ISPRS TC II Mid-term Symposium "Towards Photogrammetry 2020"
Untertitel:
4–7 June 2018, Riva del Garda, Italy
Reihentitel:
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Bandnummer Reihe:
IV-2
Konferenztitel:
ISPRS TC II Mid-term Symposium (2018, Riva del Garda)
Tagungsort:
Riva del Garda, Italy
Jahr der Konferenz:
2018
Datum Beginn der Konferenz:
04.06.2018
Datum Ende der Konferenz:
07.06.2018
Verlegende Institution:
ISPRS
Jahr:
2018
Seiten (Monografie):
223-230
Sprache:
Englisch
Stichwörter:
Facade Segmentation ; Model Fitting ; CNN ; Object Detection
Abstract:
e present a pipeline for high quality semantic segmentation of building facades using Structured Random Forest (SRF), Region Proposal Network (RPN) based on a Convolutional Neural Network (CNN) as well as rectangular fitting optimization. Our main contribution is that we employ features created by the RPN as channels in the SRF.We empirically show that this is very effective especially for doors and windows. Our pipeline is evaluated on two datasets where we outperform current state-of-the-art methods. Additionally, we quantify the contribution of the RPN and the rectangular fitting optimization on the accuracy of the result. «
e present a pipeline for high quality semantic segmentation of building facades using Structured Random Forest (SRF), Region Proposal Network (RPN) based on a Convolutional Neural Network (CNN) as well as rectangular fitting optimization. Our main contribution is that we employ features created by the RPN as channels in the SRF.We empirically show that this is very effective especially for doors and windows. Our pipeline is evaluated on two datasets where we outperform current state-of-the-art m... »