CN112418126A - Unmanned aerial vehicle-based vehicle illegal parking detection method and device and storage medium - Google Patents

Unmanned aerial vehicle-based vehicle illegal parking detection method and device and storage medium Download PDF

Info

Publication number
CN112418126A
CN112418126A CN202011373148.1A CN202011373148A CN112418126A CN 112418126 A CN112418126 A CN 112418126A CN 202011373148 A CN202011373148 A CN 202011373148A CN 112418126 A CN112418126 A CN 112418126A
Authority
CN
China
Prior art keywords
vehicle
information
parking
image
unmanned aerial
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011373148.1A
Other languages
Chinese (zh)
Inventor
蒋润锦
周文略
黎繁胜
翟懿奎
张俊亮
刘始匡
李汶睿
陈乐轩
黄俊威
陈泽聪
詹英培
梁汝桐
王天雷
梁艳阳
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.)
Wuyi University
Original Assignee
Wuyi University
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 Wuyi University filed Critical Wuyi University
Priority to CN202011373148.1A priority Critical patent/CN112418126A/en
Publication of CN112418126A publication Critical patent/CN112418126A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42—Determining position
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • 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
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • 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
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08—Detecting or categorising vehicles

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a vehicle illegal parking detection method, a device and a storage medium based on an unmanned aerial vehicle, wherein the method comprises the following steps: the camera arranged on the unmanned aerial vehicle is used for shooting the flight of the no-parking area and collecting the image information of the no-parking area; identifying and judging the image information of the no-parking area by using a target detection algorithm; if the recognition and judgment result shows that the illegal parking vehicles exist in the forbidden parking area, the camera and the GPS module are utilized to collect vehicle information of the illegal parking vehicles, and vehicle illegal parking information is obtained; and the vehicle illegal parking information is sent to the monitoring terminal, so that illegal parking detection efficiency can be improved, and the detection cost is well reduced.

