Tag: hyperspectral

Abstract: In many remote sensing and hyperspectral image analysis applications, precise ground truth information is unavailable or impossible to obtain. Imprecision in ground truth often results from highly mixed or sub-pixel spectral responses over classes of interest, a mismatch between the precision of global positioning system (GPS) units and the spatial resolution of collected imagery, and misalignment […]

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 of the Function of Multiple Instances approach (FUMI). Additional details can be found in the […]

Congratulations to our labmates and collaborators: Ben Weinstein, Sarah Graves, Sergio Marconi, Aditya Singh, Alina Zare, Dylan Stewart, Stephanie Bohlman and Ethan P. White!  Their paper, “A benchmark dataset for individual tree crown delineation in co-registered airborne RGB, LiDAR and hyperspectral imagery from the National Ecological Observation Network”, was recently accepted to PLOS Computational Biology.  […]

Abstract: Imprecise labels or label uncertainty are common problems in many real supervised and semi-supervised learning problems. However, most of the state-of-the-art supervised learning methods in the literature rely on accurate labels. Accurate labels are often either expensive, time-consuming, or even impossible to obtain in many real applications. There are many approaches in the literature […]

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 recently accepted to the IEEE Geoscience and Remote Sensing Magezine. In their paper, the authors […]

Congratulations to our labmates: Susan K. Meerdink, James Bocinsky, Alina Zare, Nick Kroeger, Connor H. McCurley, Daniel Shats and Paul D. Gader!  Their paper, “Multi-Target Multiple Instance Learning for Hyperspectral Target Detection” was recently accepted to IEEE Transactions on Geoscience and Remote Sensing (TGRS).   In their paper, the authors introduce an approach to estimate multiple […]

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 resulting in limited capacity to improve product quality eventually leading to food loss and waste. […]

Abstract: Broad scale remote sensing promises to build forest inventories at unprecedented scales. A crucial step in this process is designing individual tree segmentation algorithms to associate pixels into delineated tree crowns. While dozens of tree delineation algorithms have been proposed, their performance is typically not compared based on standard data or evaluation metrics, making […]

  Dylan Stewart recently presented as a guest speaker for Stevenson Elementary School’s “Engineering Week”.  During his presentation, Dylan showed a class of Russellville, KY first graders how he flies drones to “help farmers find healthy and dead plants”.  Additionally, Dylan fielded a variety of questions about a “day in the life” of a PhD […]

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 is as easy as hitting pip install SPICE-HSI in your python terminal or conda install […]