毫米波目标检测论文 阅读笔记 | Radar Transformer: An Object Classification Network Based on 4D MMW Imaging Radar
毫米波目标检测论文 | Radar Transformer: An Object Classification Network Based on 4D MMW Imaging Radar
Jie Bai, Lianqing Zheng , Sen Li , Bin Tan, Sihan Chen and Libo Huang
同济大学
Sensors
原始论文地址: https://www.mdpi.com/1424-8220/21/11/3854
本文为毫米波目标检测论文
Radar Transformer: An Object Classification Network Based on 4D MMW Imaging Radar
的阅读笔记, 原载于R.X. NLOS的博客
笔记难免存在问题,欢迎联系 981591477@qq.com 指正。
内容在CSDN、知乎和微信公众号同步更新
- CSDN博客
- 知乎
- 微信公众号
Abstract
- millimeter-wave (MMW) 4D radar的重要性
- essential in automomous vehicles
- 因为its robustness in all weather conditions
- 但传统automotive radar分辨率低
- 难以完成object Classification任务
- 因此,有了4D imaging radar
- azimuth and elevation 分辨率高 + 包括了Doppler信息
- 能够产生高质量3D点云 + speed
- essential in automomous vehicles
- 本文工作
- 提出了Radar Transformer
- 用于雷达点云目标检测
- 核心:注意力机制
- 包括vector attention和scalar attention
- to make full use of 空间信息、Doppler信息、点云强度信息,实现deep fusion
- 实验结果:
- 采集了数据集,完成了标注
- 识别准确率94.9%
- The prosposed method适合radar点云识别任务
- 提出了Radar Transformer
Introduction
p1: 为什么要研究基于MMW点云的object detection: 自动驾驶很重要 + MMW 4D sensor具有优势 + 现有研究较少
- 近年来,自动驾驶developed rapidly
- Auto. vehicles包括多个模块:
- 感知 perception (is siginificant)
- (预测)、规划 path planing
- 控制 decision control
- 4D MMW radar在perception中很重要:
- cameras and LiDAR对不同天气、光照的鲁棒性差
- 传统MMW radar分辨率低、缺少高度信息, 仅起到最终警告作用
- 4D MMW radar 能够形成点云、包含Doppler信息、对天气鲁棒,但相关算法仍in the initial stage
介绍4D毫米波雷达的相关文章[5-7]:
[5]. Brisken, S.; Ruf, F.; Höhne, F. Recent evolution of automotive imaging radar and its information content. IET Radar Sonar Navig. 2018.
[6]. Li, G.; Sit, Y.L.; Manchala, S.; Kettner, T.; Ossowska, A.; Krupinski, K.; Sturm, C.; Lubbert, U. Novel 4D 79 GHz Radar Concept for Object Detection and Active Safety Applications. In Proceedings of the 2019 12th German Microwave Conference (GeMiC), Stuttgart, Germany, 2019.
[7]. Stolz, M.;Wolf, M.; Meinl, F.; Kunert, M.; Menzel,W. A New Antenna Array and Signal Processing Concept for an Automotive 4D Radar. In Proceedings of the 2018 15th European Radar Conference (EuRAD), Spain, 2018.
p2: Related Works on 4D imaging radar (Hardware + 相应Detection Alg.)
- imaging radar Hardware:
- [6]: 4D radar operates at 79HZ, 使用FMCW, bandwidth 1.6GHz
- 利用MIMO和BPSK transmitting signals to obtain elevation info.
- 能够用来完成简单的检测任务(如road edge height estimation)
- [7]: used a new antenna array – can measure angles in azimuth and elevation
- 通过combining them to estimate the direction of arrival
- [8]: exploited high-resolution MMW radar to obtain radar point-cloud represen.
- then using GMM for point-cloud segmentation (交通场景)
- [6]: 4D radar operates at 79HZ, 使用FMCW, bandwidth 1.6GHz
- imaging radar Harware --> Algorithm
- [9] used planar phased FMCW radar产生3D点云,用于detecting human motions
- 通过calculating the direction of arrival获得3D点云
- CNN for classification: acc 80%
- [10] made a dataset including radar, LiDAR and Camera
- radar: Astyx 6455 HiRes[5], 高分辨率imaging radar
- most of the objects are cars --> 难以应用
- [9] used planar phased FMCW radar产生3D点云,用于detecting human motions
p3: Related Works on Point-Cloud Object Detection
- Deep learning have made impressive achievements
- including in data structures like point clouds
- 点云特性:permutation and orientation invariance
- 传统CNN不适合such irregularly strucured data
- MVCNN: from different views
- 3DMV: integrates RGB + geometric features
- Voxel-based methods: Vox Net; 3DCNN;
- GCN: DGCNN, EdgeConv;
- Point-wise network: PointNet series
- often hierarchically extract/combined features
p4: Related Works on Transformers and its applications in Point-Cloud Object Detection
- Transformers has dominated in NLP:
- BERT, Transformer-XL, BioBERT, etc.
