Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214536678> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4214536678 endingPage "1176" @default.
- W4214536678 startingPage "1176" @default.
- W4214536678 abstract "The point clouds scanned by lidar are generally sparse, which can result in fewer sampling points of objects. To perform precise and effective 3D object detection, it is necessary to improve the feature representation ability to extract more feature information of the object points. Therefore, we propose an adaptive feature enhanced 3D object detection network based on point clouds (AFE-RCNN). AFE-RCNN is a point-voxel integrated network. We first voxelize the raw point clouds and obtain the voxel features through the 3D voxel convolutional neural network. Then, the 3D feature vectors are projected to the 2D bird’s eye view (BEV), and the relationship between the features in both spatial dimension and channel dimension is learned by the proposed residual of dual attention proposal generation module. The high-quality 3D box proposals are generated based on the BEV features and anchor-based approach. Next, we sample key points from raw point clouds to summarize the information of the voxel features, and obtain the key point features by the multi-scale feature extraction module based on adaptive feature adjustment. The neighboring contextual information is integrated into each key point through this module, and the robustness of feature processing is also guaranteed. Lastly, we aggregate the features of the BEV, voxels, and point clouds as the key point features that are used for proposal refinement. In addition, to ensure the correlation among the vertices of the bounding box, we propose a refinement loss function module with vertex associativity. Our AFE-RCNN exhibits comparable performance on the KITTI dataset and Waymo open dataset to state-of-the-art methods. On the KITTI 3D detection benchmark, for the moderate difficulty level of the car and the cyclist classes, the 3D detection mean average precisions of AFE-RCNN can reach 81.53% and 67.50%, respectively." @default.
- W4214536678 created "2022-03-02" @default.
- W4214536678 creator A5008177360 @default.
- W4214536678 creator A5062793914 @default.
- W4214536678 creator A5065706194 @default.
- W4214536678 creator A5068014633 @default.
- W4214536678 creator A5069025128 @default.
- W4214536678 date "2022-02-27" @default.
- W4214536678 modified "2023-09-26" @default.
- W4214536678 title "AFE-RCNN: Adaptive Feature Enhancement RCNN for 3D Object Detection" @default.
- W4214536678 cites W1988115241 @default.
- W4214536678 cites W2115579991 @default.
- W4214536678 cites W2897529137 @default.
- W4214536678 cites W2979750740 @default.
- W4214536678 cites W2980547801 @default.
- W4214536678 cites W2997495697 @default.
- W4214536678 cites W3008105217 @default.
- W4214536678 cites W3013604743 @default.
- W4214536678 cites W3022285594 @default.
- W4214536678 cites W3129605393 @default.
- W4214536678 cites W3175262579 @default.
- W4214536678 cites W3188046901 @default.
- W4214536678 doi "https://doi.org/10.3390/rs14051176" @default.
- W4214536678 hasPublicationYear "2022" @default.
- W4214536678 type Work @default.
- W4214536678 citedByCount "3" @default.
- W4214536678 countsByYear W42145366782022 @default.
- W4214536678 countsByYear W42145366782023 @default.
- W4214536678 crossrefType "journal-article" @default.
- W4214536678 hasAuthorship W4214536678A5008177360 @default.
- W4214536678 hasAuthorship W4214536678A5062793914 @default.
- W4214536678 hasAuthorship W4214536678A5065706194 @default.
- W4214536678 hasAuthorship W4214536678A5068014633 @default.
- W4214536678 hasAuthorship W4214536678A5069025128 @default.
- W4214536678 hasBestOaLocation W42145366781 @default.
- W4214536678 hasConcept C115961682 @default.
- W4214536678 hasConcept C131979681 @default.
- W4214536678 hasConcept C138885662 @default.
- W4214536678 hasConcept C147037132 @default.
- W4214536678 hasConcept C153180895 @default.
- W4214536678 hasConcept C154945302 @default.
- W4214536678 hasConcept C2776151529 @default.
- W4214536678 hasConcept C2776401178 @default.
- W4214536678 hasConcept C31972630 @default.
- W4214536678 hasConcept C41008148 @default.
- W4214536678 hasConcept C41895202 @default.
- W4214536678 hasConcept C52622490 @default.
- W4214536678 hasConcept C53533937 @default.
- W4214536678 hasConcept C54170458 @default.
- W4214536678 hasConceptScore W4214536678C115961682 @default.
- W4214536678 hasConceptScore W4214536678C131979681 @default.
- W4214536678 hasConceptScore W4214536678C138885662 @default.
- W4214536678 hasConceptScore W4214536678C147037132 @default.
- W4214536678 hasConceptScore W4214536678C153180895 @default.
- W4214536678 hasConceptScore W4214536678C154945302 @default.
- W4214536678 hasConceptScore W4214536678C2776151529 @default.
- W4214536678 hasConceptScore W4214536678C2776401178 @default.
- W4214536678 hasConceptScore W4214536678C31972630 @default.
- W4214536678 hasConceptScore W4214536678C41008148 @default.
- W4214536678 hasConceptScore W4214536678C41895202 @default.
- W4214536678 hasConceptScore W4214536678C52622490 @default.
- W4214536678 hasConceptScore W4214536678C53533937 @default.
- W4214536678 hasConceptScore W4214536678C54170458 @default.
- W4214536678 hasFunder F4320321001 @default.
- W4214536678 hasIssue "5" @default.
- W4214536678 hasLocation W42145366781 @default.
- W4214536678 hasLocation W42145366782 @default.
- W4214536678 hasOpenAccess W4214536678 @default.
- W4214536678 hasPrimaryLocation W42145366781 @default.
- W4214536678 hasRelatedWork W1892011953 @default.
- W4214536678 hasRelatedWork W1986586280 @default.
- W4214536678 hasRelatedWork W2380902646 @default.
- W4214536678 hasRelatedWork W2546942002 @default.
- W4214536678 hasRelatedWork W2550539038 @default.
- W4214536678 hasRelatedWork W2766547489 @default.
- W4214536678 hasRelatedWork W2767563364 @default.
- W4214536678 hasRelatedWork W3015973434 @default.
- W4214536678 hasRelatedWork W3177497967 @default.
- W4214536678 hasRelatedWork W3211653591 @default.
- W4214536678 hasVolume "14" @default.
- W4214536678 isParatext "false" @default.
- W4214536678 isRetracted "false" @default.
- W4214536678 workType "article" @default.