[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN118037231B - SAAS-based intelligent park management system and method - Google Patents

SAAS-based intelligent park management system and method Download PDF

Info

Publication number
CN118037231B
CN118037231B CN202410260865.5A CN202410260865A CN118037231B CN 118037231 B CN118037231 B CN 118037231B CN 202410260865 A CN202410260865 A CN 202410260865A CN 118037231 B CN118037231 B CN 118037231B
Authority
CN
China
Prior art keywords
vehicle parking
feature
training
park
parking
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
Application number
CN202410260865.5A
Other languages
Chinese (zh)
Other versions
CN118037231A (en
Inventor
梅勇波
谢晶
俞雯菁
徐欣湄
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Yangbo Technology Co ltd
Original Assignee
Hangzhou Yangbo Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Yangbo Technology Co ltd filed Critical Hangzhou Yangbo Technology Co ltd
Priority to CN202410260865.5A priority Critical patent/CN118037231B/en
Publication of CN118037231A publication Critical patent/CN118037231A/en
Application granted granted Critical
Publication of CN118037231B publication Critical patent/CN118037231B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/02—Reservations, e.g. for tickets, services or events
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • 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
    • 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
    • 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
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Tourism & Hospitality (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Business, Economics & Management (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Biophysics (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present disclosure relates to a SAAS-based intelligent park management system and method. The method comprises the following steps: inputting, inquiring, counting and analyzing basic information, customer information, contract information and cost information of the park; monitoring, maintaining and alarming the water, electricity, gas, fire, security and parking lots in the park; publishing, reserving, evaluating and settling property, cleaning, catering and express delivery services of the park; and carrying out communication, exchange, interaction and cooperation among clients of the park to construct the ecological circle of the park. Thus, the management efficiency of the park can be improved, the service quality of the park can be improved, and the safety of the park can be improved.

Description

SAAS-based intelligent park management system and method
Technical Field
The disclosure relates to the technical field of intelligent park management, in particular to an intelligent park management system and method based on SAAS.
Background
With the increasing speed of the urbanization process, the number of campuses is increasing and the management of campuses is becoming more and more complex. The appearance of wisdom garden management system has brought brand-new solution for the garden management, and it can help the garden manager to realize the unified management to various resources in the garden, improves garden management efficiency.
Parking lots are one of the important public facilities in a park, and parking lot management is also an important component of a smart park management system. However, the conventional parking lot management method mainly relies on manual management, such as manually charging parking fees, checking parking certificates, handling illegal parking, maintaining order of the parking lot, etc., which is very heavy, and particularly for large-scale parking lots, parking lot management personnel often need to work with a shift and add points. In addition, the conventional parking lot management mode often has the problems of unreasonable parking space distribution and low parking space utilization rate, and simultaneously has the problem of disordered parking order, for example, some vehicles are parked in disorder, and occupy a plurality of parking spaces, so that other vehicles cannot be parked. In addition, some vehicles are parked on fire-fighting channels or disabled parking spaces, and the normal passing of other vehicles is affected. These problems can lead to disordered parking lots and affect the normal parking of other vehicles.
Therefore, a SAAS-based intelligent campus management system is desired.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
In a first aspect, the present disclosure provides a SAAS-based intelligent campus management system, the system comprising:
The park information management module is used for inputting, inquiring, counting and analyzing basic information, client information, contract information and cost information of the park;
The park facility management module is used for monitoring, maintaining and alarming water, electricity, gas, fire, security and parking lots of the park;
The park service management module is used for publishing, reserving, evaluating and settling property, cleaning, catering and express delivery services of the park;
And the park community management module is used for carrying out communication, exchange, interaction and collaboration among clients of the park to construct a park ecological circle.
Optionally, the campus facility management module includes: an image acquisition unit for the parking state of the vehicle, the method comprises the steps of acquiring a vehicle parking state image acquired by a camera deployed in a park parking lot; a vehicle parking specification reference image acquisition unit for extracting a dataset of vehicle parking specification reference images from a database; a vehicle parking standard image feature extraction unit, configured to perform feature extraction on each vehicle parking standard reference image in the data set of the vehicle parking standard reference images through a vehicle parking image feature extractor based on a deep neural network model, so as to obtain a set of vehicle parking standard reference feature images; the vehicle parking standard reference common mode coding unit is used for inputting the set of the vehicle parking standard reference characteristic diagrams into the vehicle parking standard common mode characteristic extractor to obtain the vehicle parking standard reference common characteristic diagram; the vehicle parking state feature extraction unit is used for extracting features of the vehicle parking state image through the vehicle parking image feature extractor based on the deep neural network model so as to obtain a vehicle parking state feature map; and a vehicle parking specification detection unit for calculating a difference feature between the vehicle parking specification reference commonality feature map and the vehicle parking state feature map, and determining whether the vehicle is in a parking specification based on the difference feature.
Optionally, the deep neural network model is a convolutional neural network model.
Optionally, the vehicle parking specification refers to a common mode encoding unit for: inputting the set of the vehicle parking specification reference feature images into the vehicle parking specification commonality mode feature extractor to process according to the following vehicle parking specification commonality formula so as to obtain the vehicle parking specification reference commonality feature images; wherein, the vehicle parking standard commonality formula is: ; wherein, AndRespectively, the vehicle parking specification reference feature map is the first in the setAnd (d)The individual vehicle parking specifications refer to the feature map,Is a set of the vehicle parking specification reference feature maps,A logarithmic function with a base of 2 is shown,、AndRespectively representing the height, width and number of channels of the vehicle parking specification reference feature map,Reference is made to the number of feature maps in the set of feature maps-1 for the vehicle parking specification,The feature values of the respective positions in the semantic difference feature map are referenced for the vehicle parking specifications,Is the number of feature values in the vehicle parking specification reference semantic difference feature map,For the exponential operation of the feature map,Is the vehicle parking specification reference commonality feature map.
Optionally, the vehicle parking specification detection unit includes: a vehicle parking state feature difference calculation subunit for calculating a difference feature map between the vehicle parking specification reference commonality feature map and the vehicle parking state feature map; and the vehicle parking standardability judging subunit is used for passing the differential feature map through a parking standardability discriminator based on a classifier to obtain a discrimination result, wherein the discrimination result is used for indicating whether the vehicle is in a parking standardability.
Optionally, the method further comprises a training module for training the convolutional neural network model-based vehicle parking image feature extractor, the vehicle parking specification commonality mode feature extractor and the classifier-based parking specification discriminator.
Optionally, the training module includes: the vehicle parking state image acquisition unit is trained, the method comprises the steps of acquiring a parking state image of a training vehicle acquired by a camera deployed in a park parking lot; a training vehicle parking specification reference image acquisition unit for extracting a data set of a training vehicle parking specification reference image from a database; the training vehicle parking standard image feature extraction unit is used for respectively carrying out feature extraction on each training vehicle parking standard reference image in the training vehicle parking standard reference image data set through the vehicle parking image feature extractor based on the depth neural network model so as to obtain a set of training vehicle parking standard reference feature images; the training vehicle parking standard reference common mode coding unit is used for inputting the set of the training vehicle parking standard reference feature graphs into the vehicle parking standard common mode feature extractor to obtain a training vehicle parking standard reference common feature graph; the training vehicle parking state feature extraction unit is used for extracting features of the training vehicle parking state image through the vehicle parking image feature extractor based on the deep neural network model so as to obtain a training vehicle parking state feature map; a training vehicle parking state feature difference calculation unit for calculating a training difference feature map between the training vehicle parking specification reference commonality feature map and the training vehicle parking state feature map; the training correction unit is used for correcting the training differential feature map based on the feature matrix to obtain a corrected training differential feature map; the training classification unit is used for passing the corrected training difference feature map through the classifier-based parking specification discriminator to obtain a classification loss function value; and the training unit is used for training the vehicle parking image feature extractor, the vehicle parking standard commonality mode feature extractor and the classifier-based parking standard discriminator based on the convolutional neural network model based on the classification loss function value.
In a second aspect, the present disclosure provides a smart park management method based on SAAS, the method comprising:
Inputting, inquiring, counting and analyzing basic information, customer information, contract information and cost information of the park;
monitoring, maintaining and alarming the water, electricity, gas, fire, security and parking lots in the park;
publishing, reserving, evaluating and settling property, cleaning, catering and express delivery services of the park;
and carrying out communication, exchange, interaction and cooperation among clients of the park to construct the ecological circle of the park.
Optionally, monitoring, maintaining and alarming the hydropower, fire protection, security protection and parking lot of the park comprises: acquiring a vehicle parking state image acquired by a camera deployed in a park parking lot; extracting a dataset of vehicle parking specification reference images from a database; respectively extracting features of each vehicle parking specification reference image in the data set of the vehicle parking specification reference images through a vehicle parking image feature extractor based on a deep neural network model to obtain a set of vehicle parking specification reference feature images; inputting the set of the vehicle parking specification reference feature maps into a vehicle parking specification commonality mode feature extractor to obtain a vehicle parking specification reference commonality feature map; the feature extraction of the vehicle parking state image is carried out by the vehicle parking image feature extractor based on the deep neural network model so as to obtain a vehicle parking state feature map; and calculating a difference characteristic between the vehicle parking specification reference commonality characteristic diagram and the vehicle parking state characteristic diagram, and determining whether the vehicle is in a parking specification or not based on the difference characteristic.
Optionally, the deep neural network model is a convolutional neural network model.
By adopting the technical scheme, basic information, client information, contract information and cost information of the park are input, inquired, counted and analyzed; monitoring, maintaining and alarming the water, electricity, gas, fire, security and parking lots in the park; publishing, reserving, evaluating and settling property, cleaning, catering and express delivery services of the park; and carrying out communication, exchange, interaction and cooperation among clients of the park to construct the ecological circle of the park. Thus, the management efficiency of the park can be improved, the service quality of the park can be improved, and the safety of the park can be improved.
Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale. In the drawings:
fig. 1 is a block diagram illustrating a SAAS-based intelligent campus management system, according to an example embodiment.
Figure 2 is a flow chart illustrating a method of smart park management based on SAAS, according to an example embodiment.
Fig. 3 is a block diagram of an electronic device, according to an example embodiment.
Figure 4 is an application scenario diagram of a SAAS-based intelligent campus management system, according to an example embodiment.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
Parking lots are one of the important public facilities in a park, and parking lot management is also an important component of a smart park management system. However, the conventional parking lot management method mainly relies on manual management, such as manually charging parking fees, checking parking certificates, handling illegal parking, maintaining parking lot order, and the like.
Conventional parking lot management methods have certain drawbacks, such as the large workload of conventional manual management methods, and particularly for large parking lots, parking lot management personnel often need to work at a teams and points. In addition, manual management is inefficient and prone to error. Traditional manual management mode often has the unreasonable, the low problem of parking stall utilization ratio of parking stall distribution, for example, some parking areas distribute the parking stall to specific people or vehicles, lead to other vehicles unable to park, and in addition, some parking areas do not have the reasonable planning parking stall, lead to the low parking stall utilization ratio.
The conventional manual management mode often has the problem of disordered parking order. For example, some vehicles are parked in disorder, occupy a plurality of parking spaces, and other vehicles cannot be parked. In addition, some vehicles are parked on fire-fighting channels or disabled parking spaces to influence the normal passing of other vehicles, and the problems can lead to disordered parking lots and influence the normal parking of other vehicles. The traditional manual management mode often has the problem of high potential safety hazard, for example, some parking lots are not provided with monitoring cameras, so that the accidents such as theft, robbery and the like are easy to occur in the parking lots. In addition, some parking lots are not reasonably planned with parking spaces, so that the parking spaces are narrow, and scratch accidents are easy to occur to vehicles.
These defects all lead to low management efficiency of the parking lot, influence the use effect of the parking lot and bring potential safety hazards. The intelligent parking lot management system can effectively overcome the defects of the traditional parking lot management mode, improves the management efficiency of the parking lot, improves the service quality of the parking lot and improves the safety of the parking lot.
In order to solve the above problems, the present disclosure provides a smart park management system and method based on SAAS, which performs entry, inquiry, statistics and analysis of basic information, customer information, contract information and fee information of a park; monitoring, maintaining and alarming the water, electricity, gas, fire, security and parking lots in the park; publishing, reserving, evaluating and settling property, cleaning, catering and express delivery services of the park; and carrying out communication, exchange, interaction and cooperation among clients of the park to construct the ecological circle of the park. Thus, the management efficiency of the park can be improved, the service quality of the park can be improved, and the safety of the park can be improved.
Specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
It should be appreciated that SAAS stands for Software as a service (Software AS A SERVICE), a mode of Software delivery in which Software is provided to users in a subscription form over the Internet. In SAAS mode, users do not need to purchase, install, or maintain software, but rather access and use the software via the Internet. Users typically subscribe to software services on demand, paying a fee based on usage.
Based on the above, in the technical scheme of the application, the intelligent park management system based on SAAS is provided, and in the SAAS mode, a user does not need to purchase an expensive software license or carry out complicated deployment and maintenance work, only needs to subscribe to the service as required and pay corresponding fees, thereby greatly reducing the cost of the park management system. And moreover, the intelligent park management system based on SAAS has flexibility and expandability, a user can select and subscribe different functional modules according to needs, and the system can be conveniently upgraded and expanded along with the expansion of the park scale or the change of the needs. In addition, the SAAS-based intelligent park management system is responsible for the deployment, updating, maintenance and safety of software by a service provider, so that users do not need to worry about management and maintenance problems of the software, and can concentrate on core business of park management.
Fig. 1 is a block diagram illustrating a SAAS-based intelligent campus management system, according to an example embodiment. As shown in fig. 1, the intelligent campus management system 100 includes:
The campus information management module 101 is configured to enter, query, count and analyze basic information, customer information, contract information and fee information of a campus;
A campus facility management module 102 for monitoring, maintaining and alarming water, electricity, fire, security and parking lots of the campus;
A campus service management module 103, configured to issue, reserve, evaluate, and settle the property, sanitation, catering, and express services of the campus;
and the campus community management module 104 is used for carrying out communication, interaction and collaboration among clients of the campus to construct a campus ecological circle.
The intelligent park management system is a system for realizing intelligent, efficient, synergistic and safe management of various resources in the park by utilizing technologies such as cloud computing, internet of things, big data and the like. The system provides on-demand, on-demand and on-time services for park clients based on SAAS mode, namely software as a service, reduces park operation cost and improves park competitiveness.
Wherein, wisdom garden management system includes following several modules:
park information management module: is responsible for the entry, inquiry, statistics and analysis of campus basic information, customer information, contract information, fee information and the like.
Park facility management module: is responsible for monitoring, controlling, maintaining and alarming of various facilities (such as water, electricity, gas, fire, security, parking lots and the like) in the park.
Park service management module: is responsible for the release, reservation, evaluation and settlement of various services (such as property, cleaning, catering, express delivery and the like) in the park.
Park community management module: is responsible for communication, interaction and cooperation among clients in the park, and constructs the ecological circle of the park.
The intelligent park management system has the advantages that: the efficiency and the level of park management are improved, and the optimal configuration and the utilization of park resources are realized; the satisfaction degree and the loyalty degree of the park clients are improved, and the brand image and influence of the park are enhanced; the operation risk and cost of the park are reduced, and the profit capability and sustainable development capability of the park are improved; innovative park service modes and value claims, and building park core competitiveness and differentiated advantages.
Accordingly, in the above-mentioned smart park management system based on SAAS, in the process of managing park facilities, monitoring needs to be performed on parking lots in the park, where the monitoring content is: illegal parking is monitored, such as parking beyond a parking spot boundary, parking in a no-parking area, or exceeding a parking time limit. Specifically, the technical concept of the application is to monitor and collect the vehicle parking state image in real time through a camera arranged in a park parking lot, introduce an image processing and analyzing algorithm based on artificial intelligence at the rear end to analyze the vehicle parking state image, and compare the vehicle parking state image with a reference state commonality mode of the vehicle parking specification so as to judge whether the vehicle is in a parking specification. Therefore, the parking state of the vehicle in the parking lot can be monitored in real time, and the illegal parking behavior can be captured and punished in time, so that the management efficiency and quality of the parking lot are improved.
In one embodiment of the present disclosure, the campus facility management module includes: an image acquisition unit for the parking state of the vehicle, the method comprises the steps of acquiring a vehicle parking state image acquired by a camera deployed in a park parking lot; a vehicle parking specification reference image acquisition unit for extracting a dataset of vehicle parking specification reference images from a database; a vehicle parking standard image feature extraction unit, configured to perform feature extraction on each vehicle parking standard reference image in the data set of the vehicle parking standard reference images through a vehicle parking image feature extractor based on a deep neural network model, so as to obtain a set of vehicle parking standard reference feature images; the vehicle parking standard reference common mode coding unit is used for inputting the set of the vehicle parking standard reference characteristic diagrams into the vehicle parking standard common mode characteristic extractor to obtain the vehicle parking standard reference common characteristic diagram; the vehicle parking state feature extraction unit is used for extracting features of the vehicle parking state image through the vehicle parking image feature extractor based on the deep neural network model so as to obtain a vehicle parking state feature map; and a vehicle parking specification detection unit for calculating a difference feature between the vehicle parking specification reference commonality feature map and the vehicle parking state feature map, and determining whether the vehicle is in a parking specification based on the difference feature.
The deep neural network model is a convolutional neural network model.
Specifically, in the technical scheme of the present application, first, a vehicle parking state image acquired by a camera disposed in a park is acquired, and a data set of a vehicle parking specification reference image is extracted from a database. Then, feature mining is carried out on each vehicle parking specification reference image in the data set of the vehicle parking specification reference images by using a vehicle parking image feature extractor based on a convolutional neural network model, wherein the vehicle parking image feature extractor has excellent performance in terms of implicit feature extraction of images, so that the semantic feature information about the vehicle in each vehicle parking specification reference image is extracted respectively, and a set of vehicle parking specification reference feature images is obtained. Therefore, the key features of the vehicle parking in each vehicle parking standard reference image, such as the vehicle position, the parking angle and the like, can be extracted, and a basis is provided for subsequent comparison and analysis.
Then, considering that the various vehicle parking specification reference images contain different semantic features related to the vehicle specification parking states, in order to establish an association relation for the specification parking state semantics in the reference images, so as to capture common mode features in a set, in the technical scheme of the application, the set of the vehicle parking specification reference feature images is further input into a vehicle parking specification common mode feature extractor to obtain a vehicle parking specification reference common feature image. It will be appreciated that by inputting a set of different vehicle park specification reference feature maps into the commonality pattern feature extractor, commonality features, i.e. common features and patterns between semantic features in the different vehicle park specification reference images regarding vehicle specification park, may be extracted from these feature maps. This helps the system better understand and capture the general characteristics of the vehicle parking specifications. That is, the vehicle parking specification commonality pattern feature extractor may help the system identify and learn commonality patterns and laws between different vehicle parking specification reference images, thereby establishing a deeper understanding and cognition of the parking specifications. In addition, by extracting the vehicle parking specification reference commonality feature map, the system can more accurately identify whether the vehicle accords with the parking specification, and avoid misjudgment caused by individual features, so that the system can adapt to the parking specification under different scenes and conditions, thereby improving the accuracy and stability of identification and improving the applicability and universality of the system.
In one embodiment of the present disclosure, the vehicle parking specification refers to a common mode encoding unit for: inputting the set of the vehicle parking specification reference feature images into the vehicle parking specification commonality mode feature extractor to process according to the following vehicle parking specification commonality formula so as to obtain the vehicle parking specification reference commonality feature images; wherein, the vehicle parking standard commonality formula is: ; wherein, AndRespectively, the vehicle parking specification reference feature map is the first in the setAnd (d)The individual vehicle parking specifications refer to the feature map,Is a set of the vehicle parking specification reference feature maps,A logarithmic function with a base of 2 is shown,、AndRespectively representing the height, width and number of channels of the vehicle parking specification reference feature map,Reference is made to the number of feature maps in the set of feature maps-1 for the vehicle parking specification,The feature values of the respective positions in the semantic difference feature map are referenced for the vehicle parking specifications,Is the number of feature values in the vehicle parking specification reference semantic difference feature map,For the exponential operation of the feature map,Is the vehicle parking specification reference commonality feature map.
And similarly, inputting the vehicle parking state image into the vehicle parking image feature extractor based on the convolutional neural network model for feature mining so as to extract the state semantic features of the monitored vehicle parking state image about the actual parking of the vehicle, thereby obtaining a vehicle parking state feature map.
Further, in order to monitor whether the actual parking of the vehicle meets the parking specification, in the technical scheme of the application, a difference feature map between the vehicle parking specification reference commonality feature map and the vehicle parking state feature map is further calculated. By calculating the differential feature map, the difference between the common semantic features of the vehicle parking specifications and the semantic features of the actual parking states can be intuitively displayed, and the system is helped to identify the deviation and abnormal conditions of the vehicle parking states. That is, the difference feature map can highlight the difference between the vehicle parking state and the standard reference, which is helpful for the system to quickly find out illegal parking behavior or abnormal parking state, and meanwhile, can avoid misjudgment caused by the small semantic difference between images, improve the accuracy and reliability of identification, and provide data support for park management.
The differential feature map is then passed through a classifier-based parking specification discriminator to obtain a discrimination result that is used to represent whether the vehicle is parked in the specification. That is, the specification discrimination of the actual vehicle parking is performed by using the difference feature information between the vehicle parking specification commonality semantic feature and the actual parking state semantic feature, thereby judging whether the vehicle is in the parking specification. Therefore, the parking state of the vehicle in the parking lot can be monitored in real time, and the illegal parking behavior can be captured and punished in time, so that the management efficiency and quality of the parking lot are improved.
In one embodiment of the present disclosure, the vehicle parking specification detection unit includes: a vehicle parking state feature difference calculation subunit for calculating a difference feature map between the vehicle parking specification reference commonality feature map and the vehicle parking state feature map; and the vehicle parking standardability judging subunit is used for passing the differential feature map through a parking standardability discriminator based on a classifier to obtain a discrimination result, wherein the discrimination result is used for indicating whether the vehicle is in a parking standardability.
In one embodiment of the present disclosure, the SAAS-based intelligent park management system further comprises a training module for training the convolutional neural network model-based vehicle parking image feature extractor, the vehicle parking specification commonality pattern feature extractor, and the classifier-based parking specification discriminator. The training module comprises: the vehicle parking state image acquisition unit is trained, the method comprises the steps of acquiring a parking state image of a training vehicle acquired by a camera deployed in a park parking lot; a training vehicle parking specification reference image acquisition unit for extracting a data set of a training vehicle parking specification reference image from a database; the training vehicle parking standard image feature extraction unit is used for respectively carrying out feature extraction on each training vehicle parking standard reference image in the training vehicle parking standard reference image data set through the vehicle parking image feature extractor based on the depth neural network model so as to obtain a set of training vehicle parking standard reference feature images; the training vehicle parking standard reference common mode coding unit is used for inputting the set of the training vehicle parking standard reference feature graphs into the vehicle parking standard common mode feature extractor to obtain a training vehicle parking standard reference common feature graph; the training vehicle parking state feature extraction unit is used for extracting features of the training vehicle parking state image through the vehicle parking image feature extractor based on the deep neural network model so as to obtain a training vehicle parking state feature map; a training vehicle parking state feature difference calculation unit for calculating a training difference feature map between the training vehicle parking specification reference commonality feature map and the training vehicle parking state feature map; the training correction unit is used for correcting the training differential feature map based on the feature matrix to obtain a corrected training differential feature map; the training classification unit is used for passing the corrected training difference feature map through the classifier-based parking specification discriminator to obtain a classification loss function value; and the training unit is used for training the vehicle parking image feature extractor, the vehicle parking standard commonality mode feature extractor and the classifier-based parking standard discriminator based on the convolutional neural network model based on the classification loss function value.
In the technical scheme of the application, each feature matrix of the training vehicle parking standard reference feature map expresses image semantic features based on a common mode of the training vehicle parking standard reference image, each feature matrix of the training vehicle parking standard reference image follows the common mode feature distribution based on image semantics of each training vehicle parking standard reference image, each feature matrix of the training vehicle parking state feature map expresses image semantic features of the training vehicle parking state image, and each feature matrix of the training vehicle parking standard reference feature map follows the channel distribution of the convolutional neural network model, so that when the training vehicle parking standard reference feature map and the training vehicle parking state feature map are calculated to obtain the training differential feature map, the training differential feature map also has obvious channel distribution differential representation in the channel dimension, and the feature matrix feature distribution unit of the training feature map is reduced in the whole, thereby influencing the training differential feature map to pass through a classifier, namely, the training differential feature map has an accurate classification result.
Based on the above, the applicant firstly converts each feature matrix in the training differential feature map into a square matrix through linear transformation, and then corrects the training differential feature map based on the feature matrix, specifically expressed as follows; correcting the training differential feature map based on the feature matrix by using the following optimization formula to obtain a corrected training differential feature map; wherein, the optimization formula is: ; wherein, AndRespectively the first of the training differential feature mapsAnd (d)A feature matrix, andAndRespectively, feature matrixAndIs used to determine the global average value of (c),Is the first in the training differential feature mapThe transpose of the individual feature matrices is,Is the first in the training differential feature mapThe inverse of the individual feature matrix is used,Is the first training difference characteristic diagram after correctionThe number of feature matrices is chosen such that,Representing the multiplication by the position point,Representing a matrix multiplication.
Here, the feature matrix of the training differential feature map is used as a seed point for scene transmission in a channel dimension along the center of channel distribution, each feature value of the feature matrix of the training differential feature map is subjected to robust aggregation and sub-sampling proposal through matrix multiplication, so that directional constraint is transmitted by a distribution boundary frame of an adjacent feature matrix on the basis of participation of each feature value of the feature matrix of the training differential feature map, the integrity of feature representation of the training differential feature map is improved on the basis of context correlation of the whole training differential feature map from bottom to top along the channel dimension, and the class probability convergence effect of the training differential feature map through a classifier is improved, namely the speed of classification training and the accuracy of classification results are improved. Like this, can real-time supervision parking area internal vehicle's parking state to in time take a candid photograph and punishment to the parking behavior that breaks rules and regulations, improved the management efficiency in parking area and the management quality in wisdom garden.
In summary, by adopting the above scheme, the camera disposed in the park parking lot is used for monitoring and collecting the vehicle parking state image in real time, and the image processing and analysis algorithm based on artificial intelligence is introduced at the rear end to analyze the vehicle parking state image, and meanwhile, the image processing and analysis algorithm is compared with the reference state commonality mode of the vehicle parking standard, so that whether the vehicle is parked in the standard is judged. Therefore, the parking state of the vehicle in the parking lot can be monitored in real time, and the illegal parking behavior can be captured and punished in time, so that the management efficiency and quality of the parking lot are improved.
FIG. 2 is a flow chart illustrating a SAAS-based intelligent campus management method, as shown in FIG. 2, according to one exemplary embodiment, the method comprising:
Step 201, inputting, inquiring, counting and analyzing basic information, customer information, contract information and cost information of a park;
Step 202, monitoring, maintaining and alarming water, electricity, gas, fire, security and parking lots in the park;
Step 203, publishing, reserving, evaluating and settling property, cleaning, catering and express service of the park;
And 204, carrying out communication, interaction and collaboration among clients of the park to construct an ecological circle of the park.
In one embodiment of the present disclosure, monitoring, maintaining and alerting of hydropower, fire, security and parking areas of the campus, comprising: acquiring a vehicle parking state image acquired by a camera deployed in a park parking lot; extracting a dataset of vehicle parking specification reference images from a database; respectively extracting features of each vehicle parking specification reference image in the data set of the vehicle parking specification reference images through a vehicle parking image feature extractor based on a deep neural network model to obtain a set of vehicle parking specification reference feature images; inputting the set of the vehicle parking specification reference feature maps into a vehicle parking specification commonality mode feature extractor to obtain a vehicle parking specification reference commonality feature map; the feature extraction of the vehicle parking state image is carried out by the vehicle parking image feature extractor based on the deep neural network model so as to obtain a vehicle parking state feature map; and calculating a difference characteristic between the vehicle parking specification reference commonality characteristic diagram and the vehicle parking state characteristic diagram, and determining whether the vehicle is in a parking specification or not based on the difference characteristic.
In one embodiment of the present disclosure, the deep neural network model is a convolutional neural network model.
Referring now to fig. 3, a schematic diagram of an electronic device 600 suitable for use in implementing embodiments of the present disclosure is shown. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 3, the electronic device 600 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data required for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM602, and the RAM603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
In general, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, magnetic tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 600 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via communication means 609, or from storage means 608, or from ROM 602. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 601.
It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText TransferProtocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented in software or hardware. The name of the module is not limited to the module itself in some cases, and for example, the test parameter obtaining module may also be described as "a module for obtaining the device test parameter corresponding to the target device".
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In accordance with one or more embodiments of the present disclosure, example 1 provides a SAAS-based smart campus management system, the system comprising:
The park information management module is used for inputting, inquiring, counting and analyzing basic information, client information, contract information and cost information of the park;
The park facility management module is used for monitoring, maintaining and alarming water, electricity, gas, fire, security and parking lots of the park;
The park service management module is used for publishing, reserving, evaluating and settling property, cleaning, catering and express delivery services of the park;
And the park community management module is used for carrying out communication, exchange, interaction and collaboration among clients of the park to construct a park ecological circle.
In accordance with one or more embodiments of the present disclosure, example 2 provides the system of example 1, the campus facility management module comprising:
An image acquisition unit for the parking state of the vehicle, the method comprises the steps of acquiring a vehicle parking state image acquired by a camera deployed in a park parking lot;
a vehicle parking specification reference image acquisition unit for extracting a dataset of vehicle parking specification reference images from a database;
A vehicle parking standard image feature extraction unit, configured to perform feature extraction on each vehicle parking standard reference image in the data set of the vehicle parking standard reference images through a vehicle parking image feature extractor based on a deep neural network model, so as to obtain a set of vehicle parking standard reference feature images;
the vehicle parking standard reference common mode coding unit is used for inputting the set of the vehicle parking standard reference characteristic diagrams into the vehicle parking standard common mode characteristic extractor to obtain the vehicle parking standard reference common characteristic diagram;
the vehicle parking state feature extraction unit is used for extracting features of the vehicle parking state image through the vehicle parking image feature extractor based on the deep neural network model so as to obtain a vehicle parking state feature map;
And a vehicle parking specification detection unit for calculating a difference feature between the vehicle parking specification reference commonality feature map and the vehicle parking state feature map, and determining whether the vehicle is in a parking specification based on the difference feature.
Example 3 provides the system of example 2, the deep neural network model being a convolutional neural network model, in accordance with one or more embodiments of the present disclosure.
According to one or more embodiments of the present disclosure, example 4 provides the system of example 3, the vehicle parking specification referencing a common mode encoding unit to: inputting the set of the vehicle parking specification reference feature images into the vehicle parking specification commonality mode feature extractor to process according to the following vehicle parking specification commonality formula so as to obtain the vehicle parking specification reference commonality feature images;
wherein, the vehicle parking standard commonality formula is: ; wherein, AndRespectively, the vehicle parking specification reference feature map is the first in the setAnd (d)The individual vehicle parking specifications refer to the feature map,Is a set of the vehicle parking specification reference feature maps,A logarithmic function with a base of 2 is shown,、AndRespectively representing the height, width and number of channels of the vehicle parking specification reference feature map,Reference is made to the number of feature maps in the set of feature maps-1 for the vehicle parking specification,The feature values of the respective positions in the semantic difference feature map are referenced for the vehicle parking specifications,Is the number of feature values in the vehicle parking specification reference semantic difference feature map,For the exponential operation of the feature map,Is the vehicle parking specification reference commonality feature map.
According to one or more embodiments of the present disclosure, example 5 provides the system of example 4, the vehicle parking specification detection unit comprising:
a vehicle parking state feature difference calculation subunit for calculating a difference feature map between the vehicle parking specification reference commonality feature map and the vehicle parking state feature map;
And the vehicle parking standardability judging subunit is used for passing the differential feature map through a parking standardability discriminator based on a classifier to obtain a discrimination result, wherein the discrimination result is used for indicating whether the vehicle is in a parking standardability.
In accordance with one or more embodiments of the present disclosure, example 6 provides the system of example 5, further comprising a training module for training the convolutional neural network model-based vehicle parking image feature extractor, the vehicle parking specification commonality pattern feature extractor, and the classifier-based parking specification discriminator.
Example 7 provides the system of example 6, according to one or more embodiments of the present disclosure, the training module comprising:
The vehicle parking state image acquisition unit is trained, the method comprises the steps of acquiring a parking state image of a training vehicle acquired by a camera deployed in a park parking lot;
A training vehicle parking specification reference image acquisition unit for extracting a data set of a training vehicle parking specification reference image from a database;
The training vehicle parking standard image feature extraction unit is used for respectively carrying out feature extraction on each training vehicle parking standard reference image in the training vehicle parking standard reference image data set through the vehicle parking image feature extractor based on the depth neural network model so as to obtain a set of training vehicle parking standard reference feature images;
The training vehicle parking standard reference common mode coding unit is used for inputting the set of the training vehicle parking standard reference feature graphs into the vehicle parking standard common mode feature extractor to obtain a training vehicle parking standard reference common feature graph;
The training vehicle parking state feature extraction unit is used for extracting features of the training vehicle parking state image through the vehicle parking image feature extractor based on the deep neural network model so as to obtain a training vehicle parking state feature map;
a training vehicle parking state feature difference calculation unit for calculating a training difference feature map between the training vehicle parking specification reference commonality feature map and the training vehicle parking state feature map;
The training correction unit is used for correcting the training differential feature map based on the feature matrix to obtain a corrected training differential feature map;
The training classification unit is used for passing the corrected training difference feature map through the classifier-based parking specification discriminator to obtain a classification loss function value;
And the training unit is used for training the vehicle parking image feature extractor, the vehicle parking standard commonality mode feature extractor and the classifier-based parking standard discriminator based on the convolutional neural network model based on the classification loss function value.
Example 8 provides a SAAS-based smart park management method, according to one or more embodiments of the present disclosure, the method comprising:
Inputting, inquiring, counting and analyzing basic information, customer information, contract information and cost information of the park;
monitoring, maintaining and alarming the water, electricity, gas, fire, security and parking lots in the park;
publishing, reserving, evaluating and settling property, cleaning, catering and express delivery services of the park;
and carrying out communication, exchange, interaction and cooperation among clients of the park to construct the ecological circle of the park.
Example 9 provides the method of example 8, monitoring, maintaining and alerting hydropower, fire, security and parking parks of the park, according to one or more embodiments of the disclosure, comprising: acquiring a vehicle parking state image acquired by a camera deployed in a park parking lot; extracting a dataset of vehicle parking specification reference images from a database; respectively extracting features of each vehicle parking specification reference image in the data set of the vehicle parking specification reference images through a vehicle parking image feature extractor based on a deep neural network model to obtain a set of vehicle parking specification reference feature images; inputting the set of the vehicle parking specification reference feature maps into a vehicle parking specification commonality mode feature extractor to obtain a vehicle parking specification reference commonality feature map; the feature extraction of the vehicle parking state image is carried out by the vehicle parking image feature extractor based on the deep neural network model so as to obtain a vehicle parking state feature map; and calculating a difference characteristic between the vehicle parking specification reference commonality characteristic diagram and the vehicle parking state characteristic diagram, and determining whether the vehicle is in a parking specification or not based on the difference characteristic.
Figure 4 is an application scenario diagram of a SAAS-based intelligent campus management system, according to an example embodiment. As shown in fig. 4, in this application scenario, first, a vehicle parking state image acquired by a camera disposed in a parking lot of a park is acquired (e.g., C1 as illustrated in fig. 4); extracting a dataset of vehicle parking specification reference images from a database (e.g., C2 as illustrated in fig. 4); the acquired data sets of the vehicle parking status image and the vehicle parking profile reference image are then input into a server (e.g., S as illustrated in fig. 4) deployed with a SAAS-based smart park management algorithm, wherein the server is capable of processing the data sets of the vehicle parking status image and the vehicle parking profile reference image based on the SAAS-based smart park management algorithm to determine whether the vehicle is in a parking profile based on the differential features.
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).
Moreover, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are example forms of implementing the claims. The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.

Claims (2)

1. An sais-based intelligent campus management system, comprising:
The park information management module is used for inputting, inquiring, counting and analyzing basic information, client information, contract information and cost information of the park;
The park facility management module is used for monitoring, maintaining and alarming water, electricity, gas, fire, security and parking lots of the park;
The park service management module is used for publishing, reserving, evaluating and settling property, cleaning, catering and express delivery services of the park;
the park community management module is used for carrying out communication, exchange, interaction and collaboration among clients of the park to construct a park ecological circle;
Wherein, the campus facilities management module includes:
An image acquisition unit for the parking state of the vehicle, the method comprises the steps of acquiring a vehicle parking state image acquired by a camera deployed in a park parking lot;
a vehicle parking specification reference image acquisition unit for extracting a dataset of vehicle parking specification reference images from a database;
A vehicle parking standard image feature extraction unit, configured to perform feature extraction on each vehicle parking standard reference image in the data set of the vehicle parking standard reference images through a vehicle parking image feature extractor based on a deep neural network model, so as to obtain a set of vehicle parking standard reference feature images;
the vehicle parking standard reference common mode coding unit is used for inputting the set of the vehicle parking standard reference characteristic diagrams into the vehicle parking standard common mode characteristic extractor to obtain the vehicle parking standard reference common characteristic diagram;
the vehicle parking state feature extraction unit is used for extracting features of the vehicle parking state image through the vehicle parking image feature extractor based on the deep neural network model so as to obtain a vehicle parking state feature map;
a vehicle parking specification detection unit configured to calculate a difference feature between the vehicle parking specification reference commonality feature map and the vehicle parking state feature map, and determine whether a vehicle is in a parking specification based on the difference feature;
the deep neural network model is a convolutional neural network model;
Wherein the vehicle parking specification refers to a common mode encoding unit for: inputting the set of the vehicle parking specification reference feature images into the vehicle parking specification commonality mode feature extractor to process according to the following vehicle parking specification commonality formula so as to obtain the vehicle parking specification reference commonality feature images;
wherein, the vehicle parking standard commonality formula is:
，
wherein, AndRespectively, the vehicle parking specification reference feature map is the first in the setAnd (d)The individual vehicle parking specifications refer to the feature map,Is a set of the vehicle parking specification reference feature maps,A logarithmic function with a base of 2 is shown,、AndRespectively representing the height, width and number of channels of the vehicle parking specification reference feature map,Reference is made to the number of feature maps in the set of feature maps-1 for the vehicle parking specification,The feature values of the respective positions in the semantic difference feature map are referenced for the vehicle parking specifications,Is the number of feature values in the vehicle parking specification reference semantic difference feature map,For the exponential operation of the feature map,Is the vehicle parking specification reference commonality feature map;
Wherein, the vehicle parking specification detection unit includes:
a vehicle parking state feature difference calculation subunit for calculating a difference feature map between the vehicle parking specification reference commonality feature map and the vehicle parking state feature map;
the vehicle parking standardability judging subunit is used for enabling the differential feature map to pass through a parking standardability discriminator based on a classifier to obtain a discrimination result, wherein the discrimination result is used for indicating whether a vehicle is in a standardability or not;
The system further comprises a training module for training the vehicle parking image feature extractor based on the convolutional neural network model, the vehicle parking specification commonality mode feature extractor and the classifier-based parking specification discriminator;
Wherein, training module includes:
The vehicle parking state image acquisition unit is trained, the method comprises the steps of acquiring a parking state image of a training vehicle acquired by a camera deployed in a park parking lot;
A training vehicle parking specification reference image acquisition unit for extracting a data set of a training vehicle parking specification reference image from a database;
The training vehicle parking standard image feature extraction unit is used for respectively carrying out feature extraction on each training vehicle parking standard reference image in the training vehicle parking standard reference image data set through the vehicle parking image feature extractor based on the depth neural network model so as to obtain a set of training vehicle parking standard reference feature images;
The training vehicle parking standard reference common mode coding unit is used for inputting the set of the training vehicle parking standard reference feature graphs into the vehicle parking standard common mode feature extractor to obtain a training vehicle parking standard reference common feature graph;
The training vehicle parking state feature extraction unit is used for extracting features of the training vehicle parking state image through the vehicle parking image feature extractor based on the deep neural network model so as to obtain a training vehicle parking state feature map;
a training vehicle parking state feature difference calculation unit for calculating a training difference feature map between the training vehicle parking specification reference commonality feature map and the training vehicle parking state feature map;
The training correction unit is used for correcting the training differential feature map based on the feature matrix to obtain a corrected training differential feature map;
The training classification unit is used for passing the corrected training difference feature map through the classifier-based parking specification discriminator to obtain a classification loss function value;
And the training unit is used for training the vehicle parking image feature extractor, the vehicle parking standard commonality mode feature extractor and the classifier-based parking standard discriminator based on the convolutional neural network model based on the classification loss function value.
2. A method for SAAS-based intelligent campus management using the SAAS-based intelligent campus management system of claim 1, comprising:
Inputting, inquiring, counting and analyzing basic information, customer information, contract information and cost information of the park;
monitoring, maintaining and alarming the water, electricity, gas, fire, security and parking lots in the park;
publishing, reserving, evaluating and settling property, cleaning, catering and express delivery services of the park;
and carrying out communication, exchange, interaction and cooperation among clients of the park to construct the ecological circle of the park.
CN202410260865.5A 2024-03-07 2024-03-07 SAAS-based intelligent park management system and method Active CN118037231B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410260865.5A CN118037231B (en) 2024-03-07 2024-03-07 SAAS-based intelligent park management system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410260865.5A CN118037231B (en) 2024-03-07 2024-03-07 SAAS-based intelligent park management system and method

