Benchmark of Visual SLAM Algorithms: ORB-SLAM2 vs RTAB-Map

Ragot, Nicolas; Khemmar, Redouane; Pokala, Adithya; Rossi, Romain; Ertaud, Jean-Yves

doi:10.1109/est.2019.8806213

Cited by 25 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Overall, the reported qualitative and the quantitative results prove that our deep learning proposal is robust enough against challenges of road scenes. Ultimately, we aim to use our solution in both indoor (such as smart wheelchair for disabled people [24]) and outdoor (soft mobility for car and tramway) environments. The road and tramway domains are quite similar to outdoor environments, which allows the algorithms trained on the road domain to offer good performances when inferring on the tramway domain.…”

Section: Discussionmentioning

confidence: 99%

“…These sensors have the ability to provide what is called a depth map providing 3D information related to the distance of the surfaces of filmed objects from a specific viewpoint. These cameras have been used in [24] to make visual SLAM (Simultaneous Localisation and Mapping), or cartography and simultaneous localisation. This visual sensor has the ability to provide reliable results when used indoors but has not been tested in outdoor conditions.…”

Section: Acquisition Systemmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Real-Time 3D Multi-Object Detection, Localisation, and Tracking: Application to Smart Mobility

Mauri

Khemmar

Decoux

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

In core computer vision tasks, we have witnessed significant advances in object detection, localisation and tracking. However, there are currently no methods to detect, localize and track objects in road environments, and taking into account real-time constraints. In this paper, our objective is to develop a deep learning multi object detection and tracking technique applied to road smart mobility. Firstly, we propose an effective detector-based on YOLOv3 which we adapt to our context. Subsequently, to localize successfully the detected objects, we put forward an adaptive method aiming to extract 3D information, i.e., depth maps. To do so, a comparative study is carried out taking into account two approaches: Monodepth2 for monocular vision and MADNEt for stereoscopic vision. These approaches are then evaluated over datasets containing depth information in order to discern the best solution that performs better in real-time conditions. Object tracking is necessary in order to mitigate the risks of collisions. Unlike traditional tracking approaches which require target initialization beforehand, our approach consists of using information from object detection and distance estimation to initialize targets and to track them later. Expressly, we propose here to improve SORT approach for 3D object tracking. We introduce an extended Kalman filter to better estimate the position of objects. Extensive experiments carried out on KITTI dataset prove that our proposal outperforms state-of-the-art approches.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Acquisition Systemmentioning

confidence: 99%

Deep Learning for Real-Time 3D Multi-Object Detection, Localisation, and Tracking: Application to Smart Mobility

Mauri

Khemmar

Decoux

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Throughout the year's several benchmark comparisons of VO algorithms have been proposed, usually focusing on the localization of wheeled mobile robots. A comparison between Real-Time Appearance Based Mapping (RTAB-MAP) and Oriented Fast and Rotated Brief (ORB) Simultaneous Localisation and Mapping (SLAM), was done in [37] and their tests proved that the trajectory estimation by RTAB-Map is accurate but odometry is not as accurate as ORB SLAM. Three off-the-shelf odometry systems were compared with OptiTrack ground truth information in [38], where Intel RealSense T265 and Zed mini provided comparable results.…”

Section: Benchmark Comparisons Of Visual Odometry Algorithmsmentioning

confidence: 99%

Construction and benchmark of an autonomous tracked mobile robot system

Ārents¹,

Ahluwalia²,

Oraby³

et al. 2022

Robot. syst., appl.

View full text Add to dashboard Cite

Robots require a certain set of skills to perceive and analyse the environment and act accordingly. For tracked mobile robots getting good odometry data from sensory information is a challenging key prerequisite to perform in an unstructured dynamic environment, thus an essential issue in the tracked mobile robotics domain. In this article, we construct a ROS-based tracked mobile robot system taking the Jaguar V4 mobile robot as the base platform. On which several visual odometry solutions based on different cameras and methods (Intel RealSense T265, Zed camera, RTAB-Map RGBD) are integrated and benchmark comparison is performed. Analysis of new challenges faced by different methods while applied on a tracked vehicle as well as recommendations and conclusions are presented. Intel RealSense T265 solution proved to perform well in uncertain conditions which involves bounded vibrations and low lighting conditions with low latency, which result in good map generation. Further evaluations with a path planning algorithm and Intel RealSense T265 were conducted to test the effect of the robot's motion profiles on odometry data accuracy.

show abstract

“…Some testbeds are designed with the purpose of evaluating only the location and orientation accuracy, while others can also evaluate the correctness of 3D reconstructions in SLAM based methods. Several research papers released to the public a series of datasets and evaluation tools [139,155,156], while others proposed reference systems that can be used for testing the accuracy of localization solutions [157], the latter enabling fair comparisons of existing localization systems in similar conditions [158][159][160].…”

Section: Benchmarksmentioning

confidence: 99%

A Comprehensive Survey of Indoor Localization Methods Based on Computer Vision

Morar

Moldoveanu

Mocanu

et al. 2020

Sensors

122

View full text Add to dashboard Cite

Computer vision based indoor localization methods use either an infrastructure of static cameras to track mobile entities (e.g., people, robots) or cameras attached to the mobile entities. Methods in the first category employ object tracking, while the others map images from mobile cameras with images acquired during a configuration stage or extracted from 3D reconstructed models of the space. This paper offers an overview of the computer vision based indoor localization domain, presenting application areas, commercial tools, existing benchmarks, and other reviews. It provides a survey of indoor localization research solutions, proposing a new classification based on the configuration stage (use of known environment data), sensing devices, type of detected elements, and localization method. It groups 70 of the most recent and relevant image based indoor localization methods according to the proposed classification and discusses their advantages and drawbacks. It highlights localization methods that also offer orientation information, as this is required by an increasing number of applications of indoor localization (e.g., augmented reality).

show abstract

Benchmark of Visual SLAM Algorithms: ORB-SLAM2 vs RTAB-Map

Cited by 25 publications

References 23 publications

Deep Learning for Real-Time 3D Multi-Object Detection, Localisation, and Tracking: Application to Smart Mobility

Deep Learning for Real-Time 3D Multi-Object Detection, Localisation, and Tracking: Application to Smart Mobility

Construction and benchmark of an autonomous tracked mobile robot system

A Comprehensive Survey of Indoor Localization Methods Based on Computer Vision

Contact Info

Product

Resources

About