Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225564650> ?p ?o ?g. }
- W4225564650 endingPage "9" @default.
- W4225564650 startingPage "9" @default.
- W4225564650 abstract "The goal of background reconstruction is to recover the background image of a scene from a sequence of frames showing this scene cluttered by various moving objects. This task is fundamental in image analysis, and is generally the first step before more advanced processing, but difficult because there is no formal definition of what should be considered as background or foreground and the results may be severely impacted by various challenges such as illumination changes, intermittent object motions, highly cluttered scenes, etc. We propose in this paper a new iterative algorithm for background reconstruction, where the current estimate of the background is used to guess which image pixels are background pixels and a new background estimation is performed using those pixels only. We then show that the proposed algorithm, which uses stochastic gradient descent for improved regularization, is more accurate than the state of the art on the challenging SBMnet dataset, especially for short videos with low frame rates, and is also fast, reaching an average of 52 fps on this dataset when parameterized for maximal accuracy using acceleration with a graphics processing unit (GPU) and a Python implementation." @default.
- W4225564650 created "2022-05-05" @default.
- W4225564650 creator A5007519704 @default.
- W4225564650 creator A5079099554 @default.
- W4225564650 date "2022-01-11" @default.
- W4225564650 modified "2023-09-30" @default.
- W4225564650 title "Fast and Accurate Background Reconstruction Using Background Bootstrapping" @default.
- W4225564650 cites W1974204721 @default.
- W4225564650 cites W1992381997 @default.
- W4225564650 cites W2062520372 @default.
- W4225564650 cites W2065853093 @default.
- W4225564650 cites W2112204123 @default.
- W4225564650 cites W2118246710 @default.
- W4225564650 cites W2121274305 @default.
- W4225564650 cites W2122038601 @default.
- W4225564650 cites W2124102681 @default.
- W4225564650 cites W2141572457 @default.
- W4225564650 cites W2142651109 @default.
- W4225564650 cites W2145962650 @default.
- W4225564650 cites W2147732868 @default.
- W4225564650 cites W2184872067 @default.
- W4225564650 cites W2294546190 @default.
- W4225564650 cites W2295628903 @default.
- W4225564650 cites W2312654522 @default.
- W4225564650 cites W2406379805 @default.
- W4225564650 cites W2517109129 @default.
- W4225564650 cites W2549532711 @default.
- W4225564650 cites W2557414982 @default.
- W4225564650 cites W2566016175 @default.
- W4225564650 cites W2570149284 @default.
- W4225564650 cites W2608052159 @default.
- W4225564650 cites W2608259753 @default.
- W4225564650 cites W2608533835 @default.
- W4225564650 cites W2610071666 @default.
- W4225564650 cites W2738306816 @default.
- W4225564650 cites W2741989487 @default.
- W4225564650 cites W2750950678 @default.
- W4225564650 cites W2765590630 @default.
- W4225564650 cites W2793896956 @default.
- W4225564650 cites W2810408121 @default.
- W4225564650 cites W2887887082 @default.
- W4225564650 cites W2902239439 @default.
- W4225564650 cites W2914843691 @default.
- W4225564650 cites W2948390862 @default.
- W4225564650 cites W2963084556 @default.
- W4225564650 cites W2981036845 @default.
- W4225564650 cites W653074768 @default.
- W4225564650 doi "https://doi.org/10.3390/jimaging8010009" @default.
- W4225564650 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35049850" @default.
- W4225564650 hasPublicationYear "2022" @default.
- W4225564650 type Work @default.
- W4225564650 citedByCount "2" @default.
- W4225564650 countsByYear W42255646502023 @default.
- W4225564650 crossrefType "journal-article" @default.
- W4225564650 hasAuthorship W4225564650A5007519704 @default.
- W4225564650 hasAuthorship W4225564650A5079099554 @default.
- W4225564650 hasBestOaLocation W42255646501 @default.
- W4225564650 hasConcept C111919701 @default.
- W4225564650 hasConcept C11413529 @default.
- W4225564650 hasConcept C115961682 @default.
- W4225564650 hasConcept C124504099 @default.
- W4225564650 hasConcept C154945302 @default.
- W4225564650 hasConcept C160633673 @default.
- W4225564650 hasConcept C165464430 @default.
- W4225564650 hasConcept C2776135515 @default.
- W4225564650 hasConcept C2779851693 @default.
- W4225564650 hasConcept C31972630 @default.
- W4225564650 hasConcept C41008148 @default.
- W4225564650 hasConcept C5134670 @default.
- W4225564650 hasConceptScore W4225564650C111919701 @default.
- W4225564650 hasConceptScore W4225564650C11413529 @default.
- W4225564650 hasConceptScore W4225564650C115961682 @default.
- W4225564650 hasConceptScore W4225564650C124504099 @default.
- W4225564650 hasConceptScore W4225564650C154945302 @default.
- W4225564650 hasConceptScore W4225564650C160633673 @default.
- W4225564650 hasConceptScore W4225564650C165464430 @default.
- W4225564650 hasConceptScore W4225564650C2776135515 @default.
- W4225564650 hasConceptScore W4225564650C2779851693 @default.
- W4225564650 hasConceptScore W4225564650C31972630 @default.
- W4225564650 hasConceptScore W4225564650C41008148 @default.
- W4225564650 hasConceptScore W4225564650C5134670 @default.
- W4225564650 hasFunder F4320320883 @default.
- W4225564650 hasIssue "1" @default.
- W4225564650 hasLocation W42255646501 @default.
- W4225564650 hasLocation W42255646502 @default.
- W4225564650 hasLocation W42255646503 @default.
- W4225564650 hasLocation W42255646504 @default.
- W4225564650 hasLocation W42255646505 @default.
- W4225564650 hasLocation W42255646506 @default.
- W4225564650 hasLocation W42255646507 @default.
- W4225564650 hasOpenAccess W4225564650 @default.
- W4225564650 hasPrimaryLocation W42255646501 @default.
- W4225564650 hasRelatedWork W121273120 @default.
- W4225564650 hasRelatedWork W2002009170 @default.
- W4225564650 hasRelatedWork W2034462085 @default.
- W4225564650 hasRelatedWork W2141888456 @default.
- W4225564650 hasRelatedWork W2164918837 @default.
- W4225564650 hasRelatedWork W2337415362 @default.