Abstract: During automatic target recognition once a detector has found points of interest the classifier is then tasked with identifying target objects from non-target objects. However, occasionally the detector may find something that is neither known false alarm nor expected… Read More
PublicationPublication
Segmentation Pseudo-label Generation using the Multiple Instance Learning Choquet Integral
Abstract: Weakly supervised target detection and semantic segmentation (WSSS) approaches aim at learning object or pixel level classification labels from imprecise, uncertain, or ambiguous data annotations. A crucial step in WSSS is to produce pseudolabels which can be used to… Read More
HyperPRI: A Dataset of Hyperspectral Images for Underground Plant Root Study
Abstract: Collecting and analyzing hyperspectral imagery (HSI) of plant roots over time can enhance our understanding of their function, responses to environmental factors, turnover, and relationship with the rhizosphere. Current belowground red-green-blue (RGB) root imaging studies infer such functions from… Read More
Individual tree crown maps for the National Ecological Observatory Network
Abstract: The ecology of forest ecosystems depends on the composition of trees. Capturing fine-grained information on individual trees at broad scales allows an unprecedented view of forest ecosystems, forest restoration and responses to disturbance. To create detailed maps of tree… Read More
Hyperspectral image analysis for the evaluation of chilling injury in avocado fruit during cold storage
Abstract: Many vegetables and fruit are sensitive to storage at lower temperatures and experience chilling injury that can result in internal disorder, leading to postharvest waste and economic loss. Most tropical and subtropical fruit, such as avocado and mango, are… Read More
Robust GANs for Semi-Supervised Classification
Abstract: Semi-supervised learning attempts to take advantage of the large amount of unlabeled information present in many datasets. However, unlabeled data will often contain samples outside the classes of interest. Many existing semi-supervised learning methods do not address this issue.… Read More
Capturing long-tailed individual tree diversity using an airborne imaging and a multi-temporal hierarchical model
Abstract: Measuring forest biodiversity using terrestrial surveys is expensive and can only capture common species abundance in large heterogeneous landscapes. In contrast, combining airborne imagery with computer vision can generate individual tree data at the scales of hundreds of thousands… Read More
Discriminative Feature Learning with Imprecise, Uncertain, and Ambiguous Data
Abstract: Target detection is a paramount task in remote sensing which aims to detect points of interest from a set of data. A crucial aspect attributed to the success of target detection methods is the representation of the data which… Read More
Spatial and Texture Analysis of Root System distribution with Earth mover’s Distance (STARSEED)
Abstract: Root system architectures are complex and challenging to characterize effectively for agronomic and ecological discovery. We propose a new method, Spatial and Texture Analysis of Root System distribution with Earth mover’s Distance (STARSEED), for comparing root system distributions that… Read More
Weakly Supervised Image Segmentation with Multiple Instance Learning Neural Network
Abstract: In my dissertation, we present multiple instance learning U-net (MILUnet) algorithm and multiple instance learning class activation map (MILCAM) algorithm for weakly supervised semantic segmentation. Both the MILUnet and MILCAM algorithms requires only training images paired with image-level label… Read More