CN109063612A - City intelligent red line management method and machine readable storage medium - Google Patents
City intelligent red line management method and machine readable storage medium Download PDFInfo
- Publication number
- CN109063612A CN109063612A CN201810798182.XA CN201810798182A CN109063612A CN 109063612 A CN109063612 A CN 109063612A CN 201810798182 A CN201810798182 A CN 201810798182A CN 109063612 A CN109063612 A CN 109063612A
- Authority
- CN
- China
- Prior art keywords
- image
- regulations
- extracted
- violating
- video monitoring
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to city intelligent management domains.The embodiment of the present invention provides a kind of city intelligent red line management method and machine readable storage medium, and the city intelligent red line management method includes: to obtain video monitoring picture；The characteristics of image in the video monitoring picture is extracted, and identifies whether extracted characteristics of image is characteristics of image violating the regulations based on scene characteristic model and the violation recognition rule of setting；If extracted characteristics of image is characteristics of image violating the regulations, judge whether the extracted characteristics of image meets alarm conditions；And when the extracted characteristics of image meets alarm conditions, alarm operation is executed.Thus, city management personnel are changed into video auditor from by video monitor personnel, it frees from " extremely staring at " screen, the event that absorbed center of gravity is placed on after video analytic system alarm triggering is verified in work, realize that efficient expansion of the video monitoring system in city management field utilizes.
Description
Technical field
The present invention relates to city intelligent management domains, can more particularly to a kind of city intelligent red line management method and machine
Read storage medium.
Background technique
It investigates and prosecutes currently, municipal administration is violating the regulations mainly by scene patrol and video monitoring.Wherein, on the one hand, scene patrol will lead to
The waste of human resources, and supervisory efficiency is low；On the other hand, traditional video monitoring system needs to set up full-time video
Monitoring inspection troop, and need uninterruptedly manually to check video-frequency monitor content for a long time, it is easy to cause staff's vision tired
Labor, decreased attention, inefficiency；Also, often an operator on duty needs against multiple monitors, and eye-observation range has
Limit can not pay close attention to multiple screens simultaneously for a long time, can not effectively find illegal activities and be handled；In addition, since human eye regards
Feel that sensitivity is limited, light is changed greatly, monitors and can not discover apart from farther away scene；Traditional video monitoring system is only
Only naked eyes are unfolded around video monitoring picture itself, easy to omit illegal activities taken by monitor video.
Summary of the invention
The purpose of the embodiment of the present invention is that providing a kind of city intelligent red line management method and machine readable storage medium, use
At least to solve the problems, such as that video monitoring picture excessively relies on personnel's monitoring in the prior art.
To achieve the goals above, the embodiment of the present invention provides a kind of city intelligent red line management method, comprising: obtains view
Frequency monitored picture；The characteristics of image in the video monitoring picture is extracted, and the violation based on scene characteristic model and setting
Recognition rule identifies whether extracted characteristics of image is characteristics of image violating the regulations；If extracted characteristics of image is that image violating the regulations is special
Sign, then judge whether the extracted characteristics of image meets alarm conditions；And when the extracted characteristics of image meets alarm
When condition, alarm operation is executed.
On the other hand the embodiment of the present invention provides a kind of machine readable storage medium, store on the machine readable storage medium
There is instruction, which is used for so that machine executes the above-mentioned city intelligent red line management method of the application.
Through the above technical solutions, automatic Prediction alarm scheme is proposed, so that after obtaining video monitoring picture certainly
Whether it is act of violating regulations for dynamic prediction, and alarm operation is executed when determining is act of violating regulations.It reduces as a result, and manually checks video
Monitor workload, by traditional personal monitoring's video transformation be intelligent recognition, automatic alarm, manual examination and verification confirmation mode,
Video monitor personnel are changed into video auditor, frees from " extremely staring at " screen, absorbed center of gravity is placed on video analysis
Event after system alarm triggering is verified in work, realizes that efficient expansion of the video monitoring system in city management field utilizes.
The other feature and advantage of the embodiment of the present invention will the following detailed description will be given in the detailed implementation section.
