Related Experiment Video
Updated: Mar 11, 2026
07:05
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
Published on: June 18, 2021
2.9K
The Successive Projection Algorithm (SPA), an Algorithm with a Spatial Constraint for the Automatic Search of
Jinkai Zhang1, Benoit Rivard2, D M Rogge3
1Alberta Terrestrial Imaging Center, 401, 817 - 4th Avenue South, Lethbridge, Alberta Canada, T1J 0P3. benoit.rivard@ualberta.ca.
Sensors (Basel, Switzerland)
|November 24, 2016
Summary
The Successive Projection Algorithm (SPA) improves remote sensing by using spatial adjacency to find realistic spectral endmembers, reducing outlier susceptibility. This method enhances hyperspectral data analysis without dimensionality reduction.
Area of Science:
- Remote Sensing
- Geospatial Analysis
- Spectral Imaging
Background:
- Spectral mixing in remote sensing data leads to pixels representing multiple materials, complicating analysis.
- Linear spectral mixture analysis assumes pixel variability arises from differing proportions of spectral endmembers.
- Existing endmember-search algorithms often rely on convex geometry and orthogonal projection.
Purpose of the Study:
- Introduce a novel endmember-search algorithm, the Successive Projection Algorithm (SPA).
- Address the limitations of existing methods by incorporating spatial constraints.
- Improve the accuracy and reliability of endmember extraction from hyperspectral data.
Main Methods:
- Developed the Successive Projection Algorithm (SPA), incorporating spatial adjacency of endmember candidate pixels.
- Utilized spectral angle and spatial continuity to constrain endmember selection.
- Applied SPA to AVIRIS Cuprite and Probe-1 hyperspectral imagery for validation.
Main Results:
- SPA successfully extracts endmembers from hyperspectral data without dimensionality reduction.
- The algorithm demonstrates reduced susceptibility to outlier pixels, generating more realistic endmembers.
- Case studies validated SPA-derived endmembers against ground truth data.
- SPA provides data on simplex volume ratio changes, indicating convergence and aiding in determining the number of endmembers.
Conclusions:
- The Successive Projection Algorithm (SPA) offers a robust method for endmember extraction in hyperspectral remote sensing.
- Incorporating spatial adjacency significantly enhances the reliability and realism of extracted endmembers.
- SPA's ability to operate without dimensionality reduction and provide convergence insights makes it a valuable tool for geospatial analysis.
Related Concept Videos
02:18Fischer Projections
17.3K
Learning to draw Fischer projections of molecules and understanding their relevance plays a crucial role in the visual depiction of organic molecules. A Fischer projection is a two-dimensional projection on a planar surface to simplify the three-dimensional wedge–dash representation of molecules. This is especially helpful in the case of molecules with multiple chiral centers that can be difficult to draw. Here, all the bonds of interest are represented as horizontal or vertical lines. While...
17.3K
02:06Newman Projections
23.2K
Different notations are used to represent the three-dimensional structure of molecules on two-dimensional surfaces. One of the most commonly used representations is the dash-wedge formula. The dashed wedges, solid wedges, and the plane lines indicate the groups situated behind the plane, coming out of the plane, and in the plane, respectively.
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...
23.2K