Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289694512> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4289694512 abstract "Moving Object Segmentation is a challenging task for jittery/wobbly videos. For jittery videos, the non-smooth camera motion makes discrimination between foreground objects and background layers hard to solve. While most recent works for moving video object segmentation fail in this scenario, our method generates an accurate segmentation of a single moving object. The proposed method performs a sparse segmentation, where frame-wise labels are assigned only to trajectory coordinates, followed by the pixel-wise labeling of frames. The sparse segmentation involving stabilization and clustering of trajectories in a 3-stage iterative process. At the 1st stage, the trajectories are clustered using pairwise Procrustes distance as a cue for creating an affinity matrix. The 2nd stage performs a block-wise Procrustes analysis of the trajectories and estimates Frechet means (in Kendall's shape space) of the clusters. The Frechet means represent the average trajectories of the motion clusters. An optimization function has been formulated to stabilize the Frechet means, yielding stabilized trajectories at the 3rd stage. The accuracy of the motion clusters are iteratively refined, producing distinct groups of stabilized trajectories. Next, the labels obtained from the sparse segmentation are propagated for pixel-wise labeling of the frames, using a GraphCut based energy formulation. Use of Procrustes analysis and energy minimization in Kendall's shape space for moving object segmentation in jittery videos, is the novelty of this work. Second contribution comes from experiments performed on a dataset formed of 20 real-world natural jittery videos, with manually annotated ground truth. Experiments are done with controlled levels of artificial jitter on videos of SegTrack2 dataset. Qualitative and quantitative results indicate the superiority of the proposed method." @default.
- W4289694512 created "2022-08-04" @default.
- W4289694512 creator A5000019969 @default.
- W4289694512 creator A5052298809 @default.
- W4289694512 date "2018-08-14" @default.
- W4289694512 modified "2023-09-26" @default.
- W4289694512 title "Moving Object Segmentation in Jittery Videos by Stabilizing Trajectories Modeled in Kendall's Shape Space" @default.
- W4289694512 doi "https://doi.org/10.48550/arxiv.1808.04551" @default.
- W4289694512 hasPublicationYear "2018" @default.
- W4289694512 type Work @default.
- W4289694512 citedByCount "0" @default.
- W4289694512 crossrefType "posted-content" @default.
- W4289694512 hasAuthorship W4289694512A5000019969 @default.
- W4289694512 hasAuthorship W4289694512A5052298809 @default.
- W4289694512 hasBestOaLocation W42896945121 @default.
- W4289694512 hasConcept C124504099 @default.
- W4289694512 hasConcept C146849305 @default.
- W4289694512 hasConcept C147597530 @default.
- W4289694512 hasConcept C14961307 @default.
- W4289694512 hasConcept C153180895 @default.
- W4289694512 hasConcept C154945302 @default.
- W4289694512 hasConcept C160633673 @default.
- W4289694512 hasConcept C185592680 @default.
- W4289694512 hasConcept C25694479 @default.
- W4289694512 hasConcept C2781238097 @default.
- W4289694512 hasConcept C31972630 @default.
- W4289694512 hasConcept C33923547 @default.
- W4289694512 hasConcept C41008148 @default.
- W4289694512 hasConcept C65885262 @default.
- W4289694512 hasConcept C73555534 @default.
- W4289694512 hasConcept C89600930 @default.
- W4289694512 hasConceptScore W4289694512C124504099 @default.
- W4289694512 hasConceptScore W4289694512C146849305 @default.
- W4289694512 hasConceptScore W4289694512C147597530 @default.
- W4289694512 hasConceptScore W4289694512C14961307 @default.
- W4289694512 hasConceptScore W4289694512C153180895 @default.
- W4289694512 hasConceptScore W4289694512C154945302 @default.
- W4289694512 hasConceptScore W4289694512C160633673 @default.
- W4289694512 hasConceptScore W4289694512C185592680 @default.
- W4289694512 hasConceptScore W4289694512C25694479 @default.
- W4289694512 hasConceptScore W4289694512C2781238097 @default.
- W4289694512 hasConceptScore W4289694512C31972630 @default.
- W4289694512 hasConceptScore W4289694512C33923547 @default.
- W4289694512 hasConceptScore W4289694512C41008148 @default.
- W4289694512 hasConceptScore W4289694512C65885262 @default.
- W4289694512 hasConceptScore W4289694512C73555534 @default.
- W4289694512 hasConceptScore W4289694512C89600930 @default.
- W4289694512 hasLocation W42896945121 @default.
- W4289694512 hasLocation W42896945122 @default.
- W4289694512 hasOpenAccess W4289694512 @default.
- W4289694512 hasPrimaryLocation W42896945121 @default.
- W4289694512 hasRelatedWork W1669643531 @default.
- W4289694512 hasRelatedWork W1982826852 @default.
- W4289694512 hasRelatedWork W2026019026 @default.
- W4289694512 hasRelatedWork W2118381968 @default.
- W4289694512 hasRelatedWork W2384989255 @default.
- W4289694512 hasRelatedWork W2549936415 @default.
- W4289694512 hasRelatedWork W2566648451 @default.
- W4289694512 hasRelatedWork W2892474421 @default.
- W4289694512 hasRelatedWork W3203023927 @default.
- W4289694512 hasRelatedWork W1967061043 @default.
- W4289694512 isParatext "false" @default.
- W4289694512 isRetracted "false" @default.
- W4289694512 workType "article" @default.