CN108510750A - A method of the unmanned plane inspection parking offense based on neural network model - Google Patents
A method of the unmanned plane inspection parking offense based on neural network model Download PDFInfo
- Publication number
- CN108510750A CN108510750A CN201810375741.6A CN201810375741A CN108510750A CN 108510750 A CN108510750 A CN 108510750A CN 201810375741 A CN201810375741 A CN 201810375741A CN 108510750 A CN108510750 A CN 108510750A
- Authority
- CN
- China
- Prior art keywords
- parking
- unmanned plane
- neural network
- network model
- image
- 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
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The method of the invention discloses a kind of unmanned plane inspection parking offense based on neural network model, belong to field of artificial intelligence, based on the image recognition algorithm in deep learning, the model of training certain depth study, and the model is applied to UAV system, realize the detection of parking lot illegal parking behavior.Implementation method is as follows:Parking facility image information is acquired, and demarcates parking data collection;The parking data collection training neural network model parameter obtained using S1;It is used for the neural network model that training is completed that classification is identified to the video image that unmanned plane acquires, class categories correspond to parking data collection spotting;The image of cruise shooting is sent to control centre by unmanned plane, and whether in violation of rules and regulations control centre is based on image recognition algorithm judgement parking, and sends corresponding control instruction to unmanned plane.Image recognition technology is combined by the present invention with UAV system, can continue to optimize management structure, realizes the intelligent management of large parking lot.
Description
Technical field
The present invention relates to field of artificial intelligence, specifically a kind of unmanned plane inspection based on neural network model
The method of parking offense.
Background technology
With the rapid development in city, the problem of city vehicle is more and more, parking difficulty, is also more and more prominent, thereupon
Be that the scale in parking lot is constantly expanded.With ever-expanding park construction, various the asking of parking generation in parking lot
Inscribe it is increasingly prominent, parking management become it is more complicated.The phenomenon that especially open parking ground, various unreasonable parkings, generally deposits
, illegal parking brings many troubles to the trip of people, if as soon as a vehicle is getting lodged in road or stand not just, have
May cause below vehicle all can not normal pass the case where.And due to the continuous expansion of parking lot scale, traditional manually patrols
Inspection, artificial commander and labor management far can not meet the needs of large parking lot.
In big data using increasingly extensive today, parking data resource how is efficiently used, by data analysis
It is effectively combined with parking management, is current problem to be solved to efficiently realize the quick, intelligent management of large parking lot.
Invention content
The technical assignment of the present invention is to be directed to the above shortcoming, provides a kind of unmanned plane based on neural network model and patrols
The method for examining parking offense, data analysis is combined with UAV system, continues to optimize management structure, realizes large parking lot
Intelligent management.
The technical solution adopted by the present invention to solve the technical problems is:
A method of the unmanned plane inspection parking offense based on neural network model is calculated based on the image recognition in deep learning
Method, the model of training certain depth study, and the model is applied to UAV system, realize parking lot illegal parking behavior
Detection;Its implementation is as follows:
S1:Parking facility image information is acquired, and demarcates parking data collection;
S2:The parking data collection training neural network model parameter obtained using S1;
S3:It is used for the neural network model that training is completed that classification is identified to the video image that unmanned plane acquires, class of classifying
Parking data collection spotting is not corresponded to;
S4:The image of cruise shooting is sent to control centre by unmanned plane, and control centre is based on image recognition algorithm judgement parking
Whether in violation of rules and regulations, and corresponding control instruction is sent to unmanned plane.
Image recognition algorithm is that computer handles image, analyzed and understood, to identify the mesh of various different modes
Mark and object, that is, the content that allows computer to understand image as people.By image recognition technology, we can not only lead to
It crosses picture searching and obtains information faster, a kind of new mode interact with the external world can also be generated, so that outside can allow
The more intelligent operation in the world.Currently, the fast development of deep learning, considerable application is obtained in images steganalysis field,
It can be by training neural network model, to identify the specific objective in image.
For the parking stall on open parking ground and road, many advantages, first, unmanned plane have been detected with unmanned plane
Mobility is good, can not only fly to and shot in the air to entire parking facility, but also can cruise along parking stall, to individual
Vehicle carries out positioning shooting;In addition, the method for unmanned plane inspection can greatly save manpower, administrative staff only need in data
Center carries out shirtsleeve operation to unmanned plane.Unmanned plane may be implemented high-altitude take photo by plane detection vehicle, automatic cruising detection vehicle
And automatically record violation vehicle car plate.
