GPSlam: Marrying Sparse Geometric and Dense Probabilistic Visual Mapping

Pirker, Katrin; Rüther, Matthias; Schweighofer, Gerald; Bischof, Horst

doi:10.5244/c.25.115

Cited by 17 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This map representation is provided by the OctoMap framework of Hornung et al (2013), which includes the ability to take measurement uncertainties into account and implicitly represent free and occupied space while being space efficient. An explicit voxel volumetric occupancy representation is used by Pirker et al (2011) in their GPSlam system which uses sparse visual feature correspondences for camera pose estimation. They make use of visual place recognition and sliding window bundle adjustment in a pose graph optimisation framework.…”

Section: Related Workmentioning

confidence: 99%

Real-time large-scale dense RGB-D SLAM with volumetric fusion

Whelan

Kaess

Johannsson

et al. 2014

The International Journal of Robotics Research

417

332

View full text Add to dashboard Cite

We present a new SLAM system capable of producing high quality globally consistent surface reconstructions over hundreds of metres in real-time with only a low-cost commodity RGB-D sensor. By using a fused volumetric surface reconstruction we achieve a much higher quality map over what would be achieved using raw RGB-D point clouds. In this paper we highlight three key techniques associated with applying a volumetric fusion-based mapping system to the SLAM problem in real-time. First, the use of a GPU-based 3D cyclical buffer trick to efficiently extend dense every frame volumetric fusion of depth maps to function over an unbounded spatial region. Second, overcoming camera pose estimation limitations in a wide variety of environments by combining both dense geometric and photometric camera pose constraints. Third, efficiently updating the dense map according to place recognition and subsequent loop closure constraints by the use of an "as-rigid-as-possible" space deformation. We present results on a wide variety of aspects of the system and show through evaluation on de facto standard RGB-D benchmarks that our system performs strongly in terms of trajectory estimation, map quality and computational performance in comparison to other state-of-the-art systems.

show abstract

Section: Related Workmentioning

confidence: 99%

Real-time large-scale dense RGB-D SLAM with volumetric fusion

Whelan

Kaess

Johannsson

et al. 2014

The International Journal of Robotics Research

417

332

View full text Add to dashboard Cite

show abstract

“…Henry et al [9] implemented an advanced iterative closes point variant to robustly estimate inter-frame motion while realistic surface modeling is handled by Surfels [10]. Our system workflow component on map building mainly follows the approach presented by Pirker et al [2]. Here, large scale, cyclic environments are reconstructed by fusing bundle adjustment techniques with probabilistic occupancy grid mapping.…”

Section: B Vision Based Dense Reconstruction Of the Environmentmentioning

confidence: 99%

“…Figure 1 visualizes how accurately human gaze is mapped into the 3D model for further analysis. The methodology for the recovery of human attention in 3D environments is based on the workflow as sketched in Figure 2: For a spatio-temporal analysis of human attention in the 3D environment, we firstly build a spatial reference in terms of a three-dimensional model of the environment using RGB-D SLAM methodology (i.e., GPSlam [2]) 6HFRQGO\ WKH XVHU ¶V YLHZ LV gathered with eye tracking glasses within the environment and localized from extracted local descriptors [15]. Finally, the distribution of saliency onto the 3D environment is computed for further human attention analysis, such as, evaluation of the attention mapping with respect to object and scene awareness.…”

Section: Introductionmentioning

confidence: 99%

Visual recovery of saliency maps from human attention in 3D environments

Santner

Fritz

Paletta

et al. 2013

2013 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

² The estimation of human attention has recently been addressed in the context of human robot interaction. Today, joint work spaces already exist and challenge cooperating systems to jointly focus on common objects, scenes and work niches. With the advent of Google glasses and increasingly affordable wearable eye-tracking, monitoring of human attention will soon become ubiquitous. The presented work describes for the first time a method for the estimation of human fixations in 3D environments that does not require any artificial landmarks in the field of view and enables attention mapping in 3D models. It enables full 3D recovery of the human view frustum and the gaze pointer in a previously acquired 3D model of the environment in real time. The study on the precision of this method reports a mean projection error §1.1 cm and a mean angOH HUURU §0.6º within the chosen 3D model -the precision does not go below the one of the technical LQVWUXPHQW § ž This innovative methodology will open new opportunities for joint attention studies as well as for bringing new potential into automated processing for human factors technologies.

show abstract

“…The GPSlam algorithm of Pirker et al uses sparse visual features in combination with a dense volumetric occupancy grid for the modeling of large environments [10]. Sliding window bundle adjustment is used with visual place recognition in a pose graph optimisation framework.…”

Section: Related Workmentioning

confidence: 99%

Deformation-based loop closure for large scale dense RGB-D SLAM

Whelan

Kaess

Leonard

et al. 2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-In this paper we present a system for capturing large scale dense maps in an online setting with a low cost RGB-D sensor. Central to this work is the use of an "as-rigid-aspossible" space deformation for efficient dense map correction in a pose graph optimisation framework. By combining pose graph optimisation with non-rigid deformation of a dense map we are able to obtain highly accurate dense maps over large scale trajectories that are both locally and globally consistent. With low latency in mind we derive an incremental method for deformation graph construction, allowing multi-million point maps to be captured over hundreds of metres in real-time. We provide benchmark results on a well established RGB-D SLAM dataset demonstrating the accuracy of the system and also provide a number of our own datasets which cover a wide range of environments, both indoors, outdoors and across multiple floors.

show abstract

GPSlam: Marrying Sparse Geometric and Dense Probabilistic Visual Mapping

Cited by 17 publications

References 25 publications

Real-time large-scale dense RGB-D SLAM with volumetric fusion

Real-time large-scale dense RGB-D SLAM with volumetric fusion

Visual recovery of saliency maps from human attention in 3D environments

Deformation-based loop closure for large scale dense RGB-D SLAM

Contact Info

Product

Resources

About