Reconstructed vegetation remote sensing discrimination method based on long-time sequence vegetation indexes
A technology of vegetation index and discrimination method, applied in data processing applications, character and pattern recognition, instruments, etc., can solve the problems that the reliability of discrimination results cannot be guaranteed, and the differences in vegetation spectral characteristics are not obvious.
Pending Publication Date: 2020-10-27
DATONG COAL MINE GRP +1
View PDF0 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The current remote sensing discrimination method for reconstructed vegetation relies heavily on the difference in spectral characteristics between reconstructed vegetation and other types of vegetation. influence, the reliability of the discriminant results cannot be guaranteed
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0100] S1. Determine the vegetation range.
[0101] In this example, first use GoogleEarth software to locate the southern suburb of Datong City, Shanxi Province, and select two arbor-covered areas in the southern suburb of Datong City, Shanxi Province by visual interpretation with reference to the latest satellite remote sensing images: forest land A and forest land B, and then Use the tool that comes with the software to draw the rough boundaries of the two vegetation, and save it as a shp file in UTM coordinate system.
[0102] S2. Obtain time-series vegetation index data.
[0103] In this instance, through the USGS ( https: / / glovis.usgs.gov / ) obtained the normalized difference vegetation index (NDVI) data of all Landsat series remote sensing image files covering the southern suburbs of Datong City, Shanxi Province, and obtained 8-day interval NDVI data sets including Landsat4 / 5 TM, Landsat7 ETM and Landsat8OLC images, a total of 829 Period data, time series from May 29...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a reconstructed vegetation remote sensing discrimination method based on long-time sequence vegetation indexes, and is suitable for the technical field of mine ecological environment monitoring. Through long-time sequence vegetation indexes of vegetation are used and after noise identification and prediction value calculation, a vegetation growth curve is constructed basedon Fourier series and a least square method, and the annual vegetation index mean value of the regional vegetation in the time sequence year is further obtained; and the method further includes calculating the change trend of the vegetation index in every five years by utilizing linear fitting, taking the difference degree between the past change trend and the future five years at a certain time point as a judgment index, and when the difference degree exceeds a set threshold value, determining that the vegetation is reconstructed and the year with the maximum difference degree is the vegetation reconstruction starting time. According to the invention, the complete growth process of the vegetation is effectively reflected, so that the one-sidedness of single-time-point data is reduced, theaccuracy of time series data is improved through noise identification and predicted value calculation, and the influence of abnormal data of a single year on the overall growth trend of the vegetation is reduced by taking the vegetation growth trend difference degree as a judgment index.
Description
technical field [0001] The invention relates to a reconstruction vegetation remote sensing discrimination method based on a long-time series vegetation index, which is especially suitable for use in the technical field of mine ecological environment monitoring. Background technique [0002] The rapid identification of re-vegetation is an important task in mine land reclamation and ecological restoration. Over the past 20 years, mine ecological restoration has received widespread attention, and a large number of vegetation reconstruction projects have been carried out in mining areas across the country. In order to grasp the implementation of vegetation reconstruction work, it is first necessary to identify various vegetation in the mining area. However, traditional field surveys are difficult to meet the requirements of efficient, accurate, and real-time monitoring, which makes it impossible for the regulatory authorities to evaluate the effectiveness of mine vegetation rec...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/00G06Q10/06G06Q50/02
CPCG06Q10/0639G06Q50/02G06V20/188
Inventor 马占元米家鑫赵晨德张绍良常晓华路喜王玉明魏川博岳雪莲杨永均
Owner DATONG COAL MINE GRP