Preferably, calibration parking data collection is to be labeled the image information of collected parking facility, label target
Including vehicle, headstock, free parking spaces, car plate and stop line.For special screne or with development and improve the parking occurred
In the diversified scene in field, when these above-mentioned label targets can not preferably react parking information, label target can be increased newly, and will be new
Label target after increasing carries out neural network model training, to reach real-time update model, adapts to the diversified demand in parking lot.
Further, include vehicle, headstock, free parking spaces, car plate to the video image classifier classification of unmanned plane acquisition
And stop line;Headstock detection is for judging whether parking direction meets regulation;Car plate detection is right after violation vehicle for detecting
The evidence obtaining of taking pictures of car plate;Free parking spaces detect the quantity and orientation for obtaining the current free parking spaces in parking lot, Ke Yizuo
For the foundation of stopping guide;Stop line detection is for judging the vehicle on parking stall with the presence or absence of crimping or beyond the feelings on parking stall
Condition.Classified by information above, control centre accurate can identify the parking information of vehicle.Certainly, for improvement,
While parking data collection label target is changed, the video image classifier classification of unmanned plane acquisition can also change correspondingly.
Preferably, training neural network model parameter is selected neural network model of the SSD models as image recognition, is repaiied
Change last full articulamentum, class categories is set as to demarcate the mark classification of parking data collection, by the data of calibration for instructing
Practice the neural network model, the image recognition model after the completion of training is realized in UAV system.
In open parking ground, unmanned plane flies first to taking photo by plane in midair to entire parking lot, identifies vehicle location, sky
Set parking stall and headstock direction, the image comprising these information be sent to control centre, control centre by comparison nobody
Whether in violation of rules and regulations the parking stall of parking position and standard that machine is sent judges parking, including be in the way vehicle and headstock be not towards reciprocity
Behavior;Then unmanned plane cruises one by one to parking stall inspection by cruise route, which controls or press predetermined road by staff
Diameter starts, to stop it is not in place, checked beyond the phenomenon that parking stall frame, carry out car plate automatically to violation vehicle and take pictures to take
Card.
UAV system is equally applicable for parking garage, indoors in parking lot, since the space of parking garage has
Limit, can not carry out high-altitude and take photo by plane, can directly carry out inspection.Unmanned plane carries out cruise inspection one by one by cruise route to parking stall,
The vehicle image information of shooting is sent to control centre, control centre is by comparing the parking position and standard that unmanned plane is sent
Parking stall, judge parking whether in violation of rules and regulations, and to stop it is not in place, checked beyond the phenomenon that parking stall frame, to violation vehicle
The automatic car plate that carries out is taken pictures evidence obtaining.
Preferably, unmanned plane cruise route includes specified cruise route and automatic cruising route, specify cruise route according to
Control centre feeds back parking violation information and in violation of rules and regulations multiple ground and specifies, the rule-breaking vehicle data that can be obtained according to control centre
Information specifies unmanned plane cruise route;Automatic cruising route is to preset route, ensures the parking order in entire parking lot.
Specified cruise route and automatic cruising route can jointly be completed by multiple UAVs, when parking lot is busier, both can guarantee and stopped
Parking lot is locally unimpeded, and can guarantee that entire parking lot is in perfect order.
Preferably, acquisition parking facility image information includes not timing acquisition special screne information, when image information is classified
When classification matches that improper, effect is bad with data set spotting, which is marked again, and is used for neural network mould
The further training of type, suitably increases class categories to special screne, remodifies trained neural network model.Ensure number with this
According to diversified, more scenes and not timing, meet different scenes, demand in different time periods.
Preferably, the acquisition of parking lot image information is carried out using unmanned plane.Data set information is set to be patrolled with use
The information acquired of navigating is more close to it is more accurate to judge.
Preferably, control centre is provided with display screen, the image information for showing unmanned plane shooting.Staff can thing
Real observation Parking information, convenient for management.
The present invention a kind of unmanned plane inspection parking offense based on neural network model method compared to the prior art,
It has the advantages that:
This method realizes the detection of parking lot illegal parking behavior based on image recognition technology on unmanned aerial vehicle platform, using depth
Image recognition algorithm in study, the learning model of training certain depth, and then applied to the parking information intelligence of unmanned plane shooting
It can detect, including high-altitude takes photo by plane and detects vehicle, automatic cruising detection vehicle and automatically record violation vehicle car plate, enumerates from height
Empty detection, automatic cruising, the whole flow process positioned in violation of rules and regulations.It can check the stand of vehicle, headstock direction, whether be in the way
Behavior.
Unmanned plane have the characteristics that mobility strong, can high-altitude shooting, automatic cruising, be very suitable for open parking ground in violation of rules and regulations
The behavioral value of parking contributes to the management in wisdom parking lot.Using the method for unmanned plane inspection, administrative staff only need in number
Shirtsleeve operation is carried out to unmanned plane according to center, manpower can be greatly saved, improve the efficiency of management.
Description of the drawings
Fig. 1 is the schematic diagram of the unmanned plane inspection parking offense method the present invention is based on neural network model.
Specific implementation mode
The present invention is further explained in the light of specific embodiments.
A method of the unmanned plane inspection parking offense based on neural network model is known based on the image in deep learning
Other algorithm, the model of training certain depth study, and the model is applied to UAV system, taken photo by plane by unmanned plane high-altitude,
The method of automatic cruising and parking stall measure realizes the detection of parking lot illegal parking behavior, checks vehicle parking position, headstock side
To, whether the behaviors such as be in the way, and take pictures evidence obtaining to violation vehicle automatically.
Image recognition algorithm is that computer handles image, analyzed and understood, to identify the mesh of various different modes
Mark and object, that is, the content that allows computer to understand image as people.By image recognition technology, we can not only lead to
It crosses picture searching and obtains information faster, a kind of new mode interact with the external world can also be generated, so that outside can allow
The more intelligent operation in the world.Currently, the fast development of deep learning, considerable application is obtained in images steganalysis field,
It can be by training neural network model, to identify the specific objective in image.
For the parking stall on open parking ground and road, many advantages, first, unmanned plane have been detected with unmanned plane
Mobility is good, can not only fly to and shot in the air to entire parking facility, but also can cruise along parking stall, to individual
Vehicle carries out positioning shooting;In addition, the method for unmanned plane inspection can greatly save manpower, administrative staff only need in data
Center carries out shirtsleeve operation to unmanned plane.Unmanned plane may be implemented high-altitude take photo by plane detection vehicle, automatic cruising detection vehicle
And automatically record violation vehicle car plate.
The realization of this method is as follows:
1, parking facility image information is acquired, and demarcates parking data collection.Gathered data is with diversification, more scenes and not timing
Subject to, to meet demand in different time periods, collected data are manually marked, label target include vehicle, headstock,
Free parking spaces, car plate and stop line.And for special screne or with development improve in the parking lot diversification scene occurred,
When these above-mentioned label targets can not preferably react parking information, label target can be increased newly, and will it is newly-increased after label target
Neural network model training is carried out, to reach real-time update model, adapts to the diversified demand in parking lot.
The acquisition of parking lot image information is carried out using unmanned plane.Make data set information and cruise acquisition in use
Information is more close to it is more accurate to judge.
2, the parking data collection demarcated using step 1 trains neural network model on the server.Selected SSD models are made
For the neural network model of image recognition, last full articulamentum is changed, class categories are set as to demarcate parking data collection
Classification is marked, by the data of calibration for training the neural network model, the image recognition mould after the completion of training on the server
Type is realized in UAV system.
It is used for the neural network model that training is completed that classification is identified to the video image that unmanned plane acquires, class of classifying
Parking data collection spotting is not corresponded to.Video image classifier classification to unmanned plane acquisition includes vehicle, headstock, vacant parking
Position, car plate and stop line;Headstock detection is for judging whether parking direction meets regulation;Car plate detection is used to detect in violation of rules and regulations
It takes pictures evidence obtaining to car plate after vehicle;Free parking spaces detect the quantity and orientation for obtaining the current free parking spaces in parking lot,
It can be as the foundation of stopping guide;Stop line detection is for judging the vehicle on parking stall with the presence or absence of crimping or beyond parking
The case where position.Classified by information above, control centre accurate can identify the parking information of vehicle.Certainly, for
It improves, while parking data collection label target is changed, the video image classifier classification of unmanned plane acquisition also can be therewith
Change.