Detailed description of the invention
Attached drawing is to further understand for providing to the embodiment of the present invention, and constitute part of specification, under
The specific embodiment in face is used to explain the present invention embodiment together, but does not constitute the limitation to the embodiment of the present invention.Attached
In figure:
Fig. 1 is the flow chart of the city intelligent red line management method of one embodiment of the invention；
Fig. 2A is the operation principle schematic diagram applied to the semantic segmentation model in the embodiment of the present invention；
Fig. 2 B is the operation principle schematic diagram applied to the scene characteristic model in the embodiment of the present invention；
Fig. 3 is the training flow chart for scene characteristic model；
Fig. 4 is the general frame of the image recognition engine of one embodiment of the invention；
Fig. 5 is the flow chart of the city intelligent red line management method of another embodiment of the present invention.
Specific embodiment
It is described in detail below in conjunction with specific embodiment of the attached drawing to the embodiment of the present invention.It should be understood that this
Locate described specific embodiment and be merely to illustrate and explain the present invention embodiment, is not intended to restrict the invention embodiment.
As shown in Figure 1, the city intelligent red line management method of one embodiment of the invention, comprising:
S11, video monitoring picture is obtained, such as can be the video monitoring picture for parsing single frames from monitor video.
About the execution object of present invention method, one side can be various universal terminals or server,
, by installation application to be able to carry out above-mentioned method, another aspect, which can be, is exclusively used in setting for city intelligent red line management for it
It is standby etc..
Characteristics of image in S12, extraction video monitoring picture, and identified based on the violation of scene characteristic model and setting
Rule identifies whether extracted characteristics of image is characteristics of image violating the regulations.
Specifically, it can be extracts target zone by semantic segmentation model from video monitoring picture, the wherein language
Adopted parted pattern can be based on full convolutional neural networks (FCN) as shown in Figure 2 A, and detect in target zone
The characteristics of image of potential object violating the regulations is further as shown in Figure 2 B identified by the violation of scene characteristic model and setting
Rule classifies to characteristics of image, to determine whether that there are acts of violating regulations；Wherein, which is also possible to convolution
Neural network model, and the violation recognition rule then includes: identification region, quantity, accounts for figure ratio, similarity, whether has ginseng
With, whether combine identification, there are the combinations of one of interval time or a variety of Rule of judgment, to identified object and its group
Whether conjunction, which falls into the Rule of judgment, is determined.
Furthermore in order to rapidly identify whether characteristics of image belongs to characteristics of image violating the regulations, it can be and obtain in advance
There is no the initial video monitored pictures collected of Video Monitoring Terminal when act of violating regulations, and initial video monitored picture is demarcated
Background frame is monitored, wherein the monitoring background frame is schemed for identification by scene characteristic model and the violation recognition rule of setting
As whether feature is characteristics of image violating the regulations.
One of the convolutional neural networks model of deep layer is primary disadvantage is that need a large amount of data to carry out supporting network parameter
Training, otherwise network training is easy to not restrain.In order to solve this problem, the embodiment of the present invention proposes needle as shown in Figure 3
To the training process of scene characteristic model, the image data of corresponding characteristics of image violating the regulations is acquired including S121, from internet；
S122, classify according to characteristics of image violating the regulations to acquired image data, to obtain classification image data；S123, it is based on
Image data of classifying and corresponding characteristics of image violating the regulations, Training scene characteristic model.For example, characteristics of image violating the regulations includes following
One or more of: flowing street pedlar, occupy-street-exploit and illegal invasion region outside shop, and the aforementioned scene characteristic model due to
Belong to the scene characteristic model in the violation recognition rule of setting, meets the violation recognition rule, that is, meet preset identification
Region, quantity, account for figure ratio, similarity, whether someone participates in, whether combines identification, there are one of interval times or more
In the determination range that kind Rule of judgment combines, therefore it is judged as characteristics of image violating the regulations.
The embodiment of the present invention proposes the mode of transfer learning as a result,.First instructed using the taxonomy database on network
Practice, obtain the model of a pre-training, the model of pre-training can learn some shallow-layer features into image well, such as:
Texture, shape, the information such as color.The parameter of pre-training model is moved to again, training is gone to learn high-level language in actual task
Adopted feature promotes actual recognition effect.
If S13, extracted characteristics of image are characteristics of image violating the regulations, judge whether the extracted characteristics of image meets
Alarm conditions.
