000 03338nam a22005417a 4500
001 sulb-eb0024712
003 BD-SySUS
005 20160413122453.0
007 cr nn 008mamaa
008 130220s2013 gw | s |||| 0|eng d
020 _a9783642364181
_9978-3-642-36418-1
024 7 _a10.1007/978-3-642-36418-1
_2doi
050 4 _aTJ210.2-211.495
050 4 _aT59.5
072 7 _aTJFM1
_2bicssc
072 7 _aTEC037000
_2bisacsh
072 7 _aTEC004000
_2bisacsh
082 0 4 _a629.892
_223
100 1 _aNicosevici, Tudor.
_eauthor.
245 1 0 _aEfficient 3D Scene Modeling and Mosaicing
_h[electronic resource] /
_cby Tudor Nicosevici, Rafael Garcia.
264 1 _aBerlin, Heidelberg :
_bSpringer Berlin Heidelberg :
_bImprint: Springer,
_c2013.
300 _aXXII, 161 p. 97 illus., 76 illus. in color.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aSpringer Tracts in Advanced Robotics,
_x1610-7438 ;
_v87
505 0 _aIntroduction -- Literature Review -- Direct Structure from Motion -- Online Loop Detection -- Online 3D Model Simplification -- Conclusions.
520 _aThis book proposes a complete pipeline for monocular (single camera) based 3D mapping of terrestrial and underwater environments. The aim is to provide a solution to large-scale scene modeling that is both accurate and efficient. To this end, we have developed a novel Structure from Motion algorithm that increases mapping accuracy by registering camera views directly with the maps. The camera registration uses a dual approach that adapts to the type of environment being mapped.   In order to further increase the accuracy of the resulting maps, a new method is presented, allowing detection of images corresponding to the same scene region (crossovers). Crossovers then used in conjunction with global alignment methods in order to highly reduce estimation errors, especially when mapping large areas. Our method is based on Visual Bag of Words paradigm (BoW), offering a more efficient and simpler solution by eliminating the training stage, generally required by state of the art BoW algorithms.   Also, towards developing methods for efficient mapping of large areas (especially with costs related to map storage, transmission and rendering in mind), an online 3D model simplification algorithm is proposed. This new algorithm presents the advantage of selecting only those vertices that are geometrically representative for the scene.
650 0 _aEngineering.
650 0 _aArtificial intelligence.
650 0 _aImage processing.
650 0 _aRobotics.
650 0 _aAutomation.
650 1 4 _aEngineering.
650 2 4 _aRobotics and Automation.
650 2 4 _aArtificial Intelligence (incl. Robotics).
650 2 4 _aImage Processing and Computer Vision.
700 1 _aGarcia, Rafael.
_eauthor.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer eBooks
776 0 8 _iPrinted edition:
_z9783642364174
830 0 _aSpringer Tracts in Advanced Robotics,
_x1610-7438 ;
_v87
856 4 0 _uhttp://dx.doi.org/10.1007/978-3-642-36418-1
912 _aZDB-2-ENG
942 _2Dewey Decimal Classification
_ceBooks
999 _c46804
_d46804