Results 1  10
of
45
Determining Optical Flow
 ARTIFICIAL INTELLIGENCE
, 1981
"... Optical flow cannot be computed locally, since only one independent measurement is available from the image sequence at a point, while the flow velocity has two components. A second constraint is needed. A method for finding the optical flow pattern is presented which assumes that the apparent veloc ..."
Abstract

Cited by 1727 (7 self)
 Add to MetaCart
Optical flow cannot be computed locally, since only one independent measurement is available from the image sequence at a point, while the flow velocity has two components. A second constraint is needed. A method for finding the optical flow pattern is presented which assumes that the apparent velocity of the brightness pattern varies smoothly almost everywhere in the image. An iterative implementation is shown which successfully computes the optical flow for a number of synthetic image sequences. The algorithm is robust in that it can handle image sequences that are quantized rather coarsely in space and time. It is also insensitive to quantization of brightness levels and additive noise. Examples are included where the assumption of smoothness is violated at singular points or along lines in the image.
Shapeadapted smoothing in estimation of 3D shape cues from affine distortions of local 2D brightness structure
, 2001
"... This article describes a method for reducing the shape distortions due to scalespace smoothing that arise in the computation of 3D shape cues using operators (derivatives) de ned from scalespace representation. More precisely, we are concerned with a general class of methods for deriving 3D shap ..."
Abstract

Cited by 52 (3 self)
 Add to MetaCart
This article describes a method for reducing the shape distortions due to scalespace smoothing that arise in the computation of 3D shape cues using operators (derivatives) de ned from scalespace representation. More precisely, we are concerned with a general class of methods for deriving 3D shape cues from 2D image data based on the estimation of locally linearized deformations of brightness patterns. This class
Perceptual Completion of Occluded Surfaces
, 1994
"... Researchers in computer vision have primarily studied the problem of visual reconstruction of environmental structure that is plainly visible. In this thesis, the conventional goals of visual reconstruction are generalized to include both visible and occluded forward facing surfaces. This larger f ..."
Abstract

Cited by 31 (5 self)
 Add to MetaCart
Researchers in computer vision have primarily studied the problem of visual reconstruction of environmental structure that is plainly visible. In this thesis, the conventional goals of visual reconstruction are generalized to include both visible and occluded forward facing surfaces. This larger fraction of the environment is termed the anterior surfaces. Because multiple anterior surface neighborhoods project onto a single image neighborhood wherever surfaces overlap, surface neighborhoods and image neighborhoods are not guaranteed to be in onetoone correspondence, as conventional "shapefrom" methods assume. The result is that the topology of threedimensional scene structure can no longer be taken for granted, but must be inferred from evidence...
Entropybased Gaze Planning
 Image and Vision Computing
, 1999
"... This paper describes an algorithm for recognizing known objects in an unstructured environment (e.g. landmarks) from measurements acquired with a single monochrome television camera mounted on a mobile observer. The approach is based on the concept of an entropy map, which is used to guide the mobi ..."
Abstract

Cited by 23 (0 self)
 Add to MetaCart
This paper describes an algorithm for recognizing known objects in an unstructured environment (e.g. landmarks) from measurements acquired with a single monochrome television camera mounted on a mobile observer. The approach is based on the concept of an entropy map, which is used to guide the mobile observer along an optimal trajectory that minimizes the ambiguity of recognition as well as the amount of data that must be gathered. Recognition itself is based on the optical flow signatures that result from the camera motion  signatures that are inherently ambiguous due to the confounding of motion, structure and imaging parameters. We show how gaze planning partially alleviates this problem by generating trajectories that maximize discriminability. A sequential Bayes approach is used to handle the remaining ambiguity by accumulating evidence for different object hypotheses over time until a clear assertion can be made. Results from an experimental recognition system using a gantrymounted television camera are presented to show the effectiveness of the algorithm on a large class of common objects. 1
A contribution to visionbased autonomous helicopter flight in urban environments
 Robotics and Autonomous Systems
, 2005
"... A navigation strategy that exploits the optic flow and inertial information to continuously avoid collisions with both lateral and frontal obstacles has been used to control a simulated helicopter flying autonomously in a textured urban environment. Experimental results demonstrate that the correspo ..."
Abstract

Cited by 23 (3 self)
 Add to MetaCart
A navigation strategy that exploits the optic flow and inertial information to continuously avoid collisions with both lateral and frontal obstacles has been used to control a simulated helicopter flying autonomously in a textured urban environment. Experimental results demonstrate that the corresponding controller generates cautious behavior, whereby the helicopter tends to stay in the middle of narrow corridors, while its forward velocity is automatically reduced when the obstacle density increases. When confronted with a frontal obstacle, the controller is also able to generate a tight Uturn that ensures the UAV’s survival. The paper provides comparisons with related work, and discusses the applicability of the approach to real platforms. Key words: Helicopter, optic flow, obstacleavoidance, urban environment Airborne devices are specific platforms whose control raises distinctive difficulties as compared to ground robots. For instance, they can hardly rely upon usual sensors to navigate, especially if the challenge is to let them move in an urban environment – because infrared sensors are sensitive to external light
Extracting Structure from Optical Flow Using the Fast Error Search Technique
 International Journal of Computer Vision
, 1998
"... In this paper, we present a robust and computationally efficient technique for estimating the focus of expansion (FOE) of an optical flow field, using fast partial search. For each candidate location on a discrete sampling of the image area, we generate a linear system of equations for determining ..."
Abstract

