Remote sensing survey method and system for estimating tree coverage percentage of city

A measurement method and coverage technology, which is applied in the fields of remote sensing image processing and application, urban garden statistics, forest and vegetation mapping, can solve the problems of low precision and difficulty in determining the coverage length and radius, and achieve high precision, accuracy and precision Improvement, high efficiency effect

Inactive Publication Date: 2009-04-08
BEIJING JIAOTONG UNIV
2 Cites 18 Cited by

AI-Extracted Technical Summary

Problems solved by technology

Since it is impossible for all urban trees to have the same size of canopy coverage, and the coverage length...
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 more

Abstract

The invention discloses a remote sensing surveying method used for estimating the urban tree coverage rate with high precision and a remote sensing surveying system thereof. The method comprises the following steps: S110, a multispectral remote-sensing image is utilized to carry out the partition aiming at extracting crown coverage areas; S120, aiming at the image areas generated by the partition, a fuzzy classifier is built to carry out the tree coverage classification of oriented objects; S130, the precision evaluation of the classified result is carried out; and S140, the urban tree coverage rate is calculated according to the classified tree coverage area. According to the invention, the actual crown ground cover area which is accordant with each tree in an urban area is extracted from the remote sensing images with high resolution, then the total area of the tree coverage in the urban area is calculated according to the pixel ground resolution of the remote sensing images, and finally, the tree coverage rate in the urban area is obtained. Compared with a tree coverage rate calculating method applied currently, the invention has the advantages that the estimation precision is obviously improved, and the actual position of the crown layer ground coverage area of each tree can be obtained.

Application Domain

Technology Topic

Image

  • Remote sensing survey method and system for estimating tree coverage percentage of city
  • Remote sensing survey method and system for estimating tree coverage percentage of city
  • Remote sensing survey method and system for estimating tree coverage percentage of city

Examples

  • Experimental program(1)

