CN107515920A - A kind of image big data analysis method based on dynamic aerial survey - Google Patents
A kind of image big data analysis method based on dynamic aerial survey Download PDFInfo
- Publication number
- CN107515920A CN107515920A CN201710722496.7A CN201710722496A CN107515920A CN 107515920 A CN107515920 A CN 107515920A CN 201710722496 A CN201710722496 A CN 201710722496A CN 107515920 A CN107515920 A CN 107515920A
- Authority
- CN
- China
- Prior art keywords
- image
- data
- aerial survey
- processing
- character
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/54—Browsing; Visualisation therefor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of image big data analysis method based on dynamic aerial survey, comprise the following steps method, step 1：Data acquisition is carried out using image aerial survey transmission equipment；Step 2：The data collected are imported in data storage identification processing system；Step 3：Data are cleaned, converted, extracted and calculated by using data storage identification processing system；The data cleansing includes the double typing contrasts of data, data merge, searches repetition values, searches missing values and searches exceptional value；Step 4：Statistical analysis is carried out to the data after step 3 processing using database and depth is excavated；Step 5：Presented using database and the data after step 4 processing are presented in the form of form, picture and word.The advantages of present invention reaches the purpose of Data Integration, quicklook, and to have that processing speed is fast, analysis efficiency is high etc. notable.
Description
Technical field
The present invention relates to technical field of data processing, specially a kind of image big data analysis side based on dynamic aerial survey
Method.
Background technology
Data analysis refer to appropriate statistical analysis technique to collect come mass data analyze, extract useful letter
Cease and form conclusion and data are subject to the process of research and summary in detail.This process is also the branch of quality management system
Hold process.In practicality, data analysis can help people to judge, to take appropriate action.The mathematics base of data analysis
Plinth has just been established in early stage in 20th century, but until the appearance of computer just makes it possible practical operation, and so that data are divided
Analysis is promoted.Data analysis is the product that mathematical and computer sciences are combined.
Current data analysis problems faced is that the variations such as big data volume, multiple structural forms and real-time require,
These problems add data acquisition and integrate difficulty, and the architecture design of traditional storage system based on block and file can not expire
The needs of the analysis of image data of sufficient dynamic aerial survey.
This problem just needs to be improved traditional method for more than, then how to invent a kind of based on dynamic
The image big data analysis method of aerial survey, this, which turns into us, needs to solve the problems, such as.
The content of the invention
It is an object of the invention to provide a kind of image big data analysis method based on dynamic aerial survey, solves background skill
The problem of proposed in art.
To solve the above problems, the present invention provides following technical scheme：Comprise the following steps method,
Step 1：Data acquisition is carried out using image aerial survey transmission equipment；
Step 2：The data collected are imported in data storage identification processing system；
Step 3：Data are cleaned, converted, extracted and calculated by using data storage identification processing system；The number
Include the double typing contrasts of data according to cleaning, data merge, search repetition values, search missing values and search exceptional value；
Step 4：Statistical analysis is carried out to the data after step 3 processing using database and depth is excavated；
Step 5：Presented using database and the data after step 4 processing are presented in the form of form, picture and word.
Preferably, in step 1, described image aerial survey transmission equipment includes high-definition image capturing unit, image preprocessing list
Member and identification transmission unit, the high-definition image capturing unit are used to gather image, described image pretreatment unit and the height
Clear image capturing unit connection, for image is carried out successively the processing of image closure, image unlatching processing, edge enhancing processing and
Picture smooth treatment is transmitted with output smoothing image, the identification transmission unit to image.
