An Experimental Study of Aerial Stereo Visual Odometry

Kelly, Jonathan; Sukhatme, Gaurav S.

doi:10.3182/20070903-3-fr-2921.00036

Cited by 22 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, the only work that has examined the effect of camera orientation on stereo visual odometry estimates is that of Kelly and Sukhatme [5]. The authors presented a brief experimental study of camera pitch on stereo visual odometry computed from images collected onboard a radio-controlled helicopter (note that this differs from our work, which studies camera yaw on ground vehicles).…”

Section: Related Workmentioning

confidence: 92%

“…As with all deadreckoning techniques, stereo VO exhibits error that grows without bound with the distance travelled. Unlike other techniques, however, stereo VO can produce accurate pose estimates over significant distances, with errors as low as a few percent of the distance travelled on trajectories of several hundred meters [5]. It is also particularly useful because, unlike monocular implementations, the absolute scale of the motion can be recovered without the use of any additional sensors or prior knowledge of scene structure.…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Optimizing Camera Perspective for Stereo Visual Odometry

Peretroukhin

Kelly

Barfoot

2014

2014 Canadian Conference on Computer and Robot Vision

Self Cite

View full text Add to dashboard Cite

Visual Odometry (VO) is an integral part of many navigation techniques in mobile robotics. In this work, we investigate how the orientation of the camera affects the overall position estimates recovered from stereo VO. Through simulations and experimental work, we demonstrate that this error can be significantly reduced by changing the perspective of the stereo camera in relation to the moving platform. Specifically, we show that orienting the camera at an oblique angle to the direction of travel can reduce VO error by up to 82% in simulations and up to 59% in experimental data. A variety of parameters are investigated for their effects on this trend including frequency of captured images and camera resolution.

show abstract

Section: Related Workmentioning

confidence: 92%

Section: Introductionmentioning

confidence: 98%

Optimizing Camera Perspective for Stereo Visual Odometry

Peretroukhin

Kelly

Barfoot

2014

2014 Canadian Conference on Computer and Robot Vision

Self Cite

View full text Add to dashboard Cite

show abstract

“…Good results have been obtained using stereo camera configurations [Kelly and Sukhatme, 2007;Tomić et al, 2012;Shen et al, 2013], and RGB-D sensor systems Valenti et al, 2014;Loianno et al, 2015b]. However, these algorithms generally require powerful computers to produce and deal with fairly dense point clouds.…”

Section: Related Workmentioning

confidence: 99%

Visual Guidance of Unmanned Aerial Manipulators

Santamaria-Navarro

Solà

Andrade‐Cetto

2019

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

The ability to fly has greatly expanded the possibilities for robots to perform surveillance, inspection or map generation tasks. Yet it was only in recent years that research in aerial robotics was mature enough to allow active interactions with the environment. The robots responsible for these interactions are called aerial manipulators and usually combine a multirotor platform and one or more robotic arms. The main objective of this thesis is to formalize the concept of aerial manipulator and present guidance methods, using visual information, to provide them with autonomous functionalities. A key competence to control an aerial manipulator is the ability to localize it in the environment. Traditionally, this localization has required external infrastructure of sensors (e.g., GPS or IR cameras), restricting the real applications. Furthermore, localization methods with on-board sensors, exported from other robotics fields such as simultaneous localization and mapping (SLAM), require large computational units becoming a handicap in vehicles where size, load, and power consumption are important restrictions. In this regard, this thesis proposes a method to estimate the state of the vehicle (i.e., position, orientation, velocity and acceleration) by means of on-board, low-cost, lightweight and high-rate sensors. With the physical complexity of these robots, it is required to use advanced control techniques during navigation. Thanks to their redundancy on degrees-of-freedom, they offer the possibility to accomplish not only with mobility requirements but with other tasks simultaneously and hierarchically, prioritizing them depending on their impact to the overall mission success. In this work we present such control laws and define a number of these tasks to drive the vehicle using visual information, guarantee the robot integrity during flight, and improve the platform stability or increase arm operability. The main contributions of this research work are threefold: (1) Present a localization technique to allow autonomous navigation, this method is specifically designed for aerial platforms with size, load and computational burden restrictions. (2) Obtain control commands to drive the vehicle using visual information (visual servo). (3) Integrate the visual servo commands into a hierarchical control law by exploiting the redundancy of the robot to accomplish secondary tasks during flight. These tasks are specific for aerial manipulators and they are also provided. All the techniques presented in this document have been validated throughout extensive experimentation with real robotic platforms. i

show abstract

“…[4][5][6] In many cases, VO is integrated with an Inertial Measurement Unit (IMU), [7][8][9] and it is then termed a Vision-Aided Inertial Navigation System (VAINS). Alternately, many other sensor configurations rely on using vision alone as a pose estimator [10][11][12] and these are simply called Vision-Based Navigation (VBN). Both VAINS and VBN can be classified into two main approaches (1) monocular VO and (2) stereo VO.…”

Section: Visual Sensors For Gnss Denied Environmentsmentioning

confidence: 99%

A smart hybrid vision aided inertial navigation system approach for UAVs in a GNSS denied environment

et al. 2018

View full text Add to dashboard Cite

This paper presents a smart hybrid vision‐aided inertial navigation system (VAINS) for enhancing the navigation accuracy of UAVs in GNSS‐denied environments. The proposed system consists of GNSS, INS, monocular visual odometry (VO) based on optical flow and regression trees, a Gaussian process regression (GPR), and extended Kalman filter (EKF) for data fusion. Although a variety of monocular VO‐based on photogrammetric, structure from motion, and machine learning approaches have been proposed to assist the navigation process, the accuracy of 3‐D positioning using these techniques is still affected by some factors such as the lack of the observed features, incorrect matches, and the accumulated positioning drift errors. Therefore, the development of a reliable navigation system that can handle such challenges is necessary. In this system, the GPR algorithm is deployed to model these errors when the GNSS signal is available and to correct them when the GNSS signal is lost.

show abstract

An Experimental Study of Aerial Stereo Visual Odometry

Cited by 22 publications

References 9 publications

Optimizing Camera Perspective for Stereo Visual Odometry

Optimizing Camera Perspective for Stereo Visual Odometry

Visual Guidance of Unmanned Aerial Manipulators

A smart hybrid vision aided inertial navigation system approach for UAVs in a GNSS denied environment

Contact Info

Product

Resources

About