CN115250268B - Automatic driving data acquisition method based on pull mode and automobile - Google Patents
Automatic driving data acquisition method based on pull mode and automobile Download PDFInfo
- Publication number
- CN115250268B CN115250268B CN202210653346.6A CN202210653346A CN115250268B CN 115250268 B CN115250268 B CN 115250268B CN 202210653346 A CN202210653346 A CN 202210653346A CN 115250268 B CN115250268 B CN 115250268B
- Authority
- CN
- China
- Prior art keywords
- acquisition
- data
- vehicle end
- vehicle
- json file
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/2866—Architectures; Arrangements
- H04L67/30—Profiles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q9/00—Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an automatic driving data acquisition method based on a pull mode, which comprises the steps of formulating acquisition task configuration according to requirements; converting the configuration of the acquisition task into parameters, and carrying out configuration parameterization to form an acquisition configuration file; compiling parameters in the acquisition configuration file by utilizing a compiler to form a new json file; storing the new json file in a cloud end, and after the vehicle end is electrified, the cloud end transmits the new json file to the vehicle end; analyzing the new json file by the vehicle end, and reconfiguring the new json file to enable the new json file to be solidified to the vehicle end to form a new acquisition rule; when the vehicle meets the condition of the trigger rule of the vehicle end, the vehicle information acquisition equipment records corresponding data and stores the corresponding data in the vehicle end, and the vehicle end acquires and packages the related data which accords with the acquisition rule in the recorded data under the constraint of the acquisition rule; uploading the packed data to a cloud end for storage by a vehicle end; and after the acquisition requirement is met, the vehicle end stops acquiring data.
Description
Technical Field
The invention relates to the technical field of automatic driving of automobiles, in particular to an automatic driving data acquisition method based on a pull mode and an automobile.
Background
The amount of data required for the autopilot development process is enormous and the magnitude of data required increases exponentially as the level of autopilot increases. The development of the automatic driving algorithm requires multiple incremental algorithm training to improve the performance of the vehicle-end algorithm. The training of the vehicle-end algorithm requires using data related to voice, NLP (natural language processing) text, video, pictures and radar point clouds, wherein the data are important sources of perception training data sets, the data sets are collected by the vehicle end, the data sets are transmitted to a cloud for storage through a Tbox (wireless data transmission module) after the collection is completed, and a large amount of data is directly clouded through a cloud-up channel, so that channel bandwidth can become a bottleneck for data uploading.
The current data acquisition process is forward triggering acquisition, namely, a scene meets an abnormal triggering condition, a vehicle end uploads a picture at the moment, radar point clouds and video packaging files 10 seconds before and after the occurrence moment of an abnormal event to a cloud end, and cloud end file management is responsible for storing the files. However, the algorithm engineering training algorithm is guided by business, the algorithm required by different scenes needs data of corresponding characteristics to be fed, the data set requirement from algorithm training is against the forward trigger type acquisition mode, so that the acquired data amount is large, but the available data which can be truly used for algorithm training after manual or machine screening is very small. Therefore, the adoption of the service-oriented pull-type data acquisition method is significant for solving the problem of lack of training data of algorithm engineers.
At present, the data uploading is basically forward uploading, namely, a vehicle end records data through a collecting device, the recorded data is stored in a storage medium, and the data is uploaded to a cloud server through a wireless module. For example, the patent CN112277842a sets up a data acquisition system on the basis of a vehicle body sensor, so that the data acquisition system can be used normally, and meanwhile, the data acquisition system can also be ensured to be consistent with the data in the test process, and the extra calculation force and hardware resources occupied by an automatic driving platform are avoided. The method mainly reduces the acquisition load of the whole vehicle controller through hardware optimization, but is still a forward trigger logic. The patent CN110264586a uses data acquisition and synchronization technology and data encoding and caching technology to reduce the physical occupation space of uploading data files, so as to save uploading bandwidth, and the method only changes the encoding mode of data from the data uploading angle, but the method improves the uploading efficiency, and still is a push-type data acquisition mode, so that the problem of lack of the acquired unnecessary training data still exists. Aiming at fast-developing automatic driving business, the data acquisition strategy which depends on acquisition equipment push at present is difficult to meet the increasingly multiplied algorithm training data requirements, and the situation of 'data barren' of algorithm training cannot be turned over at all.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to solve the technical problems that: how to provide an automatic driving data acquisition method based on a pull mode, which realizes configured quantitative acquisition, meets the data set requirement required by the acquisition, and reduces the bandwidth resource uploaded by a cloud.