Specifically, on the one hand, parameter involved in the definition of alarm conditions includes: can be act of violating regulations duration threshold
Value, and by comparing extracted characteristics of image duration and the act of violating regulations duration threshold, at this time can be with
It is the duration for extracting the above-mentioned characteristics of image of continuous multiframe monitored picture, when the extracted characteristics of image is lasting
Time be greater than act of violating regulations duration threshold when execute alarm operation, such as when judge there are exceed the usual object in this region
The object of area-limit, and the duration of the object has been more than certain time, it may be considered that there may be the behavior of setting up a stall,
Meet alarm conditions.On the other hand, extracted behavior is related to target object, and alarm conditions include the quantity about target object
Threshold value, and when the instruction of extracted characteristics of image is there are when the target object that quantity is more than the amount threshold, execution alarm is grasped
Make, such as target object can be desk, stool, refrigerator-freezer etc., when identifying there are when multiple desks or stool, it may be considered that
There may be the behaviors of setting up a stall, and meet alarm conditions.
Since the required monitored object in different monitoring region and alarm conditions are different, in the embodiment of the present invention
In some preferred embodiments, it can be and corresponding alarm conditions are determined based on monitoring area type, wherein monitoring area type
It is pre-configured to be in Video Monitoring Terminal.It should be noted that Video Monitoring Terminal is mounted in the various types of of city
Region, bus station, shop along street can be mounted in and/or limited into area etc., however different regions is to row violating the regulations
For define and be different, such as bus station does not allow to set up a stall, limits and do not allow pedestrian to enter into area.As such, it can be that
Corresponding monitoring area type is configured for it for the installation environment of Video Monitoring Terminal, so that can in analytic process later
To determine alarm conditions according to the monitoring area type, such as it can be and be pre-configured in city intelligent red line management system
There is the relation table for having mapping relations " bus station-set up a stall alarm conditions ", " restricted area-illegal invasion area condition " etc.
Lattice.
S14, when the extracted characteristics of image meets alarm conditions, execute alarm operation.
About the mode of alarm operation, sound-light alarm, short message alarm etc. can be, to remind supervisor to pay attention to pair
The video monitoring picture that this is predicted or the video corresponding to it take measures.
To the camera photographed scene of each presetting bit, mark scene by hand is carried out, identification region is manually set, identifies object
Duration etc. in product and its characteristic parameter, recognition time section and article picture, remember as normal background, and by the information
Enter " one grade of a machine ", establishes archives for each camera.It, can quick lock in illegal activities using the matched archive information of case institute
Position.One one grade of machine " mainly records administration people, region scene classification corresponding to camera and camera types etc..
The multiple presetting bits of single camera can also be utilized, realize monitoring head presetting bit switching, realize that a machine monitoring is more
The function of a multiple events of scene, the comparison of grade image is stayed by presetting bit, to determine current presetting bit, and is utilized multiple preset
Image captured by position, many-sided comparison information reach making full use of for camera resource, one grade of a presetting bit are realized, thus right
The presetting bit of setting carries out corresponding intellectual analysis.
It is special due to municipal administration's business as shown in figure 4, the general frame of the image recognition engine of one embodiment of the invention
Property, determine personalization, the diversification of image recognition demand.The business of municipal administration is varied, and business focus also can be diversified,
Cause customer demand and business demand very scattered, there are many article to be identified and unlawful practice and continue to increase.Therefore, image
Well-designed engine is wanted in identification, facilitates extension and the good application of system.In addition, in intelligent red line management system, using with
Image is to be closely connected and mutually independent two parts.In development process, it should be noted that the modularization and interface specification of system.It is logical
Interface and service are crossed, two parts and the docking of more modules are got up, the maintainability and reliability of system are improved.
Image recognition engine includes video analysis service basic platform, algorithm model library and model iteration more new frame.It encloses
It is all kinds of interfaces with interface applications around image recognition engine, including one grade of a machine, images serve, region scene mark, immediately
Communication protocol etc. realizes whole video red line management by the integration with service application.
Wherein, image analysis service infrastructure platform meets the video image parsing demand of high concurrent, and multiple points are sent out simultaneously
Image is sent, different servers is distributed in and concurrently parses.Can meet the needs of high concurrent image analysis with fast construction cluster.
