Pietro Perona

Camera Calibration from Points and Lines in Dual-Space Geometry (2007)

This paper describes the dual space formalism and its direct application to camera calibration using planar rigs. The same formalism was previously introduced in the context of another application...

Motion from Points, Lines and P-Lines on N views (2007)

Camera calibration is essential to many computer vision applications. Most existing calibration algorithms in the literature consist of estimating both intrinsic and extrinsic camera parameters...

What Do Planar Shadows Tell Us About Scene Geometry? (2007)

We study the problem of 3D motion analysis based on points and lines correspondence across any number of images. An intuitive geometric approach is provided, leading to precise algebraic relations....

Jean-yves Bouguet, Markus Weber, Pietro Perona

This paper presents a method for reconstructing 3D scene geometry from a set of projected shadows. It is composed of two stages. First, the scene geometry is retrieved up to three scalar unknowns...

Method for recovering 3D surface shape based on grayscale structured lighting (2007)

Recursive 3D Visual Motion Estimation Using Subspace Constraints (2007)

Introduction The recovery of 3D structure of surfaces finds many industrial applications. There exist different methods for recovery: either based on mechanical systems, or purely based on images...

[EEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL 12 NO 7. JULY 1990 Scale-Space and Edge Detection Using Diffusion (2007)

The problem of estimating rigid motion from projections may be characterized using a nonlinear dynamical system, composed of the rigid motion constraint and the perspective map. The time derivative...

Pietro Perona, Jitendra Malik

Abstract--The scale-space technique introduced by Witkin involves generating coarser resolution images by convolving the original image with a Gaussian kernel. This approach has a major drawback: it...

PRIMITIVES FOR HUMAN MOTION: A DYNAMICAL APPROACH (2007)

Domitilla Del, Vecchio Richard, M. Murray, Pietro Perona

Abstract: Using tools from dynamical systems theory and systems identification theory we develop the study of primitives for human motion which we refer to as movemes. We introduce basic definitions...

Vision and Pattern Recogn., 1999, To appear. (2007)

Brian Curless, Marc Levoy, Jean-yves Bouguet, Pietro Perona

[83] G.P. Stein, "Accurate internal camera calibration using rotation, with analysis of sources of error, " in Proc. 5 th

A New Geometrical Interpretation of Trilinear Constraints (2007)

Xiaolin Feng, Jean-yves Bouguet, Pietro Perona

We give a new geometrical interpretation of the well-known algebraic trilinear constraints used in motion analysis from three views observation. We show that those algebraic equations correspond to...

Motion from "X " by Compensating "Y" (2007)

Measuring and Predicting Importance of Objects in Our Visual World (2007)

A unified framework for motion estimation from image sequences by compensating for the image-motion of a point, a line or a plane

Spain, Merrielle, Perona, Pietro

Associating keywords with images automatically is an approachable and useful goal for visual recognition researchers. Keywords are distinctive and informative objects. We argue that keywords need to...

Caltech-256 Object Category Dataset (2007)

Griffin, Gregory, Holub, Alex, Perona, Pietro

We introduce a challenging set of 256 object categories containing a total of 30607 images. The original Caltech-101 [1] was collected by choosing a set of object categories, downloading examples...

What do we perceive in a glance of a real-world scene? (2007)

Li, Fei Fei, Iyer, Asha, Koch, Christof, Perona, Pietro

What do we see when we glance at a natural scene and how does it change as the glance becomes longer? We asked naive subjects to report in a free-form format what they saw when looking at briefly...

The pyramid match kernel: Efficient learning with sets of features (2007)

Kristen Grauman, Trevor Darrell, Pietro Perona

In numerous domains it is useful to represent a single example by the set of the local features or parts that comprise it. However, this representation poses a challenge to many conventional machine...

Graph-based visual saliency (2007)

Jonathan Harel, Christof Koch, Pietro Perona

A new bottom-up visual saliency model, Graph-Based Visual Saliency (GBVS), is proposed. It consists of two steps: rst forming activation maps on certain feature channels, and then normalizing them in...

One-shot learning of object categories (2006)

Li, Fei-Fei, Fergus, Rob, Perona, Pietro

Learning visual models of object categories notoriously requires hundreds or thousands of training examples. We show that it is possible to learn much information about a category from just one, or a...

