Wednesday, 24. May 2017


KTH Research Project Database

KTH Research Projec...
PROJECT




Architectural and Civil Engineering


Chemistry and biotechnology


Computer Science & Information Technology


Electrical Engineering


Mathematics


Physics and Energy


Production and Mechanical Engineering


Social Sciences and Humanities


Environment and sustainable development


OVERVIEWS

»Research Fields

»Organisational Structure

»Persons



Scale-space theory for invariant and covariant visual receptive fields (» Remove from Infobox)

Research Leader: Professor Tony Lindeberg
PhD student Ylva Jansson


Computational Biology

When we humans interpret the visual information that reaches our eyes, we are able to maintain a stable perception although the visual stimuli vary substantially on the retina due to geometric transformations and lighting variations in the environment. This project aims at developing new generically useful methodologies for computing image features at the first levels of visual processing in terms of receptive fields, with emphasis on deriving invariant and covariant features under illumination transformations and on handling spatio-temporal image data (video) using time-causal and time-recursive image operations, with the aim of designing more robust and computationally efficient methods for visual recognition and video analysis.

The project is organised into the two tasks (A) Illumination-invariant receptive fields for visual recognition and (B) Time-causal and time-recursive receptive fields for video analysis and real-time image streams, with subgoals regarding theoretical analysis, discrete implementation and experimental evaluation.

The theories and algorithms developed in this way are intended as (i) general purpose primitives for building perceptual, cognitive or robotic vision systems or other tasks related to automated interpretation of visual information and (ii) computational tools for understanding possibilities for visual perception.



Period: 2015-01-01 - 2018-12-31

Keywords:
Computer Vision, Feature Detection, Invariance, Object Recognition, Receptive Fields

Project URL:
https://www.kth.se/profile/76171/page/computational-vision-at-csc-kth/

SOURCE OF FUNDING (1/1) 

VR (The Swedish Research Council)


SEARCH



»Advanced Search



INFOBOX (1/1) show all
»
Project: Scale-space theory for invariant and covariant visual receptive fields




Powered by AVERISinfo@avedas.com