DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local Features

Kang, Rong; Shi, Jieqi; Li, Xueming; Liu, Yang; Liu, Xiao

doi:10.48550/arxiv.1901.07223

Cited by 15 publications

(16 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case, the antipolar geometric constraints are not applicable. Here, the LK optical flow method is adopted to further detect the dynamic objects in the environment and filter the dynamic feature points for the third time [22][23][24].…”

Section: Epipolar Geometry Constraintsmentioning

confidence: 99%

RGB-D Visual SLAM Based on Yolov4-Tiny in Indoor Dynamic Environment

Chang

Sun³

et al. 2022

Micromachines

View full text Add to dashboard Cite

For a SLAM system operating in a dynamic indoor environment, its position estimation accuracy and visual odometer stability could be reduced because the system can be easily affected by moving obstacles. In this paper, a visual SLAM algorithm based on the Yolov4-Tiny network is proposed. Meanwhile, a dynamic feature point elimination strategy based on the traditional ORBSLAM is proposed. Besides this, to obtain semantic information, object detection is carried out when the feature points of the image are extracted. In addition, the epipolar geometry algorithm and the LK optical flow method are employed to detect dynamic objects. The dynamic feature points are removed in the tracking thread, and only the static feature points are used to estimate the position of the camera. The proposed method is evaluated on the TUM dataset. The experimental results show that, compared with ORB-SLAM2, our algorithm improves the camera position estimation accuracy by 93.35% in a highly dynamic environment. Additionally, the average time needed by our algorithm to process an image frame in the tracking thread is 21.49 ms, achieving real-time performance.

show abstract

Section: Epipolar Geometry Constraintsmentioning

confidence: 99%

RGB-D Visual SLAM Based on Yolov4-Tiny in Indoor Dynamic Environment

Chang

Sun³

et al. 2022

Micromachines

View full text Add to dashboard Cite

show abstract

“…While these single-robot SLAM systems have been widely used, multi-robot SLAM remains to be intractable and still under exploration. A considerable part of the works focuses on the algorithm layer, including multi-sensor fusion [51]- [55] and deep learning assistance [56]- [58], etc. CCM-SLAM [36] proposes a data-sharing mechanism between multiple robots to solve communication problems.…”

Section: Related Workmentioning

confidence: 99%

Edge Robotics: Edge-Computing-Accelerated Multi-Robot Simultaneous Localization and Mapping

Huang¹,

Zeng²,

Xu³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the wide penetration of smart robots in multifarious fields, Simultaneous Localization and Mapping (SLAM) technique in robotics has attracted growing attention in the community. Yet collaborating SLAM over multiple robots still remains challenging due to performance contradiction between the intensive graphics computation of SLAM and the limited computing capability of robots. While traditional solutions resort to the powerful cloud servers acting as an external computation provider, we show by real-world measurements that the significant communication overhead in data offloading prevents its practicability to real deployment. To tackle these challenges, this paper promotes the emerging edge computing paradigm into multi-robot SLAM and proposes RecSLAM, a multi-robot laser SLAM system that focuses on accelerating map construction process under the robot-edge-cloud architecture. In contrast to conventional multi-robot SLAM that generates graphic maps on robots and completely merges them on the cloud, RecSLAM develops a hierarchical map fusion technique that directs robots' raw data to edge servers for real-time fusion and then sends to the cloud for global merging. To optimize the overall pipeline, an efficient multi-robot SLAM collaborative processing framework is introduced to adaptively optimize robot-to-edge offloading tailored to heterogeneous edge resource conditions, meanwhile ensuring the workload balancing among the edge servers. Extensive evaluations show RecSLAM can achieve up to 39.31% processing latency reduction over the state-of-the-art. Besides, a proof-of-concept prototype is developed and deployed in real scenes to demonstrate its effectiveness.

show abstract

“…For the sparse feature-based category, some work has been done using learning-based methods, e.g. [3], [32]- [34]. In [32], the feature descriptor of a two-layer shallow network is combined with the SLAM pipeline.…”

Section: Related Workmentioning

confidence: 99%

“…[3], [32]- [34]. In [32], the feature descriptor of a two-layer shallow network is combined with the SLAM pipeline. In addition, SuperPoint [3], [33], which is a learned feature extractor, is combined with BA to update the stability score for each point.…”

Section: Related Workmentioning

confidence: 99%

Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints

Jau¹,

Zhu²,

Sheng³

et al. 2020

Preprint

View full text Add to dashboard Cite

Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry (VO) and simultaneous localization and mapping (SLAM), where classic methods consisting of hand-crafted features and samplingbased outlier rejection have been a dominant choice for over a decade. Although multiple works propose to replace these modules with learning-based counterparts, most have not yet been as accurate, robust and generalizable as conventional methods. In this paper, we design an end-to-end trainable framework consisting of learnable modules for detection, feature extraction, matching and outlier rejection, while directly optimizing for the geometric pose objective. We show both quantitatively and qualitatively that pose estimation performance may be achieved on par with the classic pipeline. Moreover, we are able to show by end-to-end training, the key components of the pipeline could be significantly improved, which leads to better generalizability to unseen datasets compared to existing learning-based methods.

show abstract

DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local Features

Cited by 15 publications

References 50 publications

RGB-D Visual SLAM Based on Yolov4-Tiny in Indoor Dynamic Environment

RGB-D Visual SLAM Based on Yolov4-Tiny in Indoor Dynamic Environment

Edge Robotics: Edge-Computing-Accelerated Multi-Robot Simultaneous Localization and Mapping

Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints

Contact Info

Product

Resources

About