CN113095276A - Method for measuring data complexity of automobile image scene library - Google Patents
Method for measuring data complexity of automobile image scene library Download PDFInfo
- Publication number
- CN113095276A CN113095276A CN202110455537.7A CN202110455537A CN113095276A CN 113095276 A CN113095276 A CN 113095276A CN 202110455537 A CN202110455537 A CN 202110455537A CN 113095276 A CN113095276 A CN 113095276A
- Authority
- CN
- China
- Prior art keywords
- scene
- complexity
- layer
- elements
- traffic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000007613 environmental effect Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 description 9
- 230000008901 benefit Effects 0.000 description 7
- 206010039203 Road traffic accident Diseases 0.000 description 6
- 238000010276 construction Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of automatic driving, and particularly relates to a method for measuring the complexity of data in an automobile image scene library, which comprises the following steps of: s1, layering scene data corresponding to each scene in the scene library according to the scene elements; s2, respectively appointing complexity values for scene elements corresponding to each layered scene; s3, giving scene probability of scene element of each layer of scene; s4, comprehensively calculating the complexity of each layer of scene according to the complexity value and the scene probability of the scene element of each layer of scene; and S5, adding the scene complexity of each layer to obtain the final scene complexity of the scene data. The invention can quantify the quality of scene data in the scene library so as to compare the quality of different scene libraries.
Description
Technical Field
The invention belongs to the technical field of automatic driving, and particularly relates to a method for measuring the complexity of data in an automobile image scene library.
Background
The test and verification of the automatic driving automobile is an indispensable link before the research and development and the marketing of the automatic driving automobile, and a matched test and evaluation system is a necessary condition for promoting the technical development of the automatic driving automobile. The scene library of the real vehicle road test plays a very key role in the intelligent network connection automobile test evaluation system, is the basis and the starting point of the test and the evaluation, and can laterally influence the complexity of the task. To ensure the sufficiency of the test scenario, the scenario library should make automatic driving safer and more reliable than all scenarios encountered by human driving.
Currently, most enterprises and organizations focus on the collection of scene library data in the construction process of the scene library, and appropriate quantitative indexes for the quality of the collected scene data are lacked. This undoubtedly brings about two problems:
1. the scene library may contain a large amount of repeated and low-quality scene data, so that the test time based on the scene library is too long, even the performance defect of the automatic driving automobile cannot be found, and the reliability of the test result is reduced;
2. the superiority and inferiority comparison between different scene libraries cannot be carried out, so that the optimal scene library data cannot be selected in the automatic driving automobile scene library test.
Disclosure of Invention
The invention aims to provide a method for measuring the data complexity of an automobile image scene library, which can quantify the quality of scene data in the scene library so as to compare the quality of different scene libraries.
In order to achieve the above object, a method for measuring the complexity of data in an automobile image scene library is provided, which comprises the following steps:
s1, layering scene data corresponding to each scene in the scene library according to the scene elements;
s2, respectively appointing complexity values for scene elements corresponding to each layered scene;
s3, giving scene probability of scene element of each layer of scene;
s4, comprehensively calculating the complexity of each layer of scene according to the complexity value and the scene probability of the scene element of each layer of scene;
and S5, adding the scene complexity of each layer to obtain the final scene complexity of the scene data.
The principle and the advantages are as follows:
the more complex the scene data, the more challenging the associated system, and the greater the likelihood of detecting performance deficiencies of the associated system. Therefore, the complexity of the scene data can be considered as one of the key factors affecting the quality of the scene library. According to the scheme, the scene data is hierarchically split by utilizing the scene elements so as to reduce the overall complexity of the scene data, and the complexity corresponding to each layer of scene can be obtained by specifying the complexity value and giving the scene probability to the scene elements corresponding to each layer of scene. And then, the complexity corresponding to each layer of scene is accumulated and calculated, so that the complexity of each scene can be quantized, and by analogy, the complexity of different scene libraries can be quantized, thereby facilitating the comparison of the advantages and disadvantages of the different scene libraries.
