Monocular image space tracking on a computationally limited MAV

Ok, Kyel; Gamage, Dinesh; Drummond, Tom; Dellaert, Frank; Roy, Nicholas

doi:10.1109/icra.2015.7140100

Cited by 3 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Coupled with computationally inexpensive object detectors [11], [12], the above closed-form measurement model allows for the use of readily available bounding box detections as the only source of measurements to fully constrain vehicle poses and approximate object volumes. This property makes the ellipsoid representation attractive for graph-based SLAM [23] formulations, and is similar to the property of pointbased landmarks in feature-based SLAM [1] that associated feature detections in camera images can be the only source of information to constrain the entire system.…”

Section: A Ellipsoids As Object Representationmentioning

confidence: 90%

“…Past work in building vision-based geometric maps of the world, i.e., vision-based simultaneous localization and mapping (vSLAM), focuses on constructing accurate geometric representations of the world, but is often inadequate for real-time path planning. Sparse [1], [2] and semi-sparse [3]- [5] methods employ a point-cloud representation of the world for computational efficiency, but the sparsity of this representation impedes collision-checking. Dense methods [6], [7] address the problem of sparsity by using a volumetric or mesh-based representation, but these methods often have a high computational burden, while the reconstruction quality deteriorates in scenes with low texture.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Object-based SLAM for High-speed Autonomous Navigation

Liu

Frey

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

We present Robust Object-based SLAM for Highspeed Autonomous Navigation (ROSHAN), a novel approach to object-level mapping suitable for autonomous navigation. In ROSHAN, we represent objects as ellipsoids and infer their parameters using three sources of information -bounding box detections, image texture, and semantic knowledge -to overcome the observability problem in ellipsoid-based SLAM under common forward-translating vehicle motions. Each bounding box provides four planar constraints on an object surface and we add a fifth planar constraint using the texture on the objects along with a semantic prior on the shape of ellipsoids. We demonstrate ROSHAN in simulation where we outperform the baseline, reducing the median shape error by 83% and the median position error by 72% in a forward-moving camera sequence. We demonstrate similar qualitative result on data collected on a fast-moving autonomous quadrotor.

show abstract

Section: A Ellipsoids As Object Representationmentioning

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Robust Object-based SLAM for High-speed Autonomous Navigation

Liu

Frey

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In literature most MAVs which are suitable for operating in indoor and outdoor environments are using cameras as their main sensor. They either use one monocular camera (M. Achtelik, Achtelik, Weiss, & Siegwart, 2011; Ok, Gamage, Drummond, Dellaert, & Roy, 2015; Weiss, Achtelik, Lynen, Chli, & Siegwart, 2012), a stereo setup (Matthies et al, 2014; Schmid, Lutz, et al, 2014; Tomić et al, 2012) or even multiple stereo setups (Schauwecker & Zell, 2014). To further enhance the FOV, (Schneider & Förstner, 2015) used a wide angle stereo camera configuration.…”

Section: Related Workmentioning

confidence: 99%

ARDEA—An MAV with skills for future planetary missions

Lutz

Müller

Maier

et al. 2020

Journal of Field Robotics

View full text Add to dashboard Cite

We introduce a prototype flying platform for planetary exploration: autonomous robot design for extraterrestrial applications (ARDEA). Communication with unmanned missions beyond Earth orbit suffers from time delay, thus a key criterion for robotic exploration is a robot's ability to perform tasks without human intervention. For autonomous operation, all computations should be done on-board and GlobalNavigation Satellite System (GNSS) should not be relied on for navigation purposes.Given these objectives ARDEA is equipped with two pairs of wide-angle stereo cameras and an inertial measurement unit (IMU) for robust visual-inertial navigation and time-efficient, omni-directional 3D mapping. The four cameras cover a 240 ∘ vertical field of view, enabling the system to operate in confined environments such as caves formed by lava tubes. The captured images are split into several pinhole cameras, which are used for simultaneously running visual odometries. The stereo output is used for simultaneous localization and mapping, 3D map generation and collision-free motion planning. To operate the vehicle efficiently for a variety of missions, ARDEA's capabilities have been modularized into skills which can be assembled to fulfill a mission's objectives. These skills are defined generically so that they are independent of the robot configuration, making the approach suitable for different heterogeneous robotic teams. The diverse skill set also makes the micro aerial vehicle (MAV) useful for any task where autonomous exploration is needed.For example terrestrial search and rescue missions where visual navigation in GNSSdenied indoor environments is crucial, such as partially collapsed man-made structures like buildings or tunnels. We have demonstrated the robustness of our system in indoor and outdoor field tests. K E Y W O R D S aerial robotics, computer vision, exploration, GPS-denied operation, planetary robotics ---This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…We do not require a high-performance GPU but can render images using a software-only implementation of OpenGL, such as MESA Gallium llvmpipe, or with an embedded graphics unit such as Intel HD 4400 available on compact PCs used on modern MAVs [19], [20].…”

Section: B Keyframe Renderingmentioning

confidence: 99%

Simultaneous tracking and rendering: Real-time monocular localization for MAVs

Ok¹,

Greene²,

Roy³

2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Abstract-We propose a method of real-time monocular camera-based localization in known environments. With the goal of controlling high-speed micro air vehicles (MAVs), we localize with respect to a mesh map of the environment that can support both pose estimation and trajectory planning. Using only limited hardware that can be carried on a MAV, we achieve accurate pose estimation at rates above 50 Hz, an order of magnitude faster than the current state-of-the-art meshbased localization algorithms. In our simultaneous tracking and rendering (STAR) approach, we render virtual images of the environment and track camera images with respect to them using a robust semi-direct image alignment technique. Our main contribution is the decoupling of camera tracking from virtual image rendering, which drastically reduces the number of rendered images and enables accurate full camerarate tracking without needing a high-end GPU. We demonstrate our approach in GPS-denied indoor environments.

show abstract

Monocular image space tracking on a computationally limited MAV

Cited by 3 publications

References 26 publications

Robust Object-based SLAM for High-speed Autonomous Navigation

Robust Object-based SLAM for High-speed Autonomous Navigation

ARDEA—An MAV with skills for future planetary missions

Simultaneous tracking and rendering: Real-time monocular localization for MAVs

Contact Info

Product

Resources

About