The Syndicated

FPGA-Based Solutions for Video and Image Processing

By Brian Jentz and Rob Kruger

Consumer demand for innovations such as high-definition televisions (HDTVs) and digital cinema drives the rapid evolution of video and image processing applications. With major advances in image capture and display resolutions, advanced compression techniques and video intelligence, the processing bandwidth required for video applications continues to grow. Further, rapid changes in standards and higher resolutions are pushing designers away from off-the-shelf technology. High-performance FPGAs provide a flexible alternative to traditional digital signal processing (DSP) solutions, offering easy upgradability, processing power and fast time-to-market with a path to cost reduction. Altera’s DSP solutions, when combined with Synplicity tools, can improve cost, performance and productivity for many video and imaging applications.

Video and Image Processing Trends

Many exciting innovations such as HDTV and digital cinema revolve around the rapid evolution of video and image processing. Image capture and display resolutions, advanced compression techniques and video intelligence are the driving forces behind the technological innovation. Resolutions in particular have increased significantly over the last few years for a variety of applications such as military surveillance, medical imaging and machine vision, and the move from standard definition (SD) to high definition (HD) dramatically increases the data that needs to be processed. Advanced compression techniques are replacing previous-generation technology, offering enhancements such as better streaming capability, higher compression for a given quality and lower latency.

Advances in scaleable video coding (SVC) address coding schemes for reliable video delivery to diverse clients over heterogeneous networks using available system resources, particularly where downstream client capabilities, system resources and network conditions are not known in advance. For example, clients may have different display resolutions, systems may have different caching or intermediate storage resources, and networks may have varying bandwidths, loss rates and best-effort or quality of service (QoS) capabilities. Other developments provide scalability at the bitstream level with good compression efficiency, and allow free combinations of scalable modes (such as spatial, temporal and SNR/fidelity scalability). Application areas include video surveillance systems, mobile streaming video, wireless multichannel video production and distribution and multiparty video telephony/conferencing.

Another rapidly evolving area is video intelligence. The ability of cameras to pan, tilt, zoom and panorama will be driven increasingly by system intelligence rather than manual intervention. Motion detection allows more efficient hard disk storage by only archiving video frames where a motion threshold is passed. The promise of video object recognition would allow automated surveillance monitoring, which is much more effective than manual surveillance monitoring.

FPGA Video and Image Processing Solutions: Managing Performance, Cost and Time to Market

Rapidly evolving resolutions, compressions and standards are creating a need for a higher performance, more flexible alternative to traditional DSP solutions. As technologies mature and volumes increase, cost will become more important. While DSP devices, ASSPs and ASICs can meet some of the industry’s needs, only FPGAs offer the combination of performance, low cost, reprogrammability and in-field upgrades needed for video and image processing applications.

DSP devices alone cannot meet the processing requirements of many video and imaging applications. FPGA solutions improve the price-to-performance ratio by letting FPGA coprocessors do the heavy lifting. For example, designers can implement cost-effective HD solutions using a single DSP device and a single FPGA instead of as many as 8 to 10 DSP devices, improving system integration and lowering cost. Because FPGAs have no nonrecurring engineering (NRE) costs, they are a cost-effective alternative to ASICs and ASSPs in low and mid volumes. To further lower costs, a migration path to structured ASICs is available for high volumes, making FPGAs ideal for both prototyping and production applications.

FPGAs can be used as common platforms in video solutions because, unlike ASICs and ASSPs, they are reprogrammable and can be easily upgraded in the field to support higher resolutions and new video standards, eliminating the risk of obsolescence. This flexibility allows you to innovate in real time to support new emerging standards or feature requests, and to quickly respond to competitive markets.

Video and Image Processing Solutions

Altera provides solutions for video and image processing through a wide range of development kits, intellectual property (IP) and reference designs. These complete FPGA solutions are obsolescence-proof and can easily be customized and optimized for cost, performance and functionality. Solutions can be targeted to any of Altera's latest device families, including the low-cost Cyclone™ II FPGAs and high-density, high-performance Stratix® II FPGAs. Stratix II solutions include a no-risk cost reduction path to HardCopy® II structured ASICs.

Video and image processing solutions include:

Pre- and postprocessing functions for video and imaging applications
Video system I/O including the digital video broadcast asynchronous serial interface (DVB-ASI) and serial digital video interface (SDI) standards
Video compression encoding and decoding for the latest standards, including H.264, JPEG, JPEG2000, MPEG-2, MPEG-4

Information on all Altera® video and image processing solutions—including Altera’s Video and Image Processing Suite, a collection of MegaCore® functions that can be used to facilitate the development of customer video and image processing designs—is available on www.altera.com/video_imaging. Figure 1 shows an example of the types of systems that can be developed using the new Video and Image Processing Suite.

Figure 1. Video Processing Example Design

System-Level Design for Video and Image Processing

High-level design tools increasingly help designers gain strategic advantages in the product design cycle and improve their time to market. Synplicity's Synplify DSP enables developers to rapidly create high-level video and image processing models that can be automatically synthesized into optimized RTL for FPGA implementation. This high-level synthesis approach focuses on algorithm behavior and design exploration without encumbering implementation details. Once the algorithm is verified and completed, the RTL code is synthesized and can be automatically optimized for speed, area or multichannel design considerations and optimally mapped into Stratix II or Cyclone II FPGA resources.

Synplify DSP also supports third-party IP such as the Altera Video and Image Processing Suite through its blackbox feature. By leveraging Altera IP and DSP synthesis technology together, designers can realize significant improvements in productivity and time to market.

Conclusion

FPGAs are ideal for a wide range of video and image processing applications such as broadcast infrastructure, medical imaging, HD videoconferencing, video surveillance and military imaging. Video and image processing solutions for Altera FPGAs, when combined with Synplicity design and verification tools suite, can improve cost, performance and productivity for many video and imaging applications. More information about the Altera video and image processing solutions can be found at www.altera.com/video_imaging.