Wherein, algorithm model library is summarizing for all kinds of image recognition models, meets multiple business demand.Model algorithm reconciliation
It is relatively independent to analyse basic platform, it is convenient that model is continued to increase.Model algorithm largely uses deep learning and image understanding etc.
Cutting edge technology.And the violation recognition rule is accordingly advised also with changing as defined in alteration of law and administration
Adjustment then.
Wherein, model modification frame supports municipal administration's image recognition to need to carry out performance and function lasting iteration and update,
The convenience of this frame guarantee model modification.
By deep learning modelling technique and image recognition technology and make violation rule settings by oneself in embodiments of the present invention
It combines, for there is great amount of images data, the labeled data of high quality is obtained by the cleaning arrangement to data.Projected depth
Study detection identification model identifies municipal administration's concern target, objective attribute target attribute feature, the related event of target etc., realizes municipal administration
The intelligence of red line management.In actual items, according to specific business and the equipment situation of selection, function can be identified to product intelligent
It can be carried out expansion, such as increase the algorithm to the identification of vehicle dregs, architecture against regulations identification judgement.
On the other hand the embodiment of the present invention also provides a kind of machine readable storage medium, deposit on the machine readable storage medium
Instruction is contained, it is above-mentioned as performed by terminal the step of city intelligent red line management method to be respectively used to execute the application, should
The terminal that machine readable storage medium is installed can be arbitrary terminal, such as computer or server etc., specific skill
The details and effect of art scheme are referred to the description of embodiment of the method above, just do not repeat herein.
The optional embodiment of the embodiment of the present invention is described in detail in conjunction with attached drawing above, still, the embodiment of the present invention is simultaneously
The detail being not limited in above embodiment can be to of the invention real in the range of the technology design of the embodiment of the present invention
The technical solution for applying example carries out a variety of simple variants, these simple variants belong to the protection scope of the embodiment of the present invention.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case where shield, it can be combined in any appropriate way.In order to avoid unnecessary repetition, the embodiment of the present invention pair
No further explanation will be given for various combinations of possible ways.
It will be appreciated by those skilled in the art that implementing the method for the above embodiments is that can pass through
Program is completed to instruct relevant hardware, which is stored in a storage medium, including some instructions are used so that single
Piece machine, chip or processor (processor) execute all or part of the steps of each embodiment the method for the application.And it is preceding
The storage medium stated includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), magnetic or disk.
In addition, any combination can also be carried out between a variety of different embodiments of the embodiment of the present invention, as long as it is not
The thought of the embodiment of the present invention is violated, equally should be considered as disclosure of that of the embodiment of the present invention.
Claims (10)
1. a kind of city intelligent red line management method, comprising: obtain video monitoring picture；It extracts in the video monitoring picture
Characteristics of image, and identify whether extracted characteristics of image is separated based on scene characteristic model and the violation recognition rule of setting
Chapter characteristics of image；If extracted characteristics of image is characteristics of image violating the regulations, judge whether the extracted characteristics of image meets
Alarm conditions；And when the extracted characteristics of image meets alarm conditions, alarm operation is executed.
2. the method according to claim 1, wherein the violation recognition rule include: identification region, quantity,
Account for figure ratio, similarity, whether someone participates in, whether combines identification, there are one of interval time or a variety of Rule of judgment
Combination, to determine whether identified object and combinations thereof falls into the Rule of judgment.
3. the method according to claim 1, wherein the alarm conditions include act of violating regulations duration threshold
Value, wherein the execution alarm operation when the extracted characteristics of image meets alarm conditions includes: when the extracted figure
When being greater than the act of violating regulations duration threshold as feature duration, alarm operation is executed.
4. the method according to claim 1, wherein the extracted behavior is related to target object and described
Alarm conditions include the amount threshold about target object, wherein described when the extracted characteristics of image meets alarm conditions
Executing alarm operation includes: when there are the target objects that quantity is more than the amount threshold for the extracted characteristics of image instruction
When, execute alarm operation.
