Scheduled System Maintenance
On Saturday, December 10, single article sales and account management will be unavailable from 5:00 AM-7:30 PM ET.
We apologize for the inconvenience.
By Topic

The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)

7-9 June 2006

Filter Results

Displaying Results 1 - 25 of 85
  • The 3rd Canadian Conference on Computer and Robot Vision - Cover

    Publication Year: 2006, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (208 KB)
    Freely Available from IEEE
  • The 3rd Canadian Conference on Computer and Robot Vision - Title Page

    Publication Year: 2006, Page(s): i
    Request permission for commercial reuse | PDF file iconPDF (33 KB)
    Freely Available from IEEE
  • The 3rd Canadian Conference on Computer and Robot Vision - Copyright Page

    Publication Year: 2006, Page(s): iv
    Request permission for commercial reuse | PDF file iconPDF (33 KB)
    Freely Available from IEEE
  • The 3rd Canadian Conference on Computer and Robot Vision - Table of contents

    Publication Year: 2006, Page(s):v - ix
    Request permission for commercial reuse | PDF file iconPDF (99 KB)
    Freely Available from IEEE
  • Preface

    Publication Year: 2006, Page(s): x
    Request permission for commercial reuse | PDF file iconPDF (78 KB) | HTML iconHTML
    Freely Available from IEEE
  • Invited Talks

    Publication Year: 2006, Page(s): xi
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (29 KB) | HTML iconHTML

    Provides an abstract for each of the invited presentations and a brief professional biography of each presenter. The complete presentations were not made available for publication as part of the conference proceedings. View full abstract»

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

    Publication Year: 2006, Page(s): xiv
    Request permission for commercial reuse | PDF file iconPDF (53 KB)
    Freely Available from IEEE
  • Learning to classify by ongoing feature selection

    Publication Year: 2006, Page(s): 1
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (696 KB) | HTML iconHTML

    Existing classification algorithms use a set of training examples to select classification features, which are then used for all future applications of the classifier. A major problem with this approach is the selection of a training set: a small set will result in reduced performance, and a large set will require extensive training. In addition, class appearance may change over time requiring an ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generic Detection of Multi-Part Objects by High-Level Analysis

    Publication Year: 2006, Page(s): 2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (616 KB) | HTML iconHTML

    A method is proposed to detect multi-part man-made or natural objects in complex images. It consists in first extracting simple curves and straight lines from the edge map. Then, a search tree is expanded by selecting and ordering the segmented primitives on the basis of generic local and global grouping criteria. The set of partial contours provided by the parallel search are combined into more c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Autonomous Learning of Object Appearances using Colour Contour Frames

    Publication Year: 2006, Page(s): 3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1208 KB) | HTML iconHTML

    In this paper we make use of the idea that a robot can autonomously discover objects and learn their appearances by poking and prodding at interesting parts of a scene. In order to make the resultant object recognition ability more robust, and discriminative, we replace earlier used colour histogram features with an invariant texture-patch method. The texture patches are extracted in a similarity ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Local Feature Matching For Face Recognition

    Publication Year: 2006, Page(s): 4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (264 KB) | HTML iconHTML

    In this paper a novel technique for face recognition is proposed. Using the statistical Local Feature Analysis (LFA) method, a set of feature points is extracted for each face image at locations with highest deviations from the expectation. Each feature point is described by a sequence of local histograms captured from the Gabor responses at different frequencies and orientations around the featur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated Detection of Unusual Events on Stairs

    Publication Year: 2006, Page(s): 5
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1840 KB) | HTML iconHTML

    This paper presents a method for automatically detecting and recognising unusual events on stairs from video data. The motivation is to provide a tool for biomedical researchers to rapidly find and analyse the events of interest within large quantities of video data. Our system identifies potential sequences containing anomalies, and reduces the amount of data that needs to be searched by a human.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simultaneous Tracking and Action Recognition using the PCA-HOG Descriptor

    Publication Year: 2006, Page(s): 6
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2336 KB) | HTML iconHTML

    This paper presents a template-based algorithm to track and recognize athlete’s actions in an integrated system using only visual information. Conventional template-based action recognition systems usually consider action recognition and tracking as two independent problems, and solve them separately. In contrast, our algorithm emphasizes that tracking and action recognition can be tightly co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interpreting Camera Operations in the Context of Content-based Video Indexing and Retrieval

    Publication Year: 2006, Page(s): 7
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB) | HTML iconHTML

    In this work, we intend to go one step further to overcome the difficulty that lies in the gap between low-level media features (e.g. colors, texture, motion, etc.) and high-level concepts to perform a reliable content-based indexing and retrieval. More especially, our work proposes a new way to establish a connection between both geometric and radiometric deformations and the characterization of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Toward an Application of Content-Based Video Indexing to Computer- Assisted Descriptive Video

