CN108012117A - A kind of city based on background modeling is set up a stall detection method - Google Patents
A kind of city based on background modeling is set up a stall detection method Download PDFInfo
- Publication number
- CN108012117A CN108012117A CN201711231709.2A CN201711231709A CN108012117A CN 108012117 A CN108012117 A CN 108012117A CN 201711231709 A CN201711231709 A CN 201711231709A CN 108012117 A CN108012117 A CN 108012117A
- Authority
- CN
- China
- Prior art keywords
- stall
- background
- city
- setting
- interchanger
- 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
-
- 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
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
Set up a stall detection method in a kind of city based on background modeling, carry out city by the detection device of setting up a stall of the city based on background modeling and set up a stall detection, city based on background modeling detection device of setting up a stall includes the cabinet that is installed in test point upright bar and is placed on the data processing server and interchanger of monitoring point, embedded board is installed in cabinet, megaphone and camera, data processing server and interchanger are placed on computer room or municipal administration's monitoring hall for making monitoring point, camera and embedded board are connected by cable with interchanger, interchanger is connected with data processing server;The present invention makes full use of the video camera that the projects such as day net engineering, safe city are laid in street, realize that headend equipment automatic identification is set up a stall and unit and send audio alarm voice, reach comprehensive, timely, accurately deploy to ensure effective monitoring and control of illegal activities to unit of setting up a stall, so as to greatly reduce the waste of the workload and human resources of city management personnel.
Description
Technical field
The present invention relates to city management monitoring technology field, more particularly to a kind of city based on background modeling to set up a stall
Detection method.
Background technology
With economic development, society is constantly progressive, and urbanization is increasingly deep, and urban population is being continuously increased, city rule
Mould also gradually moves towards maximization;The maximization in city favorably also has disadvantage, on the one hand, and the maximization in city contributes to economic development,
The reasonable redistribution of resource, on the other hand, the maximization in city cause urban size increase, avenue complication, city pipe
Reason personnel it is long-term deficiency so that city management become more difficult, wherein it is especially prominent the problem of be that city breaks rules and regulations to set up a stall
Management, unmanageable reason violating the regulations of setting up a stall mainly have following:1st, such stand mobility is big, without fixed ground
Point;2nd, such personnel of setting up a stall are mostly the self-employed personnel of long campaigns;3rd, currently for it is this kind of set up a stall deploy to ensure effective monitoring and control of illegal activities
Source is only limitted to city management personnel timing inspection or reports, can not accomplish to deploy to ensure effective monitoring and control of illegal activities in all directions, in time.
In recent years, country makes safe city, day net engineering energetically so that all brings supervision of the cities into city streets and lanes
In the range of, monitoring spreads all over each corner in city, but these supervision of the cities overwhelming majority is used for public security department, and only a small amount of monitoring is used
Set up a stall supervision in city, city management of setting up a stall mainly is carried out using the pattern of personnel's On-line monitor, this results in nothing
Method is timely, it is comprehensive deploy to ensure effective monitoring and control of illegal activities to the behavior of setting up a stall violating the regulations, and then cause waste of human resource and monitoring device to utilize
It is not in place.
The content of the invention
Technical problem solved by the invention is to provide a kind of city based on background modeling and sets up a stall detection method,
The shortcomings that to solve in above-mentioned background technology.