Cited by 21 (0 self)
 Add to MetaCart
In this paper, we present a robust and computationally efficient technique for estimating the focus of expansion (FOE) of an optical flow field, using fast partial search. For each candidate location on a discrete sampling of the image area, we generate a linear system of equations for determining the remaining unknowns, viz. rotation and inverse depth. We compute the least squares error of the system without actually solving the equations, to generate an error surface that describes the goodness of fit across the hypotheses. Using Fourier techniques, we prove that given an N \Theta N flow field, the FOE can be estimated in O(N 2 log N) operations. Since the resulting system is linear, bounded perturbations in the data lead to bounded errors. We support the theoretical development and proof of our algorithm with experiments on synthetic and real data. Through a series of experiments on synthetic data, we prove the correctness, robustness and operating envelope of our algorithm. We d...
Deformed lattice detection in realworld images using meanshift belief propagation
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 2009
"... Abstract—We propose a novel and robust computational framework for automatic detection of deformed 2D wallpaper patterns in realworld images. The theory of 2D crystallographic groups provides a sound and natural correspondence between the underlying lattice of a deformed wallpaper pattern and a deg ..."
Abstract

Cited by 17 (0 self)
 Add to MetaCart
Abstract—We propose a novel and robust computational framework for automatic detection of deformed 2D wallpaper patterns in realworld images. The theory of 2D crystallographic groups provides a sound and natural correspondence between the underlying lattice of a deformed wallpaper pattern and a degree4 graphical model. We start the discovery process with unsupervised clustering of interest points and voting for consistent lattice unit proposals. The proposed lattice basis vectors and pattern element contribute to the pairwise compatibility and joint compatibility (observation model) functions in a Markov Random Field (MRF). Thus, we formulate the 2D lattice detection as a spatial, multitarget tracking problem, solved within an MRF framework using a novel and efficient MeanShift Belief Propagation (MSBP) method. Iterative detection and growth of the deformed lattice are interleaved with regularized thinplate spline (TPS) warping, which rectifies the current deformed lattice into a regular one to ensure stability of the MRF model in the next round of lattice recovery. We provide quantitative comparisons of our proposed method with existing algorithms on a diverse set of 261 realworld photos to demonstrate significant advances in accuracy and speed over the state of the art in automatic discovery of regularity in real images. Index Terms—Belief propagation, MRF, mean shift, lattice detection, wallpaper patterns. Ç
Sensor Planning for 3D Object Search
, 1996
"... The task of sensor planning for object search is formulated and a strategy for this task is proposed. The searcher is assumed to be a mobile platform equipped with an active camera and a method of calculating depth, like a stereo or laser range finder. The formulation casts sensor planning as an opt ..."
Abstract

Cited by 16 (2 self)
 Add to MetaCart
The task of sensor planning for object search is formulated and a strategy for this task is proposed. The searcher is assumed to be a mobile platform equipped with an active camera and a method of calculating depth, like a stereo or laser range finder. The formulation casts sensor planning as an optimization problem: the goal is to maximize the probability of detecting the target with minimum cost. The search region is thus characterized by the probability distribution of the presence of the target. The control of the sensing parameters depends on the current state of the search region and the detecting abilities of the recognition algorithm. In order to efficiently determine the sensing actions over time, the huge space of possible actions is reduced to a finite set of actions that must be considered. The result of each sensing operation is used to update the status of the search space.
Visuoinertial stabilization in spacevariant binocular systems
, 2000
"... Stabilization of gaze is a major functional prerequisite for robots exploring the environment. The main reason for a “steadyimage” requirement is to prevent the robot’s own motion to compromise its “visual functions”. In this paper we present an artificial system, the LIRA robot head, capable of co ..."
Abstract

Cited by 15 (4 self)
 Add to MetaCart
Stabilization of gaze is a major functional prerequisite for robots exploring the environment. The main reason for a “steadyimage” requirement is to prevent the robot’s own motion to compromise its “visual functions”. In this paper we present an artificial system, the LIRA robot head, capable of controlling its cameras/eyes to stabilize gaze. The system features a stabilization mechanism relying on principles exploited by natural systems: an inertial sensory apparatus and images of spacevariant resolution. The inertial device measures angular velocities and linear acceleration along the vertical and horizontal frontoparallel axes. The spacevariant image geometry facilitates realtime computation of optic flow and the extraction of firstorder motion parameters. Experiments which describe the performance of the LIRA robot head are presented. The results show that the stabilization mechanism improves the reactivity of the system to changes occurring suddenly at new spotted locations.