Electrical - Electronic Engineering / Elektrik - Elektronik Mühendisliği

Permanent URI for this collectionhttps://hdl.handle.net/11147/11

Browse

Filters

2004 - 20087

Settings

End date: 2009Institution Author: search.filters.institutionAuthor.Gümüştekin, Şevket

Search Results

Now showing 1 - 7 of 7
  • Conference Object
    Citation - WoS: 2
    Citation - Scopus: 4
    Tek Kamera ve Aynalar Kullanan Bir Görsel Denetleme Sistemi
    (Institute of Electrical and Electronics Engineers Inc., 2004) Gümüştekin, Şevket
    In this paper the geometrical properties of an imaging system are investigated. This system uses mirrors to simulate additional cameras. The geometry developed here helps us to capture the images of an object from meaningful viewpoint locations. The imaging system with the desired geometry is realized by adjusting the positions and orientations of mirrors. A special calibration pattern is used for the process of camera calibration which finds the unknown camera parameters and gives feedback about the degree of compliance with the desired geometry. The calibrated camera and its mirror images are used to create a 2D image of an object surface with a uniform geometry. After a pre-defined inner or outer surface of a test object is imaged from different view angles using mirrors, these images are warped and blended in a single image which is used for visual inspection. Hence, the vaguely defined process of inspecting 3D objects and their surface textures is converted to an efficient and well defined process of inspecting 2D images.
  • Conference Object
    Citation - Scopus: 1
    Hava Fotoğraflarından Deniz Kıyılarının Belirlenmesi
    (Institute of Electrical and Electronics Engineers Inc., 2006) Kahraman, Metin; Gümüştekin, Şevket
    The unique structures of different coastline segments provide distinctive image features for several applications such as oceanography, georeferencing, cartography and autonomous navigation. In this paper, a procedure involving automatic multiresolution coastline extraction is described. Using this method, sea and land textures are segmented utilizing cooccurrence and histogram features of wavelet image representation. The coastlines are identified as the boundaries of the sea regions.
  • Conference Object
    H264/avc ile Sıkıştırılmış Videoda Sahne Değişimi Kestirimi için Bir Yaklaşım
    (Institute of Electrical and Electronics Engineers Inc., 2007) Şimşek, Gökhan; Gümüştekin, Şevket
    In this paper, we provide methods to detect abrupt and gradual scene changes on ISO/ITU H264/AVC coded video sequence using macro-block type information. The analysis is realized in compressed domain without the need of full decompression to pixel domain. In order to realize the proposed methods, several video test sequences are constructed in QCIF resolution. The syntax and semantics, parsing, decoding processes of ISO/ITU H264/AVC is followed to realize such analysis and proposed methods are realized using reference software. The application addresses emerging standard ISO/ITU H264/AVC coded video databases as low level tools to realize a video summarization, abstraction or segmentation system.
  • Conference Object
    Detection of Urban Change Using Remote Sensing and Gis: Izmir Case
    (Taylor and Francis Ltd., 2008) Tarhan, Çiğdem; Arkon, Cemal; Çelik, M.; Gümüştekin, Şevket; Tecim, V.
    This study is an example of how land use changes could be detected via high resolution remotely sensed data. In order to perform "change detection" IKONOS satellite images, belonging to 2001 and 2004, have been used. An automated Graphical User Interface (GUI) has been created for detection of environment. Different image enhancement techniques and a fuzzy inference system have been combined in the GUI. The detection results are classified according to some basic levels such as 20-50% and 70%. Additionally, four different change detection algorithms have been applied which are pixel-based, object based, feature based. These algorithms have been examined according to change detection levels with different image enhancement techniques. At the end of the study, the results have been compared.
  • Conference Object
    Modifiye Bitüm Görüntülerinde Gabor Öznitelikleri ile Doku Analizi
    (Institute of Electrical and Electronics Engineers Inc., 2008) Gümüştekin, Şevket; Topal, Ali; Şengöz, Burak
    İnşaat sanayinde, özellikle ulaşım uygulamalarının vazgerçilmez bir malzemesi olan bütün, gelişmekte olan malzeme teknolojilerinin de katkısı ile daha dayanıklı ve giivenilir yol ve yapıların yapılabilmesi için öncelikli bir araştırma konusu olmuştur. Çeşitli polimer katkı maddelerinin bitüme eklenmesi standart bir uygulama haline gelmiştir. Yapım sırasında kalite kontrolünün sağlanması ve denetlenmesi için modifiye bitümlerin test edilmesi büyük önem taşımaktadır. Bu çalışmada mekanik yöntemlere alternatif olan yeni bir yöntem sunulmuştur. Gabor öznitelikleri kullanılarak modifiye bitiim gorüntülerinin dokusal özellikleri incelenmiş; bitüme eklenen katkı maddelerinin ve bu maddelerin hangi oranda eklendiğinin algılanmasınzı büyük ölçüde mümkün olduğu gorülmüştür.
  • Conference Object
    Matching Aerial Coastline Images With Map Data Using Dynamic Programming
    (Institute of Electrical and Electronics Engineers Inc., 2006) Kahraman, Metin; Gümüştekin, Şevket
    Matching aerial images with map data is an important task in several remote sensing applications such as autonomous navigation, cartography, oceanography. The unique and distinctive shapes of coastlines can be effectively utilized to solve this problem. In this study a completely automatic scheme is proposed to detect coastlines using multiresolution texture analysis and to match the detected coastlines to a map database. A shape matching method using dynamic programming is used and tested on the satellite images of the western coast of Turkey.
  • Conference Object
    Citation - WoS: 1
    Citation - Scopus: 2
    A Case Study on Logging Visual Activities: Chess Game
    (Springer Verlag, 2006) Ozan, Şükrü; Gümüştekin, Şevket
    Automatically recognizing and analyzing visual activities in complex environments is a challenging and open-ended problem. In this study this task is performed in a chess game scenario where the rules, actions and the environment are well defined. The purpose here is to detect and observe a FIDE (Fédération International des Ėchecs) compatible chess board, generating a log file of the moves made by human players. A series of basic image processing operations have been applied to perform the desired task. The first step of automatically detecting a chess board is followed by locating the positions of the pieces. After the initial setup is established every move made by a player is automatically detected and verified. Intel® Open Source Computer Vision Library (OpenCV) is used in the current software implementation.