Dr. Heesung Kwon Profile

Dr. Heesung Kwon

Electronic Engineer at DEVCOM Army Research Lab

SPIE Involvement:

Author

Publications (36)

Proceedings Article | 6 June 2022 Poster + Paper

Archangel dataset: UAV-based imagery with position and pose metadata

Damon Conover, Eung-Joo Lee, Yaesop Lee, Shuvra Bhattacharyya, Heesung Kwon, G. Jeremy Leong, Jason Hill, Kenneth Evensen, Yi-Ting Shen

Proceedings Volume 12113, 121131T (2022) https://doi.org/10.1117/12.2618636

KEYWORDS: Unmanned aerial vehicles, Performance modeling, Target detection, Cameras, Machine learning, Analytical research

Read Abstract +

Proceedings Article | 27 May 2022 Presentation + Paper

Object detection on resource-constrained platforms using a configurable ensemble of detectors

Alexander Mattingly, Jing Xie, Heesung Kwon, Shuvra Bhattacharyya, Eung-Joo Lee

Proceedings Volume 12102, 121020C (2022) https://doi.org/10.1117/12.2618342

KEYWORDS: Image processing, Detection and tracking algorithms, Computing systems, Unmanned aerial vehicles, Signal processing, Prototyping, Performance modeling

Read Abstract +

Proceedings Article | 12 April 2021 Presentation + Paper

Validation of object detection in UAV-based images using synthetic data

Eung-Joo Lee, Heesung Kwon, Shuvra Bhattacharyya, Jason Hill, Kenneth Evensen, Damon Conover

Proceedings Volume 11746, 117462A (2021) https://doi.org/10.1117/12.2586860

KEYWORDS: Unmanned aerial vehicles, Eye models, Performance modeling, Neural networks, Data modeling, Cameras, Machine learning, Eye

Read Abstract +

Proceedings Article | 21 April 2020 Presentation + Paper

An optimal end-to-end training strategy for multi-expert-based neural architecture

Hyungtae Lee, Heesung Kwon

Proceedings Volume 11413, 114130L (2020) https://doi.org/10.1117/12.2558553

KEYWORDS: Network architectures, Optimization (mathematics), Image processing, Data modeling, Performance modeling, Computer architecture, Machine learning, Neodymium, Feature extraction, Analytical research

Read Abstract +

Proceedings Article | 14 May 2019 Presentation

Improving unmanned aerial vehicle-based object detection via adversarial training: a (almost) free lunch to enjoy (Conference Presentation)

Zhenyu Wu, Karthik Suresh, Zhangyang Wang, Priya Narayanan, Heesung Kwon

Proceedings Volume 11006, 110061B (2019) https://doi.org/10.1117/12.2518835

KEYWORDS: Unmanned aerial vehicles, Surveillance, Agriculture, Photography, Cameras

Read Abstract +

Proceedings Article | 10 May 2019 Paper

Overview of machine learning (ML) based perception algorithms for unstructured and degraded visual environments

Zhenyu Wu, Priya Narayanan, Heesung Kwon, Zhangyang Wang, Raghuveer Rao

Proceedings Volume 11006, 110061T (2019) https://doi.org/10.1117/12.2519029

KEYWORDS: Algorithm development, Visualization, Detection and tracking algorithms, Cameras, Video, Neural networks, Machine learning, Light sources and illumination, Data modeling, Roads

Read Abstract +

Proceedings Article | 10 May 2019 Paper

How to practically deploy deep neural networks to distributed network environments for scene perception

Hyungtae Lee, Heesung Kwon

Proceedings Volume 11006, 110061R (2019) https://doi.org/10.1117/12.2519885

KEYWORDS: Image classification, Neural networks, Network architectures, Image segmentation, Object recognition, Analytical research

Read Abstract +

Proceedings Article | 27 April 2018 Paper

Going deeper with CNN in malicious crowd event classification

Hyungtae Lee, Sungmin Eum, Heesung Kwon

Proceedings Volume 10646, 1064616 (2018) https://doi.org/10.1117/12.2306086

KEYWORDS: Image classification, Network architectures, Convolution, Visualization, Classification systems, Tumor growth modeling, Convolutional neural networks, Image enhancement, Facial recognition systems, Data modeling

Read Abstract +

Proceedings Article | 27 April 2018 Presentation + Paper

A real-time object detection framework for aerial imagery using deep neural networks and synthetic training images

Priya Narayanan, Christoph Borel-Donohue, Hyungtae Lee, Heesung Kwon, Raghuveer Rao

Proceedings Volume 10646, 1064614 (2018) https://doi.org/10.1117/12.2306154

KEYWORDS: Neural networks, Airborne remote sensing, Unmanned aerial vehicles, Machine vision, Computer vision technology, Video surveillance, Video, Situational awareness sensors, Object recognition, Surveillance

Read Abstract +

Proceedings Article | 25 May 2016 Paper

Single-trial EEG RSVP classification using convolutional neural networks

Hyungtae Lee, Heesung Kwon, Amar Marathe, Vernon Lawhern, William Nothwang, Jared Shamwell

Proceedings Volume 9836, 983622 (2016) https://doi.org/10.1117/12.2224172

KEYWORDS: Convolutional neural networks, Electroencephalography, Data modeling, Visualization, Signal to noise ratio, Visual process modeling, Machine vision, Performance modeling, Convolution, Data fusion

Read Abstract +

Proceedings Article | 25 May 2016 Paper

An efficient fusion approach for combining human and machine decisions

Hyungtae Lee, Heesung Kwon, Ryan Robinson, William Nothwang, Amar Marathe

Proceedings Volume 9836, 983621 (2016) https://doi.org/10.1117/12.2220788

KEYWORDS: Sensors, Probability theory, Target detection, Sensor performance, Image fusion, Detection and tracking algorithms, Machine vision, Computer vision technology, Analytical research, Composites, Chemical elements

Read Abstract +

Proceedings Article | 20 June 2014 Paper

Thermal-to-visible face recognition using multiple kernel learning

Shuowen Hu, Prudhvi Gurram, Heesung Kwon, Alex Chan

Proceedings Volume 9091, 909110 (2014) https://doi.org/10.1117/12.2051033

KEYWORDS: Facial recognition systems, Visible radiation, Mid-IR, Neodymium, Feature extraction, Thermography, Short wave infrared radiation, Long wavelength infrared, Optical filters, Databases

Read Abstract +

Proceedings Article | 24 May 2012 Paper

Kernel-based joint spectral and spatial exploitation using Hilbert space embedding for hyperspectral classification

Heesung Kwon, Prudhvi Gurram

Proceedings Volume 8390, 83901R (2012) https://doi.org/10.1117/12.918338

KEYWORDS: Composites, Hyperspectral imaging, Associative arrays, Data modeling, Algorithm development, Spectroscopy, Spatial resolution, Spectral resolution, Analytical research, Image processing

Read Abstract +

Proceedings Article | 5 May 2012 Paper

Classification of Shiga toxin-producing escherichia coli (STEC) serotypes with hyperspectral microscope imagery

Seung-Chul Yoon, Prudhvi Gurram, Scott Ladely, William Windham, Bosoon Park, Kurt Lawrence, Heesung Kwon, William Cray, Neelam Narang

Proceedings Volume 8369, 83690L (2012) https://doi.org/10.1117/12.919695

KEYWORDS: Microscopes, Hyperspectral imaging, Pathogens, Glasses, Bacteria, Image classification, Imaging systems, Image acquisition, Scattering, Crystals

Read Abstract +

Proceedings Article | 20 May 2011 Paper

Hyperspectral anomaly detection using sparse kernel-based ensemble learning

Prudhvi Gurram, Timothy Han, Heesung Kwon

Proceedings Volume 8048, 80481C (2011) https://doi.org/10.1117/12.883383

KEYWORDS: Hyperspectral imaging, Niobium, Detection and tracking algorithms, Target detection, Sensors, Data modeling, Digital imaging, Roads, Image classification, Binary data

