Improving the efficiency of hierarchical structure-and-motion

Gherardi, Riccardo; Farenzena, Michela; Fusiello, Andrea

doi:10.1109/cvpr.2010.5539782

Cited by 110 publications

(77 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 3D points were produced by Samantha [44], together with the hierarchical partitioning of the data.…”

Section: Resultsmentioning

confidence: 99%

“…In this section we leverage the hierarchical partitioning of data (camera and points) provided by Samantha [44] to obtain a hierarchical patch fitting procedure which is more computationally e cient, inherently parallel and suitable for out-of-core processing. Samantha is a structure-andmotion pipeline that first runs an agglomerative clustering on the set of images and then processes them following the dendrogram.…”

Section: Hierarchical Processingmentioning

confidence: 99%

See 1 more Smart Citation

Image-consistent patches from unstructured points with J-linkage

Toldo

Fusiello

2013

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

Going from unstructured cloud of points to surfaces is a challenging problem. However, as points are produced by a structure-and-motion pipeline, image-consistency is a powerful clue that comes to the rescue. In this paper we present a method for extracting planar patches from an unstructured cloud of points, based on the detection of image-consistent planar patches with J-linkage, a robust algorithm for multiple models fitting. The method integrates several constraints inside J-linkage, optimizes the position of the points with regard to image-consistency and deploys a hierarchical processing scheme that decreases the computational load. With respect to previous work this approach has the advantage of starting from sparse data. Several results show the e↵ectiveness of the proposed approach.

show abstract

“…The 3D points were produced by Samantha [44], together with the hierarchical partitioning of the data.…”

Section: Resultsmentioning

confidence: 99%

Section: Hierarchical Processingmentioning

confidence: 99%

Image-consistent patches from unstructured points with J-linkage

Toldo

Fusiello

2013

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…In particular, image based large scale 3D reconstruction systems have demonstrated strong potentials in obtaining accurate maps for cultural heritage and entertainment purposes [1], [2], [3]. However these systems are normally not parsimonious in the sense that they require thousands/millions/billions of images in order to obtain a satisfactory reconstruction.…”

Section: Introductionmentioning

confidence: 99%

A directional visual descriptor for large-scale coverage problems

Tamassia

Farinelli

Murino

et al. 2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-Visual coverage of large scale environments is a challenging problem that has many practical applications such as large scale 3D reconstruction, search and rescue and active video surveillance. In this paper, we consider a setting where mobile robots must acquire visual information using standard cameras, while minimizing associated movement costs. The main source of complexity for such scenario is the lack of a priori knowledge of 3D structures for the surrounding environment. To address this problem, we propose a novel descriptor for visual coverage that aims at measuring the orientation dependent visual information of an area, based on a regular discretization of the 3D environment in voxels. Next, we use the proposed visual descriptor to define an autonomous cooperative exploration approach, which controls the robot movements so to maximize information accuracy and minimizing movement costs. We empirically evaluate our approach in a simulation scenario based on real data for large scale 3D environments, and on widely used robotic tools (such as ROS and Stage). Experimental results show that the proposed method significantly outperforms a baseline random approach and an uncoordinated one, thus being a valid proposal for visual coverage in large scale outdoor scenarios.

show abstract

“…Attempts to improve SfM efficiency have been previously proposed [6]- [8], and multi-core processors and Graphics Processing Units (GPUs) have been employed to accelerate computation [9]. However, while some work has considered SfM in a cluster environment [10], little attention has been given to processing datasets relevant to wide-area georegistration, such as aerial video, on a large-scale computing grid.…”

Section: Introductionmentioning

confidence: 99%

Cluster-based 3D reconstruction of aerial video

Sawyer

Bliss

2012

2012 IEEE Conference on High Performance Extreme Computing

View full text Add to dashboard Cite

Abstract-Large-scale 3D scene reconstruction using Structure from Motion (SfM) continues to be very computationally challenging despite much active research in the area. We propose an efficient, scalable processing chain designed for cluster computing and suitable for use on aerial video. The sparse bundle adjustment step, which is iterative and difficult to parallelize, is accomplished by partitioning the input image set, generating independent point clouds in parallel, and then fusing the clouds and combining duplicate points. We compare this processing chain to a leading parallel SfM implementation, which exploits fine-grained parallelism in various matrix operations and is not designed to scale beyond a multi-core workstation with GPU. We show our cluster-based approach offers significant improvement in scalability and runtime while producing comparable point cloud density and more accurate point location estimates.

show abstract

Improving the efficiency of hierarchical structure-and-motion

Cited by 110 publications

References 20 publications

Image-consistent patches from unstructured points with J-linkage

Image-consistent patches from unstructured points with J-linkage

A directional visual descriptor for large-scale coverage problems

Cluster-based 3D reconstruction of aerial video

Contact Info

Product

Resources

About