Yazar "Deniz, Umut" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ N/A ]
    Öğe
    Ardışık görüntülerde hareket analizi
    (Hatay Mustafa Kemal Üniversitesi, 2004) Deniz, Umut; Oral, Mustafa
    ÖZET ARDIŞIK GÖRÜNTÜLERDE HAREKET ANALİZİ Hareket analizi, görüntülerin yorumlanması, işlenmesi ve sıkıştırılması gibi uygulama alanlarında kullanılan temel tekniklerden biridir. Bu çalışmada, video kamera cihazından alınan ardışık görüntülerde hareketin analizi için kullanılan 8 ayrı yöntem incelenip uygulanarak, elde edilen sonuçlar tartışılmıştır. Bu yöntemler, Arka Plan Farkı Yöntemleri ve İstatistiksel Yöntemler olmak üzere iki kategoride incelenmiştir. Bu yöntemlere ek olarak yeni bir hareket tespiti metodu, "Ağırlık Merkezi Analizi Yöntemi", bu çalışma ile ilk kez önerilmiş ve sonuçlan karşılaştırmalı olarak tartişılmıştır. Yöntemler için geliştirilen algoritmaların test aşamalarında, değişik ortamlardan alman farklı ışık yoğunluğuna sahip görüntüler kullamlmıştır. Yapılan testlerde, özellikle arka plan farkı yöntemlerinde, algoritmaların ışık yoğunluğu değişimlerine hassas olduğu gözlenmiştir. Işık yoğunluğunun mümkün olduğunca sabit olduğu iç ortamlardan alman görüntülerden, her iki kategorideki yöntemlerden de tatmin edici sonuçlar alınırken; dış ortamlardan alman görüntülerdeki ışık yoğunluğu değişimlerine olan hassasiyeti indirgemek için istatistiksel yaklaşmılarda bulunan ikinci grup yöntemlerin daha başarılı olduğu görülmüştür. Her ne kadar ışık yoğunluğu değişimlerine olan hassasiyet sorunu kısmen çözülmüş olsa da, görüntülerin kontrollü ortamlardan alnıma ihtiyacı devam etmektedir. 2004, 74 sayfa
  • Küçük Resim
    Öğe
    Centre of mass model - A novel approach to background modelling for segmentation of moving objects
    (Elsevier, 2007) Oral, Mustafa; Deniz, Umut
    This paper describes a novel method, centre of mass model, to detect moving objects in a dynamic scene based on background subtraction. Any displacement of the position of centre of mass (CoMs) in two consecutive frames is the indicator of a moving object in a scene. Dividing a scene into subregions and modelling them as individual masses allow segmentation of the moving object(s). In the proposed scheme, an image is divided into blocks that are called super-pixels and each super-pixel is represented with the x and y components of CoM of a block. The segmentation is achieved by taking the absolute difference between CoM of current super-pixel and the mean of CoMs of previous corresponding super-pixels, and thresholding the difference with a dynamically updated value. A comparative work has been carried out to evaluate the performance of the proposed model and the previously reported seven different methods. The model produced consistent outputs for the images taken in different environmental conditions. The moving objects were successfully segmented with no post-processing operations. Centre of mass model demonstrated better overall performance than the methods previously reported. Its output was superior for auto-focused video images. (c) 2007 Published by Elsevier B.V.
  • Küçük Resim
    Öğe
    Motion detection in moving pictures
    (2005) Oral, Mustafa; Deniz, Umut
    Motion analysis is one of the major techniques which is used in applications related with interpretation, processing and compressing digital images. In this thesis, seven different methods that are widely used for the motion detection in a moving picture sequence, were studied and implemented, and their performances were discussed. These methods were investigated under two major headings namely Background Subtraction Methods and Statistical Methods. The performance tests for the methods were carried out for the images that were taken under various illumination conditions. The results showed that the background subtraction methods are very sensitive to sudden illumination changes on a running sequence which is a major drawback. While both of the methods are quite satisfactory for indoor scenes that provide stable illumination conditions, the methods that were studied under secondary group of the statistical methods have been found to be successful for the outdoor scenes that present sudden illumination changes. Although, the pitfalls of the methods resulting sudden illumination changes have been improved, the need for taking the images under a carefully illuminated environment, needs further investigation. © 2005 IEEE.
  • [ N/A ]
    Öğe
    A novel approach for motion segmentation in moving pictures: Centre of Mass Model
    (Ieee, 2007) Oral, Mustafa; Deniz, Umut
    A novel background model for segmentation of moving objects in running images is presented in this paper. The segmentation algorithm is based on the statistics of the current and previous locations of center of mass of super pixels that are the collection of a group of pixels. The algorithm is superior to those previously reported in the literature due to its immunity to sudden illumination changes and slight changes in the intensity distribution functions of the super-pixels. The performance of the Center of Mass Model is compared with previously reported seven different models that were selected from the Background Subtracting Methods and the Statistical Methods.