CN110852804B - Intelligent vehicle real-time inspection system based on deep learning - Google Patents
Intelligent vehicle real-time inspection system based on deep learning Download PDFInfo
- Publication number
- CN110852804B CN110852804B CN201911097591.8A CN201911097591A CN110852804B CN 110852804 B CN110852804 B CN 110852804B CN 201911097591 A CN201911097591 A CN 201911097591A CN 110852804 B CN110852804 B CN 110852804B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- subsystem
- intelligent vehicle
- information
- illegal
- 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
- 238000013135 deep learning Methods 0.000 title claims abstract description 35
- 238000007689 inspection Methods 0.000 title claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000013475 authorization Methods 0.000 claims abstract description 10
- 238000007726 management method Methods 0.000 claims description 23
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims 3
- 230000002159 abnormal effect Effects 0.000 claims 2
- 238000003672 processing method Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0248—Avoiding fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the field of intelligent vehicle real-time inspection based on deep learning, in particular to an intelligent vehicle real-time inspection system based on deep learning. The system comprises an account authorization management subsystem for carrying out real-name authentication on information registered by a user and distributing accounts and passwords with use rights for the user, an account management subsystem for storing account information and account states, an intelligent vehicle inspection management subsystem for managing intelligent vehicle inspection routes and image pick-up devices carried by the intelligent vehicle, an image identification processing subsystem for judging advertisement legitimacy, and a message notification subsystem for advertising illegal information broadcasting and real-time notification of illegal advertisement processing conditions. The image processing method based on deep learning provided by the invention realizes accurate and efficient identification of the urban illegal advertisement, and assists the user to better process the illegal advertisement, thereby achieving the purposes of smart city and intelligent management.
Description
Technical Field
The invention relates to the field of intelligent vehicle real-time inspection based on deep learning, in particular to an intelligent vehicle real-time inspection system based on deep learning.
Background
In the informatization era advocating smart cities and intelligent management, the realization of the optimization construction of cities by using computer technology is the current trend of the era. At present, most cities in China are greatly developed to establish civilized city activities, and illegal advertisements in the cities are one of the problems to be processed in the process of establishing the civilized cities. Due to the characteristics of large quantity, difficult judgment, difficult recognition and the like of illegal advertisements, law enforcement agencies input a large amount of manpower, material resources and financial resources in the law enforcement process, but the effect is poor. Today, the technology is rapidly developed, and a system capable of identifying and judging urban illegal advertisements is lacking, so that law enforcement authorities are assisted to process illegal advertisements more conveniently, efficiently and accurately.
Disclosure of Invention
The invention aims to provide an intelligent vehicle real-time inspection system based on deep learning, which aims to accurately identify and judge urban illegal advertisements, realize real-time monitoring of the illegal advertisements and assist law enforcement authorities to process the illegal advertisements more efficiently, conveniently and accurately, thereby achieving intelligent management of smart cities.
In order to achieve the above object, the present invention provides the following solutions:
the intelligent vehicle real-time patrol system based on deep learning comprises an account input authorization subsystem, an account management subsystem, an intelligent vehicle patrol management subsystem, an image recognition processing subsystem and a message notification subsystem. Wherein,,
the account input authorization subsystem is used for carrying out real-name authentication on information registered by a user and distributing an account and a password with use permission to the user; the user information mainly comprises department names, department codes and department contact phones. After the authentication of the filled information is completed, the system automatically allocates and grants a user account number with the system use authority and an initial password for the user; the user account and the initial password are generated by using a logic algorithm according to the information filled by the user, and are encrypted and stored in an effective code of a unique identifiable identity in the account registration subsystem, wherein the initial password can be automatically changed in the account input authorization subsystem.
