Unsupervised visual landmark extraction for place recognition

Evangelos Sariyanidi*, Hakan Temeltaş

*Bu çalışma için yazışmadan sorumlu yazar

Araştırma sonucu: ???type-name???Konferans katkısıbilirkişi

Özet

This paper presents an approach to detect visually salient patches in order to use them for visual place recognition. We formulate the saliency detection problem as an optimization problem, and define an energy function which describes the distinctiveness of a given image patch. We employ a Branch & Bound based search technique to efficiently find the global optimum of the energy function. Moreover, we use integral images to further increase the efficiency of the approach. The proposed saliency detection technique is able to detect patches which are suitable to be used as visual landmarks, and it performs with very high efficiency.

Orijinal dilİngilizce
Ana bilgisayar yayını başlığıFull Motion Video (FMV) Workflows and Technologies for Intelligence, Surveillance, and Reconnaissance (ISR) and Situational Awareness
DOI'lar
Yayın durumuYayınlandı - 2012
EtkinlikFull Motion Video (FMV) Workflows and Technologies for Intelligence, Surveillance, and Reconnaissance (ISR) and Situational Awareness - Baltimore, MD, United States
Süre: 23 Nis 201224 Nis 2012

Yayın serisi

AdıProceedings of SPIE - The International Society for Optical Engineering
Hacim8386
ISSN (Basılı)0277-786X

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???Full Motion Video (FMV) Workflows and Technologies for Intelligence, Surveillance, and Reconnaissance (ISR) and Situational Awareness
Ülke/BölgeUnited States
ŞehirBaltimore, MD
Periyot23/04/1224/04/12

Parmak izi

Unsupervised visual landmark extraction for place recognition' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

Alıntı Yap