Learning to predict slip for ground robots (2006)

Angelova, Anelia, Matthies, Larry, Helmick, Daniel, Sibley, Gabe, Perona, Pietro

In this paper we predict the amount of slip an exploration rover would experience using stereo imagery by learning from previous examples of traversing similar terrain. To do that, the information of...

A sparse object category model for efficient learning and complete recognition (2006)

Fergus, Robert, Perona, Pietro, Zisserman, Andrew

We present a 'parts and structure' model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from example images containing category...

One-shot learning of object categories (2006)

Li Fei-fei, Rob Fergus, Student Member, Pietro Perona

Abstract—Learning visual models of object categories notoriously requires hundreds or thousands of training examples. We show that it is possible to learn much information about a category from...

A Hierarchy of Support Vector Machines for Pattern Detection (2006)

Hichem Sahbi, Donald Geman, Pietro Perona

We introduce a computational design for pattern detection based on a tree-structured network of support vector machines (SVMs). An SVM is associated with each cell in a recursive partitioning of the...

Multi-View Image Compositions (2005)

Zelnik-Manor, Lihi, Perona, Pietro

The geometry of single-viewpoint panoramas is well understood: multiple pictures taken from the same viewpoint may be stitched together into a consistent panorama mosaic. By contrast, when the point...

Learning object categories from Google's image search (2005)

Fergus, Robert, Fei-Fei, Li, Perona, Pietro, Zisserman, Andrew

Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can learn an object...

Pruning training sets for learning of object categories (2005)

Angelova, Anelia, Abu-Mostafa, Yaser S., Perona, Pietro

Training datasets for learning of object categories are often contaminated or imperfect. We explore an approach to automatically identify examples that are noisy or troublesome for learning and...

Beyond pairwise clustering (2005)

Agarwal, Sameer, Lim, Jongwoo, Zelnik-Manor, Lihi, Perona, Pietro, Kriegman, David, Belongie, Serge

We consider the problem of clustering in domains where the affinity relations are not dyadic (pairwise), but rather triadic, tetradic or higher. The problem is an instance of the hypergraph...

A sparse object category model for efficient learning and exhaustive recognition (2005)

Fergus, Robert, Perona, Pietro, Zisserman, Andrew

We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semi-supervised manner: the model is learnt from example images containing category...

A sparse object category model for efficient learning and exhaustive recognition (2005)

Fergus, Robert, Perona, Pietro, Zisserman, Andrew

We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semi-supervised manner: the model is learnt from example images containing category...

Selective visual attention enables learning and recognition of multiple objects in cluttered scenes (2005)

Dirk Walther, Ueli Rutishauser, Christof Koch, Pietro Perona

multiple objects in cluttered scenes

Combining generative models and Fisher kernels for object class recognition (2005)

Alex D. Holub, Max Welling, Pietro Perona

Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and classification have, in principle, superior...

Evaluation of features detectors and descriptors based on 3d objects (2005)

Hybrid Models for Human Motion Recognition (2005)

We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on...

Claudio Fanti, Lihi Zelnik-manor, Pietro Perona

Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the human motion model as...

Pruning training sets for learning of object categories (2005)

Anelia Angelova, Yaser Abu-mostafa, Pietro Perona

Training datasets for learning of object categories are often contaminated or imperfect. We explore an approach to automatically identify examples that are noisy or troublesome for learning and...

Synergistic face detection and pose estimation with energy-based model (2005)

Margarita Osadchy, Yann Le Cun, Matthew L. Miller, Pietro Perona

We describe a novel method for simultaneously detecting faces and estimating their pose in real time. The method employs a convolutional network to map images of faces to points on a lowdimensional...

Beyond pairwise clustering (2005)

Sameer Agarwal, Jongwoo Lim, Lihi Zelnik-manor, Pietro Perona, David Kriegman, Serge Belongie

We consider the problem of clustering in domains where the affinity relations are not dyadic (pairwise), but rather triadic, tetradic or higher. The problem is an instance of the hypergraph...

Evaluation of features detectors and descriptors based on 3d objects (2005)

Beyond pairwise clustering (2005)

We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on...

