Power-efficient re-gridding architecture for accelerating Non-uniform Fast Fourier Transform

Cheema, Umer I.; Nash, Gregory; Ansari, Rashid; Khokhar, Ashfaq

doi:10.1109/fpl.2014.6927451

Cited by 5 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most computationally intensive step is data translation for which we define a specific architecture. A key difference in this work from our prior NuFFT work on FPGA [16] and another FPGA based implementation [17] is that the samples come in a known order. This is exploitable in the following way.…”

Section: Non-uniform Fftmentioning

confidence: 99%

Power-efficient RMA SAR imaging using pipelined Non-uniform Fast Fourier Transform

Nash

Cheema

Ansari

et al. 2015

2015 IEEE Radar Conference (RadarCon)

Self Cite

View full text Add to dashboard Cite

Range Migration Algorithm (RMA) is one of the most practiced frequency domain based algorithms for Synthetic Aperture Radar (SAR) image reconstruction. While computationally more intensive than Polar Format Algorithm (PFA), it has superior image reconstruction for large squint angles. Due to the real-time nature of SAR imaging-related tasks, it is desired to have faster hardware implementations of reconstruction algorithms. In this paper we study FPGA-based implementation of the RMA algorithm using a novel pipelined Non-uniform FFT (NuFFT) module that optimizes its operation by exploiting the order in which samples are presented. We demonstrate that we can achieve processing speed of over 600 Msps (Mega Samples per Second) for the implemented RMA algorithm using the FPGA.

show abstract

Section: Non-uniform Fftmentioning

confidence: 99%

Power-efficient RMA SAR imaging using pipelined Non-uniform Fast Fourier Transform

Nash

Cheema

Ansari

et al. 2015

2015 IEEE Radar Conference (RadarCon)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Non-uniform fast Fourier transforms (NUFFTs) are efficient, accurate alternatives to standard FDMs, particularly for range-migration algorithms [4], [5], [6]. NUFFTs do not suffer from beam-width limitations as do chirp-z transforms [7] and its computational complexity is O(N 2 log N ) for N data points.…”

Section: Introductionmentioning

confidence: 99%

Thresholded Non-Uniform Fourier Frame-Based Reconstruction for Stripmap SAR

McKay¹,

Gelb²,

Jayasuriya³

et al. 2019

Preprint

View full text Add to dashboard Cite

Fourier domain methods are fast algorithms for SAR imaging. They typically involve an interpolation in the frequency domain to re-grid non-uniform data so inverse fast Fourier transforms can be performed. In this paper, we apply a frame reconstruction algorithm, extending the non-uniform fast Fourier transform, to stripmap SAR data. Further, we present an improved thresholded frame reconstruction algorithm for robust performance and improved computational efficiency. We demonstrate compelling results on real stripmap SAR data.

show abstract

“…D IGITAL image reconstruction, such as image translation, scaling, rotation, and geometric correction, has been widely used in civilian and medical fields [1]- [19]. Owing to the increasing demand of performance, power consumption, and reliability, real-time digital image reconstruction is predominantly implemented on field programmable gate array (FPGA) [2], [3], [5], [6], [8]- [19].…”

Section: Introductionmentioning

confidence: 99%

“…Owing to the increasing demand of performance, power consumption, and reliability, real-time digital image reconstruction is predominantly implemented on field programmable gate array (FPGA) [2], [3], [5], [6], [8]- [19].…”

Section: Introductionmentioning

confidence: 99%

Block Region of Interest Method for Real-Time Implementation of Large and Scalable Image Reconstruction

2015

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

In field programmable gate array (FPGA)-based reconstruction of high-resolution (several-gigabyte) images, architectures that store the entire source image in block memory are no longer feasible. In this letter, a block region of interest (ROI) method is proposed for large and scalable image reconstruction, using 2D truncated sinc interpolation by storing only a slice of the source image in block memory. To ensure a high hit rate in block memory for interpolation and improve memory access efficiency, this method provides an effective criterion for partitioning, which subdivides the output image into blocks based on the ROI in the source image. Moreover, a special storage pattern is designed to simultaneously provide 16 pixels for each interpolation to enable real-time implementation by full pipelining with no memory data redundancy. The proposed method was validated by experimental results on an FPGA board along with the corresponding simulations on MATLAB. Various image sizes were tested to prove its flexibility. The time required to reconstruct an output image of k k at 200 MHz was 2.79 s, thereby achieving a processing speed of 385 Mpixels/s in single floating point precision. Index Terms-2D sinc interpolation, block region of interest (ROI), large-image reconstruction, real-time implementation, scalable.1070-9908

show abstract

Power-efficient re-gridding architecture for accelerating Non-uniform Fast Fourier Transform

Cited by 5 publications

References 12 publications

Power-efficient RMA SAR imaging using pipelined Non-uniform Fast Fourier Transform

Power-efficient RMA SAR imaging using pipelined Non-uniform Fast Fourier Transform

Thresholded Non-Uniform Fourier Frame-Based Reconstruction for Stripmap SAR

Block Region of Interest Method for Real-Time Implementation of Large and Scalable Image Reconstruction

Contact Info

Product

Resources

About