Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383109286> ?p ?o ?g. }
- W4383109286 abstract "Outdoor 3D object detection has played an essential role in the environment perception of autonomous driving. In complicated traffic situations, precise object recognition provides indispensable information for prediction and planning in the dynamic system, improving self-driving safety and reliability. However, with the vehicle's veering, the constant rotation of the surrounding scenario makes a challenge for the perception systems. Yet most existing methods have not focused on alleviating the detection accuracy impairment brought by the vehicle's rotation, especially in outdoor 3D detection. In this paper, we propose DuEqNet, which first introduces the concept of equivariance into 3D object detection network by leveraging a hierarchical embedded framework. The dual-equivariance of our model can extract the equivariant features at both local and global levels, respectively. For the local feature, we utilize the graph-based strategy to guarantee the equivariance of the feature in point cloud pillars. In terms of the global feature, the group equivariant convolution layers are adopted to aggregate the local feature to achieve the global equivariance. In the experiment part, we evaluate our approach with different baselines in 3D object detection tasks and obtain State-Of-The-Art performance. According to the results, our model presents higher accuracy on orientation and better prediction efficiency. Moreover, our dual-equivariance strategy exhibits the satisfied plug-and-play ability on various popular object detection frameworks to improve their performance." @default.
- W4383109286 created "2023-07-05" @default.
- W4383109286 creator A5009875459 @default.
- W4383109286 creator A5049166168 @default.
- W4383109286 creator A5069977623 @default.
- W4383109286 creator A5085100533 @default.
- W4383109286 creator A5085238831 @default.
- W4383109286 date "2023-05-29" @default.
- W4383109286 modified "2023-10-16" @default.
- W4383109286 title "DuEqNet: Dual-Equivariance Network in Outdoor 3D Object Detection for Autonomous Driving" @default.
- W4383109286 cites W2071042563 @default.
- W4383109286 cites W2748775427 @default.
- W4383109286 cites W2799123546 @default.
- W4383109286 cites W2889874857 @default.
- W4383109286 cites W2897529137 @default.
- W4383109286 cites W2963351448 @default.
- W4383109286 cites W2963423708 @default.
- W4383109286 cites W2963727135 @default.
- W4383109286 cites W2964166085 @default.
- W4383109286 cites W2968296999 @default.
- W4383109286 cites W2980547801 @default.
- W4383109286 cites W2980698950 @default.
- W4383109286 cites W3008105217 @default.
- W4383109286 cites W3033591146 @default.
- W4383109286 cites W3034239557 @default.
- W4383109286 cites W3034681945 @default.
- W4383109286 cites W3035172746 @default.
- W4383109286 cites W3035461736 @default.
- W4383109286 cites W3035574168 @default.
- W4383109286 cites W3103179390 @default.
- W4383109286 cites W3107422826 @default.
- W4383109286 cites W3108884723 @default.
- W4383109286 cites W3110109289 @default.
- W4383109286 cites W3118341329 @default.
- W4383109286 cites W3166470370 @default.
- W4383109286 cites W3167095230 @default.
- W4383109286 cites W3205835814 @default.
- W4383109286 doi "https://doi.org/10.1109/icra48891.2023.10161353" @default.
- W4383109286 hasPublicationYear "2023" @default.
- W4383109286 type Work @default.
- W4383109286 citedByCount "0" @default.
- W4383109286 crossrefType "proceedings-article" @default.
- W4383109286 hasAuthorship W4383109286A5009875459 @default.
- W4383109286 hasAuthorship W4383109286A5049166168 @default.
- W4383109286 hasAuthorship W4383109286A5069977623 @default.
- W4383109286 hasAuthorship W4383109286A5085100533 @default.
- W4383109286 hasAuthorship W4383109286A5085238831 @default.
- W4383109286 hasBestOaLocation W43831092862 @default.
- W4383109286 hasConcept C124952713 @default.
- W4383109286 hasConcept C131979681 @default.
- W4383109286 hasConcept C132525143 @default.
- W4383109286 hasConcept C138885662 @default.
- W4383109286 hasConcept C142362112 @default.
- W4383109286 hasConcept C153180895 @default.
- W4383109286 hasConcept C154945302 @default.
- W4383109286 hasConcept C171036898 @default.
- W4383109286 hasConcept C202444582 @default.
- W4383109286 hasConcept C2776151529 @default.
- W4383109286 hasConcept C2776401178 @default.
- W4383109286 hasConcept C2780980858 @default.
- W4383109286 hasConcept C2781238097 @default.
- W4383109286 hasConcept C31972630 @default.
- W4383109286 hasConcept C33923547 @default.
- W4383109286 hasConcept C41008148 @default.
- W4383109286 hasConcept C41895202 @default.
- W4383109286 hasConcept C45347329 @default.
- W4383109286 hasConcept C50644808 @default.
- W4383109286 hasConcept C74050887 @default.
- W4383109286 hasConcept C80444323 @default.
- W4383109286 hasConceptScore W4383109286C124952713 @default.
- W4383109286 hasConceptScore W4383109286C131979681 @default.
- W4383109286 hasConceptScore W4383109286C132525143 @default.
- W4383109286 hasConceptScore W4383109286C138885662 @default.
- W4383109286 hasConceptScore W4383109286C142362112 @default.
- W4383109286 hasConceptScore W4383109286C153180895 @default.
- W4383109286 hasConceptScore W4383109286C154945302 @default.
- W4383109286 hasConceptScore W4383109286C171036898 @default.
- W4383109286 hasConceptScore W4383109286C202444582 @default.
- W4383109286 hasConceptScore W4383109286C2776151529 @default.
- W4383109286 hasConceptScore W4383109286C2776401178 @default.
- W4383109286 hasConceptScore W4383109286C2780980858 @default.
- W4383109286 hasConceptScore W4383109286C2781238097 @default.
- W4383109286 hasConceptScore W4383109286C31972630 @default.
- W4383109286 hasConceptScore W4383109286C33923547 @default.
- W4383109286 hasConceptScore W4383109286C41008148 @default.
- W4383109286 hasConceptScore W4383109286C41895202 @default.
- W4383109286 hasConceptScore W4383109286C45347329 @default.
- W4383109286 hasConceptScore W4383109286C50644808 @default.
- W4383109286 hasConceptScore W4383109286C74050887 @default.
- W4383109286 hasConceptScore W4383109286C80444323 @default.
- W4383109286 hasLocation W43831092861 @default.
- W4383109286 hasLocation W43831092862 @default.
- W4383109286 hasOpenAccess W4383109286 @default.
- W4383109286 hasPrimaryLocation W43831092861 @default.
- W4383109286 hasRelatedWork W1971759388 @default.
- W4383109286 hasRelatedWork W2007544051 @default.
- W4383109286 hasRelatedWork W2025800131 @default.
- W4383109286 hasRelatedWork W2035456249 @default.
- W4383109286 hasRelatedWork W2095705906 @default.
- W4383109286 hasRelatedWork W2129974284 @default.