Facade Interpretation Using a Marked Point Process

Wenzel, Susanne; Förstner, Wolfgang

doi:10.5194/isprsannals-iii-3-363-2016

Cited by 3 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gadde et al (2016) segment 2D images and 3D point clouds of building facades and present empirical results on all available 2D and 3D facade benchmark datasets. Symmetries in the facade imagery can also be exploited by applying specific shape priors for energy minimization (Teboul et al, 2010;Wenzel and Förstner, 2016). Mathias et al (2016) present a three layered approach consisting of an initial semantic segmentation, the subsequent object detection and a final layer introducing building-specific meta-knowledge by so-called weak architectural principles.…”

Section: Related Workmentioning

confidence: 99%

Neural Networks for the Classification of Building Use From Street-View Imagery

Laupheimer¹,

Tutzauer²,

Haala³

et al. 2018

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Within this paper we propose an end-to-end approach for classifying terrestrial images of building facades into five different utility classes (<i>commercial, hybrid, residential, specialUse, underConstruction</i>) by using Convolutional Neural Networks (CNNs). For our examples we use images provided by Google Street View. These images are automatically linked to a coarse city model, including the outlines of the buildings as well as their respective use classes. By these means an extensive dataset is available for training and evaluation of our Deep Learning pipeline. The paper describes the implemented end-to-end approach for classifying street-level images of building facades and discusses our experiments with various CNNs. In addition to the classification results, so-called Class Activation Maps (CAMs) are evaluated. These maps give further insights into decisive facade parts that are learned as features during the training process. Furthermore, they can be used for the generation of abstract presentations which facilitate the comprehension of semantic image content. The abstract representations are a result of the stippling method, an importance-based image rendering.

show abstract

Section: Related Workmentioning

confidence: 99%

Neural Networks for the Classification of Building Use From Street-View Imagery

Laupheimer¹,

Tutzauer²,

Haala³

et al. 2018

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…In the following years, a lot of work was done on automatic window detection. Most approaches require prior knowledge [Wen16]. Often, either assumptions of a typical grid structure of windows in facades [LR04; WF08; RL10] or assumptions about the geometry and appearance of windows [CS08] are used.…”

Section: Facade Image Interpretationmentioning

confidence: 99%

“…There are different methods to detect regions of interest, such as windows, in images [Wen16]. The two most important techniques are gradient projection to find aligned edges [LR04;RL10] and the use of classifiers that detect regions of interest within the image [ASJ+07;WF08].…”

Section: Facade Image Interpretationmentioning

confidence: 99%

See 1 more Smart Citation

Robust and Accurate Detection of Mid-level Primitives for 3D Reconstruction in Man-Made Environments

Wolters¹

View full text Add to dashboard Cite

The detection of geometric primitives such as points, lines and arcs is a fundamental step in computer vision techniques like image analysis, pattern recognition and 3D scene reconstruction. In this thesis, we present a framework that enables a reliable detection of geometric primitives in images. The focus is on application in man-made environments, although the process is not limited to this. The method provides robust and subpixel accurate detection of points, lines and arcs, and builds up a graph describing the topological relationships between the detected features. The detection method works directly on distorted perspective and fisheye images. The additional recognition of repetitive structures in images ensures the unambiguity of the features in their local environment. We can show that our approach achieves a high localization accuracy comparable to the state-of-the-art methods and at the same time is more robust against disturbances caused by noise. In addition, our approach allows extracting more fine details in the images. The detection accuracy achieved on the real-world scenes is constantly above that achieved by the other methods. Furthermore, our process can reliably distinguish between line and arc segments. The additional topological information extracted by our method is largely consistent over several images of a scene and can therefore be a support for subsequent processing steps, such as matching and correspondence search. We show how the detection method can be integrated into a complete feature-based 3D reconstruction pipeline and present a novel reconstruction method that uses the topological relationships of the features to create a highly abstract but semantically rich 3D model of the reconstructed scenes, in which certain geometric structures can easily be detected.

show abstract

A future for learning semantic models of man-made environments

Förstner

2016

2016 23rd International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

Facade Interpretation Using a Marked Point Process

Cited by 3 publications

References 18 publications

Neural Networks for the Classification of Building Use From Street-View Imagery

Neural Networks for the Classification of Building Use From Street-View Imagery

Robust and Accurate Detection of Mid-level Primitives for 3D Reconstruction in Man-Made Environments

A future for learning semantic models of man-made environments

Contact Info

Product

Resources

About