Towards Real-time Semantic RGB-D SLAM in Dynamic Environments

Ji, Tete; Wang, Chen; Xie, Lihua

doi:10.1109/icra48506.2021.9561743

Cited by 69 publications

(48 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some systems are designed to handle dynamic environments through the use of elimination strategies, where moving objects are detected and removed from the tracking and mapping processes (e.g. [27]- [32]). While this strategy offers an improvement over the static scene assumption in standard SLAM systems, it still requires that enough static background is visible for robust tracking and throws away any information contained in the dynamic parts of the environment.…”

Section: Visual Slam With Dynamic Objectsmentioning

confidence: 99%

BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking

Henning¹,

Laidlow²,

Leutenegger³

2022

Preprint

View full text Add to dashboard Cite

Estimating human motion from video is an active research area due to its many potential applications. Most stateof-the-art methods predict human shape and posture estimates for individual images and do not leverage the temporal information available in video. Many "in the wild" sequences of human motion are captured by a moving camera, which adds the complication of conflated camera and human motion to the estimation. We therefore present BodySLAM, a monocular SLAM system that jointly estimates the position, shape, and posture of human bodies, as well as the camera trajectory. We also introduce a novel human motion model to constrain sequential body postures and observe the scale of the scene. Through a series of experiments on video sequences of human motion captured by a moving monocular camera, we demonstrate that BodySLAM improves estimates of all human body parameters and camera poses when compared to estimating these separately.

show abstract

Section: Visual Slam With Dynamic Objectsmentioning

confidence: 99%

BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking

Henning¹,

Laidlow²,

Leutenegger³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The other category of potential dynamic targets is considered to be static targets based on prior knowledge, which have the possibility of movement, such as books, computers, chairs, etc. To enhance the performance of recognizing dynamic objects, the current methods combining geometric and semantic methods have been widely used in SLAM systems [ 10 , 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

DGFlow-SLAM: A Novel Dynamic Environment RGB-D SLAM without Prior Semantic Knowledge Based on Grid Segmentation of Scene Flow

Long

Ding

2022

Biomimetics

View full text Add to dashboard Cite

Currently, using semantic segmentation networks to distinguish dynamic and static key points has become a mainstream designing method for semantic SLAM systems. However, the semantic SLAM systems must have prior semantic knowledge of relevant dynamic objects, and their processing speed is inversely proportional to the recognition accuracy. To simultaneously enhance the speed and accuracy for recognizing dynamic objects in different environments, a novel SLAM system without prior semantics called DGFlow-SLAM is proposed in this paper. A novel grid segmentation method is used in the system to segment the scene flow, and then an adaptive threshold method is used to roughly detect the dynamic objects. Based on this, a deep mean clustering segmentation method is applied to find potential dynamic targets. Finally, the results of grid segmentation and depth mean clustering segmentation are jointly used to find moving objects accurately, and all the feature points of the moving objects are removed on the premise of retaining the static part of the moving object. The experimental results show that on the dynamic sequence dataset of TUM RGB-D, compared with the DynaSLAM system with the highest accuracy for detecting moderate and violent motion and the DS-SLAM with the highest accuracy for detecting slight motion, DGflow-SLAM obtains similar accuracy results and improves the accuracy by 7.5%. In addition, DGflow-SLAM is 10 times and 1.27 times faster than DynaSLAM and DS-SLAM, respectively.

show abstract

“…Ji et al [53] proposed a faster Semantic RGB-D SLAM method for dynamic environments extracting semantic information only from keyframes. Also, they combined K-Means with depth reprojection to identify unknown moving objects in the other frames.…”

Section: Visual Slam In Highly Dynamic Environmentsmentioning

confidence: 99%

“…The proposed method has a robust keypoint classification algorithm that filters a priori dynamic objects and uses an Extended Kalman Filter to track movable objects in the scene. This resulted in a visual SLAM system for highly dynamic environments that runs faster than DOT-Mask [52] and the method of Ji et al [53], with an accuracy similar to DynaSLAM [30] and SaD-SLAM [32]. Furthermore, the problem of feature depletion caused by filtering features from the background in the bounding boxes is solved with a fast and reliable method, using statistical data of the depth in each bounding box.…”

Section: Original Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Metric-Semantic Visual Slam for Dynamic and Changing Environments

CARLOS VIRGOLINO SOARES

View full text Add to dashboard Cite

show abstract

Towards Real-time Semantic RGB-D SLAM in Dynamic Environments

Cited by 69 publications

References 30 publications

BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking

BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking

DGFlow-SLAM: A Novel Dynamic Environment RGB-D SLAM without Prior Semantic Knowledge Based on Grid Segmentation of Scene Flow

Real-Time Metric-Semantic Visual Slam for Dynamic and Changing Environments

Contact Info

Product

Resources

About