Image Processing Algorithms for Target Discrimination

Award Information
Agency: Department of Defense
Branch: Missile Defense Agency
Contract: HQ00603C0074
Agency Tracking Number: 031-1641
Amount: $69,300.00
Phase: Phase I
Program: SBIR
Awards Year: 2003
Solicitation Year: N/A
Solicitation Topic Code: N/A
Solicitation Number: N/A
Small Business Information
c/o Hughes & Luce, LLP,, 111 Congress Ave. Suite 9, Austin, TX, 78701
HUBZone Owned: N
Woman Owned: N
Socially and Economically Disadvantaged: N
Principal Investigator
 Csaba Rekeczky
 (512) 482-6816
Business Contact
 Les Belady
Title: C.E.O.
Phone: (512) 482-6816
Research Institution
A cellular neural network (CNN) technology based adaptive multi-target track-ing and discrimination system with compact cellular visual microprocessor is pro-posed.Methodology: The primary motivation of the present proposal is to offer a to-pographic microprocessor architecture for multi-target discrimination with embedded sensors capable of operating in a process real-time manner. The performance of multi-targettracking (MTT) and discrimination systems can be significantly increased with stored program adaptive cellular array sensors. In the ongoing experiments the input data flow of array sensors is processed on an adaptive CNN-UM architecture consist-ing ofboth cellular nonlinear network (CNN) and digital signal processing (DSP) mi-croprocessors. The algorithms designed for this combined hardware platform use adaptive multi-channel CNN solutions for instantaneous position estimation and mor-phologicalcharacterization of all targets and the DSP environment for distance calcu-lation, gating, data association, track maintenance and dynamic target motion predic-tion. A special feature of the proposed architecture is that it allows an interactivecommunication between the sensor and the digital environment. The multi-channel adaptive target tracking system implemented on the CNN visual microprocessor makes possible to develop a robust and very fast target discrimination system.Deliverables: The hardware and software framework for these experiments is under development as an extended adaptive CNN architecture and as a prototyping system within the PC104+ industrial framework (Phase I). After theoretical foundation and set up thealgorithmic framework for the discrimination, the system will be capa-ble of processing in a laboratory environment (Phase II). The compact version of this system - COMPACT CVM- (not exceeding 1 kg in weight) is currently under design and can be completedfor a demonstration during Phase II. Full integration of the en-tire system will be completed in Phase III resulting in a module weighing less than 200 g.Technical content of the proposal: This proposal provides an overview of the core technology and a methodology used, describes the main architecture and the re-lated feasibility studies to be completed in Phase I-II, gives a detailed task description forPhase I, and concludes with an overview of the key tasks to be performed in Phase II-III. Within MDA/DoD: AnaLogic is already working on projects with the DoD through EAORD. We will use our presence in the United States through EUTECUS and the work that we will be doing under Phase 1 of this project to further the relationship. Phase 1will investigate and decide the most effective way to utilize the CNN technology for the purpose of Target Discrimination and because it is an airborne application will benefit from the miniaturization and weight reduction - this will probably mean that wewill take a further step toward a

* Information listed above is at the time of submission. *

Agency Micro-sites

SBA logo
Department of Agriculture logo
Department of Commerce logo
Department of Defense logo
Department of Education logo
Department of Energy logo
Department of Health and Human Services logo
Department of Homeland Security logo
Department of Transportation logo
Environmental Protection Agency logo
National Aeronautics and Space Administration logo
National Science Foundation logo
US Flag An Official Website of the United States Government