Matches in SemOpenAlex for { <https://semopenalex.org/work/W3022983882> ?p ?o ?g. }
- W3022983882 abstract "Detecting persons using a 2D LiDAR is a challenging task due to the low information content of 2D range data. To alleviate the problem caused by the sparsity of the LiDAR points, current state-of-the-art methods fuse multiple previous scans and perform detection using the combined scans. The downside of such a backward looking fusion is that all the scans need to be aligned explicitly, and the necessary alignment operation makes the whole pipeline more expensive -- often too expensive for real-world applications. In this paper, we propose a person detection network which uses an alternative strategy to combine scans obtained at different times. Our method, Distance Robust SPatial Attention and Auto-regressive Model (DR-SPAAM), follows a forward looking paradigm. It keeps the intermediate features from the backbone network as a template and recurrently updates the template when a new scan becomes available. The updated feature template is in turn used for detecting persons currently in the scene. On the DROW dataset, our method outperforms the existing state-of-the-art, while being approximately four times faster, running at 87.2 FPS on a laptop with a dedicated GPU and at 22.6 FPS on an NVIDIA Jetson AGX embedded GPU. We release our code in PyTorch and a ROS node including pre-trained models." @default.
- W3022983882 created "2020-05-13" @default.
- W3022983882 creator A5035393218 @default.
- W3022983882 creator A5071006649 @default.
- W3022983882 creator A5071563379 @default.
- W3022983882 date "2020-04-29" @default.
- W3022983882 modified "2023-09-24" @default.
- W3022983882 title "DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data" @default.
- W3022983882 cites W1536680647 @default.
- W3022983882 cites W1578421573 @default.
- W3022983882 cites W2111957821 @default.
- W3022983882 cites W2113207845 @default.
- W3022983882 cites W2282391807 @default.
- W3022983882 cites W2337890890 @default.
- W3022983882 cites W2512784927 @default.
- W3022983882 cites W2555618208 @default.
- W3022983882 cites W2560609797 @default.
- W3022983882 cites W2653246566 @default.
- W3022983882 cites W2780608998 @default.
- W3022983882 cites W2793130599 @default.
- W3022983882 cites W2796347433 @default.
- W3022983882 cites W2796372625 @default.
- W3022983882 cites W2897529137 @default.
- W3022983882 cites W2898044248 @default.
- W3022983882 cites W2949708697 @default.
- W3022983882 cites W2962855257 @default.
- W3022983882 cites W2963121255 @default.
- W3022983882 cites W2963125977 @default.
- W3022983882 cites W2963150697 @default.
- W3022983882 cites W2963171508 @default.
- W3022983882 cites W2963182550 @default.
- W3022983882 cites W2963400571 @default.
- W3022983882 cites W2963403868 @default.
- W3022983882 cites W2963653352 @default.
- W3022983882 cites W2963727135 @default.
- W3022983882 cites W2964062501 @default.
- W3022983882 cites W2964286567 @default.
- W3022983882 cites W2968296999 @default.
- W3022983882 cites W2969987486 @default.
- W3022983882 cites W2979750740 @default.
- W3022983882 cites W2981949127 @default.
- W3022983882 cites W2988715931 @default.
- W3022983882 cites W2994810768 @default.
- W3022983882 cites W3003618643 @default.
- W3022983882 cites W3034430142 @default.
- W3022983882 cites W3089444959 @default.
- W3022983882 cites W3100935401 @default.
- W3022983882 doi "https://doi.org/10.48550/arxiv.2004.14079" @default.
- W3022983882 hasPublicationYear "2020" @default.
- W3022983882 type Work @default.
- W3022983882 sameAs 3022983882 @default.
- W3022983882 citedByCount "0" @default.
- W3022983882 crossrefType "posted-content" @default.
- W3022983882 hasAuthorship W3022983882A5035393218 @default.
- W3022983882 hasAuthorship W3022983882A5071006649 @default.
- W3022983882 hasAuthorship W3022983882A5071563379 @default.
- W3022983882 hasBestOaLocation W30229838821 @default.
- W3022983882 hasConcept C111919701 @default.
- W3022983882 hasConcept C119599485 @default.
- W3022983882 hasConcept C127313418 @default.
- W3022983882 hasConcept C127413603 @default.
- W3022983882 hasConcept C138885662 @default.
- W3022983882 hasConcept C141353440 @default.
- W3022983882 hasConcept C153180895 @default.
- W3022983882 hasConcept C154945302 @default.
- W3022983882 hasConcept C159985019 @default.
- W3022983882 hasConcept C162324750 @default.
- W3022983882 hasConcept C187736073 @default.
- W3022983882 hasConcept C192562407 @default.
- W3022983882 hasConcept C199360897 @default.
- W3022983882 hasConcept C204323151 @default.
- W3022983882 hasConcept C2776401178 @default.
- W3022983882 hasConcept C2780008327 @default.
- W3022983882 hasConcept C2780451532 @default.
- W3022983882 hasConcept C31972630 @default.
- W3022983882 hasConcept C41008148 @default.
- W3022983882 hasConcept C41895202 @default.
- W3022983882 hasConcept C43521106 @default.
- W3022983882 hasConcept C51399673 @default.
- W3022983882 hasConcept C62611344 @default.
- W3022983882 hasConcept C62649853 @default.
- W3022983882 hasConcept C66938386 @default.
- W3022983882 hasConceptScore W3022983882C111919701 @default.
- W3022983882 hasConceptScore W3022983882C119599485 @default.
- W3022983882 hasConceptScore W3022983882C127313418 @default.
- W3022983882 hasConceptScore W3022983882C127413603 @default.
- W3022983882 hasConceptScore W3022983882C138885662 @default.
- W3022983882 hasConceptScore W3022983882C141353440 @default.
- W3022983882 hasConceptScore W3022983882C153180895 @default.
- W3022983882 hasConceptScore W3022983882C154945302 @default.
- W3022983882 hasConceptScore W3022983882C159985019 @default.
- W3022983882 hasConceptScore W3022983882C162324750 @default.
- W3022983882 hasConceptScore W3022983882C187736073 @default.
- W3022983882 hasConceptScore W3022983882C192562407 @default.
- W3022983882 hasConceptScore W3022983882C199360897 @default.
- W3022983882 hasConceptScore W3022983882C204323151 @default.
- W3022983882 hasConceptScore W3022983882C2776401178 @default.
- W3022983882 hasConceptScore W3022983882C2780008327 @default.
- W3022983882 hasConceptScore W3022983882C2780451532 @default.
- W3022983882 hasConceptScore W3022983882C31972630 @default.