scene needing to be tested before the intelligent internet connection vehicle gets on the road is complicated. The traditional test method mainly comprises simulation test, closed scene test and open road test. The simulation test process is difficult to accurately model people, vehicles and environments, so that the simulation result is often far from the real situation. If both the closed road test and the actual road test are performed, the required cost and time are difficult to measure. It is estimated that testing an unmanned system requires approximately 8b miles (80 hundred million miles) of road testing, which is equivalent to 100 unmanned vehicles running 400 years 24 hours a day, 7 days a week, 365 days a year.
Therefore, it is an urgent need to solve the above technical problems by providing an intelligent internet vehicle-oriented in-the-loop scene oriented adaptive evaluation testing method and system.
Disclosure of Invention
In view of the above, the invention provides an intelligent internet vehicle-oriented in-the-loop scene-oriented self-adaptive evaluation testing method and system, which adjust the subsequent scene according to the real-time testing result of the vehicle, combine virtual and real tests, effectively reduce the testing cost and improve the testing safety and accuracy.
In order to achieve the purpose, the invention adopts the following technical scheme:
the intelligent network vehicle-oriented in-the-loop scene oriented self-adaptive evaluation test method comprises the following steps of:
a data acquisition step: extracting risk scene slices from the video data by using a deep neural network;
a database establishing step: extracting traffic scene information from the risk scene slices, determining the scene risk level, and establishing a scene description file according to the scene risk level to form a risk scene library;
and (3) an analysis step: and adjusting the risk coping capability estimators of the tested vehicle by using the risk scenes of different levels to obtain the final risk coping capability of the tested vehicle.
Optionally, the specific content of the data obtaining step includes: and training a deep neural network through the marked automatic driving risk scene data, automatically identifying the risk scene in the video data set by using the neural network, and outputting a risk scene slice with preset continuous video frame numbers.
Optionally, the specific content of the database establishing step includes: any frame of image in the risk scene slice is extracted, and after target detection and classification, lane line detection, structured information calculation, risk measurement and standard format scene formation are carried out in sequence, standard scene storage is carried out, and a risk scene library is formed.
Optionally, the specific content of the analyzing step includes: triggering a corresponding scene from a risk scene library based on the state of the detected vehicle and the prior risk corresponding capacity estimator, and adjusting the risk corresponding capacity evaluation of the detected vehicle according to the response of the detected vehicle to different risk level scenes to obtain the final risk corresponding capacity of the detected vehicle.
The intelligent network vehicle-oriented in-the-loop scene oriented self-adaptive evaluation testing system comprises a data acquisition module, a database establishing module and an analysis and evaluation module which are sequentially connected;
the data acquisition module is used for extracting risk scene slices from the video data by using a deep neural network;
the database establishing module is used for extracting traffic scene information from the risk scene slices, determining the scene risk level, and establishing a scene description file according to the scene risk level to form a risk scene library;
and the analysis and evaluation module is used for adjusting the risk coping capability estimators of the tested vehicle by using the risk scenes of different levels to obtain the final risk coping capability of the tested vehicle.
Optionally, the database establishing module includes a target detecting and classifying unit, a lane line detecting unit, a structured information calculating unit, a risk measuring unit and a standard format scene forming unit, which are connected in sequence;
the target detection and classification unit is used for acquiring information of each traffic entity in any frame of image in the risk scene slice;
the lane line detection unit is used for acquiring road linear topological information;
the structured information calculation unit is used for acquiring the position and the projection speed of the traffic entity on the lane by combining the road linear topological information;
the risk measurement unit is used for calculating the maximum value of the risk measurement of each traffic entity in the main vehicle and the image as the risk measurement of the scene;
and the standard format scene forming unit is used for forming standard format scenes and storing the standard format scenes by using XML or Json format.
