# LeGO-LOAM for kitti dataset
This repository contains the modified code of LeGO-LOAM to run and evaluate with the kitti-data set. When you run the code, you'll get the trajectory results of LeGO-LOAM in KITTI ground-truth format and you can directly evaluate the result with KITTI ground-truth by EVO-eval kit. Wish you find it helpful, especially for those who are not familiar with ROS and LOAM.
## Dependency
- [ROS](http://wiki.ros.org/ROS/Installation) (tested with indigo and kinetic)
- [gtsam](https://github.com/borglab/gtsam/releases) (Georgia Tech Smoothing and Mapping library, 4.0.0-alpha2)
```
wget -O ~/Downloads/gtsam.zip https://github.com/borglab/gtsam/archive/4.0.0-alpha2.zip
cd ~/Downloads/ && unzip gtsam.zip -d ~/Downloads/
cd ~/Downloads/gtsam-4.0.0-alpha2/
mkdir build && cd build
cmake ..
sudo make install
```
## Compile
1. You can use the following commands to download and compile the package.
```
cd ~/catkin_ws/src
git clone https://github.com/Mitchell-Lee-93/kitti-lego-loam.git
cd ..
rosdep install --from-paths src --ignore-src -r -y
catkin_make
```
## Making new bagfile from kitti dataset
Download odometry dataset(color or gray, velodyne, calibration, ground truth)
from : http://www.cvlibs.net/datasets/kitti/eval_odometry.php and Merge them all in one dataset directory
1. Edit the launch file
```
gedit ~/catkin_ws/src/kittibag/launch/kittibag.launch
```
Change 'dataset_folder' and 'output_bag_file' to your own directories
2. Run the launch file:
```
roslaunch kittibag kittibag.launch
```
## Run the package
1. Before run, you should change the directory of the result files
```
gedit ~/catkin_ws/src/LeGO-LOAM/LeGO-LOAM/launch/run.launch
```
change 'RESULT_PATH' to your result dir
2. Run the launch file:
```
roslaunch lego_loam run.launch
```
Notes: The parameter "/use_sim_time" is set to "true" for simulation, "false" to real robot usage.
3. Play existing bag files:
```
rosbag play *.bag --clock
```
## Evaluation with evo kit
Check and follow this repository
https://github.com/MichaelGrupp/evo
## Evaluation results
<img src = "https://raw.githubusercontent.com/Mitchell-Lee-93/kitti-lego-loam/master/kittibag/pic/1.png" width = "300"> <img src = "https://raw.githubusercontent.com/Mitchell-Lee-93/kitti-lego-loam/master/kittibag/pic/2.png" width = "300"> <img src = "https://raw.githubusercontent.com/Mitchell-Lee-93/kitti-lego-loam/master/kittibag/pic/3.png" width = "200">
## For A-LOAM with kitti
check https://github.com/Mitchell-Lee-93/kitti-A-LOAM
## Original code from
https://github.com/RobustFieldAutonomyLab/LeGO-LOAM
Modified code
1. utility.h
for Velodyne 64 channel
```
extern const string pointCloudTopic = "/kitti/velo/pointcloud"; <- you should check your own bag file topic
//param for vel-64
extern const int N_SCAN = 64;
extern const int Horizon_SCAN = 1800;
extern const float ang_res_x = 0.2;
extern const float ang_res_y = 0.427;
extern const float ang_bottom = 24.9;
extern const int groundScanInd = 50;
```
2. featureAssociation.cpp
Since kitti data already have removed the distortion
```
float s 10 * (pi->intensity - int(pi->intensity)); -> float s = 1;
// to delete all the code that corrects point cloud distortion
TransformToEnd(&cornerPointsLessSharp->points[i], &cornerPointsLessSharp->points[i]); -> removed
TransformToEnd(&surfPointsLessFlat->points[i], &surfPointsLessFlat->points[i]); -> removed
*Notes: The parameter "loopClosureEnableFlag" is set to "true" for SLAM.