Preferably, in step 3, the data storage identification processing system, gathered according to described image aerial survey transmission equipment
Multi-frame video image, character recognition is carried out to each frame video image gathered, and each frame video image is identified
Character code；To encoding the statistics of step-by-step one by one corresponding to each frame in multiple image, the maximum frequency of occurrences of kinds of characters is obtained
And the frequency is recorded, wherein occur maximum character according to the acquisition orders step-by-step reserve frequency of multiple image in statistics, and
Upgraded in time when new peak frequency character occurs；After acquired image frame number reaches default judgement starting frame number,
The maximum for each character that step-by-step statistics identifies, whether it is all higher than being equal in advance after judging the maximum step-by-step weighting of every character
If the effective threshold of statistics, if it is judged that to be, the hand over word that step-by-step counts recorded is significant character, if
Judged result such as judges knot otherwise to continue to judge that counted step-by-step updates whether number is more than or equal to default significance bit threshold
Fruit is to be, the hand over word that now step-by-step counts recorded is significant character, if it is judged that new otherwise to resurvey
One two field picture, and redirect and perform each frame video image progress hand over word identification to being gathered, and each frame is regarded
The hand over word coding step that frequency image recognition goes out, completes the pretreatment of view data.
Preferably, in step 4, binary coding is carried out to the example for not obtaining binary code in database also, crosses and claims
Meaning obtains x low-dimensional real number value by s=(B ' B+2I) -1B ' x, then obtains it by hash function to each example x
Low-dimensional binary code, wherein B be definition base space, I is the unit matrix with dimension with B, for arbitrary two
Between body i and j, if there is communications records, then using number of image frames, image number, picture frequency data as parameter calculate i and
Contact weight coefficient between j, calculation formula are as follows：Wij=e φ (t)+θ (n)+γ (f), wherein Wij represent weighted value,
φ (t), θ (n), γ (f) are transmission duration t respectively, image frequency n, picture frequency f function, the concrete form of function according to
Specific application scenarios and user's is empirically determined, can select decaying exponential function, linear function etc., such as also need to consider
More factors, it is only necessary to increase new mapping function on exponential term, encoded to whole database, complete data
Advanced treating.
Preferably, in step 5, data entity is analyzed, obtains data entity analysis result, then by entity point
Analysis result application scenarios are analyzed, and obtain data application scene analysis result, to entity analysis result and scene analysis knot
Fruit carries out Statistical Comparison.
Compared with prior art, beneficial effects of the present invention are as follows：
The present invention is carried out by the collection of the view data to dynamic aerial survey, storage, processing and analysis using continuous multiple frames image
Identification, while analyze information using the correlation of each character bit, big data in the positional information of each two field picture, single frames and know to optimize
Not, data by analysis are then presented to user with modes such as word, picture and forms again, reach the mesh of Data Integration
, quicklook, the advantages of to have that processing speed is fast, analysis efficiency is high etc. notable.
Brief description of the drawings
Fig. 1 is a kind of image big data analysis method schematic flow sheet based on dynamic aerial survey of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
Referring to Fig. 1, this practicality invention provides a kind of technical scheme：Comprise the following steps method,
Step 1：Data acquisition is carried out using image aerial survey transmission equipment；
Step 2：The data collected are imported in data storage identification processing system；
Step 3：Data are cleaned, converted, extracted and calculated by using data storage identification processing system；The number
Include the double typing contrasts of data according to cleaning, data merge, search repetition values, search missing values and search exceptional value；
Step 4：Statistical analysis is carried out to the data after step 3 processing using database and depth is excavated；
Step 5：Presented using database and the data after step 4 processing are presented in the form of form, picture and word.
In step 1, described image aerial survey transmission equipment includes high-definition image capturing unit, image pre-processing unit and knowledge
Other transmission unit, the high-definition image capturing unit are used to gather image, described image pretreatment unit and the high-definition image
Capturing unit connects, and is put down for carrying out the processing of image closure, image unlatching processing, edge enhancing processing and image successively to image
Sliding processing is transmitted with output smoothing image, the identification transmission unit to image.
