Deep cross-domain building extraction for selective depth estimation from oblique aerial imagery

@article{Ruf2018DeepCB,
  title={Deep cross-domain building extraction for selective depth estimation from oblique aerial imagery},
  author={Boitumelo Ruf and Laurenz Thiel and Martin Weinmann},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.08302}
}
With the technological advancements of aerial imagery and accurate 3d reconstruction of urban environments, more and more attention has been paid to the automated analyses of urban areas. In our work, we examine two important aspects that allow live analysis of building structures in city models given oblique aerial imagery, namely automatic building extraction with convolutional neural networks (CNNs) and selective real-time depth estimation from aerial imagery. We use transfer learning to… Expand
Large-Scale Synthetic Urban Dataset for Aerial Scene Understanding
TLDR
A novel method to generate synthetic large-scale dataset for geometric and semantic urban scene understanding from bird’s eye view and the experiment result show that, in both pure and combined mode, the dataset can improve the performance significantly. Expand
Efficient Surface-Aware Semi-Global Matching with Multi-View Plane-Sweep Sampling
TLDR
This work presents a hierarchical algorithm that allows for efficient depth and normal map estimation together with confidence measures for each estimate and shows that the results of this approach are comparable to the ones achieved by refined Structure-from-Motion pipelines, such as COLMAP, which are designed for offline processing. Expand

References

SHOWING 1-10 OF 40 REFERENCES
Extracting 3D urban models from oblique aerial images
TLDR
The matching pipeline tackles occlusions and large view-point changes are especially demanding during dense image matching can be very challenging for oblique imagery in complex urban environment by a coarse-to-fine modification of the SGM method. Expand
The Cityscapes Dataset for Semantic Urban Scene Understanding
TLDR
This work introduces Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling, and exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Expand
DETERMINING PLANE-SWEEP SAMPLING POINTS IN IMAGE SPACE USING THE CROSS-RATIO FOR IMAGE-BASED DEPTH ESTIMATION
Abstract. With the emergence of small consumer Unmanned Aerial Vehicles (UAVs), the importance and interest of image-based depth estimation and model generation from aerial images has greatlyExpand
A comprehensive study on object proposals methods for vehicle detection in aerial images
Detecting vehicles in aerial images is an important task in many applications such as traffic monitoring or screening of large areas. In general, vehicle detection in aerial images is performed byExpand
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Expand
Benchmarking High Density Image Matching for Oblique Airborne Imagery
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 researchExpand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
ISPRS benchmark for multi - platform photogrammetry
TLDR
The acquired data, the pre-processing steps, the evaluation procedures as well as some preliminary results achieved with commercial software will be presented. Expand
Geometric Change Detection in Urban Environments Using Images
TLDR
The proposed method can be used to significantly optimize the process of updating the 3D model of an urban environment that is changing overtime, by restricting this process to only those areas where changes are detected. Expand
The ISPRS benchmark on urban object classification and 3D building reconstruction
TLDR
The results achieved by different methods are compared and analysed to identify promising strategies for automatic urban object extraction from current airborne sensor data, but also common problems of state-of-the-art methods. Expand
...
1
2
3
4
...