Dense depth map estimation for object segmentation in multi-view video

Çığla, Cevahir
In this thesis, novel approaches for dense depth field estimation and object segmentation from mono, stereo and multiple views are presented. In the first stage, a novel graph-theoretic color segmentation algorithm is proposed, in which the popular Normalized Cuts 59H[6] segmentation algorithm is improved with some modifications on its graph structure. Segmentation is obtained by the recursive partitioning of the weighted graph. The simulation results for the comparison of the proposed segmentation scheme with some well-known segmentation methods, such as Recursive Shortest Spanning Tree 60H[3] and Mean-Shift 61H[4] and the conventional Normalized Cuts, show clear improvements over these traditional methods. The proposed region-based approach is also utilized during the dense depth map estimation step, based on a novel modified plane- and angle-sweeping strategy. In the proposed dense depth estimation technique, the whole scene is assumed to be region-wise planar and 3D models of these plane patches are estimated by a greedy-search algorithm that also considers visibility constraint. In order to refine the depth maps and relax the planarity assumption of the scene, at the final step, two refinement techniques that are based on region splitting and pixel-based optimization via Belief Propagation 62H[32] are also applied. Finally, the image segmentation algorithm is extended to object segmentation in multi-view video with the additional depth and optical flow information. Optical flow estimation is obtained via two different methods, KLT tracker and region-based block matching and the comparisons between these methods are performed. The experimental results indicate an improvement for the segmentation performance by the usage of depth and motion information.


Noise reduction in time-frequency domain
Kalyoncu, Özden; SÜnver, Zafer; Department of Electrical and Electronics Engineering (2007)
In this thesis work, time-frequency filtering of nonstationary signals in noise using Wigner-Ville Distribution is investigated. Continuous-time, discrete-time and discrete Wigner Ville Distribution definitions, their relations, and properties are given. Time-Frequency Peak Filtering Method is presented. The effects of different parameters on the performance of the method are investigated, and the results are presented. Time-Varying Wiener Filter is presented. Using simulations it is shown that the performa...
Dim target detection in infrared imagery
Çifçi, Barış; Atalay, Aydın; Department of Electrical and Electronics Engineering (2006)
This thesis examines the performance of some dim target detection algorithms in low-SNR imaging scenarios. In the past research, there have been numerous attempts for detection and tracking barely visible targets for military surveillance applications with infrared sensors. In this work, two of these algorithms are analyzed via extensive simulations. In one of these approaches, dynamic programming is exploited to coherently integrate the visible energy of dim targets over possible relative directions, where...
FPGA implementation of graph cut method for real time stereo matching
Sağlık Özsaraç, Havva; Ünver, Baki Zafer; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2010)
The present graph cut methods cannot be used directly for real time stereo matching applications because of their recursive structure. Graph cut method is modified to change its recursive structure so that making it suitable for real time FPGA (Field Programmable Gate Array) implementation. The modified method is firstly tested by MATLAB on several data sets, and the results are compared with those of previous studies. Although the disparity results of the modified method are not better than other methods’,...
Investigation of music algorithm based and wd-pca method based electromagnetic target classification techniques for their noise performances
Ergin, Emre; Sayan, Gönül; Department of Electrical and Electronics Engineering (2009)
Multiple Signal Classification (MUSIC) Algorithm based and Wigner Distribution-Principal Component Analysis (WD-PCA) based classification techniques are very recently suggested resonance region approaches for electromagnetic target classification. In this thesis, performances of these two techniques will be compared concerning their robustness for noise and their capacity to handle large number of candidate targets. In this context, classifier design simulations will be demonstrated for target libraries con...
Tracker-aware detection : a theoretical and an experimental study
Aslan, Murat Şamil; Saranlı, Afşar; Department of Electrical and Electronics Engineering (2009)
A promising line of research attempts to bridge the gap between detector and tracker by means of considering jointly optimal parameter settings for both of these subsystems. Along this fruitful path, this thesis study focuses on the problem of detection threshold optimization in a tracker-aware manner so that a feedback from the tracker to the detector is established to maximize the overall system performance. Special emphasis is given to the optimization schemes based on two non-simulation performance pred...
Citation Formats
C. Çığla, “Dense depth map estimation for object segmentation in multi-view video,” M.S. - Master of Science, Middle East Technical University, 2007.