FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1495507103> ?p ?o ?g. }

• W1495507103 abstract "Visual object tracking has been extensively investigated in the last two decades for its attractiveness and profitability. It remains an active area of research because of the lack of a satisfactory holistic tracking system that can deal with intrinsic and extrinsic distortions. Illumination variations, occlusions, noise and errors in object matching and classification are only a fraction of the problems currently encountered in visual object tracking. The work developed in this thesis integrates contextual information in a Bayesian framework for object tracking and abnormal behavior detection; more precisely, it focuses on the intrinsic characteristics of video signals in conjunction with object behavior to improve tracking outcomes. The representation of probability density functions is essential for modeling stochastic variables. In particular, parametric modeling is convenient since it makes possible the efficient storage of the representation and the simulation of the underlying stochastic process. The Gaussian mixture model is employed in this thesis to represent the pixel color distribution for segregation of foreground from background. The model adapts quickly to fast changes in illumination and resolves the problem of ``pixel saturation'' experienced by some existing background subtraction algorithms. The technique leads to better accuracy in the extraction of the foreground for higher-level tasks such as motion estimation. The solution of the Bayesian inference problem for Markov chains and, in particular, the well-known Kalman and particle filters is also investigated. The integration of contextual inference is of paramount importance in the aforementioned estimators; it results in object-specific tracking solutions with improved robustness. The vehicle tracking problem is explored in detail. The projective transformation, imposed by the environment configuration, is integrated into the Kalman and particle filters, which yields the ``projective Kalman filter'' and the ``projective particle filer''. Extensive experimental results are presented, which demonstrate that the projective Kalman and particle filters improve tracking robustness by reducing tracking drift and errors in the estimated trajectory. The constraint on the known nature of the environment is then relaxed to allow general tracking of pedestrians. A mixture of Gaussian Markov random fields is introduced to learn patterns of motion and model contextual information with particle filtering. Such inference results in an increased tracking robustness to occlusions. The local modeling with the Markov random fields also provides inference on abnormal behavior detection. Since local patterns are unveiled by the Markov random field mixture, detecting abnormal behavior is reduced to the matching of an object feature vector to the underlying local distribution, whereas the global approach, introducing generalization errors, involves complex, cumbersome and inaccurate decisions. Experimental evaluation on synthetic and real data show superior results in abnormal behavior detection for driving under the influence of alcohol and pedestrians crossing highways." @default.
• W1495507103 created "2016-06-24" @default.
• W1495507103 creator A5008092547 @default.
• W1495507103 date "2010-07-08" @default.
• W1495507103 modified "2023-09-26" @default.
• W1495507103 title "Contextual bayesian inference for visual object tracking and abnormal behavior detection" @default.
• W1495507103 cites W1494853941 @default.
• W1495507103 cites W1499677203 @default.
• W1495507103 cites W1499877760 @default.
• W1495507103 cites W1502024436 @default.
• W1495507103 cites W1513008779 @default.
• W1495507103 cites W1516558816 @default.
• W1495507103 cites W1538390141 @default.
• W1495507103 cites W154669480 @default.
• W1495507103 cites W1553272164 @default.
• W1495507103 cites W1554663460 @default.
• W1495507103 cites W1564419782 @default.
• W1495507103 cites W1570441711 @default.
• W1495507103 cites W1571866903 @default.
• W1495507103 cites W1572700469 @default.
• W1495507103 cites W1572755383 @default.
• W1495507103 cites W1582808469 @default.
• W1495507103 cites W1586623029 @default.
• W1495507103 cites W1652775531 @default.
• W1495507103 cites W1672056451 @default.
• W1495507103 cites W1836111812 @default.
• W1495507103 cites W1862119688 @default.
• W1495507103 cites W1892329859 @default.
• W1495507103 cites W1961030615 @default.
• W1495507103 cites W1974558763 @default.
• W1495507103 cites W1974999836 @default.
• W1495507103 cites W1975559841 @default.
• W1495507103 cites W1979059554 @default.
• W1495507103 cites W1981685777 @default.
• W1495507103 cites W1988790447 @default.
• W1495507103 cites W1990149295 @default.
• W1495507103 cites W1990360726 @default.
• W1495507103 cites W1992825118 @default.
• W1495507103 cites W1995903777 @default.
• W1495507103 cites W1996714826 @default.
• W1495507103 cites W2000662299 @default.
• W1495507103 cites W2002381192 @default.
• W1495507103 cites W2002465252 @default.
• W1495507103 cites W2006063325 @default.
• W1495507103 cites W2007052055 @default.
• W1495507103 cites W2014984672 @default.
• W1495507103 cites W2019032869 @default.
• W1495507103 cites W2019595010 @default.
• W1495507103 cites W2020934227 @default.
• W1495507103 cites W2022686119 @default.
• W1495507103 cites W2025865186 @default.
• W1495507103 cites W2026140901 @default.
• W1495507103 cites W2029061296 @default.
• W1495507103 cites W2031124702 @default.
• W1495507103 cites W2031254036 @default.
• W1495507103 cites W2040870580 @default.
• W1495507103 cites W2044732953 @default.
• W1495507103 cites W2045516333 @default.
• W1495507103 cites W2049633694 @default.
• W1495507103 cites W2049882758 @default.
• W1495507103 cites W2056672493 @default.
• W1495507103 cites W2057487175 @default.
• W1495507103 cites W2060746984 @default.
• W1495507103 cites W2067191022 @default.
• W1495507103 cites W2068113013 @default.
• W1495507103 cites W2069295011 @default.
• W1495507103 cites W2073105997 @default.
• W1495507103 cites W2078864071 @default.
• W1495507103 cites W2079690285 @default.
• W1495507103 cites W2081171933 @default.
• W1495507103 cites W2085201020 @default.
• W1495507103 cites W2089599467 @default.
• W1495507103 cites W2095345422 @default.
• W1495507103 cites W2095640719 @default.
• W1495507103 cites W2095706930 @default.
• W1495507103 cites W2095905764 @default.
• W1495507103 cites W2095907543 @default.
• W1495507103 cites W2095950780 @default.
• W1495507103 cites W2096578785 @default.
• W1495507103 cites W2097121457 @default.
• W1495507103 cites W2097509141 @default.
• W1495507103 cites W2099097799 @default.
• W1495507103 cites W2100004375 @default.
• W1495507103 cites W2100428290 @default.
• W1495507103 cites W2100435576 @default.
• W1495507103 cites W2101399927 @default.
• W1495507103 cites W2102625004 @default.
• W1495507103 cites W2102959189 @default.
• W1495507103 cites W2103007496 @default.
• W1495507103 cites W2103679841 @default.
• W1495507103 cites W2103876808 @default.
• W1495507103 cites W2104414727 @default.
• W1495507103 cites W2104766217 @default.
• W1495507103 cites W2105238356 @default.
• W1495507103 cites W2105714141 @default.
• W1495507103 cites W2106300334 @default.
• W1495507103 cites W2107401725 @default.
• W1495507103 cites W2107777165 @default.
• W1495507103 cites W2107864516 @default.
• W1495507103 cites W2107990130 @default.

• next