Abstract not found

This paper describes a new motion estimation algorithm which is potentially useful for both computer vision and video compression applications. It is hierarchical in structure, using a separable 2-d Discrete Wavelet Transform (DWT) on each frame to efficiently construct a multiresolution pyramid of subimages. The DWT is based on a complex-valued pair of 4-tap FIR filters with Gabor-like characteristics. The resulting Complex DWT (CDWT) effectively implements an analysis by an ensemble of Gabor-like filters with a variety of orientations and scales. The phase difference between the subband coefficients of each frame at a given subpel bears a predictable relation to a local translation in the region of the reference frame subtended by that subpel. That relation is used to estimate the displacement field at the coarsest scale of the multiresolution pyramid. Each estimate is accompanied by a directional confidence measure in the form of the parameters of a quadratic matching surface. The i...

Abstract—We aim at developing autonomous microflyers capable of navigating within houses or small indoor environments using vision as the principal source of information. Due to severe weight and energy constraints, inspiration is taken from the fly for the selection of sensors, for signal processing, and for the control strategy. The current 30-g prototype is capable of autonomous steering in a IT IT m textured environment. This paper describes models and algorithms which allow for efficient course stabilization and collision avoidance using optic flow and inertial information. Index Terms—Collision avoidance, indoor flying robot, optic flow (OF), steering control. I.

The purpose of this report 1 is to define optic flow for scalar and density images without using a priori knowledge other than its defining conservation principle, and to incorporate measurement duality, notably the scale-space paradigm. It is argued that the design of optic flow based applications may benefit from a manifest separation between factual image structure on the one hand, and goal-specific details and hypotheses about image flow formation on the other. The approach is based on a physical symmetry principle known as gauge invariance. Data-independent models can be incorporated by means of admissible gauge conditions, each of which may single out a distinct solution, but all of which must be compatible with the evidence supported by the image data. The theory is illustrated by examples and verified by simulations, and performance is compared to several techniques reported in the literature. 1 Introduction The conventional "spacetime" representation of a movie as...

Abstract—This paper focuses on the representation and view generation of three-dimensional (3-D) scenes. In contrast to existing methods that construct a full 3-D model or those that exploit geometric invariants, our representation consists of dense depth maps at several preselected viewpoints from an image sequence. Furthermore, instead of using multiple calibrated stationary cameras or range scanners, we derive our depth maps from image sequences captured by an uncalibrated camera with only approximately known motion. We propose an adaptive matching algorithm that assigns various confidence levels to different regions in the depth maps. Nonuniform bicubic spline interpolation is then used to fill in low confidence regions in the depth maps. Once the depth maps are computed at preselected viewpoints, the intensity and depth at these locations are used to reconstruct arbitrary views of the 3-D scene. Specifically, the depth maps are regarded as vertices of a deformable 2-D mesh, which are transformed in 3-D, projected to 2-D, and rendered to generate the desired view. Experimental results are presented to verify our approach. I.

Image displacement fields---optical flow fields, stereo disparity fields, normal flow fields---due to rigid motion possess a global geometric structure which is independent of the scene in view. Motion vectors of certain lengths and directions are constrained to lie on the imaging surface at particular loci whose location and form depends solely on the 3D motion parameters. If optical flow fields or stereo disparity fields are considered, then equal vectors are shown to lie on conic sections. Similarly, for normal motion fields, equal vectors lie within regions whose boundaries also constitute conics. By studying various properties of these curves and regions and their relationships, a characterization of the structure of rigid motion fields is given. The goal of this paper is to introduce a concept underlying the global structure of image displacement fields. This concept gives rise to various constraints that could form the basis of algorithms for the recovery of visual information f...

This paper describes a self-organizing neural network architecture that transforms optic flow information into representations of heading, scene depth, and moving object locations. These representations are used to reactively navigate in simulations involving obstacle avoidance and pursuit of a moving target. The network's weights are trained during an action-perception cycle in which self-generated eye and body movements produce optic flow information, thus allowing the network to tune itself without requiring explicit knowledge of sensor geometry. The confounding effect of eye movement during translation is suppressed by learning the relationship between eye movement outflow commands and the optic flow signals that they induce. The remaining optic flow field is due only to observer translation and independent motion of objects in the scene. A self-organizing feature map categorizes normalized translational flow patterns, thereby creating a map of cells that code heading directions. H...

ers' performance when compared to that of a nonmoving observer receiving similar optic information. Other studies have found that selfmotion helps to resolve discrete symmetries in optic flow [8, 9], or to decrease integration times in SfM [10]. In the first experiment we tested extraretinal contributions to the extraction of depth from motion by means of a cue-conflict paradigm, in which motion parallax cues to 3D structure were weighed against conflicting linear perspective (i.e., the assumption that lines nearly parallel or perpendicular in the image are actually parallel or perpendicular in 3D space). The observer saw a planar 3D grid in motion, and provided an estimate of its `tilt' (i.e., the direction of its normal relative to the frontoparallel plane [11]). Motion parallax could be actively produced or passively observed. In the active case, parallax was due to the observer's head movements around a virtual object; in the passive case, the observer remained still while watchin

Studies of image motion typically address motion categories on a case-by-case basis. Examples include a moving point, a moving contour, or a 2D optical flow field. The typical assumption made in these studies is that there is a unique velocity at each moving point in the image. In this paper we relax this assumption. We introduce a broader set of motion categories in which the set of motions at a moving point can be 0-D, 1-D, or 2-D. We consider one new motion category in detail, which we call optical snow. This motion category occurs, for example, when an observer translates relative to a massively cluttered scene. Examples include the motion seen by an observer moving through bushes, or falling snow seen by a stationary observer. Optical snow is characterized by a 1-D set of velocities at each moving point and, as such, it cannot be analyzed using a classical computational method such as optical flow. We introduce a technique for analyzing optical snow which is based on a bow tie signature of the motion in the frequency domain. We demonstrate the effectiveness of the technique using both synthetic and real image sequences.

This paper describes a novel method to measure the differential invariants of the image velocity field from the integral of normal image velocities around image contours. This is equivalent to measuring the temporal changes in the area of a closed contour. This avoids having to recover a dense image velocity field and taking partial derivatives. It also does not require point or line correspondences. Moreover integration provides some immunity to image measurement noise. It is shown