Further, the scene elements comprise road elements, traffic facility elements, temporary traffic event elements, traffic participant elements, environmental condition elements and information elements, and each layered scene is a road layer, a traffic facility layer, a temporary traffic event layer, a traffic participant layer, an environmental condition layer and an information layer.
The setting of road elements, traffic facility elements, temporary traffic event elements, traffic participant elements, environmental condition elements and information elements can split complex scene data, reduce the complexity to a certain extent, and further perform subsequent complexity quantitative calculation.
Further, the complexity of the road element is selected and set according to the visibility degree of the lane line, the complexity of the traffic facility element is selected and set according to the visibility degree of the traffic facility, the complexity of the temporary traffic event element is selected and set according to the contingency and predictability of the event, the complexity of the traffic participant element is selected and set according to the commonalities and the compliance of the participants, the complexity of the environmental condition element is selected and set according to the visibility of the environment, and the complexity of the information element is set according to the existence or nonexistence of traffic information.
So as to facilitate the selection and arrangement of road elements, traffic facility elements, temporary traffic event elements, traffic participant elements, environmental condition elements and information elements.
Further, the scene probability is set according to the occurrence frequency of scene elements in the scene.
The scene probability is selected so as to be suitable for the real scene, thereby ensuring that the complexity of subsequent acquisition has more referential significance.
Further, in step S5, the final scene complexity is calculated as follows:
wherein C is the final scene complexity of the scene data, Ci is the complexity of the ith layer of scene element, and Pi is the scene probability of the ith layer of scene element occurring when the relevant system operates.
The complexity of each scene is convenient to quantify, so that the complexity of the scene library is convenient to quantify, and the advantages and the disadvantages of different scene libraries are convenient to compare.
Drawings
Fig. 1 is a flowchart of a method for measuring complexity of data in an automobile image scene library according to an embodiment of the present invention;
fig. 2 is an example diagram of a scene.
Detailed Description
The following is further detailed by way of specific embodiments:
example one
A method for measuring the complexity of data in an automobile image scene library is basically as shown in the accompanying figure 1: the method comprises the following steps:
s1, layering scene data corresponding to each scene in the scene library according to the scene elements; the scene elements are road elements, traffic facility elements, temporary traffic events, traffic participants, environmental conditions and information elements, and each layered scene is a road layer, a traffic facility layer, a temporary traffic events layer, a traffic participants layer, an environmental conditions layer and an information layer.
A first layer: the road layer, the road element includes protecting the geometry and topological structure of the road, etc.;
a second layer: the traffic facility layer comprises traffic signs, traffic signal lamps and the like;
and a third layer: the temporary traffic incident layer comprises the elements of traffic accidents, road construction, traffic control and the like;
a fourth layer: the traffic participant layer comprises movable and interactive dynamic elements such as pedestrians, vehicles, motorcycles and the like;
and a fifth layer: the environmental condition layer, the environmental condition key element includes weather, electromagnetic intensity and night, etc.;
a sixth layer: the information layer, the information elements include V2X information, high precision maps, and the like.
S2, respectively appointing complexity values for scene elements corresponding to each layered scene;
the first layer, the complexity on road layer is mainly selected by the visibility degree of lane line and is set up:
for example, for a clear lane line, its complexity is specified as 1;
the identification of the lane line can be influenced by the shielded or worn lane line, and the complexity is 2;
the accumulated water and ice on the road surface affect the identification of lane lines and cause difficulty in driving, and the complexity is 3;
the irregular lane lines can cause the lane lines to be recognized wrongly, so that the driving direction of the vehicle is wrong, and the complexity is 4;
the lane-free scene may affect the driving direction of the vehicle, and the complexity is 5.