5. method described in claim 1, which is characterized in that judge whether extracted characteristics of image meets alarm bar described
Before part, this method further include: corresponding alarm conditions are determined based on monitoring area type, wherein the monitoring area type is
It is pre-configured to be in Video Monitoring Terminal.
6. according to the method described in claim 4, it is characterized in that, the monitoring area type includes one of following or more
Person: it bus station, shop along street and limits into area.
7. the method according to claim 1, wherein the characteristics of image violating the regulations includes one of following or more
Person: it is illegal set up a stall, occupy-street-exploit outside shop, region invasion, vehicle are disobeyed and stop and leave about in violation of rules and regulations article.
8. the method according to claim 1, wherein the violation of the scene characteristic model and setting identification rule
It is then convolutional neural networks model, wherein this method further includes for the violation of the scene characteristic model and setting identification rule
Training step then, specifically includes: the image data of corresponding characteristics of image violating the regulations is acquired from internet；It is special according to image violating the regulations
Sign classifies to described image data collected, to obtain classification image data；Based on the classification image data and phase
The violation recognition rule of corresponding characteristics of image violating the regulations, the training scene characteristic model and setting.
9. the method according to claim 1, wherein the characteristics of image extracted in the video monitoring picture
It include: to extract target zone from acquired video monitoring picture using semantic segmentation model, wherein the semantic segmentation mould
Type is based on full convolutional network model；Detect the characteristics of image of potential object violating the regulations in the target zone.
10. a kind of machine readable storage medium, it is stored with instruction on the machine readable storage medium, which is used for so that machine
Perform claim requires city intelligent red line management method described in any one of 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810798182.XA CN109063612A (en) | 2018-07-19 | 2018-07-19 | City intelligent red line management method and machine readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810798182.XA CN109063612A (en) | 2018-07-19 | 2018-07-19 | City intelligent red line management method and machine readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109063612A true CN109063612A (en) | 2018-12-21 |
Family
ID=64817393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810798182.XA Pending CN109063612A (en) | 2018-07-19 | 2018-07-19 | City intelligent red line management method and machine readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063612A (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109671244A (en) * | 2018-12-25 | 2019-04-23 | 张鸿青 | A kind of dangerous tip method and device based on bus station |
| CN109788222A (en) * | 2019-02-02 | 2019-05-21 | 视联动力信息技术股份有限公司 | A kind of processing method and processing device regarding networked video |
| CN109815852A (en) * | 2019-01-03 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Smart city event management method, device, computer equipment and storage medium |
| CN109889781A (en) * | 2019-02-02 | 2019-06-14 | 视联动力信息技术股份有限公司 | A kind of processing method and processing device regarding networked video |
| CN109905727A (en) * | 2019-02-02 | 2019-06-18 | 视联动力信息技术股份有限公司 | A kind of processing method and processing device regarding networked video |
| CN110012268A (en) * | 2019-04-02 | 2019-07-12 | 浙江璟恩物联网科技有限公司 | Pipe network AI intelligent control method, system, readable storage medium storing program for executing and equipment |
| CN110213530A (en) * | 2019-04-26 | 2019-09-06 | 视联动力信息技术股份有限公司 | Method for early warning, device and readable storage medium storing program for executing |