3, after inspection starts, unmanned plane, which can be flown to, in the air takes photo by plane to entire parking lot, identifies position, the sky of vehicle
Parking stall and the direction of headstock are set, the image of cruise shooting is sent to control centre by unmanned plane.
4, control centre is disobeyed by comparing the parking stall of parking position and standard that unmanned plane is sent to determine whether existing
The behavior of parking is advised, including be in the way vehicle and the not reciprocity behavior of headstock direction, unmanned plane pair is controlled after finding unlawful practice
Violation vehicle carries out evidence obtaining of taking pictures, which has used license plate image identification, it can be achieved that automatic evidence-collecting process.
5, control centre is provided with display screen, the image information for showing unmanned plane shooting.Control centre is by unmanned plane
In the free parking spaces presentation of information to display screen sent, guiding carrys out vehicle and is quickly found out parking stall;Meanwhile staff can be true
Parking information is observed, convenient for management.
6, following unmanned plane carries out cruise inspection in the case where control centre controls or by with top route, which has used vehicle
Bit line checking process, emphasis judgement parking is not in place, exceeds the phenomenon that parking stall frame.
7, unmanned plane traverses all parking stalls successively, judges that there is vehicle in current parking stall by image recognition first, then identifies
Parking stall line, when discovery parking stall line missing(It is blocked)The case where after, according to missing parking stall line position judgment be parking it is not in place
Then the problem of being also above parking frame carries out automatic Car license recognition, evidence obtaining of taking pictures to violation vehicle.
The process that primary cruise checks generally is initiated by parking lot staff.
In open parking ground, unmanned plane flies first to taking photo by plane in midair to entire parking lot, identifies vehicle location, sky
Set parking stall and headstock direction, the image comprising these information be sent to control centre, control centre by comparison nobody
Whether in violation of rules and regulations the parking stall of parking position and standard that machine is sent judges parking, including be in the way vehicle and headstock be not towards reciprocity
Behavior;Then unmanned plane cruises one by one to parking stall inspection by cruise route, which controls or press predetermined road by staff
Diameter starts, to stop it is not in place, checked beyond the phenomenon that parking stall frame, carry out car plate automatically to violation vehicle and take pictures to take
Card.
UAV system is equally applicable for parking garage, indoors in parking lot, since the space of parking garage has
Limit, can not carry out high-altitude and take photo by plane, can directly carry out inspection.Unmanned plane carries out cruise inspection one by one by cruise route to parking stall,
The vehicle image information of shooting is sent to control centre, control centre is by comparing the parking position and standard that unmanned plane is sent
Parking stall, judge parking whether in violation of rules and regulations, and to stop it is not in place, checked beyond the phenomenon that parking stall frame, to violation vehicle
The automatic car plate that carries out is taken pictures evidence obtaining.
Unmanned plane cruise route includes specified cruise route and automatic cruising route, specifies cruise route according to control centre
Feedback parking violation information and violation are specified multiplely, and the rule-breaking vehicle data information that can be obtained according to control centre refers to
Determine unmanned plane cruise route;Automatic cruising route is to preset route, ensures the parking order in entire parking lot.Specified cruise
Route and automatic cruising route can jointly be completed by multiple UAVs, when parking lot is busier, both can guarantee parking lot part
It is unimpeded, and can guarantee that entire parking lot is in perfect order.
Acquisition parking facility image information includes not timing acquisition special screne information, when image information class categories and number
According to when collection spotting matching is improper, effect is bad, which is marked again, and for neural network model into one
Step training, suitably increases class categories to special screne, remodifies trained neural network model.Ensure the various of data with this
Change, more scenes and not timing, meet different scenes, demand in different time periods.
This method utilizes unmanned plane, is taken photo by plane by high-altitude and detects vehicle, automatic cruising detects vehicle and automatically records in violation of rules and regulations
The method of vehicle license plate realizes the management in parking lot, saves a large amount of human resources, and realizes parking lot fast and efficiently
Intelligent management.
The technical personnel in the technical field can readily realize the present invention with the above specific embodiments,.But it answers
Work as understanding, the present invention is not limited to above-mentioned specific implementation modes.On the basis of the disclosed embodiments, the technical field
Technical staff can arbitrarily combine different technical features, to realize different technical solutions.
It is the known technology of those skilled in the art in addition to the technical characteristic described in specification.
