Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380050110> ?p ?o ?g. }
- W4380050110 endingPage "2986" @default.
- W4380050110 startingPage "2986" @default.
- W4380050110 abstract "In autonomous driving, LiDAR (light detection and ranging) data are acquired over time. Most existing 3D object detection algorithms propose the object bounding box by processing each frame of data independently, which ignores the temporal sequence information. However, the temporal sequence information is usually helpful to detect the object with missing shape information due to long distance or occlusion. To address this problem, we propose a temporal sequence information fusion 3D point cloud object detection algorithm based on the Ada-GRU (adaptive gated recurrent unit). In this method, the feature of each frame for the LiDAR point cloud is extracted through the backbone network and is fed to the Ada-GRU together with the hidden features of the previous frames. Compared to the traditional GRU, the Ada-GRU can adjust the gating mechanism adaptively during the training process by introducing the adaptive activation function. The Ada-GRU outputs the temporal sequence fusion features to predict the 3D object in the current frame and transmits the hidden features of the current frame to the next frame. At the same time, the label uncertainty of the distant and occluded objects affects the training effect of the model. For this problem, this paper proposes a probability distribution model of 3D bounding box coordinates based on the Gaussian distribution function and designs the corresponding bounding box loss function to enable the model to learn and estimate the uncertainty of the positioning of the bounding box coordinates, so as to remove the bounding box with large positioning uncertainty in the post-processing stage to reduce the false positive rate. Finally, the experiments show that the methods proposed in this paper improve the accuracy of the object detection without significantly increasing the complexity of the algorithm." @default.
- W4380050110 created "2023-06-10" @default.
- W4380050110 creator A5022045896 @default.
- W4380050110 creator A5026288596 @default.
- W4380050110 creator A5034620195 @default.
- W4380050110 creator A5086624383 @default.
- W4380050110 creator A5090156119 @default.
- W4380050110 date "2023-06-08" @default.
- W4380050110 modified "2023-10-11" @default.
- W4380050110 title "3D Point Cloud Object Detection Algorithm Based on Temporal Information Fusion and Uncertainty Estimation" @default.
- W4380050110 cites W2031489346 @default.
- W4380050110 cites W2157331557 @default.
- W4380050110 cites W2566079294 @default.
- W4380050110 cites W2767094803 @default.
- W4380050110 cites W2793130599 @default.
- W4380050110 cites W2897529137 @default.
- W4380050110 cites W2948551291 @default.
- W4380050110 cites W2949708697 @default.
- W4380050110 cites W2949888942 @default.
- W4380050110 cites W2963167203 @default.
- W4380050110 cites W2963727135 @default.
- W4380050110 cites W2968296999 @default.
- W4380050110 cites W2970594690 @default.
- W4380050110 cites W2981958729 @default.
- W4380050110 cites W3000681136 @default.
- W4380050110 cites W3035172746 @default.
- W4380050110 cites W3035346742 @default.
- W4380050110 cites W3035574168 @default.
- W4380050110 cites W3100591638 @default.
- W4380050110 cites W3114753236 @default.
- W4380050110 cites W3117901461 @default.
- W4380050110 cites W3131452527 @default.
- W4380050110 cites W3156669901 @default.
- W4380050110 cites W3167095230 @default.
- W4380050110 cites W4313149358 @default.
- W4380050110 doi "https://doi.org/10.3390/rs15122986" @default.
- W4380050110 hasPublicationYear "2023" @default.
- W4380050110 type Work @default.
- W4380050110 citedByCount "0" @default.
- W4380050110 crossrefType "journal-article" @default.
- W4380050110 hasAuthorship W4380050110A5022045896 @default.
- W4380050110 hasAuthorship W4380050110A5026288596 @default.
- W4380050110 hasAuthorship W4380050110A5034620195 @default.
- W4380050110 hasAuthorship W4380050110A5086624383 @default.
- W4380050110 hasAuthorship W4380050110A5090156119 @default.
- W4380050110 hasBestOaLocation W43800501101 @default.
- W4380050110 hasConcept C11413529 @default.
- W4380050110 hasConcept C115961682 @default.
- W4380050110 hasConcept C126042441 @default.
- W4380050110 hasConcept C131979681 @default.
- W4380050110 hasConcept C147037132 @default.
- W4380050110 hasConcept C153180895 @default.
- W4380050110 hasConcept C154945302 @default.
- W4380050110 hasConcept C2776151529 @default.
- W4380050110 hasConcept C2778112365 @default.
- W4380050110 hasConcept C2781238097 @default.
- W4380050110 hasConcept C31972630 @default.
- W4380050110 hasConcept C33954974 @default.
- W4380050110 hasConcept C41008148 @default.
- W4380050110 hasConcept C54355233 @default.
- W4380050110 hasConcept C63584917 @default.
- W4380050110 hasConcept C76155785 @default.
- W4380050110 hasConcept C86803240 @default.
- W4380050110 hasConceptScore W4380050110C11413529 @default.
- W4380050110 hasConceptScore W4380050110C115961682 @default.
- W4380050110 hasConceptScore W4380050110C126042441 @default.
- W4380050110 hasConceptScore W4380050110C131979681 @default.
- W4380050110 hasConceptScore W4380050110C147037132 @default.
- W4380050110 hasConceptScore W4380050110C153180895 @default.
- W4380050110 hasConceptScore W4380050110C154945302 @default.
- W4380050110 hasConceptScore W4380050110C2776151529 @default.
- W4380050110 hasConceptScore W4380050110C2778112365 @default.
- W4380050110 hasConceptScore W4380050110C2781238097 @default.
- W4380050110 hasConceptScore W4380050110C31972630 @default.
- W4380050110 hasConceptScore W4380050110C33954974 @default.
- W4380050110 hasConceptScore W4380050110C41008148 @default.
- W4380050110 hasConceptScore W4380050110C54355233 @default.
- W4380050110 hasConceptScore W4380050110C63584917 @default.
- W4380050110 hasConceptScore W4380050110C76155785 @default.
- W4380050110 hasConceptScore W4380050110C86803240 @default.
- W4380050110 hasFunder F4320321001 @default.
- W4380050110 hasIssue "12" @default.
- W4380050110 hasLocation W43800501101 @default.
- W4380050110 hasOpenAccess W4380050110 @default.
- W4380050110 hasPrimaryLocation W43800501101 @default.
- W4380050110 hasRelatedWork W2369744843 @default.
- W4380050110 hasRelatedWork W2756241593 @default.
- W4380050110 hasRelatedWork W2766547489 @default.
- W4380050110 hasRelatedWork W2801801420 @default.
- W4380050110 hasRelatedWork W3043237494 @default.
- W4380050110 hasRelatedWork W3145385008 @default.
- W4380050110 hasRelatedWork W3217090486 @default.
- W4380050110 hasRelatedWork W4285209691 @default.
- W4380050110 hasRelatedWork W4292829955 @default.
- W4380050110 hasRelatedWork W4317383325 @default.
- W4380050110 hasVolume "15" @default.
- W4380050110 isParatext "false" @default.
- W4380050110 isRetracted "false" @default.