Sameer Agarwal, Jongwoo Lim, Lihi Zelnik-manor, Pietro Perona, David Kriegman, Serge Belongie

We consider the problem of clustering in domains where the affinity relations are not dyadic (pairwise), but rather triadic, tetradic or higher. The problem is an instance of the hypergraph...

A sparse object category model for efficient learning and exhaustive recognition (2005)

Rob Fergus, Pietro Perona, Andrew Zisserman

We present a “parts and structure ” model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from example images containing...

Evaluation of features detectors and descriptors based on 3d objects (2005)

Sampling methods for unsupervised learning (2004)

We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on...

Fergus, Robert, Zisserman, Andrew, Perona, Pietro

We present an algorithm to overcome the local maxima problem in estimating the parameters of mixture models. It combines existing approaches from both EM and a robust tting algorithm, RANSAC, to give...

Knowledge Discovery in Large Image Databases: Dealing with Uncertainties in Ground Truth (2004)

Smyth, Padhraic, Burl, Michael C., Fayyad, Usama M., Perona, Pietro

This paper discusses the problem of knowledge discovery in image databases with particular focus on the issues which arise when absolute ground truth is not available.

Volcano Detection Without Ground Truth (2004)

Smyth, Padhraic, Fayyad, Usama, Burl, Michael, Perona, Pietro

Mutual boosting for contextual inference (2004)

Michael Fink, Pietro Perona

Mutual Boosting is a method aimed at incorporating contextual information to augment object detection. When multiple detectors of objects and parts are trained in parallel using AdaBoost [1], object...

Mutual boosting for contextual inference (2004)

Michael Fink, Pietro Perona

Mutual Boosting is a method aimed at incorporating contextual information to augment object detection. When multiple detectors of objects and parts are trained in parallel using AdaBoost [1], object...

Recognition by probabilistic hypothesis construction (2004)

Pierre Moreels, Michael Maire, Pietro Perona

Abstract. We present a probabilistic framework for recognizing objects in images of cluttered scenes. Hundreds of objects may be considered and searched in parallel. Each object is learned from a...

Self-tuning spectral clustering (2004)

Lihi Zelnik-manor, Pietro Perona

We study a number of open issues in spectral clustering: (i) Selecting the appropriate scale of analysis, (ii) Handling multi-scale data, (iii) Clustering with irregular background clutter, and, (iv)...

Common-Frame Model for Object Recognition (2004)

On the usefulness of attention for object recognition (2004)

A generative probabilistic model for objects in images is presented. An object consists of a constellation of features. Feature appearance and pose are modeled probabilistically. Scene images are...

Dirk Walther, Ueli Rutishauser, Christof Koch, Pietro Perona

Today’s object recognition systems have become very good at learning and recognizing isolated objects or objects in images with little clutter. However, unsupervised learning and recognition in...

Is bottom-up attention useful for object recognition (2004)

Ueli Rutishauser, Dirk Walther, Christof Koch, Pietro Perona

A key problem in learning multiple objects from unlabeled images is that it is a priori impossible to tell which part of the image corresponds to each individual object, and which part is irrelevant...

Unsupervised learning of human motion (2003)

Song, Yang, Goncalves, Luis, Perona, Pietro

An unsupervised learning algorithm that can obtain a probabilistic model of an object composed of a collection of parts (a moving human body in our examples) automatically from unlabeled training...

Visual identification by signature tracking (2003)

Munich, Mario E., Perona, Pietro

We propose a new camera-based biometric: visual signature identification. We discuss the importance of the parameterization of the signatures in order to achieve good classification results,...

The Full Images for Natural Knowledge Caltech Office DB (2003)

Fink, Michael, Perona, Pietro

We describe the image collection and labeling procedures of an office scene database. The office database is aimed at providing training and benchmarking tools for multiclass object detection in...

Visual identification by signature tracking (2003)

Unsupervised learning of human motion (2003)

Abstract—We propose a new camera-based biometric: visual signature identification. We discuss the importance of the parameterization of the signatures in order to achieve good classification...

Unsupervised Learning of Human Motion (2003)

Abstract—An unsupervised learning algorithm that can obtain a probabilistic model of an object composed of a collection of parts (a moving human body in our examples) automatically from unlabeled...