The account management subsystem is used for storing account information and account states, wherein the account information comprises position information of illegal and illegal advertisements and advertisement illegal and illegal detail information besides user information; the account state comprises a pending state of the illegal advertisement and a processed state of the illegal advertisement. In the process of the intelligent vehicle for tour management of the city, if illegal and illegal advertisements in the city are found and confirmed, the advertisements at the position are marked as the illegal and illegal advertisement pending states by the system; after the system finishes processing the illegal and illegal advertisements when the user goes to the place where the illegal and illegal advertisements are located, the advertisement is marked as the processed state of the illegal and illegal advertisements by the system.
The intelligent vehicle inspection management subsystem is used for managing the intelligent vehicle, including the management of the intelligent vehicle inspection route and the management of the image pickup equipment carried by the intelligent vehicle. The intelligent vehicle performs optimal path planning according to the law enforcement place set by the user, and then automatically travels to the road section required to be managed by the user. After reaching the specified location, the in-vehicle image pickup apparatus will perform image collection and sampling on the destination.
The image recognition processing subsystem is used for judging the validity of the advertisement. After the advertisement image of the law enforcement place is collected, the image recognition processing subsystem processes the image, recognizes advertisement information contained in the image, and performs validity check on the recognized advertisement information by using a deep learning algorithm according to advertisement validity criteria to obtain a judging result.
The message notification subsystem is used for broadcasting the advertisement illegal information and notifying the illegal advertisement processing condition in real time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a real-time inspection system for intelligent vehicles based on deep learning according to an embodiment of the invention;
FIG. 2 is a schematic flow chart of a deep learning-based intelligent vehicle real-time inspection system according to an embodiment of the invention;
FIG. 3 is a schematic flow chart of capturing images to perform advertisement validity checking according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of a decision making using a deep learning algorithm according to an embodiment of the present invention;
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
The invention aims to provide an intelligent vehicle real-time inspection system based on deep learning, which aims to accurately identify and judge urban illegal advertisements, realize real-time monitoring of the illegal advertisements and assist law enforcement authorities to process the illegal advertisements more efficiently, conveniently and accurately, thereby achieving intelligent management of smart cities.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Example 1
Fig. 2 is a schematic flow chart of an intelligent vehicle real-time inspection system based on deep learning according to an embodiment of the invention. As shown in fig. 2, a real-time inspection system for intelligent vehicles based on deep learning includes:
step 100: the system authenticates the information registered by the user, distributes available accounts and passwords for the user after the authentication is completed, and allows the user to log in and then use the system.
Step 200: and the intelligent vehicle tour management subsystem calls an internal navigation interface of the system, performs optimal path planning according to the tour destination set by the user, and navigates to the target place.
Step 300: the vehicle-mounted image pickup device collects and samples images at a destination and transmits the collected images to the image recognition processing subsystem in real time.
Step 400: and the image recognition processing subsystem performs validity check on the advertisement by utilizing a deep learning algorithm according to the advertisement validity criterion in the system, and transmits the check result to the message notification subsystem.
Step 500: the message notification subsystem broadcasts a validity check result and a processing condition notification of the illegal advertisement in real time.
Example 2
The embodiment provides a process of checking the validity of advertisements by using an image recognition processing subsystem after the user acquires the images. FIG. 3 is a flow chart of capturing images to perform advertisement validity checking according to an embodiment of the present invention. The method comprises the following steps:
s100: the user logs in to the system.
S101: the in-vehicle image pickup apparatus performs image collection and sampling at a destination.
S102: the acquired images are transferred to an image recognition processing subsystem.
S103: the system determines whether an advertisement legitimacy criterion has been set. If it has been set, S105 is performed; otherwise, S104 is performed.
S104: and setting advertisement validity standard.
S105: the system utilizes a deep learning algorithm to perform validity check on the advertisement based on a validity standard set by a user.
S106: and the message notification subsystem broadcasts the validity check in real time.
Example 3
The present embodiment provides a detailed flow of decisions made by the system using a deep learning algorithm. Fig. 4 is a flowchart illustrating a decision making process using a deep learning algorithm according to an embodiment of the present invention. The method comprises the following steps:
s200, the system starts to operate.
