Revealing the Earth (Intel Labs@SC12)

Satellite photography enables earth-mapping applications such as Google Earth to pull together vast amounts of imagery to provide high resolution views of the planet for a spectrum of personal, business, and government applications. However, satellites have two fundamental limitations: they can’t see at night and they can’t see through obscuring trees or other vegetation.

Radar imaging can do both of these by probing the earth with radio waves and using a computer to process and render their echoes as a picture. This imaging technique provides information about the materials on or just below the surface of the earth. Such an approach is the subject of a paper at SC12 this week.

This has practical applications beyond the obvious military ones, such as for:

  • Monitoring crop characteristics for farmers
  • Revealing ice hazards for ocean navigation
  • Geology and mineral exploration
  • Environmental monitoring of deforestation or oil spills
  • Providing aircraft autopilots with real-time, all-weather images of the terrain ahead

The challenge with radar imaging is that due to the nature of radio waves, the aperture size required to collect the image is many meters – very large compared to a telescope lens, and not at all portable. Instead, a large aperture is synthesized by flying a plane-mounted radar system in a circular pattern and combining all the data into one image. This technique is called “synthetic aperture radar” or SAR.

In order to make SAR capabilities available for the civilian applications listed, two challenges must be addressed. First, creating a SAR image is computationally intense, requiring 100s of Teraflops processing power. Second, the collection algorithms typically used require that the surface to be imaged be very flat and the plane’s flight path to be nearly perfect, inducing many practical challenges.

Intel is presenting a paper at SC12 that tackles both problems successfully. Intel Labs and Intel’s Software & Services Group (SSG), in collaboration with Georgia Institute of Technology demonstrate the potential for significant reductions in computational cost using a ‘backprojection’ algorithm. Backprojection is a SAR imaging technique that allows non-flat surfaces to be imaged with more flexible flight paths – i.e. without having to fly in an absolutely perfect circle. However, backprojection has been considered less computationally efficient. Intel Labs and SSG demonstrate that through algorithmic innovation and parallel processing using Intel® Xeon® systems equipped with the new Intel® Xeon Phi™ co-processor (two per node), over 35 billion SAR backprojection calculations per second can be performed. This is enough to generate the equivalent of one 3000 x 3000 pixel image per second per compute node. The addition of Xeon Phi cards sped each node by 4.8x for this application (see notices below).

Furthermore, these algorithmic improvements have the potential to be applied to imaging applications in a variety of other fields. The backprojection method is similar to those used in medical applications such as X-ray CT scans and ultrasound imaging. Hence this research could help advance imaging capability for a variety of data-intensive image processing applications.

Legal Notices:
  • Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products.  For more information go to
  • Intel’s compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.  Notice revision #20110804


Sean Koehl

About Sean Koehl

Sean Koehl (@smkoehl) is a Vision Strategist for Intel Labs, the global research arm of Intel Corporation. He is responsible for crafting visions of how Intel R&D efforts could impact daily life in the future. He leverages insights from Intel’s technologists, social scientists, futurists, and business strategists to articulate how technology innovations and new user experiences could improve lives and society. Sean received a bachelor’s degree in Physics from Purdue University and launched his career at Intel in 1998. He has worn many hats in his career including those of an engineer, evangelist, writer, creative director, spokesperson, and strategist. He has led a variety of projects and events, authored numerous technology publications and blogs, and holds seven patents. He is based at Intel’s headquarters in Santa Clara, California.

Comments are closed.