On-chip ego-motion estimation based on optical flow

Authors:
Mauricio Vanegas;Leonardo Rubio;Matteo Tomasi;Javier Diaz;Eduardo Ros
Affiliations:
Department of Computer Architecture and Technology, University of Granada, Granada, Spain and PSPC-Group, Department of Biophysical and Electronic Engineering (DIBE), University of Genoa, Italy;Department of Computer Architecture and Technology, University of Granada, Granada, Spain;Department of Computer Architecture and Technology, University of Granada, Granada, Spain;Department of Computer Architecture and Technology, University of Granada, Granada, Spain;Department of Computer Architecture and Technology, University of Granada, Granada, Spain
Venue:
ARC'11 Proceedings of the 7th international conference on Reconfigurable computing: architectures, tools and applications
Year:
2011

Citing 9
Cited 0

Subspace methods for recovering rigid motion I: algorithm and implementation

International Journal of Computer Vision
Analog-VLSI, array-processor-based, Bayesian, multi-scale optical flow estimation: Research Articles

International Journal of Circuit Theory and Applications - Special Issue on CNN Technology (Part 1)
Vehicle Ego-Motion Estimation and Moving Object Detection using a Monocular Camera

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 04
Optimal instantaneous rigid motion estimation insensitive to local minima

Computer Vision and Image Understanding
Superpipelined high-performance optical-flow computation architecture

Computer Vision and Image Understanding
An Efficient Linear Method for the Estimation of Ego-Motion from Optical Flow

Proceedings of the 31st DAGM Symposium on Pattern Recognition
Hardware implementation of optical flow constraint equation using FPGAs

Computer Vision and Image Understanding
Multi-port abstraction layer for FPGA intensive memory exploitation applications

Journal of Systems Architecture: the EUROMICRO Journal
A phase-based approach to the estimation of the optical flow field using spatial filtering

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel system on chip (SoC) is presented for estimating the ego-motion of the vehicle based on optical flow cues. The main novelty of the system consists in its implementation as an on-chip hybrid hardware/ software system. The improvements in the FPGA technology allows to have programmable logic resources accompanied by processors on the same chip. In this way, inherently sequential tasks are implemented as software modules executed in embedded general purpose processors while hardware friendly modules are implemented in specific purpose co-processing engines. The proposed SoC is capable of estimating egomotion by using the PowerPC available in the FPGA XC4VFX60-10 of Xilinx.