Claims (10)
1. a kind of method of the unmanned plane inspection parking offense based on neural network model, it is characterised in that based in deep learning
Image recognition algorithm, training certain depth study model, and by the model be applied to UAV system, realize parking lot disobey
Advise the detection of parking behavior;Its implementation is as follows:
S1:Parking facility image information is acquired, and demarcates parking data collection;
S2:The parking data collection training neural network model parameter obtained using S1;
S3:It is used for the neural network model that training is completed that classification is identified to the video image that unmanned plane acquires, class of classifying
Parking data collection spotting is not corresponded to;
S4:The image of cruise shooting is sent to control centre by unmanned plane, and control centre is based on image recognition algorithm judgement parking
Whether in violation of rules and regulations, and corresponding control instruction is sent to unmanned plane.
2. a kind of method of unmanned plane inspection parking offense based on neural network model according to claim 1, special
Sign be demarcate parking data collection be to be labeled the image information of collected parking facility, label target include vehicle,
Headstock, free parking spaces, car plate and stop line.
3. a kind of method of unmanned plane inspection parking offense based on neural network model according to claim 2, special
Sign is that the video image classifier classification that unmanned plane acquires include vehicle, headstock, free parking spaces, car plate and stop line;Vehicle
Head detection is for judging whether parking direction meets regulation;Car plate detection is for taking taking pictures for car plate after detecting violation vehicle
Card;Free parking spaces detect the quantity and orientation for obtaining the current free parking spaces in parking lot;Stop line is detected for judging
The case where vehicle on parking stall whether there is crimping or exceed parking stall.
4. a kind of method of unmanned plane inspection parking offense based on neural network model according to claim 1 or 2,
It is characterized in that training neural network model parameter, selectes neural network model of the SSD models as image recognition, change last
Class categories are set as demarcating the mark classification of parking data collection, by the data of calibration for training the nerve by full articulamentum
Network model, the image recognition model after the completion of training are realized in UAV system.
5. a kind of method of unmanned plane inspection parking offense based on neural network model according to claim 3, special
Sign is in open parking ground that unmanned plane flies first to taking photo by plane in midair to entire parking lot, and identification vehicle location vacant stops
In violation of rules and regulations whether the image comprising these information is sent to control centre by parking stall and headstock direction, judge parking;Then nobody
Machine cruises one by one to parking stall inspection by cruise route.
6. a kind of method of unmanned plane inspection parking offense based on neural network model according to claim 3, special
Sign is in parking garage that unmanned plane carries out cruise inspection one by one by cruise route to parking stall, by the vehicle image of shooting
In violation of rules and regulations whether information is sent to control centre, judge parking.
7. a kind of method of unmanned plane inspection parking offense based on neural network model according to claim 5 or 6,
It is characterized in that unmanned plane cruise route includes specified cruise route and automatic cruising route, specifies cruise route according to control centre
Feedback parking violation information and violation are specified multiplely, and automatic cruising route is to preset route.
8. a kind of method of unmanned plane inspection parking offense based on neural network model according to claim 1, special
Sign is that it includes not timing acquisition special screne information to acquire parking facility image information, when image information class categories and data
Collect spotting to match not at that time, which is marked again, and for the further training of neural network model.
9. a kind of method of unmanned plane inspection parking offense based on neural network model according to claim 1, special
Sign is to carry out the acquisition of parking lot image information using unmanned plane.
