Trajectory Drift–Compensated Solution of a Stereo RGB-D Mapping System

2020 ◽  
Vol 86 (6) ◽  
pp. 359-372
Author(s):  
Shengjun Tang ◽  
Qing Zhu ◽  
You Li ◽  
Wu Chen ◽  
Bo Wu ◽  
...  
Keyword(s):  
Three Dimensional ◽  
Camera Tracking ◽  
Robotic Vision ◽  
Multiple Sensors ◽  
Pose Tracking ◽  
Localization And Mapping ◽  
Mapping System ◽  
Map Updating ◽  
Time Drift ◽  
Mapping Solution

Multiple sensors are commonly used for three-dimensional (3D)-mapping or robotic-vision applications, as they provide a larger field of view and sufficient observations to fulfill frame-registration and map-updating tasks. However, the data sequences generated by multiple sensors can be inconsistent and contain significant time drift. In this paper, we describe the trajectory drift–compensated strategy that we designed to eliminate the influence of time drift between sensors, remove the inconsistency between the sequences from various sensors, and thereby generate a coarse-to-fine procedure for robust camera-tracking based on two-dimensional–3D observations from stereo sensors. We present the mathematical analysis of the iterative optimizations for pose tracking in a stereo red, green, blue plus depth (RGB-D) camera. Finally, complex indoor scenario experiments demonstrate the efficiency of the proposed stereo RGB-D simultaneous localization and mapping solution. The results verify that the proposed stereo RGB-D mapping solution effectively improves the accuracies of both camera-tracking and 3D reconstruction.

scholarly journals Stereo RGB-D indoor mapping with precise stream fusing strategy

2019 ◽  
Vol 1 ◽  
pp. 1-2
Author(s):  
Shengjun Tang ◽  
Weixi Wang ◽  
Xiaoming Li ◽  
Zhilu Yuan
Keyword(s):  
Visual Slam ◽  
Multiple Cameras ◽  
Camera Tracking ◽  
Extrinsic Calibration ◽  
Loop Closure ◽  
Multiple Camera ◽  
Loop Closure Detection ◽  
Pose Tracking ◽  
Map Updating ◽  
Time Drift

<p><strong>Abstract.</strong> In order to achieve more robust pose tracking and mapping of visual SLAM, the robotics researcher has recently shown a growing interest in utilising multiple camera, which is able to provide more sufficient observations to fulfil the frame registration and map updating tasks. This implies that better pose tracking robustness can be achieved by extending monocular visual SLAM to utilise measurements from multiple cameras.[1] proposed a visual SLAM method using multiple RGB-D cameras, which integrate the observations from multi-camera for camera tracking. However, they ignored the time-drift between the frames obtained by different cameras, which may result at inaccurate positions of observation used for map updating. Besides, loop closure detection was not been implemented. [2] constructed a multiple RGB-D system with three Kinects V2 camera. This work mainly concentrated on the intrinsic and extrinsic calibration and verify the effectiveness of mapping using multiply RGB-D cameras.</p>

scholarly journals Visual SLAM Framework Based on Segmentation with the Improvement of Loop Closure Detection in Dynamic Environments

2021 ◽  
Vol 33 (6) ◽  
pp. 1385-1397
Author(s):  
Leyuan Sun ◽  
Rohan P. Singh ◽  
Fumio Kanehiro ◽  
◽  
◽  
...  
Keyword(s):  
Point Cloud ◽  
Three Dimensional ◽  
Dynamic Environments ◽  
Camera Tracking ◽  
Loop Closure ◽  
Loop Closure Detection ◽  
Multiple Datasets ◽  
Localization And Mapping ◽  
Object Based ◽  
Precision Recall Curve

Most simultaneous localization and mapping (SLAM) systems assume that SLAM is conducted in a static environment. When SLAM is used in dynamic environments, the accuracy of each part of the SLAM system is adversely affected. We term this problem as dynamic SLAM. In this study, we propose solutions for three main problems in dynamic SLAM: camera tracking, three-dimensional map reconstruction, and loop closure detection. We propose to employ geometry-based method, deep learning-based method, and the combination of them for object segmentation. Using the information from segmentation to generate the mask, we filter the keypoints that lead to errors in visual odometry and features extracted by the CNN from dynamic areas to improve the performance of loop closure detection. Then, we validate our proposed loop closure detection method using the precision-recall curve and also confirm the framework’s performance using multiple datasets. The absolute trajectory error and relative pose error are used as metrics to evaluate the accuracy of the proposed SLAM framework in comparison with state-of-the-art methods. The findings of this study can potentially improve the robustness of SLAM technology in situations where mobile robots work together with humans, while the object-based point cloud byproduct has potential for other robotics tasks.

scholarly journals Use of 3D mapping system for ablating an accessory pathway associated with coronary sinus diverticulum

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Mohammad Paymard ◽  
Marc W. Deyell ◽  
Santabhanu Chakrabarti ◽  
Zachary W. Laksman ◽  
Jacob Larsen ◽  
...  
Keyword(s):  
Coronary Sinus ◽  
Accessory Pathway ◽  
Three Dimensional ◽  
Radiofrequency Energy ◽  
Cardiac Mapping ◽  
Unsuccessful Attempt ◽  
White Syndrome ◽  
Mapping System ◽  
Coronary Sinus Diverticulum ◽  
Wolff Parkinson White Syndrome

