A Compatible Framework for RGB-D SLAM in Dynamic Scenes

Zhao, Lili; Liu, Zhili; Chen, Jianwen; Cai, Weitong; Wang, Wenyi; Zeng, Liaoyuan

doi:10.1109/access.2019.2922733

Cited by 32 publications

(27 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SfM-Net [30] segmented moving objects in the scene without supervised information. Zhao et al [31] proposed a method for detecting potentially dynamic objects using semantic information, then using a contour refinement algorithm to detect objects more accurately. However, how to better integrate with the system to play a better role in deep learning is worth exploring.…”

Section: Visual Slam With Semantic Informationmentioning

confidence: 99%

A Mobile Robot Visual SLAM System With Enhanced Semantics Segmentation

Liang

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Traditional visual simultaneous localization and mapping (SLAM) systems mostly based on small-area static environments. In recent years, some studies focused on combining semantic information with visual SLAM. However, most of them are hard to obtain better performance in the large-scale dynamic environment. And the accuracy, rapidity of the system still needs to strengthen. In this paper, we develop a more efficient semantic SLAM system in the two-wheeled mobile robot by using semantic segmentation to recognize people, chairs, and other objects in every keyframe. With a preliminary understanding of the environment, fusing the RGB-D camera and encoders information, to localization and creating a dense colored octree map without dynamic objects. Besides, for the incomplete identification of movable objects, we used image processing algorithms to enhance the semantic segmentation effect. In the proposed method, enhanced semantic segmentation in keyframes dramatically increases the efficiency of the system. Moreover, fusing the different sensors can highly raise localization accuracy. We conducted experiments on various datasets and in some real environments and compared them with DRE-SLAM, DS-SLAM, to evaluate the performance of the proposed approach. The results suggest we significantly improve the processing efficiency, robustness, and quality of the map.

show abstract

Section: Visual Slam With Semantic Informationmentioning

confidence: 99%

A Mobile Robot Visual SLAM System With Enhanced Semantics Segmentation

Liang

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The optical flow is firstly used to judge and cull the dynamic point, and then dynamic characteristics of the remaining feature points are detected by judging whether they fall within the semantic dynamic object which is obtained by the PSPNet semantic segmentation. For the method proposed by Zhao et al [21], it firstly used the Mask-RCNN and edge refinement to obtain the contour of potentially dynamic object, and then the optical flow is implemented to further detect the state of potentially dynamic object by checking the consistency of potentially dynamic object and background areas. In general, the 'loosely coupled' scheme takes either intersection or union of the two detection results from the semantic information and the geometry calculation.…”

Section: A Related Workmentioning

confidence: 99%

“…Second, we compare our SDF-SLAM with other stateof-the-art semantic SLAM systems which were proposed in recent two years and towards the dynamic environment. In specific, the DS-SLAM [18], DynaSLAM [19], Detect-SLAM [14], the system proposed by Zhang et al [15], the system proposed by Zhao et al [21],SOF-SLAM [22], and PSPNet-SLAM [20] are adopted for comparisons. All the above systems are built on ORB-SLAM2, and are tested on the dynamic sequences from TUM dataset.…”

Section: B Experiments and Analysismentioning

confidence: 99%

SDF-SLAM: Semantic Depth Filter SLAM for Dynamic Environments

Cui

2020

IEEE Access

View full text Add to dashboard Cite

Simultaneous Localization and Mapping (SLAM) has been widely applied in computer vision and robotics. For the dynamic environments which are very common in the real word, traditional visual SLAM system faces significant drop in localization and mapping accuracy due to the static world assumption. Recently, the semantic visual SLAM systems towards dynamic scenes have gradually attracted more and more attentions, which use the semantic information of images to help remove dynamic feature points. Existing semantic visual SLAM systems commonly detect the dynamic feature points by the semantic prior, geometry constraint or the combine of them, then map points corresponding to dynamic feature points are removed. In the visual SLAM framework, pose calculation is essentially around the 3D map points, so the essence of improving the accuracy of visual SLAM system is to build a more accurate and reliable map. These existing semantic visual SLAM systems are actually adopting an indirect way to acquire reliable map points, and several drawbacks exist. In this paper, we present SDF-SLAM: Semantic Depth Filter SLAM, a visual semantic SLAM system towards dynamic environments, which utilizes the technology of depth filter to directly judge whether a 3D map point is dynamic or not. First, the semantic information is integrated into the original pure geometry SLAM system by the semantic optical flow method to perform reliable map initialization. Second, design the semantic depth filter that satisfies the Gaussian Uniform mixture distribution to describe the inverse depth of each map point. Third, updating the inverse depth of 3D map point in a Bayesian estimation framework, and dividing the 3D map point into active one or inactive one. Last, only the active map points are utilized to achieve robust camera pose tracking. Experiments on TUM dataset demonstrate that our approach outperforms original ORB-SLAM2 and other state-of-the-art semantic SLAM systems.

show abstract

“…Kim et al [20] proposed to obtain the static parts of a scene by computing the difference between consecutive depths of images projected over the same plane. Similarly, Zhao et al [21] used depth images to detect dynamic objects. However, these methods were prone to be affected by the uncertainty of depth images.…”

Section: Related Workmentioning

confidence: 99%

SGC-VSLAM: A Semantic and Geometric Constraints VSLAM for Dynamic Indoor Environments

Fan

Bai

Zhao

et al. 2020

Sensors

View full text Add to dashboard Cite

As one of the core technologies for autonomous mobile robots, Visual Simultaneous Localization and Mapping (VSLAM) has been widely researched in recent years. However, most state-of-the-art VSLAM adopts a strong scene rigidity assumption for analytical convenience, which limits the utility of these algorithms for real-world environments with independent dynamic objects. Hence, this paper presents a semantic and geometric constraints VSLAM (SGC-VSLAM), which is built on the RGB-D mode of ORB-SLAM2 with the addition of dynamic detection and static point cloud map construction modules. In detail, a novel improved quadtree-based method was adopted for SGC-VSLAM to enhance the performance of the feature extractor in ORB-SLAM (Oriented FAST and Rotated BRIEF-SLAM). Moreover, a new dynamic feature detection method called semantic and geometric constraints was proposed, which provided a robust and fast way to filter dynamic features. The semantic bounding box generated by YOLO v3 (You Only Look Once, v3) was used to calculate a more accurate fundamental matrix between adjacent frames, which was then used to filter all of the truly dynamic features. Finally, a static point cloud was estimated by using a new drawing key frame selection strategy. Experiments on the public TUM RGB-D (Red-Green-Blue Depth) dataset were conducted to evaluate the proposed approach. This evaluation revealed that the proposed SGC-VSLAM can effectively improve the positioning accuracy of the ORB-SLAM2 system in high-dynamic scenarios and was also able to build a map with the static parts of the real environment, which has long-term application value for autonomous mobile robots.

show abstract

A Compatible Framework for RGB-D SLAM in Dynamic Scenes

Cited by 32 publications

References 33 publications

A Mobile Robot Visual SLAM System With Enhanced Semantics Segmentation

A Mobile Robot Visual SLAM System With Enhanced Semantics Segmentation

SDF-SLAM: Semantic Depth Filter SLAM for Dynamic Environments

SGC-VSLAM: A Semantic and Geometric Constraints VSLAM for Dynamic Indoor Environments

Contact Info

Product

Resources

About