Technical problem solved by the invention is realized using following technical scheme:
A kind of city based on background modeling is set up a stall detection method, is set up a stall detection by the city based on background modeling
Device carries out city and sets up a stall detection, and detection device is set up a stall including being stood installed in test point in the city based on background modeling
Cabinet on bar and the data processing server and interchanger for being placed on monitoring point, are provided with embedded board in cabinet, amplify
Loudspeaker and camera, data processing server and interchanger are placed on computer room or municipal administration's monitoring hall for making monitoring point, take the photograph
Picture head and embedded board are connected by cable with interchanger, and interchanger is connected with data processing server, is comprised the following steps that:
(1)Data processing server obtains the video fluxion of camera collection first by Open-Source Tools FFMPEG from interchanger
According to;
(2)Data processing server is decoded to step using CUDA(1)The video stream data of middle acquisition is decoded, every to obtain
The data of frame picture, are then used to be modeled based on VIBE background modeling methods and are set with judging whether that someone sets up a stall on street
Point, and the first frame picture is made into background template;
(3)According to current scene, threshold value is set, then by step(2)In decoded mould is carried out per frame picture and background template
Plate matches, and when picture value is more than threshold value, then this frame picture is prospect, if picture value is less than threshold value, this frame picture is background, and
Afterwards by current background according to 1/16 probability updating into background template;
(4)It will be preserved containing the video frame set up a stall into data processing server MySQL database, and the area that will set up a stall
Domain size is reached in database, while the area size that will set up a stall is arranged to background subtraction, to determine whether moving target
Threshold value, when there is the threshold value of moving target, the background frames of background subtraction will be arranged to containing the video frame set up a stall;
(5)Administrative staff set time of fire alarming threshold value, in this section of time threshold, Mei Yifen to violating the regulations set up a stall according to demand
Clock extracts a frame and carries out subtraction with background frames, if the size of moving target is suitable with area size of above setting up a stall, that is, deletes and preserves
Set up a stall picture and area size of setting up a stall in the database, carry out next working cycles;If in this time threshold
Interior, it is suitable with area size of setting up a stall not occur moving target, then passes through embedded board audio port and export audio alarm and believe
Number, voice warning is carried out to current street by megaphone and is expelled, if other side ignores, can notify administrative staff nearby
Expelled.
In the present invention, it is to the method for judgement violating the regulations of setting up a stall:Judging there is pendulum by VIBE background modeling methods
Stand sets up an office after personnel's entrance, records pixel size and region that the unit set up a stall is accounted in video frame, and present frame is made
For the background of background subtraction, within the subsequent time, subtraction is done according to a frame per minute and background frames, if in the alarm of setting
Between in threshold value, in region of above setting up a stall, have and the moving target for size of setting up a stall left away, do not alarm, if not moving
Target is left away, that is, is alarmed.
Beneficial effect:The present invention makes full use of the video camera that the projects such as day net engineering, safe city are laid in street, realizes
Headend equipment automatic identification, which is set up a stall, unit and sends audio alarm voice, reach it is comprehensive, timely, accurately to setting up a stall
Unit is deployed to ensure effective monitoring and control of illegal activities, so as to greatly reduce the waste of the workload and human resources of city management personnel.
Brief description of the drawings
Fig. 1 is the structure diagram of presently preferred embodiments of the present invention.
Fig. 2 is the flow diagram of presently preferred embodiments of the present invention.
Embodiment
In order to make the technical means, the creative features, the aims and the efficiencies achieved by the present invention easy to understand, tie below
Conjunction is specifically illustrating, and the present invention is further explained.
Set up a stall detection method referring to a kind of city based on background modeling of Fig. 1~2, by based on background modeling
City detection device of setting up a stall carries out city and sets up a stall detection, and the city based on background modeling is set up a stall detection device bag
The cabinet in test point upright bar and the data processing server and interchanger that are placed on monitoring point are included, is provided with cabinet
Embedded board, megaphone and camera, data processing server and interchanger be placed on computer room for making monitoring point or
Municipal administration monitors hall, and camera and embedded board are connected by cable with interchanger, and interchanger connects with data processing server
Connect, embedded board is used to carry out algorithm calculating and then exports audio signal, and megaphone is expelled for carrying out voice warning, number
Access, collect evidence for the region set up a stall, specifically to MySQL database for municipal administration personnel according to processing server
Step is as follows:
(1)Data processing server obtains the video fluxion of camera collection first by Open-Source Tools FFMPEG from interchanger
According to;
(2)Data processing server is decoded to step using CUDA(1)The video stream data of middle acquisition is decoded, every to obtain
The data of frame picture, are then used to be modeled based on VIBE background modeling methods and are set with judging whether that someone sets up a stall on street
Point, and the first frame picture is made into background template;
(3)According to current scene, threshold value is set, then by step(2)In decoded mould is carried out per frame picture and background template
Plate matches, and when picture value is more than threshold value, then this frame picture is prospect, if picture value is less than threshold value, this frame picture is background, and
Afterwards by current background according to 1/16 probability updating into background template;
(4)It will be preserved containing the video frame set up a stall into data processing server MySQL database, and the area that will set up a stall
Domain size is reached in database, while the area size that will set up a stall is arranged to background subtraction, to determine whether moving target
Threshold value, when there is the threshold value of moving target, the background frames of background subtraction will be arranged to containing the video frame set up a stall;
(5)Administrative staff set time of fire alarming threshold value to violating the regulations set up a stall according to demand, such as 10 minutes or 30 minutes, at this
In section time threshold, each minute one frame of extraction carries out subtraction with background frames, if the size of moving target and region of above setting up a stall
Sizableness(Not necessarily it is equal to herein, can manually arranges error in the range of some), that is, delete and preserve in the database
Set up a stall picture and area size of setting up a stall, carry out next working cycles;If in time threshold, do not move
Target is suitable with area size of setting up a stall, then audio alarming signal is exported by embedded board audio port, by megaphone
Voice warning is carried out to current street to expel, if other side ignores, can notify that administrative staff nearby are expelled.
