Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034183649> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3034183649 endingPage "161" @default.
- W3034183649 startingPage "143" @default.
- W3034183649 abstract "Classical image segmentation algorithms exploit the detection of similarities and discontinuities of different visual cues to define and differentiate multiple regions of interest in images. However, due to the high variability and uncertainty of image data, producing accurate results is difficult. In other words, segmentation based just on color is often insufficient for a large percentage of real-life scenes. This work presents a novel multi-modal segmentation strategy that integrates depth and appearance cues from RGB-D images by building a hierarchical region-based representation, i.e., a multi-modal segmentation tree (MM-tree). For this purpose, RGB-D image pairs are represented in a complementary fashion by different segmentation maps. Based on color images, a color segmentation tree (C-tree) is created to obtain segmented and over-segmented maps. From depth images, two independent segmentation maps are derived by computing planar and 3D edge primitives. Then, an iterative region merging process can be used to locally group the previously obtained maps into the MM-tree. Finally, the top emerging MM-tree level coherently integrates the available information from depth and appearance maps. The experiments were conducted using the NYU-Depth V2 RGB-D dataset, which demonstrated the competitive results of our strategy compared to state-of-the-art segmentation methods. Specifically, using test images, our method reached average scores of 0.56 in Segmentation Covering and 2.13 in Variation of Information." @default.
- W3034183649 created "2020-06-19" @default.
- W3034183649 creator A5011898862 @default.
- W3034183649 creator A5014726135 @default.
- W3034183649 creator A5030063596 @default.
- W3034183649 date "2020-05-15" @default.
- W3034183649 modified "2023-10-14" @default.
- W3034183649 title "Multi-modal RGB-D Image Segmentation from Appearance and Geometric Depth Maps" @default.
- W3034183649 cites W125693051 @default.
- W3034183649 cites W1973771202 @default.
- W3034183649 cites W2010975286 @default.
- W3034183649 cites W2016726354 @default.
- W3034183649 cites W2035850930 @default.
- W3034183649 cites W2066813062 @default.
- W3034183649 cites W2067912884 @default.
- W3034183649 cites W2073886755 @default.
- W3034183649 cites W2086374833 @default.
- W3034183649 cites W2108402667 @default.
- W3034183649 cites W2110158442 @default.
- W3034183649 cites W2115193009 @default.
- W3034183649 cites W2116046277 @default.
- W3034183649 cites W2116373927 @default.
- W3034183649 cites W2121189958 @default.
- W3034183649 cites W2141729166 @default.
- W3034183649 cites W2151047074 @default.
- W3034183649 cites W2152632881 @default.
- W3034183649 cites W2155033583 @default.
- W3034183649 cites W2345333930 @default.
- W3034183649 cites W2404760654 @default.
- W3034183649 cites W2770233088 @default.
- W3034183649 cites W2777686015 @default.
- W3034183649 cites W2780351918 @default.
- W3034183649 cites W2963896186 @default.
- W3034183649 cites W35043963 @default.
- W3034183649 cites W4300650665 @default.
- W3034183649 doi "https://doi.org/10.22430/22565337.1538" @default.
- W3034183649 hasPublicationYear "2020" @default.
- W3034183649 type Work @default.
- W3034183649 sameAs 3034183649 @default.
- W3034183649 citedByCount "1" @default.
- W3034183649 countsByYear W30341836492022 @default.
- W3034183649 crossrefType "journal-article" @default.
- W3034183649 hasAuthorship W3034183649A5011898862 @default.
- W3034183649 hasAuthorship W3034183649A5014726135 @default.
- W3034183649 hasAuthorship W3034183649A5030063596 @default.
- W3034183649 hasBestOaLocation W30341836491 @default.
- W3034183649 hasConcept C113174947 @default.
- W3034183649 hasConcept C124504099 @default.
- W3034183649 hasConcept C134306372 @default.
- W3034183649 hasConcept C153180895 @default.
- W3034183649 hasConcept C154945302 @default.
- W3034183649 hasConcept C25694479 @default.
- W3034183649 hasConcept C31972630 @default.
- W3034183649 hasConcept C33923547 @default.
- W3034183649 hasConcept C41008148 @default.
- W3034183649 hasConcept C42314347 @default.
- W3034183649 hasConcept C65885262 @default.
- W3034183649 hasConcept C67561299 @default.
- W3034183649 hasConcept C82990744 @default.
- W3034183649 hasConcept C89600930 @default.
- W3034183649 hasConceptScore W3034183649C113174947 @default.
- W3034183649 hasConceptScore W3034183649C124504099 @default.
- W3034183649 hasConceptScore W3034183649C134306372 @default.
- W3034183649 hasConceptScore W3034183649C153180895 @default.
- W3034183649 hasConceptScore W3034183649C154945302 @default.
- W3034183649 hasConceptScore W3034183649C25694479 @default.
- W3034183649 hasConceptScore W3034183649C31972630 @default.
- W3034183649 hasConceptScore W3034183649C33923547 @default.
- W3034183649 hasConceptScore W3034183649C41008148 @default.
- W3034183649 hasConceptScore W3034183649C42314347 @default.
- W3034183649 hasConceptScore W3034183649C65885262 @default.
- W3034183649 hasConceptScore W3034183649C67561299 @default.
- W3034183649 hasConceptScore W3034183649C82990744 @default.
- W3034183649 hasConceptScore W3034183649C89600930 @default.
- W3034183649 hasIssue "48" @default.
- W3034183649 hasLocation W30341836491 @default.
- W3034183649 hasLocation W30341836492 @default.
- W3034183649 hasOpenAccess W3034183649 @default.
- W3034183649 hasPrimaryLocation W30341836491 @default.
- W3034183649 hasRelatedWork W2044548884 @default.
- W3034183649 hasRelatedWork W2069711651 @default.
- W3034183649 hasRelatedWork W2074857711 @default.
- W3034183649 hasRelatedWork W2384989255 @default.
- W3034183649 hasRelatedWork W2558375057 @default.
- W3034183649 hasRelatedWork W2566648451 @default.
- W3034183649 hasRelatedWork W2739874619 @default.
- W3034183649 hasRelatedWork W2785932105 @default.
- W3034183649 hasRelatedWork W2897195263 @default.
- W3034183649 hasRelatedWork W4361265312 @default.
- W3034183649 hasVolume "23" @default.
- W3034183649 isParatext "false" @default.
- W3034183649 isRetracted "false" @default.
- W3034183649 magId "3034183649" @default.
- W3034183649 workType "article" @default.