CN115359301A - Data mining method based on cloud platform - Google Patents
Data mining method based on cloud platform Download PDFInfo
- Publication number
- CN115359301A CN115359301A CN202211081456.6A CN202211081456A CN115359301A CN 115359301 A CN115359301 A CN 115359301A CN 202211081456 A CN202211081456 A CN 202211081456A CN 115359301 A CN115359301 A CN 115359301A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- vehicle
- model
- cloud
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a data mining method based on a cloud platform, which comprises the following steps: perception data and vehicle signal acquisition module: the vehicle-end platform utilizes equipment to collect data and adopts different measures to obtain vehicle complete information data according to different conditions; a data mining device: the system comprises a cloud end platform, a deployed algorithm model and an acquisition strategy, wherein the cloud end platform is used for sending original data acquired by a vehicle to the cloud end platform, and the cloud end platform utilizes the deployed algorithm model and the acquisition strategy to perform special data mining according to different data requirements; a data processing module: the system is used for acquiring screened data, performing duplicate removal and slicing, and performing pre-labeling by using a large model; an automatic correction module: the method is used for transmitting the marked data back to the local platform, and model iteration can be performed after correction is completed.
Description
Technical Field
The invention relates to the field of automatic driving data processing, in particular to a data mining method based on a cloud platform.
Background
With the development of artificial intelligence technology, users have a demand for intelligent driving of fast landing of related products on automobiles, and the safety and stability of related products of automatic driving become important research directions. In the current stage, scene recognition in the automobile driving process is finished on the basis of a deep learning technology, and the final recognition accuracy of the perception model is directly determined by training data of a deep learning model. Because the traffic scene is complex and changeable, the coverage learning of all traffic scenes cannot be completed, so that the perception model needs long-time data accumulation learning for the scenes which cannot be identified and have errors, and the process consumes a large amount of manpower and material resources.
The traditional intelligent driving difficult scene mining method needs to consume a large amount of testing personnel to carry out vehicle following tests, potential difficult scene data are collected by means of experience of technicians, the method consumes manpower and material resources seriously, the requirement on technical literacy of collection personnel is high, a large amount of invalid collected data can be generated in the specific implementation process, and the efficiency is low.
Disclosure of Invention
In order to overcome the defects of the prior art, the data mining method based on the cloud platform is provided, data are mined, classified and marked by combining a vehicle-mounted sensor, the marking cost of the data in the later period can be effectively reduced, difficult data required by the current sensing model can be accurately and automatically acquired, a technician is not required to follow a vehicle for testing in the whole acquisition process, the acquisition efficiency is effectively improved, and the method has high popularization value.
In order to solve the technical problems, the invention provides the following technical scheme: a data mining method based on a cloud platform comprises the following steps: perception data and vehicle signal acquisition module: the vehicle-end platform collects the information by using equipment and adopts different measures according to different conditions to obtain vehicle complete information data; a data mining device: the system comprises a cloud end platform, a deployed algorithm model and an acquisition strategy, wherein the cloud end platform is used for sending original data acquired by a vehicle to the cloud end platform, and the cloud end platform utilizes the deployed algorithm model and the acquisition strategy to perform special data mining according to different data requirements; a data processing module: the system is used for acquiring screened data, performing duplicate removal and slicing, and performing pre-labeling by using a large model; an automatic correction module: and the method is used for transmitting the marked data back to the local platform, and performing model iteration after correction is completed.
As a preferable technical scheme of the invention, the equipment in the perception data and vehicle signal acquisition module comprises a camera, a laser radar, a millimeter wave radar, an ultrasonic radar and other sensors, and the perception data and vehicle signal acquisition module acquires signals of a vehicle body such as gears, a chassis, tires and the like and stores the acquired vehicle body data and road perception data.
The data mining device comprises an image quality analysis module, a working condition recognition mining module, a large model DIFF module, a target tracking module, a picture searching module, a vehicle body signal analysis module and a cloud map index module.
As a preferred technical solution of the present invention, the image quality analysis module is configured to perform image quality analysis according to a condition that a lens of the camera is dirty.
As a preferred technical scheme of the invention, the working condition identification and mining module extracts the required image data information according to different working condition requirements.
As a preferred technical solution of the present invention, the large model DIFF module performs differential comparison between a result of vehicle-side model detection and a result of cloud-side large model detection to obtain missing detection image data of a current vehicle-side model, where the large model is a deep learning identification model trained by using massive data and a complex network, and cannot be deployed on a vehicle due to computational power of a vehicle-mounted-side computing chip and operator support limitation.