S201, setting classification standards for the billboard images according to whether the billboard images accord with the rule of illegal advertising violation.
And S202, performing image preprocessing and image enhancement on the collected images.
And S203, learning the billboard images according to the determined classification standards, and training a neural network model.
S204, judging whether the training round and the target accuracy requirements are met, if yes, performing step S205; otherwise, S203 is performed.
And S205, obtaining a trained neural network model.
S206, waiting for receiving advertisement validity judging request.
S207, judging whether an advertisement validity judging request is received. If yes, go to S208; otherwise, S206 is performed.
And S208, classifying the images according to the trained model.
S209, returning the judging result and sending the result to the message notification subsystem.
Claims (8)
1. The intelligent vehicle real-time inspection system based on deep learning is characterized in that an account input authorization subsystem, an account management subsystem, an intelligent vehicle inspection management subsystem, an image recognition processing subsystem and a message notification subsystem are adopted; wherein,,
the account input authorization subsystem is used for carrying out real-name authentication on information registered by a user and distributing an account and a password with use permission to the user; the user information mainly comprises department names, department codes and department contact phones; after the authentication of the filled information is completed, the system automatically allocates and grants a user account number with the system use authority and an initial password for the user; the user account and the initial password are generated by using a logic algorithm according to the information filled by the user, and are encrypted and stored in an effective code of a unique identifiable identity in the account registration subsystem, wherein the initial password can be automatically changed in the account input authorization subsystem;
the account management subsystem is used for storing account information and account states, wherein the account information comprises position information of illegal and illegal advertisements and advertisement illegal and illegal detail information besides user information; the account state comprises a pending state of the illegal advertisement and a processed state of the illegal advertisement; in the process of the intelligent vehicle for tour management of the city, if illegal and illegal advertisements in the city are found and confirmed, the advertisements at the position are marked as the illegal and illegal advertisement pending states by the system; after the system finishes processing when the user goes to the place where the illegal and illegal advertisement is located, the advertisement is marked as the processed state of the illegal and illegal advertisement by the system;
the intelligent vehicle inspection management subsystem is used for managing the intelligent vehicle by a user, and comprises the management of an intelligent vehicle inspection route and the management of image pickup equipment carried by the intelligent vehicle; the intelligent vehicle performs optimal path planning according to a law enforcement place set by a user, and then automatically runs to a road section required to be managed by the user; after reaching the appointed place, the vehicle-mounted image pickup equipment collects and samples the image of the destination;
the image recognition processing subsystem is used for judging the validity of the advertisement; after the advertisement image of the law enforcement place is collected, the image recognition processing subsystem processes the image, recognizes advertisement information contained in the image, and performs validity check on the recognized advertisement information by using a deep learning algorithm according to an advertisement validity criterion to obtain a judging result; the method for obtaining the advertisement information by using the deep learning algorithm to carry out validity check on the identified advertisement information to obtain a judging result specifically comprises the following steps:
s200, starting the system to operate;
s201, setting classification standards for the billboard images according to whether the billboard images accord with the rule of illegal advertisement violation;
s202, performing image preprocessing and image enhancement on the collected images;
s203, learning the billboard images according to the determined classification standards, and training a neural network model;
s204, judging whether the training round and the target accuracy requirements are met, if yes, performing step S205; otherwise, S203 is performed;
s205, obtaining a trained neural network model;
s206, waiting for receiving an advertisement validity judging request;
s207, judging whether an advertisement validity judging request is received or not; if yes, go to S208; otherwise, S206 is performed;
s208, classifying the images according to the trained model;
s209, returning a judging result and sending the result to the message notification subsystem;
the message notification subsystem is used for broadcasting the advertisement illegal information and notifying the illegal advertisement processing condition in real time.
2. The intelligent vehicle real-time tour system based on deep learning according to claim 1, wherein the intelligent vehicle tour management subsystem detects problematic advertisements through the image recognition processing subsystem, and the advertisement is notified through the message to the manager, which is the user authorized by the account entry authorization subsystem.
