Authors : A.Ben Abdelali , A. Mtibaa , E. Bourennane and M. Abid
Abstract: Content based video indexing is currently employed in variety of new applications, including video surveillance, Access to real time incoming video, intelligent transmission of video data, etc. Several methods aiming at automating this time and resource consuming process have appeared in literature. They employ several content analysis and feature extraction techniques including, typically, signal and image processing techniques to analyze color, texture, form, sound, etc. Implementing such applications on a general purpose computer can be easier, but not sufficient to support the complexity and the performance needs of some new applications. The use of application specific hardware permits to offer much greater speed and performance. In this study we focus on hardware implementation of content based video indexing techniques by using the FPGA technology. We aim to propose hardware modules that can satisfy requirements of applications under hard constraints, such as real time applications and applications of high complexity. We represent tow examples of micro-architectures related to the dominant colors descriptor and the compact color descriptor. The synthesis and simulation results for the provided solutions are also given.
A.Ben Abdelali , A. Mtibaa , E. Bourennane and M. Abid , 2006. Design of Hardware Accelerators for Content Based Video Indexing. Asian Journal of Information Technology, 5: 976-984.