RigidFusion: Robot Localisation and Mapping in Environments With Large Dynamic Rigid Objects

Long, Ran; Rauch, Christian; Zhang, Tianwei; Ivan, Vladimir; Vijayakumar, Sethu

doi:10.1109/lra.2021.3066375

Cited by 21 publications

(25 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar effect occurs when multiple dynamic targets appear in the visual field at the same time, resulting in large areas of invalid visual features. The introducing an ego-motion prior is a promising approach to cope with such rigid object occlusion problem [26].…”

Section: Discussionmentioning

confidence: 99%

AcousticFusion: Fusing Sound Source Localization to Visual SLAM in Dynamic Environments

Zhang

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Dynamic objects in the environment, such as people and other agents, lead to challenges for existing simultaneous localization and mapping (SLAM) approaches. To deal with dynamic environments, computer vision researchers usually apply some learning-based object detectors to remove these dynamic objects. However, these object detectors are computationally too expensive for mobile robot on-board processing. In practical applications, these objects output noisy sounds that can be effectively detected by on-board sound source localization. The directional information of the sound source object can be efficiently obtained by direction of sound arrival (DoA) estimation, but the depth estimation is difficult. Therefore, in this paper, we propose a novel audio-visual fusion approach that fuses sound source direction into the RGB-D image and thus removes the effect of dynamic obstacles on the multi-robot SLAM system. Experimental results of multirobot SLAM in different dynamic environments show that the proposed method uses very small computational resources to obtain very stable self-localization results.

show abstract

Section: Discussionmentioning

confidence: 99%

AcousticFusion: Fusing Sound Source Localization to Visual SLAM in Dynamic Environments

Zhang

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Robot proprioception, such as IMU and wheel odometry, can be fused with visual sensors to improve the accuracy and robustness of localisation in dynamic environments [16], [17]. Kim et al [16] uses the camera motion prior from an IMU to compensate the camera motion and select static keypoints based on motion vectors.…”

Section: Related Workmentioning

confidence: 99%

“…Kim et al [16] uses the camera motion prior from an IMU to compensate the camera motion and select static keypoints based on motion vectors. RigidFusion (RF) [17] uses both camera and object motion priors to simultaneously reconstruct the static background and one rigid dynamic object where the major part of the camera view is occluded. However, both of these methods are unable to track multiple dynamic objects independently.…”

Section: Related Workmentioning

confidence: 99%

“…1) Residual term: Following the previous work [7], [17], we consider image pairs (I t−1 , D t−1 ) and (I t , D t ) from two consecutive frames. For a pixel p with coordinate x p t ∈ R 2 in the current frame t, the intensity residual r p I (ξ ) and depth residual r p I (ξ ) against the previous frame under motion ξ are given by:…”

Section: Joint Camera Tracking and Background Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

RGB-D SLAM in Indoor Planar Environments with Multiple Large Dynamic Objects

Long¹,

Rauch²,

Zhang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

This work presents a novel dense RGB-D SLAM approach for dynamic planar environments that enables simultaneous multi-object tracking, camera localisation and background reconstruction. Previous dynamic SLAM methods either rely on semantic segmentation to directly detect dynamic objects; or assume that dynamic objects occupy a smaller proportion of the camera view than the static background and can, therefore, be removed as outliers. Our approach, however, enables dense SLAM when the camera view is largely occluded by multiple dynamic objects with the aid of camera motion prior. The dynamic planar objects are separated by their different rigid motions and tracked independently. The remaining dynamic non-planar areas are removed as outliers and not mapped into the background. The evaluation demonstrates that our approach outperforms the state-of-the-art methods in terms of localisation, mapping, dynamic segmentation and object tracking. We also demonstrate its robustness to large drift in the camera motion prior.

show abstract

“…In a TSDF approach based on [21], MID-Fusion [15] combines the segmentation of [9] with motion cues to reconstruct multiple moving objects. Long et al [22] additionally include motion tracking to reconstruct a single large moving object.…”

Section: B Object-centric Mappingmentioning

confidence: 99%

Panoptic Multi-TSDFs: a Flexible Representation for Online Multi-resolution Volumetric Mapping and Long-term Dynamic Scene Consistency

Schmid,

Delmerico,

Schönberger

et al. 2021

Preprint

View full text Add to dashboard Cite

For robotic interaction in an environment shared with multiple agents, accessing a volumetric and semantic map of the scene is crucial. However, such environments are inevitably subject to long-term changes, which the map representation needs to account for. To this end, we propose panoptic multi-TSDFs, a novel representation for multiresolution volumetric mapping over long periods of time. By leveraging high-level information for 3D reconstruction, our proposed system allocates high resolution only where needed. In addition, through reasoning on the object level, semantic consistency over time is achieved. This enables to maintain up-to-date reconstructions with high accuracy while improving coverage by incorporating and fusing previous data. We show in thorough experimental validations that our map representation can be efficiently constructed, maintained, and queried during online operation, and that the presented approach can operate robustly on real depth sensors using non-optimized panoptic segmentation as input.

show abstract

RigidFusion: Robot Localisation and Mapping in Environments With Large Dynamic Rigid Objects

Cited by 21 publications

References 23 publications

AcousticFusion: Fusing Sound Source Localization to Visual SLAM in Dynamic Environments

AcousticFusion: Fusing Sound Source Localization to Visual SLAM in Dynamic Environments

RGB-D SLAM in Indoor Planar Environments with Multiple Large Dynamic Objects

Panoptic Multi-TSDFs: a Flexible Representation for Online Multi-resolution Volumetric Mapping and Long-term Dynamic Scene Consistency

Contact Info

Product

Resources

About