SBIR-STTR Award

The proliferation of group 3-5 unmanned aerial systems (UAS) provides an excellent opportunity for robust, passive, maritime target recognition and classification. These platforms can be outfitted with (1) high-quality camera systems, (2) high-performance compute resources, and (3) encrypted links for relaying tactical information to other nodes. RDRTec has already demonstrated the ability to perform maritime target classification from ISAR imagery at very long ranges which separates combatants from commercial vessels wand is able to distinguish combatants at levels of detail below fine naval class. Our toolset and reference database divides ships of the world into over 1500 types. This approach requires no training and performance has been demonstrated on datasets from new sensors with no parameter tuning. RDRTecs Maritime Classification Aid (MCA) sorts image frames into categories. MCAs profile feature extraction will work with almost no modifications for EO/IR imagery taken from angles +/- 65 deg from broadside and grazing angles up to 15 deg. For these angles, feature extraction identifyies superstructure location and width at various heights. Our database is fully populated for superstructure features for all 1500+ templates. For frames that are not profile views which use RCS-based feature extraction, direct measurement of superstructure locations and sizes are not always directly measurable. MCA has demonstrated that we can approximate the expected extracted features from these viewing angles right from a single profile view reference image and perform classification without any 3D information. RDRTecs MCA has already been integrated with mission systems such as the USNs Minotaur system, and sensor resource managers such as Lambda Sciences SEMS. It has been hosted on flight ready tactical processors. Part of MCAs design requirements has always been the ability to run in real-time on modest processor resources. Currently we have a delivered configuration that can run in a single 3U Open-VPX slot while performing not only classification but also performs ISAR image formation starting from raw IQ data. RDRTec is currently advancing a hybrid physics-based / ML addition to MCA for exploiting vibration and rotating aperture signatures and will take a similar approach in augmenting MCA for use with EO/IR sensors across wide viewing angles. Keys to RDRTecs approach include (1) proven performance on ISAR imagery, (2) existing database of ships of the world, (3) prior integrations with mission systems and sensor resource managers, (4) no training required, (5) very conservative SWAP, (6) successful transitions as a supplier of third-party modes/apps to DoD primes and DoD labs.

Benefit:
At the completion of this phase I effort, if the approach is demonstrated to be feasible, RDRTec will be postured for a Phase II effort to refine the algorithms and techniques explored in phase I. A successful Phase II prototype would then lead to Phase III opportunities to transition the technology both as part of MCA and as a standalone EO/IR based classifier to existing and future radar systems. RDRTec has a proven record of transitioning SBIR technologies such as MCA through the following three approaches: Licensing of technology to primes for integration with their existing products. Example: Licensing MCA to Telephonics for integration with their maritime surveillance radar systems. Partnering with primes to leverage their manufacturing and integration capability. Example: Partnering with Raytheon to bring our ISAR mode to multiple families of COARPs Radar Systems Working directly with the DoD to integrate our technologies with their mission systems. Examples: Integrating MCA with Minotaur for transition into Triton, Fire Scout, Poseidon, and MH60-R. Integration of MCA into the AST lab to assist with truthing of collected ISAR data. All of these will be used for transitioning the innovative passive target recognition technologies developed under this SBIR. RDRTec is already engaged with group 3 Vanilla, group 4 Fire Scout, and group 5 Triton platforms on other projects which will ease the logistics of transitioning a passive maritime target recognition mode to those and similar platforms. RDRTec continues to work collaboratively with Raytheon delivering third party apps and modes for their sensors and is already in discussion with them regarding possible transition of the research proposed under this topics for their Multi-spectral Targeting Systems. Potential land-based and airborne commercial applications include port surveillance, patrolling fisheries, and search and rescue missions.

Keywords:
EO/IR, EO/IR, Hybrid Classification, Machine Learning, Maritime Target Classification

The proliferation of unmanned aerial systems provides an excellent opportunity for robust, passive, maritime target recognition and classification. These platforms can be outfitted with (1) high-quality camera systems, (2) high-performance compute resources, and (3) encrypted links for relaying tactical information to other nodes.RDRTec has already demonstrated the ability to perform maritime target classification from ISAR imagery at very long ranges (100s of km) which not only separates combatants from commercial vessels with excellent accuracy but further is able to distinguish combatants at levels of detail even below fine naval class. This Automatic Combat Vessel Classifier (ACVC) divides ships of the world into over 1500 types. Classification is done using a sensor agnostic, physics-based classifier and a reference database populated with all of the templates. This approach requires no training and performance has been demonstrated on datasets from new sensors with no parameter tuning.ACVC s profile feature extraction will work with almost no modifications for EO/IR imagery taken from angles +/- 65 deg from broadside and grazing angles up to 15 deg as optical imagery is similar in presentation to the ISAR imagery which ACVC currently processes. ACVC feature extraction consists of identifying superstructure location and width at various heights from the deck line. The ACVC database is populated with features for all 1500+ templates, and we have demonstrated that we can approximate the expected extracted features from these viewing angles correctly from a single ISAR profile view and perform classification based on this feature set.The predecessor of RDRTecs ACVC system, MCA, has already been integrated with mission systems such as the USNs Minotaur system and sensor resource managers systems. It has been hosted on flight ready tactical processors. Part of ACVCs design requirements has always been the ability to run in real-time on modest processor resources. Currently we have a delivered configuration that can run in a single 3U Open-VPX slot while performing not only classification but also performs ISAR image formation starting from raw IQ data.RDRTec is currently advancing a hybrid physics-based / ML addition to ACVC for exploiting vibration and rotating aperture signatures and will take a similar approach in augmenting ACVC for use with EO/IR sensors across wide viewing angles. During Phase I we demonstrated successful optical image-based classification using the ACVC system with default ISAR settings. These efforts included a proof-of-concept vessel foreground extraction algorithm using custom developed MATLAB code and manual processes for creating input to ACVC. These were effective in confirming the feasibility of our approach. In Phase II we will develop processes to provide a fully automated classification pipeline that operates similar to the existing ISAR-based system.

Benefit:
A successful Phase II prototype will lead to Phase III opportunities to transition the technology both as part of ACVC and as a standalone EO/IR based classifier to existing and future radar systems. RDRTec has a proven record of transitioning SBIR technologies such as ACVCs predecessor MCA through the following three approaches:Licensing of technology to primes for integration with their existing products.Example: Licensing MCA to Telephonics for integration with their maritime surveillance radar systems.Partnering with primes to leverage their manufacturing and integration capability.Example: Partnering with Raytheon to bring our ISAR mode to multiple families of COARPs Radar SystemsWorking directly with the DoD to integrate our technologies with their mission systems.Examples: Integrating MCA with Minotaur for transition into Triton, Fire Scout, Poseidon, and MH60-R. Integration of MCA into the AST lab to assist with truthing of collected ISAR data.All of these will be used for transitioning the innovative passive target recognition technologies developed under this SBIR.RDRTec is already engaged with group 3 Vanilla, group 4 Fire Scout, and group 5 Triton platforms on other projects which will ease the logistics of transitioning a passive maritime target recognition mode to those and similar platforms. RDRTec continues to work collaboratively with Raytheon delivering third party apps and modes for their sensors and is already in discussion with them regarding possible transition of the research proposed under this topic for their Multi-spectral Targeting Systems.In addition to military applications, this technology has potential land-based and airborne commercial applications which include port surveillance, patrolling fisheries, and search and rescue missions.

Keywords:
ACVC, ATR, Automatic Target Recognition