Yüksek Lisans Tezleri

Permanent URI for this communityhttps://hdl.handle.net/20.500.12416/57

Browse

Browsing Yüksek Lisans Tezleri by Subject "2D'den 3D'ye"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • Item
    Citation Count: Isawi, Muthana Yaseen Nawaf (2016). Structure from motion using a single camera / Tek kamera kullanımıyla hareketten yapı oluşturma. Yayımlanmış yüksek lisans tezi. Ankara: Çankaya Üniversitesi, Fen Bilimleri Enstitüsü.
    Structure from motion using a single camera
    (2016) Isawi, Muthana Yaseen Nawaf.; Çankaya Üniversitesi,Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Ana Bilim Dalı
    This thesis introduces a general survey of conversion algorithms, their advantages and disadvantages and a thorough explanation of the basic concepts in the field of 3D model reconstruction. The thesis concentrates, step by step, on the structures of motion technique and reconstruction of three-dimensional models from image pairs. The reconstruction process is carried out using a single calibrated camera and an algorithm based on only two views of a scene, the SFM technique based on detecting the correspondence points between the two images, and the epipolar inliers. All the experimental results have been computed using MATLAB (R2015b). By using the KLT algorithm we figure out the incompatibility of it with the widely-spaced images. Also, the ability of reducing the rate of reprojection error by removing the images that have the biggest rate of error. The experimental results are consisting from three stages. The first stage is done by using a scene with soft surfaces, the performance of the algorithm shows some deficiencies with the soft surfaces which are have few details. The second stage is done by using different scene with objects which have more details and rough surfaces, the algorithm results become more accurate than the first scene. The third stage is done by using the first scene of the first stage but after adding more details for surface of the ball in order to motivate the algorithm to detect more points, the results become more accurate than the results of the first stage. The experiments are showing the performance of the algorithm with different scenes and demonstrate the way of improving the algorithm. At last, we would like to mention that the aim of thesis is to figure out the depth information from two 2D images, and not to create 3D image from two 2D images.