This paper presents a new robust global motion estimation method based on pre-analysis of the video content. The novel idea in the proposed method, compared to classical robust statistics-based estimation methods, is to classify the video sequences into 3 classes based on the analysis of scene content before motion estimation. Different motion models and estimation methods are applied to differ...

ÐWe describe a new direct method for estimating structure and motion from image intensities of multiple views. We extend the direct methods of Horn and Weldon [18] to three views. Adding the third view enables us to solve for motion and compute a dense depth map of the scene, directly from image spatio-temporal derivatives in a linear manner without first having to find point correspondences or...

A framework for learning parameterized models of optical flow from image sequences is presented. A class of motions is represented by a set of orthogonal basis flow fields that are computed from a training set using principal component analysis. Many complex image motions can be represented by a linear combination of a small number of these basis flows. The learned motionmodels may be used for ...

The features inherent in the visual motion field of a mobile robot indicate important clues about its navigation and environment. Combining these visual clues with additional inertial sensor information allows reliable detection of navigation direction for a mobile robot and the independent motion which may be present in the scene. The motion field, which is the 2D projection of the 3D scene va...

Optic flow, i.e., retinal image movement resulting from ego-motion, is a crucial source of information used for obstacle avoidance and course control in flying insects. Optic flow analysis may prove promising for mobile robotics although it is currently not among the standard techniques. Insects have developed a computationally cheap analysis mechanism for image motion. Detailed computational m...

Several video coding standards and techniques have been introduced for multimedia applications, particularly the h.26x series processing. These employ motion estimation processing to reduce amount of data that is required store or transmit video. The process an inextricable part as it removes temporal redundancy between successive frames sequences. This paper about these algorithms, their searc...

The cellular neural network is a locally interconnected neural network capable of high-speed computation when implemented in analog VLSI. This work describes a CNN algorithm for estimating the optical flow from an image sequence. The algorithm is based on the spatio-temporal filtering approach to image motion analysis and is shown to estimate the optical flow more accurately than a comparable a...