In step 3, the data storage identification processing system, multiframe is gathered according to described image aerial survey transmission equipment and regarded
Frequency image, character recognition is carried out to each frame video image gathered, and the character identified to each frame video image is compiled
Code；To encoding the statistics of step-by-step one by one corresponding to each frame in multiple image, obtain the maximum frequency of occurrences of kinds of characters and record
The frequency, wherein occur maximum character according to the acquisition orders step-by-step reserve frequency of multiple image in statistics, and new
Peak frequency character upgrades in time when occurring；After acquired image frame number reaches default judgement starting frame number, step-by-step system
The maximum of each character identified is counted, whether is all higher than being equal to default system after judging the maximum step-by-step weighting of every character
In respect of effect threshold, if it is judged that to be, the hand over word that step-by-step counts recorded is significant character, if it is determined that knot
Otherwise fruit is continues to judge that counted step-by-step updates whether number is more than or equal to default significance bit threshold, if judged result is yes
The hand over word that then now step-by-step counts recorded is significant character, if it is judged that otherwise to resurvey new frame figure
Picture, and redirect and perform each frame video image progress hand over word identification to being gathered, and to each frame video image
The hand over word coding step identified, completes the pretreatment of view data.
In step 4, binary coding is carried out to the example for not obtaining binary code in database also, crosses appellation to every
One example x, x low-dimensional real number value is obtained by s=(B ' B+2I) -1B ' x, its low-dimensional is then obtained by hash function
Binary code, wherein B are the base spaces of definition, and I is the unit matrix with dimension with B, for arbitrary two individual i and j
Between, if there is communications records, then using number of image frames, image number, picture frequency data between parameter calculating i and j
Contact weight coefficient, calculation formula is as follows：Wij=e φ (t)+θ (n)+γ (f), wherein Wij represent weighted value, φ
(t), θ (n), γ (f) are transmission duration t respectively, and image frequency n, picture frequency f function, the concrete form of function is according to tool
The application scenarios of body and user's is empirically determined, can select decaying exponential function, linear function etc., such as also need to consider more
More factor, it is only necessary to increase new mapping function on exponential term, encoded to whole database, complete data
Advanced treating.
In step 5, data entity is analyzed, obtains data entity analysis result, then should by entity analysis result
Analyzed with scene, and obtain data application scene analysis result, entity analysis result and scene analysis result are united
Meter contrast.
In summary, the present invention is by the collection of the view data to dynamic aerial survey, storage, processing and analysis, using even
Continuous multiple image is identified, while utilizes the correlation of each character bit, big data point in the positional information of each two field picture, single frames
Analysis information carrys out Statistical error, and data by analysis then are presented into user with modes such as word, picture and forms again, reached
The purpose of Data Integration, quicklook, the advantages of to have that processing speed is fast, analysis efficiency is high etc. notable.
Finally it should be noted that：The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention,
Although the present invention is described in detail with reference to the foregoing embodiments, for those skilled in the art, it still may be used
To be modified to the technical scheme described in foregoing embodiments, or equivalent substitution is carried out to which part technical characteristic.
Within the spirit and principles of the invention, any modification, equivalent substitution and improvements made etc., it should be included in the present invention's
Within protection domain.
Claims (5)
- A kind of 1. image big data analysis method based on dynamic aerial survey, it is characterised in that：Comprise the following steps method,Step 1：Data acquisition is carried out using image aerial survey transmission equipment；Step 2：The data collected are imported in data storage identification processing system；Step 3：Data are cleaned, converted, extracted and calculated by using data storage identification processing system；The number Include the double typing contrasts of data according to cleaning, data merge, search repetition values, search missing values and search exceptional value；Step 4：Statistical analysis is carried out to the data after step 3 processing using database and depth is excavated；Step 5：Presented using database and the data after step 4 processing are presented in the form of form, picture and word.
- A kind of 2. image big data analysis method based on dynamic aerial survey according to claim 1, it is characterised in that：Step In one, described image aerial survey transmission equipment includes high-definition image capturing unit, image pre-processing unit and identification transmission unit, institute High-definition image capturing unit to be stated to be used to gather image, described image pretreatment unit is connected with the high-definition image capturing unit, For carrying out the processing of image closure, image unlatching processing, edge enhancing processing and picture smooth treatment successively to image to export Smoothed image, the identification transmission unit are transmitted to image.
- A kind of 3. image big data analysis method based on dynamic aerial survey according to claim 1, it is characterised in that：Step In three, the data storage identification processing system, multi-frame video image is gathered according to described image aerial survey transmission equipment, to being adopted Each frame video image of collection carries out character recognition, and to character code that each frame video image identifies；To multiple image In coding corresponding to each frame step-by-step counts one by one, obtain the maximum frequency of occurrences of kinds of characters and record the frequency, wherein Occur maximum character during statistics according to the acquisition orders step-by-step reserve frequency of multiple image, and go out in new peak frequency character Upgrade in time now；After acquired image frame number reaches default judgement starting frame number, step-by-step counts each word identified The maximum of symbol, whether it is all higher than being equal to the default effective threshold of statistics after judging the maximum step-by-step weighting of every character, such as Fruit judged result is to be, the hand over word that step-by-step counts recorded is significant character, if it is judged that otherwise to continue to sentence Whether disconnected counted step-by-step renewal number is more than or equal to default significance bit threshold, the now step-by-step statistics if judged result is to be The hand over word recorded is significant character, if it is judged that otherwise to resurvey a new two field picture, and redirect execution It is described to carry out hand over word identification to each frame video image for being gathered, and to hand-over word that each frame video image identifies Coding step is accorded with, completes the pretreatment of view data.
- A kind of 4. image big data analysis method based on dynamic aerial survey according to claim 1, it is characterised in that：Step In four, binary coding is carried out to the example for not obtaining binary code in database also, appellation is crossed to each example x, leads to Cross s=(B ' B+2I) -1B ' x and obtain x low-dimensional real number value, its low-dimensional binary code is then obtained by hash function, its Middle B is the base space of definition, and I is the unit matrix with dimension with B, between arbitrary two individual i and j, if there is Communications records, then using the contact weight system of number of image frames, image number, picture frequency data between parameter calculating i and j Number, calculation formula are as follows：Wij=e φ (t)+θ (n)+γ (f), wherein Wij represent weighted value, φ (t), θ (n), γ (f) Transmission duration t respectively, image frequency n, picture frequency f function, the concrete form of function according to specific application scenarios with And user's is empirically determined, decaying exponential function, linear function etc. can be selected, such as also needs to consider more factors, is only needed To increase new mapping function on exponential term, whole database is encoded, complete the advanced treating of data.
- A kind of 5. image big data analysis method based on dynamic aerial survey according to claim 1, it is characterised in that：Step In five, data entity is analyzed, obtains data entity analysis result, is then divided entity analysis result application scenarios Analysis, and data application scene analysis result is obtained, Statistical Comparison is carried out to entity analysis result and scene analysis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710722496.7A CN107515920A (en) | 2017-08-22 | 2017-08-22 | A kind of image big data analysis method based on dynamic aerial survey |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710722496.7A CN107515920A (en) | 2017-08-22 | 2017-08-22 | A kind of image big data analysis method based on dynamic aerial survey |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107515920A true CN107515920A (en) | 2017-12-26 |
Family
ID=60723262
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710722496.7A Pending CN107515920A (en) | 2017-08-22 | 2017-08-22 | A kind of image big data analysis method based on dynamic aerial survey |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107515920A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846034A (en) * | 2018-05-28 | 2018-11-20 | 贵州中科恒运软件科技有限公司 | A method of about user behavior analysis |
| CN110544222A (en) * | 2019-09-05 | 2019-12-06 | 重庆瑞信展览有限公司 | Visual transmission image sharpening processing method and system |
| CN111199232A (en) * | 2019-12-20 | 2020-05-26 | 中译语通文娱科技(青岛)有限公司 | Object recognition technology based on optical induction |