10. a kind of method of unmanned plane inspection parking offense based on neural network model according to claim 1, special
Sign is that control centre is provided with display screen, the image information for showing unmanned plane shooting.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810375741.6A CN108510750A (en) | 2018-04-25 | 2018-04-25 | A method of the unmanned plane inspection parking offense based on neural network model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810375741.6A CN108510750A (en) | 2018-04-25 | 2018-04-25 | A method of the unmanned plane inspection parking offense based on neural network model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108510750A true CN108510750A (en) | 2018-09-07 |
Family
ID=63399106
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810375741.6A Pending CN108510750A (en) | 2018-04-25 | 2018-04-25 | A method of the unmanned plane inspection parking offense based on neural network model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108510750A (en) |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109118779A (en) * | 2018-10-12 | 2019-01-01 | 东软集团股份有限公司 | Break in traffic rules and regulations information identifying method, equipment and readable storage medium storing program for executing |
CN109360423A (en) * | 2018-12-03 | 2019-02-19 | 广元量知汇科技有限公司 | A kind of traffic based on cloud computing is separated to stop cruising inspection system |
CN109447069A (en) * | 2018-10-31 | 2019-03-08 | 沈阳工业大学 | Collecting vehicle information recognition methods and system towards intelligent terminal |
CN109635762A (en) * | 2018-12-18 | 2019-04-16 | 正元地理信息有限责任公司 | A kind of city management method, system and device |
CN109686087A (en) * | 2018-12-28 | 2019-04-26 | 西安艾润物联网技术服务有限责任公司 | The management method and device of patrol robot |
CN109800658A (en) * | 2018-12-26 | 2019-05-24 | 中汽研(天津)汽车工程研究院有限公司 | Parking position type online recognition neural network based and positioning system and method |
CN109815912A (en) * | 2019-01-28 | 2019-05-28 | 象谱信息产业有限公司 | A kind of expressway safety inspection system based on artificial intelligence |
CN109887325A (en) * | 2019-03-19 | 2019-06-14 | 南京维智感网络科技有限公司 | Road-surface concrete field managing device and its method based on Xian Zou mechanism |
CN110619750A (en) * | 2019-08-15 | 2019-12-27 | 重庆特斯联智慧科技股份有限公司 | Intelligent aerial photography identification method and system for illegal parking vehicle |
CN111147738A (en) * | 2019-12-19 | 2020-05-12 | 武汉裕众信息科技有限公司 | Police vehicle-mounted panoramic and coma system, device, electronic equipment and medium |
CN111259809A (en) * | 2020-01-17 | 2020-06-09 | 五邑大学 | Unmanned aerial vehicle coastline floating garbage inspection system based on DANet |
CN112052768A (en) * | 2020-08-28 | 2020-12-08 | 五邑大学 | Urban illegal parking detection method and device based on unmanned aerial vehicle and storage medium |
CN112149595A (en) * | 2020-09-29 | 2020-12-29 | 爱动超越人工智能科技(北京)有限责任公司 | Method for detecting lane line and vehicle violation by using unmanned aerial vehicle |
CN112201051A (en) * | 2020-11-27 | 2021-01-08 | 中航金城无人系统有限公司 | Unmanned aerial vehicle end road surface vehicle illegal parking detection and evidence obtaining system and method |
CN113158989A (en) * | 2021-05-19 | 2021-07-23 | 北京骑胜科技有限公司 | Two-wheeled vehicle parking violation detection method and device, electronic equipment and readable storage medium |
CN113469114A (en) * | 2021-07-19 | 2021-10-01 | 国网陕西省电力公司电力科学研究院 | Method, device and equipment for identifying environmental water conservation disturbed soil range of power transmission line |
CN113554878A (en) * | 2021-09-18 | 2021-10-26 | 深圳市城市交通规划设计研究中心股份有限公司 | Road section impedance function determination method, calculation device and storage medium |
CN114446059A (en) * | 2021-12-29 | 2022-05-06 | 北京智联云海科技有限公司 | System and method for vehicle-mounted monitoring of roadside parking vehicles |
CN114724364A (en) * | 2022-03-29 | 2022-07-08 | 北京万集科技股份有限公司 | Vehicle management and control method, device, equipment, storage medium and program product |
CN114724363A (en) * | 2022-03-29 | 2022-07-08 | 北京万集科技股份有限公司 | Vehicle management and control method, device, equipment, storage medium and program product |
CN115497329A (en) * | 2022-09-19 | 2022-12-20 | 安徽凯旋智能停车设备有限公司 | Unmanned management system of small-size garage parking |
