Matches in SemOpenAlex for { <https://semopenalex.org/work/W3135859438> ?p ?o ?g. }
- W3135859438 abstract "Understanding and interpreting a 3d environment is a key challenge for autonomous vehicles. Semantic segmentation of 3d point clouds combines 3d information with semantics and thereby provides a valuable contribution to this task. In many real-world applications, point clouds are generated by lidar sensors in a consecutive fashion. Working with a time series instead of single and independent frames enables the exploitation of temporal information. We therefore propose a recurrent segmentation architecture (RNN), which takes a single range image frame as input and exploits recursively aggregated temporal information. An alignment strategy, which we call Temporal Memory Alignment, uses ego motion to temporally align the memory between consecutive frames in feature space. A Residual Network and ConvGRU are investigated for the memory update. We demonstrate the benefits of the presented approach on two large-scale datasets and compare it to several stateof-the-art methods. Our approach ranks first on the SemanticKITTI multiple scan benchmark and achieves state-of-the-art performance on the single scan benchmark. In addition, the evaluation shows that the exploitation of temporal information significantly improves segmentation results compared to a single frame approach." @default.
- W3135859438 created "2021-03-15" @default.
- W3135859438 creator A5001570322 @default.
- W3135859438 creator A5025754260 @default.
- W3135859438 creator A5045549799 @default.
- W3135859438 creator A5050681793 @default.
- W3135859438 date "2021-03-03" @default.
- W3135859438 modified "2023-09-23" @default.
- W3135859438 title "LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment" @default.
- W3135859438 cites W1924770834 @default.
- W3135859438 cites W2057653135 @default.
- W3135859438 cites W2064675550 @default.
- W3135859438 cites W2150066425 @default.
- W3135859438 cites W2180092181 @default.
- W3135859438 cites W2460657278 @default.
- W3135859438 cites W2552900565 @default.
- W3135859438 cites W2560609797 @default.
- W3135859438 cites W2788158258 @default.
- W3135859438 cites W2795587607 @default.
- W3135859438 cites W2796347433 @default.
- W3135859438 cites W2797997528 @default.
- W3135859438 cites W2890441886 @default.
- W3135859438 cites W2896992394 @default.
- W3135859438 cites W2902302021 @default.
- W3135859438 cites W2949117887 @default.
- W3135859438 cites W2949558113 @default.
- W3135859438 cites W2949650786 @default.
- W3135859438 cites W2950635152 @default.
- W3135859438 cites W2962815021 @default.
- W3135859438 cites W2962912109 @default.
- W3135859438 cites W2963120444 @default.
- W3135859438 cites W2963121255 @default.
- W3135859438 cites W2963125977 @default.
- W3135859438 cites W2963226018 @default.
- W3135859438 cites W2963323244 @default.
- W3135859438 cites W2964076878 @default.
- W3135859438 cites W2964257316 @default.
- W3135859438 cites W2990613095 @default.
- W3135859438 cites W2991216808 @default.
- W3135859438 cites W2995208943 @default.
- W3135859438 cites W3003437478 @default.
- W3135859438 cites W3008942546 @default.
- W3135859438 cites W3012494314 @default.
- W3135859438 cites W3034486798 @default.
- W3135859438 cites W3035275207 @default.
- W3135859438 cites W3035617611 @default.
- W3135859438 cites W3035750285 @default.
- W3135859438 cites W3109944402 @default.
- W3135859438 hasPublicationYear "2021" @default.
- W3135859438 type Work @default.
- W3135859438 sameAs 3135859438 @default.
- W3135859438 citedByCount "0" @default.
- W3135859438 crossrefType "posted-content" @default.
- W3135859438 hasAuthorship W3135859438A5001570322 @default.
- W3135859438 hasAuthorship W3135859438A5025754260 @default.
- W3135859438 hasAuthorship W3135859438A5045549799 @default.
- W3135859438 hasAuthorship W3135859438A5050681793 @default.
- W3135859438 hasConcept C11413529 @default.
- W3135859438 hasConcept C126042441 @default.
- W3135859438 hasConcept C131979681 @default.
- W3135859438 hasConcept C13280743 @default.
- W3135859438 hasConcept C138885662 @default.
- W3135859438 hasConcept C147168706 @default.
- W3135859438 hasConcept C153180895 @default.
- W3135859438 hasConcept C154945302 @default.
- W3135859438 hasConcept C155512373 @default.
- W3135859438 hasConcept C162324750 @default.
- W3135859438 hasConcept C165696696 @default.
- W3135859438 hasConcept C184337299 @default.
- W3135859438 hasConcept C185798385 @default.
- W3135859438 hasConcept C187736073 @default.
- W3135859438 hasConcept C199360897 @default.
- W3135859438 hasConcept C205649164 @default.
- W3135859438 hasConcept C26517878 @default.
- W3135859438 hasConcept C2776401178 @default.
- W3135859438 hasConcept C2780451532 @default.
- W3135859438 hasConcept C31972630 @default.
- W3135859438 hasConcept C38652104 @default.
- W3135859438 hasConcept C41008148 @default.
- W3135859438 hasConcept C41895202 @default.
- W3135859438 hasConcept C50644808 @default.
- W3135859438 hasConcept C51399673 @default.
- W3135859438 hasConcept C62649853 @default.
- W3135859438 hasConcept C76155785 @default.
- W3135859438 hasConcept C89600930 @default.
- W3135859438 hasConceptScore W3135859438C11413529 @default.
- W3135859438 hasConceptScore W3135859438C126042441 @default.
- W3135859438 hasConceptScore W3135859438C131979681 @default.
- W3135859438 hasConceptScore W3135859438C13280743 @default.
- W3135859438 hasConceptScore W3135859438C138885662 @default.
- W3135859438 hasConceptScore W3135859438C147168706 @default.
- W3135859438 hasConceptScore W3135859438C153180895 @default.
- W3135859438 hasConceptScore W3135859438C154945302 @default.
- W3135859438 hasConceptScore W3135859438C155512373 @default.
- W3135859438 hasConceptScore W3135859438C162324750 @default.
- W3135859438 hasConceptScore W3135859438C165696696 @default.
- W3135859438 hasConceptScore W3135859438C184337299 @default.
- W3135859438 hasConceptScore W3135859438C185798385 @default.
- W3135859438 hasConceptScore W3135859438C187736073 @default.
- W3135859438 hasConceptScore W3135859438C199360897 @default.