By Topic

Computer Vision, IET

Issue 4 • Date December 2009

Filter Results

Displaying Results 1 - 5 of 5
  • Editorial

    Page(s): 175
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (70 KB)  

    This Special Issue contains four papers whose short versions appeared at the Digital Image Computing: Techniques and Applications (DICTA) Conference which took place at the Rydges Lakeside in Canberra from the 1st??3rd December 2008. Since 1991, DICTA has been the main Australian venue for the presentation of advances and research results on digital image computing. From its establishment, DICTA has been a biannual meeting. In 2008, it turned into an annual conference. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust video stabilisation algorithm using feature point selection and delta optical flow

    Page(s): 176 - 188
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1386 KB)  

    In this study, the authors propose a novel video stabilisation algorithm for mobile platforms with moving objects in the scene. The quality of videos obtained from mobile platforms, such as unmanned airborne vehicles, suffers from jitter caused by several factors. In order to remove this undesired jitter, the accurate estimation of global motion is essential. However, it is difficult to estimate global motions accurately from mobile platforms because of increased estimation errors and noises. Additionally, large moving objects in the video scenes contribute to the estimation errors. Currently, only very few motion estimation algorithms have been developed for video scenes collected from mobile platforms, and this study shows that these algorithms fail when there are large moving objects in the scene. In this study, a theoretical proof is provided which demonstrates that the use of delta optical flow can improve the robustness of video stabilisation in the presence of large moving objects in the scene. The authors also propose to use sorted arrays of local motions and the selection of feature points to separate outliers from inliers. The proposed algorithm is tested over six video sequences, collected from one fixed platform, four mobile platforms and one synthetic video, of which three contain large moving objects. Experiments show that our proposed algorithm performs well to all these video sequences. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Conditions for motion-background segmentation using fundamental matrix

    Page(s): 189 - 200
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (809 KB)  

    In common motion segmentation and estimation applications, where the exact nature of objects' motions and the camera parameters are not known a priori, the most general motion model (the fundamental matrix) is applied. Although the estimation of a fundamental matrix and its use for motion segmentation are well understood, the conditions governing the feasibility of segmentation for different types of motions are yet to be discovered. In this work, the authors study the feasibility of separating motions of a 3D object from its static background using the fundamental matrix. The authors theoretically prove that a pure translational motion cannot be separated from its static background and the success of motion-background segmentation depends on the rotational part of the motion. An extensive set of controlled experiments using both synthetic and real images was conducted to validate the theoretical results. In addition, the authors quantified the conditions for successful motion-background segmentation in terms of the minimum required rotation angle. These results are useful for practitioners designing motion segmentation or estimation solutions for computer vision problems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Curvature-based approach for multi-scale feature extraction from 3D meshes and unstructured point clouds

    Page(s): 201 - 212
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (2006 KB)  

    A framework for extracting salient local features from 3D models is presented in this study. In the proposed method, the amount of curvature at a surface point is specified by a positive quantitative measure known as the curvedness. This value is invariant to rigid body transformation such translation and rotation. The curvedness at a surface position is calculated at multiple scales by fitting a manifold to the local neighbourhoods of different sizes. Points corresponding to local maxima and minima of curvedness are selected as suitable features and a confidence measure of each keypoint is also calculated based on the deviation of its curvedness from the neighbouring values. The advantage of this framework is its applicability to both 3D meshes and unstructured point clouds. Experimental results on a different number of models are shown to demonstrate the effectiveness and robustness of our approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Band selection for hyperspectral imagery using affinity propagation

    Page(s): 213 - 222
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (619 KB)  

    Hyperspectral imagery generally contains enormous amounts of data because of hundreds of spectral bands. Band selection is often adopted to reduce computational cost and accelerate knowledge discovery and other tasks such as subsequent classification. An exemplar-based clustering algorithm termed affinity propagation for band selection is proposed. Affinity propagation is derived from factor graph, and operates by initially considering all data points as potential cluster centres (exemplars) and then exchanging messages between data points until a good set of exemplars and clusters emerges. Affinity propagation has been applied to computer vision and bioinformatics, and shown to be much faster than other clustering methods for large data. By combining the information about the discriminative capability of each individual band and the correlation/similarity between bands, the exemplars generated by affine propagation have higher importance and less correlation/similarity. The performance of band selection is evaluated through a pixel image classification task. Experimental results demonstrate that, compared with some popular band selection methods, the bands selected by affinity propagation best characterise the hyperspectral imagery from the pixel classification standpoint. 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