In the present embodiment, to the setting of time of fire alarming threshold value violating the regulations of setting up a stall:In view of some possibility of setting up a stall
It is simply interim to stop, then withdraw, for such case, administrative staff can set unit of setting up a stall stop how long into
Row alarm, the method used are judging to set up a stall to improve background subtraction to judge by VIBE background modeling methods
After personnel enter, pixel size and region that the unit set up a stall is accounted in video frame are recorded, and using present frame as background
The background of subtraction, within the subsequent time, does subtraction, if in the time of fire alarming threshold value of setting according to a frame per minute and background frames
It is interior, in region of above setting up a stall, have and the moving target for size of setting up a stall leave away and do not alarm, if without moving target from
Go, that is, alarm.
In the present embodiment, computing carrier of the embedded board as algorithm, it is contemplated that front audio exports and equipment takes
Electricity, takes embedded;Since audio output cannot be transmitted at a distance, therefore megaphone is placed using front end, pass through plate
Block the audio port carried and carry out closely audio output, the voice document of output can be the audio file of speech synthesis software synthesis
The audio file either recorded.
In the present embodiment, administrative staff can choose database according to demand, pass through MySQL numbers in data processing server
Data sharing and passback are realized according to storehouse remote inquiry method.
The basic principles, main features and the advantages of the invention have been shown and described above.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and modifications of the present invention are possible, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (3)
- The detection method 1. a kind of city based on background modeling is set up a stall, it is characterised in that pass through the city based on background modeling City's detection device of setting up a stall carries out city and sets up a stall detection, and the detection device of setting up a stall of the city based on background modeling includes Cabinet in test point upright bar and the data processing server and interchanger for being placed on monitoring point, are provided with cabinet embedding Enter formula board, megaphone and camera, data processing server and interchanger are placed on computer room or city for making monitoring point Pipe monitors hall, comprises the following steps that:(1)Data processing server obtains the video fluxion of camera collection first by Open-Source Tools FFMPEG from interchanger According to;(2)Data processing server is decoded to step using CUDA(1)The video stream data of middle acquisition is decoded, every to obtain The data of frame picture, are then used to be modeled based on VIBE background modeling methods and are set with judging whether that someone sets up a stall on street Point, and the first frame picture is made into background template;(3)According to current scene, threshold value is set, then by step(2)In decoded mould is carried out per frame picture and background template Plate matches, and when picture value is more than threshold value, then this frame picture is prospect, if picture value is less than threshold value, this frame picture is background, and Afterwards by current background according to 1/16 probability updating into background template;(4)It will be preserved containing the video frame set up a stall into data processing server MySQL database, and the area that will set up a stall Domain size is reached in database, while the area size that will set up a stall is arranged to background subtraction, to determine whether moving target Threshold value, when there is the threshold value of moving target, the background frames of background subtraction will be arranged to containing the video frame set up a stall;(5)Administrative staff set time of fire alarming threshold value, in this section of time threshold, Mei Yifen to violating the regulations set up a stall according to demand Clock extracts a frame and carries out subtraction with background frames, if the size of moving target is suitable with area size of above setting up a stall, that is, deletes and preserves Set up a stall picture and area size of setting up a stall in the database, carry out next working cycles;If in this time threshold Interior, it is suitable with area size of setting up a stall not occur moving target, then passes through embedded board audio port and export audio alarm and believe Number, voice warning is carried out to current street by megaphone and is expelled, if other side ignores, notify administrative staff nearby into Row expels.
- The detection method 2. a kind of city based on background modeling according to claim 1 is set up a stall, it is characterised in that take the photograph Picture head and embedded board are connected by cable with interchanger, and interchanger is connected with data processing server.
