Person:

Yezzi, Anthony

Permanent Link

https://hdl.handle.net/1853/71866

Associated Organization(s)

Organizational Unit

School of Electrical and Computer Engineering

Full item page

Publication Search Results

Now showing 1 - 10 of 74

Space-time reconstruction of oceanic sea states via variational stereo methods

(Georgia Institute of Technology, 2012-06) Gallego, Guillermo ; Yezzi, Anthony ; Fedele, Francesco ; Benetazzo, Alvise

We present a remote sensing observational method for the measurement of the spatio-temporal dynamics of ocean waves. Variational techniques are used to recover a coherent space-time reconstruction of oceanic sea states given stereo video imagery. The stereoscopic reconstruction problem is expressed in a variational optimization framework. There, we design an energy functional whose minimizer is the desired temporal sequence of wave heights. The functional combines photometric observations as well as spatial and temporal regularizers. A nested iterative scheme is devised to numerically solve, via 3-D multigrid methods, the system of partial di erential equations resulting from the optimality condition of the energy functional. The output of our method is the coherent, simultaneous estimation of the wave surface height and radiance at multiple snapshots. We demonstrate our algorithm on real data collected o ffshore. Statistical and spectral analysis are performed. Comparison with respect to an existing sequential method is analyzed.
Wave statistics and space-time extremes via stereo imaging

(Georgia Institute of Technology, 2012-06) Fedele, Francesco ; Benetazzo, Alvise ; Gallego, Guillermo ; Shih, Ping-Chang ; Yezzi, Anthony ; Barbariol, Francesco

We present an analysis of the space-time dynamics of oceanic sea states exploiting stereo imaging techniques. In particular, a novel Wave Acquisition Stereo System (WASS) has been developed and deployed at the oceanographic tower Acqua Alta in the Northern Adriatic Sea, off the Venice coast in Italy. The analysis of WASS video measurements yields accurate estimates of the oceanic sea state dynamics, the associated directional spectra and wave surface statistics that agree well with theoretical models. Finally, we show that a space-time extreme, defined as the expected largest surface wave height over an area, is considerably larger than the maximum crest observed in time at a point, in agreement with theoretical predictions.
Optimization of Foraging Multi-Agent System Front: A Flux-Based Curve Evolution Method

(Georgia Institute of Technology, 2011-12) Haque, Musad A. ; Rahmani, Amir R. ; Egerstedt, Magnus B. ; Yezzi, Anthony

Numerous social foragers form a foraging front that sweeps through the aggregation of prey. Based on this strategy, and using variational arguments, we develop an algorithm to provide a group-level specification of the shape of the sweeping front for a foraging multi-robot system. The presented flux-based algorithm has the desired property of generating more regular shapes than previously introduced algorithms.
Active Geodesics: Region based Active Contour Segmentation with a Global Edge based Constraint

(Georgia Institute of Technology, 2011-11) Appia, Vikram ; Yezzi, Anthony

We present an active geodesic contour model in which we constrain the evolving active contour to be a geodesic with respect to a weighted edge-based energy through its entire evolution rather than just at its final state (as in the traditional geodesic active contour models). Since the contour is always a geodesic throughout the evolution, we automatically get local optimality with respect to an edge fitting criterion. This enables us to construct a purely region-based energy minimization model without having to devise arbitrary weights in the combination of our energy function to balance edge-based terms with the region-based terms. We show that this novel approach of combining edge information as the geodesic constraint in optimizing a purely region-based energy yields a new class of active contours which exhibit both local and global behaviors that are naturally responsive to intuitive types of user interaction. We also show the relationship of this new class of globally constrained active contours with traditional minimal path methods, which seek global minimizers of purely edge-based energies without incorporating region-based criteria. Finally, we present some numerical examples to illustrate the benefits of this approach over traditional active contour models.
Localized Principal Component Analysis based Curve Evolution: A Divide and Conquer Approach

(Georgia Institute of Technology, 2011-11) Appia, Vikram ; Ganapathy, Balaji ; Yezzi, Anthony ; Faber, Tracy

We propose a novel localized principal component analysis (PCA) based curve evolution approach which evolves the segmenting curve semi-locally within various target regions (divisions) in an image and then combines these locally accurate segmentation curves to obtain a global segmentation. The training data for our approach consists of training shapes and associated auxiliary (target) masks. The masks indicate the various regions of the shape exhibiting highly correlated variations locally which may be rather independent of the variations in the distant parts of the global shape. Thus, in a sense, we are clustering the variations exhibited in the training data set. We then use a parametric model to implicitly represent each localized segmentation curve as a combination of the local shape priors obtained by representing the training shapes and the masks as a collection of signed distance functions. We also propose a parametric model to combine the locally evolved segmentation curves into a single hybrid (global) segmentation. Finally, we combine the evolution of these semi-local and global parameters to minimize an objective energy function. The resulting algorithm thus provides a globally accurate solution, which retains the local variations in shape. We present some results to illustrate how our approach performs better than the traditional approach with fully global PCA.
Biologically Motivated Shape Optimization of Foraging Fronts

