By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 10 • Date Oct. 2008

Filter Results

Displaying Results 1 - 20 of 20
  • [Front cover]

    Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (152 KB)  
    Freely Available from IEEE
  • [Inside front cover]

    Page(s): c2
    Save to Project icon | Request Permissions | PDF file iconPDF (80 KB)  
    Freely Available from IEEE
  • Guest Editors' Introduction to the Special Section on CVPR Papers

    Page(s): 1681 - 1682
    Save to Project icon | Request Permissions | PDF file iconPDF (78 KB)  
    Freely Available from IEEE
  • Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles

    Page(s): 1683 - 1698
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3538 KB) |  | HTML iconHTML  

    We present a novel approach for multi-object tracking which considers object detection and spacetime trajectory estimation as a coupled optimization problem. Our approach is formulated in a minimum description length hypothesis selection framework, which allows our system to recover from mismatches and temporarily lost tracks. Building upon a state-of-the-art object detector, it performs multiview/multicategory object recognition to detect cars and pedestrians in the input images. The 2D object detections are checked for their consistency with (automatically estimated) scene geometry and are converted to 3D observations which are accumulated in a world coordinate frame. A subsequent trajectory estimation module analyzes the resulting 3D observations to find physically plausible spacetime trajectories. Tracking is achieved by performing model selection after every frame. At each time instant, our approach searches for the globally optimal set of spacetime trajectories which provides the best explanation for the current image and for all evidence collected so far while satisfying the constraints that no two objects may occupy the same physical space nor explain the same image pixels at any point in time. Successful trajectory hypotheses are then fed back to guide object detection in future frames. The optimization procedure is kept efficient through incremental computation and conservative hypothesis pruning. We evaluate our approach on several challenging video sequences and demonstrate its performance on both a surveillance-type scenario and a scenario where the input videos are taken from inside a moving vehicle passing through crowded city areas. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spectral Matting

    Page(s): 1699 - 1712
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3129 KB) |  | HTML iconHTML  

    We present spectral matting: a new approach to natural image matting that automatically computes a basis set of fuzzy matting components from the smallest eigenvectors of a suitably defined Laplacian matrix. Thus, our approach extends spectral segmentation techniques, whose goal is to extract hard segments, to the extraction of soft matting components. These components may then be used as building blocks to easily construct semantically meaningful foreground mattes, either in an unsupervised fashion, or based on a small amount of user input. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pedestrian Detection via Classification on Riemannian Manifolds

    Page(s): 1713 - 1727
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3586 KB) |  | HTML iconHTML  

    We present a new algorithm to detect pedestrian in still images utilizing covariance matrices as object descriptors. Since the descriptors do not form a vector space, well known machine learning techniques are not well suited to learn the classifiers. The space of d-dimensional nonsingular covariance matrices can be represented as a connected Riemannian manifold. The main contribution of the paper is a novel approach for classifying points lying on a connected Riemannian manifold using the geometry of the space. The algorithm is tested on INRIA and DaimlerChrysler pedestrian datasets where superior detection rates are observed over the previous approaches. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Life Spans

    Page(s): 1728 - 1740
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4566 KB) |  | HTML iconHTML  

    Tracking object in low frame rate video or with abrupt motion poses two main difficulties which most conventional tracking methods can hardly handle: 1) poor motion continuity and increased search space; 2) fast appearance variation of target and more background clutter due to increased search space. In this paper, we address the problem from a view which integrates conventional tracking and detection, and present a temporal probabilistic combination of discriminative observers of different lifespans. Each observer is learned from different ranges of samples, with different subsets of features, to achieve varying level of discriminative power at varying cost. An efficient fusion and temporal inference is then done by a cascade particle filter which consists of multiple stages of importance sampling. Experiments show significantly improved accuracy of the proposed approach in comparison with existing tracking methods, under the condition of low frame rate data and abrupt motion of both target and camera. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Effective Approach for Iris Recognition Using Phase-Based Image Matching

    Page(s): 1741 - 1756
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5414 KB) |  | HTML iconHTML  

    This paper presents an efficient algorithm for iris recognition using phase-based image matching - an image matching technique using phase components in 2D discrete Fourier transforms (DFTs) of given images. Experimental evaluation using the CASIA iris image databases (versions 1.0 and 2.0) and Iris challenge evaluation (ICE) 2005 database clearly demonstrates that the use of phase components of iris images makes it possible to achieve highly accurate iris recognition with a simple matching algorithm. This paper also discusses the major implementation issues of our algorithm. In order to reduce the size of iris data and to prevent the visibility of iris images, we introduce the idea of 2D Fourier phase code (FPC) for representing iris information. The 2D FPC is particularly useful for implementing compact iris recognition devices using state-of-the-art digital signal processing (DSP) technology. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Spatially Variant White-Patch and Gray-World Method for Color Image Enhancement Driven by Local Contrast

