R & D

Technologies Publications

Recently, 21CSi’s R&D team has researched, developed, and matured technologies for the efforts listed below.

SBIR Phase I

AMADEUS – Airspace Management And Deconfliction Environment for Unmanned Systems Virtual Trainer [SBIR, U.S. Air Force]

300px-OHMAS1The increasing congestion of airspace with unmanned aerial systems (UASs) in close proximity with manned systems poses a serious and potentially deadly problem of catastrophic mishaps. At present, Remotely Piloted Aircraft (RPA) pilot training in airspace management is minimal. 21st Century Systems, Inc. (21CSi), which has been developing intelligent agent-based decision support tools for more than 14 years, is applying its mature technology and research experience to help address this challenge. Teamed with academia and industry, 21CSi is researching and developing AMADEUS, an advanced, intelligent agent-driven, airspace training module, openly architected to be compatible with third-party simulators, providing instructors with an advanced scenario authoring capability and a more flexible vignette insertion capability, leading to a higher fidelity airspace training experience. AMADEUS will allow the U.S. Air Force and other services to improve airspace awareness in their RPA operators while making more effective use of simulator training assets.

Casual-View [SBIR, U.S. Army]

Causal View is a graphical causal data mining tool suite capable of visualizing causal relationships in multi-sourced data. The concept behind Causal View is to use machine intelligence to identify abnormalities within the data that may indicate information that should be attended to. For example, changes in vehicle performance may be a precursor to engine faults. Or, in the intelligence community, sequences of actions may point to nefarious behavior being planned or perpetrated. Causal View relies on cutting edge technologies and state-of-the-art decision support utilities to achieve this goal. Built on an agent-enabled framework, Causal-View utilizes intelligent agents for data extraction, data mining, hypothesis generation, and data reasoning in order to customize the feature set in order to determine causal relationships that the user is interested in.

MADOC – Measure and Alert on Data Omitted by Compression [SBIR, U.S. Army]

Critical information can be lost when lossy compression techniques are used in bandwidth limited environments, such as from unmanned systems. More serious, this lost information is unknown to the analyst, which can lead to incorrect analysis and potentially fatal conclusions. The goal of this effort is to develop a system capable of detecting such data loss and providing notification when compression has omitted information that may be important. The MADOC system will effectively deal with the problem caused by compression effects by detecting, alerting, and mitigating compression problems. By integrating with existing streaming media servers, MADOC can improve decision making, reduce overall bandwidth, and provide operators of UAV’s, UGV’s, or other video-based operations the ability to handle situations of extreme compression without impairing performance. The MADOC solution provides the opportunity to recover at least some of the higher quality video containing information that would otherwise be lost. A fully integrated video streaming solution with MADOC included makes it possible for operators and commanders to make effective decisions with more certainty – and in the military, this could mean saving lives, or stopping a combatant from getting away.


Transmission Surveillance (TRANSURV) [SBIR, U.S. Army]

300px-TRANSURV1The potential for radio communications to be used in asymmetric operations against coalition forces has grown exponentially and has expanded well beyond the now-familiar IED detonators. Expeditionary forces, in particular, convoys on the move, need an effective counter surveillance capability to combat this threat. Following a very successful Phase I effort, the team of 21st Century Systems Incorporated (21CSI) and Missouri University of Science and Technology continued to pursue our research and development of a counter surveillance concept called TRANSURV. This transmission surveillance tool is the synergistic pairing of RF DF equipment and video cameras to provide persistent perimeter surveillance without incurring a large manpower footprint. The RF sensors are used to cue video cameras (slew-to-cue), which slew to the RF source. Utilizing advanced video analytics, TRANSURV analyzes the scene for human presence and alerts the operator. Built on 21CSI’s successful force protection product line, now spun off into a new company called Persistent Sentinel LLC, TRANSURV provides decision support that enhances situational awareness and security. Combining 21CSI’s extensive experience in force protection decision support, service oriented architectures, and video analytic technologies, with MS&T’s expertise in RF detection, this team is the most qualified to field this capability.

