.png){kind=icon}
返回
GRNet: Geometric relation network for 3D object detection from point clouds
.png){kind=icon}
PRE
AI
DOI：10.1016/j.isprsjprs.2020.05.008.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Rapid detection of 3D objects in indoor environments is essential for indoor mapping and modeling, robotic perception and localization, and building reconstruction. 3D point clouds acquired by a low-cost RGB-D camera have become one of the most commonly used data sources for 3D indoor mapping. However, due to the sparse surface, empty object center, and various scales of point cloud objects, 3D bounding boxes are challenging to be estimated and located accurately. To address this, geometric shape, topological structure, and object relation are commonly employed to extract box reasoning information. In this paper, we describe the geometric feature among object points as an intra-object feature and the relation feature between different objects as an inter-object feature. Based on these two features, we propose an end-to-end point cloud geometric relation network focusing on 3D object detection, which is termed as geometric relation network (GRNet). GRNet first extracts intra-object and inter-object features for each representative point using our proposed backbone network. Then, a centralization module with a scalable loss function is proposed to centralize each representative object point to its center. Next, proposal points are sampled from these shifted points, following a proposal feature pooling operation. Finally, an object-relation learning module is applied to predict bounding box parameters. Such parameters are the additive sum of prediction results from the relation-based inter-object feature and the aggregated intra-object feature. Our model achieves state-of-the-art 3D detection results with 59.1% mAP@0.25 and 39.1% mAP@0.5 on ScanNetV2 dataset, 58.4% mAP@0.25 and 34.9% mAP@0.5 on SUN RGB-D dataset.
Keyword:
Deep learning
3D object detection
Point cloud
Geometric relation
Indoor mapping
RGB-D
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:
12.2
论文数:
4.4K
被引数:
3.2W
机构
引用论文
A Frustum-based probabilistic framework for 3D object detection by fusion of LiDAR and camera data基于平截头体的激光雷达和相机数据融合的3D目标检测概率框架
.png){kind=icon}
PREAI
分享收藏Automatic Semantic Modeling of Indoor Scenes from Low-quality RGB-D Data using Contextual Information使用上下文信息从低质量rgb-d数据对室内场景进行自动语义建模
OAAI
OAAI分享收藏Semantic line framework-based indoor building modeling using backpacked laser scanning point cloud
PREAI
分享收藏
查看更多内容