Kyle Bradbury

Conference Proceedings 2024 IEEE Winter Conference on Applications of Computer Vision Wacv 2024 · January 3, 2024 Recently, the first foundation model developed specifically for image segmentation tasks was developed, termed the "Segment Anything Model"(SAM). SAM can segment objects in input imagery based on cheap input prompts, such as one (or more) points, a boundin ... Full text Cite

Enhanced Remote Sensing Model Performance Through Self-Supervised Learning with Multi-Spectral Data

Conference International Geoscience and Remote Sensing Symposium IGARSS · January 1, 2024 Recently, self-supervised learning methods have shown remarkable performance rivaling supervised approaches, particularly in the realm of computer vision. This paper addresses a gap in current literature by focusing on the application of the SwAV (Swapping ... Full text Cite

Transformers For Recognition In Overhead Imagery: A Reality Check

Conference Proceedings 2023 IEEE Winter Conference on Applications of Computer Vision Wacv 2023 · January 1, 2023 There is evidence that transformers offer state-of-the-art recognition performance on tasks involving overhead imagery (e.g., satellite imagery). However, it is difficult to make unbiased empirical comparisons between competing deep learning models, making ... Full text Cite

Wind Turbine Detection with Synthetic Overhead Imagery

Conference International Geoscience and Remote Sensing Symposium IGARSS · January 1, 2021 Automatic object detection in overhead imagery is greatly increasing the pace at which we learn about anthropic activity across diverse fields such as economics, environmental management, and engineering. Properly-trained object detection models save signi ... Full text Cite

Do Deep Learning Models Generalize to Overhead Imagery from Novel Geographic Domains? the xGD Benchmark Problem

Conference International Geoscience and Remote Sensing Symposium IGARSS · September 26, 2020 Recently, Convolutional Neural Networks (CNNs) have demonstrated impressive performance on several visual recognition benchmark datasets utilizing overhead imagery. However, most of these analyses performed on benchmark datasets involve testing pre-trained ... Full text Cite

Mapping Electric Transmission Line Infrastructure from Aerial Imagery with Deep Learning

Conference International Geoscience and Remote Sensing Symposium IGARSS · September 26, 2020 Access to electricity positively correlates with many beneficial socioeconomic outcomes in the developing world including improvements in education, health, and poverty. Efficient planning for electricity access requires information on the location of exis ... Full text Cite

Designing Synthetic Overhead Imagery to Match a Target Geographic Region: Preliminary Results Training Deep Learning Models

Conference International Geoscience and Remote Sensing Symposium IGARSS · September 26, 2020 Convolutional Neural Networks (CNNs) have dominated performance on benchmark problems for object recognition in remote sensing imagery. However, recent work has shown that they may perform poorly when tested on imagery collected over a geographic location ... Full text Cite

The synthinel-1 dataset: A collection of high resolution synthetic overhead imagery for building segmentation

Conference Proceedings 2020 IEEE Winter Conference on Applications of Computer Vision Wacv 2020 · March 1, 2020 Recently deep learning - namely convolutional neural networks (CNNs) - have yielded impressive performance for the task of building segmentation on large overhead (e.g., satellite) imagery benchmarks. However, these benchmark datasets only capture a small ... Full text Cite

Training a single multi-class convolutional segmentation network using multiple datasets with heterogeneous labels: Preliminary results

Conference International Geoscience and Remote Sensing Symposium IGARSS · July 1, 2019 Segmentation convolutional neural networks (CNNs) are now popular for the semantic segmentation (i.e., dense pixel-wise labeling) of remote sensing imagery, such as color or hyperspectral satellite imagery. In recent years a large number of hand-labeled da ... Full text Cite

A simple rotational equivariance loss for generic convolutional segmentation networks: Preliminary results

Conference International Geoscience and Remote Sensing Symposium IGARSS · July 1, 2019 Segmentation convolutional neural networks (SCNNs) are now popular for the semantic segmentation (i.e., dense pixel-wise labeling) of remote sensing imagery, such as color or hyperspectral satellite imagery. One desirable property of SCNNs when applied to ... Full text Cite

Large-scale semantic classification: Outcome of the first year of inria aerial image labeling benchmark

Conference International Geoscience and Remote Sensing Symposium IGARSS · October 31, 2018 Over the recent years, there has been an increasing interest in large-scale classification of remote sensing images. In this context, the Inria Aerial Image Labeling Benchmark has been released online in December 2016. In this paper, we discuss the outcome ... Full text Cite

On the extraction of training imagery from very large remote sensing datasets for deep convolutional segmenatation networks

Conference International Geoscience and Remote Sensing Symposium IGARSS · October 31, 2018 In this work, we investigate strategies for training convolutional neural networks (CNNs) to perform recognition on remote sensing imagery. In particular we consider the particular problem of semantic segmentation in which the goal is to obtain a dense pix ... Full text Cite

Deep convolutional segmentation of remote sensing imagery: A simple and efficient alternative to stitching output labels

Conference International Geoscience and Remote Sensing Symposium IGARSS · October 31, 2018 In this work we consider the application of convolutional neural networks (CNNs) for the semantic segmentation of remote sensing imagery (e.g., aerial color or hyperspectral imagery). In segmentation the goal is to provide a dense pixel-wise labeling of th ... Full text Cite

Semisupervised adversarial discriminative domain adaptation, with application to remote sensing data

