Real-Time Primary Image Processing

Abstract

Image processing operations have been classified into three main levels, namely low (primary), intermediate, and high. In order to combine speed and flexibility, an optimum hardware/software configuration is required. For multitask primary processing, a pipeline configuration is proposed. This structure, which is an interface between the sensing element (camera) and the main processing system, achieves real time video signal preprocessing, during the image acquisition time. In order to form the working neighborhoods, the input image signal is delayed (two lines and three pixels). Thus, locally 3×3 type processing modules are created. A successive comparison median filter and a logical filter for edge detection are implemented for a pipeline configuration. On the other hand, for low level, intermediate, and high level operations, software algorithms on parallel platforms are proposed. Finally, a case study of lines detection using directional filter discusses the performance dependency on number of processors.