```
3. transformfusion.cpp
To correct two diffrent TF of lego-loam results and kitti gt. And also to save the results in kitti gt format
```
From line 222 to 286, saving results code added
```
Reference : https://github.com/RobustFieldAutonomyLab/LeGO-LOAM/issues/12
没有合适的资源?快使用搜索试试~ 我知道了~
kitti-lego-loam:使用KITTI数据轻松描述运行和评估Lego-LOAM
共35个文件
png:5个
cpp:5个
h:3个
5星 · 超过95%的资源 需积分: 49 47 下载量 56 浏览量
2021-05-14
22:21:43
上传
评论 7
收藏 26.84MB ZIP 举报
温馨提示
用于kitti数据集的LeGO-LOAM 该存储库包含LeGO-LOAM的修改后的代码,可通过kitti数据集运行和评估。 运行代码时,您将以KITTI地面格式获取LeGO-LOAM的轨迹结果,并且可以通过EVO-eval套件使用KITTI地面真实结果直接评估结果。 希望对您有所帮助,特别是对于那些不熟悉ROS和LOAM的用户。 相依性 (经靛蓝和动力学测试) (乔治亚州技术平滑和映射库,4.0.0-alpha2) wget -O ~/Downloads/gtsam.zip https://github.com/borglab/gtsam/archive/4.0.0-alpha2.zip cd ~/Downloads/ && unzip gtsam.zip -d ~/Downloads/ cd ~/Downloads/gtsam-4.0.0-alpha2/ mkdir bu
资源推荐
资源详情
资源评论
收起资源包目录
kitti-lego-loam-master.zip (35个子文件)
kitti-lego-loam-master
LICENSE 1KB
LeGO-LOAM
Shan_Englot_IROS_2018_Preprint.pdf 4.35MB
LICENSE 1KB
LeGO-LOAM
CMakeLists.txt.user 27KB
src
featureAssociation.cpp 73KB
transformFusion.cpp 13KB
imageProjection.cpp 20KB
mapOptmization.cpp 68KB
launch
jackal-label.jpg 32KB
seg-total.jpg 136KB
demo.gif 18.26MB
odometry.jpg 22KB
test.rviz 15KB
block.png 32KB
google-earth.png 926KB
dataset-demo.gif 3.54MB
run.launch 1KB
package.xml 1KB
include
utility.h 5KB
CMakeLists.txt 1KB
cloud_msgs
msg
cloud_info.msg 324B
package.xml 750B
CMakeLists.txt 468B
README.md 48B
kittibag
src
kittibag.cpp 7KB
launch
kittibag.launch 548B
LICENSE 2KB
package.xml 1KB
include
aloam_velodyne
tic_toc.h 601B
common.h 2KB
CMakeLists.txt 772B
pic
2.png 45KB
3.png 12KB
1.png 33KB
README.md 4KB
共 35 条
- 1
资源评论
- BJWcn2023-07-27在实际操作中,这篇文件的描述非常实用,给出的步骤和案例都很具体,让人能够迅速上手。
- 柔粟2023-07-27文章的结构清晰,逻辑性强,使得读者能够很方便地找到自己想了解的内容。
- 查理捡钢镚2023-07-27这篇文件对于理解和使用kitti-lego-loam算法非常有帮助,详细描述了其运行和评估过程。
- 焦虑肇事者2023-07-27尽管有一些技术术语,但是作者使用了简洁明了的语言,非常易于理解,适合各种读者阅读。
- 邢小鹏2023-07-27对于初学者来说,这篇文件提供了清晰的指导,使得理解和应用kitti-lego-loam变得相对容易。
RonaldWang
- 粉丝: 22
- 资源: 4586
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- Screenshot_20240427_031602.jpg
- 网页PDF_2024年04月26日 23-46-14_QQ浏览器网页保存_QQ浏览器转格式(6).docx
- 直接插入排序,冒泡排序,直接选择排序.zip
- 在排序2的基础上,再次对快排进行优化,其次增加快排非递归,归并排序,归并排序非递归版.zip
- 实现了7种排序算法.三种复杂度排序.三种nlogn复杂度排序(堆排序,归并排序,快速排序)一种线性复杂度的排序.zip
- 冒泡排序 直接选择排序 直接插入排序 随机快速排序 归并排序 堆排序.zip
- 课设-内部排序算法比较 包括冒泡排序、直接插入排序、简单选择排序、快速排序、希尔排序、归并排序和堆排序.zip
- Python排序算法.zip
- C语言实现直接插入排序、希尔排序、选择排序、冒泡排序、堆排序、快速排序、归并排序、计数排序,并带图详解.zip
- 常用工具集参考用于图像等数据处理
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功