Category: Thesis

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. In this work, we propose to address this problem. Generative Adversarial Networks (GANs) are a […]

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 goes into them. Consequentially, feature representation learning has been explored extensively in the literature [1, […]

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 to classify pixels into one or other classes into images. Compared with supervised semantic segmentation […]

Abstract: Feature engineering often plays a vital role in the fields of computer vision and machine learning. A few common examples of engineered features include histogram of oriented gradients (HOG) , local binary patterns (LBP), and edge histogram descriptors (EHD). Features such as pixel gradient directions and magnitudes for HOG, encoded pixel differences for LBP, […]

Abstract: The domain of multi-look scene understanding problems includes scenarios where multiple passes over the same area have occurred and combining information from them is desired. For example, in remotely sensed SAS surveys, the same location on the seafloor is captured from multiple views where the UTM coordinates may not fully overlap. Additionally, error in […]

Abstract: Feature engineering often plays a vital role in the fields of computer vision and machine learning. A few common examples of engineered features include histogram of oriented gradients (HOG) (Dalal and Triggs, 2005), local binary patterns (LBP) (Ojala et al., 1994), and edge histogram descriptors (EHD) (Frigui and Gader, 2008). Features such as pixel […]

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 […]

Abstract: The adoption of remote sensing techniques in plant science enables noninvasive or minimally invasive measurement, which is also time and labor saving when compared to traditional field measurements. In this thesis, a method to distinguish switchgrass genotypes with the analysis of remotely-sensed hyperspectral imagery is proposed. A processing protocol for hyperspectral imagery including preprocessing, […]

Abstract: Automated anomaly and target detection are commonly used as a prescreening step within a larger target detection and target classification framework to find regions of interest for further analysis. Many anomaly and target detection algorithms in the literature have been developed for application to target detection in Synthetic Aperture Sonar (SAS) imagery which produces […]

Abstract: The Multiple Instance Adaptive Cosine Estimator and the Multiple Instance Subspace Match Filter are algorithms used in target detection, where a target class of interest is attempted to be detected amongst a non-target, background class. These algorithms learn a single feature vector representation to estimate a target class in a transformed feature space that […]