Read Abstract +

Proceedings Article | 13 May 2010 Paper

Use of ensemble learning technique for detection/identification of chemical plumes

Patrick Rauss, Heesung Kwon

Proceedings Volume 7695, 76951T (2010) https://doi.org/10.1117/12.850039

KEYWORDS: Sensors, Algorithm development, Palladium, Chemical analysis, Image processing, Detection and tracking algorithms, Visualization, Hyperspectral imaging, Neural networks, Absorption

Read Abstract +

Proceedings Article | 13 May 2010 Paper

Ensemble learning based on multiple kernel learning for hyperspectral chemical plume detection

Prudhvi Gurram, Heesung Kwon

Proceedings Volume 7695, 76951U (2010) https://doi.org/10.1117/12.850101

KEYWORDS: Hyperspectral imaging, Binary data, Chemical analysis, Matrices, Image processing, Data centers, FT-IR spectroscopy, Long wavelength infrared, Artificial neural networks, Machine learning

Read Abstract +

Recently, a SVM-based ensemble learning technique has been introduced by the authors for hyperspectral plume detection/classification. The SVM-based ensemble learning consists of a number of SVM classifiers and the decisions from these sub-classifiers are combined to generate a final ensemble decision. The SVM-based ensemble technique first randomly selects spectral feature subspaces from the input data. Each individual classifier then independently conducts its own learning within its corresponding spectral feature space. Each classifier constitutes a weak classifier. These weak classifiers are combined to make an ensemble decision. The ensemble learning technique provides better performance than the conventional single SVM in terms of error rate. Various aggregating techniques like bagging, boosting, majority voting and weighted averaging were used to combine the weak classifiers, of which majority voting was found to be most robust. Yet, the ensemble of SVMs is suboptimal. Techniques that optimally weight the individual decisions from the sub-classifiers are strongly desirable to improve ensemble learning performance. In the proposed work, a recently introduced kernel learning technique called Multiple Kernel Learning (MKL) is used to optimally weight the kernel matrices of the sub-SVM classifiers. MKL basically iteratively performs l2 optimization on the Euclidian norm of the normal vector of the separating hyperplane between the classes (background and chemical plume) defined by the weighted kernel matrix followed by gradient descent optimization on the l1 regularized weighting coefficients of the individual kernel matrices. Due to l1 regularization on the weighting coefficients, the optimized weighting coefficients become sparse. The proposed work utilizes the sparse weighting coefficients to combine decision results of the SVM-based ensemble technique. A performance comparison between the aggregating techniques - MKL and majority voting as applied to hyperspectral chemical plume detection is presented in the paper.

SPIE Journal Paper | 1 August 2007

Change detection methods for identification of mines in synthetic aperture radar imagery

Nasser Nasrabadi, Maria Tates, Heesung Kwon

JARS, Vol. 1, Issue 01, 013525, (August 2007) https://doi.org/10.1117/12.10.1117/1.2776947

KEYWORDS: Synthetic aperture radar, Speckle, Surface plasmons, Land mines, Error analysis, Mining, Distance measurement, Image processing, Signal processing, Image registration

Read Abstract +

Proceedings Article | 18 May 2006 Paper

Multiband anomaly detection using signal subspace processing

Kenneth Ranney, Heesung Kwon, Mehrdad Soumekh

Proceedings Volume 6217, 62172Y (2006) https://doi.org/10.1117/12.665967

KEYWORDS: Detection and tracking algorithms, Digital filtering, Signal processing, Signal detection, Algorithm development, Electronic filtering, Sensors, Optical filters, Target detection, Synthetic aperture radar

Read Abstract +

Proceedings Article | 17 May 2006 Paper

Wiener filter-based change detection for SAR imagery

Nasser Nasrabadi, Heesung Kwon, Maria Tates, Carl White

Proceedings Volume 6237, 62370N (2006) https://doi.org/10.1117/12.665945

KEYWORDS: Synthetic aperture radar, Electronic filtering, Filtering (signal processing), Mahalanobis distance, Image filtering, Mining, Land mines, Detection and tracking algorithms, Speckle, Error analysis

