首页下载资源后端RANSAC 和最小二乘法实现雷达自我速度估计

ZIPRANSAC 和最小二乘法实现雷达自我速度估计

qq_403013515.77MB需要积分:1

资源文件列表:

reve.zip 大约有110个文件
  1. reve/
  2. reve/.clang-format 2.36KB
  3. reve/.gitignore 455B
  4. reve/LICENSE 34.33KB
  5. reve/README.md 5.14KB
  6. reve/.git/
  7. reve/.git/config 303B
  8. reve/.git/description 73B
  9. reve/.git/HEAD 23B
  10. reve/.git/packed-refs 114B
  11. reve/.git/index 6.77KB
  12. reve/.git/info/
  13. reve/.git/info/exclude 240B
  14. reve/.git/branches/
  15. reve/.git/hooks/
  16. reve/.git/hooks/prepare-commit-msg.sample 1.46KB
  17. reve/.git/hooks/pre-applypatch.sample 424B
  18. reve/.git/hooks/update.sample 3.53KB
  19. reve/.git/hooks/fsmonitor-watchman.sample 3.01KB
  20. reve/.git/hooks/pre-merge-commit.sample 416B
  21. reve/.git/hooks/pre-receive.sample 544B
  22. reve/.git/hooks/pre-rebase.sample 4.78KB
  23. reve/.git/hooks/applypatch-msg.sample 478B
  24. reve/.git/hooks/pre-commit.sample 1.6KB
  25. reve/.git/hooks/pre-push.sample 1.32KB
  26. reve/.git/hooks/commit-msg.sample 896B
  27. reve/.git/hooks/post-update.sample 189B
  28. reve/.git/refs/
  29. reve/.git/refs/heads/
  30. reve/.git/refs/heads/master 41B
  31. reve/.git/refs/tags/
  32. reve/.git/refs/remotes/
  33. reve/.git/refs/remotes/origin/
  34. reve/.git/refs/remotes/origin/HEAD 32B
  35. reve/.git/objects/
  36. reve/.git/objects/pack/
  37. reve/.git/objects/pack/pack-ecf5a75c287282fa7a355493beb16b35fc6e15e7.pack 2.86MB
  38. reve/.git/objects/pack/pack-ecf5a75c287282fa7a355493beb16b35fc6e15e7.idx 4.52KB
  39. reve/.git/objects/info/
  40. reve/.git/logs/
  41. reve/.git/logs/HEAD 201B
  42. reve/.git/logs/refs/
  43. reve/.git/logs/refs/remotes/
  44. reve/.git/logs/refs/remotes/origin/
  45. reve/.git/logs/refs/remotes/origin/HEAD 201B
  46. reve/.git/logs/refs/heads/
  47. reve/.git/logs/refs/heads/master 201B
  48. reve/demo_datasets/
  49. reve/demo_datasets/calib_rio.yaml 617B
  50. reve/demo_datasets/calib_ti_mmwave_rospkg.yaml 551B
  51. reve/demo_datasets/demo_rio_format.bag 4.72MB
  52. reve/demo_datasets/demo_ti_mmwave_rospkg_format.bag 3.85MB
  53. reve/radar_ego_velocity_estimator/
  54. reve/radar_ego_velocity_estimator/CMakeLists.txt 2.06KB
  55. reve/radar_ego_velocity_estimator/package.xml 831B
  56. reve/radar_ego_velocity_estimator/cfg/
  57. reve/radar_ego_velocity_estimator/cfg/RadarEgoVelocityEstimator.cfg 398B
  58. reve/radar_ego_velocity_estimator/cfg/cfg_radar_ego_velocity_estimation/
  59. reve/radar_ego_velocity_estimator/cfg/cfg_radar_ego_velocity_estimation/__init__.py
  60. reve/radar_ego_velocity_estimator/cfg/cfg_radar_ego_velocity_estimation/radar_ego_velocity_estimator.py 3.15KB
  61. reve/radar_ego_velocity_estimator/cfg/cfg_radar_ego_velocity_estimation/__pycache__/
  62. reve/radar_ego_velocity_estimator/cfg/cfg_radar_ego_velocity_estimation/__pycache__/__init__.cpython-38.pyc 206B
  63. reve/radar_ego_velocity_estimator/cfg/cfg_radar_ego_velocity_estimation/__pycache__/radar_ego_velocity_estimator.cpython-38.pyc 2.75KB
  64. reve/radar_ego_velocity_estimator/config/
  65. reve/radar_ego_velocity_estimator/config/params_demo_dataset.yaml 1.83KB
  66. reve/radar_ego_velocity_estimator/include/
  67. reve/radar_ego_velocity_estimator/include/radar_ego_velocity_estimator/
  68. reve/radar_ego_velocity_estimator/include/radar_ego_velocity_estimator/data_types.h 3.12KB
