Bottom-up and top-down object matching using asynchronous agents and a contrario principles

Abstract : We experiment a vision architecture for object matching based on a hierarchy of independent agents running asynchronously in parallel. Agents communicate through bidirectional signals, enabling the mix of top-down and bottom-up influences. Following the so-called a contrario principle, each signal is given a strength according to the statistical relevance of its associated visual data. By handling most important signals first, the system focuses on most promising hypotheses and provides relevant results as soon as possible. Compared to an equivalent feed-forward and sequential algorithm, our architecture is shown capable of handling more visual data and thus reach higher detection rates in less time.
Document type :
Conference papers
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01500849
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Monday, April 3, 2017 - 5:13:31 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:05 AM
Long-term archiving on : Tuesday, July 4, 2017 - 1:54:24 PM

File

Liris-3445.pdf
Files produced by the author(s)

Identifiers

Citation

Nicolas Burrus, Thierry Bernard, Jean-Michel Jolion. Bottom-up and top-down object matching using asynchronous agents and a contrario principles. 6th International Conference on Computer Vision Systems (ICVS 2008), May 2008, Santorini, Greece. pp.343-352, ⟨10.1007/978-3-540-79547-6_33⟩. ⟨hal-01500849⟩

Share

Metrics

Record views

240

Files downloads

92