Unlock instant, AI-driven research and patent intelligence for your innovation.

Intelligent vehicle real-time inspection system based on deep learning

A deep learning and smart car technology, applied in marketing, instruments, computer parts, etc., can solve problems that are difficult to determine, large in quantity, difficult to identify, etc.

Active Publication Date: 2020-02-28
XIANGTAN UNIV
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the large number of illegal advertisements, difficult to determine, difficult to identify and other characteristics, law enforcement agencies have invested a lot of manpower, material and financial resources in the process of law enforcement, but the effect is not good
Today, with the rapid development of science and technology, we lack a system that can identify and judge illegal advertisements in cities and assist law enforcement agencies to deal with illegal advertisements more conveniently, efficiently and accurately

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent vehicle real-time inspection system based on deep learning
  • Intelligent vehicle real-time inspection system based on deep learning
  • Intelligent vehicle real-time inspection system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] figure 2 It is a schematic flow chart of the real-time inspection system for intelligent vehicles based on deep learning according to the embodiment of the present invention. Such as figure 2 As shown, a real-time inspection system for intelligent vehicles based on deep learning, including:

[0021] Step 100: the system authenticates the information registered by the user, and after the authentication is completed, assigns a valid and available account and password to the user for the user to log in and then use the system.

[0022] Step 200: The smart car patrol management subsystem invokes the internal navigation interface of the system, performs optimal route planning according to the patrol destination set by the user, and navigates to the target location.

[0023] Step 300: The vehicle-mounted camera equipment collects and samples images at the destination, and transmits the collected images to the image recognition processing subsystem in real time.

[0024] ...

Embodiment 2

[0027] This embodiment provides a process for the user to check the legality of the advertisement by using the image recognition processing subsystem after the user realizes the image acquisition. image 3 It is a schematic flow diagram of the embodiment of the present invention from image acquisition to advertisement legality check. details as follows:

[0028] S100: After logging in, the user enters the system.

[0029] S101: The vehicle-mounted camera equipment performs image collection and sampling at the destination.

[0030] S102: Send the collected images to the image recognition processing subsystem.

[0031] S103: the system judges whether an advertisement legality standard has been set. If it has been set, go to S105; otherwise, go to S104.

[0032] S104: Set an advertisement legality standard.

[0033] S105: The system uses a deep learning algorithm to check the legality of the advertisement based on the legality standard set by the user.

[0034] S106: The me...

Embodiment 3

[0036] This embodiment provides a detailed process for the system to use a deep learning algorithm to make a decision. Figure 4 It is a schematic flow chart of using a deep learning algorithm to make a decision in an embodiment of the present invention. details as follows:

[0037] S200: The system starts to operate.

[0038] S201: Set a classification standard for the billboard image according to whether it conforms to the advertising law and regulation violation criterion.

[0039] S202: Perform image preprocessing and image enhancement on the collected images.

[0040] S203: Learning the billboard image according to the determined classification standard, and training the neural network model.

[0041] S204: Judging whether the training rounds and target accuracy requirements are met, if so, proceed to step S205; otherwise, proceed to S203.

[0042] S205: Obtain a trained neural network model.

[0043] S206: Waiting to receive an advertisement legality determination r...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

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 used for carrying out real-name authentication on information registered by a user, and distributing the account and the password with usepermission to a user, an account management subsystem used for storing account information and account states, an intelligent vehicle inspection management subsystem used for managing an intelligentvehicle inspection route and camera equipment carried by an intelligent vehicle, an image recognition processing subsystem used for judging the validity of advertisements, and a message notification subsystem used for broadcasting advertisement violation information and notifying violation advertisement processing conditions in real time. According to the invention, the image processing method based on deep learning achieves the precise and efficient recognition of the urban illegal and illegal advertisements, assists a user to better process the illegal and illegal advertisements, and achieves the purposes of smart city and intelligent management.

Description

technical field [0001] The invention relates to the field of real-time inspection of intelligent vehicles based on deep learning, in particular to a real-time inspection system of intelligent vehicles based on deep learning. Background technique [0002] In the information age that vigorously advocates smart cities and intelligent management, it is the current trend of the times to use computer technology to realize the optimization and construction of cities. At present, most cities in our country are vigorously carrying out activities to create civilized cities, and illegal advertisements in cities are one of the problems that need to be dealt with in the process of building civilized cities. Due to the large number of illegal advertisements, difficult to determine, and difficult to identify, law enforcement agencies have invested a lot of manpower, material and financial resources in the process of law enforcement, but the effect is not good. Today, with the rapid develo...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q30/02G06K9/00
CPCG06Q30/0248G06V20/40
Inventor 王求真黄家文孙宇翔杨源陈乐生郭建强王佳琦李谭哲
Owner XIANGTAN UNIV