Description

Unmanned aerial vehicle-based vehicle illegal parking detection method and device and storage medium
Technical Field
The invention relates to the field of illegal parking detection, in particular to a vehicle illegal parking detection method and device based on an unmanned aerial vehicle and a storage medium.
Background
Along with the continuous development of economy, the living standard of people is continuously improved, the quantity of automobile ownership of people is continuously increased, and due to limited parking spaces, the phenomenon of random parking and random parking often occurs; when the vehicle is parked in a no-parking area, road congestion is easily caused, the traveling of personnel is influenced, even traffic accidents are caused, and the road safety is influenced. In order to reduce the situation, cameras are often installed in the no-parking areas, but the cameras are not installed in all the no-parking areas, so that a traffic police is required to patrol, a large amount of manpower and material resources are consumed, the checking efficiency of the illegal parking is low, and the illegal parking phenomenon cannot be well restrained.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art.
Therefore, the invention provides the vehicle illegal parking detection method based on the unmanned aerial vehicle, which can improve the illegal parking detection efficiency and well reduce the detection cost.
The invention also provides a vehicle illegal parking detection device based on the unmanned aerial vehicle, which applies the vehicle illegal parking detection method based on the unmanned aerial vehicle.
The invention also provides a computer readable storage medium applying the unmanned aerial vehicle-based vehicle illegal parking detection method.
According to the embodiment of the first aspect of the invention, the vehicle illegal parking detection method based on the unmanned aerial vehicle is applied to a vehicle illegal parking detection system, the vehicle illegal parking detection system comprises the unmanned aerial vehicle, a camera, a GPS module, a controller and a monitoring terminal, the unmanned aerial vehicle, the camera, the GPS module and the monitoring terminal are all in data connection with the controller, and the vehicle illegal parking detection method based on the unmanned aerial vehicle comprises the following steps:
the camera arranged on the unmanned aerial vehicle is used for shooting the flight of the no-parking area and collecting the image information of the no-parking area;
identifying and judging the image information of the no-parking area by using a target detection algorithm;
if the recognition and judgment result shows that the illegal parking vehicles exist in the forbidden parking area, the camera and the GPS module are utilized to collect vehicle information of the illegal parking vehicles, and vehicle illegal parking information is obtained;
and sending the vehicle illegal parking information to the monitoring terminal.
The vehicle illegal parking detection method based on the unmanned aerial vehicle at least has the following beneficial effects: firstly, controlling an unmanned aerial vehicle to fly to a set no-parking area, and then carrying out image acquisition processing by using a camera arranged on the unmanned aerial vehicle to obtain image information of the no-parking area; then, identifying and judging the collected image information of the no-parking area by using a target detection algorithm; when the illegal vehicles exist in the forbidden parking area, the illegal vehicles are identified and judged, information acquisition is carried out on the illegal vehicles by using the camera and a GPS module arranged on the unmanned aerial vehicle, and information of the illegal vehicles is obtained; and finally, the information of the illegal parking of the vehicle is sent to the monitoring terminal, so that monitoring personnel can utilize the monitoring terminal to flexibly and rapidly monitor and collect evidences of the illegal parking vehicle, the illegal parking inspection efficiency is well improved, and the inspection cost is well reduced.
According to some embodiments of the present invention, the performing flight shooting on the no-parking area through the camera arranged on the unmanned aerial vehicle, and acquiring image information of the no-parking area includes:
controlling the unmanned aerial vehicle to fly to a no-parking area by using the GPS module;
and shooting the no-parking area by using the camera to acquire image information of the no-parking area.
According to some embodiments of the present invention, the identifying and determining the image information of the no-parking area by using a target detection algorithm includes:
image preprocessing is carried out on the image information of the no-parking area to obtain gray image information and an image database;
extracting the characteristics of the gray level image information by using a residual neural network to obtain an image characteristic model;
training the image feature model by using the image database to obtain an image training model;
and inputting the data set in the image database into the image training model to obtain a recognition judgment result.
According to some embodiments of the present invention, the image preprocessing the image information of the no-parking area to obtain the gray image information and the image database includes:
performing frame extraction on the image information of the forbidden area to obtain multi-frame image information;
filtering the multi-frame image information to obtain filtered image information;
carrying out binarization processing on the filtered image information to obtain the gray level image information;
and constructing the image database by using the gray image information.
According to some embodiments of the present invention, if the recognition and determination result indicates that there is an illegal parking vehicle in the prohibited area, acquiring vehicle information of the illegal parking vehicle by using the camera and the GPS module to obtain vehicle illegal parking information, including:
shooting the whole illegal vehicle and the license plate number by using the camera to obtain vehicle information; acquiring time information and positioning information by using a GPS module to obtain illegal parking check information;
and merging the vehicle information and the illegal parking check information into vehicle illegal parking information.