Yang Song Member, Yang Song, Luis Goncalves, Pietro Perona

An unsupervised learning algorithm that can obtain a probabilistic model of an object composed of a collection of parts (a moving human body in our examples) automatically from unlabeled training...

Unsupervised Learning of Human Motion Models (2003)

An Improved Scheme for Detection and (2003)

This paper presents an unsupervised learning algorithm that can derive the probabilistic dependence structure of parts of an object (a moving human body in our examples) automatically from unlabeled...

Labelling In Johansson, Claudio Fanti, Marzia Polito, Pietro Perona

Consider a number of moving points, where each point is attached to a joint of the human body and projected onto an image plane.

A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories (2003)

Li Fei-fei, Rob Fergus, Pietro Perona

Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires models containing...

Rapid natural scene categorization in the near absence of attent (2002)

Li, Fei Fei, VanRullen, Rufin, Koch, Christof, Perona, Pietro

What can we see when we do not pay attention? It is well known that we can be "blind" even to major aspects of natural scenes when we attend elsewhere. The only tasks that do not need attention...

Visual input for pen-based computers (2002)

Munich, Mario E., Perona, Pietro

The design and implementation of a camera-based, human-computer interface for acquisition of handwriting is presented. The camera focuses on a standard sheet of paper and images a common pen; the...

Martial Hebert, co-Chair (2002)

Shyjan Mahamud, Takeo Kanade, Jianbo Shi, Pietro Perona

ONR N00014-00-1-0915.

Grouping and Dimensionality reduction by Locally Linear Embedding (2002)

Marzia Polito, Pietro Perona

Locally Linear Embedding (LLE) is an elegant nonlinear dimensionality-reduction technique recently introduced by Roweis and Saul [2]. It fails when the data is divided into separate groups. We study...

Martial Hebert, co-Chair (2002)

Shyjan Mahamud, Takeo Kanade, Jianbo Shi, Pietro Perona

search, discrimination.

Unsupervised Learning of Human Motion Models (2001)

Unsupervised Learning of Human Motion Models (2001)

This paper presents an unsupervised learning algorithm that can derive the probabilistic dependence structure of parts of an object (a moving human body in our examples) automatically from unlabeled...

Bayesian Reasoning on Qualitative Descriptions from Images and Speech (2000)

This paper presents an unsupervised learning algorithm that can derive the probabilistic dependence structure of parts of an object (a moving human body in our examples) automatically from unlabeled...

Gudrun Socher, Gerhard Sagerer, Pietro Perona

Image understanding denotes not only the ability to extract specific, non-numerical information from images, but it implies also reasoning about the extracted information. We propose a qualitative...

Towards Detection of Human Motion (2000)

Yang Song Xiaolin, Yang Song, Xiaolin Feng, Pietro Perona

Detecting humans in images is a useful application of computer vision. Loose and textured clothing, occlusion and scene clutter make it a difficult problem because bottom-up segmentation and grouping...

Monocular Perception of Biological Motion - Clutter and Partial Occlusion (2000)

Monocular Perception Of Biological Motion - Clutter And Partial Occlusion (2000)

The problem of detecting and labeling a moving human body viewed monocularly in a cluttered scene is considered. The task is to decide whether or not one or more people are in the scene (detection),...

Image recognition: Visual grouping, recognition, and learning (1999)

The problem of detecting and labeling a moving human body viewed monocularly in a cluttered scene is considered. The task is to decide whether or not one or more people are in the scene (detection),...

Buhmann, Joachim M., Malik, Jitendra, Perona, Pietro

Vision extracts useful information from images. Reconstructing the three-dimensional structure of our environment and recognizing the objects that populate it are among the most important functions...

Continuous Dynamic Time Warping for translation-invariant curve alignment with applications to signature verification (1999)

Visual Signature Verification using Affine Arc-length (1999)

The problem of establishing correspondence and measuring the similarity of a pair of planar curves arises in many applications in computer vision and pattern recognition. This paper presents a new...

Monocular Perception of Biological Motion - Detection and Labeling (1999)

Signatures can be acquired with a camera-based system with enough resolution to perform verification. This paper presents the performance of a visual-acquisition signature verification system,...

Yang Song Luis, Yang Song, Luis Goncalves, Enrico Di Bernardo, Pietro Perona

Computer perception of biological motion is key to developing convenient and powerful human-computer interfaces. Successful body tracking algorithms have been developed; however, initialization is...