And on the second layer, the complexity of the traffic facility layer is mainly selected and set by the visibility degree of the traffic facility:
for example: a scene without transportation facilities, the complexity of which is 1;
a scene with clear traffic facilities, the complexity of which is 2;
scenes which cannot be clearly identified due to too long distance of traffic facilities and the like are 3 in complexity;
scenes which are difficult to identify due to reflection, dirt and the like of traffic facilities have the complexity of 4;
traffic facilities are irregular, false identification can be caused, dangerous behaviors such as vehicles running red light can be caused, and the complexity is 5.
The third layer, the complexity of the temporary traffic event layer is mainly set by the contingency and predictability of its events:
for example: no temporary traffic incident, with a complexity of 1;
traffic control and other temporary traffic events with special personnel maintaining the site, wherein the complexity is 2;
the complexity of temporary traffic events with warning signs such as road construction is 3;
temporary traffic incidents such as traffic accidents and the like which have great influence on driving have the complexity of 4;
temporary traffic incidents such as falling rocks and falling wheels which are sporadically strong and difficult to predict have the complexity of 5;
and the complexity of the traffic participant layer is set according to the commonalities and the compliance of the participants:
for example: no traffic participant, with a complexity of 1;
a scene containing only vehicles, with a complexity of 2;
including pedestrians, bicycles and other common participants, and located in the regulated positions (such as sidewalks, bicycle lanes and the like), with the complexity of 3;
including pedestrians, bicycle lights, etc. and they are not located in the legal place (pedestrians cross the road, bicycles travel on motorways, etc.), with a complexity of 4;
unusual traffic participants (e.g., elephant-towing trucks, horse-riding pedestrians, etc.) have a complexity of 5.
Fifth, the complexity of the ambient condition layer is mainly set by the visibility:
for example: high visibility in sunny days, the complexity is 1;
visibility in rainy, evening days, with a complexity of 2;
at night, the environment is lighted, and the complexity is 3;
at night, no ambient light exists, the visibility is low, and the complexity is 4;
the visibility in foggy days is extremely low, and the complexity is 5.
Sixth layer, the complexity of the information layer is mainly set by whether there is traffic information:
for example: if a high-precision map or V2X provides traffic information, the complexity is 1;
without a high precision map or V2X providing traffic information, the complexity is 2.
S3, giving scene probability of scene element of each layer of scene; the scene probability is set according to the frequency of scene elements in the scene. For example: the system is only used on the expressway, and the probability coefficient of only containing vehicles appearing in the traffic participant layer is greater than the probability coefficient of pedestrians and bicycles; for a system that can be used in urban traffic scenarios, the probability coefficient for the presence of pedestrians, bicycles in the traffic participant layer is greater than the probability coefficient for vehicles alone.
S4, comprehensively calculating the complexity of each layer of scene according to the complexity value and the scene probability of the scene element of each layer of scene;
and S5, adding the scene complexity of each layer to obtain the final scene complexity of the scene data.
The final scene complexity calculation formula is as follows:
wherein C is the final scene complexity of the scene data, Ci is the complexity of the ith layer of scene element, and Pi is the scene probability of the ith layer of scene element occurring when the relevant system operates.
The specific implementation process is as follows:
as shown in fig. 2, (1) scene element is layered:
a first layer: and (3) road layer: freeways, three lanes, straight lanes;
a second layer: a traffic facility layer: a traffic sign is arranged 50m on the right side of the road;
and a third layer: temporary traffic event layer: the traffic accident happens 50m right ahead of the road, and affects the current driving lane;
a fourth layer: traffic participant layer: accident trucks, rescue personnel;
and a fifth layer: environmental condition layer: on sunny days, the illumination intensity is 50000 lux;
a sixth layer: information layer: no V2X and high precision maps.
