MATLAB implementation of Multi-target Extended Functions of Multiple Instances has been made public! It is available in our GitHub repository MT_eFUMI MT_eFUMI is capable of learning multiple target spectral signatures from weakly- and inaccurately-labeled hyperspectral imagery. It is a generalization… Read More
Tag: unmixing
SPECTRAL VARIABILITY IN HSI ACCEPTED TO GRSM!
Congratulations to our labmates and collaborators: Ricardo Augusto Borsoi, Tales Imbiriba, Jose Carlos Moreira Bermudez, Cedric Richard, Jocelyn Chanussot, Lucas Drumets, Jean-Yves Tourneret, Alina Zare and Christian Jutten! Their publication, “Spectral Variability in Hyperspectral Data Unmixing: A Comprehensive Review” was… Read More
EVALUATION OF POSTHARVEST SENESCENCE IN BROCCOLI VIA HYPERSPECTRAL IMAGING
Abstract: Fresh fruit and vegetables are invaluable for human health; however, their quality often deteriorates before reaching consumers due to ongoing biochemical processes and compositional changes. We currently lack any objective indices which indicate the freshness of fruit or vegetables… Read More
SPICE IS NOW AVAILABLE IN ANACONDA!
Sparsity Promoting Iterated Constrained Endmemebers (SPICE) is now installable with conda! SPICE is an algorithm for finding hyperspectral endmembers and corresponding proportions for a scene. The Python implementation can now be installed easily from PyPI or through the conda-forge. Installation… Read More
Spectral Variability in Hyperspectral Data Unmixing: A Comprehensive Review
Abstract: The spectral signatures of the materials contained in hyperspectral images (HI), also called endmembers (EM), can be significantly affected by variations in atmospheric, illumination or environmental conditions typically occurring within an HI. Traditional spectral unmixing (SU) algorithms neglect the… Read More
Target Concept Learning From Ambiguously Labeled Data
Abstract: The multiple instance learning problem addresses the case where training data comes with label ambiguity, i.e., the learner has access only to inaccurately labeled data. For example, in target detection from remotely sensed hyperspectral imagery, targets are usually sub-pixel… Read More
Multiple Instance Hybrid Estimator for Hyperspectral Target Characterization and Sub-pixel Target Detection
Abstract: The Multiple Instance Hybrid Estimator for discriminative target characterization from imprecisely labeled hyperspectral data is presented. In many hyperspectral target detection problems, acquiring accurately labeled training data is difficult. Furthermore, each pixel containing target is likely to be a… Read More
Hyperspectral Unmixing with Endmember Variability using Semi-supervised Partial Membership Latent Dirichlet Allocation
Abstract: A semi-supervised Partial Membership Latent Dirichlet Allocation approach is developed for hyperspectral unmixing and endmember estimation while accounting for spectral variability and spatial information. Partial Membership Latent Dirichlet Allocation is an effective approach for spectral unmixing while representing spectral… Read More
Classification Label Map for MUUFL Gulfport Released!
We are excited to announce that we have released a classification label map for the MUUFL Gulfport co-registered hyperspectral and Lidar Campus 1 image . The MUUFL Gulfport data set was collected in November 2010 over the campus of the… Read More
Map-guided Hyperspectral Image Superpixel Segmentation Using Proportion Maps
Abstract: A map-guided superpixel segmentation method for hyperspectral imagery is developed and introduced. The proposed approach develops a hyperspectral-appropriate version of the SLIC superpixel segmentation algorithm, leverages map information to guide segmentation, and incorporates the semi-supervised Partial Membership Latent Dirichlet… Read More