.png){kind=icon}
返回
Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds
.png){kind=icon}
OA
AI
DOI：10.1109/TITS.2021.3095719.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Varying density of point clouds increases the difficulty of 3D detection. In this paper, we present a context-aware dynamic network (CADNet) to capture the variance of density by considering both point context and semantic context. Point-level contexts are generated from original point clouds to enlarge the effective receptive filed. They are extracted around the voxelized pillars based on our extended voxelization method and processed with the context encoder in parallel with the pillar features. With a large perception range, we are able to capture the variance of features for potential objects and generate attentive spatial guidance to help adjust the strengths for different regions. In the region proposal network, considering the limited representation ability of traditional convolution where same kernels are shared among different samples and positions, we propose a decomposable dynamic convolutional layer to adapt to the variance of input features by learning from the local semantic context. It adaptively generates the position-dependent coefficients for multiple fixed kernels and combines them to convolve with local features. Based on our dynamic convolution, we design a dual-path convolution block to further improve the representation ability. We conduct experiments on KITTI dataset and the proposed CADNet has achieved superior performance of 3D detection outperforming SECOND and PointPillars by a large margin at the speed of 30 FPS.
Keyword:
Three-dimensional displays
Feature extraction
Convolution
Proposals
Kernel
Laser radar
Semantics
Point clouds
3D detection
dynamic network
context features
期刊
IF:
8.4
论文数:
9.7K
被引数:
6.3W
机构
引用论文
分享收藏Localization of myosin II to chromosome arms and spindle fibers in PtK1 cells: a possible role for an actomyosin system in mitosis.png)
Protoplasma
ProtoplasmaIF0
PREAI
分享收藏Maximizing the Computational Efficiency of Temporary Housing Decision Support Following Disasters
PREAI
分享收藏Thermal comfort, perceived air quality, and cognitive performance when personally controlled air movement is used by tropically acclimatized persons当热带适应的人使用个人控制的空气运动时，热舒适性，感知的空气质量和认知表现Indoor Air
OAAI
Indoor AirIF0
OAAI分享收藏
查看更多内容