CN105069398A - Grassland coverage-degree extraction method based on mobile phone camera - Google Patents
Grassland coverage-degree extraction method based on mobile phone camera Download PDFInfo
- Publication number
- CN105069398A CN105069398A CN201510406382.2A CN201510406382A CN105069398A CN 105069398 A CN105069398 A CN 105069398A CN 201510406382 A CN201510406382 A CN 201510406382A CN 105069398 A CN105069398 A CN 105069398A
- Authority
- CN
- China
- Prior art keywords
- vegetation
- pixel
- mobile phone
- coverage
- ndi
- 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
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Abstract
The invention discloses a grassland coverage-degree extraction method based on a mobile phone camera. Data from a prairie grassland picture photographed by the mobile phone camera is used; the photographed picture is uploaded to a server, and a photographing place, photographing longitude, photographing latitude, photographing time and a photographing person are uploaded to a server side database at the same time; a vegetation coverage degree in the picture is extracted through adoption of a DNI method; and comparative analyses of a calculation result obtained through the DNI method and a classification result obtained through a supervision classification method are performed. The grassland coverage-degree extraction method is advantageous in that a result obtained through a mobile phone photographing extracting method is accurate, the grassland coverage-degree extraction method can rely on a mode that herdsmen take pictures using herdsmen's mobile phones and upload the pictures, and a lot of manpower and material resources can be saved.
Description
Technical field
The invention belongs to technical field of image processing, relate to the Grass cover degree extracting method based on mobile phone camera.
Background technology
Vegetation coverage is the index of reflection vegetation basic condition, is the important parameter that agronomy, ecology etc. are concerned about.Obtain earth's surface digital photograph onestep extraction vegetation coverage of going forward side by side and become a kind of means of vegetation coverage being carried out to ground survey of most potentiality.Chi Hongkang etc.
[1]use the vegetation of Photoshop image processing software manual extraction digital photograph and non-vegetation pixel, thus calculate vegetation cover degree.Zhou and Robson
[2]utilize digital photograph, by being extracted Grass cover degree in conjunction with the not supervised classification of spectrum and texture, result proves that the method utilizes k-means unsupervised classification and maximum likelihood method supervised classification than simple, and order of accuarcy is greatly improved.Song Xuefeng etc.
[3]meadow sample prescription photo is obtained with digital camera, from sample prescription picture data, extract 6 indexs, set up logic discrimination model, comparison film Green vegetation part makes deciphering, measure In Xilingol League In Inner Mongolia southwestern end meadow cover degree, totally judge that precision reaches 94.7%.Zhang Qingping etc.
[4]utilize color analysis software WinCAM, the color standard of selected consistent vegetation and non-vegetation, extract vegetation by color comparison and try to achieve vegetation coverage.Zhang Xuexia etc.
[5]by choosing the area-of-interest of vegetation and non-vegetation, analyzing respective spectral information rule, utilizing the method for linear spectral unmixing to obtain vegetation coverage.Zhang Chaobin etc.
[6]analyze the RGB color mode feature of a large amount of Desert Grassland photo on the spot, construct RGB color and differentiate that decision tree distinguishes the non-vegetation pixel of vegetation to calculate the coverage of vegetation.Ren Jie etc.
[7]use for reference the imitative normalized site attenuation method that Woebbecke etc. proposes, establish the model of the calculating batch digital photograph vegetation coverage based on NDI method, contrast supervised classification, the method robotization and fast more.Ban Aiqin etc.
[8]consider light condition when taking pictures, adopt vegetation decision flowchart method (VDF method), calculate vegetation coverage, and treatment effect and result of calculation and NDI method are contrasted.When result shows under gentle light, the accuracy of two kinds of method result of calculation is suitable, and VDF method is better than NDI method under intense light conditions.Hu Jianbo etc.
