CN114333101A - Vehicle data processing method - Google Patents
Vehicle data processing method Download PDFInfo
- Publication number
- CN114333101A CN114333101A CN202111561591.6A CN202111561591A CN114333101A CN 114333101 A CN114333101 A CN 114333101A CN 202111561591 A CN202111561591 A CN 202111561591A CN 114333101 A CN114333101 A CN 114333101A
- Authority
- CN
- China
- Prior art keywords
- scene
- basic
- vehicle data
- vehicle
- basic trigger
- 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
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vehicle data processing method, wherein a plurality of basic triggers are deployed at a vehicle end; the method comprises the following steps: when the vehicle end runs to a set scene to cause at least one basic trigger to be triggered, inquiring scene deployment information; the vehicle end evaluates the condition of the vehicle data acquired in the set scene according to the scene deployment information, and uploads the vehicle data and the calling state information of the basic trigger to a cloud end when the data uploading condition is met; the cloud end classifies the vehicle data in a scene library according to the scene deployment information; according to the method and the device, the basic trigger is deployed at the vehicle end, the vehicle data uploading and the automatic classification of the cloud are triggered based on the calling triggering condition of the basic trigger, a data acquisition mode that the vehicle end and the cloud are combined is realized, and compared with a mode that all data are uploaded to the cloud by a vehicle in the prior art, the method and the device can effectively reduce the burden of the vehicle end and improve the flexibility of data acquisition.
Description
Technical Field
The invention relates to the technical field of vehicle data acquisition, in particular to a vehicle data processing method.
Background
With the rapid development of automobile intellectualization, the automatic driving of the automobile is more and more concerned. However, the existing automatic driving of the automobile still has great potential safety hazard and low reliability. And the automobile data acquisition can provide a large amount of data support for the automatic driving technology, and has a vital influence on the reliability and safety of automatic driving. At present, data collection of a vehicle is generally divided into two stages, one is that the vehicle stores data generated by the vehicle in a local hard disk, and the other is that the local hard disk of the vehicle is uploaded to a server periodically. However, the existing vehicle data acquisition mode is to generally store and upload all data generated by the vehicle to the server, so that on one hand, the burden of vehicle data acquisition is large, on the other hand, scene discrimination on the vehicle data cannot be performed, and the flexibility of data acquisition is low.
Disclosure of Invention
The embodiment of the invention provides a vehicle data processing method which can reduce the burden of a vehicle end and improve the flexibility of data acquisition.
An embodiment of the invention provides a vehicle data processing method, wherein a plurality of basic triggers are deployed at a vehicle end; the method comprises the following steps:
when the vehicle end runs to a set scene to cause at least one basic trigger to be triggered, inquiring scene deployment information;
the vehicle end evaluates the condition of the vehicle data acquired in the set scene according to the scene deployment information, and uploads the vehicle data and the calling state information of the basic trigger to a cloud end when the data uploading condition is met;
and the cloud end classifies the vehicle data in a scene library according to the scene deployment information.
As an improvement of the above solution, the evaluating, by the vehicle end, the condition of the vehicle data acquired in the set scene according to the scene deployment information includes:
the vehicle end scores the vehicle data acquired under the set scene according to the scene deployment information;
and when the score of the vehicle data is larger than a preset threshold value, determining that a data uploading condition is met.
As an improvement of the above scheme, a plurality of the basic triggers form a plurality of basic trigger groups; the scene deployment information carries the calling state of the basic triggers in each basic trigger group;
then, the vehicle end scoring the vehicle data acquired in the set scene according to the scene deployment information includes:
the vehicle end determines the triggering quantity of the called basic triggers in each basic trigger group according to the scene deployment information;
and the vehicle end scores the vehicle data according to the triggering quantity of the called basic triggers in each basic trigger group and the preset weight corresponding to the basic trigger group.
As an improvement of the above solution, the scoring the vehicle data according to the triggering number of the basic triggers called in each basic trigger group and the preset weight corresponding to the basic trigger group includes:
according to the formula Q ═ Σ wj·xjCalculating a total score for the vehicle data;
wherein, wjA predetermined weight, x, representing the jth group of elementary triggersjRepresenting the triggering quantity of the called basic triggers in the jth basic trigger group;
and carrying out normalization processing on the total score of the vehicle data to obtain the score of the vehicle data.