Read Abstract +

Proceedings Article | 4 May 2006 Paper

Kernel canonical correlation analysis for hyperspectral anomaly detection

Nasser Nasrabadi, Heesung Kwon

Proceedings Volume 6233, 623303 (2006) https://doi.org/10.1117/12.664112

KEYWORDS: Simulation of CCA and DLA aggregates, Canonical correlation analysis, Hyperspectral imaging, Sensors, Detection and tracking algorithms, Target detection, Nonlinear dynamics, Hyperspectral target detection, Correlation function, Roads

Read Abstract +

Proceedings Article | 20 February 2006 Paper

Kernel subspace matched target detectors

Nasser Nasrabadi, Heesung Kwon

Proceedings Volume 6064, 60641A (2006) https://doi.org/10.1117/12.655689

KEYWORDS: Sensors, Target detection, Signal detection, Nonlinear filtering, Optical filters, Detection and tracking algorithms, Single mode fibers, Associative arrays, Hyperspectral target detection, Hyperspectral imaging

Read Abstract +

Proceedings Article | 1 June 2005 Paper

Kernel RX: a new nonlinear anomaly detector

Heesung Kwon, Nasser Nasrabadi

Proceedings Volume 5806, (2005) https://doi.org/10.1117/12.601834

KEYWORDS: Target detection, Sensors, Detection and tracking algorithms, Data modeling, Hyperspectral imaging, Hyperspectral target detection, Principal component analysis, Statistical analysis, Signal processing, Infrared imaging

Read Abstract +

Proceedings Article | 1 June 2005 Paper

A comparative study of kernel spectral matched signal detectors for hyperspectral target detection

Nasser Nasrabadi, Heesung Kwon

Proceedings Volume 5806, (2005) https://doi.org/10.1117/12.602182

KEYWORDS: Sensors, Signal detection, Target detection, Nonlinear filtering, Hyperspectral target detection, Optical filters, Detection and tracking algorithms, Associative arrays, Hyperspectral imaging, Single mode fibers

Read Abstract +

SPIE Journal Paper | 1 August 2004

Adaptive target detection in forward-looking infrared imagery using the eigenspace separation transform and principal component analysis

S. Susan Young, Heesung Kwon, Sandor Der, Nasser Nasrabadi

OE, Vol. 43, Issue 08, (August 2004) https://doi.org/10.1117/12.10.1117/1.1768534

KEYWORDS: Target detection, Forward looking infrared, Detection and tracking algorithms, Principal component analysis, Databases, Image filtering, Image processing, Optical engineering, Image enhancement, Solids

Read Abstract +

SPIE Journal Paper | 1 November 2003

Adaptive anomaly detection using subspace separation for hyperspectral imagery

Heesung Kwon, Sandor Der, Nasser Nasrabadi

OE, Vol. 42, Issue 11, (November 2003) https://doi.org/10.1117/12.10.1117/1.1614265

KEYWORDS: Principal component analysis, Hyperspectral imaging, Sensors, Target detection, Detection and tracking algorithms, Matrices, Ferroelectric LCDs, Hyperspectral target detection, Optical engineering, Automatic target recognition

Proceedings Article | 16 September 2003 Paper

Adaptive target detection in FLIR imagery using the eigenspace separation transform and principal component analysis

Nasser Nasrabadi, Sandor Der, Heesung Kwon, S. Young

Proceedings Volume 5094, (2003) https://doi.org/10.1117/12.487625

KEYWORDS: Principal component analysis, Detection and tracking algorithms, Target detection, Forward looking infrared, Databases, Image filtering, Image processing, Linear filtering, Solar energy, Automatic target recognition

Read Abstract +

Proceedings Article | 16 September 2003 Paper

Dual-window-based anomaly detection for hyperspectral imagery

Nasser Nasrabadi, Sandor Der, Heesung Kwon

Proceedings Volume 5094, (2003) https://doi.org/10.1117/12.486056

KEYWORDS: Hyperspectral imaging, Sensors, Principal component analysis, Detection and tracking algorithms, Target detection, Hyperspectral target detection, Ferroelectric LCDs, Automatic target recognition, Infrared sensors, Image sensors

