Improving MAV pose estimation using visual information

Andersen, E.D.; Taylor, Clark N.

doi:10.1109/iros.2007.4399563

Cited by 25 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several innovative algorithms fusing GPS and MEMS observations have been shown to improve the modelling of the large stochastic drifts within MEMS IMUs and as a consequence the accuracy of orientation estimates [23][24][25]. Furthermore, the augmentation of techniques developed within the fields of photogrammetry and computer vision have contributed to improving the accuracies of MEMS-based navigation systems when used for direct georeferencing [26][27][28]. These developments suggest that a UAV system consisting of a lightweight MEMS based IMU along with GPS and visual observations can provide estimates of position and orientation with the accuracy required for mapping forest metrics using UAV-borne LiDAR.…”

Section: Introductionmentioning

confidence: 99%

Development of a UAV-LiDAR System with Application to Forest Inventory

et al. 2012

View full text Add to dashboard Cite

We present the development of a low-cost Unmanned Aerial Vehicle-Light Detecting and Ranging (UAV-LiDAR) system and an accompanying workflow to produce 3D point clouds. UAV systems provide an unrivalled combination of high temporal and spatial resolution datasets. The TerraLuma UAV-LiDAR system has been developed to take advantage of these properties and in doing so overcome some of the current limitations of the use of this technology within the forestry industry. A modified processing workflow including a novel trajectory determination algorithm fusing observations from a GPS receiver, an Inertial Measurement Unit (IMU) and a High Definition (HD) video camera is presented. The advantages of this workflow are demonstrated using a rigorous assessment of the spatial accuracy of the final point clouds. It is shown that due to the inclusion of video the horizontal accuracy of the final point cloud improves from 0.61 m to 0.34 m (RMS error assessed against ground control). The effect of the very high density point clouds (up to 62 points per m 2 ) produced by the UAV-LiDAR system on the measurement of tree location, height and crown width are also assessed by performing repeat surveys over individual isolated trees. The standard deviation of tree height is shown to reduce from 0.26 m, when using data with a density of 8 points per m 2 , to 0.15 m when the higher density data was used.Improvements in the uncertainty of the measurement of tree location, 0.80 m to 0.53 m, and crown width, 0.69 m to 0.61 m are also shown.Remote Sens. 2012, 4 1520

show abstract

Section: Introductionmentioning

confidence: 99%

Development of a UAV-LiDAR System with Application to Forest Inventory

et al. 2012

View full text Add to dashboard Cite

show abstract

“…Another strategy is registration of live video to previously acquired satellite imagery [3], which provides a direct measurement of a viewable object's world location. Either of these may be combined with simultaneous visual UAV pose refinement techniques such as Extended Kalman Filter (EKF) visual landmark tracking [4], [5], structure from motion [6], and homography-based pose refinement [7] for additional observation accuracy. However, terrain matching techniques assume the availability of recent prior imagery and are vulnerable to changes since this imagery was acquired.…”

Section: Related Workmentioning

confidence: 99%

Efficient target geolocation by highly uncertain small air vehicles

Grocholsky

Dille

Nuske

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-Geolocation of a ground object or target of interest from live video is a common task required of small and micro unmanned aerial vehicles (SUAVs and MAVs) in surveillance and rescue applications. However, such vehicles commonly carry low-cost and light-weight sensors providing poor bandwidth and accuracy whose contribution to observations is nonlinear, resulting in poor geolocation performance by standard techniques. This paper proposes the application of an efficient over-parameterized state representation to the problem of geolocation that is able to handle large, time-varying, and non-Gaussian sensor error to produce better geolocation estimates than typical approaches and which provides computing and communication benefits in applications such as predictive control and distributed collaboration. We evaluate our filter on real flight data, demonstrating its ability to efficiently produce a solution with tight confidence bounds given highly uncertain data.

show abstract

“…Rather than run full visual and wheel odometry systems in parallel, we have focused on how to best exploit wheel odometry to lighten the computational burden of VO. A number of authors have used visual matching to correct IMU or GPS data on aerial platforms (Brown and Sullivan, 2002) (Andersen and Taylor, 2007) . Our system is implemented on a ground rover, where many of the assumptions afforded in the air, such as nearly coplanar features and slow visual flow, do not apply.…”

Section: Related Workmentioning

confidence: 99%

A multirange architecture for collision‐free off‐road robot navigation

Sermanet

Hadsell

Scoffier

et al. 2008

Journal of Field Robotics

View full text Add to dashboard Cite

We present a multi-layered mapping, planning, and command execution system developed and tested on the LAGR mobile robot. Key to robust performance under uncertainty is the combination of a short-range perception system operating at high frame rate and low resolution and a long-range, adaptive vision system operating at lower frame rate and higher resolution. The short-range module performs local planning and obstacle avoidance with fast reaction times, while the long-range module performs strategic visual planning. Probabilistic traversability labels provided by the perception modules are combined and accumulated into a robot-centered hyperbolic-polar map with a 200 meter effective range. Instead of using a dynamical model of the robot for short-range planning, the system uses a large lookup table of physically-possible trajectory segments recorded on the robot in a wide variety of driving conditions. Localization is performed using a combination of GPS, wheel odometry, IMU, and a high-speed, low-complexity rotational visual odometry module. The end to end system was developed and tested on the LAGR mobile robot, and was verified in independent government tests.

show abstract

Improving MAV pose estimation using visual information

Cited by 25 publications

References 15 publications

Development of a UAV-LiDAR System with Application to Forest Inventory

Development of a UAV-LiDAR System with Application to Forest Inventory

Efficient target geolocation by highly uncertain small air vehicles

A multirange architecture for collision‐free off‐road robot navigation

Contact Info

Product

Resources

About