Peter Zulch
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Peter Zulch has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Erik Blasch
Air Force Research Laboratory
2 shared publications Genshe Chen
Intelligent Fusion Technology, Inc.,Germantown,MD,20876
2 shared publicationsJingyang Lu
Intelligent Fusion Technology, Inc.,Germantown,MD,20876
2 shared publications- Ruixin Niu
Virginia Commonwealth University
2 shared publications - Zhonghai Wang
College of Physics, Key Laboratory of Radiation Physics and Technology, Ministry of Education, Sichuan University, Chengdu, 610064, China
2 shared publications Asad Vakil
Oakland University, Rochester, MI, USA
1 shared publication
Latest Publications
- 7 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Aerospace and Electronic Systems Magazine
- Vol. 36 (7) , 44-61
A Survey of Multimodal Sensor Fusion for Passive RF and EO Information Integration
Integrating information collected by different types of sensors observing the same or related phenomenon can lead to more accurate and robust decision making. The purpose of this article is to review sensor fusion approaches to achieve passive radio frequency (RF) and electro-optical (EO) sensor fusion and to present the proposed fusion of EO/RF neural network (FERNN). While research has been conducted to integrate complementary data collected by EO and RF modalities, the processing of RF data usually applies traditional features, such as Doppler. This article explores the viability of using the histogram of I/Q (in-phase and quadrature) data for the purposes of augmenting the detection accuracy that EO input alone is incapable of achieving. Specifically, by processing the histogram of I/Q data via deep learning and enhancing feature input for neural network fusion. Using the simulated data from the Digital Imaging and Remote Sensing Image Generation dataset, FERNN can achieve 95% accuracy in vehicle detection and scenario categorization, which is a 23% improvement over the accuracy achieved by a stand-alone EO sensor.
- 7 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Aerospace and Electronic Systems Magazine
- Vol. 36 (7) , 44-61
A Survey of Multimodal Sensor Fusion for Passive RF and EO Information Integration
Integrating information collected by different types of sensors observing the same or related phenomenon can lead to more accurate and robust decision making. The purpose of this article is to review sensor fusion approaches to achieve passive radio frequency (RF) and electro-optical (EO) sensor fusion and to present the proposed fusion of EO/RF neural network (FERNN). While research has been conducted to integrate complementary data collected by EO and RF modalities, the processing of RF data usually applies traditional features, such as Doppler. This article explores the viability of using the histogram of I/Q (in-phase and quadrature) data for the purposes of augmenting the detection accuracy that EO input alone is incapable of achieving. Specifically, by processing the histogram of I/Q data via deep learning and enhancing feature input for neural network fusion. Using the simulated data from the Digital Imaging and Remote Sensing Image Generation dataset, FERNN can achieve 95% accuracy in vehicle detection and scenario categorization, which is a 23% improvement over the accuracy achieved by a stand-alone EO sensor.
- 1 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Joint Sparsity Aided Joint Manifold Learning for Sensor Fusion
This paper presents a joint sparsity aided joint manifold learning (JSAJML) approach for heterogenous sensor fusion of image and radio frequency (RF) data. A typical scenario includes several objects (with RF emitters), which are observed by a network of platforms with Medium Wavelength Infrared (MWIR) cameras and/or RF Doppler sensors. In the past, we developed two heterogeneous approaches for mixed and/or mixed sensor modalities. The joint sparsity (JS) approach for cases without ground truth and joint manifold learning (JML) for cases with ground truth. In this paper, we unify the abovementioned methods. We propose an interactive learning/training of JML based on joint sparsity results. We use the joint sparsity support recovery to generate estimated ground truth and train the JML framework. On the other hand, the joint sparsity can use the JML results to improve the data fusion results and speed up the processing as well. The JSAJML approach is tested and verified on AFRL datasets.
- 1 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Joint Sparsity Aided Joint Manifold Learning for Sensor Fusion
This paper presents a joint sparsity aided joint manifold learning (JSAJML) approach for heterogenous sensor fusion of image and radio frequency (RF) data. A typical scenario includes several objects (with RF emitters), which are observed by a network of platforms with Medium Wavelength Infrared (MWIR) cameras and/or RF Doppler sensors. In the past, we developed two heterogeneous approaches for mixed and/or mixed sensor modalities. The joint sparsity (JS) approach for cases without ground truth and joint manifold learning (JML) for cases with ground truth. In this paper, we unify the abovementioned methods. We propose an interactive learning/training of JML based on joint sparsity results. We use the joint sparsity support recovery to generate estimated ground truth and train the JML framework. On the other hand, the joint sparsity can use the JML results to improve the data fusion results and speed up the processing as well. The JSAJML approach is tested and verified on AFRL datasets.
- 28 September 2017
- Published by DEStech Publications
- No. shm
DDDAS-based Joint Nonlinear Manifold Learning for Target Localization
The dynamic data-driven applications system (DDDAS) paradigm uses the controlled measurement data to update models. When big data streams are available, signal processing can be used for situation awareness. However, many times, the physical world prevents sensor measurements availability which provides an opportunity to use heterogeneous sensor information; but methods are needed for data normalization, sampling alignment, and data mining. In this paper, we highlight a joint nonlinear manifold learning approach to that incorporates advances in machine learning, data fusion, and model-based simulation propagators. The context of the situation monitoring includes a multiple moving targets, a video sensor, and distributed signal sensors. The challenge is to determine the moving emitter amongst a cluttered scene during an experiment with large data streams. Resolving the signature triangulation of the emitter with that of the video sensor is both a nonlinear tracking problem as well as data learning issue. The paper presents the joint nonlinear manifold learning approach that is theoretically developed such sensor models could not only be the tracking scenario; but that of structure health monitoring as well as internet of things (IoT) examples. The theoretical analysis, heterogeneous data set, machine learning, and results are presented to showcase the importance of real-time DDDAS modeling updates of kinematic models.
- 28 September 2017
- Published by DEStech Publications
- No. shm
DDDAS-based Joint Nonlinear Manifold Learning for Target Localization
The dynamic data-driven applications system (DDDAS) paradigm uses the controlled measurement data to update models. When big data streams are available, signal processing can be used for situation awareness. However, many times, the physical world prevents sensor measurements availability which provides an opportunity to use heterogeneous sensor information; but methods are needed for data normalization, sampling alignment, and data mining. In this paper, we highlight a joint nonlinear manifold learning approach to that incorporates advances in machine learning, data fusion, and model-based simulation propagators. The context of the situation monitoring includes a multiple moving targets, a video sensor, and distributed signal sensors. The challenge is to determine the moving emitter amongst a cluttered scene during an experiment with large data streams. Resolving the signature triangulation of the emitter with that of the video sensor is both a nonlinear tracking problem as well as data learning issue. The paper presents the joint nonlinear manifold learning approach that is theoretically developed such sensor models could not only be the tracking scenario; but that of structure health monitoring as well as internet of things (IoT) examples. The theoretical analysis, heterogeneous data set, machine learning, and results are presented to showcase the importance of real-time DDDAS modeling updates of kinematic models.