An evaluation of real-time RGB-D visual odometry algorithms on mobile devices

Angladon, Vincent; Gasparini, Simone; Charvillat, Vincent; Pribanić, Tomislav; Petković, Tomislav; Đonlić, Matea; Ahsan, Benjamin; Bruel, Frédéric

doi:10.1007/s11554-017-0670-y

Cited by 14 publications

(5 citation statements)

References 48 publications

(100 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous research [12] compared monocular visual-inertial odometry for six degrees of freedom (6DoF) trajectories of flying robots. [13] assessed performance of VO algorithms using image and depth sensors (RGB-D) for an application of mobile devices. Prior research [14] evaluated VO techniques in challenging underwater conditions.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Three Off-the-Shelf Visual Odometry Systems

et al. 2020

View full text Add to dashboard Cite

Positioning is an essential aspect of robot navigation, and visual odometry an important technique for continuous updating the internal information about robot position, especially indoors without GPS (Global Positioning System). Visual odometry is using one or more cameras to find visual clues and estimate robot movements in 3D relatively. Recent progress has been made, especially with fully integrated systems such as the RealSense T265 from Intel, which is the focus of this article. We compare between each other three visual odometry systems (and one wheel odometry, as a known baseline), on a ground robot. We do so in eight scenarios, varying the speed, the number of visual features, and with or without humans walking in the field of view. We continuously measure the position error in translation and rotation thanks to a ground truth positioning system. Our result shows that all odometry systems are challenged, but in different ways. The RealSense T265 and the ZED Mini have comparable performance, better than our baseline ORB-SLAM2 (mono-lens without inertial measurement unit (IMU)) but not excellent. In conclusion, a single odometry system might still not be sufficient, so using multiple instances and sensor fusion approaches are necessary while waiting for additional research and further improved products.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison of Three Off-the-Shelf Visual Odometry Systems

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Various open-source implementations of VO motion-tracking algorithms may also be suitable for deployment with further development (e.g. [92]). Future work may seek to compare the performance of (or augment) animal-attached VIO motion tracking with previously described magnetometer, accelerometer, and GPS-based dead-reckoning methods (e.g.…”

Section: Discussionmentioning

confidence: 99%

Joining the dots: reconstructing 3D environments and movement paths using animal-borne devices

McClune

2018

Anim Biotelemetry

View full text Add to dashboard Cite

Background: Animal-attached sensors are increasingly used to provide insights on behaviour and physiology. However, such tags usually lack information on the structure of the surrounding environment from the perspective of a study animal and thus may be unable to identify potentially important drivers of behaviour. Recent advances in robotics and computer vision have led to the availability of integrated depth-sensing and motion-tracking mobile devices. These enable the construction of detailed 3D models of an environment within which motion can be tracked without reliance on GPS. The potential of such techniques has yet to be explored in the field of animal biotelemetry. This report trials an animal-attached structured light depth-sensing and visual-inertial odometry motion-tracking device in an outdoor environment (coniferous forest) using the domestic dog (Canis familiaris) as a compliant test species.Results: A 3D model of the forest environment surrounding the subject animal was successfully constructed using point clouds. The forest floor was labelled using a progressive morphological filter. Trees trunks were modelled as cylinders and identified by random sample consensus. The predicted and actual presence of trees matched closely, with an object-level accuracy of 93.3%. Individual points were labelled as belonging to tree trunks with a precision, recall, and F β score of 1.00, 0.88, and 0.93, respectively. In addition, ground-truth tree trunk radius measurements were not significantly different from random sample consensus model coefficient-derived values. A first-person view of the 3D model was created, illustrating the coupling of both animal movement and environment reconstruction. Conclusions:Using data collected from an animal-borne device, the present study demonstrates how terrain and objects (in this case, tree trunks) surrounding a subject can be identified by model segmentation. The device pose (position and orientation) also enabled recreation of the animal's movement path within the 3D model. Although some challenges such as device form factor, validation in a wider range of environments, and direct sunlight interference remain before routine field deployment can take place, animal-borne depth sensing and visual-inertial odometry have great potential as visual biologging techniques to provide new insights on how terrestrial animals interact with their environments.

show abstract

“…Range sensors and their equivalents can be used in addition to, or in replacement of, a monocular camera, in order to eliminate the scale observability issue of VIO. Most approaches leverage either lidar or radar scans [23], RGBD cameras [24], or stereo visual measurements [25]. Unlike VIO, these options suffer either from range limitation or integration costs 2 that limit their use in robotics applications.…”

Section: Vio Scale Drift Mitigationmentioning

confidence: 99%

Range-Visual-Inertial Odometry: Scale Observability Without Excitation

Delaune

Bayard

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Traveling at constant velocity is the most efficient trajectory for most robotics applications. Unfortunately without accelerometer excitation, monocular Visual-Inertial Odometry (VIO) cannot observe scale and suffers severe error drift. This was the main motivation for incorporating a 1D laser range finder in the navigation system for NASA's Ingenuity Mars Helicopter. However, Ingenuity's simplified approach was limited to flat terrains. The current paper introduces a novel range measurement update model based on using facet constraints. The resulting range-VIO approach is no longer limited to flat scenes, but extends to any arbitrary structure for generic robotic applications. An important theoretical result shows that scale is no longer in the right nullspace of the observability matrix for zero or constant acceleration motion. In practical terms, this means that scale becomes observable under constant-velocity motion, which enables simple and robust autonomous operations over arbitrary terrain. Due to the small range finder footprint, range-VIO retains the minimal size, weight, and power attributes of VIO, with similar runtime. The benefits are evaluated on real flight data representative of common aerial robotics scenarios. Robustness is demonstrated using indoor stress data and fullstate ground truth. We release our software framework, called xVIO, as open source.

show abstract

An evaluation of real-time RGB-D visual odometry algorithms on mobile devices

Abstract: OATAO is an open access repository that collects the work of some Toulouse researchers and makes it freely available over the web where possible.

Cited by 14 publications

References 48 publications

Comparison of Three Off-the-Shelf Visual Odometry Systems

Comparison of Three Off-the-Shelf Visual Odometry Systems

Joining the dots: reconstructing 3D environments and movement paths using animal-borne devices

Range-Visual-Inertial Odometry: Scale Observability Without Excitation

Contact Info

Product

Resources

About