Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

Computer Vision, IET

Issue 4 • Date July 2012

Filter Results

Displaying Results 1 - 10 of 10
  • Face colour synthesis using partial least squares and the luminance-/alpha/-β colour transform

    Publication Year: 2012 , Page(s): 263 - 272
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1274 KB)  

    For many tasks, it is necessary to synthesise realistic colour in faces from greyscale values. This is the problem the authors address in this study. Rather than propagating colour information in some regions of the image or transferring colour from an image source to a greyscale using some corresponding criterion, as many colouring systems attempt to do, they seek to synthesise facial colour information using a database of examples. This methodology is divided into two main stages. In the first stage the facial skin tone is predicted through the multiple linear regression method known as partial least squares. This regression allows to define a linear transformation between facial greyscale and colour subspaces. The second stage involves the luminance-α-β (Lαβ) colour transform which is responsible for the recovery of the fine facial detail. The core of the proposed methodology is the combination of statistical subspace analysis with the appropriate colour transform so as to produce realistic facial colourisation results in a direct manner. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Three-dimensional curve reconstruction from multiple images

    Publication Year: 2012 , Page(s): 273 - 284
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1098 KB)  

    In this study, the authors propose a new approach for reconstructing three-dimensional (3D) curves from multiple 2D images taken by uncalibrated cameras. The method is point based and does not require parameterisation of 2D or 3D curves. 2D curves are detected on multiple views as sequences of sampled points along the curves. A curve in 3D space is reconstructed as a sequence of 3D points sampled along the curve that minimise the geometric distances from their projections to the measured 2D curves on different images (i.e. 2D reprojection error). The minimisation problem is solved by an iterative algorithm which is guaranteed to converge to a (local) minimum of the 2D reprojection error. Without requiring calibrated cameras or additional point features, their method can reconstruct multiple 3D curves simultaneously from multiple images and it readily handles images with missing and/or partially occluded curves. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vision-based hand pose estimation through similarity search using the earth mover's distance

    Publication Year: 2012 , Page(s): 285 - 295
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (888 KB)  

    Vision-based hand pose estimation presents unique challenges, particularly if high-fidelity reconstruction is desired. Searching large databases of synthetic pose candidates for items similar to the input offers an attractive means of attaining this goal. The earth mover's distance is a perceptually meaningful measure of dissimilarity that has shown great promise in content-based image retrieval. It is in general, however, a computationally expensive operation and must be used sparingly. The authors investigate a way of economising on its use while preserving much of its accuracy when applied naively in the context of searching for hand pose candidates in large synthetic databases. In particular, a two-tier search method is proposed which achieves similar accuracy with a speed increase of two orders of magnitude. The system performance is evaluated using real input and the results obtained using the different approaches are compared. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Crowded pedestrian counting at bus stops from perspective transformations of foreground areas

    Publication Year: 2012 , Page(s): 296 - 305
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (728 KB)  

    Automated bus fleet scheduling and dispatch require an accurate measurements of current passenger demand. This study presents an effective holistic approach for estimating the number of people waiting at regular open bus stops by means of image processing. This is a non-trivial problem because of several varying conditions that complicate the detection process, such as illumination, crowdedness and different people poses, to name a few. The proposed method estimates the pedestrian count using measurements of foreground areas corrected by perspective. Four approaches are evaluated to find the best mapping between the area measurements and the people count. These mappings include two parametric (standard linear regression model, linear discriminant analysis) and two non-parametric (probabilistic neural network, k-nearest neighbours) approaches. This study also evaluates the performance of the algorithm when thermal and panoramic catadioptric cameras are used instead of standard perspective colour cameras. The proposed method is shown to yield better pedestrian count estimates than those obtained using milestone detectors, and requires model fitting procedures than can be easily implemented without requiring very large datasets for proper classifier training. The approach can also be employed to count people in other public spaces, such as buildings and crosswalks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stereo matching based on nonlinear diffusion with disparity-dependent support weights

    Publication Year: 2012 , Page(s): 306 - 313
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (731 KB)  

    In stereo matching, computing matching cost or similarity between pixels across different images is one of the main steps to get reliable results. More accurate and robust matching cost can be obtained by aggregating per-pixel raw matching cost within the predefined support area. Here, it is very important to aggregate only valid supports from neighbouring pixels. However, unfortunately, it is hard to evaluate the validity of the supports from neighbours beforehand. To resolve this problem, we propose a new method for the matching cost computation based on the nonlinear diffusion. The proposed method helps to aggregate truly valid supports from neighbouring pixels and does not require any local stopping criterion of iteration. This is achieved by using disparity-dependent support weights that are also updated at every iteration. As a result, the proposed method combined with a simple winner-take-all disparity selection method yields good results not only in homogeneous areas but also in depth discontinuity areas as the iteration goes on without the critical degradation of performance. In addition, when combined with global methods for the disparity selection, the proposed method truly improve the matching performance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Four-point-algorithm for the recovery of the pose of a one-dimensional camera with unknown focal length