  69. reve/radar_ego_velocity_estimator/include/radar_ego_velocity_estimator/math_helper.h 1.12KB
  70. reve/radar_ego_velocity_estimator/include/radar_ego_velocity_estimator/odr.h 2.42KB
  71. reve/radar_ego_velocity_estimator/include/radar_ego_velocity_estimator/radar_body_velocity_estimator.h 2.35KB
  72. reve/radar_ego_velocity_estimator/include/radar_ego_velocity_estimator/radar_body_velocity_estimator_ros.h 4.14KB
  73. reve/radar_ego_velocity_estimator/include/radar_ego_velocity_estimator/radar_ego_velocity_estimator.h 7.21KB
  74. reve/radar_ego_velocity_estimator/include/radar_ego_velocity_estimator/radar_ego_velocity_estimator_ros.h 3.66KB
  75. reve/radar_ego_velocity_estimator/include/radar_ego_velocity_estimator/radar_point_cloud.h 1.8KB
  76. reve/radar_ego_velocity_estimator/include/radar_ego_velocity_estimator/ros_helper.h 1.9KB
  77. reve/radar_ego_velocity_estimator/include/radar_ego_velocity_estimator/simple_profiler.h 3.35KB
  78. reve/radar_ego_velocity_estimator/launch/
  79. reve/radar_ego_velocity_estimator/launch/demo_rio_body_velocity.launch 2.35KB
  80. reve/radar_ego_velocity_estimator/launch/demo_rio_ego_velocity.launch 2.45KB
  81. reve/radar_ego_velocity_estimator/launch/demo_ti_mmwave_body_velocity.launch 2.36KB
  82. reve/radar_ego_velocity_estimator/launch/demo_ti_mmwave_ego_velocity.launch 2.23KB
  83. reve/radar_ego_velocity_estimator/python/
  84. reve/radar_ego_velocity_estimator/python/velocity_estimation_evaluator.py 5.7KB
  85. reve/radar_ego_velocity_estimator/src/
  86. reve/radar_ego_velocity_estimator/src/odr.cpp 10.99KB
  87. reve/radar_ego_velocity_estimator/src/radar_body_velocity_estimator.cpp 6.39KB
  88. reve/radar_ego_velocity_estimator/src/radar_body_velocity_estimator_ros.cpp 8.45KB
  89. reve/radar_ego_velocity_estimator/src/radar_ego_velocity_estimator.cpp 17.14KB
  90. reve/radar_ego_velocity_estimator/src/radar_ego_velocity_estimator_ros.cpp 6.76KB
  91. reve/radar_ego_velocity_estimator/src/radar_point_cloud.cpp 7.08KB
  92. reve/radar_ego_velocity_estimator/src/simple_profiler.cpp 5.03KB
  93. reve/radar_ego_velocity_estimator/src/nodes/
  94. reve/radar_ego_velocity_estimator/src/nodes/radar_body_velocity_estimation_ros_node.cpp 1.17KB
  95. reve/radar_ego_velocity_estimator/src/nodes/radar_body_velocity_estimation_rosbag_node.cpp 1.74KB
  96. reve/radar_ego_velocity_estimator/src/nodes/radar_ego_velocity_estimation_ros_node.cpp 1.16KB
  97. reve/radar_ego_velocity_estimator/src/nodes/radar_ego_velocity_estimation_rosbag_node.cpp 1.73KB
  98. reve/radar_ego_velocity_estimator/src/odrpack/
  99. reve/radar_ego_velocity_estimator/src/odrpack/d_lpk.f 38.84KB
  100. reve/radar_ego_velocity_estimator/src/odrpack/d_mprec.f 5.3KB
  101. reve/radar_ego_velocity_estimator/src/odrpack/d_odr.f 359.26KB
  102. reve/radar_ego_velocity_estimator/src/odrpack/d_test.f 69.1KB
  103. reve/radar_ego_velocity_estimator/src/odrpack/dlunoc.f 260B
  104. reve/radar_ego_velocity_estimator/src/odrpack/lpkbls.f 68.77KB
  105. reve/radar_ego_velocity_estimator/src/odrpack/odrpack_guide.pdf 550.31KB
  106. reve/radar_ego_velocity_estimator/src/odrpack/real_precision.f 172B
  107. reve/res/
  108. reve/res/demo_rio_format_v_body.jpeg 198.86KB
  109. reve/res/demo_rio_format_v_body_err.jpeg 250.92KB
  110. reve/res/demo_rio_format_v_radar.jpeg 194.55KB