Read Abstract +

SPIE Journal Paper | 1 January 2002

Adaptive multisensor target detection using feature-based fusion

Heesung Kwon, Sandor Der, Nasser Nasrabadi

OE, Vol. 41, Issue 01, (January 2002) https://doi.org/10.1117/12.10.1117/1.1425788

KEYWORDS: Image fusion, Target detection, Image processing, Infrared sensors, Sensors, Infrared imaging, Feature extraction, Optical engineering, Automatic target recognition, Cameras

Proceedings Article | 22 October 2001 Paper

Multisensor target detection using adaptive feature-based fusion

Nasser Nasrabadi, Sandor Der, Heesung Kwon

Proceedings Volume 4379, (2001) https://doi.org/10.1117/12.445357

KEYWORDS: Image fusion, Target detection, Infrared imaging, Automatic target recognition, Infrared sensors, Sensors, Optical sensors, Feature extraction, Image processing, Infrared radiation

Read Abstract +

Proceedings Article | 29 December 2000 Paper

Unsupervised segmentation algorithm based on an iterative spectral dissimilarity measure for hyperspectral imagery

Nasser Nasrabadi, Sandor Der, Heesung Kwon

Proceedings Volume 4310, (2000) https://doi.org/10.1117/12.411792

KEYWORDS: Image segmentation, Hyperspectral imaging, Image processing algorithms and systems, Iterative methods, Detection and tracking algorithms, Imaging systems, Analytical research, Roads, Image processing, Hyperspectral target detection

Read Abstract +

Proceedings Article | 1 October 1999 Paper

Use of hyperspectral imagery for material classification in outdoor scenes

Nasser Nasrabadi, Hyeonjoon Moon, Heesung Kwon, Sandor Der

Proceedings Volume 3804, (1999) https://doi.org/10.1117/12.363954

KEYWORDS: Image segmentation, Hyperspectral imaging, Principal component analysis, Vegetation, Prototyping, Imaging systems, Infrared imaging, Thermography, Image processing, Image classification

Read Abstract +

SPIE Journal Paper | 1 October 1998

Multiscale video compression using adaptive finite-state vector quantization

Heesung Kwon, Mahesh Venkatraman, Nasser Nasrabadi

JEI, Vol. 7, Issue 04, (October 1998) https://doi.org/10.1117/12.10.1117/1.482660

KEYWORDS: Computer programming, Video, Video coding, Video compression, Quantization, Image compression, Neural networks, Signal to noise ratio, Digital imaging, Neurons

Proceedings Article | 3 April 1997 Paper

Very low bit rate compression for one-to-N video broadcast

Heesung Kwon, Nasser Nasrabadi, Mahesh Venkatraman

Proceedings Volume 3078, (1997) https://doi.org/10.1117/12.271765

KEYWORDS: Video compression, Video, Quantization

Read Abstract +

Proceedings Article | 10 January 1997 Paper

Compression of SAR imagery using adaptive residual vector quantization

Nasser Nasrabadi, Heesung Kwon, Mahesh Venkatraman

Proceedings Volume 3024, (1997) https://doi.org/10.1117/12.263293

KEYWORDS: Quantization, Image compression, Detection and tracking algorithms, Synthetic aperture radar, Computer programming, Distortion, Neural networks, Image processing, Signal processing, Target detection

Read Abstract +

Proceedings Article | 10 June 1996 Paper

High compression of SAR imagery for battlefield surveillance

Joseph Sattler, Heesung Kwon, Syed Rizvi, Nasser Nasrabadi

Proceedings Volume 2757, (1996) https://doi.org/10.1117/12.242052

KEYWORDS: Image compression, Synthetic aperture radar, Computer programming, Distortion, Detection and tracking algorithms, Quantization, Wavelets, Image resolution, Surveillance, Algorithm development

Read Abstract +

Showing 5 of 36 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years