As a preferred technical scheme of the invention, the target tracking module performs scene tracking analysis before and after a target result detected by the vehicle-mounted model, and judges whether the current tracking target is missed or mistakenly detected according to a preset rule. And therefore, data to be optimized of the current vehicle-mounted model are mined.
As a preferred technical scheme of the invention, the image searching module mainly mines the image sample data which is rare in data set and has high error rate, learns the convolution characteristics of the image by utilizing a deep convolution neural network, traverses an image database and searches the image sample with high characteristic similarity.
As a preferred technical solution of the present invention, the vehicle body signal analysis module is configured to analyze vehicle body information, and if the recognition result of the vehicle-side model is normal driving and there are signals of driver emergency braking, steering, and the like in the vehicle body signal, trigger an automatic data collection policy, and determine the acquired image data as abnormal data to be mined.
According to the optimal technical scheme, the cloud map indexing module embeds the cloud platform into the map information module, and the acquired road data can be matched to directly extract the required road data such as tunnels, viaducts, muddiness and the like.
Compared with the prior art, the invention can achieve the following beneficial effects:
according to the method, the vehicle-mounted sensor is combined to mine, classify and mark the data, so that the later-stage marking cost of the data can be effectively reduced, difficult data required by the current sensing model can be accurately and automatically acquired, a technician vehicle-following test is not needed in the whole acquisition process, the acquisition efficiency is effectively improved, and the method has high popularization value.
Drawings
FIG. 1 is a schematic overall flow diagram of the present invention;
FIG. 2 is a block diagram of the overall module of the present invention;
Detailed Description
The present invention will be further described with reference to specific embodiments for the purpose of facilitating an understanding of technical means, characteristics of creation, objectives and functions realized by the present invention, but the following embodiments are only preferred embodiments of the present invention, and are not intended to be exhaustive. Based on the embodiments in the implementation, other embodiments obtained by those skilled in the art without any creative efforts belong to the protection scope of the present invention. The experimental methods in the following examples are conventional methods unless otherwise specified, and materials, reagents and the like used in the following examples are commercially available unless otherwise specified.
Example (b):
example 1:
as shown in fig. 1 and 2, the present invention provides a data mining method based on a cloud platform, including: perception data and vehicle signal acquisition module: the vehicle-end platform collects the information by using equipment and adopts different measures according to different conditions to obtain vehicle complete information data; a data mining device: the system comprises a cloud end platform, a deployed algorithm model and an acquisition strategy, wherein the cloud end platform is used for sending original data acquired by a vehicle to the cloud end platform, and the cloud end platform utilizes the deployed algorithm model and the acquisition strategy to perform special data mining according to different data requirements; a data processing module: the system is used for acquiring screened data, performing duplicate removal and slicing, and performing pre-labeling by using a large model; an automatic correction module: the data mining device comprises an image quality analysis module, a working condition recognition mining module, a large model DIFF module, a target tracking module, a map searching module, a vehicle body signal analysis module and a cloud map indexing module, wherein the data mining device comprises the image quality analysis module, the working condition recognition mining module, the large model DIFF module, the target tracking module, the map searching module, the vehicle body signal analysis module and the cloud map indexing module;
according to the method, firstly, data are collected through a perception data and vehicle signal collection module, signals such as gears, chassis and tires of a vehicle body are collected through sensors such as a camera, a laser radar, a millimeter wave radar and an ultrasonic radar, the collected vehicle body data and road perception data are stored, then, the raw data collected by the vehicle are sent to a cloud end platform through a data mining device, the cloud end platform utilizes a deployed algorithm model and a collection strategy to mine special data according to different data requirements, the data mining device comprises an image quality analysis module, a working condition recognition mining module, a large model DIFF module, a target tracking module, a map searching module, a vehicle body signal analysis module and a cloud end map indexing module, the screened data are subjected to de-weighting and slicing through a data processing module, the large model is used for pre-labeling, the labeled data are transmitted back to a local platform through an automatic correction module, model iteration can be carried out after correction is completed, the labeling cost of the data in the later period can be effectively reduced, the difficult data required by the current perception model can be accurately and automatically collected, the whole collection process does not need to follow a test, the technical staff collection efficiency is effectively improved, and the popularization value is higher.
Example 2:
the data mining method based on the cloud platform is characterized in that an image quality analysis module is used for carrying out image quality analysis according to the condition that a lens of a camera is dirty and the like, a working condition identification mining module extracts required image data information according to different working condition requirements, a large model DIFF module carries out differentiation comparison on the result detected by a vehicle-end model and the result detected by a cloud large model to obtain the undetected image data of the current vehicle-end model, the large model is a deep learning identification model trained by using mass data and a complex network, the vehicle-mounted model cannot be deployed on the vehicle due to the calculation power and operator support limitation of a vehicle-mounted end computing chip, a target tracking module carries out front and back scene tracking analysis on the target result detected by the vehicle-mounted model, and whether the current tracked target is undetected and mistakenly detected or not is judged according to preset rules. The data to be optimized of the current vehicle-mounted model are excavated, the image searching module is mainly used for excavating image sample data which are rare in data concentration and high in error rate, a deep convolutional neural network is used for learning convolution characteristics of the image, an image database is traversed, image samples with high characteristic similarity are searched, the vehicle body signal analysis module is used for analyzing vehicle body information, if the recognition result of the vehicle-end model is normal driving and signals of emergency braking, steering and the like of a driver exist in vehicle body signals, an automatic data collection strategy is triggered, the acquired image data are judged to be abnormal data which need to be excavated, the cloud end map indexing module embeds a cloud end platform into a map information module, and the required road data such as tunnels, viaducts, muddy bridges, muddy roads and the like can be directly extracted by matching with the acquired road data;
in the data mining process, an image quality analysis module performs image quality analysis according to the situations that a lens of a camera is dirty and the like, a working condition identification mining module extracts required image data information according to different working condition requirements, a large model DIFF module performs differentiation comparison on the result detected by a vehicle end model and the result detected by a cloud large model to obtain the undetected image data of the current vehicle end model, wherein the large model is a deep learning identification model trained by using massive data and a complex network, the vehicle end model cannot be deployed on the vehicle due to calculation power and operator support limitation of a vehicle end computing chip, a target tracking module performs front-back scene tracking analysis on the target result detected by the vehicle end model, judges whether the current tracking target is detected and detected wrongly according to preset rules, so as to dig out data to be optimized of the current vehicle model, learns the image data to be optimized by using a convolution depth neural network if the main image searching module is used for image sample data mining with high data concentration and error rate, learns the characteristics of the image by using a convolution depth neural network, traverses an image database to search, searches for searching the image sample with high feature similarity, and searches for the vehicle body information analysis module, if the vehicle end model is used for acquiring a road map, and the road information of a road information acquisition module which is used for acquiring a road which a driver needs to acquire a road.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A data mining method based on a cloud platform is characterized by comprising the following steps: the method comprises the following steps:
perception data and vehicle signal acquisition module: the vehicle-end platform utilizes equipment to collect data and adopts different measures to obtain vehicle complete information data according to different conditions;
the data mining device comprises: the system comprises a cloud end platform, a deployed algorithm model and an acquisition strategy, wherein the cloud end platform is used for sending original data acquired by a vehicle to the cloud end platform, and the cloud end platform utilizes the deployed algorithm model and the acquisition strategy to perform special data mining according to different data requirements;
a data processing module: the system is used for acquiring screened data, performing duplicate removal and slicing, and performing pre-labeling by using a large model;
an automatic correction module: and the method is used for transmitting the marked data back to the local platform, and performing model iteration after correction is completed.
2. The cloud platform-based data mining method of claim 1, wherein: the device in the perception data and vehicle signal acquisition module comprises a camera, a laser radar, a millimeter wave radar, an ultrasonic radar and other sensors, the perception data and vehicle signal acquisition module acquires signals of gears, chassis, tires and the like of a vehicle body and stores the acquired vehicle body data and road perception data.
3. The cloud platform-based data mining method of claim 1, wherein: the data mining device comprises an image quality analysis module, a working condition recognition mining module, a large model DIFF module, a target tracking module, a map searching module, a vehicle body signal analysis module and a cloud map indexing module.
4. The cloud platform-based data mining method of claim 3, wherein: the image quality analysis module is used for carrying out image quality analysis according to the conditions of lens dirtiness and the like of the camera.
5. The cloud platform-based data mining method of claim 3, wherein: the working condition identification mining module extracts the required image data information according to different working condition requirements.