Abstract Background This is a rare and challenging case of Wolff–Parkinson–White syndrome due to a posteroseptal accessory pathway located in the coronary sinus diverticulum. It is often difficult to precisely locate this type of accessory pathway, and the ablation procedure could be associated with collateral damage to the neighbouring coronary arteries. Case Presentation The patient was a 49-year-old female with Wolff–Parkinson–White syndrome who was referred for catheter ablation. She had had a previous unsuccessful attempt at ablation and had remained symptomatic despite drug therapy. The pre-procedural cardiac computed tomography scan revealed the presence of a diverticulum in the proximal coronary sinus. Using an advanced three-dimensional cardiac mapping system, the electroanatomic map of the diverticulum was created. The accessory pathway potential was identified within the diverticulum preceding the ventricular insertion. The accessory pathway was then successfully ablated using radiofrequency energy. Conclusion We have demonstrated that the advanced three-dimensional cardiac mapping system plays a very important role in guiding clinicians in order to precisely locate and safely ablate this type of challenging accessory pathway.

Is It Possible to Perform a Linear Lesion with No Local Electrograms Using a Three-Dimensional Mapping System for the Ablation of Typical Atrial Flutter?

Cardiology ◽  
2007 ◽  
Vol 108 (4) ◽  
pp. 358-362
Author(s):  
Carmine Muto ◽  
Luca Ottaviano ◽  
Michelangelo Canciello ◽  
Giovanni Carreras ◽  
Salvatore Angelini ◽  
...  
Keyword(s):  
Atrial Flutter ◽  
Three Dimensional ◽  
Three Dimensional Mapping ◽  
Typical Atrial Flutter ◽  
Mapping System ◽  
Dimensional Mapping

Abstract 16807: Role of Rotor Activation Within the Pulmonary Vein as the Driving Sources for Atrial Fibrillation: Three-dimensional Analysis using a Non-contact Mapping System

Circulation ◽  
2015 ◽  
Vol 132 (suppl_3) ◽  
Author(s):  
Hiroshige Yamabe ◽  
Hisanori Kanazawa ◽  
Tadashi Hoshiyama ◽  
Miwa Ito ◽  
Shozo Kaneko ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Pulmonary Vein ◽  
Three Dimensional ◽  
Recording Site ◽  
Contact Mapping ◽  
Proximal Half ◽  
Mapping System ◽  
Endocardial Mapping ◽  
Activation Sequence

Background: It has been suggested rotor which is located within the pulmonary vein (PV) acted as the driving sources of atrial fibrillation (AF). However, it has never been confirmed whether or not the rotor exists within PV in human. Objectives: We analyzed the activation sequence within the PV during AF and examined how the PV acted as the driving sources of AF. Methods: Selective endocardial mapping of left superior PV (LSPV) was performed during AF in 11 paroxysmal AF patients using a non-contact mapping system (EnSite 3000). Presence of rotor activation was defined when the circular activation around the functional block line once completed its whole reentrant activation. We analyzed the relation between the pivoting activation and the rotor activation. To define the preferable site of rotor and pivoting activation, we also analyzed the relation between the location of rotor and pivoting activation and region of the complex fractionated electrogram (CFE) recording site. Results: Rotor activation was observed with a mean number of 4.6±3.6 times/sec. CFE was observed at the roof (n=5), ridge (n=11) and carina (n=7) of the proximal half of LSPV with a mean area of 9.1±3.4 cm2. The number of rotor activation observed at the CFE area was significantly higher than that at the non-CFE area (4.1±3.9 vs. 0.7±1.2 times/sec, p=0.025). Total frequency of pivoting activation was 37.0±14.7 times/sec. Pivoting activation involved in the rotor activation was significantly lower than that not involved in the rotor activation (8.8±8.1 vs. 27.7±15.8 times/sec, p=0.0116). Regarding the CFE area, pivoting activation involved in the rotor activation was also significantly lower than that not involved in the rotor activation (8.4±8.2 vs. 24.1±12.0 times/sec, p=0.0105). However, there was no difference between the frequencies of pivoting activation with and without rotor activation in the non-CFE area (1.0±2.0 vs. 3.6±6.1 times/sec, p=NS). Conclusions: Rotor activation was observed at the proximal portion of the LSPV coincided with the location of CFE area. However, most of pivoting activation was not involved in the rotor activation. These suggest that AF was driven by the other meandering propagation associated with frequent non-stable pivoting activation over the CFE area.

scholarly journals Research and Implementation of Robot Path Planning Based onVSLAM

2018 ◽  
Vol 160 ◽  
pp. 06004
Author(s):  
Zi-Qiang Wang ◽  
He-Gen Xu ◽  
You-Wen Wan
Keyword(s):  
Path Planning ◽  
Three Dimensional ◽  
Planning Problem ◽  
A Algorithm ◽  
Algorithm Efficiency ◽  
Grid Map ◽  
Localization And Mapping ◽  
Improve Algorithm ◽  
Path Planning Problem ◽  
Robot Path

In order to solve the problem of warehouse logistics robots planpath in different scenes, this paper proposes a method based on visual simultaneous localization and mapping (VSLAM) to build grid map of different scenes and use A* algorithm to plan path on the grid map. Firstly, we use VSLAMto reconstruct the environment in three-dimensionally. Secondly, based on the three-dimensional environment data, we calculate the accessibility of each grid to prepare occupied grid map (OGM) for terrain description. Rely on the terrain information, we use the A* algorithm to solve path planning problem. We also optimize the A* algorithm and improve algorithm efficiency. Lastly, we verify the effectiveness and reliability of the proposed method by simulation and experimental results.

Sign in / Sign up

Export Citation Format

Share Document