FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200318260> ?p ?o ?g. }

• W3200318260 endingPage "3151" @default.
• W3200318260 startingPage "3139" @default.
• W3200318260 abstract "Most supervised learning-based pose estimation methods for stacked scenes are trained on massive synthetic datasets. In most cases, the challenge is that the learned network on the training dataset is no longer optimal on the testing dataset. To address this problem, we propose a pose regression network PPR-Net++. It transforms each scene point into a point in the centroid space, followed by a clustering process and a voting process. In the training phase, a mapping function between the network’s critical parameter (i.e., the bandwidth of the clustering algorithm) and the compactness of the centroid distributions is obtained. This function is used to adapt the bandwidth between centroid distributions of two different domains. In addition, to further improve the pose estimation accuracy, the network also predicts the confidence of each point, based on its visibility and pose error. Only the points with high confidence have the right to vote for the final object pose. In experiments, our method is trained on the IPA synthetic dataset and compared with the state-of-the-art algorithm. When tested with the public synthetic Siléane dataset, our method is better in all eight objects, where five of them are improved by more than 5% in average precision (AP). On IPA real dataset, our method outperforms a large margin by 20%. This lays a solid foundation for robot grasping in industrial scenarios. Note to Practitioners—Our work is motivated by industrial product assembly based on robot grasping. The industrial parts are usually manufactured by numerical machines and piled in bins. Our method can estimate the poses of visible parts accurately. A pose of a part includes its centroid and spatial orientations. Combined with a depth camera, this algorithm allows an industrial robot to understand complex stacked scenes. We improve the pose estimation accuracy in order to assemble parts with robot grasping, without an additional pose adjuster. Our network can learn from a synthetic dataset and apply it to real-world data, without a significant accuracy drop. The synthetic dataset can be obtained easily by computer simulation programs, so the training data are sufficient. Experiments demonstrate that our method outperforms the state-of-the-art pose estimation approaches." @default.
• W3200318260 created "2021-09-27" @default.
• W3200318260 creator A5029947227 @default.
• W3200318260 creator A5033940457 @default.
• W3200318260 creator A5046890485 @default.
• W3200318260 creator A5057629968 @default.
• W3200318260 date "2022-10-01" @default.
• W3200318260 modified "2023-10-16" @default.
• W3200318260 title "PPR-Net++: Accurate 6-D Pose Estimation in Stacked Scenarios" @default.
• W3200318260 cites W1969868017 @default.
• W3200318260 cites W2013995856 @default.
• W3200318260 cites W2033574012 @default.
• W3200318260 cites W2052789223 @default.
• W3200318260 cites W2067191022 @default.
• W3200318260 cites W2082511574 @default.
• W3200318260 cites W2084450672 @default.
• W3200318260 cites W2161168419 @default.
• W3200318260 cites W2400577036 @default.
• W3200318260 cites W2560609797 @default.
• W3200318260 cites W2584009249 @default.
• W3200318260 cites W2600447016 @default.
• W3200318260 cites W2605102758 @default.
• W3200318260 cites W2769312834 @default.
• W3200318260 cites W2806070179 @default.
• W3200318260 cites W2915251461 @default.
• W3200318260 cites W2963158438 @default.
• W3200318260 cites W2963188159 @default.
• W3200318260 cites W2963390419 @default.
• W3200318260 cites W2963727135 @default.
• W3200318260 cites W2963729424 @default.
• W3200318260 cites W2964249569 @default.
• W3200318260 cites W2966885779 @default.
• W3200318260 cites W3003215308 @default.
• W3200318260 cites W3034986117 @default.
• W3200318260 cites W3088158297 @default.
• W3200318260 cites W3089979088 @default.
• W3200318260 cites W3100901148 @default.
• W3200318260 cites W3102010291 @default.
• W3200318260 cites W62794737 @default.
• W3200318260 doi "https://doi.org/10.1109/tase.2021.3108800" @default.
• W3200318260 hasPublicationYear "2022" @default.
• W3200318260 type Work @default.
• W3200318260 sameAs 3200318260 @default.
• W3200318260 citedByCount "5" @default.
• W3200318260 countsByYear W32003182602021 @default.
• W3200318260 countsByYear W32003182602022 @default.
• W3200318260 countsByYear W32003182602023 @default.
• W3200318260 crossrefType "journal-article" @default.
• W3200318260 hasAuthorship W3200318260A5029947227 @default.
• W3200318260 hasAuthorship W3200318260A5033940457 @default.
• W3200318260 hasAuthorship W3200318260A5046890485 @default.
• W3200318260 hasAuthorship W3200318260A5057629968 @default.
• W3200318260 hasConcept C119857082 @default.
• W3200318260 hasConcept C124101348 @default.
• W3200318260 hasConcept C146599234 @default.
• W3200318260 hasConcept C153180895 @default.
• W3200318260 hasConcept C154945302 @default.
• W3200318260 hasConcept C31972630 @default.
• W3200318260 hasConcept C41008148 @default.
• W3200318260 hasConcept C52102323 @default.
• W3200318260 hasConcept C73555534 @default.
• W3200318260 hasConcept C774472 @default.
• W3200318260 hasConceptScore W3200318260C119857082 @default.
• W3200318260 hasConceptScore W3200318260C124101348 @default.
• W3200318260 hasConceptScore W3200318260C146599234 @default.
• W3200318260 hasConceptScore W3200318260C153180895 @default.
• W3200318260 hasConceptScore W3200318260C154945302 @default.
• W3200318260 hasConceptScore W3200318260C31972630 @default.
• W3200318260 hasConceptScore W3200318260C41008148 @default.
• W3200318260 hasConceptScore W3200318260C52102323 @default.
• W3200318260 hasConceptScore W3200318260C73555534 @default.
• W3200318260 hasConceptScore W3200318260C774472 @default.
• W3200318260 hasFunder F4320321001 @default.
• W3200318260 hasIssue "4" @default.
• W3200318260 hasLocation W32003182601 @default.
• W3200318260 hasOpenAccess W3200318260 @default.
• W3200318260 hasPrimaryLocation W32003182601 @default.
• W3200318260 hasRelatedWork W1583866266 @default.
• W3200318260 hasRelatedWork W2002351209 @default.
• W3200318260 hasRelatedWork W2007009951 @default.
• W3200318260 hasRelatedWork W2082644203 @default.
• W3200318260 hasRelatedWork W2104220356 @default.
• W3200318260 hasRelatedWork W2350539780 @default.
• W3200318260 hasRelatedWork W2381926679 @default.
• W3200318260 hasRelatedWork W2611300636 @default.
• W3200318260 hasRelatedWork W3122652148 @default.
• W3200318260 hasRelatedWork W3165040664 @default.
• W3200318260 hasVolume "19" @default.
• W3200318260 isParatext "false" @default.
• W3200318260 isRetracted "false" @default.
• W3200318260 magId "3200318260" @default.
• W3200318260 workType "article" @default.