In order to solve the technical problems, the invention adopts the following technical scheme:
an automatic driving data acquisition method based on a pull mode comprises the following steps:
(1) Formulating acquisition task configuration according to requirements;
(2) Converting the configuration of the acquisition task into parameters, and carrying out configuration parameterization to form an acquisition configuration file;
(3) Compiling parameters in the acquisition configuration file by utilizing a compiler to form a new json file;
(4) Storing the new json file in a cloud end, and after the vehicle end is electrified, the cloud end transmits the new json file to the vehicle end;
(5) Analyzing the new json file by the vehicle end, and reconfiguring the new json file to enable the new json file to be solidified to the vehicle end to form a new acquisition rule;
(6) When the vehicle meets the condition of the triggering rule of the vehicle end, the vehicle information acquisition equipment records corresponding data and stores the corresponding data in the vehicle end, and the vehicle end acquires and packages the related data which accords with the acquisition rule in the recorded data under the constraint of the acquisition rule in the step (5);
(7) Uploading the packed data to a cloud end for storage by a vehicle end;
(8) And after the acquisition requirement is met, the vehicle end stops acquiring data.
As an optimization, in step (1), the acquisition task configuration includes an acquisition type, an acquisition frequency, an acquisition number and an acquisition scene classification, and the acquisition type includes a picture, a radar point cloud, a voice, a gesture, a video and a text.
In the step (4), after the vehicle end is powered on, uploading an original json file existing at the vehicle end to a cloud end, and carrying out consistency verification on the new json file and the original json file by the cloud end, if the verification is passed, not issuing the new json file, and if the verification is not passed, issuing the new json file to replace the original json file at the vehicle end.
As optimization, according to corresponding parameters in the acquisition configuration file as acquisition control requirements, in the process that the vehicle end uploads the packed data to the cloud end, the vehicle end performs acquisition verification on the uploaded data, meanwhile, the cloud end performs acquisition verification on the received data, whether the vehicle end and the cloud end meet the acquisition control requirements at the same time is judged, if so, the cloud end issues a stop acquisition signal, the vehicle end receives the signal, and the stop acquisition operation is executed.
An automobile adopts the automatic driving data acquisition method based on the pull mode to acquire data.
Compared with the prior art, the invention has the following beneficial effects: the invention has the following advantages:
1) The configurable pull type acquisition mode is oriented, the accurate acquisition can be realized by taking the training service requirement as a guide, the configured quantitative acquisition is realized, and the acquired data set requirement is met;
2) The data acquisition in the pull mode can avoid uploading the data which is worthless to training to the cloud for storage, so that the consumption of storage resources can be saved and the dependence on bandwidth can be reduced;
3) The unexpected that the car end was gathered has been avoided, the high in the clouds of realizing gathering is controllable, very big reduction the dynamics of gathering and screening, practice thrift the power resource.
Drawings
FIG. 1 is a schematic diagram of pull mode data acquisition in accordance with the present invention;
fig. 2 is a flow chart of the pull mode data acquisition function of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. In the description of the present invention, it should be noted that, directions or positional relationships indicated by terms such as "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., are directions or positional relationships based on those shown in the drawings, or are directions or positional relationships conventionally put in use of the inventive product, are merely for convenience of describing the present invention and simplifying the description, and are not indicative or implying that the apparatus or element to be referred to must have a specific direction, be constructed and operated in a specific direction, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," "third," and the like are used merely to distinguish between descriptions and should not be construed as indicating or implying relative importance. Furthermore, the terms "horizontal," "vertical," and the like do not denote a requirement that the component be absolutely horizontal or overhang, but rather may be slightly inclined. As "horizontal" merely means that its direction is more horizontal than "vertical", and does not mean that the structure must be perfectly horizontal, but may be slightly inclined. In the description of the present invention, it should also be noted that, unless explicitly specified and limited otherwise, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
As shown in fig. 1 and 2, the automatic driving data collection method based on the pull mode in this embodiment includes the following steps:
(1) Formulating acquisition task configuration according to requirements;
(2) Converting the configuration of the acquisition task into parameters, and carrying out configuration parameterization to form an acquisition configuration file;
(3) Compiling parameters in the acquisition configuration file by utilizing a compiler to form a new json file;
(4) Storing the new json file in a cloud end, and after the vehicle end is electrified, the cloud end transmits the new json file to the vehicle end;
(5) Analyzing the new json file by the vehicle end, and reconfiguring the new json file to enable the new json file to be solidified to the vehicle end to form a new acquisition rule;
(6) When the vehicle meets the condition of the triggering rule of the vehicle end, the vehicle information acquisition equipment records corresponding data and stores the corresponding data in the vehicle end, and the vehicle end acquires and packages the related data which accords with the acquisition rule in the recorded data under the constraint of the acquisition rule in the step (5);
(7) Uploading the packed data to a cloud end for storage by a vehicle end;
(8) And after the acquisition requirement is met, the vehicle end stops acquiring data.
In this embodiment, in step (1), the acquisition task configuration includes an acquisition type, an acquisition frequency, an acquisition number, and an acquisition scene classification, and the acquisition type includes a picture, a radar point cloud, a voice, a gesture, a video, and a text.
In this embodiment, in step (4), after the vehicle end is powered on, the original json file existing in the vehicle end is uploaded to the cloud end, the cloud end performs consistency verification on the new json file and the original json file, if the verification is passed, the new json file is not issued, and if the verification is not passed, the new json file is issued to replace the original json file of the vehicle end.
In this embodiment, according to the corresponding parameters in the acquisition configuration file as the acquisition control requirement, in the process that the vehicle end uploads the packed data to the cloud end, the vehicle end performs acquisition verification on the uploaded data, and meanwhile, the cloud end performs acquisition verification on the received data, and judges whether the vehicle end and the cloud end meet the acquisition control requirement at the same time, if so, the cloud end issues an acquisition stopping signal, the vehicle end receives the signal, and the acquisition stopping operation is executed. And the cloud end and the vehicle end execute double verification to ensure that the uploaded data can be received.
An automobile adopts the automatic driving data acquisition method based on the pull mode to acquire data.
The acquisition task of the pull mode needs to be guided by requirements, a proper acquisition task is set according to the requirements of algorithm training on data, then data acquisition is driven according to the acquisition task, and the acquisition requirement is assumed to be In_req.
Collecting task input:
s1: the acquisition task is configured according to the acquisition requirement, and In_req #type,f,n,C tag …), wherein type is an acquisition type comprising pictures, videos, radar point clouds and the like, acquisition frequencyfFor determining acquisition intervals or acquisition frequencies, acquisition numbersnEnsuring the number of demands and classifying the acquired scenesC tag Other acquisition conditions such as red light scenes displayed in the embodiment are submitted to an acquisition strategy center through a task form to configure acquisition rulesI 1 。
And (3) acquisition configuration:
s2: as shown in fig. 1, the acquisition task is input immediately afterI 1 = In_req(type,f,n,C tag …), type is typically data such AS Picture, point cloud, AS, gestme, video, text, etc., which is taken in this exampletype= "Picture", the acquisition frequency may set the acquisition frame rate, such asf=30fps, the number of acquisitions is determined from the demand input, taken in this examplen=1000, acquisition scene can select system subdivision scene label C tag = "red_light", configuration regularization of the above inputs,C tag and (3) associating with a system Trigger (a vehicle end triggering rule), training data under a specified scene can be acquired, for example, 1000 camera picture data are acquired according to 30 frames per second under the current lane red light scene.
S3: the acquisition configuration file is formed after the acquisition rule is parameterized, and the configuration rule is used for converting the configuration parameters into a json file executable by the controller at the momentI 2 =y*。
{
“type”: "picture",
“frame”:“30”，
“number”:“1000”
“Ctag”:“red_light”
}
S4: the cloud actively pulls the configuration file y of the vehicle end when the vehicle end is electrified o If the cloud has the newly generated configuration file y, assigning y to y o I.e. y → y o Otherwise, the assignment operation is not performed. And when the vehicle is electrified every time, the cloud end pulls the vehicle end configuration file and checks consistency, if the vehicle end configuration file is consistent, the vehicle end configuration file is not updated, and if the vehicle end configuration file is inconsistent, the vehicle end configuration file is updated.
Assigning y to y o And the cloud is used for issuing the configuration file to the vehicle controller again, and the configuration file is updatedI 3 The vehicle acquires the latest configuration file, then analyzes the latest configuration file into acquisition parameters, transmits the acquisition parameters to the file uploading controller, and simultaneously checks the configuration fileQ 3 And controlling the Trigger uploading of the file by the file uploading controller.
