Mountain Landscape Building Extraction via NDVI NDBI NSBI Thresholding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for extracting landscape buildings from remote sensing images in scenic areas, particularly in mountainous regions, face challenges such as low efficiency, poor accuracy, and difficulty in handling complex terrain and shadow effects, leading to cumbersome processes and high costs.
Innovation Solution
A method utilizing normalized difference vegetation index (NDVI), normalized difference buildup index (NDBI), and normalized difference build shadow index (NSBI) with threshold segmentation to effectively separate vegetation, building, and shadow areas, enhancing spectral differences and reducing the influence of terrain shadows, allowing for efficient extraction of landscape buildings in scattered distributions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If supervised classification method is used for extraction of landscape buildings, then classification can be performed based on remote sensing images, but the efficiency of the analysis process is low and the accuracy needs to be improved
Solution Approach 1:
The patent segments the remote sensing image into multiple patches and processes each patch independently through multiple stages of classification and filtering. This segmentation approach enables parallel processing of different regions, improving analysis efficiency while maintaining extraction accuracy through localized feature analysis.
Solution Approach 2:
The patent performs preliminary actions by first identifying candidate building patches through initial classification, then applying subsequent filtering and verification steps. This preliminary identification followed by refined processing improves overall efficiency by focusing computational resources on potential building areas rather than processing the entire image uniformly.
2Adaptability or versatility
If samples are selected to cover the extraction area in mountainous regions with interlaced buildings and bare land, then classification can be performed, but the selected samples will be offset due to shadow differences and the method is difficult to apply to large-scale scenic areas
Solution Approach 1:
The patent applies local quality by using different classification thresholds and parameters for different patches based on their local characteristics. Each patch is processed with adaptive thresholds that account for local shadow conditions, terrain variations, and building densities, enabling accurate extraction across diverse large-scale scenic areas without uniform sample offset.
Solution Approach 2:
The patent implements dynamic adaptation by adjusting classification parameters and thresholds based on local image characteristics such as shadow presence, terrain slope, and building density. This dynamic parameter adjustment allows the method to adapt to varying conditions across large-scale areas, maintaining sample selection accuracy despite shadow differences and terrain variations.
3Measurement precision
If rectangular shape based fuzzy algorithm is used for extraction, then buildings with obvious rectangular shape can be extracted, but the process is cumbersome and the algorithm cost is high
Solution Approach 1:
The patent extracts only the essential features needed for building identification from the full image data, focusing on key spectral and spatial characteristics rather than processing all image details through complex algorithms. This selective extraction of critical features reduces algorithmic complexity while maintaining extraction accuracy for buildings with various shapes.
4Productivity
If conventional field survey is used for obtaining building information, then accurate data can be obtained, but it lacks high frequency, wide coverage and low cost advantages
Solution Approach 1:
The patent replaces the mechanical field survey system with an automated remote sensing image processing system. This substitution uses computational algorithms to extract building information from satellite or aerial images, achieving high-frequency, wide-coverage data collection at low cost while maintaining accuracy through sophisticated image analysis techniques that identify building features automatically.
Data Source
AI summary
The present invention discloses a method and an apparatus for extracting mountain landscape buildings based on high-resolution remote sensing images. The method comprises: segmenting a remote sensing image, and extracting non-vegetation areas from the remote sensing image by using NDVI; segmenting the non-vegetation areas, and extracting building areas by using NDBI; segmenting the building areas again, and calculating a normalized difference build shadow index NSBI of each patch; calculating NSBI separator of each patch in the non-vegetation areas and setting a separator threshold, and extracting landscape building areas based on the threshold. In the present invention, by introducing a near infrared band in the remote sensing image spectrum, in which there is a significant difference between shadows and non-shadows, the influence of large shadow areas in mountainous shady areas in the remote sensing image on the result of extraction is reduced.