ABSTRACT:Both, improvements in camera technology and new pixel-wise matching approaches triggered the further development of software tools for image based 3D reconstruction. Meanwhile research groups as well as commercial vendors provide photogrammetric software to generate dense, reliable and accurate 3D point clouds and Digital Surface Models (DSM) from highly overlapping aerial images. In order to evaluate the potential of these algorithms in view of the ongoing software developments, a suitable test bed is provided by the ISPRS/EuroSDR initiative Benchmark on High Density Image Matching for DSM Computation. This paper discusses the proposed test scenario to investigate the potential of dense matching approaches for 3D data capture from oblique airborne imagery. For this purpose, an oblique aerial image block captured at a GSD of 6 cm in the west of Zürich by a Leica RCD30 Oblique Penta camera is used. Within this paper, the potential test scenario is demonstrated using matching results from two software packages, Agisoft PhotoScan and SURE from University of Stuttgart. As oblique images are frequently used for data capture at building facades, 3D point clouds are mainly investigated at such areas. Reference data from terrestrial laser scanning is used to evaluate data quality from dense image matching for several facade patches with respect to accuracy, density and reliability.

This paper aims at façade reconstruction for subsequent enrichment of LOD2 building models. We use point clouds from dense image matching with imagery both from Mobile Mapping systems and oblique airborne cameras. The interpretation of façade structures is based on a geometric reconstruction. For this purpose a pre-segmentation of the point cloud into façade points and non-façade points is necessary. We present an approach for point clouds with limited geometric accuracy where a geometric segmentation might fail. Our contribution is a radiometric segmentation approach. Via local point features, based on a clustering in hue space, the point cloud is segmented into façade-points and non-façade points. This way, the initial geometric reconstruction step can be bypassed and point clouds with limited accuracy can still serve as input for the façade reconstruction and modelling approach.

<p><strong>Abstract.</strong> We propose a feature-based approach for semantic mesh segmentation in an urban scenario using real-world training data. There are only few works that deal with semantic interpretation of urban triangle meshes so far. Most 3D classifications operate on point clouds. However, we claim that point clouds are an intermediate product in the photogrammetric pipeline. For this reason, we explore the capabilities of a Convolutional Neural Network (CNN) based approach to semantically enrich textured urban triangle meshes as generated from LiDAR or Multi-View Stereo (MVS). For each face within a mesh, a feature vector is computed and fed into a multi-branch 1D CNN. Ordinarily, CNNs are an end-to-end learning approach operating on regularly structured input data. Meshes, however, are not regularly structured. By calculating feature vectors, we enable the CNN to process mesh data. By these means, we combine explicit feature calculation and feature learning (hybrid model). Our model achieves close to 80% Overall Accuracy (OA) on dedicated test meshes. Additionally, we compare our results with a default Random Forest (RF) classifier that performs slightly worse. In addition to slightly better performance, the 1D CNN trains faster and is faster at inference.</p>

No abstract

No abstract