Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893273889> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2893273889 abstract "In this work, we propose a purely geometrical approach for the robust matching of line segments for challenging stereo streams with severe illumination changes or High Dynamic Range (HDR) environments. To that purpose, we exploit the univocal nature of the matching problem, i.e. every observation must be corresponded with a single feature or not corresponded at all. We state the problem as a sparse, convex, $ell_{1}$ -minimization of the matching vector regularized by the geometric constraints. This formulation allows for the robust tracking of line segments along sequences where traditional appearance-based matching techniques tend to fail due to dynamic changes in illumination conditions. Moreover, the proposed matching algorithm also results in a considerable speed-up of previous state of the art techniques making it suitable for real-time applications such as Visual Odometry (VO). This, of course, comes at expense of a slightly lower number of matches in comparison with appearance-based methods, and also limits its application to continuous video sequences, as it is rather constrained to small pose increments between consecutive frames. We validate the claimed advantages by first evaluating the matching performance in challenging video sequences, and then testing the method in a benchmarked point and line based VO algorithm." @default.
- W2893273889 created "2018-10-05" @default.
- W2893273889 creator A5048830936 @default.
- W2893273889 creator A5070626607 @default.
- W2893273889 date "2018-10-01" @default.
- W2893273889 modified "2023-10-06" @default.
- W2893273889 title "Geometric-based Line Segment Tracking for HDR Stereo Sequences" @default.
- W2893273889 cites W1904464160 @default.
- W2893273889 cites W1970504153 @default.
- W2893273889 cites W1972082000 @default.
- W2893273889 cites W1999174140 @default.
- W2893273889 cites W2008849352 @default.
- W2893273889 cites W2057488855 @default.
- W2893273889 cites W2068341180 @default.
- W2893273889 cites W2098012923 @default.
- W2893273889 cites W2117228865 @default.
- W2893273889 cites W2121308169 @default.
- W2893273889 cites W2145023731 @default.
- W2893273889 cites W2151290401 @default.
- W2893273889 cites W2160072137 @default.
- W2893273889 cites W2185786809 @default.
- W2893273889 cites W2341480417 @default.
- W2893273889 cites W2396274919 @default.
- W2893273889 cites W2410627718 @default.
- W2893273889 cites W2411918187 @default.
- W2893273889 cites W2564632156 @default.
- W2893273889 cites W2585355162 @default.
- W2893273889 cites W2618066342 @default.
- W2893273889 cites W2963121367 @default.
- W2893273889 cites W3102327032 @default.
- W2893273889 doi "https://doi.org/10.1109/iros.2018.8593646" @default.
- W2893273889 hasPublicationYear "2018" @default.
- W2893273889 type Work @default.
- W2893273889 sameAs 2893273889 @default.
- W2893273889 citedByCount "8" @default.
- W2893273889 countsByYear W28932738892019 @default.
- W2893273889 countsByYear W28932738892021 @default.
- W2893273889 countsByYear W28932738892022 @default.
- W2893273889 countsByYear W28932738892023 @default.
- W2893273889 crossrefType "proceedings-article" @default.
- W2893273889 hasAuthorship W2893273889A5048830936 @default.
- W2893273889 hasAuthorship W2893273889A5070626607 @default.
- W2893273889 hasBestOaLocation W28932738892 @default.
- W2893273889 hasConcept C121684516 @default.
- W2893273889 hasConcept C154945302 @default.
- W2893273889 hasConcept C15744967 @default.
- W2893273889 hasConcept C19417346 @default.
- W2893273889 hasConcept C198352243 @default.
- W2893273889 hasConcept C2524010 @default.
- W2893273889 hasConcept C2775936607 @default.
- W2893273889 hasConcept C31972630 @default.
- W2893273889 hasConcept C33923547 @default.
- W2893273889 hasConcept C41008148 @default.
- W2893273889 hasConceptScore W2893273889C121684516 @default.
- W2893273889 hasConceptScore W2893273889C154945302 @default.
- W2893273889 hasConceptScore W2893273889C15744967 @default.
- W2893273889 hasConceptScore W2893273889C19417346 @default.
- W2893273889 hasConceptScore W2893273889C198352243 @default.
- W2893273889 hasConceptScore W2893273889C2524010 @default.
- W2893273889 hasConceptScore W2893273889C2775936607 @default.
- W2893273889 hasConceptScore W2893273889C31972630 @default.
- W2893273889 hasConceptScore W2893273889C33923547 @default.
- W2893273889 hasConceptScore W2893273889C41008148 @default.
- W2893273889 hasLocation W28932738891 @default.
- W2893273889 hasLocation W28932738892 @default.
- W2893273889 hasLocation W28932738893 @default.
- W2893273889 hasOpenAccess W2893273889 @default.
- W2893273889 hasPrimaryLocation W28932738891 @default.
- W2893273889 hasRelatedWork W1497101000 @default.
- W2893273889 hasRelatedWork W1543936162 @default.
- W2893273889 hasRelatedWork W1578117154 @default.
- W2893273889 hasRelatedWork W1585873145 @default.
- W2893273889 hasRelatedWork W1971776229 @default.
- W2893273889 hasRelatedWork W2054235656 @default.
- W2893273889 hasRelatedWork W2112263445 @default.
- W2893273889 hasRelatedWork W2542256560 @default.
- W2893273889 hasRelatedWork W2766961550 @default.
- W2893273889 hasRelatedWork W4220789584 @default.
- W2893273889 isParatext "false" @default.
- W2893273889 isRetracted "false" @default.
- W2893273889 magId "2893273889" @default.
- W2893273889 workType "article" @default.