MathWorks Pixel-Streaming Algorithms for Design and Implementation of Vision Systems on FPGAs and ASICs

MathWorks Pixel-Streaming Algorithms for Design and Implementation of Vision Systems on FPGAs and ASICs : MathWorks introduced Vision HDL Toolbox. Vision HDL Toolbox provides pixel-streaming algorithms for the design and implementation of vision systems on FPGAs and ASICs. The toolbox also includes a design framework that supports a diverse set of interface types, frame sizes, and frame rates, including high-definition (1080p) video. The image processing, video, and computer vision algorithms in the toolbox use an architecture appropriate for HDL implementations. Vision algorithm developers are challenged by the combination of increasing video frame sizes, frame rates, and the complexity of prototyping or implementing the vision algorithms on FPGA and ASIC platforms. Vision HDL Toolbox helps developers overcome these challenges by providing a library of image processing and computer vision algorithms specifically designed for FPGA and ASIC implementation, as well as automatic conversion between frames of various sizes and pixels. In addition, when used with HDL Coder, designers can generate readable and vendor-independent HDL code from these algorithms. And, with HDL Verifier, designers can connect the algorithms running on the FPGA or ASIC with frame-based test models running in MATLAB or Simulink.

“FPGAs in particular are an increasingly popular platform for image processing and computer vision systems,” said John Zhao, marketing manager at MathWorks. “The new Vision HDL Toolbox has been created to help developers prototype and implement systems faster, with shortened design cycles, and more efficiently, through the ability to identify design errors early in the workflow and minimize the time needed for writing HDL code.”

Key Vision HDL Toolbox Features include Image processing, video, and computer vision algorithms with a pixel-streaming architecture, including image enhancement, filtering, morphology, and statistics. Frame-to-pixel and pixel-to-frame conversions to integrate with frame-based processing capabilities in MATLAB and Simulink. Video synchronization signals for handling nonideal timing and resolution variations and configurable frame rates and frame sizes, including 60FPS for high-definition (1080p) video.

MathWorks is the leading developer of mathematical computing software. MATLAB, the language of technical computing, is a programming environment for algorithm development, data analysis, visualization, and numeric computation. Simulink is a graphical environment for simulation and Model-Based Design for multidomain dynamic and embedded systems. Engineers and scientists worldwide rely on these product families to accelerate the pace of discovery, innovation, and development in automotive, aerospace, electronics, financial services, biotech-pharmaceutical, and other industries.