Optionally, the main reference of the risk measure in the risk measure unit is Time To Collision (TTC), and the calculation formula of the time to collision is as follows:
wherein x isc(t) is a workshop relativeDistance, vc(t) is the relative speed of the workshop, TTC is the time to collision, and higher TTC indicates lower risk of the workshop, i.e. lower risk measure; a lower TTC indicates a higher risk to the workshop, i.e. a higher risk measure; and when the calculation condition is not met or the calculation result of the TTC is a negative value, no collision risk exists, namely the risk measure is the minimum value.
According to the technical scheme, compared with the prior art, the invention provides the intelligent network vehicle-oriented in-the-environment scene-oriented self-adaptive evaluation test method and system, wherein the method comprises the following steps: the subsequent scene is adjusted according to the real-time test result of the vehicle, and the virtual test and the real test are combined, so that the test cost is effectively reduced, and the test safety and accuracy are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method for testing environment-oriented self-adaptive evaluation of an intelligent networked vehicle in the invention;
FIG. 2 is a schematic diagram illustrating a process of extracting risk scene slices using a deep neural network according to the present invention;
FIG. 3 is a flow chart of database building steps of the present invention;
FIG. 4 is a flow chart of the analytical evaluation procedure of the present invention;
FIG. 5 is a structural block diagram of an intelligent network-connected vehicle-oriented environment-oriented self-adaptive evaluation testing system;
FIG. 6 is a block diagram of a database building module according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the invention discloses an intelligent network-connected vehicle-oriented in-the-loop scene oriented self-adaptive evaluation testing method, which comprises the following steps:
a data acquisition step: extracting risk scene slices from the video data by using a deep neural network;
a database establishing step: extracting traffic scene information from the risk scene slices, determining the scene risk level, and establishing a scene description file according to the scene risk level to form a risk scene library;
and (3) an analysis step: and adjusting the risk coping capability estimators of the tested vehicle by using the risk scenes of different levels to obtain the final risk coping capability of the tested vehicle.
In a specific embodiment, referring to fig. 2, a process diagram of data acquisition is disclosed, wherein the specific content of the data acquisition step includes: the method comprises the steps of training a deep neural network through marked automatic driving risk scene data, automatically identifying a risk scene in a video data set by utilizing the neural network, and outputting a risk scene slice with preset continuous video frame numbers, wherein the preset continuous video frame numbers are artificial customization parameters and can be adjusted according to the size and frame rate condition of a data set.
The video data is a video clip of a traffic scene which is easy to happen and hard to meet.
In a specific embodiment, referring to fig. 3, a flow chart of database establishing steps is disclosed, wherein the specific contents of the database establishing steps include: any frame of image in the risk scene slice is extracted, and after target detection and classification, lane line detection, structured information calculation, risk measurement and standard format scene formation are carried out in sequence, standard scene storage is carried out, and a risk scene library is formed.
In a specific embodiment, referring to fig. 4, a flowchart of analyzing and evaluating steps is disclosed, wherein the specific content of the analyzing step includes: based on quiltThe measured vehicle state and the prior risk coping capability estimators trigger corresponding scenes from the risk scene library, and the risk coping capability assessment of the measured vehicle is adjusted according to the response of the measured vehicle to different risk level scenes to obtain the final risk coping capability of the measured vehicle, R in FIG. 4eEstimator R for prior risk response capabilitye，lEstimating a lower bound of an interval, R, for a priori risk response capabilitye，rAnd estimating an upper range for the prior risk response capability, wherein R is the vehicle risk response capability and eps is a small enough positive number.
Referring to fig. 5, the system for the intelligent networked vehicle-oriented environment-oriented self-adaptive evaluation test of the invention applies the method for the intelligent networked vehicle-oriented environment-oriented self-adaptive evaluation test, and comprises a data acquisition module, a database establishment module and an analysis evaluation module which are connected in sequence;
the data acquisition module is used for extracting risk scene slices from the video data by using a deep neural network;
the database establishing module is used for extracting traffic scene information from the risk scene slices, determining the scene risk level, and establishing a scene description file according to the scene risk level to form a risk scene library;
and the analysis and evaluation module is used for adjusting the risk coping capability estimators of the tested vehicle by using the risk scenes of different levels to obtain the final risk coping capability of the tested vehicle.