According to some embodiments of the present invention, the sending the vehicle illegal parking information to the monitoring terminal includes:
and sending the vehicle illegal parking information to a monitoring terminal through a wireless transmission module.
According to some embodiments of the invention, the wireless transmission module is a 5G transmission module.
According to the second aspect embodiment of the invention, the vehicle illegal parking detection device based on the unmanned aerial vehicle comprises:
the image acquisition unit is used for carrying out flight shooting on the no-parking area through the camera arranged on the unmanned aerial vehicle and acquiring the image information of the no-parking area;
the identification and judgment unit is used for identifying and judging the image information of the no-parking area by using a target detection algorithm; the illegal parking acquisition unit is used for acquiring vehicle information of the illegal parking vehicles by utilizing the camera and the GPS module to obtain vehicle illegal parking information if the recognition and judgment result shows that the illegal parking vehicles exist in the forbidden parking area;
and the transmission unit is used for transmitting the vehicle illegal stopping information to the monitoring terminal.
According to some embodiments of the invention, the identification determination unit comprises:
the preprocessing unit is used for preprocessing the image information of the forbidden area to obtain gray image information and an image database;
the extraction unit is used for extracting the characteristics of the gray level image information by using a residual error neural network to obtain an image characteristic model;
the training unit is used for training the image characteristic model by utilizing the image database to obtain an image training model;
and the recognition unit is used for inputting the image database into the image training model to obtain a recognition judgment result.
The vehicle illegal parking detection device based on the unmanned aerial vehicle at least has the following beneficial effects: firstly, controlling an unmanned aerial vehicle to fly to a set no-parking area, and then carrying out image acquisition processing by using a camera arranged on the unmanned aerial vehicle to obtain image information of the no-parking area; then, identifying and judging the collected image information of the no-parking area by using a target detection algorithm; when the illegal vehicles exist in the forbidden parking area, the illegal vehicles are identified and judged, information acquisition is carried out on the illegal vehicles by using the camera and a GPS module arranged on the unmanned aerial vehicle, and information of the illegal vehicles is obtained; and finally, the information of the illegal parking of the vehicle is sent to the monitoring terminal, so that monitoring personnel can utilize the monitoring terminal to flexibly and rapidly monitor and collect evidences of the illegal parking vehicle, the illegal parking inspection efficiency is well improved, and the inspection cost is well reduced.
According to the computer-readable storage medium of the third aspect of the present invention, the vehicle violation detection method based on the unmanned aerial vehicle according to the above-mentioned first aspect of the present invention can be applied.
The computer-readable storage medium according to the embodiment of the invention has at least the following advantages: firstly, controlling an unmanned aerial vehicle to fly to a set no-parking area, and then carrying out image acquisition processing by using a camera arranged on the unmanned aerial vehicle to obtain image information of the no-parking area; then, identifying and judging the collected image information of the no-parking area by using a target detection algorithm; when the illegal vehicles exist in the forbidden parking area, the illegal vehicles are identified and judged, information acquisition is carried out on the illegal vehicles by using the camera and a GPS module arranged on the unmanned aerial vehicle, and information of the illegal vehicles is obtained; and finally, the information of the illegal parking of the vehicle is sent to the monitoring terminal, so that monitoring personnel can utilize the monitoring terminal to flexibly and rapidly monitor and collect evidences of the illegal parking vehicle, the illegal parking inspection efficiency is well improved, and the inspection cost is well reduced.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of a method for detecting vehicle parking violation based on an unmanned aerial vehicle according to a first embodiment of the present invention;
fig. 2 is a flowchart of a work flow of image acquisition in a vehicle illegal parking detection method based on an unmanned aerial vehicle according to a first embodiment of the present invention;
fig. 3 is a flowchart illustrating a work flow of image judgment and recognition in a vehicle parking violation detection method based on an unmanned aerial vehicle according to a first embodiment of the present invention;
fig. 4 is a flowchart of preprocessing in an image recognition process in a vehicle parking violation detection method based on an unmanned aerial vehicle according to a first embodiment of the present invention;
fig. 5 is a flowchart of a process of acquiring information of a parking violation vehicle in the vehicle parking violation detection method based on an unmanned aerial vehicle according to the first embodiment of the present invention;
fig. 6 is another flowchart of a method for detecting vehicle parking violation based on an unmanned aerial vehicle according to a first embodiment of the present invention;
fig. 7 is a schematic structural diagram of a vehicle illegal parking detection device based on an unmanned aerial vehicle according to a second embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, unless otherwise explicitly defined, terms such as arrangement, connection and the like should be broadly construed, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the detailed contents of the technical solutions.
Example one
Referring to fig. 1, a first embodiment of the present invention provides a vehicle illegal parking detection method based on an unmanned aerial vehicle, which is applied to a vehicle illegal parking detection system, the vehicle illegal parking detection system includes the unmanned aerial vehicle, a camera, a GPS module, a controller and a monitor terminal, the unmanned aerial vehicle, the camera, the GPS module and the monitor terminal are all in data connection with the controller, and one embodiment of the vehicle illegal parking detection method based on the unmanned aerial vehicle includes, but is not limited to, the following steps:
and S100, carrying out flight shooting on the no-parking area through a camera arranged on the unmanned aerial vehicle, and acquiring image information of the no-parking area.
In this embodiment, in this step, the unmanned aerial vehicle flies to the no-parking area, and a camera arranged on the unmanned aerial vehicle is used to shoot the no-parking area, collect image information of the no-parking area, and prepare for subsequent image recognition; in the embodiment, the unmanned aerial vehicle adopts a multi-rotor (multi-shaft) unmanned aerial vehicle; many rotors (multiaxis) unmanned aerial vehicle control is simple, can hover at the fixed point, and the security is high, use cost is low. The unmanned aerial vehicle platform includes flight control module. The flight control module comprises a gyroscope and a PID linear controller; the gyroscope is used for sensing the flight attitude; the PID linear controller establishes the relationship of proportion, integral and differential between the attitude information and the rotating speed of the propeller, and the multi-rotor system control achieves the phenomenon of quick dynamic response, and neither overshooting nor deficiency by adjusting the parameter of each link. The camera is used for collecting image data and collecting images of the illegal parking areas and consists of a high-definition camera; the main function is to store the image data transmitted back by the camera into the system memory; initializing the camera module: the shooting mode, the photo proportion, the photo format, the white balance, the color and other settings are initialized, and the shooting quality is ensured. The GPS module is used for flight navigation of the unmanned aerial vehicle and comprises a GPS receiver, an angular rate gyro, an IMU module, a rudder deflection potentiometer, an image collector, a timer and the like; the non-stop area map module is contained, and the unmanned aerial vehicle flies to the non-stop area to be detected through the navigation module.
And S200, identifying and judging the image information of the no-parking area by using a target detection algorithm.
In this embodiment, in this step, the target detection algorithm is used to identify and judge the image information of the no-parking area acquired by the unmanned aerial vehicle, and determine whether there is a vehicle violating the parking in the image information of the no-parking area, so as to take further measures.
And step S300, if the recognition and judgment result shows that the illegal parking vehicles exist in the forbidden parking area, utilizing a camera and a GPS module to collect vehicle information of the illegal parking vehicles, and obtaining illegal parking information of the vehicles.
In this embodiment, in this step, when the determination result indicates that there is an illegal vehicle, the camera is used again to collect information of the illegal vehicle, and the GPS module is used to obtain the current time and location, so as to obtain the illegal vehicle information.
And step S400, sending the information of the illegal parking of the vehicle to the monitoring terminal.
In this embodiment, the vehicle information of violating the parking that this step will be gathered is sent monitor terminal, and then the control personnel just can utilize monitor terminal conveniently to look over and know the vehicle information of violating the parking, has practiced thrift the inspection cost of violating the parking to the inspection efficiency of violating the parking has been improved well.
Referring to fig. 2, in step S100 of this embodiment, the following steps may be included, but are not limited to:
and step S110, controlling the unmanned aerial vehicle to fly to a no-parking area by using the GPS module.
In this embodiment, in this step, the GPS module is used to perform positioning flight, and route planning is performed according to a no-parking area map module preset in the GPS module, so that the unmanned aerial vehicle can fly to the no-parking area.
And step S120, shooting the no-parking area by using a camera, and collecting image information of the no-parking area.
In this embodiment, in this step, after the unmanned aerial vehicle flies to the no-parking area, the no-parking area is photographed by using the camera set on the unmanned aerial vehicle, and then image information of the no-parking area can be acquired.
Referring to fig. 3, step S200 of the present embodiment may include, but is not limited to, the following steps:
step S210, image preprocessing is carried out on the image information of the no-parking area to obtain gray image information and an image database.
In this embodiment, the collected image information is preprocessed in this step to obtain grayscale image information and an image database, and a precondition is prepared for subsequent image recognition and judgment.
And step S220, utilizing a residual error neural network to perform feature extraction on the gray level image information to obtain an image feature model.
In this embodiment, in this step, a residual neural network is used to perform feature extraction on grayscale image information to obtain an image feature model, and preparation is made for subsequent deep learning.
And step S230, training the image characteristic model by using the image database to obtain an image training model.
In this embodiment, in this step, the image feature model is trained by using the image database, so as to obtain an image training model, and the training effect of the measurement model is monitored by using the loss function.
Step S240, inputting the data set in the image database into the image training model to obtain a recognition judgment result.
In this embodiment, in this step, the data set in the image database is input into the image training model again, so as to obtain the recognition and determination result, and know whether there is a parking violation vehicle in the no-parking area.
Referring to fig. 4, in step S210 of this embodiment, the following steps may be included, but are not limited to:
step S211, performing frame extraction on the image information in the no-parking area to obtain multi-frame image information.