Conference International Geoscience and Remote Sensing Symposium IGARSS · October 31, 2018 Recently, convolutional neural networks (CNNs) have received substantial attention in the literature for object recognition (e.g., buildings and roads) in several remote sensing data modalities (e.g., aerial color imagery). Although CNNs have exhibited exc ... Full text Cite

Automated building energy consumption estimation from aerial imagery

Conference International Geoscience and Remote Sensing Symposium IGARSS · October 31, 2018 This paper presents a methodology for automatically estimating the energy consumption of buildings from aerial imagery using data from Gainesville, Florida. By detecting buildings in the imagery using convolutional neural networks and extracting features f ... Full text Cite

Non-intrusive load monitoring system performance over a range of low frequency sampling rates

Conference 2017 6th International Conference on Renewable Energy Research and Applications Icrera 2017 · December 12, 2017 Non-intrusive load monitoring (NILM) systems estimate the amount of energy each appliance consumes using as input the aggregate building energy consumption. Typically, NILM results are presented for a single sampling rate. To evaluate tradeoffs between end ... Full text Cite

Estimating the electricity generation capacity of solar photovoltaic arrays using only color aerial imagery

Conference International Geoscience and Remote Sensing Symposium IGARSS · December 1, 2017 In this work, the problem of developing algorithms that automatically infer information about small-scale solar photovoltaic (PV) arrays in high resolution aerial imagery is considered. Such algorithms potentially offer a faster and cheaper solution to col ... Full text Cite

Trading spatial resolution for improved accuracy when using detection algorithms on remote sensing imagery

Conference International Geoscience and Remote Sensing Symposium IGARSS · December 1, 2017 In this work, we consider the problem of detecting target objects in remote sensing imagery; such as detecting rooftops, trees, or cars in color/hyperspectral imagery. Many detection algorithms for this problem work by assigning a decision statistic (or 'c ... Full text Cite

A deep convolutional neural network, with pre-training, for solar photovoltaic array detection in aerial imagery

Conference International Geoscience and Remote Sensing Symposium IGARSS · December 1, 2017 In this work we consider the problem of developing algorithms that automatically identify small-scale solar photovoltaic arrays in high resolution aerial imagery. Such algorithms potentially offer a faster and cheaper solution to collecting small-scale pho ... Full text Cite

Trading spatial resolution for improved accuracy in remote sensing imagery: An empirical study using synthetic data

Conference Proceedings Applied Imagery Pattern Recognition Workshop · July 2, 2017 We consider the problem of detecting objects (such as trees, rooftops, roads, or cars) in remote sensing data including, for example, color or hyperspectral imagery. Many detection algorithms applied to this problem operate by assigning a decision statisti ... Full text Cite

The poor generalization of deep convolutional networks to aerial imagery from new geographic locations: An empirical study with solar array detection

Conference Proceedings Applied Imagery Pattern Recognition Workshop · July 2, 2017 Convolutional neural networks (CNNs) have recently achieved unprecedented performance for the automatic recognition of objects (e.g., buildings, roads, or vehicles) in color aerial imagery. Although these results are promising, questions remain about their ... Full text Cite

The poor generalization of deep convolutional networks to aerial imagery from new geographic locations: An empirical study with solar array detection

Performance comparison framework for energy disaggregation systems

Conference 2015 IEEE International Conference on Smart Grid Communications Smartgridcomm 2015 · March 17, 2016 Energy disaggregation algorithms decompose building-level energy data into device-level information. We conduct a head-To-head comparison of energy disaggregation techniques across multiple metrics and data sets. Our framework for analyzing the performance ... Full text Cite

A deep convolutional neural network and a random forest classifier for solar photovoltaic array detection in aerial imagery

Conference 2016 IEEE International Conference on Renewable Energy Research and Applications Icrera 2016 · January 1, 2016 Power generation from distributed solar photovoltaic PV arrays has grown rapidly in recent years. As a result, there is interest in collecting information about the quantity, power capacity, and energy generated by such arrays; and to do so over small geo- ... Full text Cite

Image features for pixel-wise detection of solar photovoltaic arrays in aerial imagery using a random forest classifier

Conference 2016 IEEE International Conference on Renewable Energy Research and Applications Icrera 2016 · January 1, 2016 Power generation from distributed solar photovoltaic (PV) arrays has grown rapidly in recent years. As a result, there is interest in collecting information about the quantity, power capacity, and energy generated by such arrays; and to do so over small ge ... Full text Cite

Automatic solar photovoltaic panel detection in satellite imagery

Conference 2015 International Conference on Renewable Energy Research and Applications Icrera 2015 · January 1, 2015 The quantity of rooftop solar photovoltaic (PV) installations has grown rapidly in the US in recent years. There is a strong interest among decision makers in obtaining high quality information about rooftop PV, such as the locations, power capacity, and e ... Full text Cite

Realtime gaussian markov random field based ground tracking for ground penetrating radar data

Conference Proceedings of SPIE the International Society for Optical Engineering · September 8, 2009 Current ground penetrating radar algorithms for landmine detection require accurate estimates of the location of the air/ground interface to maintain high levels of performance. However, the presence of surface clutter, natural soil roughness, and antenna ... Full text Cite

Covert binary communications through the application of chaos theory: Three novel approaches

Conference Citsa 2007 Int Conference on Cybernetics and Information Technologies Systems and Applications and Ccct 2007 Int Conference on Computing Communications and Control Technologies Proceedings · December 1, 2007 Today, most covert communications systems use a spread-spectrum approach to ensure that transmissions remain clandestine. This paper expands beyond traditional spread-spectrum schemes and into chaos theory in communications by presenting a novel design for ... Cite