| CN113596356A (en) * | 2021-06-21 | 2021-11-02 | 中国科学院新疆生态与地理研究所 | Grassland mouse damage field monitoring method |
| CN114356249A (en) * | 2022-01-10 | 2022-04-15 | 苏州久道信息科技有限公司 | Processing system and processing method for automatically detecting and optimizing image quality |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003006612A (en) * | 2001-06-20 | 2003-01-10 | Ntt Data Corp | Device and method for predicting harvest |
| WO2013054130A1 (en) * | 2011-10-12 | 2013-04-18 | Hidef Aerial Surveying Limited | Aerial survey video processing |
| CN103259998A (en) * | 2013-05-16 | 2013-08-21 | 中国科学院光电技术研究所 | System and method for recording aerial survey image data |
| CN106339439A (en) * | 2016-08-22 | 2017-01-18 | 成都众易通科技有限公司 | Big data analysis method |
-
2017
- 2017-08-22 CN CN201710722496.7A patent/CN107515920A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003006612A (en) * | 2001-06-20 | 2003-01-10 | Ntt Data Corp | Device and method for predicting harvest |
| WO2013054130A1 (en) * | 2011-10-12 | 2013-04-18 | Hidef Aerial Surveying Limited | Aerial survey video processing |
| CN103259998A (en) * | 2013-05-16 | 2013-08-21 | 中国科学院光电技术研究所 | System and method for recording aerial survey image data |
| CN106339439A (en) * | 2016-08-22 | 2017-01-18 | 成都众易通科技有限公司 | Big data analysis method |
Non-Patent Citations (2)
| Title |
|---|
| 成刚等: "基于小波多层阈值平滑处理的航测图像降噪", 《计算机仿真》 * |
| 陈俐冰: "电力客服中心用户行为分析研究与实现", 《计算机技术与发展》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846034A (en) * | 2018-05-28 | 2018-11-20 | 贵州中科恒运软件科技有限公司 | A method of about user behavior analysis |
| CN110544222A (en) * | 2019-09-05 | 2019-12-06 | 重庆瑞信展览有限公司 | Visual transmission image sharpening processing method and system |
| CN110544222B (en) * | 2019-09-05 | 2023-01-03 | 重庆瑞信展览有限公司 | Visual transmission image sharpening processing method and system |
| CN111199232A (en) * | 2019-12-20 | 2020-05-26 | 中译语通文娱科技(青岛)有限公司 | Object recognition technology based on optical induction |
| CN113596356A (en) * | 2021-06-21 | 2021-11-02 | 中国科学院新疆生态与地理研究所 | Grassland mouse damage field monitoring method |
| CN114356249A (en) * | 2022-01-10 | 2022-04-15 | 苏州久道信息科技有限公司 | Processing system and processing method for automatically detecting and optimizing image quality |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107515920A (en) | A kind of image big data analysis method based on dynamic aerial survey | |
| CN100550038C (en) | Image content recognizing method and recognition system | |
| CN110379506B (en) | Arrhythmia detection method using binarization neural network for electrocardiogram data | |
| CN103559196B (en) | Video retrieval method based on multi-core canonical correlation analysis | |
| CN106372638A (en) | Method and system for identifying brand and model of electronic equipment | |
| CN104156729B (en) | A kind of classroom demographic method | |
| CN112000771B (en) | Judicial public service-oriented sentence pair intelligent semantic matching method and device | |
| CN101308543B (en) | Segmenting and recognizing method of image frame of data stream and apparatus thereof | |
| CN107481293A (en) | Based on the difference image compressed sensing reconstructing methods and intelligent terminal for assuming weighting more | |
| CN114897742B (en) | Image restoration method with texture and structural features fused twice | |
| CN110688927A (en) | Video action detection method based on time sequence convolution modeling | |
| CN109903205B (en) | Intelligent public class recommendation method and management system | |
| CN113868651B (en) | Web log-based website anticreeper method | |
| CN102004795B (en) | Hand language searching method | |
| CN117119253B (en) | High-quality video frame extraction method for target object | |
| CN109933741B (en) | Method, device and storage medium for extracting user network behavior characteristics | |
| CN104731784B (en) | Visual search method, system and mobile terminal | |
| CN113726824B (en) | Fraud website searching method and system based on image characteristics | |
| CN106778789A (en) | A kind of fast target extracting method in multi-view image | |
| CN112215160B (en) | Video three-dimensional human body posture estimation algorithm utilizing long-short period information fusion | |
| CN115204250A (en) | Non-intrusive load monitoring method for intelligent electric energy meter | |
| CN111475674A (en) | Deep learning model training data set construction method and system for violent behavior detection | |
| Kuang | Single image super resolution reconstruction algorithm based on deep learning | |
| CN113627341B (en) | Video sample comparison method, system, equipment and storage medium | |
| CN110633385A (en) | Retrieval and compression method of medical image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171226 |