Real-time motion removal based on point correlations for RGB-D SLAM in indoor dynamic environments

Wang, Kesai; Yao, Xifan; Ma, Nanfeng; Xuan, Jianhua

doi:10.1007/s00521-022-07879-x

Cited by 7 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors integrate this method into the front-end of ORB-SLAM2, effectively improving the accuracy of the original system in dynamic environments. Inspired by Dai's work, Wang et al [9] apply point correlation constraints to map feature points into the camera coordinate system. They distinguish dynamic feature points through edge variation and complete the division of dynamic regions by clustering depth images.…”

Section: Related Workmentioning

confidence: 99%

“…To further evaluate the accuracy of DMOT-SLAM, we compared our system with the state-of-the-art dynamic SLAM systems. We run both DS-SLAM [11] and RTD-SLAM [9] on fr3/w/rpy sequence, and the results of the RPE are shown in figure 10. It is evident that our system consistently achieves the lowest RPE values among the three systems, indicating that our system can provide more accurate pose estimation per second.…”

Section: Evaluation On the Tum Rgb-d Datasetmentioning

confidence: 99%

See 1 more Smart Citation

DMOT-SLAM: visual SLAM in dynamic environments with moving object tracking

Wang,

Yao,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Visual simultaneous localization and mapping (SLAM) in dynamic environments has received significant attention in recent years, and accurate segmentation of real dynamic objects is the key to enhancing the accuracy of pose estimation in such environments. In this study, we propose a visual SLAM approach based on ORB-SLAM3, namely DMOT-SLAM, which can accurately estimate the camera’s pose in dynamic environments while tracking the trajectories of moving objects. We introduce a spatial point correlation constraint and combine it with instance segmentation and epipolar constraint to identify dynamic objects. We integrate the proposed motion check method into DeepSort, an object tracking algorithm, to facilitate inter-frame tracking of dynamic objects. This integration not only enhances the stability of dynamic features detection but also enables the estimation of global motion trajectories for dynamic objects and the construction of object-level semi-dense semantic maps. We evaluate our approach on the public TUM, Bonn, and KITTI dataset, and the results show that our approach has a significant improvement over ORB-SLAM3 in dynamic scenes and performs better compared to other state-of-the-art SLAM approaches. Moreover, experiments in real-world scenarios further substantiate the effectiveness of our approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Evaluation On the Tum Rgb-d Datasetmentioning

confidence: 99%

DMOT-SLAM: visual SLAM in dynamic environments with moving object tracking

Wang,

Yao,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Literature [15] uses an object detection network and the Grab Cut algorithm [16] to segment dynamic objects. In literature [17], the YOLOv3 algorithm [18] was used to preliminarily filter the dynamic region, and then the dynamic region was segmsegmed and filtered more carefully through the consistency evaluation of the distance transform error and photometric error of the edge in the image. In literature [19], YOLOv3 is combined with a polar-line constraint algorithm based on the optical flow method to remove dynamic features, which has high pose accuracy but does not involve dynamic segmentation and dense mapping.…”

Section: Introductionmentioning

confidence: 99%

Research on Visual SLAM Navigation Techniques for Dynamic Environments

Wang,

Zhao

2023

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Synchronous positioning and mapping mainly realize the functions of self-positioning and environment map construction for intelligent navigation technology. In order to solve the problems of low positioning accuracy and poor mapping effect of existing SLAM (simultaneous localization and mapping) systems in indoor dynamic environments and to improve the positioning accuracy, timeliness, and robustness of visual SLAM systems in dynamic environments, an improved visual SLAM method is proposed. Aiming at the inconsistency between the direction of dynamic objects and static background optical flow, this method adopts a high-real-time dynamic region mask detection algorithm to eliminate the feature points in the dynamic region mask, remove the camera motion optical flow according to the original feature information, and then cluster the optical flow amplitude of dynamic objects so as to realize the dynamic region mask detection and eliminate the dynamic signpost points combined with the polar geometric constraints. In order to verify the effectiveness of the improved algorithm, the three evaluation indexes of system accuracy, real-time performance, and the amount of drift are analyzed and verified, respectively, on the TUM dataset. The results show that the proposed algorithm not only has good real-time performance but also improves the accuracy of the system and reduces the amount of drift.

show abstract

PLMOT-SLAM: a point-line features fusion SLAM system with moving object tracking

Wang,

Yao,

et al. 2024

Vis Comput

View full text Add to dashboard Cite

Real-time motion removal based on point correlations for RGB-D SLAM in indoor dynamic environments

Cited by 7 publications

References 33 publications

DMOT-SLAM: visual SLAM in dynamic environments with moving object tracking

DMOT-SLAM: visual SLAM in dynamic environments with moving object tracking

Research on Visual SLAM Navigation Techniques for Dynamic Environments

PLMOT-SLAM: a point-line features fusion SLAM system with moving object tracking

Contact Info

Product

Resources

About