| CN110263748A (en) * | 2019-06-26 | 2019-09-20 | 北京百度网讯科技有限公司 | Method and apparatus for sending information |
| CN110458082A (en) * | 2019-08-05 | 2019-11-15 | 城云科技（中国）有限公司 | A kind of city management case classification recognition methods |
| CN110719441A (en) * | 2019-09-30 | 2020-01-21 | 傅程宏 | System and method for bank personnel behavior compliance early warning management |
| CN110728815A (en) * | 2019-10-25 | 2020-01-24 | 深圳市商汤科技有限公司 | Early warning method and device based on video analysis, electronic equipment and storage medium |
| CN110807393A (en) * | 2019-10-25 | 2020-02-18 | 深圳市商汤科技有限公司 | Early warning method and device based on video analysis, electronic equipment and storage medium |
| CN110968604A (en) * | 2019-12-05 | 2020-04-07 | 长春嘉诚信息技术股份有限公司 | Method for automatically retrieving illegal operation of internet operation enterprise |
| CN111553355A (en) * | 2020-05-18 | 2020-08-18 | 城云科技（中国）有限公司 | Method for detecting out-of-store operation and notifying management shop owner based on monitoring video |
| CN111563726A (en) * | 2020-04-30 | 2020-08-21 | 平安国际智慧城市科技股份有限公司 | Enterprise rectification supervision method, device, equipment and computer readable storage medium |
| CN112037520A (en) * | 2020-11-05 | 2020-12-04 | 杭州科技职业技术学院 | Road monitoring method and system and electronic equipment |
| CN112153329A (en) * | 2020-08-17 | 2020-12-29 | 浙江大华技术股份有限公司 | Configuration method, system, computer equipment and storage medium for event monitoring |
| CN112511610A (en) * | 2020-11-19 | 2021-03-16 | 上海营邑城市规划设计股份有限公司 | Vehicle-mounted patrol intelligent method and system based on urban fine management conditions |
| CN112560562A (en) * | 2019-09-26 | 2021-03-26 | 杭州海康威视***技术有限公司 | Method, apparatus and storage medium for identifying violations |
| CN112580470A (en) * | 2020-12-11 | 2021-03-30 | 北京软通智慧城市科技有限公司 | City visual perception method and device, electronic equipment and storage medium |
| CN112749681A (en) * | 2021-01-25 | 2021-05-04 | 长威信息科技发展股份有限公司 | Violation detection method based on edge equipment and deep learning |
| CN113139434A (en) * | 2021-03-29 | 2021-07-20 | 北京旷视科技有限公司 | City management event processing method and device, electronic equipment and readable storage medium |
| WO2021164644A1 (en) * | 2020-02-18 | 2021-08-26 | 深圳市商汤科技有限公司 | Violation event detection method and apparatus, electronic device, and storage medium |
| CN113420563A (en) * | 2021-06-18 | 2021-09-21 | 北京易华录信息技术股份有限公司 | City civilization monitoring method, system and device based on artificial intelligence |
| CN113852788A (en) * | 2021-09-03 | 2021-12-28 | 泰华智慧产业集团股份有限公司 | City management system based on video intelligent analysis |
| CN114627420A (en) * | 2022-03-23 | 2022-06-14 | 北京数字政通科技股份有限公司 | City management violation event information acquisition method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104506814A (en) * | 2014-12-31 | 2015-04-08 | 天津汉光祥云信息科技有限公司 | Scene change adaptive cross-line alarm method and device |
| CN105096596A (en) * | 2015-07-03 | 2015-11-25 | 北京润光泰力科技发展有限公司 | Traffic violation detecting method and system |
| CN105513371A (en) * | 2016-01-15 | 2016-04-20 | 昆明理工大学 | Expressway illegal parking detection method based on kernel density estimation |
| CN106127143A (en) * | 2016-06-23 | 2016-11-16 | 昆明理工大学 | A kind of highway parking offense detection method |
| CN106412508A (en) * | 2016-09-30 | 2017-02-15 | 北京中星微电子有限公司 | Intelligent monitoring method and system of illegal line press of vehicles |
| CN106874863A (en) * | 2017-01-24 | 2017-06-20 | 南京大学 | Vehicle based on depth convolutional neural networks is disobeyed and stops detection method of driving in the wrong direction |
| CN107221133A (en) * | 2016-03-22 | 2017-09-29 | 杭州海康威视数字技术股份有限公司 | A kind of area monitoring warning system and alarm method |
| CN107609491A (en) * | 2017-08-23 | 2018-01-19 | 中国科学院声学研究所 | A kind of vehicle peccancy parking detection method based on convolutional neural networks |
| CN107730903A (en) * | 2017-06-13 | 2018-02-23 | 银江股份有限公司 | Parking offense and the car vision detection system that casts anchor based on depth convolutional neural networks |
-
2018
