Home | Login
Lectures       Previous announcements
Select year: 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018
Seminars in 2006
    The second chapter (“Scale normalization of derivatives of natural images”) of Ph.D. thesis which was written by Kim S. Pedersen will be presented. The chapter is based on journal paper: Kim S. Pedersen and Mads Nielsen. The Hausdorff Dimension and Scale-Space Normalisation of Natural Images. In Journal of Visual Communication and Image Representation, 11(2):266-277, 2000. Abstract Fractal Brownian motions have been introduced as a statistical descriptor of natural images. We analyze the Gaussian scale-space scaling of derivatives of fractal images. On the basis of this analysis we propose a method for estimation of the fractal dimension of images and scale-space normalization used in conjunction with automatic scale selection assuming either constant energy over scale or self-similar energy scaling.
    I'll present a paper " A Mobile Vision System for Urban detection with information local descriptors" wrote by Gerald Fritz, Christin Seifert, and Lucas Paletta. It was persented in ICVS(International Conference on Computer Visiton Systems) in 2006. The authors had applied Informative Feature Approach on SIFT key detector (called i-SIFT) for recognizing buildings taken by a mobile phone. The attached file is the original paper.
    On this weekend, I'll present "Finding Object Categories in Cluttered Images Using Minimal Shape Prototypes", based on matching prototypical object shapes to gray-level images. This paper was presented in Image Analysis, 13th Scandinavian Conference, SCIA 2003, Halmstad, Sweden, June 29 - July 2, 2003, Proceedings. Lecture Notes in Computer Science 2749 Springer 2003. The author is Johan Thureson and Stefan Carlsson in Royal Institute of Technology. If you need more information. please read full paper on attached file. Sincerely Dennis
    Seminar on the fundamental camera calibration through reviewing the textbook of three-dimensional Vision.
    On this weekend, I'll present "Adaptive Background Generation for Video Object Segmentation" decribing background generation using median filter.

    This paper was presented in 2'nd International Symposium on Visual Computing, Nov, 6, 2006 > which is one of the interesting symposium because if a paper will be accepted, it'll be published by Springer-Verlag in the Lecture Notes in Computer Science (LNCS) series.

    The author is Taekyung Kim in Univ. of Chung-Ang.

    If you need more info. please read abstract on attached file.

    At this Saturday I would like to present paper, Pedestrian Detection for Driver Assistance Using MultiresolutionI nfrared Vision, The author is Massimo Bertozzi,Associate Member,IEEE,Alberto Broggi,Associate Member,IEEE,Alessandra Fascioli,Member,IEEE,Thorsten Graf,and Marc-Michael Meinecke. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, VOL. 53, NO. 6, NOVEMBER 2004

    Abstract This paper describes a system for pedestrian detection in infrared images, which has been implemented on an experimental vehicle equipped with an infrared camera.The proposed system has been tested in many situations and has proven to be efficient and with a very low false-positive rate.It is based on a multiresolution localization of warm symmetrical objects with specific size and aspect ratio; anyway, because road infrastructures and other road participants may also have such characteristics,a set of matched filters is included in order to reduce false detections. A final validation process, based on human shape’s morphological characteristics,is used to build the list of pedestrian appearing in the scene. Neither temporal correlation nor motion cues are used in this first part of the project: the processing is based on the analysis of single frames only.
News | About us | Research | Lectures