@phdthesis {PUBA217,
	title = {Stereoscopic Depth Estimation for Online Vision Systems},
	author = {Nils Einecke},
	year = {2012},
	abstract = {The human visual perception heavily depends on stereoscopic vision. By fusing the two views that our eyes provide, a 3-D sensation of the surrounding is generated. It is therefore natural to assume that machine vision systems also benefit from a comparable sense. A lot of work has been done in the area of machine stereo vision, but a severe drawback of today{\textquoteright}s algorithms is that they either achieve high accuracy and robustness by sacrificing real-time speed or they are real-time capable but with major deficiencies in quality. The goal of this thesis is to tackle the problem of real-time, real-world, stereoscopic depth processing. In particular, the processing should be lightweight enough to be processed on mobile platforms. To this end, two new methods are introduces that have a very good balance between speed and accuracy. First, a new cost function for block-matching stereo processing is proposed. In contrast to most standard cost functions it hardly suffers from the fattening effect while being computationally very efficient. Evaluations on standard benchmarks show that this new cost function brings the standard local block-matching stereo very close to the performance of global optimization methods based on graph cut or belief propagation. As an additional benefit for real-time implementation, a multi-core parallel processing scheme for block-matching stereo is discussed which allows for a runtime gain that is linear in the number of processing cores. Second, a new algorithm for fitting parametric surface models to stereo images is introduced. This algorithm is inspired by the homography-constrained gradient descent methods which are frequently used to estimate the orientation and depth of planar surfaces. By replacing the gradient descent search with the direct search method of Hooke-Jeeves the fitting of any parametric surface model with arbitrary cost functions becomes feasible. A comparison on standard benchmarks shows that this new algorithm has a comparable depth accuracy as state-of-the-art methods while being more robust in challenging situations. Additionally, a sparse matching scheme is discussed which enables real-time estimations even for very large surfaces. In order to prove the real-world capabilities of the proposed methods, they are integrated into an automotive and a robotic vision system. The automotive system is tested in different weather and lighting conditions which demonstrates the high robustness and stability of the proposed methods for variable conditions. In the environment of the tested robotic system a lot of objects have a homogeneous color to ease their segmentation and detection. This, however, poses a grave challenge to the depth perception due to weak textures. Grasping and navigation experiments demonstrate that despite the hard challenge the proposed methods are able to estimate the depth of objects very accurately. Altogether, the experiments highlight that the developed methods are well-suited for real-time, real-world applications on mobile platforms. },
	publisher = {Universit{\"a}tsverlag Ilmenau},
	booktitle = {Uni Ilmenau},
	institution = {TU Ilmenau}
}