6. The cloud platform-based data mining method of claim 3, wherein: the large model DIFF module is used for differentially comparing a detection result of the vehicle-end model with a detection result of the cloud-end large model to obtain undetected image data of the current vehicle-end model, the large model is a deep learning identification model trained by using mass data and a complex network, and the vehicle-end computing chip cannot be used for deploying on the vehicle due to the computing power and operator support limitation.
7. The cloud platform-based data mining method of claim 3, wherein: and the target tracking module performs scene tracking analysis before and after a target result detected by the vehicle-mounted model and judges whether the current tracking target is missed or mistakenly detected according to a preset rule. And therefore, data to be optimized of the current vehicle-mounted model are mined.
8. The cloud platform-based data mining method of claim 3, wherein: the image searching module is mainly used for mining the image sample data which is rare in data set and has high error rate, learning the convolution characteristic of the image by utilizing a deep convolution neural network, traversing an image database and searching the image sample with high characteristic similarity.
9. The cloud platform-based data mining method of claim 3, wherein: the vehicle body signal analysis module is used for analyzing vehicle body information, if the recognition result of the vehicle end model is normal driving and signals of emergency braking, steering and the like of a driver exist in the vehicle body signals, a data automatic collection strategy is triggered, and the acquired image data is judged to be abnormal data needing mining.
10. The cloud platform-based data mining method of claim 3, wherein: the cloud map index module is used for embedding the cloud platform into the map information module, and the acquired road data can be matched with the map information module to directly extract required road data such as tunnels, viaducts, mud and the like.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211081456.6A CN115359301A (en) | 2022-09-06 | 2022-09-06 | Data mining method based on cloud platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211081456.6A CN115359301A (en) | 2022-09-06 | 2022-09-06 | Data mining method based on cloud platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115359301A true CN115359301A (en) | 2022-11-18 |
Family
ID=84006162
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211081456.6A Pending CN115359301A (en) | 2022-09-06 | 2022-09-06 | Data mining method based on cloud platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115359301A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117312807A (en) * | 2023-11-29 | 2023-12-29 | 浙江万胜智能科技股份有限公司 | Control state analysis method and system of circuit breaker |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105955233A (en) * | 2016-04-28 | 2016-09-21 | 郑州宇通客车股份有限公司 | Vehicle fault diagnosis method and system based on data excavation |
CN107438873A (en) * | 2017-07-07 | 2017-12-05 | 驭势科技(北京)有限公司 | A kind of method and apparatus for being used to control vehicle to travel |
US20190047572A1 (en) * | 2016-02-05 | 2019-02-14 | Tevva Motors Limited | Range Extender Control |
CN111104903A (en) * | 2019-12-19 | 2020-05-05 | 南京邮电大学 | Depth perception traffic scene multi-target detection method and system |
CN111491127A (en) * | 2020-04-21 | 2020-08-04 | 新石器慧通(北京)科技有限公司 | Video call method and system based on unmanned vehicle remote driving |
CN112346046A (en) * | 2020-10-30 | 2021-02-09 | 合肥中科智驰科技有限公司 | Single-target tracking method and system based on vehicle-mounted millimeter wave radar |
CN112415904A (en) * | 2019-08-23 | 2021-02-26 | 郑州宇通客车股份有限公司 | Remote control method, device and system for automatic driving vehicle |
CN113085655A (en) * | 2021-05-11 | 2021-07-09 | 国网黑龙江省电力有限公司电力科学研究院 | Vehicle-mounted electric automobile comprehensive service system |
CN113762406A (en) * | 2021-09-15 | 2021-12-07 | 东软睿驰汽车技术(沈阳)有限公司 | Data mining method and device and electronic equipment |
CN113780064A (en) * | 2021-07-27 | 2021-12-10 | 华为技术有限公司 | Target tracking method and device |
CN114155500A (en) * | 2021-11-30 | 2022-03-08 | 联陆智能交通科技(上海)有限公司 | Abnormal road surface real-time acquisition and sharing system and method based on vehicle body sensor |
CN114379581A (en) * | 2021-11-29 | 2022-04-22 | 江铃汽车股份有限公司 | Algorithm iteration system and method based on automatic driving |
CN114511715A (en) * | 2022-01-05 | 2022-05-17 | 惠州市德赛西威汽车电子股份有限公司 | Driving scene data mining method |
