Abstract: The Possibilistic Fuzzy Local Information C-Means (PFLICM) method is presented as a technique to segment side-look synthetic aperture sonar (SAS) imagery into distinct regions of the sea-floor. In this work, we investigate and present the results of an automated… Read More
Author: weihuang.xu@ufl.edu
Congrats to Xiaoxiao for new position as a Senior Research Engineer at the University of Michigan
Congratulations to our lab alumna, Dr. Xiaoxiao Du, on her new appointment as a Senior Research Engineer at the University of Michigan! Dr. Du will be working on machine learning and computer vision methods for pedestrian perception and scene understanding.… Read More
Multiple Instance Choquet Integral Classifier Fusion and Regression for Remote Sensing Applications
Abstract: In classifier (or regression) fusion the aim is to combine the outputs of several algorithms to boost overall performance. Standard supervised fusion algorithms often require accurate and precise training labels. However, accurate labels may be difficult to obtain in… Read More
Drought Symposium at Colorado State University
Don’t miss the Drought Symposium at Colorado State University on June 21/22! Speakers include Detlef Weigel, Malia Gehan, Duke Pauli, Alina Zare, Brook Moyers, William Beavis, Chris Topp, and Mike Olsen. Alina Zare will discuss machine learning methods for phenotyping.
Congrats to Dr. Alina Zare for being selected as a 2018 SPIE rising researcher
Congratulations to Dr. Alina Zare for being selected as a SPIE DCS 2018 Rising Researcher. The SPIE DCS Rising Researcher program is designed to recognize early career professionals (received terminal degree within the past 10 years) who are conducting outstanding… Read More
Congratulations to Jefferey Hornbeck for obtaining an internship at Amazon!
Congratulations to our labmate Jefferey Hornbeck! He will be starting a three-month internship at Amazon in Seattle, Washington in the Spring 2018 semester. He will work as a member of the AWS (Amazon Web Services) networking team. Good Luck Jeffery!… 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 Choquet Integral For MultiResolution Sensor Fusion
Abstract: Imagine you are traveling to Columbia,MO for the first time. On your flight to Columbia, the woman sitting next to you recommended a bakery by a large park with a big yellow umbrella outside. After you land, you need… Read More
Congratulations to Changzhe Jiao for obtaining an internship at Mitsubishi Electric Research Lab!
Changzhe Jiao, a member of our lab, began an internship at Mitsubishi Electric Research Lab on November 6th! His research at Mitsubishi will focus on the compression and reconstruction of remote sensing data with methods like block adaptive quantization and… 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