[9]propose the method calculating grassland vegetation coverage from digital photograph fast that one utilizes excess green vegetation index and semi-automatic threshold setting algorithm (semi-automatic threshold method).Semi-automatic threshold method manual intervention is few, and result of calculation is accurately objective, and applicability is strong; But to the unconspicuous plant of green characteristic (as celadon plant) poor effect.Zhang Yun's rosy clouds etc.
[10]in the multiscale morphology of grassland vegetation and the report of field survey, various grassland vegetation measuring method is contrasted, think that digital camera is the trend that following grassland vegetation cover degree measures development in conjunction with EO-1 hyperion and Multi-scale remotely sensed data.
Summary of the invention
The object of the present invention is to provide the Grass cover degree extracting method based on mobile phone camera, solve the artificial observational error of grassland Grass cover degree comparatively large, waste a large amount of human and material resources; And Grass cover degree extracting method complexity is carried out to existing photo, the problem that efficiency is lower.
Technical scheme of the present invention is carried out according to following steps:
Step 1: usage data derives from the grassland photo of mobile phone camera shooting;
Step 2: will take pictures and upload onto the server, upload onto the server the place of taking pictures, longitude, latitude, time, personal information of taking pictures client database simultaneously;
Step 3: in photo, vegetation coverage extracts;
1. DNI is calculated
NDI=(green-red)/(green+red)
Wherein: green represents the pixel value of green wave band; Red represents the pixel value of red wave band, DNI be on the occasion of, indicate the covering of vegetation, and increase with the increase of vegetation coverage;
2. NDI value does binary conversion treatment according to positive and negative
The value of NDI>0, is expressed as vegetation pixel, is 1 by this pixel value assignment; The value of NDI≤0, is expressed as non-vegetation pixel, and be 0 by this pixel value assignment, binaryzation formula is:
(B1GT0)*1+(B1LE0)*0
Wherein, B1 is NDI;
3. vegetation coverage is calculated
Statistics vegetation pixel occupies the ratio of total pixel, obtains the vegetation coverage of photo.The formula calculating vegetation coverage is as follows:
Wherein, N
1for vegetation pixel, N is the pixel of view picture photo;
Step 4: evaluation of result and checking;
The classification results comparative analysis that the result of calculation obtain DNI method and supervised classification method obtain.
Further, require when taking pictures in described step 1:
1. weather conditions are good, ensure that the photograph image photographed is clear;
When 2. taking pictures, mobile phone will be taken perpendicular to ground, to reduce the geometry deformation of its edges;
3. the place taken requires that gps signal is good, is convenient to obtain the accurate latitude and longitude information in spot for photography.
Beneficial effect of the present invention: realizing is taken pictures by mobile phone camera carries out the extraction of vegetation coverage.The mobile device due to mobile phone etc. with camera can be carried with, and the staff making to have mobile device can the Real-time Obtaining vegetation coverage of taking pictures.The present invention is mainly used in area, the prairie such as Inner Mongol, northeast, the existing mode by artificial observation, the manpower of at substantial, and observational error is larger.Use mobile phone photograph extracting mode result comparatively accurate, and herdsman can be relied on to carry out taking pictures and the mode uploaded with the mobile phone of oneself, the waste of a large amount of manpower and materials can be saved.
Accompanying drawing explanation
Fig. 1 is the inventive method schematic flow sheet.
Embodiment
Below in conjunction with embodiment, the present invention is described in detail.
Flow process of the present invention as shown in Figure 1, is carried out according to following steps:
Step 1: data acquisition
Usage data derives from the grassland photo of mobile phone camera shooting.
Require when taking pictures:
1. weather conditions good (fine day is optimum, the inclement weathers such as taboo rain, mist, sandstorm), ensure that the photograph image photographed is clear.
When 2. taking pictures, mobile phone will be taken perpendicular to ground, to reduce the geometry deformation of its edges.