资源介绍:

github上的免费下载 雷达自我速度估计：使用 RANSAC 和最小二乘法的 C++ 实现 在自动驾驶和机器人领域，雷达传感器是一种重要的设备，用于检测物体的位置和速度。本文将介绍如何通过 C++ 代码实现雷达自我速度估计。我们的实现结合了 RANSAC（随机采样一致性算法）和最小二乘法，以在含噪声的数据中进行鲁棒的速度估计。 代码结构 本文的代码实现包含两个主要部分： estimate 函数：处理雷达扫描数据并进行速度估计。 solve3DFullRansac 和 solve3DFull 函数：使用 RANSAC 和最小二乘法进行速度估计。
# REVE - Radar Ego Velocity Estimator REVE - Radar Ego Velocity Estimator is an efficient C++ implementation for ego velocity estimation using radar scans. Such scans (=3D point cloud) can be measured using modern mmWave radar sensors. Allows for robust and accurate ego velocity estimation even in challenging conditions (darkness, fog, smoke) as radar is not affected by such conditions! ### Highlights - Robust and accurate 3D radar ego velocity estimation - Estimation in the radar frame or a body frame defined by an IMU - Supports the [rio](https://github.com/christopherdoer/rio) and the ti_mmwave_rospkg point cloud format - Radar trigger signals can be used for better synchronization - Super fast: <0.25ms processing time per radar scan The 3D radar ego velocity is estimated with a 3-Point RANSAC Least Squares approach. It requires a single radar scan (=3D point cloud) only making use of the direction and Doppler velocity of each detected object. Thus, no scan matching is required resulting in robust velocity estimation even with high dynamics or difficult scenes with many reflections. In addition, the variances of the resulting 3D ego velocity are estimated as well enabling subsequent fusion. This approach was evaluated in indoor and outdoor environments for low and high dynamic motion achieving very accurate motion estimation as shown in the demo result. This package provides also a node which estimates the body frame velocity defined by an IMU using the measured angular velocity and extrinsic calibration (body frame to radar frame transform). ## Cite If you use REVE for your academic research, please cite our related [paper](https://christopherdoer.github.io/publication/2020_09_MFI2020): ~~~[bibtex] @INPROCEEDINGS{DoerMFI2020, author={Doer, Christopher and Trommer, Gert F.}, booktitle={2020 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)}, title={An EKF Based Approach to Radar Inertial Odometry}, year={2020}, pages={152-159}, doi={10.1109/MFI49285.2020.9235254}} ~~~ ## Demo Result The demo dataset [demo_rio_format](demo_datasets/demo_rio_format.bag) is a low dynamic dataset featuring radar scans and ground truth for the body velocity. Mean runtime to process a single radar scan on an Intel NUC i7-8650U is just 0.15 milliseconds. ### Radar Ego Velocity Estimation Estimation of the radar ego velocity expressed in the radar coordinate frame. ![image](./res/demo_rio_format_v_radar.jpeg) ### Radar Body Velocity Estimation Estimation of the body frame velocity v_b defined by an