- 2018-07-19 CN CN201810798182.XA patent/CN109063612A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104506814A (en) * | 2014-12-31 | 2015-04-08 | 天津汉光祥云信息科技有限公司 | Scene change adaptive cross-line alarm method and device |
| CN105096596A (en) * | 2015-07-03 | 2015-11-25 | 北京润光泰力科技发展有限公司 | Traffic violation detecting method and system |
| CN105513371A (en) * | 2016-01-15 | 2016-04-20 | 昆明理工大学 | Expressway illegal parking detection method based on kernel density estimation |
| CN107221133A (en) * | 2016-03-22 | 2017-09-29 | 杭州海康威视数字技术股份有限公司 | A kind of area monitoring warning system and alarm method |
| CN106127143A (en) * | 2016-06-23 | 2016-11-16 | 昆明理工大学 | A kind of highway parking offense detection method |
| CN106412508A (en) * | 2016-09-30 | 2017-02-15 | 北京中星微电子有限公司 | Intelligent monitoring method and system of illegal line press of vehicles |
| CN106874863A (en) * | 2017-01-24 | 2017-06-20 | 南京大学 | Vehicle based on depth convolutional neural networks is disobeyed and stops detection method of driving in the wrong direction |
| CN107730903A (en) * | 2017-06-13 | 2018-02-23 | 银江股份有限公司 | Parking offense and the car vision detection system that casts anchor based on depth convolutional neural networks |
| CN107609491A (en) * | 2017-08-23 | 2018-01-19 | 中国科学院声学研究所 | A kind of vehicle peccancy parking detection method based on convolutional neural networks |
Non-Patent Citations (1)
| Title |
|---|
| 吴玉枝等: "基于卷积神经网络的违章停车事件检测", 《图形图像》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109671244A (en) * | 2018-12-25 | 2019-04-23 | 张鸿青 | A kind of dangerous tip method and device based on bus station |
| CN109815852A (en) * | 2019-01-03 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Smart city event management method, device, computer equipment and storage medium |
| CN109788222A (en) * | 2019-02-02 | 2019-05-21 | 视联动力信息技术股份有限公司 | A kind of processing method and processing device regarding networked video |
| CN109889781A (en) * | 2019-02-02 | 2019-06-14 | 视联动力信息技术股份有限公司 | A kind of processing method and processing device regarding networked video |
| CN109905727A (en) * | 2019-02-02 | 2019-06-18 | 视联动力信息技术股份有限公司 | A kind of processing method and processing device regarding networked video |
| CN110012268A (en) * | 2019-04-02 | 2019-07-12 | 浙江璟恩物联网科技有限公司 | Pipe network AI intelligent control method, system, readable storage medium storing program for executing and equipment |
| CN110213530A (en) * | 2019-04-26 | 2019-09-06 | 视联动力信息技术股份有限公司 | Method for early warning, device and readable storage medium storing program for executing |
| CN110263748A (en) * | 2019-06-26 | 2019-09-20 | 北京百度网讯科技有限公司 | Method and apparatus for sending information |
| CN110458082A (en) * | 2019-08-05 | 2019-11-15 | 城云科技（中国）有限公司 | A kind of city management case classification recognition methods |
| CN110458082B (en) * | 2019-08-05 | 2022-05-03 | 城云科技（中国）有限公司 | Urban management case classification and identification method |
| CN112560562B (en) * | 2019-09-26 | 2024-02-20 | 杭州海康威视***技术有限公司 | Method, apparatus and storage medium for identifying violations |
| CN112560562A (en) * | 2019-09-26 | 2021-03-26 | 杭州海康威视***技术有限公司 | Method, apparatus and storage medium for identifying violations |
| CN110719441A (en) * | 2019-09-30 | 2020-01-21 | 傅程宏 | System and method for bank personnel behavior compliance early warning management |
| CN110728815A (en) * | 2019-10-25 | 2020-01-24 | 深圳市商汤科技有限公司 | Early warning method and device based on video analysis, electronic equipment and storage medium |
| CN110807393A (en) * | 2019-10-25 | 2020-02-18 | 深圳市商汤科技有限公司 | Early warning method and device based on video analysis, electronic equipment and storage medium |
| CN110968604A (en) * | 2019-12-05 | 2020-04-07 | 长春嘉诚信息技术股份有限公司 | Method for automatically retrieving illegal operation of internet operation enterprise |
| WO2021164644A1 (en) * | 2020-02-18 | 2021-08-26 | 深圳市商汤科技有限公司 | Violation event detection method and apparatus, electronic device, and storage medium |
| CN111563726A (en) * | 2020-04-30 | 2020-08-21 | 平安国际智慧城市科技股份有限公司 | Enterprise rectification supervision method, device, equipment and computer readable storage medium |