    Publication Year: 2012 , Page(s): 314 - 323
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (332 KB)  

    The authors give an algorithm for recovering the centre and view direction of a one-dimensional camera with known principal point but unknown focal distance, by means of one view with four recognised landmarks. The involved algebra is reduced to solving a quadratic equation. This 4-point-method appears to be more robust than the existing 5-point-algorithm for locating a totally uncalibrated camera by means of chasles conics. On the other hand, the authors' method can offer an alternative for the triangulation method if the value of the focal length is unknown or unreliable (e.g. because of autozoom). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distributed RANSAC for the robust estimation of three-dimensional reconstruction

    Publication Year: 2012 , Page(s): 324 - 333
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (756 KB)  

    Many low- or middle-level three-dimensional reconstruction algorithms involve a robust estimation and selection step whereby parameters of the best model are estimated and inliers fitting this model are selected. The RANSAC (RANdom SAmple consensus) algorithm is the most widely used robust algorithm for this task. A new version of RANSAC, called distributed RANSAC (D-RANSAC), is proposed, to save computation time and improve accuracy. The authors compare their results with those of classical RANSAC and randomised RANSAC (R-RANSAC). Experiments show that D-RANSAC is superior to RANSAC and R-RANSAC in computational complexity and accuracy in most cases, particularly when the inlier proportion is below 65%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrate tool for online analysis and offline mining of people trajectories

    Publication Year: 2012 , Page(s): 334 - 347
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (920 KB)  

    In the past literature, online alarm-based video-surveillance and offline forensic-based data mining systems are often treated separately, even from different scientific communities. However, the founding techniques are almost the same and, despite some examples in commercial systems, the cases on which an integrated approach is followed are limited. For this reason, this study describes an integrated tool capable of putting together these two subsystems in an effective way. Despite its generality, the proposal is here reported in the case of people trajectory analysis, both in real time and offline. Trajectories are modelled based on either their spatial location or their shape, and proper similarity measures are proposed. Special solutions to meet real-time requirements in both cases are also presented and the trade-off between efficiency and efficacy is analysed by comparing when using a statistical model and when not. Examples of results in large datasets acquired in the University campus are reported as preliminary evaluation of the system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semi-supervised manifold learning based on 2-fold weights

    Publication Year: 2012 , Page(s): 348 - 354
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (522 KB)  

    In locally linear embedding framework, a semi-supervised manifold learning method based on 2-fold weights is proposed. The basic idea is not only to preserve intra-class local information in the processing of dimensionality reduction but also to predict the label of a data point according to its neighbours. Different from existing approaches, our method finds the k-nearest neighbours of each point in k-multiplicity minimum spanning trees (MST) instead of the complete Euclidean graph. Two-fold weights are learned. One is the reconstruction weights for finding the embedding. The other is the derivative weights for class label propagation. The experimental results on synthetic and real data, multi-class data sets demonstrate the effectiveness of the proposed approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Three-dimensional reconstruction based on multiple virtual planes by using fusion-based camera network

    Publication Year: 2012 , Page(s): 355 - 369
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1172 KB)  

    A novel approach for three-dimensional (3D) volumetric reconstruction of an object inside a scene is proposed. A camera network is used to observe the scene. Each camera within the network is rigidly coupled with an Inertial Sensor (IS). A virtual camera is defined for each IS-camera couple using the concept of infinite homography, by fusion of inertial and visual information. Using the inertial data and without planar ground assumption, a set of virtual horizontal planes are defined. The intersections of these inertial-based virtual planes with the object are registered using the concept of planar homography. Moreover a method to estimate the translation vectors among virtual cameras is proposed, which just needs the relative heights of two 3D points in the scene with respect to one of the cameras and their correspondences on the image planes. Different experimental results for the proposed 3D reconstruction method are provided on two different types of scenarios. In the first type, a single IS-camera couple is used and placed in different locations around the object. In the second type, the 3D reconstruction of a walking person (dynamic case) is performed where a set of installed cameras in a smart-room is used for the data acquisition. Moreover, a set of experiments are simulated to analyse the accuracy of the translation estimation method. The experimental results show the feasibility and effectiveness of the proposed framework for the purpose of multi-layer data registration and volumetric reconstruction. View full abstract»

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

Aims & Scope

IET Computer Vision seeks original research papers in a wide range of areas of computer vision. The vision of the journal is to publish the highest quality research work that is relevant and topical to the field, but not forgetting those works that aim to introduce new horizons and set the agenda for future avenues of research in Computer Vision.

Full Aims & Scope