Omni-directional vision for robot navigation

Winters, Niall; Gaspar, José António; Lacey, Gerard; Santos-Victor, José

doi:10.1109/omnvis.2000.853799

Cited by 150 publications

(87 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Following a common approach to computing correspondences in omnidirectional imagery [19], [20], [21], we rectify the relevant portion of each omnidirectional image into a virtual perspective image such that epipolar lines are image rows; mask out the robot chassis, sensor mast, and peripheral pixels which are not imaged or severely distorted due to the fisheye lens; and then apply a standard pixel correspondence algorithm. The target region of a sample left camera image is outlined in Figure 4(a); this corresponds to a horizontal FOV of approximately 114…”

Section: A Height Map Computationmentioning

confidence: 99%

Integrating stereo structure for omnidirectional trail following

Rasmussen

Kocamaz

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-We describe a system which follows "trails" for autonomous outdoor robot navigation. Through a combination of appearance and structural cues derived from stereo omnidirectional color cameras, the algorithm is able to detect and track rough paths despite widely varying tread material, border vegetation, and illumination conditions. The approaching trail region is modeled as a circular arc segment of constant width. Using likelihood formulations which measure color, brightness, and/or height contrast between a hypothetical region and flanking areas, the tracker performs a robust randomized search for the most likely trail region and robot pose relative to it with no a priori appearance model. The addition of the structural information, which is derived from a semi-global dense stereo algorithm with ground-plane fitting, is shown to improve trail segmentation accuracy and provide an additional layer of safety beyond solely ladar-based obstacle avoidance. Our system's ability to follow a variety of trails is demonstrated through live runs as well as analysis of offline runs on several long sequences with diverse appearance and structural characteristics using ground-truth segmentations.

show abstract

Section: A Height Map Computationmentioning

confidence: 99%

Integrating stereo structure for omnidirectional trail following

Rasmussen

Kocamaz

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…In our case, visual environmental information was provided by an omnidirectional camera which gives a 360 • view around the vertical. This work builds on our previous research with such a system [6,27,28].…”

Section: Introductionmentioning

confidence: 97%

Information Sampling for vision-based robot navigation

Winters

Santos-Victor

2002

Robotics and Autonomous Systems

View full text Add to dashboard Cite

This paper proposes a statistical, non-feature based, attention mechanism for a mobile robot, termed Information Sampling. The selected data may be a single pixel or a number scattered throughout an image. After ranking this data, we choose only the most discriminating to build a topological representation of the environment, obtained via Principal Component Analysis (PCA). Advantageously, using this approach, our robot gains the ability to make effective use of its perceptual capabilities and limited computational resources. Real world experimental results verify that vision-based navigation is possible using only a small number of discriminating image pixels.

show abstract

“…One of these visual sensors is an omni-directional camera that provides a wide field of view of a scene that might cover almost a hemisphere or the entire 360° circle along the equator of a sphere. A fisheye lens is one of the most efficient ways to construct an omni-directional vision system [1][2][3]. Although fisheye lens cameras, which can be simply achieved by using a fisheye lens, provide us with the advantage of a wide angle of view, their images usually exhibit considerable distortion.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Rotation of Camera Direction and Distance Between Two Camera Positions by Using Fisheye Lens System

Aregawi¹,

Kwon²,

Park³

et al. 2013

Journal of Sensor Science and Technology

View full text Add to dashboard Cite

We propose a method of sensing the rotation and distance of a camera by using a fisheye lens system as a vision sensor. We estimate the rotation angle of a camera with a modified correlation method by clipping similar regions to avoid symmetry problems and suppressing highlight areas. In order to eliminate the rectification process of the distorted points of a fisheye lens image, we introduce an offline process using the normalized focal length, which does not require the image sensor size. We also formulate an equation for calculating the distance of a camera movement by matching the feature points of the test image with those of the reference image. Aug. 26, 2013, Accepted : Nov. 1, 2013 This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License(http://creativecommons.org/licenses/bync/3.0)which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited. Keywords

show abstract

Omni-directional vision for robot navigation

Cited by 150 publications

References 19 publications

Integrating stereo structure for omnidirectional trail following

Integrating stereo structure for omnidirectional trail following

Information Sampling for vision-based robot navigation

Estimation of Rotation of Camera Direction and Distance Between Two Camera Positions by Using Fisheye Lens System

Contact Info

Product

Resources

About