In a specific embodiment, referring to fig. 6, the database establishing module includes a target detecting and classifying unit, a lane line detecting unit, a structured information calculating unit, a risk measuring unit, and a standard format scene forming unit, which are connected in sequence;
the target detection and classification unit is used for acquiring information of each traffic entity in any frame of image in the risk scene slice;
the lane line detection unit is used for acquiring road linear topological information;
the structured information calculation unit is used for acquiring the position and the projection speed of the traffic entity on the lane by combining the road linear topological information;
the risk measurement unit is used for calculating the maximum value of the risk measurement of each traffic entity in the main vehicle and the image as the risk measurement of the scene;
and the standard format scene forming unit is used for forming standard format scenes and storing the standard format scenes by using XML or Json format.
In one embodiment, the traffic entity information includes the status of vehicles, non-vehicles, and pedestrians (e.g., lane, relative position, relative speed, relative heading angle, vehicle type, vehicle length, width, etc.).
In one embodiment, the primary criterion of the risk measure in the risk measure unit is Time To Collision (TTC), and the TTC calculation formula is as follows:
wherein x isc(t) is the relative distance between cars, vc(t) is the relative speed of the workshop, TTC is the time to collision, and higher TTC indicates lower risk of the workshop, i.e. lower risk measure; a lower TTC indicates a higher risk to the workshop, i.e. a higher risk measure; and when the calculation condition is not met or the calculation result of the TTC is a negative value, no collision risk exists, namely the risk measure is the minimum value.
In another specific embodiment, the vehicle-in-loop intelligent network online evaluation device comprises a collection device, an interaction device and a virtual simulation platform; wherein, collection system: obtaining the accurate position and course angle information of the vehicle through a high-precision positioning system; an interaction device: information is interacted with an intelligent online automatic driving system through TCP/UDP; a virtual simulation platform: the platform has two functions of parallel simulation and adaptive scene generation.
The parallel simulation function of the virtual simulation platform is as follows: acquiring high-precision state information of the tested intelligent internet vehicle through acquisition equipment, generating a corresponding virtual vehicle (ViL vehicle) in a simulation system after map matching and coordinate system conversion, performing corresponding matching work in a risk scene library based on a risk coping capacity estimator of the ViL vehicle and the states of surrounding roads, adding corresponding traffic entities in a scene in a virtual environment after matching is successful, setting the states of all the traffic entities to be consistent with the states of the scene, packaging the traffic entity (non-ViL) information in simulation, sending the information to the tested intelligent internet vehicle through an interaction device, and enabling the tested vehicle to act according to the states of all the traffic entities, and repeating the steps until the simulation is finished.
The self-adaptive scene generation function of the virtual simulation platform comprises the following steps: after the tested vehicle is added, a risk coping estimation interval is initialized, and the risk coping true quantity is continuously approached by using a binary search method.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention in a progressive manner. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. The intelligent networked vehicle-oriented in-the-loop scene oriented self-adaptive evaluation test method is characterized by comprising the following steps of:
a data acquisition step: extracting risk scene slices from the video data by using a deep neural network;
a database establishing step: extracting traffic scene information from the risk scene slices, determining the scene risk level, and establishing a scene description file according to the scene risk level to form a risk scene library;
and (3) an analysis step: and adjusting the risk coping capability estimators of the tested vehicle by using the risk scenes of different levels to obtain the final risk coping capability of the tested vehicle.
2. The intelligent networked vehicle-oriented environment-oriented self-adaptive evaluation testing method according to claim 1, wherein,
the specific content of the data acquisition step comprises the following steps: and training a deep neural network through the marked automatic driving risk scene data, automatically identifying the risk scene in the video data set by using the neural network, and outputting a risk scene slice with preset continuous video frame numbers.