    Page(s): 1757 - 1770
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1985 KB) |  | HTML iconHTML  

    Starting from the revolutionary Retinex by Land and McCann, several further perceptually inspired color correction models have been developed with different aims, e.g. reproduction of color sensation, robust features recognition, enhancement of color images. Such models have a differential, spatially-variant and non-linear nature and they can coarsely be distinguished between white-patch (WP) and gray-world (GW) algorithms. In this paper we show that the combination of a pure WP algorithm (RSR: random spray Retinex) and an essentially GW one (ACE) leads to a more robust and better performing model (RACE). The choice of RSR and ACE follows from the recent identification of a unified spatially-variant approach for both algorithms. Mathematically, the originally distinct non-linear and differential mechanisms of RSR and ACE have been fused using the spray technique and local average operations. The investigation of RACE allowed us to put in evidence a common drawback of differential models: corruption of uniform image areas. To overcome this intrinsic defect, we devised a local and global contrast-based and image-driven regulation mechanism that has a general applicability to perceptually inspired color correction algorithms. Tests, comparisons and discussions are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Model Driven Segmentation of Articulating Humans in Laplacian Eigenspace

    Page(s): 1771 - 1785
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2545 KB) |  | HTML iconHTML  

    We propose a general approach using Laplacian Eigenmaps and a graphical model of the human body to segment 3D voxel data of humans into different articulated chains. In the bottom-up stage, the voxels are transformed into a high-dimensional (6D or less) Laplacian Eigenspace (LE) of the voxel neighborhood graph. We show that LE is effective at mapping voxels on long articulated chains to nodes on smooth 1D curves that can be easily discriminated, and prove these properties using representative graphs. We fit 1D splines to voxels belonging to different articulated chains such as the limbs, head and trunk, and determine the boundary between splines using the spline fitting error. A top-down probabilistic approach is then used to register the segmented chains, utilizing their mutual connectivity and individual properties. Our approach enables us to deal with complex poses such as those where the limbs form loops. We use the segmentation results to automatically estimate the human body models. While we use human subjects in our experiments, the method is fairly general and can be applied to voxel-based segmentation of any articulated object composed of long chains. We present results on real and synthetic data that illustrate the usefulness of this approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • In Situ Image Segmentation Using the Convexity of Illumination Distribution of the Light Sources

    Page(s): 1786 - 1799
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2788 KB) |  | HTML iconHTML  

    When separating objects from a background in an image, we often meet difficulties to obtain the precise output due to the unclear edges of the objects as well as the poor or nonuniform illumination. In order to solve this problem, this paper presents an in situ segmentation method which takes advantages of the distribution feature of illumination of light sources, rather than analyzing the image pixels themselves. After analyzing the convexity of illumination distribution (CID) of point and linear light sources, the paper makes use of the CID features to find pixels belonging to the background. Then some background pixels are selected as control points to reconstruct the image background by means of B-spline; finally, by subtracting the reconstructed background from the original image, global thresholding can be employed to make the final segmentation. Quantitative evaluation experiments are made to test the performance of the method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Concurrent Computation of Attribute Filters on Shared Memory Parallel Machines

    Page(s): 1800 - 1813
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1724 KB) |  | HTML iconHTML  

    Morphological attribute filters have not previously been parallelized, mainly because they are both global and non-separable. We propose a parallel algorithm which achieves efficient parallelism for a large class of attribute filters, including attribute openings, closings, thinnings and thickenings, based on Salembier's Max-Trees and Min-trees. The image or volume is first partitioned in multiple slices. We then compute the Max-trees of each slice using any sequential Max-Tree algorithm. Subsequently, the Max-trees of the slices can be merged to obtain the Max-tree of the image. A C-implementation yielded good speed-ups on both a 16-processor MIPS 14000 parallel machine, and a dual-core Opteron-based machine. It is shown that the speed-up of the parallel algorithm is a direct measure of the gain with respect to the sequential algorithm used. Furthermore, the concurrent algorithm shows a speed gain of up to 72% on a single-core processor, due to reduced cache thrashing. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Layered Data Association Using Graph-Theoretic Formulation with Application to Tennis Ball Tracking in Monocular Sequences

    Page(s): 1814 - 1830
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3743 KB) |  | HTML iconHTML  

    In this paper, we propose a multi-layered data association scheme with graph-theoretic formulation for tracking multiple objects that undergo switching dynamics in clutter. The proposed scheme takes as input object candidates detected in each frame. At the object candidate level, "tracklets" are "grown" from sets of candidates that have high probabilities of containing only true positives. At the tracklet level, a directed and weighted graph is constructed, where each node is a tracklet, and the edge weight between two nodes is defined according to the "compatibility'' of the two tracklets. The association problem is then formulated as an all-pairs shortest path (APSP) problem in this graph. Finally, at the path level, by analyzing the all-pairs shortest paths, all object trajectories are identified, and track initiation and track termination are automatically dealt with. By exploiting a special topological property of the graph, we have also developed a more efficient APSP algorithm than the general-purpose ones. The proposed data association scheme is applied to tennis sequences to track tennis balls. Experiments show that it works well on sequences where other data association methods perform poorly or fail completely. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust and Accurate Visual Echo Cancelation in a Full-duplex Projector-Camera System

