TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Image-Based Localization Using Hourglass Networks

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
KustantajaIEEE
Sivut870-877
Sivumäärä8
ISBN (elektroninen)9781538610343
DOI - pysyväislinkit
TilaJulkaistu - 19 tammikuuta 2018
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE International Conference on Computer Vision Workshops -
Kesto: 1 tammikuuta 1900 → …

Conference

ConferenceIEEE International Conference on Computer Vision Workshops
Ajanjakso1/01/00 → …

Tiivistelmä

In this paper, we propose an encoder-decoder convolutional neural network (CNN) architecture for estimating camera pose (orientation and location) from a single RGB-image. The architecture has a hourglass shape consisting of a chain of convolution and up-convolution layers followed by a regression part. The up-convolution layers are introduced to preserve the fine-grained information of the input image. Following the common practice, we train our model in end-to-end manner utilizing transfer learning from large scale classification data. The experiments demonstrate the performance of the approach on data exhibiting different lighting conditions, reflections, and motion blur The results indicate a clear improvement over the previous state-of-the-art even when compared to methods that utilize sequence of test frames instead of a single frame.