(2) Complexity of scene elements per layer
A first layer: in the road layer, the lane lines are clear, and the complexity value is 1;
a second layer: the traffic facility layer is clear in traffic facilities, and the complexity value is 2;
and a third layer: a temporary traffic incident layer, a traffic accident, with a complexity value of 4;
a fourth layer: the traffic participant layer comprises common participants such as pedestrians and bicycles and is in an unreasonable position. E.g., road center, complexity value of 4;
and a fifth layer: the environmental condition layer is on sunny days, and the complexity value is 1;
a sixth layer: an information layer without a high-precision map or V2X, with a complexity value of 2;
(3) scene probability
A first layer: the road layer is clear in lane lines and high in probability, and the probability value is 90%;
a second layer: the traffic facility layer is clear in traffic facilities and high-probability events, and the probability value is 90%;
and a third layer: in the temporary traffic event layer, traffic accidents occur 50m right ahead of a road, influence the current driving lane, and are low-probability events, wherein the probability value is 5%;
a fourth layer: a traffic participant layer, an accident truck, a rescue worker and a low-probability event, wherein the probability value is 5%;
and a fifth layer: an environmental condition layer, a sunny day, illumination intensity of 50000 lux, a medium probability event, and a probability value of 70%;
a sixth layer: an information layer without V2X and a high-precision map, a high-probability event, and a probability value of 90%;
(4) final scene complexity value C
C＝1*90％+2*90％+4*5％+4*5％+1*70％+2*90％＝5.6。
Example two
Automatic driving frees the driver's hands completely, so that the driver does not need to pay attention to the current road conditions all the time. However, drivers still need to be configured in the cab, because the current automatic driving can only assist in sensing the road condition information, the cab is not completely automatic driving, and the reliability of the cab cannot completely replace the drivers, especially in the case of complex road condition environments.
The difference between the second embodiment and the first embodiment is that the method further comprises the following steps:
and S6, setting manual intervention thresholds for the layered road layer, the layered traffic facility layer, the layered temporary traffic incident layer and the layered traffic participant layer respectively, wherein the manual intervention thresholds are specifically set according to the complexity value of each layer of scene, the complementary value of the probability value and the weight proportion of the layered scene.
For example, on the road layer, on the suburban and rural sections, the lane line is fuzzy, the complexity value is 4, the probability value is 50%, and the weight proportion is 20%. The manual intervention threshold M-4 (1-50%) 20% -0.4.
In the traffic facility layer, traffic facilities are unclear, the complexity value is 3, the probability value is 50% and the weight proportion is 20% of medium probability events; the manual intervention threshold M-3 (1-50%) 20% -0.3.
In the temporary traffic event layer, traffic accidents occur 50m right ahead of a road, influence the current driving lane, the complexity value is 4, low probability events are carried out, the probability value is 5%, and the weight proportion is 40%; the manual intervention threshold M is 4 (1-5%) 40% ═ 1.52.
The complexity value of a traffic participant layer, an accident truck and rescue personnel is 4, the probability value of a low-probability event is 5%, and the weight proportion is 30%. The manual intervention threshold M-4 (1-5%) 20% -0.76.
S7, comparing and analyzing manual intervention thresholds respectively corresponding to a road layer, a traffic facility layer, a temporary traffic incident layer and a traffic participant layer with judgment thresholds corresponding to the layers, and if the manual intervention thresholds corresponding to the layers exceed the corresponding judgment thresholds, generating control mode switching prompt information for switching from automatic control to manual control; the scheme analyzes whether the current automatic driving needs manual intervention by a driver or not by judging whether the manual intervention threshold exceeds the corresponding judgment threshold or not, so that subsequent driving mode switching prompt is carried out. The subjective analysis of people can better fit own benefits compared with artificial intelligence, and the subjective analysis is hopeful to realize safety and benefit loss-free consideration, which is far different from the excessive intelligence management of a machine implementing the principle of first benefit and second benefit. Therefore, through the judgment, the comparative analysis and the warning prompt of the scheme, the driver is allowed to intervene in driving, so that accidents can be avoided to a certain degree, and meanwhile, the driver is more in good interest.