And (3) collecting and uploading:
s5: the acquisition and uploading are associated with Trigger, all Trigger forms corresponding file records, but the file uploading of which Trigger type is selected to be controlled by a configuration file, such as C tag When the scene condition of = "red_light" triggers, the file upload controller will meet the acquisition frequency and C according to the configuration file rule tag The file package of the scene of the= "red_light" is uploaded to the cloud for storage through the Tbox wireless, and the effect of promoting the cloud of the data in a pull mode is formed. In order to achieve the control requirement of on-demand acquisition, data verification is needed in the uploading process to judge whether the acquisition requirement is met, if the current acquisition can be used as a judgment basis through the uploading quantity, when n<1000 logic does not trigger the acquisition stop signal, and when n is more than or equal to 1000, logic triggersSend out stop collecting signalQ 2 。
S6: after the data acquisition meets the conditions, the acquisition process is stopped by triggering the acquisition stopping signal, otherwise, the aim of accurately controlling the acquisition scale cannot be achieved. Stopping signal acquisition by meeting demand inputI 1 To control the regulation of demand. The regulating logic is that the forward information flow changes the configuration fileI 2 The vehicle end is ensured to receive the acquisition stopping signal and execute the acquisition stopping operation.
Through the process, the vehicle-end directional data acquisition in the pull mode with the training requirement as the guide can be realized, blind data acquisition is avoided, and the data acquisition is purposeful, compared with the traditional acquisition mode, the method has the advantages that firstly, the requirement is used as the guide, the acquisition requirement is configured according to the service training requirement, the accurate acquisition required by the acquisition is realized, and the utilization rate of the acquired data is improved; secondly, the pull mode collection can configure the data of the uploaded cloud as required, the scale is controllable, the storage space is saved, and the requirement on the uploading bandwidth is reduced; thirdly, changing the qualitative Trigger forward uploading mode into the quantitative demand-guided Trigger uploading mode provides a new thought for configuring quantitative data acquisition.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the technical solution, and those skilled in the art should understand that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the present invention, and all such modifications and equivalents are included in the scope of the claims.
Claims (4)
1. An automatic driving data acquisition method based on a pull mode is characterized by comprising the following steps of: the method comprises the following steps:
(1) Formulating acquisition task configuration according to requirements;
(2) Converting the configuration of the acquisition task into parameters, and carrying out configuration parameterization to form an acquisition configuration file;
(3) Compiling parameters in the acquisition configuration file by utilizing a compiler to form a new json file;
(4) Storing the new json file in a cloud end, and after the vehicle end is electrified, the cloud end transmits the new json file to the vehicle end;
(5) Analyzing the new json file by the vehicle end, and reconfiguring the new json file to enable the new json file to be solidified to the vehicle end to form a new acquisition rule;
(6) When the vehicle meets the condition of the triggering rule of the vehicle end, the vehicle information acquisition equipment records corresponding data and stores the corresponding data in the vehicle end, and the vehicle end acquires and packages the related data which accords with the acquisition rule in the recorded data under the constraint of the acquisition rule in the step (5);
(7) Uploading the packed data to a cloud end for storage by a vehicle end;
(8) After the acquisition requirement is met, the vehicle end stops acquiring data, corresponding parameters in the acquisition configuration file are used as acquisition control requirements, in the process that the vehicle end uploads the packed data to the cloud end, the vehicle end performs acquisition verification on the uploaded data, meanwhile, the cloud end performs acquisition verification on the received data, whether the vehicle end and the cloud end meet the acquisition control requirement at the same time or not is judged, if so, the cloud end issues an acquisition stopping signal, the vehicle end receives the signal, and the acquisition stopping operation is executed.
2. The pull mode-based automatic driving data collection method according to claim 1, wherein: in step (1), the acquisition task configuration includes an acquisition type, an acquisition frequency, an acquisition number, and an acquisition scene classification, and the acquisition type includes a picture, a radar point cloud, a voice, a gesture, a video, and a text.
3. The pull mode-based automatic driving data collection method according to claim 1, wherein: in the step (4), after the vehicle end is powered on, uploading an original json file existing at the vehicle end to a cloud end, and carrying out consistency verification on the new json file and the original json file by the cloud end, if the verification is passed, not issuing the new json file, and if the verification is not passed, issuing the new json file to replace the original json file at the vehicle end.