In this embodiment, in this step, frame extraction is performed on the acquired image information to obtain multi-frame image information. Because in this embodiment, the video image information that unmanned aerial vehicle collected at first, so need carry out the framing extraction to video image information, be convenient for follow-up image identification analysis processes.
Step S212, filtering the multi-frame image information to obtain filtered image information.
In this embodiment, in this step, filtering processing is performed on multi-frame image information, and a median filtering processing method in a spatial domain is adopted to suppress impulse interference and salt and pepper noise; under certain conditions, the image detail blurring caused by linear filters such as least mean square filtering mean filtering and the like can be overcome, and the edge of the image is effectively protected.
In step S213, binarization processing is performed on the filtered image information to obtain grayscale image information.
In this embodiment, the image is binarized in this step, the distribution characteristics of the gray scale of each image are counted, the category variance is used as a criterion, and the maximum value of the inter-class variance is selected as a selected threshold. The binarized image using the optimal threshold algorithm further reduces noise and provides cleaner image data.
Step S214, an image database is constructed by utilizing the gray scale image information.
In this embodiment, in this step, an image database is constructed by using the grayscale image information obtained after binarization processing, so as to prepare for subsequent neural network model training.
Referring to fig. 5, in step S300 of this embodiment, the following steps may be included, but are not limited to:
and S310, shooting the whole illegal vehicle and the license plate number by using a camera to obtain vehicle information.
In this embodiment, in this step, the whole of the illegal vehicle and the license plate number are photographed by using the camera to obtain vehicle information;
step S320, obtaining the time information and the positioning information by using the GPS module to obtain the violation checking information.
In this embodiment, in this step, the GPS module is used to obtain the current time information and the positioning information, so as to obtain the checking information of illegal parking, and provide relevant evidence for specifying illegal parking vehicles.
In step S330, the vehicle information and the illegal parking check information are combined into vehicle illegal parking information.
In this embodiment, the collected vehicle information and the illegal parking check information are packaged and merged in this step, so that the illegal parking information of the vehicle is obtained, and the traffic police department can collect the illegal parking information of the vehicle conveniently.
In step S400, the following steps may be included, but not limited to: and sending the information of the illegal parking of the vehicle to the monitoring terminal through the wireless transmission module.
In this embodiment, the collected information of the illegal parking of the vehicle is sent to the monitoring terminal through the wireless transmission module in this step; the monitoring terminal can be a background system or a related cloud platform which interacts with the traffic police platform.
In some embodiments of the invention, the wireless transmission module is a 5G transmission module. The 5G transmission module is a newly emerging transmission module and has a high data transmission rate, so that the data can be rapidly transmitted, and the effect of monitoring a forbidden zone in real time is achieved.
Referring to fig. 6, in some embodiments of the invention, the method for detecting vehicle parking violation based on a drone may further include the steps of: the unmanned aerial vehicle carrying the camera flies to a to-be-detected no-parking area through a GPS positioning flight system; the unmanned aerial vehicle collects video data of the no-parking area in real time and carries out target detection on video data images, and a target detection algorithm based on deep learning is used for detecting whether vehicles are in the no-parking area; if the vehicle is identified and detected to be in the no-parking area, automatically starting a shooting function, shooting the license plate number of the vehicle, and acquiring shooting time and place; and packaging the number plate number of the illegal parking vehicle, the illegal parking picture of the vehicle, the illegal parking time and the place information into an illegal parking vehicle information report stream, and sending the illegal parking vehicle information report stream to a background system interacting with a traffic police department.
The method comprises the following steps of constructing a residual error network as a feature extraction network by using a residual error block, wherein the network structure comprises two layers, and the expression is as follows:
F＝W2σ(W1X)
where σ is the activation function Relu.
And then adding the output of the second network layer by a short to obtain an output y, wherein the expression is as follows:
y＝F(x,Wi)+x
a residual block is defined in the form of y ═ F (x, Wi) + x, where x and y are the input and output vectors of the residual block, respectively, and F (x, Wi) is the residual to be learned mapped onto this expression. The ResNet network is constructed from residual modules.
ResNet no longer learns a complete output H (x), but the difference H (x) -x between the output and the input, i.e., the residual. The method can obtain activation from a certain layer, then quickly feed back to another layer or even a deeper layer, a residual error network ResNet can be constructed by utilizing jump connection to train a deeper network, in the part, jump connection is introduced in a position different from a common network by constructing ResNet-34 as a characteristic extraction network residual error network, so that information of a previous residual error block can flow into a next residual error block without being blocked, information circulation is improved, and the problems of disappearing gradient and degradation caused by the fact that the network is too deep are avoided.
The residual network is formed by fusing a plurality of shallow networks in fact, the problem of vanishing gradient is not solved fundamentally, and the problem of vanishing gradient is only avoided.