- Transformers has also benn extented to CV
- The core of Transformer is the self-attention module
- this mechanism is well suited to dealing with data like point clouds
- PCT [31] applies transformer to point clouds 并取得了good results
p5: Introduces the proposed Network in this paper
- Transfomer架构
- 使用注意力机制在multi-level上fuse局部和全局features
- 完成MMW radar下的object Classification任务
- achieved the highest accuracy
- Generated an MMW imaging radar classification dataset
- collected dynamic and static road participants
- persons, cyclists, motorcyclists, cars and buses
- manually annotated them
- A total of 10,000 frames of data
- each data containing spatial (XYZ) and Doppler velocity (V) information
- collected dynamic and static road participants
- Proposed a radar point-cloud classification network beased on Transformer
- 输入为5维点云信息 -> 经过embedding, hierarchical feature extraction, multilevel deep fusion和scalar+vector attention后得到deep features
- Experiments show that the proposed network exhibits SOTA performance
p7: Organization of the remainder
- Section 2: Describe the Network
- Section 3: Experiments
- Section 4: Discussion
- Section 5: Conclusion
Methodology
- The Network architecture
- 本次没有去读详细的网络结构
- 网络结构大体上如右图所示
- input: Radar Point Cloud
- output: 分类结果
- Note that 不是检测结果
Results
Dataset
- Existed public datasets containing radar information:
- 要么只包括2D radar数据
- Nuscence
- CRUW
- Oxford Radar Robotcar Dataset
- 要么质量差 (frame太少+ unbalanced classes)
- Astyx Dataset
- only 500 frames + Most of which are cars
- 要么只包括2D radar数据
- 因此this paper collected and created own dataset:
- contain 10000 frames
- five classes
- persons, cyclists, motorcyclists, cars, buses
采集设置
- Radar: TI imaging radar TIDEP01012
- composed of four AWR2243 cascaded radar boards
- 跨多个cascaded AWR2243制作的MIMO antenna能够maximize the number of active antennas
- enabling substantially improved angular resolution
- Radar: TI imaging radar TIDEP01012
照片和Radar参数如下
Radar Signal Processing
- Processing流程图如下
- The imaging radar development board was designed in a cascade of four devices.
Radar Signal Processing具体处理过程包括:
Step 0: 预处理 (本步骤未在上页图中表明)
- Antenna calibration
- 防止由于芯片和天线耦合等因素的差异导致主设备与其余三个从设备之间的频率、相位和幅度不匹配
- 校准方法:
- 使用 TI 官方校准矩阵通过一次性视轴校准
- chirp configuration parameters
- set to those in MIMO mode
Step 1: Read and parsed the ADC data
Step 2: Perform frequency and phase calibrations
Step 3: 将校准后的数据 经过 range FFT 和 多普勒FFT
Step 4: 进行非相干集成 (non-coherent integration)
- Since there were multiple channels
- Step 5: 执行恒定虚警率 constant false-alarm rate (CFAR) 算法
- To filter out noise and interference
- Step 6: Performing maximum velocity extension and phase compensation
- 最大速度扩展和相位补偿
- Step 7: Azimuth and elevation angle estimation
- 方位角和仰角估计
- 最终获得点云
Data acquisition and Production
所采集的数据: 包括Static scenes和Dynamic scenes
- Static Scenes:
- collected data at a distance interval of 1m1 m1m and an angle interval of 45°45 \degree45°
- To fully represent the distribution of the object point cloud
- collected different types of samples for each class of objects
- To make the object classes more representative
- collected data at a distance interval of 1m1 m1m and an angle interval of 45°45 \degree45°
- Dynamic Data:
- collected them on campus roads and experimental sites
- different objects moved at different speeds and angles
每一帧的format 和 坐标变换
- The formate of the reflected points:
- pi={ri,θi,φi,vi,si}p_{i}=\left\{r_{i}, \theta_{i}, \varphi_{i}, v_{i}, s_{i}\right\}pi={ri,θi,φi,vi,si}
- rir_{i}ri: range; θi\theta_{i}θi: azimuth angle; φi\varphi_{i}φi: elevation angle; viv_{i}vi: radial velocity; sis_{i}si: signal-to-noise ratio
- 坐标变换以进行后续analysis、visualization和labeling:
- spherical coordinate to Cartesian Coordinate system
