Scalable Network Based FPGA Accelerators for an Automatic Target Recognition Application
نویسندگان
چکیده
Image processing, specifically Automatic Target Recognition (ATR) in Synthetic Aperture Radar (SAR) imagery, is an application area that can require tremendous processing throughput. In this application, data comes from high bandwidth sensors, where the processing is time-critical. There is limited space and power for processing the data in the sensor platforms or in battlefield groundstations. DoD’s strong push for using commercial-off-the-shelf (COTS) technology, the very high non-recurring engineering (NRE) costs for low volume ASICs, and evolving algorithms limit the feasibility of using custom special purpose hardware. In addition, a scalable system is required as the different sensor platforms have different image pixel rates and different mission requirements have different target recognition throughput needs per pixel.
منابع مشابه
Reconfigurable Architectures for Systems Level Applications of Adaptive Computing
The Systems Level Applications of Adaptive Computing (SLAAC) project is defining an open, distributed, scalable, adaptive computing systems architecture based on a highspeed network cluster of heterogeneous, FPGA-accelerated nodes. Two implementations of this architecture are being created. The Research Reference Platform (RRP) is a Myrinet cluster of PCs with SLAAC-1 PCI-based FPGA accelerato...
متن کاملMapping of an Automated Target Recognition Application from a Graphical Software Environment to FPGA-Based Reconfigurable Hardware
A significant obstacle to the widespread adoption of FPGAbased configurable computing hardware has been the difficulty of mapping applications onto this hardware. We are developing a software development system called CHAMPION to automate the process of mapping applications in the graphical software environment Khoros to multiple FPGA-based architectures. The work described here consists of the...
متن کاملDesign Space Exploration of FPGA-Based Deep Convolutional Neural Networks
Deep Convolutional Neural Networks (DCNN) have proven to be very effective in many pattern recognition applications, such as image classification and speech recognition. Due to their computational complexity, DCNNs demand implementations that utilize custom hardware accelerators to meet performance and energy-efficiency constraints. Leverages all sources of parallelism in DCNNs, in this paper w...
متن کاملAutomated target recognition on SPLASH 2
Automated target recognition is an application area that requires special-purpose hardware to achieve reasonable performance. FPGA-based platforms can provide a high level of performance for ATR systems if the implementation can be adapted to the limited FPGA and routing resources of these architectures. This paper discusses a mapping experiment where a linear-systolic implementation of an ATR ...
متن کاملAutomatic Target Recognition
This paper describes the acceleration of an infrared automatic target recognition (IR ATR) application with a co-processor board that contains multiple eld programmable gate array (FPGA) chips. Template and pixel level parallelism is exploited in an FPGA design for the bottleneck portion of the application. The implementation of this design achieved a speedup of 21 compared to running on the ho...
متن کامل