Unlock instant, AI-driven research and patent intelligence for your innovation.

Sub-pixel drawing method based on vector boundaries

A sub-pixel and vector technology, used in instruments, character and pattern recognition, computer components and other directions, can solve problems such as multiple rounding errors, affecting output accuracy, and inconsistent boundaries, reducing errors, strong interpretability, and reducing Gap and Overlap Effects

Active Publication Date: 2015-04-15
INST OF GEOGRAPHICAL SCI & NATURAL RESOURCE RES CAS
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But there is still room for improvement: (1) When the scaling factor is an odd number, more rounding errors will be introduced when determining the position of polygon vertices in the mixed cell
(2) For mixed pixels with multiple land cover types, the boundaries of different land cover types may be inconsistent. Although fine-tuning is allowed, it may still affect the output accuracy

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
  • Sub-pixel drawing method based on vector boundaries
  • Sub-pixel drawing method based on vector boundaries
  • Sub-pixel drawing method based on vector boundaries

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] Such as figure 1 Shown, the specific implementation steps of the present invention are as follows:

[0017] Step 1. Preprocess the remote sensing data, and obtain the soft classification information of each pixel on the image through soft classification, that is, the area ratio of each component in the pixel, also known as abundance.

[0018] Suppose there are two land cover types C in a 3×3 pixel area 1 and C 2 . Obtain the central pixel P by soft classification m and its neighborhood pixel P i The proportions of the area occupied by the two land cover types are P m {0.7,0.3},P 0 {0.35,0.65},P 1 {0.95,0.05}P 2 {1,0}P 3 {1,0}P 4 {1,0}P 5 {1,0}P 6 {0.65,0.35} and P 7 {0,1}, such as image 3 In (a) shown.

[0019] Step 2. Use the linear attenuation function to fill in the soft classification information of the boundary pixels outside the range of the fractional image.

[0020] In order to deal with the mixed pixels in the boundary area of ​​remote sensing ...

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 sub-pixel drawing method based on vector boundaries. The method comprises the steps that the accurate vector boundaries of ground objects in a mixed pixel are extracted by utilizing component (end members) area vectors or abundance of the mixed pixel or an adjacent pixel, then the accurate vector boundaries are converted into grids (sub-pixels) of the specific enlarging scales, and then the sub-pixel drawing of a video is completed. The sub-pixel drawing method based on the vector boundaries has the advantages of being wide in practicability, high in calculation speed, high in simulation precision, and suitable for remote sensing data to carry out the geoscience information extraction and geoscience data mining work such as target extraction, territorial resources surveys, global climate changes, disaster monitoring and disaster situation assessment.

Description

technical field [0001] The invention relates to a sub-pixel mapping method, which belongs to the technical field of geospatial information. technical background [0002] Making thematic maps (image classification) using digital remote sensing images is a hot field in remote sensing technology research. However, in the process of remote sensing image acquisition, due to the complexity of the surface, the influence of the external environment, and the limitations of the sensor itself, mixed pixels (Mixed Pixel) commonly exist in the image. The spectral characteristics of mixed pixels are the comprehensive characteristics of the corresponding spectral responses of different land cover types, which cause errors and uncertainties in the traditional hard classification methods in the remote sensing classification process. Therefore, the soft classification (Soft Classification) method was proposed, that is, to describe the area ratio of each object category in the pixel in the fo...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62
Inventor 葛咏陈跃红江昱李三平
Owner INST OF GEOGRAPHICAL SCI & NATURAL RESOURCE RES CAS