DocumentCode :
3096081
Title :
Architectures for FPGA-Based Implementation of Motion Estimation of Dynamic Obstacles for Autonomous Robot Navigation
Author :
Mishra, Prabhakar ; Apoorva, R. ; Parvatikar, Bhavani B. ; Nair, Lakshmi
Author_Institution :
Dept. of Telecommun. Eng., PES Inst. of Technol., Bangalore, India
fYear :
2011
fDate :
26-28 July 2011
Firstpage :
292
Lastpage :
297
Abstract :
Real time implementation is the key challenge in vision-based detection of dynamic obstacles in autonomous robot navigation systems. The Discrete Cosine Transform-Based Motion Estimation (DXT-ME) Algorithm, proposed for video coding has inherently parallel, low complexity computations and therefore, can be implemented in real time. It provides the exact displacement of the object of interest, making it suitable for fine-grained tracking. As two dimensional cosine/sine transforms are the main computations involved, this paper presents a comparison of three architectures for the FPGA implementation of the same. An architecture for DXT-ME is proposed.
Keywords :
collision avoidance; discrete cosine transforms; field programmable gate arrays; mobile robots; motion estimation; robot vision; video coding; DXT-ME Algorithm; FPGA-based Implementation; autonomous robot navigation; discrete cosine transform; dynamic obstacle detection; motion estimation; sine transforms; video coding; vision-based detection; Arrays; Field programmable gate arrays; Heuristic algorithms; Lattices; Polynomials; Transforms; Autonomous Robot Navigation; Discrete Cosine Transform; Motion Estimation; Vision-based Tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence, Communication Systems and Networks (CICSyN), 2011 Third International Conference on
Conference_Location :
Bali
Print_ISBN :
978-1-4577-0975-3
Electronic_ISBN :
978-0-7695-4482-3
Type :
conf
DOI :
10.1109/CICSyN.2011.68
Filename :
6005718
Link To Document :
بازگشت