Rolling and swaying motion estimation for a mobile robot by using omnidirectional optical flows

Yagi, Yasushi; Nishi, Wataru; Benson, Nels; Yachida, Masahiko

doi:10.1007/s00138-002-0107-9

Cited by 3 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Practical implementations of omni-directional cameras are the Sony "Full-Circle 360" Lense Mechanisms, which allows a vertical field of view −17 • ≤ φ ≤ 70 • , the IPIX fish eye lens which gives 0 ≤ θ ≤ 185, −92 ≤ φ ≤ 92 and needs two clicks, Microsofts ring cam, which combines 4 webcameras to get one 360 panoramas, a "HyperOmniVision" camera, which is made of a hyperbolic mirror used for mobile robots [36], and the "0-360 Panoramic Optic" camera which allows a one click vertical field of view of −62.5 • ≤ φ ≤ 52.5 • . This camera is an example of a so called central catadioptric system, a camera in which mirrors are involved.…”

Section: Spherical Camerasmentioning

confidence: 99%

“…It is not surprising that there is already a large scientific literature dealing with this part of computer vision. [2] Applications of omni-direction vision are in navigation of autonomous vehicles [6], robotics [32,10,4,31,36,37], tracking and motion detection, simultaneous location and mapping [22], site modeling, image sensors for security [15,37] and virtual reality [38]. The most recent addendum to google maps includes 360 degree panorama pictures embedded into the street maps.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Space and camera path reconstruction for omni-directional vision

Knill,

Ramirez-Herran

2007

Preprint

View full text Add to dashboard Cite

In this paper, we address the inverse problem of reconstructing a scene as well as the camera motion from the image sequence taken by an omni-directional camera. Our structure from motion results give sharp conditions under which the reconstruction is unique. For example, if there are three points in general position and three omni-directional cameras in general position, a unique reconstruction is possible up to a similarity. We then look at the reconstruction problem with m cameras and n points, where n and m can be large and the over-determined system is solved by least square methods. The reconstruction is robust and generalizes to the case of a dynamic environment where landmarks can move during the movie capture. Possible applications of the result are computer assisted scene reconstruction, 3D scanning, autonomous robot navigation, medical tomography and city reconstructions.

show abstract

Section: Spherical Camerasmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Space and camera path reconstruction for omni-directional vision

Knill,

Ramirez-Herran

2007

Preprint

View full text Add to dashboard Cite

show abstract

“…However, Joshua Gluckman and Shree K.Nayar [2] show that existing egomotion algorithms that rely on the computation of optical flows can work with omnidirectional vision by using a Jacobian to transform motion from a plane to a sphere. Further methods are also proposed to work directly with omnidirectional vision [3,4].…”

Section: Introductionmentioning

confidence: 99%

Robust and real-time egomotion estimation using a compound omnidirectional sensor

Thanh¹,

Nagahara²,

Sagawa

et al. 2008

2008 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

We propose a new egomotion estimation algorithm for a compound omnidirectional camera. Image features are detected by a conventional feature detector and then quickly classified into near and far features by checking infinity on the omnidirectional image of the compound omnidirectional sensor. Egomotion estimation is performed in two steps: first, rotation is recovered using far features; then translation is estimated from near features using the estimated rotation. RANSAC is used for estimations of both rotation and translation. Experiments in various environments show that our approach is robust and provides good accuracy in real-time for large motions.

show abstract