Designing a GPU-parallel algorithm for raw SAR data compression: A focus on parallel performance estimation

Abstract When a Synthetic Aperture Radar (SAR) acquires raw data using a satellite or airborne platform, it must be transferred to the ground for further processing. For example, SAR raw data need a so-called ’focusing’ signal processing to render it into a visible image. Such processing is time and computing consuming, and it is commonly carried out in computing centres. Since the data transfer rate is a typical limitation when communicating with the ground station, compression is necessary to reduce transmission time. So far, this procedure has been implemented in application-specific hardware, but recent adoption of avionic computational GPUs opened to new high-performance onboard perspectives. Due to the limited availability of avionic GPUs, we focused on parallel performance estimation starting from measures relative to a similar off-the-shelf solution. In this paper, we present a GPU algorithm for raw SAR data compression, which uses 1-dimensional DCT transforms, followed by quantisation and entropy coding. We evaluate results using ENVISAT (Environmental Satellite) ASAR Image Mode level 0 data by measuring compression rates, statistical parameters, and distortion on decompressed and then focused images. Moreover, by evaluating the Algorithmic Overhead induced by the parallelisation strategy, we predict the best thread-block configuration for possible adoption of such a GPU algorithm on one of the most available avionic hardware.

[1]  Marco Lapegna,et al.  A Study on Adaptive Algorithms for Numerical Quadrature on Heterogeneous GPU and Multicore Based Systems , 2013, PPAM.

[2]  Livia Marcellino,et al.  A GPU algorithm for tracking yeast cells in phase-contrast microscopy images , 2018, Int. J. High Perform. Comput. Appl..

[3]  Alberto Moreira,et al.  Fusion of block adaptive and vector quantizer for efficient SAR data compression , 1993, Proceedings of IGARSS '93 - IEEE International Geoscience and Remote Sensing Symposium.

[4]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[5]  Ken Kennedy,et al.  Performance of parallel processors , 1989, Parallel Comput..

[6]  T. Algra.  Compression of raw SAR data using entropy-constrained quantization , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[7]  Giulio Giunta,et al.  Virtualizing high-end GPGPUs on ARM clusters for the next generation of high performance cloud computing , 2013, Cluster Computing.

[8]  Luisa D'Amore,et al.  An objective criterion for stopping light–surface interaction. Numerical validation and quality assessment , 2017, Journal of Mathematical Imaging and Vision.

[9]  J. Marchand,et al.  SAR Image Quality Assessment , 1993 .

[10]  William J. Dally,et al.  The GPU Computing Era , 2010, IEEE Micro.

[11]  Anthony Vetro,et al.  Low complexity efficient raw SAR data compression , 2011, Defense + Commercial Sensing.

[12]  Yves-Louis Desnos,et al.  The ENVISAT advanced synthetic aperture radar system , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[13]  Eric Dubois,et al.  Block adaptive quantization of images , 1993, IEEE Trans. Commun..

[14]  W. Kinsner,et al.  A review of current raw SAR data compression techniques , 2001, Canadian Conference on Electrical and Computer Engineering 2001. Conference Proceedings (Cat. No.01TH8555).

[15]  Lucia Maddalena,et al.  A fusion-based approach to digital movie restoration , 2009, Pattern Recognit..

[16]  Emil M. Constantinescu,et al.  A PETSc parallel‐in‐time solver based on MGRIT algorithm , 2018, Concurr. Comput. Pract. Exp..

[17]  Marco Lapegna,et al.  A Loosely Coordinated Model for Heap-Based Priority Queues in Multicore Environments , 2015, International Journal of Parallel Programming.

[18]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[19]  Giuseppe Scotti,et al.  Towards a parallel component in a GPU–CUDA environment: a case study with the L-BFGS Harwell routine , 2015, Int. J. Comput. Math..

[20]  Enrico Magli,et al.  Wavelet-based compression of SAR raw data , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[21]  Helmut Rott,et al.  Advances in interferometric synthetic aperture radar (InSAR) in earth system science , 2009 .

[22]  Alberto Moreira,et al.  A comparison of several algorithms for SAR raw data compression , 1995, IEEE Trans. Geosci. Remote. Sens..

[23]  Achille Peternier,et al.  Near-real-time focusing of ENVISAT ASAR Stripmap and Sentinel-1 TOPS imagery exploiting OpenCL GPGPU technology , 2017 .

[24]  Birgit Schättler.  ASAR Level 0 Product Analysis for Image, Wide-Swath and Wave Mode , 2002 .

[25]  Almerico Murli,et al.  Mathematical Approach to the Performance Evaluation of Matrix Multiply Algorithm , 2015, PPAM.

[26]  Ian H. Witten,et al.  Arithmetic coding for data compression , 1987, CACM.

[27]  Ann Gordon-Ross,et al.  High-Performance Energy-Efficient Multicore Embedded Computing , 2012, IEEE Transactions on Parallel and Distributed Systems.

[28]  Paul Wessel,et al.  GMTSAR: An InSAR Processing System Based on Generic Mapping Tools , 2011 .

[29]  Warren P. du Plessis,et al.  Metrics to evaluate compression algorithms for raw SAR data , 2019, IET Radar, Sonar & Navigation.

[30]  Sergio Verdú,et al.  Fifty Years of Shannon Theory , 1998, IEEE Trans. Inf. Theory.

[31]  Ron Kwok,et al.  Block adaptive quantization of Magellan SAR data , 1989 .

[32]  Livia Marcellino,et al.  Deconvolution of 3D Fluorescence Microscopy Images Using Graphics Processing Units , 2011, PPAM.

[33]  Carmine Clemente,et al.  Processing of synthetic Aperture Radar data with GPGPU , 2009, 2009 IEEE Workshop on Signal Processing Systems.

[34]  Emil M. Constantinescu,et al.  Performance Evaluation for a PETSc Parallel-in-Time Solver Based on the MGRIT Algorithm , 2018, Euro-Par Workshops.

[35]  Linda Marchese,et al.  Extended capability overview of real-time optronic SAR processing , 2012 .

[36]  Michael J. Flynn,et al.  Detection and Parallel Execution of Independent Instructions , 1970, IEEE Transactions on Computers.