SAT-GCN: Self-attention graph convolutional network-based 3D object detection for autonomous driving

点云 计算机科学 目标检测 图形 激光雷达 人工智能 模式识别(心理学) 特征提取 特征(语言学) 顶点(图论) 遥感 理论计算机科学 语言学 哲学 地质学
作者
Li Wang,Ziying Song,Xinyu Zhang,Chenfei Wang,Guoxin Zhang,Lei Zhu,Jun Li,Huaping Liu
出处
期刊:Knowledge Based Systems [Elsevier BV]
卷期号:259: 110080-110080 被引量:68
标识
DOI:10.1016/j.knosys.2022.110080
摘要

Accurate 3D object detection from point clouds is critical for autonomous vehicles. However, point cloud data collected by LiDAR sensors are inherently sparse, especially at long distances. In addition, most existing 3D object detectors extract local features and ignore interactions between features, producing weak semantic information that significantly limits detection performance. We propose a self-attention graph convolutional network (SAT-GCN), which utilizes a GCN and self-attention to enhance semantic representations by aggregating neighborhood information and focusing on vital relationships. SAT-GCN consists of three modules: vertex feature extraction (VFE), self-attention with dimension reduction (SADR), and far distance feature suppression (FDFS). VFE extracts neighboring relationships between features using GCN after encoding a raw point cloud. SADR performs further weight augmentation for crucial neighboring relationships through self-attention. FDFS suppresses meaningless edges formed by sparse point cloud distributions in remote areas and generates corresponding global features. Extensive experiments are conducted on the widely used KITTI and nuScenes 3D object detection benchmarks. The results demonstrate significant improvements in mainstream methods, PointPillars, SECOND, and PointRCNN, improving the mean of AP 3D by 4.88%, 5.02%, and 2.79% on KITTI test dataset. SAT-GCN can boost the detection accuracy of the point cloud, especially at medium and long distances. Furthermore, adding the SAT-GCN module has a limited impact on the real-time performance and model parameters.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Sandy应助Yu采纳,获得40
刚刚
1秒前
夏虫发布了新的文献求助10
1秒前
1秒前
2秒前
2秒前
猪猪hero应助睡着那么快采纳,获得10
2秒前
2秒前
英姑应助令狐擎宇采纳,获得10
3秒前
3秒前
3秒前
垃圾二硫自组装纳米粒完成签到,获得积分10
3秒前
太阳花完成签到,获得积分10
4秒前
hulin_zjxu完成签到,获得积分10
4秒前
4秒前
谢丹发布了新的文献求助10
5秒前
猪猪hero应助QWSS采纳,获得10
5秒前
5秒前
DDdaisiki发布了新的文献求助10
5秒前
lullu完成签到,获得积分20
6秒前
6秒前
传奇3应助盖饭不加辣采纳,获得30
6秒前
研友_Lw7QmL发布了新的文献求助10
6秒前
Victor完成签到,获得积分10
6秒前
wuyin发布了新的文献求助10
6秒前
7秒前
桐桐应助123采纳,获得10
7秒前
7秒前
7秒前
MlUhTkE发布了新的文献求助10
8秒前
ZR14124发布了新的文献求助20
8秒前
9秒前
Bran发布了新的文献求助10
9秒前
hope完成签到,获得积分10
10秒前
阮绿凝发布了新的文献求助10
10秒前
汤飞柏发布了新的文献求助10
10秒前
拿云发布了新的文献求助10
10秒前
xigua发布了新的文献求助10
11秒前
11秒前
付绒发布了新的文献求助10
11秒前
高分求助中
The Mother of All Tableaux Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 2400
Ophthalmic Equipment Market by Devices(surgical: vitreorentinal,IOLs,OVDs,contact lens,RGP lens,backflush,diagnostic&monitoring:OCT,actorefractor,keratometer,tonometer,ophthalmoscpe,OVD), End User,Buying Criteria-Global Forecast to2029 2000
Cognitive Neuroscience: The Biology of the Mind 1000
Cognitive Neuroscience: The Biology of the Mind (Sixth Edition) 1000
Optimal Transport: A Comprehensive Introduction to Modeling, Analysis, Simulation, Applications 800
Official Methods of Analysis of AOAC INTERNATIONAL 600
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 588
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3958608
求助须知:如何正确求助?哪些是违规求助? 3504895
关于积分的说明 11120971
捐赠科研通 3236246
什么是DOI,文献DOI怎么找? 1788726
邀请新用户注册赠送积分活动 871297
科研通“疑难数据库(出版商)”最低求助积分说明 802680