3D photography using shadows in dual-space geometry (1999)

Continuous Dynamic Time Warping for translation-invariant curve alignment with applications to signature verification (1999)

A simple and inexpensive approach for extracting the threedimensional shape of objects is presented. It is based on `weak structured lighting;' and requires very little hardware besides the...

Reducing “Structure from Motion”: a general framework for dynamic vision. 2. Implementation and experimental assessment (1998)

The problem of establishing correspondence and measuring the similarity of a pair of planar curves arises in many applications in computer vision and pattern recognition. This paper presents a new...

Reducing “Structure from Motion”: a general framework for dynamic vision. 1. Modeling (1998)

For pt.1 see ibid., p.933-42 (1998). A number of methods have been proposed in the literature for estimating scene-structure and ego-motion from a sequence of images using dynamical models. Despite...

Efficient deformable filter banks (1998)

The literature on recursive estimation of structure and motion from monocular image sequences comprises a large number of apparently unrelated models and estimation techniques. We propose a framework...

Manduchi, Roberto, Perona, Pietro, Shy, Doug

This article describes efficient schemes for the computation of a large number of differently scaled/oriented filtered versions of an image. We generalize the well-known steerable/scalable...

Orientation diffusions (1998)

Perona, Pietro

Diffusions are useful for image processing and computer vision because they provide a convenient way of smoothing noisy data, analyzing images at multiple scales, and enhancing discontinuities. A...

Reducing "Structure From Motion": a General Framework for Dynamic Vision -- Part 2: Experimental Evaluation (1998)

Real time motion detection system and scene segmentation (1998)

A number of methods have been proposed in the literature for estimating scenestructure and ego-motion from a sequence of images using dynamical models. Despite the fact that all methods may be...

Xiaolin Feng, Pietro Perona

We address two issues in this report. One is the real time implementation of feature tracking and motion estimation. As a fundamental problem in vision field, feature tracking needs to be implemented...

Reducing "structure from motion" 1: modeling. submitted to the (1998)

Probabilistic Affine Invariants for Recognition (1998)

The literature on recursive estimation of structure and motion from monocular image sequences comprises a large number of different models and estimation techniques. We propose a framework that...

Thomas K. Leung, Michael C. Burl, Pietro Perona

Under a weak perspective camera model, the image plane coordinates in different views of a planar object are related by an affine transformation. Because of this property, researchers have attempted...

Learning to Recognize Volcanoes on Venus (1998)

Michael C. Burl, Lars Asker, Padhraic Smyth, Usama Fayyad, Pietro Perona, Larry Crumpler

. Dramatic improvements in sensor and image acquisition technology have created a demand for automated tools that can aid in the analysis of large image databases. We describe the development of...

A Probabilistic Approach to Object Recognition Using Local Photometry and Global Geometry (1998)

Michael C. Burl, Markus Weber, Pietro Perona

. Many object classes, including human faces, can be modeled as a set of characteristic parts arranged in a variable spatial configuration. We introduce a simplified model of a deformable object...

Probabilistic Affine Invariants for Recognition (1998)

Thomas Leung Michael, Michael C. Burl, Pietro Perona

Under a weak perspective camera model, the image plane coordinates in different views of a planar object are related by an affine transformation. Because of this property, researchers have attempted...

Camera-based ID Verification by Signature Tracking (1998)

Reducing "Structure From Motion": a General Framework for Dynamic Vision Part 1: Modeling (1998)

. A number of vision-based biometric techniques have been proposed in the past for personal identification. We present a novel one based on visual capturing of signatures. This paper describes a...

A Probabilistic Approach to Object Recognition Using Local Photometry and Global Geometry (1998)

The literature on recursive estimation of structure and motion from monocular image sequences comprises a large number of apparently unrelated models and estimation techniques. We propose a framework...

Michael C. Burl, Markus Weber, Pietro Perona

. Many object classes, including human faces, can be modeled as a set of characteristic parts arranged in a variable spatial configuration. We introduce a simplified model of a deformable object...

Probabilistic Affine Invariants for Recognition (1998)

Thomas Leung, Michael C. Burl, Pietro Perona

Under a weak perspective camera model, the image plane coordinates in different views of a planar object are related by an affine transformation. Because of this property, researchers have attempted...