3. the place taken requires that gps signal is good, is convenient to obtain the accurate latitude and longitude information in spot for photography.Step 2: photo upload
Exploitation cell phone software will be taken pictures and uploaded onto the server, and upload onto the server the place of taking pictures (warp, latitude), time, the information such as personnel of taking pictures client database simultaneously.The cell phone software of exploitation is based on Android platform, and photo upload adopts the HTTP in Android to transmit data method, and server database end is MySQL database, and connection data storehouse adopts JDBC mode.
Step 3: photo vegetation coverage extracts
1. DNI is calculated
NDI method is the imitative normalized site attenuation method that Woebbecke etc. proposes, and the method is simple, result is more accurate.DNI method is defined as the difference of the green wave band of visible ray and visible red wave band numerical value and the ratio of these two wave band numerical value sums.As follows:
NDI=(green-red)/(green+red)
Wherein: green represents the pixel value of green wave band; Red represents the pixel value of red wave band.DNI be on the occasion of, indicate the covering of vegetation, and increase with the increase of vegetation coverage.
2. NDI value does binary conversion treatment according to positive and negative
The value of NDI>0, is expressed as vegetation pixel, is 1 by this pixel value assignment; The value of NDI≤0, is expressed as non-vegetation pixel, is 0 by this pixel value assignment.Binaryzation formula is:
(B1GT0)*1+(B1LE0)*0
Wherein, B1 is NDI.
3. vegetation coverage is calculated
Statistics vegetation pixel occupies the ratio of total pixel, obtains the vegetation coverage of photo.The formula calculating vegetation coverage is as follows:
Wherein, N
1for vegetation pixel, N is the pixel of view picture photo.
Step 4: evaluation of result and checking
The classification results comparative analysis that the result of calculation obtain DNI method and supervised classification method obtain, illustrates the reliability of NDI method.
Namely supervised classification goes with the sample pixel being identified classification the process identifying other unknown classification pixel also known as training classification.Maximum likelihood method is the one of supervised classification method, and it is to evaluate the similarity between other pixel and training classification according to the average of training sample and variance.
Training sample selection is the key of supervised classification, requires as follows:
1. cell phone pictures only has red, green, blue three wave bands, and the selection of training area must under visible light wave range.
2. training area be homogeneous, not containing other classification and be not that border between other classification is connected or mixed pixel.
NDI and supervised classification method result and precision comparison, NDI method can obtain the precision of supervised classification method, and the vegetation coverage estimated by NDI method is with a high credibility.NDI than supervised classification more fast, efficiently, needs experienced personnel to go to select sample training district unlike supervised classification.
Step 5: result returns
Server end calculates vegetation coverage by step 4, and result of calculation is returned to user.User can check the coverage information of new upload pictures, can carry out the inquiry of uploading historical record simultaneously.
The above is only to better embodiment of the present invention, not any pro forma restriction is done to the present invention, every any simple modification done above embodiment according to technical spirit of the present invention, equivalent variations and modification, all belong in the scope of technical solution of the present invention.
List of references:
[1] Chi Hongkang, Zhou Guangsheng, Xu Zhenzhu, etc. the closely Remote-sensing [J] of grassland vegetation cover degree. Acta Prataculture, 2007,16 (2): 105-110.
[2]ZhouQ,RobsonM.Automatedrangelandvegetationcoveranddensityestimationusinggrounddigitalimagesandaspectral-contextualclassifier[J].InternationalJournalofRemoteSensing,2001,22(17):3457-3470.
[3] Song Xuefeng, Dong Yongping, Dan Liyan, etc. the research [J] of meadow cover degree is measured with digital camera. Inner Mongol grass cultivation, 2004,16 (4): 1-6.
[4] Zhang Qingping, Zhang Shanshan, Chen Lu, etc. application WinCAM software is sentenced and is known analysis lawn coverage [J]. Practaculture Science, 2010,27 (7): 13-17.
[5] Zhang Xuexia, Zhu Qingke, Wu Genmei, etc. photography with digital camera estimation vegetation coverage [J]. Beijing Forestry University's journal, 2008,30 (1): 164-169.