S8, respectively carrying out accumulation calculation on manual intervention thresholds corresponding to the road layer, the traffic facility layer, the temporary traffic incident layer and the traffic participant layer to obtain a manual intervention total threshold; and setting a weight ratio between the total manual intervention threshold value and the final scene complexity value C for comprehensive calculation to obtain a comprehensive scene complexity value C'. In a road layer, a traffic facility layer, a temporary traffic event layer and a traffic participant layer, uncontrollable factors are more, so that the situations that manual intervention is needed for automatic driving are more, the scheme sets a weight ratio of a total manual intervention threshold value and a final scene complexity value C to perform comprehensive calculation to obtain a comprehensive scene complexity value C', the quality of scene data can be improved, and the quality of the scene data is quantized so as to compare the quality of different scene libraries.
The foregoing is merely an example of the present invention, and common general knowledge in the field of known specific structures and characteristics is described herein in more detail, so that a person of ordinary skill in the art can understand all the prior art in the field and have the ability to apply routine experimentation before the present date, after knowing that all the common general knowledge in the field of the invention before the application date or the priority date of the invention, and the person of ordinary skill in the art can, in light of the teaching provided herein, combine his or her own abilities to complete and implement the present invention, and some typical known structures or known methods should not become an obstacle to the implementation of the present invention. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (5)
1. A method for measuring the complexity of data in an automobile image scene library is characterized by comprising the following steps: the method comprises the following steps:
s1, layering scene data corresponding to each scene in the scene library according to the scene elements;
s2, respectively appointing complexity values for scene elements corresponding to each layered scene;
s3, giving scene probability of scene element of each layer of scene;
s4, comprehensively calculating the complexity of each layer of scene according to the complexity value and the scene probability of the scene element of each layer of scene;
and S5, adding the scene complexity of each layer to obtain the final scene complexity of the scene data.
2. The method for measuring the complexity of the data in the automobile image scene library according to claim 1, wherein the method comprises the following steps: the scene elements comprise road elements, traffic facility elements, temporary traffic incident elements, traffic participant elements, environmental condition elements and information elements, and each layered scene is a road layer, a traffic facility layer, a temporary traffic incident layer, a traffic participant layer, an environmental condition layer and an information layer.
3. The method for measuring the complexity of the data in the automobile image scene library according to claim 2, wherein the method comprises the following steps: the complexity of the road elements is selected and set according to the visibility degree of the lane lines, the complexity of the traffic facility elements is selected and set according to the visibility degree of the traffic facilities, the complexity of the temporary traffic event elements is selected and set according to the contingency and predictability of events, the complexity of the traffic participant elements is selected and set according to the commonalities and the compliance of participants, the complexity of the environmental condition elements is selected and set according to the visibility of the environment, and the complexity of the information elements is set according to whether traffic information exists or not.
4. The method for measuring the complexity of the data in the automobile image scene library according to claim 3, wherein the method comprises the following steps: the scene probability is set according to the frequency of scene elements in the scene.
