HPAT Indexing for Fast Object/Scene Recognition Based on Local Appearance

A Mobile Vision System for Urban Detection with Informative Local Descriptors

“…While [13] achieved only moderate performance (≈ 86% accuracy), our i-SIFT system achieved ≈ 91% correct identifications. Note that the avg.…”

“…ZuBuD Performance Results In similar manner, we applied i-SIFT key matching to the ZuBuD database 2 (201 buildings, 5 views each, 115 query images [13]). While [13] achieved only moderate performance (≈ 86% accuracy), our i-SIFT system achieved ≈ 91% correct identifications.…”

“…[1] presented a framework for structure recovery that aims at the same time towards posterior building recognition. [13] provided the first innovative attempt on building identification proposing local affine features for object matching. [15] introduced image retrieval methodology for the indexing of visually relevant information from the web for mobile location recognition.…”

A Mobile Vision Service for Multimedia Tourist Applications in Urban Environments

“…In similar manner, we applied i-SIFT key matching to the ZuBuD database 2 (201 buildings, 5 views each, 115 query images [4]). While [4] achieved only moderate performance (≈ 86% accuracy), our i-SIFT system achieved ≈ 91% correct identifications.…”

“…[3] presented a framework for structure recovery that aims at the same time towards posterior building recognition. [4] provided the first innovative attempt on building identification proposing local affine features for object matching. [5] introduced image retrieval methodology for the indexing of visually relevant information from the web for mobile location recognition.…”