Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136191271> ?p ?o ?g. }
- W3136191271 abstract "Autonomous driving vehicles and robotic systems rely on accurate perception of their surroundings. Scene understanding is one of the crucial components of perception modules. Among all available sensors, LiDARs are one of the essential sensing modalities of autonomous driving systems due to their active sensing nature with high resolution of sensor readings. Accurate and fast semantic segmentation methods are needed to fully utilize LiDAR sensors for scene understanding. In this paper, we present Lite-HDSeg, a novel real-time convolutional neural network for semantic segmentation of full $3$D LiDAR point clouds. Lite-HDSeg can achieve the best accuracy vs. computational complexity trade-off in SemanticKitti benchmark and is designed on the basis of a new encoder-decoder architecture with light-weight harmonic dense convolutions as its core. Moreover, we introduce ICM, an improved global contextual module to capture multi-scale contextual features, and MCSPN, a multi-class Spatial Propagation Network to further refine the semantic boundaries. Our experimental results show that the proposed method outperforms state-of-the-art semantic segmentation approaches which can run real-time, thus is suitable for robotic and autonomous driving applications." @default.
- W3136191271 created "2021-03-29" @default.
- W3136191271 creator A5004036087 @default.
- W3136191271 creator A5004384330 @default.
- W3136191271 creator A5005698588 @default.
- W3136191271 creator A5075399292 @default.
- W3136191271 date "2021-03-16" @default.
- W3136191271 modified "2023-09-27" @default.
- W3136191271 title "Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions" @default.
- W3136191271 cites W1901129140 @default.
- W3136191271 cites W2194775991 @default.
- W3136191271 cites W2279098554 @default.
- W3136191271 cites W2507319753 @default.
- W3136191271 cites W2531409750 @default.
- W3136191271 cites W2549139847 @default.
- W3136191271 cites W2560609797 @default.
- W3136191271 cites W2795587607 @default.
- W3136191271 cites W2796647784 @default.
- W3136191271 cites W2962766617 @default.
- W3136191271 cites W2962912109 @default.
- W3136191271 cites W2963121255 @default.
- W3136191271 cites W2963125977 @default.
- W3136191271 cites W2963226018 @default.
- W3136191271 cites W2963281829 @default.
- W3136191271 cites W2963331974 @default.
- W3136191271 cites W2963446712 @default.
- W3136191271 cites W2963640720 @default.
- W3136191271 cites W2963759070 @default.
- W3136191271 cites W2963840672 @default.
- W3136191271 cites W2968557240 @default.
- W3136191271 cites W2981199548 @default.
- W3136191271 cites W2987175876 @default.
- W3136191271 cites W2990613095 @default.
- W3136191271 cites W2991084087 @default.
- W3136191271 cites W2991216808 @default.
- W3136191271 cites W2995208943 @default.
- W3136191271 cites W3003437478 @default.
- W3136191271 cites W3008942546 @default.
- W3136191271 cites W3010492813 @default.
- W3136191271 cites W3014448914 @default.
- W3136191271 cites W3035275207 @default.
- W3136191271 cites W3045034239 @default.
- W3136191271 cites W3047223011 @default.
- W3136191271 cites W3090146708 @default.
- W3136191271 cites W3109154950 @default.
- W3136191271 cites W3120926185 @default.
- W3136191271 doi "https://doi.org/10.48550/arxiv.2103.08852" @default.
- W3136191271 hasPublicationYear "2021" @default.
- W3136191271 type Work @default.
- W3136191271 sameAs 3136191271 @default.
- W3136191271 citedByCount "0" @default.
- W3136191271 crossrefType "posted-content" @default.
- W3136191271 hasAuthorship W3136191271A5004036087 @default.
- W3136191271 hasAuthorship W3136191271A5004384330 @default.
- W3136191271 hasAuthorship W3136191271A5005698588 @default.
- W3136191271 hasAuthorship W3136191271A5075399292 @default.
- W3136191271 hasBestOaLocation W31361912711 @default.
- W3136191271 hasConcept C111919701 @default.
- W3136191271 hasConcept C118505674 @default.
- W3136191271 hasConcept C131979681 @default.
- W3136191271 hasConcept C13280743 @default.
- W3136191271 hasConcept C154945302 @default.
- W3136191271 hasConcept C185798385 @default.
- W3136191271 hasConcept C205649164 @default.
- W3136191271 hasConcept C31972630 @default.
- W3136191271 hasConcept C41008148 @default.
- W3136191271 hasConcept C45347329 @default.
- W3136191271 hasConcept C50644808 @default.
- W3136191271 hasConcept C51399673 @default.
- W3136191271 hasConcept C62649853 @default.
- W3136191271 hasConcept C81363708 @default.
- W3136191271 hasConcept C89600930 @default.
- W3136191271 hasConceptScore W3136191271C111919701 @default.
- W3136191271 hasConceptScore W3136191271C118505674 @default.
- W3136191271 hasConceptScore W3136191271C131979681 @default.
- W3136191271 hasConceptScore W3136191271C13280743 @default.
- W3136191271 hasConceptScore W3136191271C154945302 @default.
- W3136191271 hasConceptScore W3136191271C185798385 @default.
- W3136191271 hasConceptScore W3136191271C205649164 @default.
- W3136191271 hasConceptScore W3136191271C31972630 @default.
- W3136191271 hasConceptScore W3136191271C41008148 @default.
- W3136191271 hasConceptScore W3136191271C45347329 @default.
- W3136191271 hasConceptScore W3136191271C50644808 @default.
- W3136191271 hasConceptScore W3136191271C51399673 @default.
- W3136191271 hasConceptScore W3136191271C62649853 @default.
- W3136191271 hasConceptScore W3136191271C81363708 @default.
- W3136191271 hasConceptScore W3136191271C89600930 @default.
- W3136191271 hasLocation W31361912711 @default.
- W3136191271 hasOpenAccess W3136191271 @default.
- W3136191271 hasPrimaryLocation W31361912711 @default.
- W3136191271 hasRelatedWork W2517104666 @default.
- W3136191271 hasRelatedWork W2965803762 @default.
- W3136191271 hasRelatedWork W3169001153 @default.
- W3136191271 hasRelatedWork W4214536195 @default.
- W3136191271 hasRelatedWork W4224103868 @default.
- W3136191271 hasRelatedWork W4226195147 @default.
- W3136191271 hasRelatedWork W4238992361 @default.
- W3136191271 hasRelatedWork W4288376449 @default.
- W3136191271 hasRelatedWork W4312418565 @default.
- W3136191271 hasRelatedWork W4318751999 @default.