3. A deep learning based intelligent vehicle real time patrol system as recited in claim 1, wherein problematic advertisement information in said intelligent vehicle patrol management subsystem is detected by said image recognition processing subsystem.
4. A deep learning based intelligent vehicle real time patrol system according to claim 1, wherein the discovery of problematic advertisements in said system is notified by said message notification subsystem.
5. The intelligent vehicle real-time patrol system based on the deep learning is characterized in that the intelligent vehicle real-time patrol system based on the deep learning comprises the following steps:
the user enters the authorization subsystem through the account to become an authorized user;
the authorized user logs in the intelligent vehicle real-time inspection system and sets a law enforcement place through the intelligent vehicle inspection management subsystem;
the intelligent vehicle inspection management subsystem plans an optimal route according to the law enforcement site, automatically runs on the optimal route, and photographs and samples specified advertisement points through the photographing equipment;
the image recognition processing subsystem processes the information transmitted by the intelligent vehicle inspection management subsystem, recognizes advertisement information contained in the image, and performs validity check on the recognized advertisement information by using a deep learning algorithm;
after the image recognition processing subsystem checks all monitoring points, all results are notified to the subsystem through a message to send detection information to an authorized user in real time;
the method for carrying out validity check on the identified advertisement information by utilizing the deep learning algorithm specifically comprises the following steps:
s200, starting the system to operate;
s201, setting classification standards for the billboard images according to whether the billboard images accord with the rule of illegal advertisement violation;
s202, performing image preprocessing and image enhancement on the collected images;
s203, learning the billboard images according to the determined classification standards, and training a neural network model;
s204, judging whether the training round and the target accuracy requirements are met, if yes, performing step S205; otherwise, S203 is performed;
s205, obtaining a trained neural network model;
s206, waiting for receiving an advertisement validity judging request;
s207, judging whether an advertisement validity judging request is received or not; if yes, go to S208; otherwise, S206 is performed;
s208, classifying the images according to the trained model;
s209, returning the judging result and sending the result to the message notification subsystem.
6. The deep learning based intelligent vehicle real time patrol system of claim 5, wherein the account entry authorization subsystem further comprises: information registration and real-name authentication, and an acquisition system distributes an account number and a password with use rights.
7. The intelligent vehicle real-time tour system based on deep learning according to claim 5, wherein the advertisement is detected whether it meets the specification, specifically comprising:
transmitting the information adopted by the camera equipment to a graph image recognition processing subsystem through an intelligent vehicle real-time inspection system;
the image recognition processing subsystem carries out preliminary detection on information through an internal deep learning algorithm and sends abnormal information after the detection information to an authorized user through the message notification subsystem;
the authorized user is informed of illegal advertisement information and partial abnormal advertisement information through the message informing subsystem, and the completely normal advertisement information is not received, so that the workload of the user is reduced.