CN117765417A (en) * | 2023-12-20 | 2024-03-26 | 城市大脑(广州)科技有限公司 | Shared vehicle inspection method and device based on unmanned aerial vehicle and storage medium |
CN117765417B (en) * | 2023-12-20 | 2024-07-09 | 城市大脑(广州)科技有限公司 | Shared vehicle inspection method and device based on unmanned aerial vehicle and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07230598A (en) * | 1994-02-16 | 1995-08-29 | Nagoya Denki Kogyo Kk | Parking state measuring device |
CN104112370A (en) * | 2014-07-30 | 2014-10-22 | 哈尔滨工业大学深圳研究生院 | Monitoring image based intelligent parking lot parking place identification method and system |
CN107886761A (en) * | 2017-11-14 | 2018-04-06 | 金陵科技学院 | A kind of parking lot monitoring method based on unmanned plane |
CN107909081A (en) * | 2017-10-27 | 2018-04-13 | 东南大学 | The quick obtaining and quick calibrating method of image data set in a kind of deep learning |
-
2018
- 2018-04-25 CN CN201810375741.6A patent/CN108510750A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07230598A (en) * | 1994-02-16 | 1995-08-29 | Nagoya Denki Kogyo Kk | Parking state measuring device |
CN104112370A (en) * | 2014-07-30 | 2014-10-22 | 哈尔滨工业大学深圳研究生院 | Monitoring image based intelligent parking lot parking place identification method and system |
CN107909081A (en) * | 2017-10-27 | 2018-04-13 | 东南大学 | The quick obtaining and quick calibrating method of image data set in a kind of deep learning |
CN107886761A (en) * | 2017-11-14 | 2018-04-06 | 金陵科技学院 | A kind of parking lot monitoring method based on unmanned plane |
Non-Patent Citations (2)
Title |
---|
周晓彦,王珂,李凌燕: "基于深度学习的目标检测算法综述", 《电子测量技术》 * |
林晓翠: "基于深度学习的车辆检测研究", 《万方数据知识服务平台》 * |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109118779B (en) * | 2018-10-12 | 2021-05-11 | 东软集团股份有限公司 | Traffic violation information identification method, equipment and readable storage medium |
CN109118779A (en) * | 2018-10-12 | 2019-01-01 | 东软集团股份有限公司 | Break in traffic rules and regulations information identifying method, equipment and readable storage medium storing program for executing |
CN109447069A (en) * | 2018-10-31 | 2019-03-08 | 沈阳工业大学 | Collecting vehicle information recognition methods and system towards intelligent terminal |
CN109360423A (en) * | 2018-12-03 | 2019-02-19 | 广元量知汇科技有限公司 | A kind of traffic based on cloud computing is separated to stop cruising inspection system |
CN109635762A (en) * | 2018-12-18 | 2019-04-16 | 正元地理信息有限责任公司 | A kind of city management method, system and device |
CN109800658A (en) * | 2018-12-26 | 2019-05-24 | 中汽研(天津)汽车工程研究院有限公司 | Parking position type online recognition neural network based and positioning system and method |
CN109686087A (en) * | 2018-12-28 | 2019-04-26 | 西安艾润物联网技术服务有限责任公司 | The management method and device of patrol robot |
CN109815912A (en) * | 2019-01-28 | 2019-05-28 | 象谱信息产业有限公司 | A kind of expressway safety inspection system based on artificial intelligence |
CN109815912B (en) * | 2019-01-28 | 2023-04-07 | 象谱信息产业有限公司 | Highway safety inspection system based on artificial intelligence |
CN109887325A (en) * | 2019-03-19 | 2019-06-14 | 南京维智感网络科技有限公司 | Road-surface concrete field managing device and its method based on Xian Zou mechanism |
CN110619750A (en) * | 2019-08-15 | 2019-12-27 | 重庆特斯联智慧科技股份有限公司 | Intelligent aerial photography identification method and system for illegal parking vehicle |
CN111147738A (en) * | 2019-12-19 | 2020-05-12 | 武汉裕众信息科技有限公司 | Police vehicle-mounted panoramic and coma system, device, electronic equipment and medium |
CN111259809B (en) * | 2020-01-17 | 2021-08-17 | 五邑大学 | Unmanned aerial vehicle coastline floating garbage inspection system based on DANet |
CN111259809A (en) * | 2020-01-17 | 2020-06-09 | 五邑大学 | Unmanned aerial vehicle coastline floating garbage inspection system based on DANet |
CN112052768A (en) * | 2020-08-28 | 2020-12-08 | 五邑大学 | Urban illegal parking detection method and device based on unmanned aerial vehicle and storage medium |
CN112149595A (en) * | 2020-09-29 | 2020-12-29 | 爱动超越人工智能科技(北京)有限责任公司 | Method for detecting lane line and vehicle violation by using unmanned aerial vehicle |
CN112201051A (en) * | 2020-11-27 | 2021-01-08 | 中航金城无人系统有限公司 | Unmanned aerial vehicle end road surface vehicle illegal parking detection and evidence obtaining system and method |
