CN111915899A

CN111915899A - Parking space monitoring management method and system

Info

Publication number: CN111915899A
Application number: CN202010816489.5A
Authority: CN
Inventors: 张予; 温学疆; 苏明; 郭相权
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2020-08-14
Filing date: 2020-08-14
Publication date: 2020-11-10

Abstract

A parking space monitoring management method and a system thereof are provided, the method comprises: acquiring an original image of a vehicle, and acquiring owner information according to the original image of the vehicle; recommending a plurality of remaining parking spaces to the vehicle owner according to the vehicle owner information, the parking space types and the parking space numbers corresponding to the current remaining parking spaces; and sending a corresponding position navigation map to the vehicle owner according to the remaining parking spaces selected by the vehicle owner. The parking space monitoring and management method and system can help a car owner to find a parking space suitable for parking as soon as possible, and safety management of a large parking lot is facilitated.

Description

Parking space monitoring management method and system

Technical Field

The application relates to the field of artificial intelligence and intelligent driving, in particular to a parking space monitoring management method and system.

Background

At present, most parking lots in large public places and shopping malls only inform car owners to be parked of the number of remaining parking spaces in the parking lots, but can not recommend parking spaces to the car owners according to the types of cars to be parked and the demands of the car owners for the car owners to select. Therefore, the car owner may spend much time in the process of finding the parking space through rolling. Especially for car owners whose driving technique is not yet mature, the complex parking lot environment is prone to cause parking pressure thereon. In addition, when the car owner parks the car on a complicated public transportation road section, traffic jam and even traffic accidents can be caused by long parking time.

Disclosure of Invention

Aiming at the problems in the prior art, the parking space monitoring management method and the parking space monitoring management system can help a car owner to find a parking space suitable for parking as soon as possible, and safety management of a large parking lot is facilitated.

In order to solve at least one of the above problems, the present application provides the following technical solutions:

in a first aspect, the present application provides a parking space monitoring and management method, including:

acquiring an original image of a vehicle, and acquiring owner information according to the original image of the vehicle; the vehicle owner information includes: at least one of vehicle model, vehicle owner driving age and vehicle owner historical driving record;

recommending a plurality of remaining parking spaces to the vehicle owner according to the vehicle owner information, the parking space types and the parking space numbers corresponding to the current remaining parking spaces;

and sending a corresponding position navigation map to the vehicle owner according to the remaining parking spaces selected by the vehicle owner.

Further, the acquiring of the owner information according to the original image of the vehicle comprises:

identifying the original vehicle image to obtain a license plate number corresponding to the original vehicle image;

and acquiring the vehicle owner information according to the license plate number.

Further, the identifying the original vehicle image comprises:

processing the acquired original vehicle image by using a vehicle detection model obtained by pre-training to obtain a high-definition vehicle image;

inputting the vehicle high-definition image into a license plate detection model obtained through pre-training to obtain a license plate high-definition image;

and inputting the high-definition license plate image into a license plate recognition model obtained by pre-training to obtain a license plate number corresponding to the original vehicle image.

Further, the step of training the vehicle detection model comprises:

obtaining original samples of the vehicle images in a vehicle image sample library;

and inputting the original sample of the vehicle image into a YOLOv2 network model for training to obtain the vehicle detection model.

Further, the step of training the license plate detection model comprises:

randomly grouping the original vehicle image samples;

adjusting the proportion between the vehicle detection frame and the image boundary frame of each vehicle image original sample by using a scaling factor to obtain a vehicle image high-definition sample;

and inputting the vehicle image high-definition samples into a WPOD network model according to groups for training to obtain a license plate detection model.

Further, the step of training the license plate recognition model comprises:

training a FAST-YOLO network model by using an initial data training set to obtain a license plate recognition initial model;

processing a vehicle image high-definition sample by using a license plate detection model obtained by pre-training to obtain a license plate high-definition sample;

labeling the license plate high-definition sample;

and inputting the marked high-definition sample of the license plate image into the license plate recognition initial model for training to obtain the license plate recognition model.

Further, the parking space monitoring and managing method further comprises the following steps:

when the number of the car owners is multiple, identifying the current car owner;

and acquiring the corresponding owner information according to the identified current owner.

and if the remaining parking spaces recommended to the vehicle owner cannot meet the requirements of the vehicle owner, recommending a plurality of remaining parking spaces to the vehicle owner again according to the reasons of non-satisfaction.

In a second aspect, the present application provides a parking space monitoring and management system, including:

the acquisition unit is used for acquiring an original image of a vehicle and acquiring owner information according to the original image of the vehicle;

the recommendation unit is used for recommending a plurality of remaining parking spaces to the vehicle owner according to the vehicle owner information, the parking space types and the parking space numbers corresponding to the current remaining parking spaces;

and the transmitting unit is used for transmitting the corresponding position navigation map to the vehicle owner according to the remaining parking spaces selected by the vehicle owner.

Further, the acquisition unit includes:

the identification module is used for identifying the original vehicle image to obtain a license plate number corresponding to the original vehicle image;

and the acquisition module is used for acquiring the vehicle owner information according to the license plate number.

Further, the identification module includes:

the vehicle detection submodule is used for processing the acquired original vehicle image by using a vehicle detection model obtained through pre-training to obtain a high-definition vehicle image;

the license plate detection submodule is used for inputting the vehicle high-definition image into a license plate detection model obtained through pre-training to obtain a license plate high-definition image;

and the license plate recognition sub-module is used for inputting the high-definition license plate image into a license plate recognition model obtained through pre-training to obtain a license plate number corresponding to the original vehicle image.

Further, the parking space monitoring and management system further comprises:

the sample acquisition unit is used for acquiring original samples of the vehicle images in the vehicle image sample library;

and the training unit is used for inputting the original vehicle image sample into a YOLOv2 network model for training to obtain the vehicle detection model.

Further, the parking space monitoring and management system further comprises:

the grouping unit is used for randomly grouping the original vehicle image samples;

the scaling unit is used for adjusting the proportion between the vehicle detection frame and the image boundary frame of each vehicle image original sample by using a scaling factor to obtain a vehicle image high-definition sample;

and the training unit is also used for inputting the vehicle image high-definition samples into a WPOD network model according to groups for training to obtain a license plate detection model.

Further, the parking space monitoring and management system further comprises:

the training unit is also used for training the FAST-YOLO network model by using an initial data training set to obtain a license plate recognition initial model;

the processing unit is used for processing the vehicle image high-definition sample by using a pre-trained license plate detection model to obtain a license plate high-definition sample;

the marking unit is used for marking the license plate high-definition samples;

the training unit is further used for inputting the marked license plate image high-definition sample into the license plate recognition initial model for training to obtain the license plate recognition model.

Further, the parking space monitoring and management system further comprises:

the vehicle owner identification unit is used for identifying a current vehicle owner when a plurality of vehicle owners exist;

the acquiring unit is further configured to acquire the corresponding owner information according to the identified current owner.

Further, the parking space monitoring and management system further comprises: and if the remaining parking spaces recommended to the vehicle owner cannot meet the requirements of the vehicle owner, the recommending unit is further used for recommending a plurality of remaining parking spaces to the vehicle owner again according to the reasons of non-satisfaction.

In a third aspect, the present application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the parking space monitoring and management method when executing the program.

In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the parking space monitoring and managing method.

According to the technical scheme, the parking space monitoring and management method and the parking space monitoring and management system can acquire the information of the car owner by identifying the license plate number of the vehicle to be parked, recommend the alternative parking space to the car owner according to the information of the car owner, help the car owner to find the parking space suitable for parking as soon as possible, fully relieve the problem of inconvenience in parking in public places and facilitate the safety management of large-scale parking lots.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a general flowchart of a parking space monitoring and managing method in an embodiment of the present application;

FIG. 2 is a flowchart illustrating an embodiment of obtaining owner information from an original image of a vehicle;

FIG. 3 is a flowchart illustrating an embodiment of the present disclosure for recognizing an original image of a vehicle;

FIG. 4 is a flowchart illustrating the steps of training a vehicle detection model according to an embodiment of the present disclosure;

FIG. 5 is a flowchart illustrating the steps of training a license plate detection model according to an embodiment of the present disclosure;

FIG. 6 is a flowchart illustrating the steps of training a license plate recognition model according to an embodiment of the present disclosure;

fig. 7 is a second general flowchart of the parking space monitoring and managing method according to the embodiment of the present application;

fig. 8 is one of general structural diagrams of a parking space monitoring and managing system in an embodiment of the present application;

FIG. 9 is a diagram illustrating a structure of an acquisition unit according to an embodiment of the present application;

FIG. 10 is a block diagram of an identification module in an embodiment of the present application;

fig. 11 is a second general structure diagram of the parking space monitoring and managing system in the embodiment of the present application;

fig. 12 is a third general structural diagram of a parking space monitoring and managing system in the embodiment of the present application;

fig. 13 is a fourth general structural diagram of the parking space monitoring and managing system in the embodiment of the present application;

FIG. 14 is a block diagram of a training unit in an embodiment of the present application;

fig. 15 is a schematic structural diagram of an electronic device in an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Referring to fig. 1, in order to help a car owner to find a parking space suitable for parking as soon as possible, fully alleviate the problem of inconvenience in parking in public places and facilitate safety management of large-scale parking lots, the application provides a parking space monitoring and management method, which includes:

s101: and acquiring an original image of the vehicle, and acquiring owner information according to the original image of the vehicle.

It can be understood that when the vehicle to be parked reaches the entrance of the parking lot, the camera device at the entrance of the parking lot can acquire the original image of the vehicle by taking a picture or the like, where the original image of the vehicle is the overall appearance image of the vehicle to be parked. And the license plate number of the vehicle to be parked is identified according to the original image of the vehicle, so that the information of the vehicle owner corresponding to the vehicle to be parked is obtained. These owner information may include: at least one of the vehicle model, the driving age of the vehicle owner and the historical driving record of the vehicle owner can further comprise: the vehicle owner identity, the vehicle owner gender and other information which can provide basis for the parking space recommendation.

S102: and recommending a plurality of remaining parking spaces to the vehicle owner according to the vehicle owner information, the parking space types and the parking space numbers corresponding to the current remaining parking spaces.

It can be understood that, for a large parking lot in a public place, the situation around the parking space may be very complicated, and there are possibilities of the parking space being arranged obliquely and in an arc direction. In addition, some parking spaces may be located at a certain corner in the parking lot, or the parking spaces themselves are free and available, but the surrounding of the parking spaces are full of vehicles, so that the vehicles to be parked cannot enter the parking spaces to park. Therefore, the parking space types can be divided according to the surrounding environment of the parking space, the parking difficulty needs to be considered when the parking space is divided, whether the parking space is convenient for people with limited physical conditions (such as disabled people) to use or not needs to be considered, and the like. In addition, every parking stall in the parking area all has the number that oneself corresponds, and the parking stall number can play the identification effect at the in-process that follow-up parking stall was recommended. Therefore, after the parking place types corresponding to the current remaining parking places are mastered, the parking place monitoring and management system can recommend the remaining parking places to the vehicle owner in a targeted manner according to the information of the vehicle owner, the parking place types corresponding to the current remaining parking places and the parking place numbers. The recommended remaining parking spaces can be multiple, and the vehicle owner can select from the recommended remaining parking spaces according to own preference.

S103: and sending a corresponding position navigation map to the vehicle owner according to the remaining parking spaces selected by the vehicle owner.

It can be understood that, after the car owner selects a remaining car space, the car space monitoring and managing system can send the car owner a position navigation map of the selected remaining car space, so that the car owner can reach the selected car space more quickly. The process of sending a position navigation map can be seen in the prior art.

From the above description, the parking space monitoring and management method provided by the application obtains the information of the vehicle owner by identifying the license plate number of the vehicle to be parked, and recommends the alternative parking space to the vehicle owner according to the information of the vehicle owner, so that the vehicle owner can be helped to find the parking space suitable for parking as soon as possible, the problem of inconvenience in parking in public places is fully alleviated, and the safety management of large-scale parking lots is facilitated.

Referring to fig. 2, in order to obtain owner information for subsequent more targeted recommendation of remaining parking spaces, in the parking space monitoring management method provided by the application, obtaining owner information according to the original image of the vehicle includes:

s201: and identifying the original image of the vehicle to obtain the license plate number corresponding to the original image of the vehicle.

It can be understood that the camera device can capture the original image of the vehicle to be parked when the vehicle passes through the entrance of the parking lot. These original images of the vehicle may not be very clear and have much background noise. If the original images of the vehicles are directly used for license plate number recognition, wrong recognition results are easily generated, and the residual parking space recommendation effect is influenced. Therefore, before the license plate number is identified, the original image of the vehicle needs to be processed to be clear, and the license plate position is intentionally highlighted, and the specific processing method is described in detail below. After the original image of the vehicle is processed, the license plate number corresponding to the original image of the vehicle can be identified by the specific identification method in the embodiment of the application and by the specific identification model in the embodiment of the application. Specific identification methods are described below.

S202: and acquiring the information of the vehicle owner according to the license plate number.

It can be understood that in most cases, one license plate number corresponds to one vehicle owner. And the parking space monitoring and management system can acquire the information of the vehicle owner according to the license plate number. The specific obtaining mode may include:

1) and the vehicle management station is used for interfacing with the vehicle management station and providing the owner information corresponding to the current license plate number.

2) And developing a special application program for the parking space monitoring and management system, wherein the vehicle owner of the vehicle to be parked can log in the application program and fill in related vehicle owner information on line.

According to the above description, the parking space monitoring and management method provided by the application can obtain the license plate number corresponding to the original vehicle image by performing a series of processing on the original vehicle image and finally performing identification, and then can obtain the information of the vehicle owner through different channels according to the license plate number.

Referring to fig. 3, in order to finally obtain a license plate number corresponding to an original vehicle image, in the parking space monitoring and management method provided by the present application, identifying the original vehicle image includes:

s301: and processing the acquired original vehicle image by using a vehicle detection model obtained by pre-training to obtain a high-definition vehicle image.

It can be understood that, because the original image of the vehicle may not be clear, and because of the limitation of the shooting environment, other scenes irrelevant to the license plate recognition may appear around the vehicle in the original image of the vehicle, which may interfere with the recognition process and affect the final recognition effect. Therefore, after the original image of the vehicle is subjected to the sharpening processing to obtain the high-definition image of the vehicle, the subsequent license plate recognition step can be performed. In order to meet the requirement of processing the vehicle raw image in the embodiments described in the present application, the vehicle detection model needs to be trained in advance. After the vehicle detection model is trained, the original image of the vehicle can be input into the vehicle detection model obtained by pre-training, and the image output after model processing is the high-definition image of the vehicle. The high-definition image of the vehicle is a clean and clear image of the vehicle to be parked, wherein the noise around the vehicle body is removed. Through the image, the parking space monitoring and management system can acquire the owner information such as the type (size) of the vehicle and the like so as to promote the subsequent step of recommending the remaining parking space.

S302: and inputting the high-definition images of the vehicles into a license plate detection model obtained by pre-training to obtain the high-definition images of the license plates.

It can be understood that although the vehicle high-definition image is clean and clear, most contents in the vehicle high-definition image are still vehicle appearance, the key content of the license plate cannot be highlighted, and the license plate number cannot be directly identified by using the vehicle high-definition image. Therefore, the contents of the vehicle body part in the vehicle high-definition image need to be removed, the license plate contents are simply left, the license plate high-definition image is obtained, and the subsequent license plate identification step can be advanced. In order to obtain a high-definition image of the license plate, a license plate detection model is required to be used, and the license plate detection model is obtained after being trained in advance. After the license plate detection model is trained, the high-definition images of the vehicle can be input into the license plate detection model obtained through pre-training, and the images output after model processing are the high-definition images of the license plate. In the high-definition image of the license plate, the only existing content is the license plate, so that the license plate number can be fully and clearly displayed.

S303: and inputting the high-definition license plate image into a license plate recognition model obtained by pre-training to obtain a license plate number corresponding to the original vehicle image.

It can be understood that the license plate high-definition image may contain Chinese characters, English letters and numbers, and the license plate recognition model is also obtained through pre-training. And inputting the high-definition license plate image into a license plate recognition model obtained by pre-training, and outputting the license plate number corresponding to the original vehicle image.

From the above description, the parking space monitoring and management method provided by the application can sequentially complete processing of the original image of the vehicle, processing of the high-definition image of the vehicle and recognition of the license plate number by using the pre-obtained training vehicle detection model, the license plate detection model and the license plate recognition model, and provides a basis for subsequent recommendation of the remaining parking spaces.

Referring to fig. 4, in order to complete the processing of the original image of the vehicle, the vehicle detection model needs to be trained in advance, and the training of the vehicle detection model includes:

s401: obtaining original samples of the vehicle images in a vehicle image sample library;

it is understood that the vehicle image sample library stores a plurality of vehicle image raw samples, which may be image samples with background noise such as the surrounding environment of the vehicle. Some samples are not even very sharp. The diversification of the samples can provide a better training basis for the training of the vehicle detection model.

S402: and inputting the original sample of the vehicle image into a YOLOv2 network model for training to obtain a vehicle detection model.

It can be understood that, with the original sample of the vehicle image, the original sample can be input into the YOLOv2 network model for expansion training to obtain the vehicle detection model. The specific training algorithm may refer to the prior art relating to the YOLOv2 network model. The trained vehicle detection model can process the original image of the vehicle to obtain a high-definition image of the vehicle.

From the above description, the parking space monitoring and management method provided by the application can complete training and finally obtain the vehicle detection model by using the vehicle image original sample and the YOLOv2 network model, so that the vehicle original image is processed in the actual application process to obtain the high-definition image of the vehicle.

Referring to fig. 5, in order to complete the processing of the high-definition images of the vehicle and obtain the high-definition images of the license plate, a license plate detection model needs to be trained in advance, and the step of training the license plate detection model includes:

s501: randomly grouping original samples of the vehicle images;

it can be understood that, when the license plate detection model is trained, original samples of the vehicle images are randomly grouped, the number of the samples contained in each group can be different, and the content of the samples is randomly dispersed. Therefore, the diversity of the samples can be embodied to a greater extent, and the training basis is enriched.

S502: adjusting the proportion between the vehicle detection frame and the image boundary frame of each vehicle image original sample by using the scaling factor to obtain a vehicle image high-definition sample;

it can be understood that, the image bounding box is an outer bounding box of the original sample of the vehicle image, and is usually a rectangular box; the vehicle detection frame is a frame that contains only the outermost outline of the vehicle itself, typically another rectangular frame. The size of the image bounding box is generally larger than the size of the vehicle detection box. Obviously, the closer the size of the vehicle detection frame is to the size of the image boundary frame, the clearer the vehicle can fill the original sample space of the whole vehicle image, and the easier the vehicle detection model can be trained.

Therefore, the embodiment described in the application introduces the concept of the scaling factor, and the scaling factor is used to increase the proportion between the vehicle detection frame and the image boundary frame of each vehicle image original sample, so as to obtain a vehicle image high-definition sample. Scaling factor f in the embodiments described in the present application_swIs improved, namely:

wherein, W_vAnd H_vRespectively representing the width and height values of the vehicle detection frame, D_maxAnd D_minThe statistical units of the above parameters are pixel points, which are set as 608 and 288 according to experience.

S503: and inputting the original vehicle image samples into the WPOD network model according to the groups for training to obtain the license plate detection model.

It can be understood that, since the model to be trained is a detection model for the license plate, before the original sample of the vehicle image is input to the WPOD network model for training, the license plate portion of the original sample of the vehicle image needs to be marked and highlighted, so that the WPOD network model can know that the aspect of deep learning is the license plate. In this embodiment, the learning rate of the WPOD network model is set to 0.001, the number of characteristic channels is set to 8 channels, and the size of the convolution kernel is set to 3 × 3.

According to the above description, the parking space monitoring and management method provided by the application inputs the original vehicle image sample into the WPOD network model for training, so that the license plate detection model can be obtained.

Referring to fig. 6, in order to complete the recognition of the license plate number, a license plate recognition model needs to be trained first, and the step of training the license plate recognition model includes:

s601: and training the FAST-YOLO network model by using an initial data training set to obtain a license plate recognition initial model.

It will be appreciated that the initial training set of data may be an ImageNet 1000 class data set containing a large number of vehicle image samples. The vehicle image samples are input into a FAST-YOLO network model for training, and the training of the first 20 convolutional layers, 1 Average pooling layer and 1 full-connection layer of the FAST-YOLO network model can be completed, so that the parameter initialization of the FAST-YOLO network model is realized.

S602: and processing the vehicle image high-definition sample by using a license plate detection model obtained by pre-training to obtain a license plate high-definition sample.

The vehicle license plate detection model can be put into use after the training of the vehicle license plate detection model is completed, and the processing of the vehicle image high-definition sample is completed. And inputting the high-definition vehicle image sample into a license plate detection model to obtain a clear license plate high-definition sample.

S603: and marking the high-definition sample of the vehicle image.

It can be understood that the embodiments described herein can adopt a VOC 20 labeling method to label the license plate number in the high definition sample of the vehicle image. Namely, the license plate numbers corresponding to the high-definition samples of the vehicle images are known in advance, so that comparison can be performed in the subsequent training process, and the training effect of the model is improved.

S604: and inputting the marked high-definition sample of the license plate image into the license plate recognition initial model for training to obtain the license plate recognition model.

The method can be understood that the marked license plate image high-definition sample is input into a license plate recognition initial model for training, and the license plate recognition model can be obtained. The training is based on the FAST-YOLO network model whose parameter initialization is completed in step S601.

According to the above description, the parking space monitoring and management method provided by the application can complete the training of the license plate recognition model by using the initial data training set and the license plate image high-definition sample.

Referring to fig. 7, since the owner of the same vehicle does not necessarily have only one owner, the vehicle parking space monitoring and managing method further includes:

s701: when a plurality of vehicle owners correspond to the vehicles, identifying the current vehicle owner;

it can be understood that, because the vehicle space monitoring and managing system can be provided for the vehicle owners by means of the application program, when there are a plurality of vehicle owners corresponding to the vehicle, the vehicle space monitoring and managing system can display a plurality of possible vehicle owners corresponding to the vehicle owner currently driving the vehicle through the interface of the application program. These potential owners are the ones who historically driven the vehicle, and this historical information can also be obtained in advance by the vehicle slot monitoring management system installed on the application. When the current owner driving the vehicle sees a plurality of owners displayed by the application program, the current owner can select one owner and inform the vehicle parking space monitoring and management system through the application program.

S702: and acquiring corresponding owner information according to the identified current owner.

It can be understood that, when the current owner is selected, the vehicle parking space monitoring and management system may obtain the corresponding owner information by using the method in step S202.

According to the above description, the parking space monitoring and management method provided by the application can still obtain the owner information corresponding to the current driving owner according to the result of man-machine interaction under the condition that the same vehicle corresponds to a plurality of owners, so that the recommendation of the remaining parking spaces is facilitated.

In one embodiment, if the remaining parking spaces recommended to the car owner cannot meet the requirements of the car owner, a plurality of remaining parking spaces are recommended to the car owner again according to the reasons which cannot be met.

It can be understood that sometimes, the car owner may not be satisfied with the remaining parking spaces recommended by the parking space monitoring and management system for personal reasons, and at this time, the car owner may refuse all the remaining parking spaces recommended to the car owner, and request the parking space monitoring and management system to recommend the parking spaces for the car owner again. Under the condition, the car owner can click the key through the application program, and the parking space monitoring and management system is required to recommend the remaining parking spaces for the car owner again. In addition, in order to obtain a recommendation result more satisfying for the vehicle owner when the vehicle is recommended again, the vehicle owner can inform the parking space monitoring and management system of the reason of dissatisfaction with the recommended parking space through the application program.

According to the above description, the parking space monitoring and management method provided by the application can recommend the remaining parking spaces for the car owner again according to the dissatisfaction reasons provided by the car owner.

Based on the same inventive concept, the embodiment of the present application further provides a parking space monitoring and management system, which can be used for implementing the method described in the above embodiment, as described in the following embodiments. Because the principle of solving the problems of the parking space monitoring and management system is similar to that of the parking space monitoring and management method, the implementation of the parking space monitoring and management system can refer to the implementation of a software performance benchmark-based determination method, and repeated parts are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.

Referring to fig. 8, in order to help an owner to find a parking space suitable for parking as soon as possible, fully alleviate the problem of inconvenience in parking in public places, and facilitate safety management of large parking lots, the present application provides a parking space monitoring and management system, which includes an obtaining unit 801, a recommending unit 802, and a sending unit 803.

An obtaining unit 801, configured to obtain an original vehicle image, and obtain owner information according to the original vehicle image;

a recommending unit 802, configured to recommend a plurality of remaining parking spaces to a vehicle owner according to the vehicle owner information and parking space types and parking space numbers corresponding to the current remaining parking spaces;

and the sending unit 803 is configured to send a corresponding position navigation map to the vehicle owner according to the remaining parking spaces selected by the vehicle owner.

According to the parking space monitoring and management system, the license plate number of the vehicle to be parked is identified to obtain the information of the vehicle owner, the alternative parking space is recommended to the vehicle owner according to the information of the vehicle owner, the vehicle owner can be helped to find the parking space suitable for parking as soon as possible, the problem of inconvenience in parking in public places is fully solved, and the safety management of a large parking lot is facilitated.

Referring to fig. 9, the obtaining unit 801 includes an identifying module 901 and a obtaining module 902.

The identification module 901 is configured to identify the original vehicle image to obtain a license plate number corresponding to the original vehicle image;

and the obtaining module 902 is configured to obtain the vehicle owner information according to the license plate number.

Referring to fig. 10, the identification module includes: a vehicle detection submodule 1001, a license plate detection submodule 1002 and a license plate identification submodule 1003.

The vehicle detection submodule 1001 is configured to process the acquired original vehicle image by using a vehicle detection model obtained through pre-training to obtain a high-definition vehicle image;

the license plate detection submodule 1002 is configured to input the vehicle high-definition image into a license plate detection model obtained through pre-training to obtain a license plate high-definition image;

and the license plate recognition sub-module 1003 is used for inputting the license plate high-definition image into a license plate recognition model obtained through pre-training to obtain a license plate number corresponding to the original image of the vehicle.

Referring to fig. 11, the parking space monitoring and managing system further includes: a sample acquisition unit 1101 and a training unit 1102.

A sample acquiring unit 1101 for acquiring a vehicle image original sample in the vehicle image sample library;

the training unit 1102 is configured to input the original vehicle image sample into a YOLOv2 network model for training, so as to obtain the vehicle detection model.

Referring to fig. 12, the parking space monitoring and managing system further includes a grouping unit 1201, a scaling unit 1202, and the training unit 1102.

A grouping unit 1201, configured to randomly group the vehicle image original samples;

the scaling unit 1202 is configured to adjust a ratio between a vehicle detection frame and an image boundary frame of each vehicle image original sample by using a scaling factor to obtain a vehicle image high-definition sample;

the training unit 1102 is further configured to input the vehicle image high-definition samples to a WPOD network model for training according to groups, so as to obtain a license plate detection model.

Referring to fig. 13, the parking space monitoring and managing system further includes: the training unit 1102, the processing unit 1302, and the labeling unit 1303.

The training unit 1102 is further configured to train the FAST-YOLO network model by using an initial data training set to obtain a license plate recognition initial model;

the processing unit 1302 is configured to process a vehicle image high-definition sample by using a license plate detection model obtained through pre-training to obtain a license plate high-definition sample;

the labeling unit 1303 is used for labeling the high-definition license plate samples;

the training unit 1102 is further configured to input the marked license plate image high-definition sample into the license plate recognition initial model for training, so as to obtain the license plate recognition model.

Referring to fig. 14, the parking space monitoring and managing system further includes an identification unit 1401 and the obtaining unit 801:

an identification unit 1401 for identifying a current vehicle owner when a plurality of vehicle owners are present;

the obtaining unit 801 is further configured to obtain the corresponding owner information according to the identified current owner.

Parking stall control management system still includes: if the remaining parking spaces recommended to the vehicle owner cannot meet the vehicle owner demand, the recommendation unit 802 is further specifically configured to recommend a plurality of remaining parking spaces to the vehicle owner again according to the unsatisfied reason.

In order to provide a customized distributed image recognition service for a customer, improve an image recognition effect, and optimize an image recognition experience of the customer, an embodiment of an electronic device for implementing all or part of the contents in the parking space monitoring management method is provided in the present application, where the electronic device specifically includes the following contents:

a Processor (Processor), a Memory (Memory), a communication Interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the communication interface is used for realizing information transmission between the parking space monitoring and management system and relevant equipment such as a core service system, a user terminal, a relevant database and the like; the logic controller may be a desktop computer, a tablet computer, a mobile terminal, and the like, but the embodiment is not limited thereto. In this embodiment, the logic controller may be implemented with reference to the embodiment of the parking space monitoring and managing method and the embodiment of the parking space monitoring and managing system in the embodiment, which are incorporated herein by reference, and repeated descriptions thereof are omitted.

It is understood that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a Personal Digital Assistant (PDA), an in-vehicle device, a smart wearable device, and the like. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch, intelligent bracelet etc..

In practical applications, part of the parking space monitoring and managing method may be executed on the electronic device side as described above, or all operations may be completed in the client device. The selection may be specifically performed according to the processing capability of the client device, the limitation of the user usage scenario, and the like. This is not a limitation of the present application. The client device may further include a processor if all operations are performed in the client device.

