HyperMix: A new tool for quantitative evaluation of end member identification and spectral unmixing techniques

Jiménez, Luis Ignacio; Martín, Gabriel

doi:10.1109/igarss.2012.6351276

Cited by 6 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The spatial resolution (i.e., the ability to resolve two adjacent points as separate in the image) is one of the features of remote sensing imaging systems [1]. Some researchers highlight that, no matter how high the spatial resolution might be, the instantaneous field of view of image sensors always includes several discrete elements and no image pixel is completely homogeneous in spectral characteristics [2][3][4]. Therefore, the spectrum of each pixel is caused by a mixture of spectral signals (mixed pixels) and image processing techniques that are based on spatial analysis are not applicable [2][3][4][5].…”

Section: Introductionmentioning

confidence: 99%

“…Some researchers highlight that, no matter how high the spatial resolution might be, the instantaneous field of view of image sensors always includes several discrete elements and no image pixel is completely homogeneous in spectral characteristics [2][3][4]. Therefore, the spectrum of each pixel is caused by a mixture of spectral signals (mixed pixels) and image processing techniques that are based on spatial analysis are not applicable [2][3][4][5]. In any case, since 1979, there has been a combined research effort to retrieve mixed pixel information from remote sensing images [6].…”

Section: Introductionmentioning

confidence: 99%

“…This methodology can be decomposed in two consecutive procedures: the first compares the spectrum of each mixed pixel with reference spectra to decompose it into a collection of constituent spectra (called endmembers); the second determines the proportion of each endmember present in the pixel (called fractional abundance) [4,12,13]. Since the number of endmembers must be less than the number of bands [7], some authors associated the development and use of spectral unmixing only with hyperspectral data [3,[12][13][14]. However, the literature shows that, for over 40 years, spectral unmixing has been the most commonly used procedure for analyzing not only hyperspectral, but also multispectral images (e.g., [15]).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spatial Validation of Spectral Unmixing Results: A Case Study of Venice City

Cavalli

2022

Remote Sensing

View full text Add to dashboard Cite

Since remote sensing images offer unique access to the distribution of land cover on earth, many countries are investing in this technique to monitor urban sprawl. For this purpose, the most widely used methodology is spectral unmixing which, after identifying the spectra of the mixed-pixel constituents, determines their fractional abundances in the pixel. However, the literature highlights shortcomings in spatial validation due to the lack of detailed ground truth knowledge and proposes five key requirements for accurate reference fractional abundance maps: they should cover most of the area, their spatial resolution should be higher than that of the results, they should be validated using other ground truth data, the full range of abundances should be validated, and errors in co-localization and spatial resampling should be minimized. However, most proposed reference maps met two or three requirements and none met all five. In situ and remote data acquired in Venice were exploited to meet all five requirements. Moreover, to obtain more information about the validation procedure, not only reference spectra, synthetic image, and fractional abundance models (FAMs) that met all the requirements, but also other data, that no previous work exploited, were employed: reference fractional abundance maps that met four out of five requirements, and fractional abundance maps retrieved from the synthetic image. Briefly summarizing the main results obtained from MIVIS data, the average of spectral accuracies in root mean square error was equal to 0.025; using FAMs, the average of spatial accuracies in mean absolute error (MAEk-Totals) was equal to 1.32 and more than 78% of these values were related to sensor characteristics; using reference fractional abundance maps, the average MAEk-Totals value increased to 1.97 because errors in co-localization and spatial-resampling affected about 29% of these values. In conclusion, meeting all requirements and the exploitation of different reference data increase the spatial accuracy, upgrade the validation procedure, and improve the knowledge of accuracy.

show abstract