[6] Zhang Chaobin, Li Jianlong, Zhang Ying, etc. the quantitative rapid assay methods research [J] of a kind of meadow cover degree based on RGB pattern. Acta Prataculture, 2013,22 (4): 220-226
[7] outstanding person is appointed, Bai Yanchen, Wang Jin ground. the technique study [J] of rapid extraction vegetation coverage from digital photograph. remote sensing technology and application, 2010,25 (5): 719-724.
[8] Ban Aiqin, Qian Yurong etc. with vegetation decision flowchart method rapid extraction vegetation coverage [J] from digital photograph. Journal of Northwest Sci Tech University of Agriculture and Forestry (natural science edition), 2012,40 (8): 200-206.
[9] Hu Jianbo, Zhang Lu, Huang Wei, etc. based on the grassland vegetation coverage rapid extracting method [J] of digital photograph. Practaculture Science, 2011,28 (9): 1661-1665.
[10] Zhang Yun's rosy clouds, Li Xiaobing, Zhang Yunfei. measure vegetation cover degree [J] based on digital camera, ASTER and MODIS image integration. Acta Phytoecologica Sinica, 2007,31 (5): 842-849.
Claims (2)
1., based on the Grass cover degree extracting method of mobile phone camera, it is characterized in that carrying out according to following steps:
Step 1: usage data derives from the grassland photo of mobile phone camera shooting;
Step 2: will take pictures and upload onto the server, upload onto the server the place of taking pictures, longitude, latitude, time, personal information of taking pictures client database simultaneously;
Step 3: in photo, vegetation coverage extracts;
1. DNI is calculated
NDI=(green-red)/(green+red)
Wherein: green represents the pixel value of green wave band; Red represents the pixel value of red wave band, DNI be on the occasion of, indicate the covering of vegetation, and increase with the increase of vegetation coverage;
2. NDI value does binary conversion treatment according to positive and negative
The value of NDI>0, is expressed as vegetation pixel, is 1 by this pixel value assignment; The value of NDI≤0, is expressed as non-vegetation pixel, and be 0 by this pixel value assignment, binaryzation formula is:
(B1GT0)*1+(B1LE0)*0
Wherein, B1 is NDI;
3. vegetation coverage is calculated
Statistics vegetation pixel occupies the ratio of total pixel, obtains the vegetation coverage of photo.The formula calculating vegetation coverage is as follows:
Wherein, N
1for vegetation pixel, N is the pixel of view picture photo;
Step 4: evaluation of result and checking;
The classification results comparative analysis that the result of calculation obtain DNI method and supervised classification method obtain.
2. according to the Grass cover degree extracting method based on mobile phone camera described in claim 1, it is characterized in that: require when taking pictures in described step 1:
1. weather conditions are good, ensure that the photograph image photographed is clear;
When 2. taking pictures, mobile phone will be taken perpendicular to ground, to reduce the geometry deformation of its edges;
3. the place taken requires that gps signal is good, is convenient to obtain the accurate latitude and longitude information in spot for photography.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510406382.2A CN105069398A (en) | 2015-07-10 | 2015-07-10 | Grassland coverage-degree extraction method based on mobile phone camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510406382.2A CN105069398A (en) | 2015-07-10 | 2015-07-10 | Grassland coverage-degree extraction method based on mobile phone camera |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105069398A true CN105069398A (en) | 2015-11-18 |
Family
ID=54498760
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510406382.2A Pending CN105069398A (en) | 2015-07-10 | 2015-07-10 | Grassland coverage-degree extraction method based on mobile phone camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105069398A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105719320A (en) * | 2016-01-25 | 2016-06-29 | 华中农业大学 | Vegetation canopy coverage calculation method and system based on colorful digital image |
CN105806265A (en) * | 2016-03-24 | 2016-07-27 | 北京林业大学 | Method for measuring ground coverage through mobile phone |
CN106845366A (en) * | 2016-12-29 | 2017-06-13 | 江苏省无线电科学研究所有限公司 | Sugarcane coverage automatic testing method based on image |
CN109741322A (en) * | 2019-01-08 | 2019-05-10 | 南京蓝绿物联科技有限公司 | A kind of visibility measurement method based on machine learning |
CN112967176A (en) * | 2021-02-03 | 2021-06-15 | 成都理工大学 | Method for analyzing plant coverage by using Image J and Photoshop |
CN113175918A (en) * | 2020-01-08 | 2021-07-27 | 北京林业大学 | Technical method for measuring vegetation coverage and density by smart phone |
CN113252583A (en) * | 2021-06-25 | 2021-08-13 | 成都信息工程大学 | Method for calculating alpine hay coverage based on hay vegetation index |
CN114216445A (en) * | 2021-12-08 | 2022-03-22 | 中国电建集团成都勘测设计研究院有限公司 | Water and soil conservation monitoring method for rapidly determining vegetation coverage in field |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070291994A1 (en) * | 2002-05-03 | 2007-12-20 | Imagetree Corp. | Remote sensing and probabilistic sampling based forest inventory method |
CN101303761A (en) * | 2008-06-10 | 2008-11-12 | 裘炅 | Integrated system for claim settlement of vehicle insurance capable of shooting and uploading evidence-obtaining photograph or video by mobile phone |
CN101908196A (en) * | 2009-06-03 | 2010-12-08 | 北京师范大学 | Method for estimating vegetation coverage based on vegetation-soil moisture response relation |
CN102222289A (en) * | 2011-08-02 | 2011-10-19 | 浙江大学 | Optical character recognition (OCR)-based mobile phone financial management method and system |
CN102288954A (en) * | 2011-08-01 | 2011-12-21 | 高吉喜 | Remote sensing estimation method for vegetation coverage of grassland |
CN103544477A (en) * | 2013-09-30 | 2014-01-29 | 北京师范大学 | Improved linear spectral mixture model based vegetation coverage estimation method |
-
2015
- 2015-07-10 CN CN201510406382.2A patent/CN105069398A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070291994A1 (en) * | 2002-05-03 | 2007-12-20 | Imagetree Corp. | Remote sensing and probabilistic sampling based forest inventory method |
CN101303761A (en) * | 2008-06-10 | 2008-11-12 | 裘炅 | Integrated system for claim settlement of vehicle insurance capable of shooting and uploading evidence-obtaining photograph or video by mobile phone |
CN101908196A (en) * | 2009-06-03 | 2010-12-08 | 北京师范大学 | Method for estimating vegetation coverage based on vegetation-soil moisture response relation |
CN102288954A (en) * | 2011-08-01 | 2011-12-21 | 高吉喜 | Remote sensing estimation method for vegetation coverage of grassland |
CN102222289A (en) * | 2011-08-02 | 2011-10-19 | 浙江大学 | Optical character recognition (OCR)-based mobile phone financial management method and system |
CN103544477A (en) * | 2013-09-30 | 2014-01-29 | 北京师范大学 | Improved linear spectral mixture model based vegetation coverage estimation method |
Non-Patent Citations (1)
Title |
---|
任杰等: ""从数码照片中快速提取植被覆盖度的方法研究"", 《遥感技术与应用》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105719320A (en) * | 2016-01-25 | 2016-06-29 | 华中农业大学 | Vegetation canopy coverage calculation method and system based on colorful digital image |
CN105806265A (en) * | 2016-03-24 | 2016-07-27 | 北京林业大学 | Method for measuring ground coverage through mobile phone |
CN106845366A (en) * | 2016-12-29 | 2017-06-13 | 江苏省无线电科学研究所有限公司 | Sugarcane coverage automatic testing method based on image |
CN106845366B (en) * | 2016-12-29 | 2020-03-27 | 江苏省无线电科学研究所有限公司 | Sugarcane coverage automatic detection method based on image |
CN109741322A (en) * | 2019-01-08 | 2019-05-10 | 南京蓝绿物联科技有限公司 | A kind of visibility measurement method based on machine learning |