- [xiyizi]=ri[cos(θi)cos(φi)sin(θi)cos(φi)sin(φi)]\left[\begin{array}{c}x_{i} \\ y_{i} \\ z_{i}\end{array}\right]=r_{i}\left[\begin{array}{c}\cos \left(\theta_{i}\right) \cos \left(\varphi_{i}\right) \\ \sin \left(\theta_{i}\right) \cos \left(\varphi_{i}\right) \\ \sin \left(\varphi_{i}\right)\end{array}\right]⎣⎡xiyizi⎦⎤=ri⎣⎡cos(θi)cos(φi)sin(θi)cos(φi)sin(φi)⎦⎤
数据标注方法
- 1: clustered the obtained point cloud for each frame
- to get the approximate 3D bounding box
- 2: labeled it with the information recorded by camera
- 3: final dataset contained 10,000 frames (static + dynamix)
- Visualization of some experimental data
Experimental Details
Details related to Dataset Processing (划分 + Normalization)
- Totally 10,000 frames of data
- including 5 classes
- classes are proportionally balanced
- each class had 2000 frames of data
- Train : Test = 7:3
- The information in each point:
- XYZ spatial information + Doppler velocity V + intensity information S
- Normalization:
- For each point pi={xi,yi,zi,vi,si}p_{i}=\left\{x_{i}, y_{i}, z_{i}, v_{i}, s_{i}\right\}pi={xi,yi,zi,vi,si} in one frame
- Norm:
(xi,yi,zi,vi,si)=(xi,yi,zi,vi,si)max(xi2+yi2+zi2+vi2+si2),i=1,2,…N\left(x_{i}, y_{i}, z_{i}, v_{i}, s_{i}\right)=\frac{\left(x_{i}, y_{i}, z_{i}, v_{i}, s_{i}\right)}{\max \left(\sqrt{x_{i}^{2}+y_{i}^{2}+z_{i}^{2}+v_{i}^{2}+s_{i}^{2}}\right)}, i=1,2, \ldots N(xi,yi,zi,vi,si)=max(xi2+yi2+zi2+vi2+si2
Details related to network Training
- 128 input points
- 缺失则补0,过多则采样
- Using Pytorch, SGD optimizer, momentum + weight decay
- Learning rate: 0.001
- decayed by 30% every 20 epoches
- loss function:
- softmax cross-encryption
- training
- With data augmentation
- No data augmentation in testing
- 200 epoches, batchsize = 24; 1080 Ti
Experimental Results
毫米波目标检测论文 阅读笔记 | Radar Transformer: An Object Classification Network Based on 4D MMW Imaging Radar相关推荐
- 【视频目标检测论文阅读笔记】Optimizing Video Object Detection via a Scale-Time Lattice
1.1 论文信息 标题 Optimizing Video Object Detection via a Scale-Time Lattice 会议 CVPR 2018 原文链接 Optimizing ...
- 2019 sample-free(样本不平衡)目标检测论文阅读笔记
点击我爱计算机视觉标星,更快获取CVML新技术 本文转载自知乎,已获作者同意转载,请勿二次转载 (原文地址:https://zhuanlan.zhihu.com/p/100052168) 背景 < ...
- 【目标检测论文阅读笔记】QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
Abstract 虽然深度学习的通用目标检测在过去几年取得了巨大成功,但检测小目标的性能和效率却远不尽如人意.促进小目标检测的最常见和有效的方法是使用高分辨率图像或特征图.然而,这两种方法都会导致昂贵 ...
- 【目标检测论文阅读笔记】Feature-Enhanced CenterNet for Small Object Detection in Remote Sensing Images
Abstract: 与 anchor-based基于锚点的检测器相比,anchor-free无锚点检测器 具有灵活性和较低计算复杂度的优点.然而,在复杂的遥感场景中,受限的几何尺寸.目标的弱特征 以及 ...
- 三维目标检测论文阅读:VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection 理解了PointPillars这篇文章后,看这篇文章就清 ...
- 3D目标检测论文阅读多角度解析
3D目标检测论文阅读多角度解析 一.前言 CNN(convolutional neural network)在目标检测中大放异彩,R-CNN系列,YOLO,SSD各类优秀的方法层出不穷在2D图像的目标 ...
- 3D目标检测论文阅读摘要
3D目标检测论文阅读摘要 2D Object Detection 的研究已经非常成熟了,代表作品有RPN系列的FasterRCNN,One Shot系列的YOLOv1-YOLOv3,这里推荐一个2D ...
- 目标检测论文阅读:GHM(anchor based)
目标检测论文阅读:GHM(anchor based) 论文链接:https://arxiv.org/abs/1811.05181 代码链接:https://github.com/libuyu/GHM_ ...
- 论文阅读笔记:《Hyperspectral image classification via a random patches network》(ISPRSjprs2018)
论文阅读笔记:<Hyperspectral image classification via a random patches network>(ISPRSjprs2018) 论文下载地址 ...
最新文章
- 16个很有用的在线工具
- Tensorflow学习
- html如何让条数按序号输出,JS 怎么控制页面序号较智能的生成?
- 2020年 第11届 蓝桥杯 Java B组 省赛真题详解及小结【第1场省赛 2020.7.5】
- 网站301重定向 解决方法
- 这所美国大学研发出了Wi-Fi充电技术
- 计蒜课挑战难题:罗马数字转换成整数
- linux虚拟用户登录失败,用shell用户或虚拟用户登录pureftpd
- docker镜像与容器操作流程
- jquery 获取日期时间
- php 时间日期转为时间戳,PHP日期格式转时间戳
- html页面怎么记住密码,使用html的localstorage实现登录页面的记住密码功能
- 数字后端基本概念介绍Size Blockage
- android 编译
- 组策略学习-统一部署软件
- 百度杯”CTF比赛(十一月场)
- STM32CubeIDE HAL库IIC实现气压计MS5637的数据读取
- H5自适应屏幕分辨率大小
- 用python打开windows计算器程序
- fresco混淆问题