Smart Multimodal Image Registration and Fusion (SMIRF) [SBIR, U.S. Navy]

350px-SMIRF1Through a NAVSEA SBIR Phase II effort, 21st Century Systems, Inc. (21CSi) is developing SMIRF, a Smart Multimodal Image Registration and Fusion technology that produces a higher contrast resultant image through fusion of multiple sensor modalities to improve a warfighter’s capability to simultaneously ingest and interpret multiple streams of video viewing the same scene but from different sensor modalities. The SMIRF tool will be a critical asset to the submarine’s OOD/Contact Coordinator, increasing the visibility and contrast of targets, thereby accelerating situational awareness and making surfacing and transiting safer. SMIRF’s ability to merge images from various video sources and accelerate situational awareness for the user also makes it a natural fit for the UAV/RPA ISR and border security domain space. SMIRF will reduce the need for ISR exploitation operators to manually search through multiple sensor modalities by creating a single, fused operating picture, thus reducing the exploitation workload. The algorithmic solution produces a higher contrast on targets of interest in the fused solution while providing dampening contrast in the background image; thus, increasing capability to detect, identify, and track targets within the single fused video; and enabling faster decision making.

Agent-Enabled Logistics Enterprise Intelligence System (AELEIS) [SBIR, U.S. Army]

Agent-Enabled Logistics Enterprise Intelligence System (AELEIS) is a system in which multiple database resources, along with reports and data-logs, are mined for vehicle health maintenance information that is processed into actionable logistics information. Using a Service Oriented Architecture (SOA), AELEIS data extraction agents connect to the various databases and other data sources. The extraction agents scan the databases for key pieces of data and then publish that data back to the AELEIS Central Core. There, the reasoning agents determine what tools are needed based on data clustering. Then, the mining and trending agents find the information in the data (they may also instruct the extraction agents on further data to find). Finally, compiled actionable information is published in a standard format out to users. This information is then picked up by a decision tool that the user can see the information, drill-down to see where the information originated, and make an informed decision on the logistics plan. AELEIS is being designed as a tool to assist logistics analysts with assessing the availability and prognostics of assets. AELEIS extracts data from multiple, heterogeneous data sets, aggregates it, mines it for trends, and data reasoning and prognostics tools evaluate the data for relevance and potential issues. The result affords fleet managers with instant access to both the raw data and fused information on the health of the vehicle with analysis of the remaining life or the fault that may be present. The fleet manager can then employ/deploy the most effective set of vehicles to the field. AELEIS will create actionable knowledge for fleet managers, operators, and commanders, readily available for them to access when needed.

Video20/20 [SBIR, U.S. Air Force]

The overall objective of the Video20/20 project is to create a commercial software toolset that provides effective real-time video enhancement to improve one’s capability to interpret streaming video. Unmanned vehicles today capture critical real-time video intelligence of military targets, but the videos themselves can be subject to significant jitter, noise, glare, motion blur, and other degrading factors, making it difficult for humans to interpret the video in addition to degrading further automated video analysis processes. Furthermore, the complexities of operating unmanned vehicles with such degraded surveillance and guidance data can diminish its role as a force multiplier, as, in some cases, several operators must be involved in their operation. The AFRL-supported Video20/20 Phase II effort is meant to address these concerns through prototyping a set of tools for high quality video enhancement. Dehazing for reducing cloud cover, fog, and smoke effects; contrast enhancement to deal with shadows; de-noising to increase signal while reducing distracting noise artifacts; deblurring and stabilization to counteract platform motion and jitter; and super-resolution to increase utility are all topics being investigated in the Phase II effort. In Phase II and beyond, the ultimate research and development goal is real-time adaptive algorithms, autonomously providing the appropriate algorithmic enhancement(s) in an optimal execution order. The Video20/20 commercial product will take raw video (digital or analog), clean it up in real time, and provide it to the user for situational awareness or further automated characterization and recognition analysis.


Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s