3D Semantic Parsing of Large-Scale Indoor Spaces

Armeni, Iro; Şener, Ozan; Zamir, Amir; Jiang, Helen; Brilakis, Ioannis; Fischer, Martin; Savarese, Silvio

doi:10.1109/cvpr.2016.170

Cited by 1,177 publications

(893 citation statements)

References 29 publications

Supporting

Mentioning

889

Contrasting

Unclassified

Order By: Relevance

“…In a recent work by Mura et al (2016), the authors encode the indoor components in an adjacency graph and -by finding the path from ceiling to floor -try to detect and reconstruct the main components. Armeni et al (2016) parse point clouds collected with a Matterport system into indoor components for large-scale indoor scenes. The authors use walls as space divider to semantically generate space subdivisions and use this information to detect other structure elements.…”

Section: Related Workmentioning

confidence: 99%

“…IMLS systems, in addition to the point clouds, provide a continuous trajectory of device locations instead of few discrete station points in TLS. Current methods for indoor reconstruction and semantic labelling use mainly TLSs (Becker et al, 2015;Mura et al, 2014a;Oesau et al, 2014) or RGB-Depth data (Armeni et al, 2016;Khan et al, 2015). If MLS data is used as in (Xiao and Furukawa, 2014), the benefit of trajectory data is not exploited.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting Indoor Mobile Laser Scanner Trajectories for Semantic Interpretation of Point Clouds

Nikoohemat

Peter

Elberink

et al. 2017

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

View full text Add to dashboard Cite

ABSTRACT:The use of Indoor Mobile Laser Scanners (IMLS) for data collection in indoor environments has been increasing in the recent years. These systems, unlike Terrestrial Laser Scanners (TLS), collect data along a trajectory instead of at discrete scanner positions. In this research, we propose several methods to exploit the trajectories of IMLS systems for the interpretation of point clouds. By means of occlusion reasoning and use of trajectory as a set of scanner positions, we are capable of detecting openings in cluttered indoor environments. In order to provide information about both the partitioning of the space and the navigable space, we use the voxel concept for point clouds. Furthermore, to reconstruct walls, floor and ceiling we exploit the indoor topology and plane primitives. The results show that the trajectory is a valuable source of data for feature detection and understanding of indoor MLS point clouds.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Exploiting Indoor Mobile Laser Scanner Trajectories for Semantic Interpretation of Point Clouds

Nikoohemat

Peter

Elberink

et al. 2017

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

View full text Add to dashboard Cite

show abstract

“…The creation of digital libraries of parametric objects is considerably more complex, being possible only through a coordinated effort of survey, analysis and classification of the historical building compounds [20]. Although there are some systems of automatic recognition [5], the procedures are still in their early stages and cannot be applied to ordinary BIM works. The modeling strategies of BOMs (Building Object Models) can be diversified and have to be calibrated from the study of manuals and historical treatises that describe the technology node, which cannot always be acquired through non-invasive investigations.…”

Section: H-bimmentioning

confidence: 99%

“…), which is based on the operator's knowledge and manual modeling work, despite the recent development of automated semantic recognition processes [5]. Moreover, the quality of the model is related to the "level of approximation" or the "level of simplification" that is applied during the modelling phase, in comparison with the real object.…”

Section: Introductionmentioning

confidence: 99%

Challenges and Opportunities for the Implementation of H-Bim With Regards to Historical Infrastructures: A Case Study of the Ponte Giorgini in Castiglione Della Pescaia (Grosseto – Italy)

Donato

Biagini

Bertini³

et al. 2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Historical Building Information Modeling (H-BIM) has been widely documented in literature and is becoming more popular with government bodies, who are increasingly choosing to make its use mandatory in public procurements and contracts. Although the system seems to be one of the best approaches for managing data and driving the decision-making process, several difficulties arise due to the amount of effort required in the initial phases, when the data derived from a geometrical survey must be converted into parametric elements. Moreover, users must decide on a "level of geometrical simplification" a long time in advance, and this inevitably leads to a loss of geometrical data. From this perspective, our research describes a procedure to optimize the workflow of information for existing artefacts, in order to achieve a "lean" H-BIM. In this article, we will analyse two aspects: the first relates to the level of accuracy in a digital model created from the two different point clouds achieved from laser scanner and form images, while the second concerns the conversion of this information into parametric elements (Building Object Models-BOMs) that need to have specific characteristics. The case study we are presenting is the "Ponte Giorgini" ("Giorgini Bridge") in Castiglione della Pescaia (Grosseto -Italy).

show abstract

“…In contrast to depth sensors, LiDAR devices scan the environment and obtain the 3D points one-by-one. Based on the features of scanlines, many methods have been proposed for different purposes, such as people detection, segmentation and point cloud registration [11][12][13][14][15].…”

Section: Related Workmentioning

confidence: 99%

Incremental and Enhanced Scanline-Based Segmentation Method for Surface Reconstruction of Sparse LiDAR Data

2016

View full text Add to dashboard Cite

Abstract:The segmentation of point clouds is an important aspect of automated processing tasks such as semantic extraction. However, the sparsity and non-uniformity of the point clouds gathered by the popular 3D mobile LiDAR devices pose many challenges for existing segmentation methods. To improve the segmentation results of point clouds from mobile LiDAR devices, we propose an optimized segmentation method based on Scanline Continuity Constraint (SLCC) in this work. Unlike conventional scanline-based segmentation methods, SLCC clusters scanlines using the continuity constraints in terms of the distance as well as the direction of two consecutive points. In addition, scanline clusters are agglomerated not only into primitive geometrical shapes but also irregular shapes. Another downside to existing segmentation methods is that they are not capable of incremental processing. This causes unnecessary memory and time consumption for applications that require frame-wise segmentation or when new point clouds are added. In order to address this, we propose an incremental scheme-the Incremental Recursive Segmentation (IRIS), that can be easily applied to any segmentation method. IRIS is achieved by combining the segments of newly added point clouds and the previously segmented results. Furthermore, as an example application, we construct a processing pipeline consisting of plane fitting and surface reconstruction using the segmentation results. Finally, we evaluate the proposed methods on three datasets acquired from a handheld Velodyne HDL-32E LiDAR device. The experimental results verify the efficiency of IRIS for any segmentation method and the advantages of SLCC for processing mobile LiDAR data.

show abstract

3D Semantic Parsing of Large-Scale Indoor Spaces

Cited by 1,177 publications

References 29 publications

Exploiting Indoor Mobile Laser Scanner Trajectories for Semantic Interpretation of Point Clouds

Exploiting Indoor Mobile Laser Scanner Trajectories for Semantic Interpretation of Point Clouds

Challenges and Opportunities for the Implementation of H-Bim With Regards to Historical Infrastructures: A Case Study of the Ponte Giorgini in Castiglione Della Pescaia (Grosseto – Italy)

Incremental and Enhanced Scanline-Based Segmentation Method for Surface Reconstruction of Sparse LiDAR Data

Contact Info

Product

Resources

About