ABSTRACT: A new mesh-generation scheme for motion compensation is presented and discussed. To start with, spatio-temporal segmentation is applied to an image (and a reference frame) in order to identify the boundaries of moving regions, which are then approximated with poly-gons. A triangular mesh is generated within each poly-gon, thus ensuring that no triangle straddles multiple re-gions. The affine motion parameters are then estimated separately for each triangle, using bi-directional motion estimation. Results for various test sequences demon-strate the advantages offered by the use of a content-based mesh, and by affine motion compensation.
Motion computation in scenes having multiple moving objects is performed together with object segmen...
International audienceMotion segmentation methods are effective for tracking video objects. However,...
A technique for performing progressive mesh-based motion estimation in a layered fashion is presente...
A content-based approach to the design of a triangular mesh is presented, and its application to ane...
Content-based approaches to motion compensation offer the advantage of being able to adapt to the sp...
In most video compression standards today, the generally accepted method for temporal prediction is ...
In object-based video coding systems, the scenes are described in terms of three dimensional objects...
A dual-layer algorithm for mesh-based motion compensation is described. The technique utilises meshe...
Motion compensation using 2-D mesh models requires computation of the parameters of a spatial transf...
[[abstract]]In this paper, we present a new motion estimation method for low bit-rate image sequence...
A structure from motion algorithm is described which recovers structure and camera position, modulo ...
Various computer-vision applications involve estimation of multiple motions from images of dynamic s...
Abstract: Motion estimation and compensation is an essential part of existing video coding systems. ...
In this work, three-dimensional (3-D) motion estimation is applied to the problem of motion compensa...
Interpretation of the three-dimensional (3D) world from two-dimensional (2D) images is a primary goa...
Motion computation in scenes having multiple moving objects is performed together with object segmen...
International audienceMotion segmentation methods are effective for tracking video objects. However,...
A technique for performing progressive mesh-based motion estimation in a layered fashion is presente...
A content-based approach to the design of a triangular mesh is presented, and its application to ane...
Content-based approaches to motion compensation offer the advantage of being able to adapt to the sp...
In most video compression standards today, the generally accepted method for temporal prediction is ...
In object-based video coding systems, the scenes are described in terms of three dimensional objects...
A dual-layer algorithm for mesh-based motion compensation is described. The technique utilises meshe...
Motion compensation using 2-D mesh models requires computation of the parameters of a spatial transf...
[[abstract]]In this paper, we present a new motion estimation method for low bit-rate image sequence...
A structure from motion algorithm is described which recovers structure and camera position, modulo ...
Various computer-vision applications involve estimation of multiple motions from images of dynamic s...
Abstract: Motion estimation and compensation is an essential part of existing video coding systems. ...
In this work, three-dimensional (3-D) motion estimation is applied to the problem of motion compensa...
Interpretation of the three-dimensional (3D) world from two-dimensional (2D) images is a primary goa...
Motion computation in scenes having multiple moving objects is performed together with object segmen...
International audienceMotion segmentation methods are effective for tracking video objects. However,...
A technique for performing progressive mesh-based motion estimation in a layered fashion is presente...