A general approach for egomotion estimation with omnidirectional images

Vassallo, Raquel Frizera; Santos-Victor, José; Schneebeli, Hans Jorg Andreas

doi:10.1109/omnvis.2002.1044502

Cited by 40 publications

(30 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…On such hemispherical motion field, we know that either the focus of expansion (FOE) or the focus of contraction (FOC) must be visible. Finally, motor information is estimated from the motion field adapting an egomotion algorithm designed for planar projection to spherical projection Vassallo et al (2002a). In previous works, the Jacobian matrix needed to remap image flow vectors was defined according to the system projection model Gluckman & Nayar (1998).…”

Section: Mobile Robots Navigation 568mentioning

confidence: 99%

“…To reproject flow vectors from the image plane to the sphere surface, a general Jacobian matrix J is defined by differentiating the spherical coordinates (X,Ŷ,Ẑ) on the back-projection equation with respect to the image coordinates (x, y) Vassallo et al (2002a). It maps image velocity vectors to the unit sphere surface, transforming a planar flow field to a hemispherical motion field that will help estimate egomotion (see Equation 3 and Figure 6).…”

Section: Mobile Robots Navigation 568mentioning

confidence: 99%

See 1 more Smart Citation

Topological Mapping and Navigation Using a Developmental Learning Approach Based on Imitation through Sensory-Motor Maps

Vassallo¹,

Schneebeli²,

Santos-Victor³

2010

Mobile Robots Navigation

View full text Add to dashboard Cite

Section: Mobile Robots Navigation 568mentioning

confidence: 99%

Section: Mobile Robots Navigation 568mentioning

confidence: 99%

Topological Mapping and Navigation Using a Developmental Learning Approach Based on Imitation through Sensory-Motor Maps

Vassallo¹,

Schneebeli²,

Santos-Victor³

2010

Mobile Robots Navigation

View full text Add to dashboard Cite

“…For example, Vassallo et al [6] estimate ego-motion using a non-central catadioptic imaging system. Since their approach, similar to the original KvD algorithm presented in the next section, is based on linearized equations, it is not suited for estimating large rotations between frames.…”

Section: Introductionmentioning

confidence: 99%

Monocular ego-motion estimation with a compact omnidirectional camera

Stürzl

Burschka

Suppa

2010

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-We present a generalization of the Koenderinkvan Doorn (KvD) algorithm that allows robust monocular localization with large motion between the camera frames for a wide range of optical systems including omnidirectional systems and standard perspective cameras. The KvD algorithm estimates simultaneously ego-motion parameters, i.e. rotation, translation, and object distances in an iterative way. However due to the linearization of the rotational component of optic flow, the original algorithm fails for larger rotations. We present a generalization of the algorithm to arbitrary rotations that is especially suited for omnidirectional cameras where features can be tracked for long sequences. This reduces the need for vector summation of several individual motion estimates that leads to accumulation of odometry errors.The significant improvement in the performance of the proposed generalized algorithm compared to the original KvD implementation is validated using simulated data. The algorithm is also tested in a real-world experiment with ground-truth data obtained from an external tracking system. The experiment was carried out using a novel compact omnidirectional camera that is designed for small aerial vehicles. It consists of an offthe-shelf webcam that is combined with a reflective surface machined into acrylic glass.

show abstract

“…They project the image motion on a spherical surface using Jacobians of transformations to determine egomotion of a moving platform in terms of translation and rotation of the camera. Vassalo et al [41] use the spherical projection to determine the egomotion of a moving platform in terms of translation and rotation of the camera. Ex-periments are performed using robotic platforms in an indoor environment, and the egomotion estimates are compared with those from odometry.…”

Section: Introductionmentioning

confidence: 99%

Motion analysis for event detection and tracking with a mobile omnidirectional camera

Gandhi

Trivedi

2004

Multimedia Systems

View full text Add to dashboard Cite

Abstract.A mobile platform mounted with omnidirectional vision sensor (ODVS) can be used to monitor large areas and detect interesting events such as independently moving persons and vehicles. To avoid false alarms due to extraneous features, the image motion induced by the moving platform should be compensated. This paper describes a formulation and application of parametric egomotion compensation for an ODVS. Omni images give 360• view of surroundings but undergo considerable image distortion. To account for these distortions, the parametric planar motion model is integrated with the transformations into omni image space. Prior knowledge of approximate camera calibration and camera speed is integrated with the estimation process using a Bayesian approach. Iterative, coarse-to-fine, gradient-based estimation is used to correct the motion parameters for vibrations and other inaccuracies in prior knowledge. Experiments with a camera mounted on various types of mobile platforms demonstrate successful detection of moving persons and vehicles.

show abstract

A general approach for egomotion estimation with omnidirectional images

Abstract: Computing a camera's ego-motion from an image sequence is easier to accomplish when a spherical retina is

Cited by 40 publications

References 15 publications

Topological Mapping and Navigation Using a Developmental Learning Approach Based on Imitation through Sensory-Motor Maps

Topological Mapping and Navigation Using a Developmental Learning Approach Based on Imitation through Sensory-Motor Maps

Monocular ego-motion estimation with a compact omnidirectional camera

Motion analysis for event detection and tracking with a mobile omnidirectional camera

Contact Info

Product

Resources

About