3. The intelligent networked vehicle-oriented environment-oriented self-adaptive evaluation testing method according to claim 1, wherein,
the specific contents of the database establishing step comprise: any frame of image in the risk scene slice is extracted, and after target detection and classification, lane line detection, structured information calculation, risk measurement and standard format scene formation are carried out in sequence, standard scene storage is carried out, and a risk scene library is formed.
4. The intelligent networked vehicle-oriented environment-oriented self-adaptive evaluation testing method according to claim 1, wherein,
the specific content of the analysis step comprises: triggering a corresponding scene from a risk scene library based on the state of the detected vehicle and the prior risk corresponding capacity estimator, and adjusting the risk corresponding capacity evaluation of the detected vehicle according to the response of the detected vehicle to different risk level scenes to obtain the final risk corresponding capacity of the detected vehicle.
5. The intelligent network vehicle-oriented environment-oriented self-adaptive evaluation testing system is characterized in that the intelligent network vehicle-oriented environment-oriented self-adaptive evaluation testing method disclosed by any one of claims 1 to 4 is implemented, and comprises a data acquisition module, a database establishment module and an analysis evaluation module which are sequentially connected;
the data acquisition module is used for extracting risk scene slices from the video data by using a deep neural network;
the database establishing module is used for extracting traffic scene information from the risk scene slices, determining the scene risk level, and establishing a scene description file according to the scene risk level to form a risk scene library;
and the analysis and evaluation module is used for adjusting the risk coping capability estimators of the tested vehicle by using the risk scenes of different levels to obtain the final risk coping capability of the tested vehicle.
6. The intelligent networked vehicle-oriented environment-oriented adaptive evaluation testing system according to claim 5,
the database establishing module comprises a target detecting and classifying unit, a lane line detecting unit, a structured information calculating unit, a risk measuring unit and a standard format scene forming unit which are sequentially connected;
the target detection and classification unit is used for acquiring information of each traffic entity in any frame of image in the risk scene slice;
the lane line detection unit is used for acquiring road linear topological information;
the structured information calculation unit is used for acquiring the position and the projection speed of the traffic entity on the lane by combining the road linear topological information;
the risk measurement unit is used for calculating the maximum value of the risk measurement of each traffic entity in the main vehicle and the image as the risk measurement of the scene;
and the standard format scene forming unit is used for forming standard format scenes and storing the standard format scenes by using XML or Json format.
7. The intelligent networked vehicle-oriented environment-oriented adaptive evaluation testing system according to claim 6,
the main benchmark of the risk measurement in the risk measurement unit is the distance collision time, and the calculation formula of the distance collision time is as follows:
wherein x isc(t) is the relative distance between cars, vcAnd (t) is the relative speed of the workshop.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111435477.9A CN114112435A (en) | 2021-11-29 | 2021-11-29 | Intelligent internet vehicle-oriented in-loop scene oriented self-adaptive evaluation test method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111435477.9A CN114112435A (en) | 2021-11-29 | 2021-11-29 | Intelligent internet vehicle-oriented in-loop scene oriented self-adaptive evaluation test method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114112435A true CN114112435A (en) | 2022-03-01 |
Family
ID=80371477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111435477.9A Pending CN114112435A (en) | 2021-11-29 | 2021-11-29 | Intelligent internet vehicle-oriented in-loop scene oriented self-adaptive evaluation test method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114112435A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114647582A (en) * | 2022-03-24 | 2022-06-21 | 重庆长安汽车股份有限公司 | Automatic driving scene generation method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657355A (en) * | 2018-12-20 | 2019-04-19 | 安徽江淮汽车集团股份有限公司 | A kind of emulation mode and system of road vehicle virtual scene |
