Active Appearance-Based Robot Localization Using Stereo Vision

Porta, Josep M.; Verbeek, Jakob; Kröse, B.J.A.

doi:10.1023/b:auro.0000047287.00119.b6

Cited by 67 publications

(53 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DO concentrations, chemical species sensitive to biogeochemical cycling or changing redox conditions, and those correlated with these species were incorporated into a square-root-transformed principle component analysis (PCA) Mencio and Mas-Pla, 2008;Woocay and Walton, 2008], or for samples with missing values, probabilistic PCA [Roweis, 1998;Tipping and Bishop, 1999;Porta et al, 2005].…”

Section: Data Analysis Methodsmentioning

confidence: 99%

Spatial patterns of hyporheic exchange and biogeochemical cycling around cross‐vane restoration structures: Implications for stream restoration design

Gordon

Lautz

Daniluk

2013

Water Resources Research

View full text Add to dashboard Cite

[1] Natural channel design restoration projects in streams often include the construction of cross-vanes, which are stone, dam-like structures that span the active channel. Vertical hyporheic exchange flux (HEF) and redox-sensitive solutes were measured in the streambed around four cross-vanes with different morphologies. Observed patterns of HEF and redox conditions are not dominated by a single, downstream-directed hyporheic flow cell beneath cross-vanes. Instead, spatial patterns of moderate (<0.4 m d À1 ) upwelling and downwelling are distributed in smaller cells around pool and riffle bed forms upstream and downstream of structures. Patterns of biogeochemical cycling are controlled by dissolved oxygen concentrations and resulting redox conditions, and are also oriented around secondary bed forms. Strong downwelling into the hyporheic zone (0.5-3.5 m d À1 ) was observed immediately upstream of structures, but was limited to an area 1-2 m from the cross-vane; these hyporheic flow paths likely rejoin the stream at the base of cross-vanes after residence times too short to alter nitrate concentrations or accumulate reaction products. Total hyporheic exchange volumes are $0.4% of stream discharge in restored reaches of 45-55 m. Results show that shallow hyporheic flow and associated biogeochemical cycling near cross-vanes is primarily controlled by secondary bed forms created or augmented by the cross-vane, rather than by the cross-vane itself. This study suggests that cross-vane restoration structures benefit the stream ecosystem by creating heterogeneous patches of varying HEF and redox conditions in the hyporheic zone, rather than by processing large amounts of nutrients to alter in-stream water chemistry.Citation: Gordon, R. P., L. K. Lautz, and T. L. Daniluk (2013), Spatial patterns of hyporheic exchange and biogeochemical cycling around cross-vane restoration structures: Implications for stream restoration design, Water Resour.

show abstract

Section: Data Analysis Methodsmentioning

confidence: 99%

Spatial patterns of hyporheic exchange and biogeochemical cycling around cross‐vane restoration structures: Implications for stream restoration design

Gordon

Lautz

Daniluk

2013

Water Resources Research

View full text Add to dashboard Cite

show abstract

“…Davison and Kita (2001) described a vision-based localization in which the robot actively senses the features based on visibility and information gain. Recently, Porta et al (2005) proposed an entropy-based criterion for action selection within a localization algorithm using a stereo vision system, which allows the robot to recover its location in the initial stages or within a failure recovery procedure more efficiently. Fox et al (1998) proposed an approach for active localization based on Markov localization using finegrained grid maps and laser range finder.…”

Section: Related Workmentioning

confidence: 99%

Monte Carlo localization in outdoor terrains using multilevel surface maps

Kümmerle

Triebel

Pfaff

et al. 2008

Journal of Field Robotics

View full text Add to dashboard Cite

We propose a novel combination of techniques for robustly estimating the position of a mobile robot in outdoor environments using range data. Our approach applies a particle filter to estimate the full six-dimensional state of the robot and utilizes multilevel surface maps which, in contrast to standard elevation maps, allow the robot to represent vertical structures and multiple levels in the environment. We describe probabilistic motion and sensor models to calculate the proposal distribution and to evaluate the likelihood of observations. We furthermore describe an active localization approach which actively selects the sensor orientation of the 2D laser range scanner to improve the localization results. To efficiently calculate the appropriate orientation we apply a clustering operation on the particles and only evaluate potential orientations based on these clusters. Experimental results obtained with a mobile robot in large-scale outdoor environments indicate that our approach yields robust and accurate position estimates. The experiments also demonstrate that multilevel surface maps lead to a significantly better localization performance than standard elevation maps. They additionally show that further accuracy is obtained from the active sensing approach.

show abstract

“…There are many methods for visual localization [7], [8], [9], [10]. Vision allows an accurate global localization with low cost hardware.…”

Section: B Visual Localizationmentioning

confidence: 99%

Fusing vision and odometry for accurate indoor robot localization

Bischoff

Nguyen-Tuong

Streichert

et al. 2012

2012 12th International Conference on Control Automation Robotics &Amp; Vision (ICARCV)

View full text Add to dashboard Cite

Abstract-For service robotics, localization is an essential component required in many applications, e.g. indoor robot navigation. Today, accurate localization relies mostly on high-end devices, such as A.R.T. DTrack, VICON systems or laser scanners. These systems are often expensive and, thus, require substantial investments. In this paper, our focus is on the development of a localization method using low-priced devices, such as cameras, while being sufficiently accurate in tracking performance. Vision data contains much information and potentially yields high tracking accuracy. However, due to high computational requirements vision-based localization can only be performed at a low frequency. In order to speed up the visual localization and increase accuracy, we combine vision information with robots odometry using a Kalman-Filter. The resulting approach enables sufficiently accurate tracking performance (errors in the range of few cm) at a frequency of about 35Hz. To evaluate the proposed method, we compare our tracking performance with the high precision A.R.T. DTrack localization as ground truth. The evaluations on real robot show that our low-priced localization approach is competitive for indoor robot localization tasks.

show abstract

Active Appearance-Based Robot Localization Using Stereo Vision

Cited by 67 publications

References 54 publications

Spatial patterns of hyporheic exchange and biogeochemical cycling around cross‐vane restoration structures: Implications for stream restoration design

Spatial patterns of hyporheic exchange and biogeochemical cycling around cross‐vane restoration structures: Implications for stream restoration design

Monte Carlo localization in outdoor terrains using multilevel surface maps

Fusing vision and odometry for accurate indoor robot localization

Contact Info

Product

Resources

About