Skip to content

结合YOLO目标检测的激光图像目标检测SLAM项目

License

Notifications You must be signed in to change notification settings

JS-622/YOLO-fast-lio-sam

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FAST_LIO_SAM

Object detect : YOLO

Front_end : fastlio2

Back_end : lio_sam

drawing drawing

drawing drawing

Related worked

1.FAST-LIO2为紧耦合的lio slam系统,因其缺乏前端,所以缺少全局一致性,参考lio_sam的后端部分,接入GTSAM进行后端优化。

2.FAST_LIO_SLAM的作者kim在FAST-LIO2的基础上,添加SC-PGO模块,通过加入ScanContext全局描述子,进行回环修正,SC-PGO模块与FAST-LIO2解耦,非常方便,很优秀的工作。

3.darknet_ros为YOLO系列的部分网络提供了便捷的ROS接口。

Prerequisites

  • Ubuntu 20.04 and ROS Noetic
  • PCL >= 1.8 (default for Ubuntu 18.04)
  • Eigen >= 3.3.4 (default for Ubuntu 18.04)
  • GTSAM >= 4.0.0(tested on 4.0.0-alpha2)

Build

cd YOUR_WORKSPACE/src
git clone https://github.com/JS-622/YOLO-fast-lio-sam.git
cd ..
catkin_make

Results show

For outdoor dataset

场景图片 my

未进行检测去除的运行效果

drawing drawing

使用单目相机进行赋色后的运行效果

drawing drawing

drawing drawing

使用YOLO进行目标检测的过程 my

检测结果对点云的投影

drawing drawing

drawing drawing

最终的建图效果(此处展示内容为去除了车辆)

drawing drawing

More

About

结合YOLO目标检测的激光图像目标检测SLAM项目

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published