Wherein, the image characteristic model is trained by using the constructed image database, wherein the objective function adopts a loss function (Focal loss). Focal loss is mainly used for the problem of unbalanced proportion of background samples and foreground samples in a multi-classification task. The loss function reduces the weight occupied by a large number of simple negative samples in training, and the formula is as follows:
FL(pt)＝-αt(1-pt)γlog(pt)
(1-pt)γthis term is equivalent to adding a conditioning factor to the cross-entropy loss, in order to make the model focus more on the samples that are difficult to classify when training, by reducing the weight of the samples that are easy to classify.
And the alpha coefficient is used for adjusting the proportion of positive and negative, and when the foreground class is alpha, the background class uses 1-alpha. For example, with fewer foreground classes, α can be adjusted by taking a value close to 1, while the weight of the background class is 1- α, which is a number close to 0. The imbalance in sample proportions can be adjusted by alpha.
The best effect is obtained when the parameter gamma is 2 and alpha is 0.25. And when gamma takes 0, focal length is the cross entropy loss.
And after the model converges, removing the Fc layer, inputting the data set in the image database again, obtaining the characteristic F1 output by avgpool, and forming a training pair of (F1, Y) for the characteristic fusion. The method can accurately and quickly identify whether vehicles exist in the no-parking area.
According to the scheme, the unmanned aerial vehicle is controlled to fly to the set no-parking area, and then the camera arranged on the unmanned aerial vehicle is used for image acquisition processing to obtain the image information of the no-parking area; then, identifying and judging the collected image information of the no-parking area by using a target detection algorithm; when the illegal vehicles exist in the forbidden parking area, the illegal vehicles are identified and judged, information acquisition is carried out on the illegal vehicles by using the camera and a GPS module arranged on the unmanned aerial vehicle, and information of the illegal vehicles is obtained; and finally, the information of the illegal parking of the vehicle is sent to the monitoring terminal, so that monitoring personnel can utilize the monitoring terminal to flexibly and rapidly monitor and collect evidences of the illegal parking vehicle, the illegal parking inspection efficiency is well improved, and the inspection cost is well reduced.
Example two
Referring to fig. 7, a second embodiment of the present invention provides a vehicle parking violation detection apparatus 1000 based on an unmanned aerial vehicle, including:
the image acquisition unit 1100 is used for performing flight shooting on the no-parking area through a camera arranged on the unmanned aerial vehicle and acquiring image information of the no-parking area;
the identification and judgment unit 1200 is used for identifying and judging the image information of the no-parking area by using a target detection algorithm; the illegal parking acquisition unit 1300 is used for acquiring vehicle information of the illegal parking vehicles by utilizing the camera and the GPS module to obtain vehicle illegal parking information if the recognition and judgment result indicates that the illegal parking vehicles exist in the forbidden parking area;
and the transmission unit 0014 is used for transmitting the vehicle illegal parking information to the monitoring terminal.
In this embodiment, the identification determining unit 1200 includes:
the preprocessing unit 1210 is configured to perform image preprocessing on the image information in the no-parking area to obtain grayscale image information and an image database;
the extracting unit 1220 is configured to perform feature extraction on the grayscale image information by using a residual neural network to obtain an image feature model;
the training unit 1230 is configured to train the image feature model by using an image database to obtain an image training model;
the recognition unit 1240 is configured to input the image database into the image training model to obtain a recognition determination result.
It should be noted that, because the vehicle parking violation detection apparatus based on the unmanned aerial vehicle in this embodiment is based on the same inventive concept as the vehicle parking violation detection method based on the unmanned aerial vehicle in the first embodiment, the corresponding contents in the first method embodiment are also applicable to the embodiment of the present system, and are not described in detail here.
According to the scheme, the unmanned aerial vehicle is controlled to fly to the set no-parking area, and then the camera arranged on the unmanned aerial vehicle is used for image acquisition processing to obtain the image information of the no-parking area; then, identifying and judging the collected image information of the no-parking area by using a target detection algorithm; when the illegal vehicles exist in the forbidden parking area, the illegal vehicles are identified and judged, information acquisition is carried out on the illegal vehicles by using the camera and a GPS module arranged on the unmanned aerial vehicle, and information of the illegal vehicles is obtained; and finally, the information of the illegal parking of the vehicle is sent to the monitoring terminal, so that monitoring personnel can utilize the monitoring terminal to flexibly and rapidly monitor and collect evidences of the illegal parking vehicle, the illegal parking inspection efficiency is well improved, and the inspection cost is well reduced.
EXAMPLE III
A third embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores executable instructions of a vehicle illegal parking detection device based on an unmanned aerial vehicle, and the executable instructions of the vehicle illegal parking detection device based on the unmanned aerial vehicle are used for enabling the vehicle illegal parking detection device based on the unmanned aerial vehicle to execute the above-mentioned vehicle illegal parking detection method based on the unmanned aerial vehicle, for example, execute the above-described method steps S100 to S400 in fig. 1, and implement the function of the unit 1000-1400 in fig. 7.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims (10)

