Conference paper

BREJCHA Jan and ČADÍK Martin. Camera Orientation Estimation in Natural Scenes Using Semantic Cues. In: 2018 International Conference on 3D Vision. Verona: IEEE Computer Society, 2018, pp. 208-217. ISBN 978-1-5386-2610-8.
Publication language:english
Original title:Camera Orientation Estimation in Natural Scenes Using Semantic Cues
Title (cs):Odhad orientace kamery v přírodních scénách s využitím sémantické segmentace
Pages:208-217
Proceedings:2018 International Conference on 3D Vision
Conference:International Conference on 3D Vision 2018
Place:Verona, IT
Year:2018
ISBN:978-1-5386-2610-8
DOI:10.1109/3DV.2018.00033
Publisher:IEEE Computer Society
Keywords
camera orientation estimation, camera calibration, semantic segmentation, digital elevation model of a terrain, OpenStreetMap, geo-localization, computer vision, computer graphics
Annotation
Camera orientation estimation in natural scenes has recently been approached by several methods, which rely mainly on matching a single modality - edges or horizon lines with 3D digital elevation models. In contrast to previous works, our new image to model matching scheme is based on a fusion of multiple modalities and is designed to be naturally extensible with different cues. In this paper, we use semantic segments and edges. To our knowledge, we are the first to consider using semantic segments jointly with edges for alignment with digital elevation model. We show that high-level features, such as semantic segments, complement the low-level edge information and together help to estimate the camera orientation more robustly compared to methods relying solely on edges or horizon lines. In a series of experiments, we show that segment boundaries tend to be imprecise and important information for matching is encoded in the segment area and a coarse shape. Intuitively, semantic segments encode low frequency information as opposed to edges, which encode high frequencies. Our experiments exhibit that semantic segments and edges are complementary, improving camera orientation estimation reliability when used together. We demonstrate that our method combining semantic and edge features is able to reach state-of-the-art performance on three datasets.
BibTeX:
@INPROCEEDINGS{
   author = {Jan Brejcha and Martin {\v{C}}ad{\'{i}}k},
   title = {Camera Orientation Estimation in Natural Scenes
	Using Semantic Cues},
   pages = {208--217},
   booktitle = {2018 International Conference on 3D Vision},
   year = {2018},
   location = {Verona, IT},
   publisher = {IEEE Computer Society},
   ISBN = {978-1-5386-2610-8},
   doi = {10.1109/3DV.2018.00033},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.en.iso-8859-2?id=11829}
}

Your IPv4 address: 3.91.79.74
Switch to https

DNSSEC [dnssec]