| CN109765060A (en) * | 2018-12-29 | 2019-05-17 | 同济大学 | A kind of automatic driving vehicle traffic coordinating virtual test system and method |
| CN110781578A (en) * | 2019-09-23 | 2020-02-11 | 同济大学 | Intelligent network connection algorithm testing and evaluating method based on accident scene |
| CN111310302A (en) * | 2020-01-16 | 2020-06-19 | 中国信息通信研究院 | Test scene generation method and device |
| CN112015164A (en) * | 2020-08-24 | 2020-12-01 | 苏州星越智能科技有限公司 | Intelligent networking automobile complex test scene implementation system based on digital twin |
| CN113535569A (en) * | 2021-07-22 | 2021-10-22 | 中国第一汽车股份有限公司 | Control effect determination method for automatic driving |
-
2021
- 2021-11-29 CN CN202111435477.9A patent/CN114112435A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657355A (en) * | 2018-12-20 | 2019-04-19 | 安徽江淮汽车集团股份有限公司 | A kind of emulation mode and system of road vehicle virtual scene |
| CN109765060A (en) * | 2018-12-29 | 2019-05-17 | 同济大学 | A kind of automatic driving vehicle traffic coordinating virtual test system and method |
| CN110781578A (en) * | 2019-09-23 | 2020-02-11 | 同济大学 | Intelligent network connection algorithm testing and evaluating method based on accident scene |
| CN111310302A (en) * | 2020-01-16 | 2020-06-19 | 中国信息通信研究院 | Test scene generation method and device |
| CN112015164A (en) * | 2020-08-24 | 2020-12-01 | 苏州星越智能科技有限公司 | Intelligent networking automobile complex test scene implementation system based on digital twin |
| CN113535569A (en) * | 2021-07-22 | 2021-10-22 | 中国第一汽车股份有限公司 | Control effect determination method for automatic driving |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114647582A (en) * | 2022-03-24 | 2022-06-21 | 重庆长安汽车股份有限公司 | Automatic driving scene generation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11062607B2 (en) | Systems and methods for quantitatively assessing collision risk and severity | |
| CN112700470B (en) | Target detection and track extraction method based on traffic video stream | |
| US11308330B2 (en) | Method and device for constructing autonomous driving test scenes, terminal and readable storage media | |
| CN109087510B (en) | Traffic monitoring method and device | |
| CN108877213B (en) | Traffic accident identification method and system | |
| CN110705458B (en) | Boundary detection method and device | |
| CN111458721B (en) | Exposed garbage identification and positioning method, device and system | |
| CN110728650B (en) | Well lid depression detection method based on intelligent terminal and related equipment | |
| CN109190488B (en) | Front vehicle door opening detection method and device based on deep learning YOLOv3 algorithm | |
| CN111179300A (en) | Method, apparatus, system, device and storage medium for obstacle detection | |
| CN108594244B (en) | Obstacle recognition transfer learning method based on stereoscopic vision and laser radar | |
| CN105608431A (en) | Vehicle number and traffic flow speed based highway congestion detection method | |
| CN115620518B (en) | Intersection traffic conflict judging method based on deep learning | |
| Groh et al. | Simulation and its contribution to evaluate highly automated driving functions | |
| CN112434566B (en) | Passenger flow statistics method and device, electronic equipment and storage medium | |
| CN112163348A (en) | Method and device for detecting road abnormal road surface, simulation method, vehicle and medium | |
| CN114359181A (en) | Intelligent traffic target fusion detection method and system based on image and point cloud | |
| CN114976306A (en) | Intelligent echelon utilization method of power lithium battery based on vehicle-connected cloud | |
| JP2020160840A (en) | Road surface defect detecting apparatus, road surface defect detecting method, road surface defect detecting program | |
| CN114112435A (en) | Intelligent internet vehicle-oriented in-loop scene oriented self-adaptive evaluation test method and system | |
| CN111160132B (en) | Method and device for determining lane where obstacle is located, electronic equipment and storage medium | |
| Krajewski et al. | Using drones as reference sensors for neural-networks-based modeling of automotive perception errors | |
| CN111723672B (en) | Method and device for acquiring video recognition driving track and storage medium | |
| CN111126363B (en) | Object recognition method and device for automatic driving vehicle | |
| CN112699748A (en) | Human-vehicle distance estimation method based on YOLO and RGB image |
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 |