A reconfigurable architecture for autonomous visual-navigation

Authors:
Jose Antonio Boluda;Fernando Pardo
Affiliations:
Departament d'Informàtica, Universitat de Valéncia, Avda. Vicent Andrés Estellés S/N, 46100 Burjassot, Spain;Departament d'Informàtica, Universitat de Valéncia, Avda. Vicent Andrés Estellés S/N, 46100 Burjassot, Spain
Venue:
Machine Vision and Applications
Year:
2003

Citing 12
Cited 0

Parallel algorithms: for digital image processing, computer vision and neural networks

Parallel algorithms: for digital image processing, computer vision and neural networks
Parallel stereo and motion estimation

Parallel algorithms
Affine analysis of image sequences

Affine analysis of image sequences
The computation of optical flow

ACM Computing Surveys (CSUR)
The local structure of space-variant images

Neural Networks
Dynamic Vergence Using Log-Polar Images

International Journal of Computer Vision
Real-Time Image Processing on a Custom Computing Platform

Computer
Computer-Aided Hardware-Software Codesign

IEEE Micro
On the Advantages of Polar and Log-Polar Mapping for Direct Estimation of Time-To-Impact from Optical Flow

IEEE Transactions on Pattern Analysis and Machine Intelligence
Detecting Motion Independent of the Camera Movement Through a Log-Polar Differential Approach

CAIP '97 Proceedings of the 7th International Conference on Computer Analysis of Images and Patterns
Space Variant Vision and Pipelined Architecture for Time to Impact Computation

CAMP '00 Proceedings of the Fifth IEEE International Workshop on Computer Architectures for Machine Perception (CAMP'00)
A Method for Multiple Rigid-object Motion Segmentation based on Detection and Consistent Matching of Relevant Points in Image Sequences

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 4 - Volume 4

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes the design of a reconfigurable architecture for implementing image processing algorithms. This architecture is a pipeline of small identical processing elements that contain a programmable logic device (FPGA) and double port memories. This processing system has been adapted to accelerate the computation of differential algorithms. The log-polar vision selectively reduces the amount of data to be processed and simplifies several vision algorithms, making possible their implementation using few hard-ware resources. The reconfigurable architecture design has been devoted to implementation, and has been employed in an autonomous platform, which has power consumption, size and weight restrictions. Two different vision algorithms have been implemented in the reconfigurable pipeline, for which some experimental results are shown.