3D all the way: Semantic segmentation of urban scenes from start to end in 3D

Martinović, Anđelo; Knopp, Jan; Riemenschneider, Hayko; Gool, Luc Van

doi:10.1109/cvpr.2015.7299075

Cited by 122 publications

(104 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Recent advances in augmented reality [392] and virtual reality [393]; developments in the fusion of computer graphics, GIS and BIM (e.g., [394][395][396][397][398][399]); and advances in procedural modelling [21,22,[400][401][402] appear as promising catalysts that will contribute to providing 3D city models to practitioners.…”

Section: Discussionmentioning

confidence: 99%

Applications of 3D City Models: State of the Art Review

Biljecki

Stoter

Ledoux

et al. 2015

IJGI

610

380

View full text Add to dashboard Cite

In the last decades, 3D city models appear to have been predominantly used for visualisation; however, today they are being increasingly employed in a number of domains and for a large range of tasks beyond visualisation. In this paper, we seek to understand and document the state of the art regarding the utilisation of 3D city models across multiple domains based on a comprehensive literature study including hundreds of research papers, technical reports and online resources. A challenge in a study such as ours is that the ways in which 3D city models are used cannot be readily listed due to fuzziness, terminological ambiguity, unclear added-value of 3D geoinformation in some instances, and absence of technical information. To address this challenge, we delineate a hierarchical terminology (spatial operations, use cases, applications), and develop a theoretical reasoning to segment and categorise the diverse uses of 3D city models. Following this framework, we provide a list of identified use cases of 3D city models (with a description of each), and their applications. Our study demonstrates that 3D city models are employed in at least 29 use cases that are a part of more than 100 applications. The classified inventory could be useful for scientists as well as stakeholders in the geospatial industry, such as companies and national mapping agencies, as it may serve as a reference document to better position their operations, design product portfolios, and to better understand the market.

show abstract

Section: Discussionmentioning

confidence: 99%

Applications of 3D City Models: State of the Art Review

Biljecki

Stoter

Ledoux

et al. 2015

IJGI

610

380

View full text Add to dashboard Cite

show abstract

“…A CRF model is proposed where unary potentials are from random forest and Potts model is set to calculate pairwise potentials. Instead of assigning labels to image pixels, Martinović et al (2015) design a 3D pipeline to take advantages of 2D images and 3D point clouds from Structure from Motion for 3D labeling. Height, depth, normal vector and spin image descriptors at different scales are 3D features used in a random forest classifier.…”

Section: Related Workmentioning

confidence: 99%

“…Comparing with those traditional datasets that only include a single view for each façade, this point cloud provides additional 3D geometrical cues to solve the problem. Although some previous studies employ multi-view façade images for façade segmentation (Gadde et al, 2017;Martinović et al, 2015), they only focus on terrestrial images and no semantic segmentation has been done from airborne images. This work aims to explore the potential of airborne images to address the problem.…”

Section: Introductionmentioning

confidence: 99%

Semantic Building Façade Segmentation From Airborne Oblique Images

Lin

Nex

Yang

2018

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

View full text Add to dashboard Cite

ABSTRACT:With the introduction of airborne oblique camera systems and the improvement of photogrammetric techniques, high-resolution 2D and 3D data can be acquired in urban areas. This high-resolution data allows us to perform detailed investigations on building roofs and façades which can contribute to LoD3 city modeling. Normally, façade segmentation is achieved from terrestrial views. In this paper, we address the problem from aerial views by using high resolution oblique aerial images as the data source in urban areas. In addition to traditional image features, such as RGB and SIFT, normal vector and planarity are also extracted from dense matching point clouds. Then, these 3D geometrical features are projected back to 2D space to assist façade interpretation. Random forest is trained and applied to label façade pixels. Fully connected conditional random field (CRF), capturing long-range spatial interactions, is used as a post-processing to refine our classification results. Its pairwise potential is defined by a linear combination of Gaussian kernels and the CRF model is efficiently solved by mean field approximation. Experiments show that 3D features can significantly improve classification results. Also, fully connected CRF performs well in correcting noisy pixels.

show abstract

“…For Haussmannian architecture, strong priors or regular floors may be sufficient to model the buildings [47]. For more general architecture, more relaxed structural principles such as symmetries have to be used [33,41,32]. Further even, in the case of real cities with regular planar buildings and complex shapes like statues, a hybrid model [26] or a topology joining approach [31] may be applied.…”

Section: Related Workmentioning

confidence: 99%

Architectural decomposition for 3D landmark building understanding

Kobyshev

Riemenschneider

Gool

2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

Self Cite

View full text Add to dashboard Cite

Decomposing 3D building models into architectural elements is an essential step in understanding their 3D structure. Although we focus on landmark buildings, our approach generalizes to arbitrary 3D objects. We formulate the decomposition as a multi-label optimization that identifies individual elements of a landmark. This allows our system to cope with noisy, incomplete, outlier-contaminated 3D point clouds. We detect three types of structural cues, namely dominant mirror symmetries, rotational symmetries, and polylines capturing free-form shapes of the landmark not explained by symmetry. Combining these cues enables modeling the variability present in complex 3D models, and robustly decomposing them into architectural structural elements. Our architectural decomposition facilitates significant 3D model compression and shape-specific modeling.

show abstract

3D all the way: Semantic segmentation of urban scenes from start to end in 3D

Cited by 122 publications

References 56 publications

Applications of 3D City Models: State of the Art Review

Applications of 3D City Models: State of the Art Review

Semantic Building Façade Segmentation From Airborne Oblique Images

Architectural decomposition for 3D landmark building understanding

Contact Info

Product

Resources

About