The client device may have a communication module (i.e., a communication unit), and may be communicatively connected to a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, the server may also include a server on an intermediate platform, for example, a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed apparatus.

Fig. 15 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application. As shown in fig. 15, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 15 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.

In one embodiment, the parking space monitoring and management method function may be integrated into the central processor 9100. The central processor 9100 may be configured to control as follows:

s101: acquiring an original image of a vehicle, and acquiring owner information according to the original image of the vehicle;

s102: recommending a plurality of remaining parking spaces to the vehicle owner according to the vehicle owner information, the parking space types and the parking space numbers corresponding to the current remaining parking spaces;

From the above description, the parking space monitoring and management method provided by the application obtains the information of the vehicle owner by identifying the license plate number of the vehicle to be parked, recommends the alternative parking space to the vehicle owner according to the information of the vehicle owner, can help the vehicle owner to find the parking space suitable for parking as soon as possible, fully relieves the problem of inconvenience in parking in public places, and facilitates the safety management of large-scale parking lots.

In another embodiment, the parking space monitoring and managing system may be configured separately from the central processor 9100, for example, the parking space monitoring and managing system may be configured as a chip connected to the central processor 9100, and the function of the parking space monitoring and managing method is implemented by the control of the central processor.

As shown in fig. 15, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 also does not necessarily include all of the components shown in fig. 15; further, the electronic device 9600 may further include components not shown in fig. 15, which can be referred to in the related art.

As shown in fig. 15, a central processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, which central processor 9100 receives input and controls the operation of the various components of the electronic device 9600.

The memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to realize information storage or processing, or the like.

The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. Power supply 9170 is used to provide power to electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.

The memory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 9140 could also be some other type of device. Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of the electronic device 9600 by the central processor 9100.

The memory 9140 can also include a data store 9143, the data store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers for the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).

The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.

Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing ordinary telecommunications functions. The audio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100, thereby enabling recording locally through the microphone 9132 and enabling locally stored sounds to be played through the speaker 9131.

An embodiment of the present application further provides a computer-readable storage medium capable of implementing all the steps in the parking space monitoring management method with an execution subject being a server or a client in the foregoing embodiments, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements all the steps in the parking space monitoring management method with an execution subject being a server or a client in the foregoing embodiments, for example, when the processor executes the computer program, the processor implements the following steps:

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. The parking space monitoring and managing method is characterized by comprising the following steps:

2. The parking space monitoring and management method according to claim 1, wherein the obtaining of owner information according to the original image of the vehicle comprises:

3. The parking space monitoring and managing method according to claim 2, wherein the identifying the original vehicle image comprises:

4. The parking space monitoring and management method according to claim 3, wherein the step of training the vehicle detection model comprises:

5. The parking space monitoring and management method according to claim 4, wherein the step of training the license plate detection model comprises the following steps:

randomly grouping the original vehicle image samples;

6. The parking space monitoring and management method according to claim 4, wherein the step of training the license plate recognition model comprises the following steps:

labeling the license plate high-definition sample;

7. The parking space monitoring and managing method according to claim 1, further comprising:

8. The parking space monitoring and managing method according to claim 1, further comprising:

9. The utility model provides a parking stall control management system which characterized in that includes:

10. The parking space monitoring and management system according to claim 9, wherein the obtaining unit comprises:

11. The parking space monitoring and management system according to claim 10, wherein the identification module comprises:

12. The space monitoring and management system according to claim 11, further comprising:

13. The space monitoring and management system according to claim 12, further comprising:

14. The space monitoring and management system according to claim 12, further comprising:

the marking unit is used for marking the license plate high-definition samples;

15. The parking space monitoring and management system according to claim 9, further comprising:

the identification unit is used for identifying the current vehicle owner when the number of the vehicle owners is multiple;

16. The parking space monitoring and management system according to claim 9, further comprising: and if the remaining parking spaces recommended to the vehicle owner cannot meet the requirements of the vehicle owner, the recommending unit is further used for recommending a plurality of remaining parking spaces to the vehicle owner again according to the reasons of non-satisfaction.

17. An electronic device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor implements the steps of the parking space monitoring and management method according to any one of claims 1 to 8 when executing the program.

18. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for monitoring and managing parking spaces according to any one of claims 1 to 8.