- The detection method 3. a kind of city based on background modeling according to claim 1 is set up a stall, it is characterised in that right The method of violating the regulations judgement of setting up a stall is:After the personnel that set up a stall by the judgement of VIBE background modeling methods enter, record The pixel size and region that unit of setting up a stall is accounted in video frame, and the background using present frame as background subtraction, subsequent In time, subtraction is done according to a frame per minute and background frames, if in the time of fire alarming threshold value of setting, in the area that above sets up a stall Domain, has and the moving target for size of setting up a stall is left away, and does not alarm, if no moving target is left away, that is, alarms.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711231709.2A CN108012117A (en) | 2017-11-30 | 2017-11-30 | A kind of city based on background modeling is set up a stall detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711231709.2A CN108012117A (en) | 2017-11-30 | 2017-11-30 | A kind of city based on background modeling is set up a stall detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108012117A true CN108012117A (en) | 2018-05-08 |
Family
ID=62054953
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711231709.2A Pending CN108012117A (en) | 2017-11-30 | 2017-11-30 | A kind of city based on background modeling is set up a stall detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108012117A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108765829A (en) * | 2018-07-06 | 2018-11-06 | 江西洪都航空工业集团有限责任公司 | A kind of detection of municipal stolen articles and alarm method based on intelligent video analysis |
CN108833967A (en) * | 2018-07-06 | 2018-11-16 | 江西洪都航空工业集团有限责任公司 | A kind of rapid section method based on video |
CN109345435A (en) * | 2018-12-07 | 2019-02-15 | 山东晴天环保科技有限公司 | Occupy-street-exploit managing device and method |
CN110166744A (en) * | 2019-04-28 | 2019-08-23 | 南京师范大学 | A kind of monitoring method violating the regulations of setting up a stall based on video geography fence |
CN110659546A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Illegal booth detection method and device |
CN112288613A (en) * | 2020-11-14 | 2021-01-29 | 浙江信电技术股份有限公司 | City management comprehensive law enforcement system |
CN112766055A (en) * | 2020-12-30 | 2021-05-07 | 浙江大华技术股份有限公司 | Stall management method, stall management device, stall management system, storage medium and electronic device |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102110367A (en) * | 2009-12-25 | 2011-06-29 | 刘天宇 | System for detecting illegal parking behaviors in real time and control method thereof |
CN103491351A (en) * | 2013-09-29 | 2014-01-01 | 东南大学 | Intelligent video monitoring method for illegal buildings |
CN104123709A (en) * | 2013-04-23 | 2014-10-29 | 中国科学院沈阳自动化研究所 | Key-frame extraction method based on dictionary selection |
US20150025655A1 (en) * | 2013-07-19 | 2015-01-22 | Superior Traffic Systems, LLC | Traffic management system |
CN104616501A (en) * | 2015-02-06 | 2015-05-13 | 河海大学常州校区 | Intelligent vision based vehicle law-violation parking detection system and method |
CN105447863A (en) * | 2015-11-19 | 2016-03-30 | 中国科学院自动化研究所 | Residue detection method based on improved VIBE |
CN105894817A (en) * | 2015-01-26 | 2016-08-24 | 杭州海康威视数字技术股份有限公司 | Evidence taking method of vehicle illegal parking and device thereof |
CN106408554A (en) * | 2015-07-31 | 2017-02-15 | 富士通株式会社 | Remnant detection apparatus, method and system |
CN106952476A (en) * | 2017-02-22 | 2017-07-14 | 成都华安视讯科技有限公司 | The camera chain for stopping dynamic monitoring is disobeyed available for vehicle |
-
2017
- 2017-11-30 CN CN201711231709.2A patent/CN108012117A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102110367A (en) * | 2009-12-25 | 2011-06-29 | 刘天宇 | System for detecting illegal parking behaviors in real time and control method thereof |
CN104123709A (en) * | 2013-04-23 | 2014-10-29 | 中国科学院沈阳自动化研究所 | Key-frame extraction method based on dictionary selection |
US20150025655A1 (en) * | 2013-07-19 | 2015-01-22 | Superior Traffic Systems, LLC | Traffic management system |
CN103491351A (en) * | 2013-09-29 | 2014-01-01 | 东南大学 | Intelligent video monitoring method for illegal buildings |
CN105894817A (en) * | 2015-01-26 | 2016-08-24 | 杭州海康威视数字技术股份有限公司 | Evidence taking method of vehicle illegal parking and device thereof |
