IPOL - A Domain Specific Language for Image Processing Applications
IPOL - A Domain Specific Language for Image Processing Applications
复制标题
IPOL - 用于图像处理应用程序的领域特定语言
DOI:
--
复制
发表时间:
2015
期刊:
影响因子:
--
通讯作者:
D. Fey
中科院分区:
文献类型:
--
作者:
C. Hartmann;M. Reichenbach;D. Fey
—In recent years, the use of image processing systems has increased steadily. However, most of them are very complex and contain several tasks with different complexities which result in varying requirements for computing architectures. Neverthe-less, a general processing scheme in every image processing application has a similar structure, called image processing pipeline: (1) capturing an image, (2) pre-processing using local operators, (3) processing with global operators and (4) post-processing using complex operations. Therefore, application-specialized hardware solutions combined in a heterogeneous system are used for image processing. To archive this, finding an optimal heterogeneous hardware architecture to meet the image processing application requirements is the central problem and still unsolved. Instead, engineers use languages like VHDL, Verilog, C/C++ and Cuda for designing such systems. But, these kind of languages are not suitable for system analysis - they provide a hardware specific solution for a specific algorithm. Therefore, a holistic modeling of a complete image processing pipeline, with automatic optimization and assignment to different heterogeneous computing cores is not possible. To overcome this problem, we propose in this paper a new domain specific language, called Image Processing Operator Language (IPOL). This description language contain all needed components hardware components like Sensors, Displays, execution units and software parts like image processing algorithms.