Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385516976> ?p ?o ?g. }
- W4385516976 endingPage "82166" @default.
- W4385516976 startingPage "82151" @default.
- W4385516976 abstract "This paper focuses on the computational optimization of RANSAC. We describe the Parallel Efficient Sample Consensus (PESAC) framework that allows efficient utilization of SIMD extensions and provides memory locality due to a special way of storing the input sequence of correspondences and generating a batch of samples per one main loop iteration. It is inspired by the USAC framework and has a block structure capable of implementing most modern RANSAC-based methods. We enhance it with individual blocks of sample and model restrictors that are aimed at the rejection of “bad” samples and model hypothesis before time-consuming model computation and verification blocks. We also provide a detailed description implementing 2D homography estimation problem in PESAC and benchmark the running time on the MIDV-2020 dataset of identity documents. Comparing to naive implementation, we accelerated our framework by 122 times for the document classification task (with a 6 % increase in accuracy) and by 18 times for document tracking (with a 46 % decrease in tracking failure rate) by using both restrictors and vector processing. This version also outperformed a number of USAC implementations from OpenCV-4.6.0 in runtime and accuracy of estimation (3 times faster, 6 % greater accuracy for the classification task, and 2 times faster, 33 % lower failure rate for tracking if comparing with USAC_MAGSAC)." @default.
- W4385516976 created "2023-08-04" @default.
- W4385516976 creator A5023945539 @default.
- W4385516976 creator A5040458320 @default.
- W4385516976 creator A5047135094 @default.
- W4385516976 creator A5066631478 @default.
- W4385516976 creator A5077963262 @default.
- W4385516976 creator A5092588288 @default.
- W4385516976 date "2023-01-01" @default.
- W4385516976 modified "2023-09-25" @default.
- W4385516976 title "PESAC, the generalized framework for RANSAC-based methods on SIMD computing platforms" @default.
- W4385516976 cites W102203083 @default.
- W4385516976 cites W1575387439 @default.
- W4385516976 cites W1578412938 @default.
- W4385516976 cites W1579973560 @default.
- W4385516976 cites W1594846894 @default.
- W4385516976 cites W1836071871 @default.
- W4385516976 cites W1873846702 @default.
- W4385516976 cites W1965265891 @default.
- W4385516976 cites W1986556718 @default.
- W4385516976 cites W2010583217 @default.
- W4385516976 cites W2012700833 @default.
- W4385516976 cites W2020347720 @default.
- W4385516976 cites W2026375818 @default.
- W4385516976 cites W2028257406 @default.
- W4385516976 cites W2029802015 @default.
- W4385516976 cites W2034807680 @default.
- W4385516976 cites W2036470408 @default.
- W4385516976 cites W2044531421 @default.
- W4385516976 cites W2046434485 @default.
- W4385516976 cites W2051948786 @default.
- W4385516976 cites W2085261163 @default.
- W4385516976 cites W2089378033 @default.
- W4385516976 cites W2090039150 @default.
- W4385516976 cites W2095718030 @default.
- W4385516976 cites W2106199912 @default.
- W4385516976 cites W2111073598 @default.
- W4385516976 cites W2111702258 @default.
- W4385516976 cites W2114759747 @default.
- W4385516976 cites W2116940697 @default.
- W4385516976 cites W2118334653 @default.
- W4385516976 cites W2119473545 @default.
- W4385516976 cites W2127013183 @default.
- W4385516976 cites W2129363926 @default.
- W4385516976 cites W2130017587 @default.
- W4385516976 cites W2141710440 @default.
- W4385516976 cites W2143648521 @default.
- W4385516976 cites W2144529323 @default.
- W4385516976 cites W2148963710 @default.
- W4385516976 cites W2151843422 @default.
- W4385516976 cites W2160325604 @default.
- W4385516976 cites W2164876145 @default.
- W4385516976 cites W2167999499 @default.
- W4385516976 cites W2236623899 @default.
- W4385516976 cites W2533007775 @default.
- W4385516976 cites W2560520666 @default.
- W4385516976 cites W2609550078 @default.
- W4385516976 cites W2739818851 @default.
- W4385516976 cites W2754798356 @default.
- W4385516976 cites W2786359932 @default.
- W4385516976 cites W2801335177 @default.
- W4385516976 cites W2962828767 @default.
- W4385516976 cites W2967756832 @default.
- W4385516976 cites W2999042620 @default.
- W4385516976 cites W3003246940 @default.
- W4385516976 cites W3003407834 @default.
- W4385516976 cites W3005427638 @default.
- W4385516976 cites W3005456327 @default.
- W4385516976 cites W3034373437 @default.
- W4385516976 cites W3091793544 @default.
- W4385516976 cites W3125612102 @default.
- W4385516976 cites W3130218605 @default.
- W4385516976 cites W3177126114 @default.
- W4385516976 cites W3198043015 @default.
- W4385516976 cites W3202613539 @default.
- W4385516976 cites W3216767130 @default.
- W4385516976 cites W4206515215 @default.
- W4385516976 cites W4229995443 @default.
- W4385516976 cites W4251504644 @default.
- W4385516976 cites W4281753200 @default.
- W4385516976 cites W4284712619 @default.
- W4385516976 cites W2120665892 @default.
- W4385516976 doi "https://doi.org/10.1109/access.2023.3301777" @default.
- W4385516976 hasPublicationYear "2023" @default.
- W4385516976 type Work @default.
- W4385516976 citedByCount "0" @default.
- W4385516976 crossrefType "journal-article" @default.
- W4385516976 hasAuthorship W4385516976A5023945539 @default.
- W4385516976 hasAuthorship W4385516976A5040458320 @default.
- W4385516976 hasAuthorship W4385516976A5047135094 @default.
- W4385516976 hasAuthorship W4385516976A5066631478 @default.
- W4385516976 hasAuthorship W4385516976A5077963262 @default.
- W4385516976 hasAuthorship W4385516976A5092588288 @default.
- W4385516976 hasBestOaLocation W43855169761 @default.
- W4385516976 hasConcept C11413529 @default.
- W4385516976 hasConcept C114744707 @default.
- W4385516976 hasConcept C115961682 @default.
- W4385516976 hasConcept C13280743 @default.