.png){kind=icon}
返回
Two-stage 3D object detection guided by position encoding q
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2022.06.030.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Voxel-based structures in 3D detection have achieved rapid advancement due to their superior capability for feature extraction. However, the accuracy is usually low because the point cloud is divided into a grid. In order to overcome the above problems and improve detection accuracy, we propose a flexible two -stage 3D object detection architecture, which adopts two branches to refine generated proposals, aggre-gating voxel features and raw point features simultaneously. We also design a new gating mechanism to achieve fusion features from different levels. In addition, we propose a novel feature aggregation module to reduce the semantic gap between the features of the two types. First, a transformer based on raw points is employed as an encoder to aggregate the contextual information. Then, the point-based channel-wise self-attention mechanism serves as a decoder to aggregate the global features. Experiment results on the KITTI 3D dataset and Waymo Open datest demonstrate that our approach out-performs the state-of-the-art methods and exhibits excellent scalability.(c) 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Keyword:
3D detection
Position encoding
Transformer
Self-attention
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Adversarial point cloud perturbations against 3D object detection in autonomous driving systems自动驾驶系统中针对3D物体检测的对抗点云扰动.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏ASCNet: 3D object detection from point cloud based on adaptive spatial context features qNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
分享收藏 没有更多内容
没有更多内容