As an improvement of the above scheme, the cloud is deployed with a scene library classifier and a plurality of scene libraries;
then, the cloud performs scene library classification on the vehicle data according to the scene deployment information, including:
the cloud sends the received scene deployment information and the vehicle data to the scene library classifier;
the scene library classifier inquires the calling state of the basic trigger in each basic trigger group according to the scene deployment information;
and the scene library classifier classifies the vehicle data into a corresponding scene library according to the calling state of the basic trigger in each basic trigger group.
As an improvement of the above scheme, the scene deployment information includes a character string of each of the basic trigger groups; and one bit of character in the character string of each basic trigger group corresponds to the calling state of one basic trigger.
As an improvement of the scheme, the character string is a binary code.
As an improvement of the above scheme, the vehicle end is provided with a plurality of high-order scene triggers, and each high-order scene trigger corresponds to one scene;
the method further comprises the following steps:
when the vehicle end runs to a set scene, calling and triggering the basic triggers in each basic trigger group according to scene deployment information corresponding to the set scene;
and the scene deployment information is determined according to the basic triggers which need to be called in each basic trigger group by the corresponding high-order scene triggers.
As an improvement of the above, the method further comprises:
and the vehicle end acquires vehicle data from a first set time before the triggering of the basic trigger to a second set time after the triggering.
As an improvement of the above scheme, the basic trigger group includes: the system comprises a sensing module basic trigger group, a positioning module basic trigger group, a planning module basic trigger group, a control module basic trigger group and a vehicle-road cooperation module basic trigger group.
As an improvement of the above scheme, the querying, by the scene library classifier, the call state of the basic trigger in each basic trigger group according to the scene deployment information includes:
the scene library classifier inquires the state of each bit code element of the binary code of each basic trigger group in the scene deployment information;
when the state of the ith bit code element of the binary code of the basic trigger group is 1, determining that the basic trigger corresponding to the ith bit code element in the basic trigger group is called;
when the state of the ith bit code element of the binary code of the basic trigger group is 0, determining that the basic trigger corresponding to the jth bit code element in the basic trigger group is not called; wherein j is 1, 2.. times.n; n represents the number of base flip-flops in the corresponding base flip-flop group.
Compared with the prior art, the embodiment of the invention has the beneficial effects that: a plurality of basic triggers are deployed at a vehicle end; when the vehicle end runs to a set scene to trigger at least one basic trigger, inquiring scene deployment information, then evaluating the condition of vehicle data acquired in the set scene according to the scene deployment information, and uploading the vehicle data and the calling state information of the basic triggers to a cloud end when a data uploading condition is met; the cloud end classifies the vehicle data in a scene library according to the scene deployment information; according to the embodiment of the invention, the basic trigger is deployed at the vehicle end, and the vehicle data uploading and the automatic classification of the cloud are triggered based on the calling triggering condition of the basic trigger, so that a data acquisition mode combining the vehicle end and the cloud is realized.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a vehicle data processing method provided by an embodiment of the invention;
fig. 2 is a schematic layout diagram of a trigger library according to an embodiment of 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, a schematic flow chart of a vehicle data processing method according to an embodiment of the present invention is shown, where a plurality of basic triggers are deployed at a vehicle end; the method comprises the following steps:
s11: when the vehicle end runs to a set scene to cause at least one basic trigger to be triggered, inquiring scene deployment information;
for example, the setting scene may be an APA parking scene, a low speed/high speed road condition scene, an avoidance scene, an intersection scene, and the like. A high-order scene trigger can be formed through different combination modes of the basic triggers, wherein each setting scene is correspondingly provided with the high-order scene trigger. The scene deployment information records basic triggers which need to be called corresponding to the set scene, and can be preset and stored in the local vehicle end so as to inquire the calling state of the subsequent basic triggers.
