Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367281358> ?p ?o ?g. }
- W4367281358 endingPage "12" @default.
- W4367281358 startingPage "1" @default.
- W4367281358 abstract "3D object detection with LiDAR point clouds is a challenging problem which requires 3D scene understanding, yet this task is critical to autonomous driving. Existing voxel-based 3D object detectors are becoming increasingly popular but have several shortcomings. For example, during voxelization, features of distant sparse point clouds are largely discarded, which leads to the missing detection of objects. Additionally, the correlation of points between voxels and the importance of different voxels within a region are not well learned. Therefore, we present a robust network (VP-Net) that views voxels as points to accurately detect 3D objects in LiDAR point clouds and can capture objects’ internal relationships. 3D CNN processing shows the output features of VP-Net as key points. The relationship between key points is then constructed into local graphs to enhance object feature extraction via a self-attention mechanism. Finally, the Euclidean distance between the extracted features guides our model’s weight reassignment for strengthening the importance of neighbor points, thereby enhancing the internal feature aggregation of objects. Experiments on KITTI and nuScenes 3D object detection benchmarks demonstrate the efficiency of enhancing inter-voxel validity within object features and show that the proposed VP-Net can achieve state-of-the-art performance." @default.
- W4367281358 created "2023-04-29" @default.
- W4367281358 creator A5014656305 @default.
- W4367281358 creator A5035291955 @default.
- W4367281358 creator A5060187904 @default.
- W4367281358 creator A5085282915 @default.
- W4367281358 creator A5089966579 @default.
- W4367281358 creator A5059748640 @default.
- W4367281358 date "2023-01-01" @default.
- W4367281358 modified "2023-10-16" @default.
- W4367281358 title "VP-Net: Voxels as Points for 3-D Object Detection" @default.
- W4367281358 cites W2150066425 @default.
- W4367281358 cites W2560609797 @default.
- W4367281358 cites W2897529137 @default.
- W4367281358 cites W2911486422 @default.
- W4367281358 cites W2949708697 @default.
- W4367281358 cites W2963727135 @default.
- W4367281358 cites W2964062501 @default.
- W4367281358 cites W2968296999 @default.
- W4367281358 cites W2981949127 @default.
- W4367281358 cites W2982363097 @default.
- W4367281358 cites W2997814983 @default.
- W4367281358 cites W2998254148 @default.
- W4367281358 cites W3003618643 @default.
- W4367281358 cites W3004351857 @default.
- W4367281358 cites W3008105217 @default.
- W4367281358 cites W3033591146 @default.
- W4367281358 cites W3034314779 @default.
- W4367281358 cites W3034494113 @default.
- W4367281358 cites W3034681945 @default.
- W4367281358 cites W3035346742 @default.
- W4367281358 cites W3035461736 @default.
- W4367281358 cites W3035574168 @default.
- W4367281358 cites W3107422826 @default.
- W4367281358 cites W3107819843 @default.
- W4367281358 cites W3108884723 @default.
- W4367281358 cites W3113028524 @default.
- W4367281358 cites W3118341329 @default.
- W4367281358 cites W3167095230 @default.
- W4367281358 cites W3167732492 @default.
- W4367281358 cites W3176287975 @default.
- W4367281358 cites W3177276051 @default.
- W4367281358 cites W3205005447 @default.
- W4367281358 cites W3207921941 @default.
- W4367281358 cites W3215100485 @default.
- W4367281358 cites W4214558638 @default.
- W4367281358 cites W4285139068 @default.
- W4367281358 cites W4312934050 @default.
- W4367281358 doi "https://doi.org/10.1109/tgrs.2023.3271020" @default.
- W4367281358 hasPublicationYear "2023" @default.
- W4367281358 type Work @default.
- W4367281358 citedByCount "1" @default.
- W4367281358 crossrefType "journal-article" @default.
- W4367281358 hasAuthorship W4367281358A5014656305 @default.
- W4367281358 hasAuthorship W4367281358A5035291955 @default.
- W4367281358 hasAuthorship W4367281358A5059748640 @default.
- W4367281358 hasAuthorship W4367281358A5060187904 @default.
- W4367281358 hasAuthorship W4367281358A5085282915 @default.
- W4367281358 hasAuthorship W4367281358A5089966579 @default.
- W4367281358 hasConcept C129782007 @default.
- W4367281358 hasConcept C131979681 @default.
- W4367281358 hasConcept C138885662 @default.
- W4367281358 hasConcept C153180895 @default.
- W4367281358 hasConcept C154945302 @default.
- W4367281358 hasConcept C205649164 @default.
- W4367281358 hasConcept C2524010 @default.
- W4367281358 hasConcept C26517878 @default.
- W4367281358 hasConcept C2776151529 @default.
- W4367281358 hasConcept C2776401178 @default.
- W4367281358 hasConcept C2781238097 @default.
- W4367281358 hasConcept C28719098 @default.
- W4367281358 hasConcept C31972630 @default.
- W4367281358 hasConcept C33923547 @default.
- W4367281358 hasConcept C38652104 @default.
- W4367281358 hasConcept C41008148 @default.
- W4367281358 hasConcept C41895202 @default.
- W4367281358 hasConcept C51399673 @default.
- W4367281358 hasConcept C52622490 @default.
- W4367281358 hasConcept C54170458 @default.
- W4367281358 hasConcept C62649853 @default.
- W4367281358 hasConceptScore W4367281358C129782007 @default.
- W4367281358 hasConceptScore W4367281358C131979681 @default.
- W4367281358 hasConceptScore W4367281358C138885662 @default.
- W4367281358 hasConceptScore W4367281358C153180895 @default.
- W4367281358 hasConceptScore W4367281358C154945302 @default.
- W4367281358 hasConceptScore W4367281358C205649164 @default.
- W4367281358 hasConceptScore W4367281358C2524010 @default.
- W4367281358 hasConceptScore W4367281358C26517878 @default.
- W4367281358 hasConceptScore W4367281358C2776151529 @default.
- W4367281358 hasConceptScore W4367281358C2776401178 @default.
- W4367281358 hasConceptScore W4367281358C2781238097 @default.
- W4367281358 hasConceptScore W4367281358C28719098 @default.
- W4367281358 hasConceptScore W4367281358C31972630 @default.
- W4367281358 hasConceptScore W4367281358C33923547 @default.
- W4367281358 hasConceptScore W4367281358C38652104 @default.
- W4367281358 hasConceptScore W4367281358C41008148 @default.
- W4367281358 hasConceptScore W4367281358C41895202 @default.
- W4367281358 hasConceptScore W4367281358C51399673 @default.