-
2022
- 2022-09-06 CN CN202211081456.6A patent/CN115359301A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190047572A1 (en) * | 2016-02-05 | 2019-02-14 | Tevva Motors Limited | Range Extender Control |
CN105955233A (en) * | 2016-04-28 | 2016-09-21 | 郑州宇通客车股份有限公司 | Vehicle fault diagnosis method and system based on data excavation |
CN107438873A (en) * | 2017-07-07 | 2017-12-05 | 驭势科技(北京)有限公司 | A kind of method and apparatus for being used to control vehicle to travel |
CN112415904A (en) * | 2019-08-23 | 2021-02-26 | 郑州宇通客车股份有限公司 | Remote control method, device and system for automatic driving vehicle |
CN111104903A (en) * | 2019-12-19 | 2020-05-05 | 南京邮电大学 | Depth perception traffic scene multi-target detection method and system |
CN111491127A (en) * | 2020-04-21 | 2020-08-04 | 新石器慧通(北京)科技有限公司 | Video call method and system based on unmanned vehicle remote driving |
CN112346046A (en) * | 2020-10-30 | 2021-02-09 | 合肥中科智驰科技有限公司 | Single-target tracking method and system based on vehicle-mounted millimeter wave radar |
CN113085655A (en) * | 2021-05-11 | 2021-07-09 | 国网黑龙江省电力有限公司电力科学研究院 | Vehicle-mounted electric automobile comprehensive service system |
CN113780064A (en) * | 2021-07-27 | 2021-12-10 | 华为技术有限公司 | Target tracking method and device |
CN113762406A (en) * | 2021-09-15 | 2021-12-07 | 东软睿驰汽车技术(沈阳)有限公司 | Data mining method and device and electronic equipment |
CN114379581A (en) * | 2021-11-29 | 2022-04-22 | 江铃汽车股份有限公司 | Algorithm iteration system and method based on automatic driving |
CN114155500A (en) * | 2021-11-30 | 2022-03-08 | 联陆智能交通科技(上海)有限公司 | Abnormal road surface real-time acquisition and sharing system and method based on vehicle body sensor |
CN114511715A (en) * | 2022-01-05 | 2022-05-17 | 惠州市德赛西威汽车电子股份有限公司 | Driving scene data mining method |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117312807A (en) * | 2023-11-29 | 2023-12-29 | 浙江万胜智能科技股份有限公司 | Control state analysis method and system of circuit breaker |
CN117312807B (en) * | 2023-11-29 | 2024-02-06 | 浙江万胜智能科技股份有限公司 | Control state analysis method and system of circuit breaker |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110532896B (en) | Road vehicle detection method based on fusion of road side millimeter wave radar and machine vision | |
CN108765404B (en) | A kind of road damage testing method and device based on deep learning image classification | |
CN102737247B (en) | Identification system of smoke intensity image of tail gas of diesel vehicle | |
Lekshmipathy et al. | Vibration vs. vision: Best approach for automated pavement distress detection | |
KR101977052B1 (en) | System for road surface condition investigation using unmanned air vehicle and method using the same | |
CN103914682A (en) | Vehicle license plate recognition method and system | |
CN112883936A (en) | Method and system for detecting vehicle violation | |
CN115359301A (en) | Data mining method based on cloud platform | |
CN112633120A (en) | Intelligent roadside sensing system based on semi-supervised learning and model training method | |
Thiruppathiraj et al. | Automatic pothole classification and segmentation using android smartphone sensors and camera images with machine learning techniques | |
CN115527364A (en) | Traffic accident tracing method and system based on radar vision data fusion | |
Kamenetsky et al. | Aerial car detection and urban understanding | |
Cruz et al. | Classified counting and tracking of local vehicles in manila using computer vision | |
CN111325811B (en) | Lane line data processing method and processing device | |
US20220101509A1 (en) | Deterioration diagnostic device, deterioration diagnostic system, deterioration diagnostic method, and recording medium | |
CN114973156B (en) | Night muck car detection method based on knowledge distillation | |
CN113838282B (en) | Beidou positioning-based vehicle abnormal behavior detection method | |
Pribe et al. | Learning to associate observed driver behavior with traffic controls | |
CN115409691A (en) | Bimodal learning slope risk detection method integrating laser ranging and monitoring image | |
CN114494986A (en) | Road scene recognition method and device | |
CN114037750A (en) | Method for realizing track virtual responder | |
Govada et al. | Road deformation detection | |
CN112053571A (en) | Expressway vehicle trajectory tracking method and system | |
KR20220107875A (en) | Traffic monitoring system of multi lane based on deep learning using camera | |
CN112052824A (en) | Gas pipeline specific object target detection alarm method, device and system based on YOLOv3 algorithm and storage 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 |