4. An automobile, characterized in that: a data acquisition using a pull mode based automatic driving data acquisition method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210653346.6A CN115250268B (en) | 2022-06-10 | 2022-06-10 | Automatic driving data acquisition method based on pull mode and automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210653346.6A CN115250268B (en) | 2022-06-10 | 2022-06-10 | Automatic driving data acquisition method based on pull mode and automobile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115250268A CN115250268A (en) | 2022-10-28 |
| CN115250268B true CN115250268B (en) | 2023-06-06 |
Family
ID=83698044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210653346.6A Active CN115250268B (en) | 2022-06-10 | 2022-06-10 | Automatic driving data acquisition method based on pull mode and automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115250268B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104811809A (en) * | 2014-01-23 | 2015-07-29 | 中国科学院声学研究所 | Set-top box user behavior acquisition method |
| CN108650325A (en) * | 2018-05-17 | 2018-10-12 | 浙江中控技术股份有限公司 | A kind of industrial data acquisition method, relevant device and system |
| CN112764916A (en) * | 2020-12-18 | 2021-05-07 | 北京百度网讯科技有限公司 | Data acquisition method and device |
| WO2021217630A1 (en) * | 2020-04-30 | 2021-11-04 | 上海华东汽车信息技术有限公司 | Vehicle data uploading method and apparatus, computer device, and storage medium |
| CN114495057A (en) * | 2022-01-21 | 2022-05-13 | 亿咖通(湖北)技术有限公司 | Data acquisition method, electronic device and storage medium |
| CN114545903A (en) * | 2022-02-21 | 2022-05-27 | 安徽域驰智能科技有限公司 | Vehicle feed remote monitoring and early warning system and method |
| CN114579134A (en) * | 2022-01-08 | 2022-06-03 | 智协慧同(北京)科技有限公司 | Internet of vehicles data acquisition system |
-
2022
- 2022-06-10 CN CN202210653346.6A patent/CN115250268B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104811809A (en) * | 2014-01-23 | 2015-07-29 | 中国科学院声学研究所 | Set-top box user behavior acquisition method |
| CN108650325A (en) * | 2018-05-17 | 2018-10-12 | 浙江中控技术股份有限公司 | A kind of industrial data acquisition method, relevant device and system |
| WO2021217630A1 (en) * | 2020-04-30 | 2021-11-04 | 上海华东汽车信息技术有限公司 | Vehicle data uploading method and apparatus, computer device, and storage medium |
| CN112764916A (en) * | 2020-12-18 | 2021-05-07 | 北京百度网讯科技有限公司 | Data acquisition method and device |
| CN114579134A (en) * | 2022-01-08 | 2022-06-03 | 智协慧同(北京)科技有限公司 | Internet of vehicles data acquisition system |
| CN114495057A (en) * | 2022-01-21 | 2022-05-13 | 亿咖通(湖北)技术有限公司 | Data acquisition method, electronic device and storage medium |
| CN114545903A (en) * | 2022-02-21 | 2022-05-27 | 安徽域驰智能科技有限公司 | Vehicle feed remote monitoring and early warning system and method |
Non-Patent Citations (1)
| Title |
|---|
| 基于双目视觉的桥梁检测无人机两轴云台设计与实现;王雨峰;;中国新技术新产品(第24期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115250268A (en) | 2022-10-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109131345B (en) | Vehicle and method and system for controlling vehicle | |
| CN109855646A (en) | It is distributed centralized automated driving system and method | |
| CN105407278A (en) | Panoramic video traffic situation monitoring system and method | |
| CN112929187B (en) | Network slice management method, device and system | |
| US20200409744A1 (en) | Workflow engine framework | |
| US20230137533A1 (en) | Data labeling method and apparatus, computing device, and storage medium | |
| CN109816114A (en) | A kind of generation method of machine learning model, device | |
| CN114641041B (en) | Internet of vehicles slicing method and device oriented to edge intelligence | |
| CN114697324B (en) | Real-time video analysis and processing method based on edge cloud cooperation | |
| CN115250268B (en) | Automatic driving data acquisition method based on pull mode and automobile | |
| CN114697212A (en) | Device parameter processing method, device, system and medium | |
| DE102021129569A1 (en) | Attention-driven system for adaptive streaming of vehicle sensor data to edge computing and cloud-based network devices | |
| CN114640669A (en) | Edge calculation method and device | |
| CN109698850A (en) | Processing method and system | |
| CN109905614B (en) | Video controller, video controller on-load control method, display system, and storage medium | |
| CN117132890A (en) | Remote sensing image target detection method and system based on Kubernetes edge computing cluster | |
| CN116303456A (en) | Industrial data processing method, system, device and computer readable storage medium | |
| CN114707667A (en) | Data-driven automatic model training and application system | |
| CN114764372A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN113207107A (en) | Multichannel bandwidth regulation and control method, device, equipment and storage medium | |
| CN112346437A (en) | Vehicle-mounted software management system | |
| Mesgarpour et al. | Enhancing the value of commercial vehicle telematics data through analytics and optimisation techniques | |
| CN114254766B (en) | Method and system for jointly training machine learning model at two ends of vehicle cloud | |
| CN110155056A (en) | A kind of the sideslip compensation method and system of automatic driving vehicle | |
| EP4369194A1 (en) | Electronic device for executing application in background process, and operation method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |