CN108881465A - A kind of intelligent monitor system based on big data - Google Patents
A kind of intelligent monitor system based on big data Download PDFInfo
- Publication number
- CN108881465A CN108881465A CN201810720683.6A CN201810720683A CN108881465A CN 108881465 A CN108881465 A CN 108881465A CN 201810720683 A CN201810720683 A CN 201810720683A CN 108881465 A CN108881465 A CN 108881465A
- Authority
- CN
- China
- Prior art keywords
- pixel
- super
- image
- big data
- distance
- 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
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of intelligent monitor systems based on big data, including big data Monitor And Control Subsystem, communication subsystem, data process subsystem and monitoring center, the big data Monitor And Control Subsystem is for obtaining monitoring image big data, the communication subsystem is used to the image big data of acquisition being sent to data process subsystem, the data process subsystem is for handling monitoring image big data, and according to treated, monitoring image is monitored in real time the monitoring center；The big data Monitor And Control Subsystem includes Image Acquisition terminal, GPS positioning module, and described image acquisition terminal is used to determine the position of Image Acquisition terminal for acquiring monitoring image big data, the GPS positioning module.Beneficial effects of the present invention are：A kind of intelligent monitor system based on big data is provided, by acquisition monitoring image and monitoring position, monitoring image big data is handled in real time, improves monitoring level.
Description
Technical field
The present invention relates to monitoring technology fields, and in particular to a kind of intelligent monitor system based on big data.
Background technique
With the development and progress of society, the place for needing to use monitoring is more and more, and existing monitoring system can not obtain
The location information of monitoring is taken, and a large amount of monitoring data can not be handled in real time.Intrinsic image procossing be typically all with
Basic unit of the pixel as processing, as soon as 128 × 128 image, the number of pixel have reached 16384, this
Numerical value be it is very large, this results in Algorithms T-cbmplexity very high.If by certain pixels for meeting specified conditions
A set is constituted, using these set as the basic unit of processing, then the time required for algorithm will greatly shorten.Super picture
Element generates the effective way for being to for pixel being gathered into set.Image superpixel is that will there is the pixel of like attribute to gather
A region is integrated, image is indicated instead of pixel, the process that image superpixel generates is according to gray scale, texture, face
The characteristic informations such as color and shape, adjacent pixel is combined, and constitutes a region, so that region interior pixels point
Feature is with uniformity, and the pixel for being included in the different region of any two has apparent otherness.
Summary of the invention
In view of the above-mentioned problems, the present invention is intended to provide a kind of intelligent monitor system based on big data.
The purpose of the present invention is realized using following technical scheme：
Provide a kind of intelligent monitor system based on big data, including big data Monitor And Control Subsystem, communication subsystem, number
According to processing subsystem and monitoring center, the big data Monitor And Control Subsystem is for obtaining monitoring image big data, the communicator
System is used to for the image big data of acquisition being sent to data process subsystem, and the data process subsystem is used for monitoring figure
As big data is handled, according to treated, monitoring image is monitored in real time the monitoring center；The big data monitoring
Subsystem includes Image Acquisition terminal, GPS positioning module, and described image acquisition terminal is for acquiring monitoring image big data, institute
GPS positioning module is stated for determining the position of Image Acquisition terminal.
Beneficial effects of the present invention are：A kind of intelligent monitor system based on big data is provided, by acquiring monitoring figure
Picture and monitoring position, handle monitoring image big data in real time, improve monitoring level.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is structural schematic diagram of the invention；
Appended drawing reference：
Big data Monitor And Control Subsystem 1, communication subsystem 2, data process subsystem 3, monitoring center 4.
Specific embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of intelligent monitor system based on big data of the present embodiment, including big data Monitor And Control Subsystem 1,
Communication subsystem 2, data process subsystem 3 and monitoring center 4, the big data Monitor And Control Subsystem 1 is for obtaining monitoring image
Big data, the communication subsystem 2 is used to the image big data of acquisition being sent to data process subsystem 3, at the data
Reason subsystem 3 is for handling monitoring image big data, and according to treated, monitoring image carries out in fact the monitoring center 4
When monitor；The big data Monitor And Control Subsystem 1 includes Image Acquisition terminal, GPS positioning module, and described image acquisition terminal is used for
Monitoring image big data is acquired, the GPS positioning module is used to determine the position of Image Acquisition terminal.
A kind of intelligent monitor system based on big data is present embodiments provided, acquisition monitoring image and monitoring position are passed through
It sets, monitoring image big data is handled in real time, improves monitoring level.
Preferably, the data process subsystem 3 includes super-pixel model building module, super-pixel generation module, evaluation
Module and picture recognition module, the super-pixel model building module generate mould for establishing super-pixel model, the super-pixel
Block be used for according to super-pixel model generate image superpixel, the evaluation module be used for described image super-pixel generate result into
Row evaluation, described image identification module are based on image superpixel and identify to image.
The super-pixel model building module is for establishing super-pixel model, specially：If input picture is S, it includes
Number of pixels be N, to image carry out over-segmentation, obtain super-pixel model, its super-pixel model be expressed as：
In formula, K indicates the number of super-pixel, SjAnd SiRespectively indicate j-th and i-th of super-pixel, a ideal super-pixel
Dividing mostly important property is exactly that it can be bonded image border well.
As a kind of image Segmentation Technology, difference is that image over-segmentation is by a width input picture point for image over-segmentation
It is cut into the lesser region not overlapped of more sizes, and each small region, referred to as super-pixel.This preferred embodiment
By establishing super-pixel model, reduces the order of magnitude of image expression, thereby reduces the complexity of subsequent image Processing Algorithm,
Possibility is provided for the real-time of image processing algorithm.
The super-pixel generation module is used to generate image superpixel according to super-pixel model, specially：
The first step, a given width input picture place K sub-pixel point, corresponding K super-pixel, for one first
Pixel x, calculate it to i-th of super-pixel seed point first distance, wherein i=1,2 ..., K, selected distance are the smallest
Super-pixel is marked whole pixels in input picture, has obtained defeated by pixel x labeled as the super-pixel is belonged to
Enter the initial super-pixel segmentation of image；
Second step after obtaining initial super-pixel segmentation, is updated the seed point of super-pixel, will be in initial super-pixel
The geometric center of all pixels point is as new seed point, for a pixel x, calculates its seed to i-th of super-pixel
The second distance of point, wherein pixel x is labeled as belonging to the super picture by i=1,2 ..., K, the smallest super-pixel of selected distance
Whole pixels in image are marked in element, have obtained the update super-pixel segmentation of image；
Third step repeats second step, until new and old seed point location variation is less than given threshold, by the super-pixel of generation
The super-pixel segmentation final as image.
The first distance is determined using following formula：
D (x, i)=B (x, i)+C (x, i)
In formula, D (x, i) indicates the distance of the seed point of pixel x and i-th of super-pixel, and B (x, i) indicates first distance
Impact factor, for indicating super-pixel interior pixels point consistency of colour, C (x, i) indicates second distance impact factor, is used for
Indicate the compactness of super-pixel interior pixels；
The second distance is determined using following formula：
D (x, i)=ρ1×B(x,i)+ρ2×C(x,i)
In formula, D (x, i) indicates the distance of the seed point of pixel x and i-th of super-pixel, ρ1、ρ2Indicate weight coefficient,
In,
The first distance impact factor is determined using following formula：
In formula, Lx、ax、bxPixel x is respectively indicated in L, a, b component of CIELAB color space, Li、ai、biTable respectively
Show that L, a, b component of the seed point in CIELAB color space of i-th of super-pixel, μ indicate all super-pixel seed point color sides
The average value of difference；
The second distance impact factor is determined using following formula：
In formula, px、qxRespectively indicate cross, ordinate value of the pixel x in X-Y coordinate, pi、qiIt respectively indicates i-th
Cross, ordinate value of the seed point of super-pixel in X-Y coordinate；
In super-pixel generating process, on the one hand, the pixel color inside super-pixel should be consistent, on the other hand, also
Need to consider the compactedness of super-pixel.This preferred embodiment considers one inside super-pixel in super-pixel generating process
Cause property and compactedness, internal consistency can preferably be kept again by, which obtaining, has the super-pixel of high intense, for picture material
The inhomogeneities of distribution, in the case where super-pixel number is certain, the present invention, which passes through, determines weight coefficient, so that flat site can
To be indicated using a small amount of larger-size super-pixel, and details region abundant is relatively more using quantity, size is lesser super
Pixel is indicated, so that image can obtain more accurate expression, keeps more image informations.
Preferably, the evaluation module is used to generate result to described image super-pixel and evaluate, specially：
Define the segmentation evaluation factor：
In formula, F indicates the segmentation evaluation factor, U1Indicate that the pixel of graphics standard partitioning boundary is fallen into around super-pixel boundary
Ratio in 1 pixel wide region, K indicate the number of super-pixel, miIndicate the area of i-th of super-pixel, liIt indicates i-th
The perimeter of super-pixel；The segmentation evaluation factor is bigger, indicates that the super-pixel generated more can accurately express image information；
This preferred embodiment segmentation evaluation factor comprehensively considered the super-pixel that generates to the boundary of image keep effect and
The compactedness of the super-pixel of generation is laid a good foundation for the later period using super-pixel as image procossing basic unit.
Through the above description of the embodiments, those skilled in the art can be understood that it should be appreciated that can
To realize the embodiments described herein with hardware, software, firmware, middleware, code or its any appropriate combination.For hardware
It realizes, processor can be realized in one or more the following units：Specific integrated circuit (ASIC), digital signal processor
(DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processing
Device, controller, microcontroller, microprocessor, other electronic units designed for realizing functions described herein or combinations thereof.
For software implementations, some or all of embodiment process can instruct relevant hardware to complete by computer program.
When realization, above procedure can be stored in computer-readable medium or as the one or more on computer-readable medium
Instruction or code are transmitted.Computer-readable medium includes computer storage media and communication media, wherein communication media packet
It includes convenient for from a place to any medium of another place transmission computer program.Storage medium can be computer can
Any usable medium of access.Computer-readable medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other
Optical disc storage, magnetic disk storage medium or other magnetic storage apparatus or can be used in carry or store have instruction or data
The desired program code of structure type simultaneously can be by any other medium of computer access.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (7)
1. a kind of intelligent monitor system based on big data, which is characterized in that including big data Monitor And Control Subsystem, communication subsystem
System, data process subsystem and monitoring center, the big data Monitor And Control Subsystem are described logical for obtaining monitoring image big data
Letter subsystem is used to for the image big data of acquisition being sent to data process subsystem, and the data process subsystem is used for prison
Control image big data is handled, and according to treated, monitoring image is monitored in real time the monitoring center；The big data
Monitor And Control Subsystem includes Image Acquisition terminal, GPS positioning module, and described image acquisition terminal is for acquiring the big number of monitoring image
According to the GPS positioning module is used to determine the position of Image Acquisition terminal.
2. the intelligent monitor system according to claim 1 based on big data, which is characterized in that the data processing subsystem
System includes super-pixel model building module, super-pixel generation module, evaluation module and picture recognition module, the super-pixel model
It establishes module and is used to generate the super picture of image according to super-pixel model for establishing super-pixel model, the super-pixel generation module
Element, the evaluation module are used to generate result to described image super-pixel and evaluate, and described image identification module is based on image
Super-pixel identifies image.
3. the intelligent monitor system according to claim 2 based on big data, which is characterized in that the super-pixel model is built
Formwork erection block is for establishing super-pixel model, specially：If input picture be S, it includes number of pixels be N, to image carry out
Over-segmentation obtains super-pixel model, its super-pixel model is expressed as：
In formula, K indicates the number of super-pixel, SjAnd SiRespectively indicate j-th and i-th of super-pixel, a ideal super-pixel segmentation
Mostly important property is exactly that it can be bonded image border well.
4. the intelligent monitor system according to claim 3 based on big data, which is characterized in that the super-pixel generates mould
Block is used to generate image superpixel according to super-pixel model, specially：
The first step, a given width input picture place K sub-pixel point, corresponding K super-pixel, for a pixel first
Point x, calculate it to i-th of super-pixel seed point first distance, wherein i=1,2 ..., K, the smallest super picture of selected distance
Element is marked whole pixels in input picture, has obtained input figure by pixel x labeled as the super-pixel is belonged to
The initial super-pixel segmentation of picture；
Second step after obtaining initial super-pixel segmentation, is updated the seed point of super-pixel, will be all in initial super-pixel
The geometric center of pixel is as new seed point, for a pixel x, calculates its seed point to i-th of super-pixel
Second distance, wherein pixel x is labeled as belonging to the super-pixel by i=1,2 ..., K, the smallest super-pixel of selected distance, right
Whole pixels in image are marked, and have obtained the update super-pixel segmentation of image；
Third step repeats second step, until new and old seed point location variation is less than given threshold, using the super-pixel of generation as
The final super-pixel segmentation of image.
5. the intelligent monitor system according to claim 4 based on big data, which is characterized in that the first distance uses
Following formula determines：
D (x, i)=B (x, i)+C (x, i)
In formula, D (x, i) indicates the distance of the seed point of pixel x and i-th of super-pixel, and B (x, i) indicates that first distance influences
The factor, for indicating super-pixel interior pixels point consistency of colour, C (x, i) indicates second distance impact factor, for indicating
The compactness of super-pixel interior pixels；
The second distance is determined using following formula：
D (x, i)=ρ1×B(x,i)+ρ2×C(x,i)
In formula, D (x, i) indicates the distance of the seed point of pixel x and i-th of super-pixel, ρ1、ρ2Indicate weight coefficient, wherein
6. the intelligent monitor system according to claim 5 based on big data, which is characterized in that the first distance influences
The factor is determined using following formula：
In formula, Lx、ax、bxPixel x is respectively indicated in L, a, b component of CIELAB color space, Li、ai、biRespectively indicate i-th
For the seed point of a super-pixel in L, a, b component of CIELAB color space, μ indicates the flat of all super-pixel seed point color variances
Mean value；
The second distance impact factor is determined using following formula：
In formula, px、qxRespectively indicate cross, ordinate value of the pixel x in X-Y coordinate, pi、qiIt respectively indicates and i-th surpasses picture
Cross, ordinate value of the seed point of element in X-Y coordinate.
7. the intelligent monitor system according to claim 6 based on big data, which is characterized in that the evaluation module is used for
It generates result to described image super-pixel to evaluate, specially：
Define the segmentation evaluation factor：
In formula, F indicates the segmentation evaluation factor, U1Indicate that the pixel of graphics standard partitioning boundary falls into 1 picture around super-pixel boundary
Ratio in plain width regions, K indicate the number of super-pixel, miIndicate the area of i-th of super-pixel, liIndicate i-th of super-pixel
Perimeter；The segmentation evaluation factor is bigger, indicates that the super-pixel generated more can accurately express image information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810720683.6A CN108881465A (en) | 2018-07-03 | 2018-07-03 | A kind of intelligent monitor system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810720683.6A CN108881465A (en) | 2018-07-03 | 2018-07-03 | A kind of intelligent monitor system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108881465A true CN108881465A (en) | 2018-11-23 |
Family
ID=64298758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810720683.6A Pending CN108881465A (en) | 2018-07-03 | 2018-07-03 | A kind of intelligent monitor system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108881465A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105120237A (en) * | 2015-09-17 | 2015-12-02 | 成都时代星光科技有限公司 | Wireless image monitoring method based on 4G technology |
| KR20160035274A (en) * | 2014-09-23 | 2016-03-31 | 주식회사 이니컴퍼니 | A system for detecting car being violated parking and stopping of based on big date using CCTV camera and black box vehicle |
| CN106101641A (en) * | 2016-07-18 | 2016-11-09 | 中国科学院地理科学与资源研究所 | Video frequency monitoring system and monitoring method thereof |
| CN106297198A (en) * | 2016-10-13 | 2017-01-04 | 成都亚联科科技有限公司 | A kind of high-speed railway Geological Disaster Warning System based on big data |
| CN106771856A (en) * | 2016-11-30 | 2017-05-31 | 国网河南省电力公司滑县供电公司 | Lightning strike point on electric power transmission line based on unmanned air vehicle technique determines method |
| CN107016691A (en) * | 2017-04-14 | 2017-08-04 | 南京信息工程大学 | Moving target detecting method based on super-pixel feature |
| CN108230340A (en) * | 2018-02-05 | 2018-06-29 | 南京邮电大学 | A kind of SLIC super-pixel extraction Weighting and super-pixel extracting method based on MMTD |
-
2018
- 2018-07-03 CN CN201810720683.6A patent/CN108881465A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160035274A (en) * | 2014-09-23 | 2016-03-31 | 주식회사 이니컴퍼니 | A system for detecting car being violated parking and stopping of based on big date using CCTV camera and black box vehicle |
| CN105120237A (en) * | 2015-09-17 | 2015-12-02 | 成都时代星光科技有限公司 | Wireless image monitoring method based on 4G technology |
| CN106101641A (en) * | 2016-07-18 | 2016-11-09 | 中国科学院地理科学与资源研究所 | Video frequency monitoring system and monitoring method thereof |
| CN106297198A (en) * | 2016-10-13 | 2017-01-04 | 成都亚联科科技有限公司 | A kind of high-speed railway Geological Disaster Warning System based on big data |
| CN106771856A (en) * | 2016-11-30 | 2017-05-31 | 国网河南省电力公司滑县供电公司 | Lightning strike point on electric power transmission line based on unmanned air vehicle technique determines method |
| CN107016691A (en) * | 2017-04-14 | 2017-08-04 | 南京信息工程大学 | Moving target detecting method based on super-pixel feature |
| CN108230340A (en) * | 2018-02-05 | 2018-06-29 | 南京邮电大学 | A kind of SLIC super-pixel extraction Weighting and super-pixel extracting method based on MMTD |
Non-Patent Citations (3)
| Title |
|---|
| 张育雄: ""基于几何约束和熵率的超像素分割"", 《中国优秀硕士论文全文数据库》 * |
| 王亚杰: ""一种基于熵率超像素分割的多聚焦图像融合"", 《光电工程》 * |
| 董含: ""基于超像素的图像分割方法研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112734641A (en) | Training method and device of target detection model, computer equipment and medium | |
| US11532123B2 (en) | Method for visualizing large-scale point cloud based on normal | |
| CN111798556B (en) | Image rendering method, device, equipment and storage medium | |
| CN110555085B (en) | Three-dimensional model loading method and device | |
| CN106570538B (en) | Character image processing method and device | |
| CN116756836B (en) | Tunnel super-undermining volume calculation method, electronic equipment and storage medium | |
| CN114511661A (en) | Image rendering method and device, electronic equipment and storage medium | |
| CN106910180B (en) | A kind of image quality measure method and device | |
| CN114241358A (en) | Equipment state display method, device and equipment based on digital twin transformer substation | |
| WO2014017003A1 (en) | Update area detection device | |
| CN112597983B (en) | Method for identifying target object in remote sensing image and storage medium and system thereof | |
| CN108806255A (en) | A kind of cloud traffic control system | |
| CN116051777B (en) | Super high-rise building extraction method, apparatus and readable storage medium | |
| Zhao et al. | A new k nearest neighbours algorithm using cell grids for 3d scattered point cloud | |
| CN108881465A (en) | A kind of intelligent monitor system based on big data | |
| CN111028349A (en) | Hierarchical construction method suitable for rapid visualization of massive three-dimensional live-action data | |
| CN115239746B (en) | Object-oriented remote sensing image segmentation method, device, equipment and medium | |
| CN108921912A (en) | A kind of image superpixel generation system | |
| CN108898113A (en) | A kind of big data logistics platform | |
| CN114494623A (en) | LOD-based terrain rendering method and device | |
| CN108805062A (en) | A kind of intelligent monitor system | |
| CN113920269A (en) | Project progress obtaining method and device, electronic equipment and medium | |
| CN108921094A (en) | A kind of alert management system based on big data | |
| CN108712635A (en) | A kind of intelligent domestic system | |
| CN109000670A (en) | A kind of Vehicular navigation system |
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 |
Application publication date: 20181123 |
|
| RJ01 | Rejection of invention patent application after publication |