Efficient Deformable Filter Banks (1998)

Roberto Manduchi Pietro, Roberto M, Pietro Perona, Doug Shy

This correspondence describes efficient schemes for the computation of a large number of differently scaled/oriented filtered versions of an image. We generalize the well-known steerable/scalable...

Reducing "Structure From Motion": a General Framework for Dynamic Vision Part 2: Implementation and Experimental Assessment (1998)

3D Photography Using Shadows (1998)

A number of methods have been proposed in the literature for estimating scenestructure and ego-motion from a sequence of images using dynamical models. Despite the fact that all methods may be...

3D photography on your desk (1998)

A simple and inexpensive approach for extracting the threedimensional shape of objects is presented. It is based on `weak structured lighting;' and requires little hardware besides the camera: a...

Efficient Deformable Filter Banks (1998)

A simple and inexpensive approach for extracting the three-dimensional shape of objects is presented. It is based on `weak structured lighting'; it differs from other conventional structured...

Roberto Manduchi, Roberto M, Pietro Perona, Doug Shy

This paper describes efficient schemes for the computation of a large number of differentely scaled/oriented filtered versions of an image. We generalize the well-known steerable/scalable...

3D photography on your desk (1998)

3D photography on your desk (1998)

A simple and inexpensive approach for extracting the threedimensional shape of objects is presented. It is based on `weak structured lighting'; it differs from other conventional structured...

Jean-Yves Bouguet, Pietro Perona, Pietro Perona Yz

A simple and inexpensive approach for extracting the threedimensional shape of objects is presented. It is based on `weak structured lighting'; it di#ers from other conventional structured...

Reducing "structure from motion" 1: modeling. submitted to the (1998)

Stefano Soatto, Stefano Soatto, Pietro Perona, Pietro Perona

A number of methods have been proposed in the literature for estimating scene-structure and ego-motion from a sequence of images using dynamical models. Although all methods may be derived from a...

A probabilistic approach to object recognition using local photometry and global geometry (1998)

Michael C. Burl, Markus Weber, Pietro Perona

Abstract. Many object classes, including human faces, can be modeled as a set of characteristic parts arranged in a variable spatial con guration. We introduce a simpli ed model of a deformable...

Reducing "structure from motion" 1: modeling. submitted to the (1998)

Stefano Soatto, Stefano Soatto, Pietro Perona, Pietro Perona

The literature on recursive estimation of structure and motion from monocular im-age sequences comprises a large number of different models and estimation techniques. We propose a framework that...

Feature Detection and Tracking (1997)

Pietro Perona, Ee/cns Pietro Perona

1.8> denotes the smallest singular value. In practical implementations the partial derivatives will be approximated by first difference operators and the integral by a finite sum. The expression...

Efficient Implementation of Deformable Filter Banks (1997)

Roberto Manduchi, Roberto M, Doug Shy, Pietro Perona

This paper describes efficient schemes for the computation of a large number of differentely scaled/oriented filtered versions of an image. We generalize the well-known steerable/scalable...

Efficient Implementation of Deformable Filter Banks (1997)

Roberto Manduchi, Roberto M, Pietro Perona, Doug Shy

This paper describes efficient schemes for the computation of a large number of multiscale/multioriented filtered versions of an image. We generalize the well-known steerable/scalable...

Scale-space properties of quadratic feature detectors (1996)

Kube, Paul, Perona, Pietro

We consider the scale-space properties of quadratic feature detectors and, in particular, investigate whether, like linear detectors, they permit a scale selection scheme with the “causality...

Monocular tracking of the human arm in 3D: real-time implementation and experiments (1996)

Di Bernardo, Enrico, Goncalves, Luis, Perona, Pietro

We have developed a system capable of tracking a human arm in 3D and in real time. The system is based on a previously developed algorithm for 3D tracking which requires only a monocular view and no...

Motion estimation via dynamic vision (1996)

Reducing "Structure From Motion": a General Framework for Dynamic Vision - Part 1: Modeling (1996)

Estimating the three-dimensional motion of an object from a sequence of projections is of paramount importance in a variety of applications in control and robotics, such as autonomous navigation,...

Reducing "Structure From Motion": a General Framework for Dynamic Vision - Part 2: Experimental Evaluation (1996)

The literature on recursive estimation of structure and motion from monocular image sequences comprises a large number of different models and estimation techniques. We propose a framework that...

Visual Input for Pen-Based Computers (1996)

A number of methods have been proposed in the literature for estimating scene-structure and ego-motion from a sequence of images using dynamical models. Although all methods may be derived from a...

Monocular Tracking of the Human Arm in 3D: Real-Time Implementation and Experiments (1996)

Handwriting may be captured using a video camera, rather than the customary pressure-sensitive tablet. This paper presents a simple system based on correlation and recursive prediction methods that...

Enrico Di Bernardo, Luis Goncalves, Pietro Perona

We have developed a system capable of tracking a human arm in 3D and in real time. The system is based on a previously developed algorithm for 3D tracking which requires only a monocular view and no...

Least-squares Multirate FIR Filters (1996)

Roberto Manduchi, Pietro Perona

The authors propose a new least--squares design procedure for multirate FIR filters with any desired shape of the (band--limited) frequency response. The aliasing, inherent in such systems, is...

Scale-space Properties of Quadratic Feature Detectors (1996)

Paul Kube, Pietro Perona

Feature detectors using a quadratic nonlinearity in the filtering stage are known to have some advantages over linear detectors; here we consider how their scale-space properties compare. In...

Deformable kernels for early vision (1995)

Perona, Pietro

Early vision algorithms often have a first stage of linear-filtering that `extracts' from the image information at multiple scales of resolution and multiple orientations. A common difficulty in the...

Depth from Brightness of Moving Images (1995)

Motion from "X" by Compensating "Y" (1995)

In this note we describe a method for recursively estimating the depth of a scene from a sequence of images. The input to the estimator are brightness values at a number of locations of a grid in a...

Motion from Fixations (1995)

This paper analyzes the geometry of the visual motion estimation problem in relation to transformations of the input (images) that stabilize particular output functions such as the motion of a point,...

Motion from fixation (1995)

We study the problem of estimating rigid motion from a sequence of monocular perspective images obtained by navigating around an object while fixating a particular feature point. The motivation comes...

Pyramidal Implementation Of Deformable Kernels (1995)

We study the problem of estimating rigid motion from a sequence of monocular perspective images obtained by navigating around an object while fixating a particular feature point. The motivation comes...

Roberto Manduchi, Pietro Perona

In computer vision and, increasingly, in rendering and image processing, it is useful to filter images with continuous rotated and scaled families of filters. For practical implementations, one can...

Visual Navigation Using a Single Camera (1995)

Jean-Yves Bouguet, Pietro Perona

We assess the usefulness of monocular recursive motion estimation techniques for vehicle navigation in the absence of a model for the environment. For this purpose we extend a recently proposed...

Monocular tracking of the human arm in 3D (1995)

Luis Goncalves, Enrico Di Bernardo, Enrico Ursella, Pietro Perona

We address the problem of estimating the position and motion of a human arm in 3D without any constraints on its behavior and without the use of special markers. We model the arm as two truncated...

Depth from Brightness of Moving Images (1995)

Deformable kernels for early vision (1995)

In this note we describe a method for recursively estimating the depth of a scene from a sequence of images. The input to the estimator are brightness values at a number of locations of a grid in a...

Pietro Perona

perona @ verona. caltech. edu Early vision algorithms often have a first stage of linear-filtering that 'extracts ' from the image information at multiple scales of resolution and multiple...

Motion from "X " by Compensating CCY,, * (1995)

Stefano Soatto, Pietro Perona, Stefano Soatto, Pietro Perona

Motion from "X " by Compensating CCY,, * A unified framework for motion estimation from image sequences by compensating for the image-motion of a point, a line or a plane

X-Y separable pyramid steerable scalable kernels (1994)

Shy, Douglas, Perona, Pietro

A new method for generating X-Y separable, steerable, scalable approximations of filter kernels is proposed which is based on a generalization of the singular value decomposition (SVD) to three...

On the Exact Linearization of Structure From Motion (1994)

Observability/Identifiability of Rigid Motion under Perspective Projection (1994)

The estimation of structure from motion has been a central task of computational vision over the last decade. As it is very well known, the problem is nonlinear due to the perspective nature of the...