In the embodiment of the invention, different combinations are carried out based on deployed basic triggers to form high-order scene triggers of different scenes, so that the high-order scene triggers are used for dealing with various complex automatic driving scenes, a single trigger is not required to be customized for each automatic driving scene, all development tasks are concentrated on the basic triggers, a new high-order scene trigger can be customized in a short time when a new basic trigger is not required to be added, and the development efficiency is improved; meanwhile, all the high-order scene triggers are only related to the basic triggers, and the vehicle end only needs to deploy the basic triggers, so that the resource consumption of the vehicle end can be reduced to a certain extent.
S12: the vehicle end evaluates the condition of the vehicle data acquired in the set scene according to the scene deployment information, and uploads the vehicle data and the calling state information of the basic trigger to a cloud end when the data uploading condition is met;
further, the method further comprises:
and the vehicle end acquires vehicle data from a first set time before the triggering of the basic trigger to a second set time after the triggering.
For example, the vehicle end collects vehicle data within 10s before and after the trigger is triggered.
S13: and the cloud end classifies the vehicle data in a scene library according to the scene deployment information.
Further, a scene library classifier and a plurality of scene libraries are deployed at the cloud end;
then, the cloud performs scene library classification on the vehicle data according to the scene deployment information, including:
the cloud sends the received scene deployment information and the vehicle data to the scene library classifier;
the scene library classifier inquires the calling state of the basic trigger in each basic trigger group according to the scene deployment information;
and the scene library classifier classifies the vehicle data into a corresponding scene library according to the calling state of the basic trigger in each basic trigger group.
In the embodiment of the invention, the basic triggers are deployed at the vehicle end, the vehicle data are triggered to upload to the cloud end based on the calling triggering conditions of the basic triggers, and the cloud end inquires the calling states of the basic triggers in each basic trigger group based on scene deployment information, so that which basic triggers are called by the vehicle data and are automatically classified into the corresponding scene library, the purpose of automatic data classification is achieved, and the complexity of a cloud scene library classifier is reduced; compared with the mode that all data are uploaded to the cloud side by the vehicle in the prior art, the vehicle end burden can be effectively reduced, and the flexibility of data acquisition is improved.
In an optional embodiment, the evaluating, by the vehicle end, the condition of the vehicle data acquired in the set scene according to the scene deployment information includes:
the vehicle end scores the vehicle data acquired under the set scene according to the scene deployment information;
and when the score of the vehicle data is larger than a preset threshold value, determining that a data uploading condition is met.
Illustratively, data uploading is triggered only when the score of the vehicle data is larger than a preset threshold value, otherwise, the data uploading is not triggered, so that low-value vehicle data are prevented from being uploaded to a cloud end, and the quality of the vehicle data acquired by the cloud end is improved.
In an alternative embodiment, a plurality of the basic triggers form a plurality of basic trigger groups; the scene deployment information carries the calling state of the basic triggers in each basic trigger group;
the scene deployment information comprises character strings of the basic trigger groups; and one bit of character in the character string of each basic trigger group corresponds to the calling state of one basic trigger.
Further, the character string is a binary code.
The base trigger group includes: the system comprises a sensing module basic trigger group, a positioning module basic trigger group, a planning module basic trigger group, a control module basic trigger group and a vehicle-road cooperation module basic trigger group.
Furthermore, a plurality of high-order scene triggers are deployed at the vehicle end, and each high-order scene trigger corresponds to one scene;
the method further comprises the following steps:
when the vehicle end runs to a set scene, calling and triggering the basic triggers in each basic trigger group according to scene deployment information corresponding to the set scene;
and the scene deployment information is determined according to the basic triggers which need to be called in each basic trigger group by the corresponding high-order scene triggers.
As shown in fig. 2, the basic triggers deployed at the vehicle end are stored in a basic trigger library and are, for example: sensing, positioning, planning, controlling and vehicle-road cooperation are divided into 5 basic trigger groups, and each basic trigger group comprises various basic triggers under corresponding functional modules, such as GPS signal triggering of a positioning module. Each base trigger group is managed by a specific binary code for managing which base triggers under the corresponding base trigger group need to be invoked. All binary codes are determined according to the basic triggers required to be called by each basic trigger group when the high-order scene triggers are designed in the early stage and are fixed.
