The Center for Surveillance Research (CSR) is a collaborative effort by academia, government, and industry to conduct research and student training for the next generation of technology leaders in surveillance systems, so as to advance the body of knowledge in that field. Surveillance abilities and situational awareness are needed to address societal needs of safety and security. Surveillance technology is used to provide our nation with both international and homeland security; situational awareness is necessary for disaster mitigation and management, and environmental monitoring. The key to addressing potential security and environmental threats is the effective use of sensors and sensor systems. While individual sensor technology is advancing, there is no mature theory for understanding composite surveillance systems. The challenge is to design quantitative tools that aid in designing optimal surveillance systems to achieve particular inference goals and to develop a theory for predicting surveillance performance. There is an increasing need and urgency to train and educate qualified scientists and engineers who can become the next generation of thought leaders in the surveillance systems field. Surveillance theory is a broad, multidisciplinary topic that integrates ideas and techniques across several disciplines, including sensor phenomenology, signal and image processing, machine learning, sensor technology (e.g., radar, acoustic, chemical/biological, etc.), and human factors engineering.
Research Areas
CSR’s scientific research program addresses the breadth and depth of surveillance science. The core disciplines include sensor exploitation, signature prediction, computation, and functional baseline descriptions. Performance prediction and uncertainty characterization accompany every level (signal, feature, detection, localization, tracking, targeting, and intent). Thus, the performance bounds and information metrics are likewise relevant at each level.
Recent research topics include:
Advanced regression techniques for automatic target recognition (ATR) system-performance modeling.
Algorithms for efficient, wide-field-of-view synthetic aperture radar ground moving target indication (SAR GMTI).
Deep learning for cognitive radar.
Drone synthetic aperture radar (SAR).
Evaluating impact of trust in human-ATR interaction.
Generative models with visual attention for target tracking and reacquisition
The geo-aware mobility traffic simulation framework.
Knowledge-empowered real-time event-centric situational analysis.
Merging deep networks with algorithms for imaging inverseâ€problems.
Processing of optimally constructed, noncontiguous radar transmission spectra.
Structured covariance matrix estimation with space-time adaptive processing applications.
Facilities & Resources
Partner Organizations
Abbreviation |
CSR
|
Country |
United States
|
Region |
Americas
|
Primary Language |
English
|
Evidence of Intl Collaboration? |
|
Industry engagement required? |
Associated Funding Agencies |
Contact Name |
Brian Rigling
|
Contact Title |
Center Director
|
Contact E-Mail |
brian.rigling@wright.edu
|
Website |
|
General E-mail |
|
Phone |
|
Address |
The Center for Surveillance Research (CSR) is a collaborative effort by academia, government, and industry to conduct research and student training for the next generation of technology leaders in surveillance systems, so as to advance the body of knowledge in that field. Surveillance abilities and situational awareness are needed to address societal needs of safety and security. Surveillance technology is used to provide our nation with both international and homeland security; situational awareness is necessary for disaster mitigation and management, and environmental monitoring. The key to addressing potential security and environmental threats is the effective use of sensors and sensor systems. While individual sensor technology is advancing, there is no mature theory for understanding composite surveillance systems. The challenge is to design quantitative tools that aid in designing optimal surveillance systems to achieve particular inference goals and to develop a theory for predicting surveillance performance. There is an increasing need and urgency to train and educate qualified scientists and engineers who can become the next generation of thought leaders in the surveillance systems field. Surveillance theory is a broad, multidisciplinary topic that integrates ideas and techniques across several disciplines, including sensor phenomenology, signal and image processing, machine learning, sensor technology (e.g., radar, acoustic, chemical/biological, etc.), and human factors engineering.
Abbreviation |
CSR
|
Country |
United States
|
Region |
Americas
|
Primary Language |
English
|
Evidence of Intl Collaboration? |
|
Industry engagement required? |
Associated Funding Agencies |
Contact Name |
Brian Rigling
|
Contact Title |
Center Director
|
Contact E-Mail |
brian.rigling@wright.edu
|
Website |
|
General E-mail |
|
Phone |
|
Address |
Research Areas
CSR’s scientific research program addresses the breadth and depth of surveillance science. The core disciplines include sensor exploitation, signature prediction, computation, and functional baseline descriptions. Performance prediction and uncertainty characterization accompany every level (signal, feature, detection, localization, tracking, targeting, and intent). Thus, the performance bounds and information metrics are likewise relevant at each level.
Recent research topics include:
Advanced regression techniques for automatic target recognition (ATR) system-performance modeling.
Algorithms for efficient, wide-field-of-view synthetic aperture radar ground moving target indication (SAR GMTI).
Deep learning for cognitive radar.
Drone synthetic aperture radar (SAR).
Evaluating impact of trust in human-ATR interaction.
Generative models with visual attention for target tracking and reacquisition
The geo-aware mobility traffic simulation framework.
Knowledge-empowered real-time event-centric situational analysis.
Merging deep networks with algorithms for imaging inverseâ€problems.
Processing of optimally constructed, noncontiguous radar transmission spectra.
Structured covariance matrix estimation with space-time adaptive processing applications.