CN112201051B (en) * | 2020-11-27 | 2021-07-06 | 中航金城无人系统有限公司 | Unmanned aerial vehicle end road surface vehicle illegal parking detection and evidence obtaining system and method |
CN113158989A (en) * | 2021-05-19 | 2021-07-23 | 北京骑胜科技有限公司 | Two-wheeled vehicle parking violation detection method and device, electronic equipment and readable storage medium |
CN113469114A (en) * | 2021-07-19 | 2021-10-01 | 国网陕西省电力公司电力科学研究院 | Method, device and equipment for identifying environmental water conservation disturbed soil range of power transmission line |
CN113554878A (en) * | 2021-09-18 | 2021-10-26 | 深圳市城市交通规划设计研究中心股份有限公司 | Road section impedance function determination method, calculation device and storage medium |
CN114446059A (en) * | 2021-12-29 | 2022-05-06 | 北京智联云海科技有限公司 | System and method for vehicle-mounted monitoring of roadside parking vehicles |
CN114724364A (en) * | 2022-03-29 | 2022-07-08 | 北京万集科技股份有限公司 | Vehicle management and control method, device, equipment, storage medium and program product |
CN114724363A (en) * | 2022-03-29 | 2022-07-08 | 北京万集科技股份有限公司 | Vehicle management and control method, device, equipment, storage medium and program product |
CN115497329A (en) * | 2022-09-19 | 2022-12-20 | 安徽凯旋智能停车设备有限公司 | Unmanned management system of small-size garage parking |
CN115497329B (en) * | 2022-09-19 | 2023-10-17 | 安徽凯旋智能停车设备有限公司 | Unmanned management system for small parking garage |
CN117765417A (en) * | 2023-12-20 | 2024-03-26 | 城市大脑(广州)科技有限公司 | Shared vehicle inspection method and device based on unmanned aerial vehicle and storage medium |
CN117765417B (en) * | 2023-12-20 | 2024-07-09 | 城市大脑(广州)科技有限公司 | Shared vehicle inspection method and device based on unmanned aerial vehicle and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108510750A (en) | A method of the unmanned plane inspection parking offense based on neural network model | |
CN108037770B (en) | Unmanned aerial vehicle power transmission line inspection system and method based on artificial intelligence | |
CN110197589B (en) | Deep learning-based red light violation detection method | |
CN106203265B (en) | A kind of Construction Fugitive Dust Pollution source monitors automatically and coverage forecasting system and method | |
CN110660222B (en) | Intelligent environment-friendly electronic snapshot system for black-smoke road vehicle | |
CN107886761A (en) | A kind of parking lot monitoring method based on unmanned plane | |
CN106251695B (en) | Destination parking stall intelligent recommendation system and method based on parking space state monitoring | |
CN105590479B (en) | Parking stall monitoring method and device | |
CN108189043A (en) | A kind of method for inspecting and crusing robot system applied to high ferro computer room | |
CN111009150B (en) | Open type parking lot management method and system and background server | |
CN112287827A (en) | Complex environment pedestrian mask wearing detection method and system based on intelligent lamp pole | |
CN111429726A (en) | Monitoring video illegal parking vehicle detection and management method and corresponding system | |
WO2021043074A1 (en) | Urban pet motion trajectory monitoring method based on image recognition, and related devices | |
CN109741628A (en) | A kind of cell intelligent parking system and the intelligent parking route planning method using it | |
CN107591018A (en) | A kind of open section parking management method and system | |
CN107705631A (en) | The structure and application method of managing system of car parking | |
WO2021237768A1 (en) | Data-driven-based system for implementing automatic iteration of prediction model | |
CN111898485A (en) | Parking space vehicle detection processing method and device | |
CN110070729A (en) | It is a kind of that vehicle detecting system and method are stopped based on the separated of mist calculating | |
CN111723704A (en) | Raspberry pie-based van body door opening monitoring method | |
CN113313006A (en) | Urban illegal construction supervision method and system based on unmanned aerial vehicle and storage medium | |
CN207020820U (en) | Red-running Monitor System | |
CN113486885A (en) | License plate recognition method and device, electronic equipment and storage medium | |
CN111597900A (en) | Illegal dog walking identification method | |
CN114512005B (en) | Road self-inspection method and device, unmanned aerial vehicle and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180907 |