Example Embodiment

[0031] The present invention will be described in detail below with reference to the drawings and specific embodiments.
[0032] figure 1 It is a flowchart of the remote sensing measurement method for estimating the urban tree coverage in the first embodiment of the present invention.
[0033] Such as figure 1 As shown, it includes the following processing steps:
[0034] Use multi-spectral remote sensing images to segment them for the purpose of extracting the canopy coverage area (S110);
[0035] Construct a fuzzy classifier to perform object-oriented tree coverage classification on the image regions generated by segmentation (S120);
[0036] Evaluate the accuracy of the classification results (S130);
[0037] Calculate the urban tree coverage rate according to the classified tree coverage area (S140).
[0038] In the present invention, in step S110, the resolution of the multi-spectral (blue, green, red, near-infrared band) remote sensing image used is a ground resolution of less than or equal to 0.6 m. For such high-frequency multi-spectral remote sensing image Perform segmentation for the purpose of extracting the canopy coverage area, figure 2 It is an airborne high-resolution true-color synthetic orthophoto remote sensing image map of a certain urban area, with a ground resolution of 0.6m.
[0039] In addition, in step S110, a segmentation scale is selected according to the size of the tree coverage area to be extracted, and an adjustable-scale segmentation algorithm is used. The present invention preferably has two variable-scale segmentation algorithms: one is the multi-resolution segmentation algorithm adopted in the eCognition remote sensing image analysis software (eCognition) as a commercial software; the other is the mean shift (Mean Shift) segmentation algorithm. Of course, the present invention is not limited to the above two variable-scale segmentation algorithms, and those of ordinary skill in the art can also choose a variable-scale segmentation algorithm with better segmentation performance. image 3 Shows the right figure 2 Perform segmentation image map for the purpose of extracting the area covered by the tree.
[0040] In addition, in step S120, the key classification features adopted by the constructed fuzzy classifier include the normalized difference vegetation index (NDVI), the average difference with neighboring objects, and the average brightness value. Figure 4 The grass and tree cover map displayed after performing object-oriented fuzzy classification, where dark green is grass and bright green is tree.
[0041] In step S130, a random sample is used as reference data (its category is interpreted through visual interpretation) to perform accuracy evaluation based on the confusion matrix.
[0042] Figure 5 A random sample map selected to evaluate the accuracy of the tree coverage classification for the local urban area image. The total accuracy of the tree coverage classification is 96.4%. Figure 6 Display the image for the final tree cover classification map, where the green color shows the urban tree cover area.
[0043] In step S140, the calculation formula of the urban tree coverage rate is: urban tree coverage rate=total area occupied by tree coverage/total urban area. The tree coverage rate of the local urban image in the above example is calculated to be 42.3%.
[0044] Figure 7 It is a block diagram of a remote sensing measurement system for estimating urban tree coverage in the second embodiment of the present invention. Such as Figure 7 As shown, the remote sensing measurement system for estimating urban tree coverage includes: a segmentation unit 710, which uses multi-spectral remote sensing images to perform segmentation for the purpose of extracting the canopy coverage area; a classification unit 720, which constructs a fuzzy image area generated by the segmentation The classifier performs object-oriented tree coverage classification; the evaluation unit 730 performs accuracy evaluation on the classification results; and the calculation unit 740 calculates the urban tree coverage rate according to the classified tree coverage area.
[0045] Among them, the resolution of the used multi-spectral (blue, green, red, and near-infrared band) remote sensing image is a ground resolution of less than or equal to 0.6m.
[0046] The segmentation unit 710 selects the segmentation scale according to the size of the tree coverage area to be extracted, and uses an adjustable-scale segmentation algorithm to figure 2 The airborne high-resolution true-color synthetic ortho-remote sensing image map of the local urban area shown is segmented. and image 3 Shows the right figure 2 Perform segmentation image map for the purpose of extracting the area covered by the tree. The present invention preferably has two variable-scale segmentation algorithms: one is a multi-resolution segmentation algorithm used in eCognition as a commercial software; the other is a mean shift (Mean Shift) segmentation algorithm.
[0047] Similar to the above-mentioned first embodiment, here, the classification key features adopted by the fuzzy classifier constructed by the classification unit 720 include the normalized difference vegetation index (NDVI), the average difference with neighboring objects, and the average brightness value. In the same way, after the classification processing of the classification unit 720, Figure 4 Shows the grass and tree coverage map displayed after performing object-oriented fuzzy classification, where dark green is grass and bright green is tree.
[0048] In addition, the evaluation unit 730 uses a random sample as reference data (determining its category by visual interpretation) to perform accuracy evaluation based on the confusion matrix. As in the first embodiment, after the accuracy evaluation of the evaluation unit 730, Figure 5 A random sample map selected to evaluate the accuracy of the tree coverage classification for the local urban area image. The total accuracy of the tree coverage classification is 96.4%. Figure 6 Display the image for the final tree cover classification map, where the green color shows the urban tree cover area.
[0049] In addition, as in the first embodiment, the calculation formula of the urban tree coverage ratio of the calculation unit 740 is urban tree coverage=total area occupied by tree coverage/total urban area. The tree coverage rate of the local urban image in the above example is calculated to be 42.3%.
[0050] According to the remote sensing measurement for estimating urban tree coverage and its remote sensing measurement system according to the present invention, it is possible to extract from the high-resolution remote sensing image the area in line with the real canopy and ground coverage of each tree in the urban area, and then base on the remote sensing image pixel ground Resolution, calculate the total area covered by trees in the urban area, and finally get the tree coverage in the urban area. Compared with the prior art, the estimation accuracy of the present invention is obviously improved, and the real position of the ground cover area of ​​the canopy of each tree can be obtained.
[0051] The invention has the advantages of simple technical process, fast speed, high precision, etc., and can completely replace the commonly used measurement methods and measurement systems currently in use. Therefore, it is practical and has great commercial value for promotion and application.
[0052] It should be pointed out that the above-mentioned specific embodiments may enable those skilled in the art to understand the present invention more comprehensively, but do not limit the present invention in any way. Therefore, although the present specification has described the present invention in detail with reference to the drawings and embodiments, those skilled in the art should understand that the present invention can still be modified or equivalently replaced; without departing from the spirit and technical essence of the present invention. The technical solutions and their improvements should be covered by the scope of protection of the invention patent.
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

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
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

Similar technology patents

Pretreatment kit for salbutamol sample based on immunomagnetic beads

PendingCN108508199AReduce interference from background substancesImprove accuracy and precisionMaterial analysisChemistryImmunomagnetic bead
Owner:沭阳康源泰博生物科技有限公司

Classification and recommendation of technical efficacy words

  • Improve accuracy and precision
  • Simple technical process
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products