Take the example that a certain high-order scene trigger is triggered: querying the binary codes of the basic trigger groups, wherein each basic trigger in each basic trigger cluster has a sequence number, when the binary code of a certain basic trigger group is 100110101, counting from right to left, each number represents whether the basic trigger with the corresponding number in the basic trigger group is called, 1 represents called, and 0 represents not called; for example: 100110101 indicates that the basic triggers numbered 1, 4, 5, 7, and 9 in the basic trigger group are called.
Wherein each base trigger group can be based on
To determine the symbol in which the base trigger P corresponds and then based on
Generating a binary code; wherein f isn(triggerP) generates a function of binary codes, n representing the number of base triggers in the base trigger group.
Then, the vehicle end scoring the vehicle data acquired in the set scene according to the scene deployment information includes:
the vehicle end determines the triggering quantity of the called basic triggers in each basic trigger group according to the scene deployment information;
and the vehicle end scores the vehicle data according to the triggering quantity of the called basic triggers in each basic trigger group and the preset weight corresponding to the basic trigger group.
In an optional embodiment, the scoring the vehicle data according to the triggering number of the basic triggers called in each basic trigger group and the preset weight corresponding to the basic trigger group includes:
according to the formula Q ═ Σ wj·xjCalculating a total score for the vehicle data;
wherein, wjA predetermined weight, x, representing the jth group of elementary triggersjRepresenting the triggering quantity of the called basic triggers in the jth basic trigger group;
and carrying out normalization processing on the total score of the vehicle data to obtain the score of the vehicle data.
The preset weight of each basic trigger group can be calculated according to the proportion of the basic triggers in the corresponding basic trigger group to all basic triggers deployed at the vehicle end. The total score of the vehicle data may be normalized by using a sigmoid function, which is described in the prior art and not described in detail herein.
In an ideal situation, when the vehicle end runs to a set scene, all basic triggers needing to be called in the corresponding high-order scene triggers should be called; however, in a scene, individual basic triggers may not be triggered due to the fact that a real scene is too complex, in order to collect more valuable data as far as possible, the collected vehicle data are scored at the vehicle end, and when the score after normalization is larger than a preset threshold value, the vehicle end triggers a data uploading mechanism. It should be noted that the preset threshold value may be set by a user according to an actual situation in a self-defined manner, for example, set to 0.9. When the vehicle data is scored higher than 0.9, the vehicle data is considered valuable and upload is triggered. By grading the vehicle data, valuable vehicle data can be collected as far as possible, and unnecessary data collection and uploading are reduced.
In an optional embodiment, the querying, by the scene library classifier according to the scene deployment information, the call state of the basic trigger in each basic trigger group includes:
the scene library classifier inquires the state of each bit code element of the binary code of each basic trigger group in the scene deployment information;
when the state of the ith bit code element of the binary code of the basic trigger group is 1, determining that the basic trigger corresponding to the ith bit code element in the basic trigger group is called;
when the state of the ith bit code element of the binary code of the basic trigger group is 0, determining that the basic trigger corresponding to the jth bit code element in the basic trigger group is not called; wherein j is 1, 2.. times.n; n represents the number of base flip-flops in the corresponding base flip-flop group.
In the embodiment of the invention, after the vehicle data is uploaded to the cloud, the scene library classifier in the scene library automatically classifies the uploaded vehicle data according to the calling condition of the basic trigger, for example, the vehicle data is automatically classified into the corresponding scene library according to the sensor category, the scene, the recording duration and the like corresponding to the vehicle data. The same group of vehicle data can be marked by two sets of low-order and high-order scene library systems at the same time, and a large amount of data is provided for developing high-order automatic driving technology in the future.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
1. through deploying the basic trigger at the vehicle end, the automatic classification of vehicle data upload and high in the clouds is triggered based on the calling triggering condition of the basic trigger, the data acquisition mode that the vehicle end and the high in the clouds combine has been realized, compared with the mode that the vehicle generally uploads all data to the high in the clouds among the prior art, the vehicle end burden can be effectively reduced, and data acquisition is improved and is got the flexibility.