    Page(s): 1831 - 1840
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2186 KB) |  | HTML iconHTML  

    In this paper we study the problem of "visual echo" in a full-duplex projector-camera system for tele-collaboration applications. Visual echo is defined as the appearance of projected contents observed by the camera. It can potentially saturate the projected contents, similar to audio echo in telephone conversation. Our approach to visual echo cancelation includes an off-line calibration procedure that records the geometric and photometric transfer between the projector and the camera in a look-up table. During run-time, projected contents in the captured video are identified using the calibration information and suppressed, therefore achieving the goal of canceling visual echo. Our approach can accurately handle full color images under arbitrary reflectance of display surfaces and photometric response of the projector or camera. It is robust to geometric registration errors and quantization effect, therefore particularly effective for high-frequency contents such as texts and hand drawings. We demonstrate the effectiveness of our approach with a variety of real images in a full-duplex projector-camera system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimating the Joint Statistics of Images Using Nonparametric Windows with Application to Registration Using Mutual Information

    Page(s): 1841 - 1857
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3776 KB) |  | HTML iconHTML  

    Recently, the Non-Parametric (NP) Windows has been proposed to estimate the statistics of real 1D and 2D signals. NP Windows is accurate, because it is equivalent to sampling images at a high (infinite) resolution for an assumed interpolation model. This paper extends the proposed approach to consider joint distributions of image-pairs. Secondly, Green's Theorem is used to simplify the previous NP Windows algorithm. Finally, a resolution aware NP Windows algorithm is proposed, to improve robustness to relative scaling between an image-pair. Comparative testing of 2D image registration was performed using translation-only and affine transformations. Although more expensive than other methods, NP Windows frequently demonstrated superior performance for bias (distance between ground truth and global maximum) and frequency of convergence. Unlike other methods, the number of samples and histogram bin-size has little effect on NP Windows, and the prior selection of a kernel is not required. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parametric Image Alignment Using Enhanced Correlation Coefficient Maximization

    Page(s): 1858 - 1865
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (864 KB)  

    In this work we propose the use of a modified version of the correlation coefficient as a performance criterion for the image alignment problem. The proposed modification has the desirable characteristic of being invariant with respect to photometric distortions. Since the resulting similarity measure is a nonlinear function of the warp parameters, we develop two iterative schemes for its maximization, one based on the forward additive approach and the second on the inverse compositional method. As it is customary in iterative optimization, in each iteration the nonlinear objective function is approximated by an alternative expression for which the corresponding optimization is simple. In our case we propose an efficient approximation that leads to a closed form solution (per iteration) which is of low computational complexity, the latter property being particularly strong in our inverse version. The proposed schemes are tested against the forward additive Lucas-Kanade and the simultaneous inverse compositional algorithm through simulations. Under noisy conditions and photometric distortions our forward version achieves more accurate alignments and exhibits faster convergence whereas our inverse version has similar performance as the simultaneous inverse compositional algorithm but at a lower computational complexity. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Graph Cuts via $ell_1$ Norm Minimization

    Page(s): 1866 - 1871
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1123 KB) |  | HTML iconHTML  

    Graph cuts have become an increasingly important tool for solving a number of energy minimization problems in computer vision and other fields. In this paper, the graph cut problem is reformulated as an unconstrained l1 norm minimization that can be solved effectively using interior point methods. This reformulation exposes connections between graph cuts and other related continuous optimization problems. Eventually, the problem is reduced to solving a sequence of sparse linear systems involving the Laplacian of the underlying graph. The proposed procedure exploits the structure of these linear systems in a manner that is easily amenable to parallel implementations. Experimental results obtained by applying the procedure to graphs derived from image processing problems are provided. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Erratum to "Adaptive Smoothing via Contextual and Local Discontinuities" [Oct 05 1552-1567]

    Page(s): 1872
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (42 KB)  

    In the above titled paper (ibid., vol 27, no. 10, pp. 1552-1567, Oct 05), equation (9) contained a typographical error. The corrected equation is presented here. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TPAMI Information for authors

    Page(s): c3
    Save to Project icon | Request Permissions | PDF file iconPDF (80 KB)  
    Freely Available from IEEE
  • [Back cover]

    Page(s): c4
    Save to Project icon | Request Permissions | PDF file iconPDF (152 KB)  
    Freely Available from IEEE

Aims & Scope

The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is published monthly. Its editorial board strives to present most important research results in areas within TPAMI's scope.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
David A. Forsyth
University of Illinois