Biological models for active vision: towards a unified architecture

Authors:
Kasim Terzić;David Lobato;Mário Saleiro;Jaime Martins;Miguel Farrajota;J. M. F. Rodrigues;J. M. H. Du Buf
Affiliations:
Vision Laboratory (LARSyS), University of the Algarve, Faro, Portugal;Vision Laboratory (LARSyS), University of the Algarve, Faro, Portugal;Vision Laboratory (LARSyS), University of the Algarve, Faro, Portugal;Vision Laboratory (LARSyS), University of the Algarve, Faro, Portugal;Vision Laboratory (LARSyS), University of the Algarve, Faro, Portugal;Vision Laboratory (LARSyS), University of the Algarve, Faro, Portugal;Vision Laboratory (LARSyS), University of the Algarve, Faro, Portugal
Venue:
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
Year:
2013

Citing 16
Cited 0

Connectionist Architectures for Artificial Intelligence

Computer
A process-grammar for shape

Artificial Intelligence
From image sequences towards conceptual descriptions

Image and Vision Computing
Neural mechanisms for the robust representation of junctions

Neural Computation
One-Shot Learning of Object Categories

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Object Recognition with Cortex-Like Mechanisms

IEEE Transactions on Pattern Analysis and Machine Intelligence
Video understanding for complex activity recognition

Machine Vision and Applications
A stochastic grammar of images

Foundations and Trends® in Computer Graphics and Vision
On scene interpretation with description logics

Image and Vision Computing
Ontology based complex object recognition

Image and Vision Computing
Combining structural descriptions and image-based representations for image, object, and scene recognition

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Biologically inspired mobile robot vision localization

IEEE Transactions on Robotics
Learning the Compositional Nature of Visual Object Categories for Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Dynamic Neural Fields as Building Blocks of a Cortex-Inspired Architecture for Robotic Scene Representation

IEEE Transactions on Autonomous Mental Development
Mapping a Suburb With a Single Camera Using a Biologically Inspired SLAM System

IEEE Transactions on Robotics
Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Building a general-purpose, real-time active vision system completely based on biological models is a great challenge. We apply a number of biologically plausible algorithms which address different aspects of vision, such as edge and keypoint detection, feature extraction, optical flow and disparity, shape detection, object recognition and scene modelling into a complete system. We present some of the experiments from our ongoing work, where our system leverages a combination of algorithms to solve complex tasks.