IMU. The radar ego velocity is transformed into the body frame using rigid body motion making use of the extrinsic transform of the radar sensor. This includes the translation and rotational part and has to be initially calibrated e.g. using [rio](https://github.com/christopherdoer/rio). The resulting v_b can be used for further fusion using e.g. a Kalman filter. ![image](./res/demo_rio_format_v_body.jpeg) ![image](./res/demo_rio_format_v_body_err.jpeg) Error analysis of the body-frame velocity in [m/s]: - Mean error: 0.002, -0.002, 0.006 - Mean absolute error: 0.018, 0.039, 0.053 - Mean error norm: 0.078 - STD: 0.027, 0.058, 0.083 ## Run the Demos Run the radar ego velocity demo launch file and generate the upper plot shown above: ~~~[shell] roslaunch radar_ego_velocity_estimator demo_rio_ego_velocity.launch mode:=rosbag ~~~ Run the body velocity demo launch file with evaluation generating the two lower plots: ~~~[shell] roslaunch radar_ego_velocity_estimator demo_rio_body_velocity.launch mode:=rosbag ~~~ Run the body velocity estimation in online mode: ~~~[shell] roslaunch radar_ego_velocity_estimator demo_rio_body_velocity.launch mode:=ros rosbag play --clock demo_rio_format.bag ~~~ Run the radar ego velocity ti_mmwave_rospkg demo: ~~~[shell] roslaunch radar_ego_velocity_estimator demo_ti_mmwave_ego_velocity.launch mode:=rosbag ~~~ Run the body velocity ti_mmwave_rospkg demo: ~~~[shell] roslaunch radar_ego_velocity_estimator demo_ti_mmwave_body_velocity.launch mode:=rosbag ~~~ ## Getting Started REVE supports: - Ubuntu 16.04 and ROS Kinetic - Ubuntu 18.04 and ROS Melodic - Ubuntu 20.04 and ROS Noetic REVE depends on: - [catkin_simple](https://github.com/catkin/catkin_simple.git) - [catkin_tools](https://catkin-tools.readthedocs.io/en/latest/) (for convenience) **Build in Release is highly recommended**: ~~~[shell] catkin build radar_ego_velocity_estimator --cmake-args -DCMAKE_BUILD_TYPE=Release ~~~ ## ROS Nodes The radar_ego_velocity_estimator_ros node is a ros interface for pure radar ego velocity estimation. The radar_body_velocity_estimator_ros node is a ros interface for the body velocity estimation. Both nodes can operate in two modes: - ros-mode: All topics are read using subscriber - rosbag-mode: A given rosbag in processed at maximum processing speed Configuration is done using dynamic reconfigure and can be adapted online using rqt_reconfigure. Check out the default parameter file [here](./radar_ego_velocity_estimator/cfg/cfg_radar_ego_velocity_estimation/radar_ego_velocity_estimator.py). ## License The source code is released under the [GPLv3](http://www.gnu.org/licenses/) license.
100+评论
captcha

    相关资源

    1. 二、前后端分离通用权限系统（2）gansu-auth-parent(2).zip

      weixin_42171159#后端ZIP84.07KB6月前
      资源摘要:二、前后端分离通用权限系统（2）gansu-auth-parent(2).zip

