Method for extracting single plant canopy from high-resolution unmanned aerial vehicle visible light remote sensing image

A remote sensing image, high-resolution technology, applied in the field of agricultural and forestry resources monitoring technology and agricultural informatization, can solve the problem of high cost, achieve fast speed, good segmentation effect, and avoid the effect of complex background

Active Publication Date: 2020-10-02
AGRI INFORMATION INST OF CAS +1
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The canopy information of a single plant based on UAV lidar data and multispectral data has high accuracy, but the cost is also high. Exploring a s

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for extracting single plant canopy from high-resolution unmanned aerial vehicle visible light remote sensing image
  • Method for extracting single plant canopy from high-resolution unmanned aerial vehicle visible light remote sensing image
  • Method for extracting single plant canopy from high-resolution unmanned aerial vehicle visible light remote sensing image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] like Figure 1 to Figure 5 As shown, the present invention is used to extract the individual plant canopy information of the Tianshan spruce forest in a forest farm at the northern foot of the Tianshan Mountains, specifically comprising the following steps:

[0038]S1. Obtain the heading and lateral overlap rate of UAV visible light remote sensing images in the forest area ≥ 60%, the resolution is not greater than 0.12m, the image is an RGB true color image, and the ground in the forest area is still covered with snow. For UAV remote sensing The image is pre-processed such as stitching and orthorectification, so that the image canopy boundary features of the region to be segmented are intact.

[0039] S2. Due to the large size of the original image and the spatial resolution of the image is 0.117748m, an image with a size of 256×256 pixels is selected as a training sample. An image of this size is equivalent to a plot of 30m×30m in the wild, which can ensure a certain ...

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 Login to view more

Abstract

The invention discloses a method for extracting a single plant canopy from a high-resolution unmanned aerial vehicle visible light remote sensing image. The method comprises the following steps: 1, preprocessing, cutting, cleaning and marking a data set on acquired unmanned aerial vehicle remote sensing data; 2, obtaining a canopy preliminary segmentation result by using a deep convolutional neural network U-Net, training a U-Net model by using the labeled data set, and segmenting the image by using the trained U-Net model to obtain a probability grey-scale map; and 3, optimizing the probability grey-scale map based on a mark control watershed algorithm to obtain a final single plant canopy segmentation result. According to the invention, the U-Net algorithm is used to avoid the complex background of the original image under the natural condition to a certain extent; the initial contour of the canopy is obtained through interference of uneven illumination intensity on canopy segmentation, a mark control watershed algorithm can well segment the canopy of a single plant and is used for optimizing the canopy result extracted by U-Net and extracting canopy information of the single plant, the canopy density precision is higher, and the canopy density speed is higher.

Description

technical field [0001] The invention belongs to the fields of agricultural and forestry resources monitoring technology and agricultural informatization, and specifically relates to a method for extracting a single plant canopy from a high-resolution UAV visible light remote sensing image. Background technique [0002] Forest resources play an important role in maintaining national ecological security, and it is necessary to keep abreast of the current situation and dynamic changes of forest resources. To realize the accurate measurement of forest resources, it is bound to implement the accurate measurement of a single standing tree. The canopy is the most direct part of the plant information. By extracting the canopy information of a single plant, the tree species can be identified, the growth status can be monitored, and the canopy of a single plant can be obtained. Layer position, crown width, diameter at breast height, single tree biomass and other parameters. Therefore...

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
no application Login to view more
IPC IPC(8): G06K9/00G06K9/34G06K9/46G06K9/62G06N3/04
CPCG06V20/188G06V10/267G06V10/44G06N3/045G06F18/214Y02T10/40
Inventor 孙伟曹姗姗金忠明吴建寨张晶邱琴周向阳朱孟帅
Owner AGRI INFORMATION INST OF CAS
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap