Multiview 3d reconstruction of a scene containing independently moving objects

Download
2005
Tola, Engin
In this thesis, the structure from motion problem for calibrated scenes containing independently moving objects (IMO) has been studied. For this purpose, the overall reconstruction process is partitioned into various stages. The first stage deals with the fundamental problem of estimating structure and motion by using only two views. This process starts with finding some salient features using a sub-pixel version of the Harris corner detector. The features are matched by the help of a similarity and neighborhood-based matcher. In order to reject the outliers and estimate the fundamental matrix of the two images, a robust estimation is performed via RANSAC and normalized 8-point algorithms. Two-view reconstruction is finalized by decomposing the fundamental matrix and estimating the 3D-point locations as a result of triangulation. The second stage of the reconstruction is the generalization of the two-view algorithm for the N-view case. This goal is accomplished by first reconstructing an initial framework from the first stage and then relating the additional views by finding correspondences between the new view and already reconstructed views. In this way, 3D-2D projection pairs are determined and the projection matrix of this new view is estimated by using a robust procedure. The final section deals with scenes containing IMOs. In order to reject the correspondences due to moving objects, parallax-based rigidity constraint is used. In utilizing this constraint, an automatic background pixel selection algorithm is developed and an IMO rejection algorithm is also proposed. The results of the proposed algorithm are compared against that of a robust outlier rejection algorithm and found to be quite promising in terms of execution time vs. reconstruction quality.

Suggestions

Analysis and design of microstrip printed structures on electromagnetic bandgap substrates
Güdü, Tamer; Alatan, Lale; Department of Electrical and Electronics Engineering (2008)
In the first part of the thesis, the 2-D structures in stratified media are analyzed using an efficient MoM technique. The method is used to optimize transmitted or reflected electric fields from the 2-D structures. The genetic algorithm is used in the optimization process. In the second part a 3-D MoM technique is implemented to analyze multilayered structures with periodically implanted material blocks. Using the method, the dispersion and reflection characteristics of the structure are calculated for dif...
Joint frequency offset and channel estimation
Avan, Muhammet; Candan, Çağatay; Department of Electrical and Electronics Engineering (2008)
In this thesis study, joint frequency offset and channel estimation methods for single-input single-output (SISO) systems are examined. The performance of maximum likelihood estimate of the parameters are studied for different training sequences. Conventionally training sequences are designed solely for the channel estimation purpose. We present a numerical comparison of different training sequences for the joint estimation problem. The performance comparisons are made in terms of mean square estimation err...
Parameter extraction and image enhancement for catadioptric omnidirectional cameras
Baştanlar, Yalın; Çetin, Yasemin; Department of Information Systems (2005)
In this thesis, catadioptric omnidirectional imaging systems are analyzed in detail. Omnidirectional image (ODI) formation characteristics of different camera-mirror configurations are examined and geometrical relations for panoramic and perspective image generation with common mirror types are summarized. A method is developed to determine the unknown parameters of a hyperboloidal-mirrored system using the world coordinates of a set of points and their corresponding image points on the ODI. A linear relati...
Image segmentation based on variational techniques
Altınoklu, Metin Burak; Ünver, Baki Zafer; Department of Electrical and Electronics Engineering (2009)
In this thesis, the image segmentation methods based on the MumfordShah variational approach have been studied. By obtaining an optimum point of the Mumford-Shah functional which is a piecewise smooth approximate image and a set of edge curves, an image can be decomposed into regions. This piecewise smooth approximate image is smooth inside of regions, but it is allowed to be discontinuous region wise. Unfortunately, because of the irregularity of the Mumford Shah functional, it cannot be directly used for ...
Robust set-valued estimation and its application to in-flight alignment of sins
Seymen, Niyazi Burak; Demirekler, Mübeccel; Department of Electrical and Electronics Engineering (2005)
In this thesis, robust set-valued estimation is studied and its application to in-flight alignment of strapdown inertial navigation systems (SINS) with large heading uncertainty is performed. It is known that the performance of the Kalman filter is vulnerable to modeling errors. One of the estimation methods, which are robust against modeling errors, is robust set-valued estimation. In this approach, the filter calculates the set of all possible states, which are consistent with uncertainty inputs satisfyin...
Citation Formats
E. Tola, “Multiview 3d reconstruction of a scene containing independently moving objects,” M.S. - Master of Science, Middle East Technical University, 2005.