    Publication Year: 2006, Page(s): 8
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1072 KB) | HTML iconHTML

    This paper presents the status of a project targeting the development of content-based video indexing tools, to assist a human in the generation of descriptive video for the hard of seeing people. We describe three main elements: (1) the video content that is pertinent for computer-assisted descriptive video, (2) the system dataflow, based on a light plug-in architecture of an open-source video pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Classification of Outdoor Images by Region Matching

    Publication Year: 2006, Page(s): 9
    Cited by:  Papers (2)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (744 KB) | HTML iconHTML

    This paper presents a novel method for image classification. It differs from previous approaches by computing image similarity based on region matching. Firstly, the images to be classified are segmented into regions or partitioned into regular blocks. Next, low-level features are extracted from each segment or block, and the similarity between two images is computed as the cost of a pairwise matc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A GPU-based Algorithm for Estimating 3D Geometry and Motion in Near Real-time

    Publication Year: 2006, Page(s): 10
    Cited by:  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (760 KB) | HTML iconHTML

    Real-time 3D geometry and motion estimation has many important applications in areas such as robot navigation and dynamic image-based rendering. A novel algorithm is proposed in this paper for estimating 3D geometry and motion of dynamic scenes based on captured stereo sequences. All computations are conducted in the 2D image space of the center view and the results are represented in forms of dis... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using 3D Spline Differentiation to Compute Quantitative Optical Flow

    Publication Year: 2006, Page(s): 11
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (576 KB) | HTML iconHTML

    We show that differentiation via fitting B-splines to the spatio-temporal intensity data comprising an image sequence provides at least the same and usually better 2D Lucas and Kanade optical flow than that computed via Simoncelli’s balanced/matched filters. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust SSD tracking with incremental 3D structure estimation

    Publication Year: 2006, Page(s): 12
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (496 KB) | HTML iconHTML

    While the geometric aspects of structure and motion estimation from uncalibrated images are well understood, and it has great promise in applications, it has not seen widespread use. In this paper we combine SSD tracking with incremental structure computation into a system computing both motion and structure on-line from video. We show how in combination the structure estimation and tracking benef... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Confidence Based updation of Motion Conspicuity in Dynamic Scenes

    Publication Year: 2006, Page(s): 13
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (936 KB) | HTML iconHTML

    Computational models of visual attention result in considerable data compression by eliminating processing on regions likely to be devoid of meaningful content. While saliency maps in static images is indexed on image region (pixels), psychovisual data indicates that in dynamic scenes human attention is object driven and localized motion is a significant determiner of object conspicuity. We have i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reflection Stereo - Novel Monocular Stereo using a Transparent Plate -

    Publication Year: 2006, Page(s): 14
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1280 KB) | HTML iconHTML

    This paper proposes a simple and novel singlecamera depth estimation method using images reflected by a single transparent parallel planar plate. The transparent plate reflects and transmits the incident light on its surface. The transmitted light is then reflected on the rear-surface and is transmitted again to the air through the surface. These two light paths create an overlapped image that com... View full abstract»

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

    Publication Year: 2006, Page(s): 15
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB) | HTML iconHTML

    The Retinex algorithm for lightness and color constancy is extended here to include 3-dimensional spatial information reconstructed from a stereo image. Tests show this modification improves retinex. A key aspect of traditional Retinex is that, within each color channel, it makes local spatial comparisons of intensity. In particular, intensities ratios are computed between neighboring spatial loca... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Photometric Stereo with Nearby Planar Distributed Illuminants

    Publication Year: 2006, Page(s): 16
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB) | HTML iconHTML

    This paper considers the problem of shape-from-shading using nearby planar distributed illuminants. It is shown that a rectangular planar nearby distributed uniform isotropic illuminant shining on a small Lambertian surface patch is equivalent to a single isotropic point light source at infinity. A closed-form solution is given for the equivalent point light source direction in terms of the illumi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sparse Disparity Map from Uncalibrated Infrared Stereo Images

    Publication Year: 2006, Page(s): 17
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1312 KB) | HTML iconHTML

    With the rapid growth in infrared sensor technology and its drastic cost reduction, the potential of application of these imaging technologies in computer vision systems has increased. One potential application for IR imaging is depth from stereo. It has been shown that the quality of uncooled sensors is not sufficient for generating dense depth maps. In this paper we investigate the production of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Photo Hull Regularized Stereo

    Publication Year: 2006, Page(s): 18
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (560 KB) | HTML iconHTML

    A regularization-based approach to 3-D reconstruction from multiple images is proposed. As one of the most widely used multiple-view 3-D reconstruction algorithms, Space Carving can produce a photo hull of a scene, which is at best a coarse volumetric model. The two-view stereo algorithm, on the other hand, can generate a more accurate reconstruction of the surfaces, provided that a given surface ... View full abstract»

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