8. The deep learning-based intelligent vehicle real-time tour system according to claim 5; the method is characterized in that when judging the validity of the advertisement, the system adopts a deep learning algorithm to judge, so as to obtain a judging result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911097591.8A CN110852804B (en) | 2019-11-11 | 2019-11-11 | Intelligent vehicle real-time inspection system based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911097591.8A CN110852804B (en) | 2019-11-11 | 2019-11-11 | Intelligent vehicle real-time inspection system based on deep learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110852804A CN110852804A (en) | 2020-02-28 |
CN110852804B true CN110852804B (en) | 2023-07-18 |
Family
ID=69601344
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911097591.8A Active CN110852804B (en) | 2019-11-11 | 2019-11-11 | Intelligent vehicle real-time inspection system based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110852804B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113448268A (en) * | 2021-05-20 | 2021-09-28 | 鄂尔多斯市龙腾捷通科技有限公司 | Wisdom city management patrol monitoring platform |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011180633A (en) * | 2010-02-26 | 2011-09-15 | Chugoku Electric Power Co Inc:The | Advertising electric pole patrol route selection system |
CN207676483U (en) * | 2017-12-26 | 2018-07-31 | 北京万集科技股份有限公司 | A kind of processing system that mark motor vehicle violation is stopped |
CN109190608A (en) * | 2018-10-30 | 2019-01-11 | 长威信息科技发展股份有限公司 | A kind of city intelligent identification Method violating the regulations |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100332404A1 (en) * | 2009-06-29 | 2010-12-30 | David Valin | Method and mechanism for protection, sharing, storage, accessing, authentication, certification, attachment and tracking anything in an electronic network |
US20110231250A1 (en) * | 2010-03-18 | 2011-09-22 | Textaway, Ltd. | System and Method for Displaying Advertisements on a User Device Based on User Preferences While Operative by the User |
CN103198657A (en) * | 2013-03-19 | 2013-07-10 | 杨熙增 | Implementation method and system of mobile vehicle-mounted parking-violation capturing |
CN106205144B (en) * | 2016-09-07 | 2018-06-19 | 东南大学 | Highway Emergency Vehicle Lane occupies supervision punishment method and system |
CN108961768A (en) * | 2018-07-30 | 2018-12-07 | 鄂尔多斯市普渡科技有限公司 | The unmanned police cruiser of one kind and patrol method |
-
2019
- 2019-11-11 CN CN201911097591.8A patent/CN110852804B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011180633A (en) * | 2010-02-26 | 2011-09-15 | Chugoku Electric Power Co Inc:The | Advertising electric pole patrol route selection system |
CN207676483U (en) * | 2017-12-26 | 2018-07-31 | 北京万集科技股份有限公司 | A kind of processing system that mark motor vehicle violation is stopped |
CN109190608A (en) * | 2018-10-30 | 2019-01-11 | 长威信息科技发展股份有限公司 | A kind of city intelligent identification Method violating the regulations |
Also Published As
Publication number | Publication date |
---|---|
CN110852804A (en) | 2020-02-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017080039A1 (en) | Vehicle driving safety monitoring method and device and system | |
CN111695472A (en) | Method for assisting in quickly inputting information, electronic equipment and storage medium | |
CN112084824B (en) | Passenger reminding method and device, electronic equipment and storage medium | |
US20150102946A1 (en) | System and method for enforcing parking rules | |
CN101271624B (en) | Parking position management system based on personal identity string code authentication | |
CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
CN110852804B (en) | Intelligent vehicle real-time inspection system based on deep learning | |
CN104616236A (en) | Police handheld multifunctional device | |
WO2016201867A1 (en) | M2m car networking identification method and apparatus | |
CN109272379A (en) | A kind of shared motor vehicle monitoring method and apparatus based on block chain | |
CN111815791B (en) | Roadside parking automatic payment method and system based on Internet of vehicles | |
CN113327451A (en) | High-precision intelligent automobile management method and system | |
Pareek et al. | IoT based prototype for smart vehicle and parking management system | |
CN107665475A (en) | Nonlocal vehicles management method and management system | |
CN105551260A (en) | Vehicle identifying method | |
KR20200052427A (en) | Sharing system of resident priority parking zone | |
CN201233653Y (en) | Parking position controller based on personal identity serial code authentication and parking position management system | |
CN111835753B (en) | Internet-based parking method, device and system | |
CA2765987A1 (en) | Method for validating a road traffic control transaction | |
CN111325987A (en) | Fake plate identification method and device for gas station | |
CN114821836A (en) | Highway authentication information platform | |
CN106530729B (en) | It is a kind of based on Beidou positioning tail number restricted driving monitoring method, apparatus and system | |
WO2022001926A1 (en) | Internet-of-vehicles device body identification method, vehicle-mounted device, roadside device, and storage medium | |
CN109685027A (en) | A kind of new added road recognition methods and system based on block chain technology | |
CN108909671B (en) | Vehicle locking method and device, storage medium and electronic equipment |
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 |