5. The method for measuring the complexity of the data in the automobile image scene library according to claim 4, wherein the method comprises the following steps: in step S5, the final scene complexity calculation formula is as follows:
wherein C is the final scene complexity of the scene data, Ci is the complexity of the ith layer of scene element, and Pi is the scene probability of the ith layer of scene element occurring when the relevant system operates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110455537.7A CN113095276A (en) | 2021-04-26 | 2021-04-26 | Method for measuring data complexity of automobile image scene library |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110455537.7A CN113095276A (en) | 2021-04-26 | 2021-04-26 | Method for measuring data complexity of automobile image scene library |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113095276A true CN113095276A (en) | 2021-07-09 |
Family
ID=76680116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110455537.7A Pending CN113095276A (en) | 2021-04-26 | 2021-04-26 | Method for measuring data complexity of automobile image scene library |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113095276A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108765235A (en) * | 2018-05-09 | 2018-11-06 | 公安部交通管理科学研究所 | Automatic driving vehicle test scene construction method and test method based on the destructing of traffic accident case |
| CN111178402A (en) * | 2019-12-13 | 2020-05-19 | 赛迪检测认证中心有限公司 | Scene classification method and device for road test of automatic driving vehicle |
| CN112465395A (en) * | 2020-12-15 | 2021-03-09 | 同济大学 | Multi-dimensional comprehensive evaluation method and device for automatically-driven automobile |
-
2021
- 2021-04-26 CN CN202110455537.7A patent/CN113095276A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108765235A (en) * | 2018-05-09 | 2018-11-06 | 公安部交通管理科学研究所 | Automatic driving vehicle test scene construction method and test method based on the destructing of traffic accident case |
| CN111178402A (en) * | 2019-12-13 | 2020-05-19 | 赛迪检测认证中心有限公司 | Scene classification method and device for road test of automatic driving vehicle |
| CN112465395A (en) * | 2020-12-15 | 2021-03-09 | 同济大学 | Multi-dimensional comprehensive evaluation method and device for automatically-driven automobile |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Akin et al. | A neural network (NN) model to predict intersection crashes based upon driver, vehicle and roadway surface characteristics | |
| CN113034952B (en) | Road traffic safety real-time early warning system based on vehicle-road cooperation | |
| CN108648490B (en) | Method for testing speed limit information response capability of automatic driving automobile | |
| CN113065685B (en) | High-precision map traffic rule model based on automatic driving application scene and implementation method thereof | |
| CN114241777A (en) | Multi-source heterogeneous networking road condition monitoring early warning system and method | |
| Richter et al. | Turning accidents between cars and trucks and cyclists driving straight ahead | |
| Scholliers et al. | Improving safety and mobility of Vulnerable Road Users through ITS applications | |
| Santhosh et al. | Evaluation of pedestrian safety in unsignalized T and X–Intersections through comparison of the frequency and severity of pedestrian conflicts | |
| CN114550445A (en) | Urban area traffic safety state evaluation method and device | |
| Sun et al. | A hybrid approach of random forest and random parameters logit model of injury severity modeling of vulnerable road users involved crashes | |
| Wang et al. | Multipattern road traffic crashes and injuries: a case study of Xi’an city | |
| Sun et al. | Impact of edge lines on safety of rural two-lane highways. | |
| CN113095276A (en) | Method for measuring data complexity of automobile image scene library | |
| CN116307699A (en) | Road hidden trouble point segment grading method, device and storage medium based on multi-source data | |
| Taheri et al. | Spatial‐Temporal Analysis of Crash Severity: Multisource Data Fusion Approach | |
| Qidong et al. | The research on the identification of ACC SOTIF triggering conditions based on scenario analysis | |
| Mostafi et al. | A Novel Predictive Modelling Approach Towards a Spatiotemporal Traffic Safety Index | |
| Sisiopiku et al. | Analysis of Crash Causes, Costs, and Countermeasures in Alabama Work Zones | |
| RU2774261C1 (en) | Method for controlling the movement of vehicles with driver assistance systems in the environment "intelligent transport system - vehicle - driver" | |
| CN110097765B (en) | Motor vehicle signal lamp removal judgment method suitable for highway level crossing | |
| Xiao et al. | Intelligent early warning system of operation risk of bridge-tunnel transition section | |
| JP2024069132A (en) | Autonomous driving safety system and autonomous driving control method sharing driving design domain based on risk level | |
| KR20240070141A (en) | Methods for managing and analyzing traffic conditions | |
| Sarabi et al. | Introducing the main factors of accidents on the roads of Iran and studying its causes and strategies applied to decrease it | |
| Dixon et al. | Highway Safety Investigation Manual for the Oregon Department of Transportation |
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 |