Complex-YOLO: An Euler-Region-Proposal for Real-Time 3D Object Detection on Point Clouds

计算机科学 点云 人工智能 目标检测 计算机视觉 水准点(测量) 对象(语法) 姿势 模式识别(心理学) 大地测量学 地理
作者
Martín Simón,Stefan Milz,Karl Amende,Horst–Michael Groß
出处
期刊:Lecture Notes in Computer Science 卷期号:: 197-209 被引量:283
标识
DOI:10.1007/978-3-030-11009-3_11
摘要

Lidar based 3D object detection is inevitable for autonomous driving, because it directly links to environmental understanding and therefore builds the base for prediction and motion planning. The capacity of inferencing highly sparse 3D data in real-time is an ill-posed problem for lots of other application areas besides automated vehicles, e.g. augmented reality, personal robotics or industrial automation. We introduce Complex-YOLO, a state of the art real-time 3D object detection network on point clouds only. In this work, we describe a network that expands YOLOv2, a fast 2D standard object detector for RGB images, by a specific complex regression strategy to estimate multi-class 3D boxes in Cartesian space. Thus, we propose a specific Euler-Region-Proposal Network (E-RPN) to estimate the pose of the object by adding an imaginary and a real fraction to the regression network. This ends up in a closed complex space and avoids singularities, which occur by single angle estimations. The E-RPN supports to generalize well during training. Our experiments on the KITTI benchmark suite show that we outperform current leading methods for 3D object detection specifically in terms of efficiency. We achieve state of the art results for cars, pedestrians and cyclists by being more than five times faster than the fastest competitor. Further, our model is capable of estimating all eight KITTI-classes, including Vans, Trucks or sitting pedestrians simultaneously with high accuracy.
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
如此发布了新的文献求助10
刚刚
1秒前
赵静1234567890完成签到,获得积分10
1秒前
xxxllllll发布了新的文献求助10
5秒前
科研通AI2S应助科研通管家采纳,获得10
5秒前
Owen应助科研通管家采纳,获得10
5秒前
乐乐应助科研通管家采纳,获得10
5秒前
科研通AI5应助科研通管家采纳,获得10
5秒前
YamDaamCaa应助科研通管家采纳,获得50
5秒前
科研通AI5应助科研通管家采纳,获得10
5秒前
科目三应助科研通管家采纳,获得10
6秒前
爆米花应助科研通管家采纳,获得10
6秒前
稳重淇完成签到 ,获得积分10
6秒前
6秒前
7秒前
8秒前
daaarrr完成签到,获得积分10
11秒前
非一发布了新的文献求助10
14秒前
14秒前
15秒前
16秒前
乐乐应助事在人为采纳,获得10
17秒前
18秒前
jisujun完成签到,获得积分20
18秒前
41应助momo采纳,获得10
19秒前
DijiaXu应助jszhoucl采纳,获得10
21秒前
热爱科研的小白鼠完成签到,获得积分10
21秒前
21秒前
爱穿毛袜完成签到,获得积分10
22秒前
大模型应助LJJ采纳,获得10
22秒前
spirit完成签到 ,获得积分10
23秒前
思源应助hhh采纳,获得10
23秒前
24秒前
正直的魔镜完成签到 ,获得积分10
25秒前
27秒前
KM比比发布了新的文献求助10
28秒前
如此完成签到,获得积分10
28秒前
qq完成签到 ,获得积分10
29秒前
qqq发布了新的文献求助10
30秒前
火星上鑫鹏完成签到,获得积分10
30秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3989334
求助须知:如何正确求助?哪些是违规求助? 3531428
关于积分的说明 11253936
捐赠科研通 3270119
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809173