CN113175918A (en) * | 2020-01-08 | 2021-07-27 | 北京林业大学 | Technical method for measuring vegetation coverage and density by smart phone |
CN113175918B (en) * | 2020-01-08 | 2022-09-06 | 北京林业大学 | Technical method for measuring vegetation coverage and density by smart phone |
CN112967176A (en) * | 2021-02-03 | 2021-06-15 | 成都理工大学 | Method for analyzing plant coverage by using Image J and Photoshop |
CN113252583A (en) * | 2021-06-25 | 2021-08-13 | 成都信息工程大学 | Method for calculating alpine hay coverage based on hay vegetation index |
CN114216445A (en) * | 2021-12-08 | 2022-03-22 | 中国电建集团成都勘测设计研究院有限公司 | Water and soil conservation monitoring method for rapidly determining vegetation coverage in field |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105069398A (en) | Grassland coverage-degree extraction method based on mobile phone camera | |
WO2022252799A1 (en) | Model training method, woodland change detection method, system, and apparatus, and medium | |
Rasmussen et al. | Tree survey and allometric models for tiger bush in northern Senegal and comparison with tree parameters derived from high resolution satellite data | |
CN108592888B (en) | Residential area extraction method | |
CN101114023A (en) | Lake and marshland flooding remote sense monitoring methods based on model | |
CN106778629B (en) | Greenhouse identification method and device | |
CN107358161B (en) | Coastline extraction method and coastline extraction system based on remote sensing image classification | |
Lang et al. | Digital photography for tracking the phenology of an evergreen conifer stand | |
Saboori et al. | Automatically selecting hot and cold pixels for satellite actual evapotranspiration estimation under different topographic and climatic conditions | |
WO2024061159A1 (en) | Method for rapidly monitoring and determining drought condition of summer corn on basis of chlorophyll content by using unmanned aerial vehicle | |
CN108399393A (en) | A kind of Vegetation canopy negative and positive leaf detection method based on fluorescence remote sensing | |
Chianucci et al. | Continuous observations of forest canopy structure using low-cost digital camera traps | |
Ainiwaer et al. | Deep learning-based rapid recognition of oasis-desert ecotone plant communities using UAV low-altitude remote-sensing data | |
CN104881659B (en) | The extracting method and device of a kind of impermeable stratum | |
Zhang et al. | A comparison of pixel-based and object-based land cover classification methods in an arid/semi-arid environment of northwestern China | |
CN110910266A (en) | Irrigation area agricultural irrigation water total amount estimation method based on remote sensing | |
WO2024061160A1 (en) | Method for rapidly monitoring and determining drought condition of winter wheat by using unmanned aerial vehicle and on basis of leaf area index | |
CN113484245A (en) | Remote sensing rapid monitoring method and system for paddy field planting pattern in hilly and mountainous areas and computer readable storage medium | |
Sierra-Soler et al. | High accuracy Land Use Land Cover (LULC) maps for detecting agricultural drought effects in rainfed agro-ecosystems in central Mexico | |
CN114359728B (en) | River channel type remote sensing extraction method | |
Zhuang et al. | A Method for water body extraction based on the tasselled cap transformation from remote sensing images | |
Liu et al. | Water extraction on the hyperspectral images of gaofen-5 satellite using spectral indices | |
CN106846309B (en) | Automatic estimation method for forest surface dead combustible load capacity based on image | |
Wei et al. | Water body extraction based on the LBV transformation analysis for China GF-1 multi-spectral images | |
Wang et al. | A Novel Wireless Leaf Area Index Sensor Based on a Combined U-Net Deep Learning Model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20151118 |