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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Online augmentation of an oblique aerial image sequence with structuralinformation is an essential aspect in the process of 3D scene interpretationand analysis. One key aspect in this is the efficient dense image matching anddepth estimation. Here, the Semi-Global Matching (SGM) approach has proven tobe one of the most widely used algorithms for efficient depth estimation,providing a good trade-off between accuracy and computational complexity.However, SGM only models a first-order smoothness assumption, thus favoringfronto-parallel surfaces. In this work, we present a hierarchical algorithmthat allows for efficient depth and normal map estimation together withconfidence measures for each estimate. Our algorithm relies on a plane-sweepmulti-image matching followed by an extended SGM optimization that allows toincorporate local surface orientations, thus achieving more consistent andaccurate estimates in areasmade up of slanted surfaces, inherent to obliqueaerial imagery. We evaluate numerous configurations of our algorithm on twodifferent datasets using an absolute and relative accuracy measure. In ourevaluation, we show that the results of our approach are comparable to the onesachieved by refined Structure-from-Motion (SfM) pipelines, such as COLMAP,which are designed for offline processing. In contrast, however, our approachonly considers a confined image bundle of an input sequence, thus allowing toperform an online and incremental computation at 1Hz-2Hz.

Efficient Surface-Aware Semi-Global Matching with Multi-View Plane-Sweep Sampling