Detection And Area Estimation For Photovoltaic Panels In Urban Hyperspectral Remote Sensing Data By An Original Nmf-Based Unmixing Method

Karoui, Moussa Sofiane; Benhalouche, Fatima Zohra; Deville, Yannick; Djerriri, Khelifa; Briottet, Xavier; Bris, Arnaud Le

doi:10.1109/igarss.2018.8518204

Cited by 14 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The investigations reported in the present paper extend the above-mentioned approach of [7], still in a linear context. Indeed, in this paper, and in addition to the method described in [7], a new linear hyperspectral-unmixing method is designed for automatically detecting photovoltaic panels and estimating their surfaces. Thus, two linear methods are reported in this paper (and their experimental performance is analyzed in a much more detailed way than in [7]).…”

Section: Introductionsupporting

confidence: 75%

“…The function ∂J ∂θ + is obtained by keeping the terms of (7) or (8) having a plus sign, whereas ∂J ∂θ − is obtained by keeping the terms having a minus sign. The multiplicativity and nonnegativity constraints can be satisfied by initializing θ with a nonnegative value and choosing the value of the learning rate matrix ϕ θ according to…”

Section: Proposed Approachesmentioning

confidence: 99%

“…To date, no hyperspectral-unmixing-based works have been reported in the literature for automatically detecting and estimating the surfaces of photovoltaic panels, other than the recent one proposed in [7]. In that work, a linear spectral unmixing (LSU) method was proposed to partially unmix a hyperspectral image, by means of a nonnegative matrix factorization (NMF) algorithm that exploits known solar panel spectra in order to automatically detect and estimate areas of this urban land surface material.…”

Section: Introductionmentioning

confidence: 99%

“…Indeed, in this paper, and in addition to the method described in [7], a new linear hyperspectral-unmixing method is designed for automatically detecting photovoltaic panels and estimating their surfaces. Thus, two linear methods are reported in this paper (and their experimental performance is analyzed in a much more detailed way than in [7]). These approaches are based on original algorithms that have relationships with NMF and that exploit known solar panel spectra.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, the designed linear methods can be considered to be Partial (or informed) NMF (Part-NMF) techniques [19,20]. The first designed approach, called Gradient-based Part-NMF (Grd-Part-NMF), employs a projected gradient descent algorithm by means of iterative update rules that include the nonnegativity constraint, whereas the second proposed one [7], called Multiplicative Part-NMF (Multi-Part-NMF), uses multiplicative and iterative gradient-based update rules.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Partial Linear NMF-Based Unmixing Methods for Detection and Area Estimation of Photovoltaic Panels in Urban Hyperspectral Remote Sensing Data

et al. 2019

Self Cite

View full text Add to dashboard Cite

High-spectral-resolution hyperspectral data are acquired by sensors that gather images from hundreds of narrow and contiguous bands of the electromagnetic spectrum. These data offer unique opportunities for characterization and precise land surface recognition in urban areas. So far, few studies have been conducted with these data to automatically detect and estimate areas of photovoltaic panels, which currently constitute an important part of renewable energy systems in urban areas of developed countries. In this paper, two hyperspectral-unmixing-based methods are proposed to detect and to estimate surfaces of photovoltaic panels. These approaches, related to linear spectral unmixing (LSU) techniques, are based on new nonnegative matrix factorization (NMF) algorithms that exploit known panel spectra, which makes them partial NMF methods. The first approach, called Grd-Part-NMF, is a gradient-based method, whereas the second one, called Multi-Part-NMF, uses multiplicative update rules. To evaluate the performance of these approaches, experiments are conducted on realistic synthetic and real airborne hyperspectral data acquired over an urban region. For the synthetic data, obtained results show that the proposed methods yield much better overall performance than NMF-unmixing-based methods from the literature. For the real data, the obtained detection and area estimation results are first confirmed by using very high-spatial-resolution ortho-images of the same regions. These results are also compared with those obtained by standard NMF-unmixing-based methods and by a one-class-classification-based approach. This comparison shows that the proposed approaches are superior to those considered from the literature.

show abstract

Section: Introductionsupporting

confidence: 75%

Section: Proposed Approachesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%