(Georgia Institute of Technology, 2011-06) Haque, Musad A. ; Rahmani, Amir R. ; Egerstedt, Magnus B. ; Yezzi, Anthony

Social animals often form a predator front to charge through an aggregation of prey. It is observed that the nature of the feeding strategy dictates the geometric shape of these charging fronts. Inspired by this observation, we model foraging multi-robot fronts as a curve moving through a prey density. We optimize the shape of the curve using variational arguments and simulate the results to illustrate the operation of the proposed curve optimization algorithm.
Weak Statistical Constraints for Variational Stereo Imaging of Oceanic Waves

(Georgia Institute of Technology, 2011-06) Gallego, Guillermo ; Yezzi, Anthony ; Fedele, Francesco ; Benetazzo, Alvise

We develop an observational technique for the stereoscopic reconstruction of the wave form of oceanic sea states via a variational stereo method. In the context of active surfaces, the shape and radiance of the wave surface are obtained as minimizers of an energy functional that combines image observations and smoothness priors. To obey the quasi Gaussianity of oceanic waves observed in nature, a given statistical wave law is enforced in the stereo variational framework as a weak constraint. Multigrid methods are then used to solve the partial differential equations derived from the optimality conditions of the augmented energy functional. An application of the developed method to two sets of experimental stereo data is finally presented.
Detection of curves with unknown endpoints using minimal path techniques

(Georgia Institute of Technology, 2010-09) Kaul, Vivek ; Tsai, Yi-Chang James ; Yezzi, Anthony

We present a novel method to detect curves with unknown endpoints using minimal path techniques. Our work builds on the state of the art minimal path techniques currently used to detect curves. Existing algorithms in the literature require the user to specify both endpoints of the curve or one endpoint plus the total length of the curve. However, in our approach, the user may specify any arbitrary initial point on the curve and the algorithm can detect the complete curve (even with multiple branches) automatically without the need for any additional information. We apply this algorithm to the problem of crack detection in civil structures where cracks are modeled as 2D curves. The results demonstrate that the algorithm is robust to variations in background and texture and is able to detect curves accurately.
Curious snakes: an active contour formulation of information-driven minimum-latency boundary detection

(Georgia Institute of Technology, 2010-06) Soatto, Stefano ; Sundaramoorthi, Ganesh ; Yezzi, Anthony

We present a region-based active contour detection algorithm for objects that exhibit relatively homogeneous photometric characteristics (e.g. smooth color or gray levels), embedded in complex background clutter. Current methods either frame this problem in Bayesian classification terms, where precious modeling resources are expended representing the complex background away from decision boundaries, or use heuristics to limit the search to local regions around the object of interest. We propose an adaptive lookout region, whose size depends on the statistics of the data, that are estimated along with the boundary during the detection process. The result is a “curious snake” that explores the outside of the decision boundary only locally to the extent necessary to achieve a good tradeoff between missed detections and narrowest “lookout” region, drawing inspiration from the literature of minimum-latency set-point change detection and robust statistics. This development makes fully automatic detection in complex backgrounds a realistic possibility for active contours, allowing us to exploit their powerful geometric modeling capabilities compared with other approaches used for segmentation of cluttered scenes. To this end, we introduce an automatic initialization method tailored to our model that overcomes one of the primary obstacles in using active contours for fully automatic object detection.
A Regions of Confidence Based Approach to Enhance Segmentation with Shape Priors

(Georgia Institute of Technology, 2010) Appia, Vikram V. ; Ganapathy, Balaji ; Abufadel, Amer Y. ; Yezzi, Anthony ; Faber, Tracy

We propose an improved region based segmentation model with shape priors that uses labels of confidence/interest to exclude the influence of certain regions in the image that may not provide useful information for segmentation. These could be regions in the image which are expected to have weak, missing or corrupt edges or they could be regions in the image which the user is not interested in segmenting, but are part of the object being segmented. In the training datasets, along with the manual segmentations we also generate an auxiliary map indicating these regions of low confidence/interest. Since, all the training images are acquired under similar conditions, we can train our algorithm to estimate these regions as well. Based on this training we will generate a map which indicates the regions in the image that are likely to contain no useful information for segmentation. We then use a parametric model to represent the segmenting curve as a combination of shape priors obtained by representing the training data as a collection of signed distance functions. We evolve an objective energy functional to evolve the global parameters that are used to represent the curve. We vary the influence each pixel has on the evolution of these parameters based on the confidence/interest label. When we use these labels to indicate the regions with low confidence; the regions containing accurate edges will have a dominant role in the evolution of the curve and the segmentation in the low confidence regions will be approximated based on the training data. Since our model evolves global parameters, it improves the segmentation even in the regions with accurate edges. This is because we eliminate the influence of the low confidence regions which may mislead the final segmentation. Similarly when we use the labels to indicate the regions which are not of importance, we will get a better segmentation of the object in the regions we are interested in.