Facade Segmentation with a Structured Random Forest
Herausgeber Sammlung:
International Society for Photogrammetry and Remote Sensing (ISPRS)
Titel Konferenzpublikation:
ISPRS Hannover Workshop: HRIGI 17 - CMRT 17 - ISA 17 - EuroCOW 17, 6-9 June 2017, Hannover, Germany
Zeitschrift:
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Heftnummer:
IV-1/W1
Konferenztitel:
International Society for Photogrammetry and Remote Sensing Workshop (14., 2017, Hannover); European Calibration and Orientation Workshop (2017, Hannover)
Tagungsort:
Hannover
Jahr der Konferenz:
2017
Datum Beginn der Konferenz:
06.06.2017
Datum Ende der Konferenz:
09.06.2017
Verlegende Institution:
International Society for Photogrammetry and Remote Sensing
Jahr:
2017
Seiten von - bis:
175-181
Sprache:
Englisch
Stichwörter:
Facade ; Image interpretation ; Structured learning ; Random Forest
Abstract:
In this paper we present a bottom-up approach for the semantic segmentation of building facades. Facades have a predefined topology, contain specific objects such as doors and windows and follow architectural rules. Our goal is to create homogeneous segments for facade objects. To this end, we have created a pixelwise labeling method using a Structured Random Forest. According to the evaluation of results for two datasets with the classifier we have achieved the above goal producing a nearly noise-free labeling image and perform on par or even slightly better than the classifier-only stages of state-of-the-art approaches. This is due to the encoding of the local topological structure of the facade objects in the Structured Random Forest. Additionally, we have employed an iterative optimization approach to select the best possible labeling. «
In this paper we present a bottom-up approach for the semantic segmentation of building facades. Facades have a predefined topology, contain specific objects such as doors and windows and follow architectural rules. Our goal is to create homogeneous segments for facade objects. To this end, we have created a pixelwise labeling method using a Structured Random Forest. According to the evaluation of results for two datasets with the classifier we have achieved the above goal producing a nearly noi... »