CN104616501A (en) * | 2015-02-06 | 2015-05-13 | 河海大学常州校区 | Intelligent vision based vehicle law-violation parking detection system and method |
CN106408554A (en) * | 2015-07-31 | 2017-02-15 | 富士通株式会社 | Remnant detection apparatus, method and system |
CN105447863A (en) * | 2015-11-19 | 2016-03-30 | 中国科学院自动化研究所 | Residue detection method based on improved VIBE |
CN106952476A (en) * | 2017-02-22 | 2017-07-14 | 成都华安视讯科技有限公司 | The camera chain for stopping dynamic monitoring is disobeyed available for vehicle |
Non-Patent Citations (1)
Title |
---|
明悦: "《视听媒体感知与识别》", 31 August 2015 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110659546A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Illegal booth detection method and device |
CN110659546B (en) * | 2018-06-29 | 2022-11-01 | 杭州海康威视数字技术股份有限公司 | Illegal booth detection method and device |
CN108765829A (en) * | 2018-07-06 | 2018-11-06 | 江西洪都航空工业集团有限责任公司 | A kind of detection of municipal stolen articles and alarm method based on intelligent video analysis |
CN108833967A (en) * | 2018-07-06 | 2018-11-16 | 江西洪都航空工业集团有限责任公司 | A kind of rapid section method based on video |
CN109345435A (en) * | 2018-12-07 | 2019-02-15 | 山东晴天环保科技有限公司 | Occupy-street-exploit managing device and method |
CN110166744A (en) * | 2019-04-28 | 2019-08-23 | 南京师范大学 | A kind of monitoring method violating the regulations of setting up a stall based on video geography fence |
CN112288613A (en) * | 2020-11-14 | 2021-01-29 | 浙江信电技术股份有限公司 | City management comprehensive law enforcement system |
CN112766055A (en) * | 2020-12-30 | 2021-05-07 | 浙江大华技术股份有限公司 | Stall management method, stall management device, stall management system, storage medium and electronic device |
CN112766055B (en) * | 2020-12-30 | 2024-04-16 | 浙江大华技术股份有限公司 | Stall management method, device, system, storage medium and electronic device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108012117A (en) | A kind of city based on background modeling is set up a stall detection method | |
CN204129891U (en) | A kind of high ferro anti-intrusion system along the line | |
CN106340179B (en) | It is a kind of with the pedestrian crosswalk signal lamp network system realization of function of collecting evidence that makes a dash across the red light | |
CN103108159B (en) | Electric power intelligent video analyzing and monitoring system and method | |
CN108931970A (en) | A kind of industrial park wisdom environment supervisory systems based on cloud platform technology | |
CN105374210B (en) | Bayonet socket verification and measurement ratio acquisition methods based on floating car data | |
CN103325216A (en) | Water conservancy flood prevention monitoring early warning method and system based on video monitoring | |
CN205232359U (en) | Electronic equipment is estimated to flow of people | |
CN110288738B (en) | Intelligent comprehensive management and control system and method for bicycle lane | |
CN205721229U (en) | A kind of intelligent estate management system | |
CN102493845A (en) | Monitoring and prewarning system for urban rail transit operating tunnel based on GIS (Geographic Information System) | |
CN113284024A (en) | Intelligent emergency management system for intensive personnel place | |
CN103279481B (en) | Intelligent Skynet intelligence image investigation system | |
CN202120402U (en) | Mass video analysis based on cloud computing and rapid retrieval system | |
CN202003508U (en) | Bus lane illegal vehicle intruding detection equipment | |
CN107437314A (en) | Personnel's intrusion detection detecting system | |
CN105118291A (en) | Road traffic flow statistic comprehensive monitoring system | |
CN204904573U (en) | Road traffic statistics of flow integrated monitoring system | |
CN117612107A (en) | Method for detecting abnormal personnel in place | |
CN204046720U (en) | A kind of safety monitoring system | |
CN104616432A (en) | Intelligent identification and control method and system for people flow density | |
CN105632171A (en) | Traffic road condition video monitoring method | |
CN110223506A (en) | A kind of novel traffic intersection pedestrian's rale violation warnings system and method | |
CN202534010U (en) | Automatic ticket checking system for railway station | |
CN115223078A (en) | Power behavior recognition early warning method, system and equipment based on high-level monitoring |
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: 20180508 |