Publications (2)

Publication Number Publication Date
CN118037231A CN118037231A (en) 2024-05-14
CN118037231B true CN118037231B (en) 2024-08-13

Family

ID=90987420

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410260865.5A Active CN118037231B (en) 2024-03-07 2024-03-07 SAAS-based intelligent park management system and method

Country Status (1)

Country Link
CN (1) CN118037231B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118365009B (en) * 2024-06-20 2024-09-06 青岛熙正数字科技有限公司 Intelligent environment-friendly service system and method based on SaaS

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113378690A (en) * 2021-06-08 2021-09-10 盐城工学院 In-road irregular parking identification method based on video data
CN117216134A (en) * 2023-07-03 2023-12-12 唐山万唯网络科技有限公司 Cloud storage system for park comprehensive service management

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
ES2178962B1 (en) * 2001-04-09 2003-06-16 Garavano Carlos Antonio Gallo SYSTEM TO FIND PARKED VEHICLES WITHIN BUILDINGS AND IN COVERED SURFACES.
US9853488B2 (en) * 2008-07-11 2017-12-26 Charge Fusion Technologies, Llc Systems and methods for electric vehicle charging and power management
US20160180261A1 (en) * 2015-08-27 2016-06-23 Sparkcity.Com Ltd. System and method of creating a dynamic parking spot and a system and method of creating a dynamic parking zone\region
CN108563993A (en) * 2018-03-13 2018-09-21 宋希刚 Data processing method and system of the vehicle based on parking image
KR102154798B1 (en) * 2019-01-14 2020-09-10 중앙대학교 산학협력단 System for detecting vacant and full places parking lot and method thereof
CN114022115A (en) * 2021-11-04 2022-02-08 国网辽宁省电力有限公司营销服务中心 Laboratory management information system and operation method
CN218409197U (en) * 2022-09-21 2023-01-31 杭州央博科技有限公司 Park information display screen

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113378690A (en) * 2021-06-08 2021-09-10 盐城工学院 In-road irregular parking identification method based on video data
CN117216134A (en) * 2023-07-03 2023-12-12 唐山万唯网络科技有限公司 Cloud storage system for park comprehensive service management

Also Published As

Publication number Publication date
CN118037231A (en) 2024-05-14

Similar Documents

Publication Publication Date Title
CN118037231B (en) SAAS-based intelligent park management system and method
CN111401228B (en) Video target labeling method and device and electronic equipment
CN110942524A (en) Cloud edge end cooperative parking management timing charging system and method based on block chain
CN110704491B (en) Data query method and device
CN111405475A (en) Multidimensional sensing data collision fusion analysis method and device
CN114898154A (en) Incremental target detection method, device, equipment and medium
Gao et al. A new curb lane monitoring and illegal parking impact estimation approach based on queueing theory and computer vision for cameras with low resolution and low frame rate
CN110866524A (en) License plate detection method, device, equipment and storage medium
CN109166336B (en) Real-time road condition information acquisition and pushing method based on block chain technology
CN108447257B (en) Web-based traffic data analysis method and system
CN111199639B (en) Method, device and system for adjusting parking fence area and server
CN114708545A (en) Image-based object detection method, device, equipment and storage medium
CN111405324B (en) Method, device and system for pushing audio and video file
Lu et al. An intelligent system for taxi service: Analysis, prediction and visualization
CN111627242B (en) Fusion positioning method for parking spaces in indoor parking garage
CN113780247B (en) Traffic light detection method and device, electronic equipment and computer readable medium
CN112810489B (en) Safe charging management system for new energy automobile
CN116824348A (en) Hidden danger information generation method, hidden danger information generation device, electronic equipment and computer readable medium
CN112967105B (en) Order information processing method, equipment, storage medium and computer program product
CN116543367A (en) Method, device, equipment and medium for generating parking space information based on fisheye camera
CN112560700B (en) Information association method and device based on action analysis and electronic equipment
CN115409985A (en) Target object detection method and device, electronic equipment and readable storage medium
CN110334763B (en) Model data file generation method, model data file generation device, model data file identification device, model data file generation apparatus, model data file identification apparatus, and model data file identification medium
CN111401224B (en) Target detection method and device and electronic equipment
CN114627400A (en) Lane congestion detection method and device, electronic equipment 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
GR01 Patent grant
GR01 Patent grant