    2. 数学（天津专用）-2025届新高三开学摸底考试卷.zip

      2402_86598838#行业研究ZIP1.48MB6月前
      资源摘要:数学（天津专用）-2025届新高三开学摸底考试卷.zip

    3. 基于PHP的水质管理系统（用户端、管理员端）

      2302_79553009#后端ZIP72.87KB6月前
      资源摘要:基于php、html、mysql、bootstrap、layui进行全栈式开发。项目完成了前端用户平台、后端管理员平台，以乡村水质检测为主题设立。项目用户页面包括“用户首页”、“关于我们”、“水质新闻”、“水质检测报告”四个模块。水质检测宣传、项目产品、项目服务、未来计划、项目团队、指导团队、成就展示、水质新闻展示、水质报告增删改查的各项功能。项目管理员页面包括“数据展示”、“用户管理”、“水域管理”三个模块。实现了后台数据库数据可视化展示、数据库全用户管理以及权限分配、水域分配以及管理的各项功能。项目登录登出与注册页面实现了用户和管理员权限区分，登录后进入不同平台的功能。语言：php、html、css、javascript工具：Wampserver、Mysql、Dreamever。框架与样式库：bootstrap、echarts、jquery、layui、popper。

    4. 中标麒麟7.6版本，离线安装nginx所需的所有依赖包和nignx压缩包

      weixin_43793741#操作系统ZIP94.74MB6月前
      资源摘要:中标麒麟7.6版本，离线安装nginx所需的所有依赖包和nignx压缩包，依赖包涉及129个，看完教程可以完全离线安装。我碰壁很多次才安装成功的。

    5. novelreaderls.zip

      2402_86819429#行业研究ZIP961.19KB6月前
      资源摘要:novelreaderls.zip

    6. thinkPHP付费资源网站源码 php视频课程网站源码 php知识付费网站源码

      u011854313#后端ZIP306B6月前
      资源摘要:我是这个程序的创作者，也是开发者，源码支持永久升级更新。这个系统是独立开发的，不依赖任何建站程序，采用的是前后端分离开发，前端用的是nuxt+Ant Design，后端用的是thinkPHP6+MySQL+redis，有视频课程板块，可以在线观看。支持卡密功能，支持支付宝、微信和虎皮椒微信支付、支持用户入驻平台发布销售资源，平台从中收取服务费、微信扫码注册/登录、七牛云存储、阿里云短信接口、网易云短信接口、短信宝接口，自动推送链接给百度，有利于百度的收录。支持一键同步资源，免去搬运资源的烦恼，让建站更简单！还支持与WordPress之间数据同步 ，如果你现有WordPress的网站，可以一键把WordPress上的数据同步到本站，也可以把本站的数据同步到WordPress。这个系统适合做资源网站、视频课程网站和知识付费系统。

    7. 独家开发thinkPHP付费资源网站源码 php视频课程网站源码 php知识付费网站源码

      u011854313#后端ZIP89.1MB6月前
      资源摘要:分享一款不错的资源网站源码，这个源码100%开源，开发者提供了免费版的源码，这不是一个普通的资源网站，它还有课程板块，可以发布课程，课程支持视频和图文两种类型。这个系统是独立开发的，不依赖任何建站程序，采用的是前后端分离开发，前端用的是nuxt+Ant Design，后端用的是thinkPHP6+MySQL+redis，支持支付宝、微信和虎皮椒微信支付、支持用户入驻平台发布销售资源，有微信扫码注册/登录、七牛云存储、阿里云短信接口、网易云短信接口、短信宝接口。最适用的是提供了资源同步功能，不用一个一个的去找资源上传，直接一键同步资源到本地。支持与WordPress之间数据同步 ，如果你现有WordPress的网站，可以一键把WordPress上的数据同步到本站，也可以把本站的数据同步到WordPress。

    8. ccf书籍-基础篇-第一章源代码

      Zhou2010_#后端ZIP5.75MB6月前
      资源摘要:ccf书籍——基础篇——第一章（编程如此简单）源代码共13个源代码介绍基本的顺序结构1.1程序设计概念1.2整数算术运算1.3实数算术运算源代码均为本人编写
    站长QQ:九六九五七三七