| CN111553355B (en) * | 2020-05-18 | 2023-07-28 | 城云科技（中国）有限公司 | Monitoring video-based method for detecting and notifying store outgoing business and managing store owner |
| CN111553355A (en) * | 2020-05-18 | 2020-08-18 | 城云科技（中国）有限公司 | Method for detecting out-of-store operation and notifying management shop owner based on monitoring video |
| CN112153329A (en) * | 2020-08-17 | 2020-12-29 | 浙江大华技术股份有限公司 | Configuration method, system, computer equipment and storage medium for event monitoring |
| CN112037520A (en) * | 2020-11-05 | 2020-12-04 | 杭州科技职业技术学院 | Road monitoring method and system and electronic equipment |
| CN112511610A (en) * | 2020-11-19 | 2021-03-16 | 上海营邑城市规划设计股份有限公司 | Vehicle-mounted patrol intelligent method and system based on urban fine management conditions |
| CN112580470A (en) * | 2020-12-11 | 2021-03-30 | 北京软通智慧城市科技有限公司 | City visual perception method and device, electronic equipment and storage medium |
| CN112749681A (en) * | 2021-01-25 | 2021-05-04 | 长威信息科技发展股份有限公司 | Violation detection method based on edge equipment and deep learning |
| CN113139434A (en) * | 2021-03-29 | 2021-07-20 | 北京旷视科技有限公司 | City management event processing method and device, electronic equipment and readable storage medium |
| CN113420563A (en) * | 2021-06-18 | 2021-09-21 | 北京易华录信息技术股份有限公司 | City civilization monitoring method, system and device based on artificial intelligence |
| CN113852788A (en) * | 2021-09-03 | 2021-12-28 | 泰华智慧产业集团股份有限公司 | City management system based on video intelligent analysis |
| CN114627420A (en) * | 2022-03-23 | 2022-06-14 | 北京数字政通科技股份有限公司 | City management violation event information acquisition method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109063612A (en) | City intelligent red line management method and machine readable storage medium | |
| US20200250435A1 (en) | Activity recognition method and system | |
| CN110458154A (en) | Face identification method, device and computer readable storage medium | |
| Tariq et al. | Gan is a friend or foe? a framework to detect various fake face images | |
| CN108197565A (en) | Target based on recognition of face seeks track method and system | |
| CN108564052A (en) | Multi-cam dynamic human face recognition system based on MTCNN and method | |
| US20120093362A1 (en) | Device and method for detecting specific object in sequence of images and video camera device | |
| KR101964683B1 (en) | Apparatus for Processing Image Smartly and Driving Method Thereof | |
| CN206272770U (en) | A kind of vehicle and face bayonet system | |
| CN109803112A (en) | Video analysis management method based on big data, apparatus and system, storage medium | |
| CN104581140B (en) | A kind of video quality evaluation method of video conferencing | |
| CN210515326U (en) | Scenic spot ticket inspection system based on face AI recognition | |
| CN111918039A (en) | Artificial intelligence high risk operation management and control system based on 5G network | |
| CN109815936A (en) | A kind of target object analysis method and device, computer equipment and storage medium | |
| WO2021114985A1 (en) | Companionship object identification method and apparatus, server and system | |
| CN108288025A (en) | A kind of car video monitoring method, device and equipment | |
| CN109872541A (en) | A kind of information of vehicles analysis method and device | |
| CN115002414A (en) | Monitoring method, monitoring device, server and computer readable storage medium | |
| CN111192459A (en) | Video monitoring deployment and control method and device | |
| KR101547255B1 (en) | Object-based Searching Method for Intelligent Surveillance System | |
| US11532158B2 (en) | Methods and systems for customized image and video analysis | |
| WO2021093625A1 (en) | Intelligent analysis algorithm selection method, apparatus and system, and electronic device | |
| CN116778673A (en) | Water area safety monitoring method, system, terminal and storage medium | |
| CN116208633A (en) | Artificial intelligence service platform system, method, equipment and medium | |
| CN111400415A (en) | Management method and related device for stability-related personnel |
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: 20181221 |