Robust and Efficient Recovery of Rigid Motion from Subspace Constraints Solved using Recursive Identification of Nonlinear Implicit Systems (1994)

The "visual motion" problem consists of estimating the motion of an object viewed under projection. In this paper we address the feasibility of such a problem. We will show that the model which...

Dynamic Estimation of Rigid Motion from Perspective Views via Recursive Identification of Exterior Differential Systems with Parameters on a Topological Manifold (1994)

The problem of estimating rigid motion from projections may be characterized using a nonlinear dynamical system, composed of the rigid motion transformation and the perspective map. The time...

Recursive Estimation of Camera Motion from Uncalibrated Image Sequences (1994)

We formulate the problem of estimating the motion of a rigid object viewed under perspective projection as the identification of a dynamic model in Exterior Differential form with parameters on a...

Three Dimensional Transparent Structure Segmentation and Multiple 3D Motion Estimation from Monocular Perspective Image Sequences (1994)

In This memo we present an extension of the motion estimation scheme presented in a previous CDS technical report [14, 16], in order to deal with image sequences coming from an uncalibrated camera....

On the exact linearization of structure from motion (1994)

A three dimensional scene can be segmented using different cues, such as boundaries, texture, motion, discontinuities of the optical flow, stereo, models for structure etc. We investigate...

Recursive Estimation Of Camera Motion From Uncalibrated Image Sequences (1994)

The estimation of structure from motion has been a central task of computational vision over the last decade. As it is very well known, the problem is nonlinear due to the perspective nature of the...

Motion Estimation on the Essential Manifold (1994)

We describe a method for estimating the motion and structure of a scene from a sequence of images taken with a camera whose geometric calibration parameters are unknown. The scheme is based upon a...

Stefano Soatto, Ruggero Frezza, Pietro Perona

. We introduce a novel perspective for viewing the "ego-motion reconstruction" problem as the estimation of the state of a dynamical system having an implicit measurement constraint and...

Dynamic Visual Motion Estimation From Subspace Constraints (1994)

Three dimensional transparent structure segmentation and multiple 3D motion estimation from monocular perspective image sequences (1994)

The problem of estimating rigid motion from projections may be characterized using a nonlinear dynamical system, composed of the rigid motion constraint and the perspective map. The time derivative...

Motion Estimation via Dynamic Vision (1994)

A three dimensional scene can be segmented using different cues, such as boundaries, texture, motion, discontinuities of the optical flow, stereo, models for structure etc. . We investigate...

Stefano Soatto, Pietro Perona, Ruggero Frezza, Giorgio Picci

Estimating the three dimensional motion of an object from a sequence of projections is of paramount importance in a variety of applications in control and robotics, such as autonomous navigation,...

Motion Estimation via Dynamic Vision (1994)

Stefano Soatto, Ruggero Frezza, Pietro Perona

Estimating the three-dimensional motion of an object from a sequence of projections is of paramount importance in a variety of applications in control and robotics, such as autonomous navigation,...

Recursive estimation of camera motion from uncalibrated image sequences (1994)

Stefano Soatto, Ruggero Frezza, Pietro Perona, Stefano Soattot, Ruggero Frezzat, Pietro Peronatt

In This memo we present an extension of the motion estimation scheme presented in a previous CDS technical report [14, 161, in order to deal with image sequences coming from an uncalibrated camera....

Observability /IdentifiabiIity of Rigid Motion under Perspective Projection (1994)

Stefano Soatto, Pietro Perona, Stefano Soatto, Pietro Perona

exterior differential systems, differential algebraic equations The "visual motion " problem consists of estimating the motion of an object viewed under projection. In this paper we...

Dynamic estimation of rigid motion from perspective views via recursive identification of exterior differential systems with parameters on a topological manifold (1994)

Stefano Soatto, Ruggero Frezza, Pietro Perona, Stefano Soattot, Ruggero Frezzat, Pietro Peronaft, ...

We formulate the problem of estimating the motion of a rigid object viewed under perspective projection as the identification of a dynamic model in Exterior Differential form with parameters on a...

Recursive Motion Estimation on the Essential Manifold (1993)