A New Hyperspectral Unmixing Method Using Co-Registered Hyperspectral and Panchromatic Images

Rebeyrol, Simon; Deville, Yannick; Achard, Véronique; Briottet, Xavier; May, Stefan

doi:10.1109/whispers.2019.8920941

Cited by 2 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We propose an improved hyperspectral unmixing method, originally introduced in Reference [57], that takes into account a panchromatic image co-registered with a hyperspectral image. This new method, called HBEE-LCNMF, is composed of two stages.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…The limitations of the current hyperspectral unmixing methods and the perspective of the forthcoming HYPXIM/HYPEX-2 [1,2] mission have motivated the development of a new unmixing approach to reduce those limitations and improve the hyperspectral unmixing process by combining the hyperspectral and panchromatic images. This paper presents an improvement of a strategy to unmix hyperspectral images given an additional PAN image that we originally proposed in Reference [57]. The method is composed of two stages described in Section 2.…”

Section: Roof Tilementioning

confidence: 99%

“…The spatial PAN heterogeneity can be assessed by a variety of statistical criteria. Instead of the full range criterion on the PAN set of pixels proposed in Reference [57], the 95%-5% percentile range, denoted η, is chosen to get rid of most of the outliers [58]. With this spatial PAN criterion, a heterogeneity map is computed and all the HS pixels below a α h threshold are designated as pure.…”

Section: Heterogeneity-based Endmember Extraction (Hbee)mentioning

confidence: 99%

“…Instead of the clustering procedure proposed in Reference [57], an ascending hierarchical clustering [59] is performed in order to gather the pure spectra. This clustering method is selected as it does not require to know the final number of classes beforehand.…”

Section: Heterogeneity-based Endmember Extraction (Hbee)mentioning

confidence: 99%

“…Its goal is to complete the first setŜ H of endmembers by extracting from mixed pixels the remaining P m endmembers applying a sequence of constrained NMFs to the HS image. This method is an improved version of the local iterative algorithm proposed in Reference [57] called Local semi-Supervised Non-negative Matrix Factorization, the main improvements being the use of constraints and a different initialization procedure. The algorithm is composed of two iteratively repeated parts.…”

Section: Local Constrained Non-negative Matrix Factorization (Lcnmf)mentioning

confidence: 99%

See 4 more Smart Citations

Using a Panchromatic Image to Improve Hyperspectral Unmixing

et al. 2020

Self Cite

View full text Add to dashboard Cite

Hyperspectral unmixing is a widely studied field of research aiming at estimating the pure material signatures and their abundance fractions from hyperspectral images. Most spectral unmixing methods are based on prior knowledge and assumptions that induce limitations, such as the existence of at least one pure pixel for each material. This work presents a new approach aiming to overcome some of these limitations by introducing a co-registered panchromatic image in the unmixing process. Our method, called Heterogeneity-Based Endmember Extraction coupled with Local Constrained Non-negative Matrix Factorization (HBEE-LCNMF), has several steps: a first set of endmembers is estimated based on a heterogeneity criterion applied on the panchromatic image followed by a spectral clustering. Then, in order to complete this first endmember set, a local approach using a constrained non-negative matrix factorization strategy, is proposed. The performance of our method, in regards of several criteria, is compared to those of state-of-the-art methods obtained on synthetic and satellite data describing urban and periurban scenes, and considering the French HYPXIM/HYPEX2 mission characteristics. The synthetic images are built with real spectral reflectances and do not contain a pure pixel for each endmember. The satellite images are simulated from airborne acquisition with the spatial and spectral features of the mission. Our method demonstrates the benefit of a panchromatic image to reduce some well-known limitations in unmixing hyperspectral data. On synthetic data, our method reduces the spectral angle between the endmembers and the real material spectra by 46% compared to the Vertex Component Analysis (VCA) and N-finder (N-FINDR) methods. On real data, HBEE-LCNMF and other methods yield equivalent performance, but, the proposed method shows more robustness over the data sets compared to the tested state-of-the-art methods. Moreover, HBEE-LCNMF does not require one to know the number of endmembers.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Roof Tilementioning

confidence: 99%

Section: Heterogeneity-based Endmember Extraction (Hbee)mentioning

confidence: 99%

Section: Heterogeneity-based Endmember Extraction (Hbee)mentioning

confidence: 99%

Section: Local Constrained Non-negative Matrix Factorization (Lcnmf)mentioning

confidence: 99%

See 3 more Smart Citations

Using a Panchromatic Image to Improve Hyperspectral Unmixing

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

Classification of Hyperspectral Reflectance Images With Physical and Statistical Criteria

Alakian

Achard

2020

Remote Sensing

View full text Add to dashboard Cite

A classification method of hyperspectral reflectance images named CHRIPS (Classification of Hyperspectral Reflectance Images with Physical and Statistical criteria) is presented. This method aims at classifying each pixel from a given set of thirteen classes: unidentified dark surface, water, plastic matter, carbonate, clay, vegetation (dark green, dense green, sparse green, stressed), house roof/tile , asphalt, vehicle/paint/metal surface and non-carbonated gravel. Each class is characterized by physical criteria (detection of specific absorptions or shape features) or statistical criteria (use of dedicated spectral indices) over spectral reflectance. CHRIPS input is a hyperspectral reflectance image covering the spectral range [400–2500 nm]. The presented method has four advantages, namely: (i) is robust in transfer, class identification is based on criteria that are not very sensitive to sensor type; (ii) does not require training, criteria are pre-defined; (iii) includes a reject class, this class reduces misclassifications; (iv) high precision and recall, F 1 score is generally above 0.9 in our test. As the number of classes is limited, CHRIPS could be used in combination with other classification algorithms able to process the reject class in order to decrease the number of unclassified pixels.

show abstract

A New Hyperspectral Unmixing Method Using Co-Registered Hyperspectral and Panchromatic Images

Cited by 2 publications

References 15 publications

Using a Panchromatic Image to Improve Hyperspectral Unmixing

Using a Panchromatic Image to Improve Hyperspectral Unmixing

Classification of Hyperspectral Reflectance Images With Physical and Statistical Criteria

Contact Info

Product

Resources

About