2. A single trigger is not required to be customized for each automatic driving scene, all development tasks are concentrated on the basic trigger, and a new high-order scene trigger can be customized in a short time when a new basic trigger is not required to be added, so that the development efficiency is improved.
3. Because all the high-order scene triggers are only related to the basic triggers, the vehicle end only needs to deploy the basic triggers, and the resource consumption of the vehicle end can be reduced to a certain extent.
4. The scene library classifier at the cloud end can automatically classify the vehicle data according to the calling condition of the basic trigger, so that the complexity of the classifier is reduced.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (11)
1. A vehicle data processing method is characterized in that a plurality of basic triggers are deployed at a vehicle end; the method comprises the following steps:
when the vehicle end runs to a set scene to cause at least one basic trigger to be triggered, inquiring scene deployment information;
the vehicle end evaluates the condition of the vehicle data acquired in the set scene according to the scene deployment information, and uploads the vehicle data and the basic trigger calling state information to a cloud end when a data uploading condition is met;
and the cloud end classifies the vehicle data in a scene library according to the scene deployment information.
2. The vehicle data processing method according to claim 1, wherein the vehicle end evaluates the condition of the vehicle data acquired under the set scene according to the scene deployment information, and includes:
the vehicle end scores the vehicle data acquired under the set scene according to the scene deployment information;
and when the score of the vehicle data is larger than a preset threshold value, determining that a data uploading condition is met.
3. The vehicle data processing method according to claim 2, wherein a plurality of the basic triggers constitute a plurality of basic trigger groups; the scene deployment information carries the calling state of the basic triggers in each basic trigger group;
then, the vehicle end scoring the vehicle data acquired in the set scene according to the scene deployment information includes:
the vehicle end determines the triggering quantity of the called basic triggers in each basic trigger group according to the scene deployment information;
and the vehicle end scores the vehicle data according to the triggering quantity of the called basic triggers in each basic trigger group and the preset weight corresponding to the basic trigger group.
4. The vehicle data processing method according to claim 3, wherein the scoring the vehicle data according to the triggering number of the basic triggers called in each basic trigger group and the preset weight corresponding to the basic trigger group comprises:
according to the formula Q ═ Σ wj·xjCalculating a total score for the vehicle data;
wherein, wjA predetermined weight, x, representing the jth group of elementary triggersjRepresenting the triggering quantity of the called basic triggers in the jth basic trigger group;
and carrying out normalization processing on the total score of the vehicle data to obtain the score of the vehicle data.
5. The vehicle data processing method of claim 3, wherein the cloud is deployed with a scene library classifier and a plurality of scene libraries;
then, the cloud performs scene library classification on the vehicle data according to the scene deployment information, including:
the cloud sends the received scene deployment information and the vehicle data to the scene library classifier;
the scene library classifier inquires the calling state of the basic trigger in each basic trigger group according to the scene deployment information;
and the scene library classifier classifies the vehicle data into a corresponding scene library according to the calling state of the basic trigger in each basic trigger group.
6. The vehicle data processing method according to claim 5, wherein the scene deployment information includes a character string of each of the base trigger groups; and one bit of character in the character string of each basic trigger group corresponds to the calling state of one basic trigger.
7. The vehicle data processing method according to claim 6, wherein the character string is a binary code.
8. The vehicle data processing method according to claim 7, wherein a plurality of high-order scene triggers are deployed at the vehicle end, and each high-order scene trigger corresponds to a scene;
the method further comprises the following steps:
when the vehicle end runs to a set scene, calling and triggering the basic triggers in each basic trigger group according to scene deployment information corresponding to the set scene;
and the scene deployment information is determined according to the basic triggers which need to be called in each basic trigger group by the corresponding high-order scene triggers.
9. The vehicle data processing method according to claim 8, characterized by further comprising:
and the vehicle end acquires vehicle data from a first set time before the triggering of the basic trigger to a second set time after the triggering.
10. The vehicle data processing method according to claim 3, wherein the base trigger group includes: the system comprises a sensing module basic trigger group, a positioning module basic trigger group, a planning module basic trigger group, a control module basic trigger group and a vehicle-road cooperation module basic trigger group.
11. The vehicle data processing method according to claim 7, wherein the querying, by the scene library classifier according to the scene deployment information, the calling states of the basic triggers in each of the basic trigger groups includes:
the scene library classifier inquires the state of each bit code element of the binary code of each basic trigger group in the scene deployment information;
when the state of the ith bit code element of the binary code of the basic trigger group is 1, determining that the basic trigger corresponding to the ith bit code element in the basic trigger group is called;
when the state of the ith bit code element of the binary code of the basic trigger group is 0, determining that the basic trigger corresponding to the jth bit code element in the basic trigger group is not called; wherein j is 1, 2.. times.n; n represents the number of base flip-flops in the corresponding base flip-flop group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111561591.6A CN114333101A (en) | 2021-12-20 | 2021-12-20 | Vehicle data processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111561591.6A CN114333101A (en) | 2021-12-20 | 2021-12-20 | Vehicle data processing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114333101A true CN114333101A (en) | 2022-04-12 |
Family
ID=81053057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111561591.6A Pending CN114333101A (en) | 2021-12-20 | 2021-12-20 | Vehicle data processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114333101A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114913620A (en) * | 2022-05-18 | 2022-08-16 | 一汽解放汽车有限公司 | Data extraction method and device, computer equipment and storage medium |
| CN115221151A (en) * | 2022-07-13 | 2022-10-21 | 小米汽车科技有限公司 | Vehicle data transmission method and device, vehicle, storage medium and chip |
-
2021
- 2021-12-20 CN CN202111561591.6A patent/CN114333101A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114913620A (en) * | 2022-05-18 | 2022-08-16 | 一汽解放汽车有限公司 | Data extraction method and device, computer equipment and storage medium |
| CN115221151A (en) * | 2022-07-13 | 2022-10-21 | 小米汽车科技有限公司 | Vehicle data transmission method and device, vehicle, storage medium and chip |
| CN115221151B (en) * | 2022-07-13 | 2024-02-02 | 小米汽车科技有限公司 | Vehicle data transmission method and device, vehicle, storage medium and chip |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114333101A (en) | Vehicle data processing method | |
| WO2021232229A1 (en) | Virtual scene generation method and apparatus, computer device and storage medium | |
| CN102799890A (en) | Image clustering method | |
| CN104239386A (en) | Method and system for prioritizion of facial recognition matches | |
| CN109063790B (en) | Object recognition model optimization method and device and electronic equipment | |
| CN111881966A (en) | Neural network training method, device, equipment and storage medium | |
| CN110322687B (en) | Method and device for determining running state information of target intersection | |
| CN115017742B (en) | Automatic driving test scene generation method, device, equipment and storage medium | |
| CN106155592A (en) | A kind of photo processing method and terminal | |
| CN110471999B (en) | Trajectory processing method, apparatus, device and medium | |
| WO2021184628A1 (en) | Image processing method and device | |
| CN109034181A (en) | The classification method and device of motion track, equipment, storage medium | |
| Sikirić et al. | Image representations on a budget: Traffic scene classification in a restricted bandwidth scenario | |
| CN113942521B (en) | Method for identifying style of driver under intelligent vehicle road system | |
| CN112329152B (en) | Driving data searching method, device and equipment | |
| CN114926791A (en) | Method and device for detecting abnormal lane change of vehicles at intersection, storage medium and electronic equipment | |
| CN114255593A (en) | Method, device and storage medium for monitoring traffic flow | |
| US20230394846A1 (en) | Coarse-to-fine attention networks for light signal detection and recognition | |
| CN111126501A (en) | Image identification method, terminal equipment and storage medium | |
| CN111381575A (en) | Automatic test method, device, server, electronic equipment and storage medium | |
| US11845470B2 (en) | Dynamic adaptation of automotive AI processing power and active sensor data | |
| CN114205223A (en) | Tracing and positioning method and device for vehicle intelligent driving function abnormal event | |
| CN112287153B (en) | Image searching method, device and system and programmable logic device | |
| CN113435343B (en) | Image recognition method and device, computer equipment and storage medium | |
| CN113879338B (en) | Driving planning module optimization method, device, equipment and medium |
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 |