1. The utility model provides a vehicle detection method that violations of parking based on unmanned aerial vehicle, is applied to vehicle detection system that violations of parking, vehicle detection system that violations of parking includes unmanned aerial vehicle, the appearance of making a video recording, GPS module, controller and monitor terminal, unmanned aerial vehicle the appearance of making a video recording, GPS module with monitor terminal all with controller data connection, its characterized in that, vehicle detection method that violations of parking based on unmanned aerial vehicle includes:
the camera arranged on the unmanned aerial vehicle is used for shooting the flight of the no-parking area and collecting the image information of the no-parking area;
identifying and judging the image information of the no-parking area by using a target detection algorithm;
if the recognition and judgment result shows that the illegal parking vehicles exist in the forbidden parking area, the camera and the GPS module are utilized to collect vehicle information of the illegal parking vehicles, and vehicle illegal parking information is obtained;
and sending the vehicle illegal parking information to the monitoring terminal.
2. The method according to claim 1, wherein the acquiring image information of the no-parking area by shooting the no-parking area in a flying manner through the camera installed on the unmanned aerial vehicle comprises:
controlling the unmanned aerial vehicle to fly to a no-parking area by using the GPS module;
and shooting the no-parking area by using the camera to acquire image information of the no-parking area.
3. The method according to claim 1, wherein the identifying and determining the image information of the no-parking area by using a target detection algorithm comprises:
image preprocessing is carried out on the image information of the no-parking area to obtain gray image information and an image database;
extracting the characteristics of the gray level image information by using a residual neural network to obtain an image characteristic model;
training the image feature model by using the image database to obtain an image training model;
and inputting the data set in the image database into the image training model to obtain a recognition judgment result.
4. The method according to claim 3, wherein the image preprocessing is performed on the image information of the no-parking area to obtain gray image information and an image database, and the method comprises:
performing frame extraction on the image information of the forbidden area to obtain multi-frame image information;
filtering the multi-frame image information to obtain filtered image information;
carrying out binarization processing on the filtered image information to obtain the gray level image information;
and constructing the image database by using the gray image information.
5. The method according to claim 1, wherein if the result of the identification is that there are illegal vehicles in the illegal parking area, the camera and the GPS module are used to collect vehicle information of the illegal vehicles to obtain information about illegal parking of vehicles, and the method comprises:
shooting the whole illegal vehicle and the license plate number by using the camera to obtain vehicle information;
acquiring time information and positioning information by using a GPS module to obtain illegal parking check information;
and merging the vehicle information and the illegal parking check information into vehicle illegal parking information.
6. The method according to claim 1, wherein the sending the vehicle illegal parking information to the monitoring terminal includes:
and sending the vehicle illegal parking information to a monitoring terminal through a wireless transmission module.
7. The unmanned aerial vehicle-based vehicle parking detection method according to claim 6, wherein: the wireless transmission module is a 5G transmission module.
8. The utility model provides a vehicle detection device that violations of parking based on unmanned aerial vehicle which characterized in that includes:
the image acquisition unit is used for carrying out flight shooting on the no-parking area through the camera arranged on the unmanned aerial vehicle and acquiring the image information of the no-parking area;
the identification and judgment unit is used for identifying and judging the image information of the no-parking area by using a target detection algorithm;
the illegal parking acquisition unit is used for acquiring vehicle information of the illegal parking vehicles by utilizing the camera and the GPS module to obtain vehicle illegal parking information if the recognition and judgment result shows that the illegal parking vehicles exist in the forbidden parking area;
and the transmission unit is used for transmitting the vehicle illegal stopping information to the monitoring terminal.
9. The apparatus of claim 9, wherein the identification and determination unit comprises:
the preprocessing unit is used for preprocessing the image information of the forbidden area to obtain gray image information and an image database;
the extraction unit is used for extracting the characteristics of the gray level image information by using a residual error neural network to obtain an image characteristic model;
the training unit is used for training the image characteristic model by utilizing the image database to obtain an image training model;
and the recognition unit is used for inputting the image database into the image training model to obtain a recognition judgment result.
10. A computer-readable storage medium characterized by: the computer readable storage medium has stored thereon unmanned aerial vehicle-based vehicle violation detection apparatus executable instructions for causing an unmanned aerial vehicle-based vehicle violation detection apparatus to perform the unmanned aerial vehicle-based vehicle violation detection method of any of claims 1-7.
CN202011373148.1A 2020-11-30 2020-11-30 Unmanned aerial vehicle-based vehicle illegal parking detection method and device and storage medium Pending CN112418126A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011373148.1A CN112418126A (en) 2020-11-30 2020-11-30 Unmanned aerial vehicle-based vehicle illegal parking detection method and device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011373148.1A CN112418126A (en) 2020-11-30 2020-11-30 Unmanned aerial vehicle-based vehicle illegal parking detection method and device and storage medium

