A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Improved Window Detection in Facade Images
Abstract A variety of applications require detailed geometric information about a building’s hull. In particular, windows are of high interest in this context. However, common 3D models only roughly outline existing buildings’ geometrical outward appearance. The field of application is, thus, severely limited by now. In this paper, we propose an approach to the automatic detection of windows in facade images complementing common building models by information derived from detected windows to enable new opportunities and widen the spectrum of applications. Therefore, we apply a soft cascaded classifier to identify windows in patches of facade images. Moreover, a postprocessing is applied to the detections. We initially refine their dimensions and alignment on the facade. From these we infer so far non-detected windows. With an overall detection rate of 95 and 97% precision our proposed detection system yields sufficient results for complementing existing 3D building models by information of the detected windows.
Improved Window Detection in Facade Images
Abstract A variety of applications require detailed geometric information about a building’s hull. In particular, windows are of high interest in this context. However, common 3D models only roughly outline existing buildings’ geometrical outward appearance. The field of application is, thus, severely limited by now. In this paper, we propose an approach to the automatic detection of windows in facade images complementing common building models by information derived from detected windows to enable new opportunities and widen the spectrum of applications. Therefore, we apply a soft cascaded classifier to identify windows in patches of facade images. Moreover, a postprocessing is applied to the detections. We initially refine their dimensions and alignment on the facade. From these we infer so far non-detected windows. With an overall detection rate of 95 and 97% precision our proposed detection system yields sufficient results for complementing existing 3D building models by information of the detected windows.
Improved Window Detection in Facade Images
Neuhausen, Marcel (author) / König, Markus (author)
2018-10-04
7 pages
Article/Chapter (Book)
Electronic Resource
English
Window detection , Cascaded classifier , Urban environments , 3D building reconstruction Engineering , Building Construction and Design , Data Mining and Knowledge Discovery , Building Repair and Maintenance , Computer-Aided Engineering (CAD, CAE) and Design , Light Construction, Steel Construction, Timber Construction , Construction Management
| Online Contents | 1999
| British Library Online Contents | 1999