A Real-Time FPGA-based Architecture for Optical Flow Computation

Autor:	C. Torres-Huitzil, S.E. Maya-Rueda, M.O. Arias-Estrada
Rok vydání:	2006
Předmět:	Hardware architecture Computer Science::Hardware Architecture Motion analysis Computer science Motion estimation Real-time computing Optical flow Optical computing Basis function Field-programmable gate array Matrix multiplication Computational science
Zdroj:	2003 IEEE International Workshop on Computer Architectures for Machine Perception.
DOI:	10.1109/camp.2003.1598166
Popis:	Motion estimation of a scene is an interesting problem in computer vision since it is the basis for the dynamic analysis of a scene. However this task is computational intensive for conventional processors. In this work, a FPGA-based hardware architecture for real-time motion estimation is proposed. The technique used for motion estimation is a variation of the optical flow algorithm where the problem is reformulated as a sum of overlapped basis functions, and solved as a linear system. The proposed architecture is based on a systolic approach and is composed of parallel modules organized in a regular structure. The systolic processor accelerates the matrix operations required to achieve real-time performance. The architecture design is presented. Preliminary results are shown and discussed
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::d58a031922f20bf32cd4f0b6b4c0f317 https://doi.org/10.1109/camp.2003.1598166 Zobrazit plný text záznamu