English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

SfM (Structure from Motion) has been extensively used for UAV (UnmannedAerial Vehicle) image orientation. Its efficiency is directly influenced byfeature matching. Although image retrieval has been extensively used for matchpair selection, high computational costs are consumed due to a large number oflocal features and the large size of the used codebook. Thus, this paperproposes an efficient match pair retrieval method and implements an integratedworkflow for parallel SfM reconstruction. First, an individual codebook istrained online by considering the redundancy of UAV images and local features,which avoids the ambiguity of training codebooks from other datasets. Second,local features of each image are aggregated into a single high-dimension globaldescriptor through the VLAD (Vector of Locally Aggregated Descriptors)aggregation by using the trained codebook, which remarkably reduces the numberof features and the burden of nearest neighbor searching in image indexing.Third, the global descriptors are indexed via the HNSW (Hierarchical NavigableSmall World) based graph structure for the nearest neighbor searching. Matchpairs are then retrieved by using an adaptive threshold selection strategy andutilized to create a view graph for divide-and-conquer based parallel SfMreconstruction. Finally, the performance of the proposed solution has beenverified using three large-scale UAV datasets. The test results demonstratethat the proposed solution accelerates match pair retrieval with a speedupratio ranging from 36 to 108 and improves the efficiency of SfM reconstructionwith competitive accuracy in both relative and absolute orientation.

Efficient Match Pair Retrieval for Large-scale UAV Images via Graph Indexed Global Descriptor