Publications (1)

Publication Number Publication Date
CN112418126A true CN112418126A (en) 2021-02-26

Family

ID=74830574

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011373148.1A Pending CN112418126A (en) 2020-11-30 2020-11-30 Unmanned aerial vehicle-based vehicle illegal parking detection method and device and storage medium

Country Status (1)

Country Link
CN (1) CN112418126A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114023100A (en) * 2021-11-04 2022-02-08 上海探寻信息技术有限公司 Warning system and method for no-stop area of vehicle
CN114596508A (en) * 2022-03-14 2022-06-07 浙江这里飞科技有限公司 Violation identification method and device based on unmanned aerial vehicle, computer equipment and storage medium
CN115083171A (en) * 2022-07-20 2022-09-20 深圳联和智慧科技有限公司 Unmanned aerial vehicle fixed-point inspection method and system based on muck vehicle monitoring
CN115482670A (en) * 2022-09-02 2022-12-16 山东浪潮新基建科技有限公司 Unmanned aerial vehicle-based vehicle illegal parking identification method and system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110009058A (en) * 2019-04-16 2019-07-12 山东博昂信息科技有限公司 A kind of parking lot Vehicle License Plate Recognition System and method
CN110766978A (en) * 2019-11-04 2020-02-07 深圳市凯达尔科技实业有限公司 Unmanned aerial vehicle-based roadside parking management method and system and storage medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110009058A (en) * 2019-04-16 2019-07-12 山东博昂信息科技有限公司 A kind of parking lot Vehicle License Plate Recognition System and method
CN110766978A (en) * 2019-11-04 2020-02-07 深圳市凯达尔科技实业有限公司 Unmanned aerial vehicle-based roadside parking management method and system and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
漆 震 等: "基于边缘计算与无人机平台的违停车辆识别系统", 《信息技术与信息化》, no. 6, pages 1 - 3 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114023100A (en) * 2021-11-04 2022-02-08 上海探寻信息技术有限公司 Warning system and method for no-stop area of vehicle
CN114023100B (en) * 2021-11-04 2023-02-21 上海探寻信息技术有限公司 Warning system and method for no-stop area of vehicle
CN114596508A (en) * 2022-03-14 2022-06-07 浙江这里飞科技有限公司 Violation identification method and device based on unmanned aerial vehicle, computer equipment and storage medium
CN115083171A (en) * 2022-07-20 2022-09-20 深圳联和智慧科技有限公司 Unmanned aerial vehicle fixed-point inspection method and system based on muck vehicle monitoring
CN115482670A (en) * 2022-09-02 2022-12-16 山东浪潮新基建科技有限公司 Unmanned aerial vehicle-based vehicle illegal parking identification method and system

Similar Documents

Publication Publication Date Title
CN112418126A (en) Unmanned aerial vehicle-based vehicle illegal parking detection method and device and storage medium
CN109358612B (en) Intelligent driving control method and device, vehicle, electronic equipment and storage medium
CN112201051B (en) Unmanned aerial vehicle end road surface vehicle illegal parking detection and evidence obtaining system and method
CN105678267A (en) Scene recognition method and device
CN108108750A (en) Metric space method for reconstructing based on deep learning and monocular vision
CN110415544B (en) Disaster weather early warning method and automobile AR-HUD system
CN111508260A (en) Vehicle parking space detection method, device and system
WO2022246852A1 (en) Automatic driving system testing method based on aerial survey data, testing system, and storage medium
CN105788269A (en) Unmanned aerial vehicle-based abnormal traffic identification method
CN110738081B (en) Abnormal road condition detection method and device
CN111723854B (en) Expressway traffic jam detection method, equipment and readable storage medium
DE102022125062A1 (en) SYSTEM AND METHOD FOR DETECTING ROAD AND LANE CONNECTIONS AT INTERSECTIONS
CN108932273A (en) Picture screening technique and device
CN111967396A (en) Processing method, device and equipment for obstacle detection and storage medium
CN113450573A (en) Traffic monitoring method and traffic monitoring system based on unmanned aerial vehicle image recognition
CN114037932A (en) Traffic abnormal event detection method, electronic device, storage medium, and program product
CN115049948A (en) Unmanned aerial vehicle inspection method and device based on neural network model and related equipment
CN107809559A (en) A kind of image self study Enhancement Method and system
CN116071711B (en) Traffic jam condition detection method and device
CN117416349A (en) Automatic driving risk pre-judging system and method based on improved YOLOV7-Tiny and SS-LSTM in V2X environment
CN107958591A (en) A kind of roadside parking management system based on street lamp
CN108563986A (en) Earthquake region electric pole posture judgment method based on wide-long shot image and system
CN115440071B (en) Automatic driving illegal parking detection method
CN115965926A (en) Vehicle-mounted road sign line inspection system
DE102022103059A1 (en) AUTOMATIC ANNOTATION OF PASSABLE ROAD SEGMENTS

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