000210604 001__ 210604
000210604 005__ 20190509132525.0
000210604 0247_ $$2doi$$a10.5075/epfl-thesis-6622
000210604 02470 $$2urn$$aurn:nbn:ch:bel-epfl-thesis6622-7
000210604 02471 $$2nebis$$a10495353
000210604 037__ $$aTHESIS
000210604 041__ $$aeng
000210604 088__ $$a6622
000210604 245__ $$aLocalizing Polygonal Objects in Man-Made Environments
000210604 269__ $$a2015
000210604 260__ $$bEPFL$$c2015$$aLausanne
000210604 300__ $$a152
000210604 336__ $$aTheses
000210604 502__ $$aProf. Pierre Dillenbourg (président) ; Prof. Pascal Fua (directeur de thèse) ; Prof. François Golay, Prof. Eric Marchand, Prof. Luigi Di Stefano (rapporteurs)
000210604 520__ $$aObject detection is a significant challenge in Computer Vision and has received a lot of attention in the field. One such challenge addressed in this thesis is the detection of polygonal objects, which are prevalent in man-made environments. Shape analysis is an important cue to detect these objects. We propose a contour-based object detection framework to deal with the related challenges, including how to efficiently detect polygonal shapes and how to exploit them for object detection. First, we propose an efficient component tree segmentation framework for stable region extraction and a multi-resolution line segment detection algorithm, which form the bases of our detection framework. Our component tree segmentation algorithm explores the optimal threshold for each branch of the component tree, and achieves a significant improvement over image thresholding segmentation, and comparable performance to more sophisticated methods but only at a fraction of computation time. Our line segment detector overcomes several inherent limitations of the Hough transform, and achieves a comparable performance to the state-of-the-art line segment detectors. However, our approach can better capture dominant structures and is more stable against low-quality imaging conditions.  Second, we propose a global shape analysis measurement for simple polygon detection and use it to develop an approach for real-time landing site detection in unconstrained man-made environments. Since the task of detecting landing sites must be performed in a few seconds or less, existing methods are often limited to simple local intensity and edge variation cues. By contrast, we show how to efficiently take into account the potential sites’ global shape, which is a critical cue in man-made scenes. Our method relies on component tree segmentation algorithm and a new shape regularity measure to look for polygonal regions in video sequences. In this way we enforce both temporal consistency and geometric regularity, resulting in reliable and consistent detections.  Third, we propose a generic contour grouping based object detection approach by exploring promising cycles in a line fragment graph. Previous contour-based methods are limited to use additive scoring functions. In this thesis, we propose an approximate search approach that eliminates this restriction. Given a weighted line fragment graph, we prune its cycle space by removing cycles containing weak nodes or weak edges, until the upper bound of the cycle space is less than the threshold defined by the cyclomatic number. Object contours are then detected as maximally scoring elementary circuits in the pruned cycle space. Furthermore, we propose another more efficient algorithm, which reconstructs the graph by grouping the strongest edges iteratively until the number of the cycles reaches the upper bound. Our approximate search approaches can be used with any cycle scoring function. Moreover, unlike other contour grouping based approaches, our approach does not rely on a greedy strategy for finding multiple candidates and is capable of finding multiple candidates sharing common line fragments. We demonstrate that our approach significantly outperforms the state-of-the-art.
000210604 6531_ $$aImage processing
000210604 6531_ $$acomputer vision
000210604 6531_ $$aobject detection
000210604 6531_ $$aimage segmentation
000210604 6531_ $$apolygon
000210604 6531_ $$acontour grouping
000210604 6531_ $$acycle basis
000210604 6531_ $$acomponent tree
000210604 6531_ $$aline segment detection
000210604 6531_ $$aautomated landing
000210604 700__ $$0244459$$g200255$$aSun, Xiaolu
000210604 720_2 $$aFua, Pascal$$edir.$$g112366$$0240252
000210604 8564_ $$uhttps://infoscience.epfl.ch/record/210604/files/EPFL_TH6622.pdf$$zn/a$$s24803102$$yn/a
000210604 909C0 $$xU10659$$0252087$$pCVLAB
000210604 909CO $$pthesis-bn2018$$pDOI$$pIC$$ooai:infoscience.tind.io:210604$$qDOI2$$qGLOBAL_SET$$pthesis
000210604 917Z8 $$x108898
000210604 917Z8 $$x108898
000210604 918__ $$dEDIC2005-2015$$cISIM$$aIC
000210604 919__ $$aCVLAB
000210604 920__ $$b2015$$a2015-8-28
000210604 970__ $$a6622/THESES
000210604 973__ $$sPUBLISHED$$aEPFL
000210604 980__ $$aTHESIS