Tag: deep convolutional neural networks

OUTLIER DETECTION THROUGH NULL SPACE ANALYSIS OF NEURAL NETWORKS

Abstract: Many machine learning classification systems lack competency awareness. Specifically, many systems lack the ability to identify when outliers (e.g., samples that are distinct from and not represented in the training data distribution) are being presented to the system. The… Read More

OVERCOMING SMALL DATASETS PUBLISHED IN COMPUTERS AND ELECTRONICS IN AGRICULTURE!

Congratulations to our labmates, Weihuang Xu, Guohao Yu and Alina Zare, as well as collaborators Brenden Zurweller, Diane Rowland, Joel Reyes-Cabrera, Felix Fritschi, Roser Matamala and Thomas Juenger!  Their paper, “Overcoming Small Minirhizotron Datasets Using Transfer Learning”, was published in… Read More

Super Resolution for Root Imaging

Abstract: High-resolution cameras have become very helpful for plant phenotyping by providing a mechanism for tasks such as target versus background discrimination, and the measurement and analysis of fine-above-ground plant attributes. However, the acquisition of high-resolution (HR) imagery of plant… Read More

Master’s Defenses!

Congratulations to our labmates, Hudanyun Sheng and Princess Lyons, for successful Master’s defenses!   Hudanyun conducted work on “Switchgrass Genotype Classification using Hyperspectral Imagery”, while Princess investigated  “Anomaly and Target Detection in Synthetic Aperture Sonar”. Great job, you two!

Congratualtions to Guohao Yu for a Successful Proposal Defense!

Congratulations to our labmate Guahao Yu for successfully defending his research proposal!  Defending an oral research proposal is the second of four milestones to completing a Ph.D. at the University of Florida.  Guohao is planning to advance image segmentation techniques… Read More

Deep convolutional neural network target classification for underwater synthetic aperture sonar imagery

Abstract: In underwater synthetic aperture sonar (SAS) imagery, there is a need for accurate target recognition algorithms. Automated detection of underwater objects has many applications, not the least of which being the safe extraction of dangerous explosives. In this paper,… Read More

A fully learnable context-driven object-based model for mapping land cover using multi-view data from unmanned aircraft systems

Abstract: Context information is rarely used in the object-based landcover classification. Previous models that attempted to utilize this information usually required the user to input empirical values for critical model parameters, leading to less optimal performance. Multi-view image information is… Read More