ROS实验笔记之——Intel Realsense l515激光相机的使用

最新推荐文章于 2024-06-11 22:41:58 发布

gwpscut

最新推荐文章于 2024-06-11 22:41:58 发布

阅读量8.6k

点赞数 10

分类专栏： ROS 文章标签：自动驾驶 c++ 机器学习

本文链接：https://blog.csdn.net/gwplovekimi/article/details/120420756

版权

ROS 同时被 3 个专栏收录

147 篇文章 181 订阅

订阅专栏

移动机器人

82 篇文章 118 订阅

订阅专栏

SLAM

30 篇文章 32 订阅

订阅专栏

最近实验室购买了Intel Realsense l515相机。本博文记录使用过程~

驱动安装

先到官网安装驱动：https://github.com/IntelRealSense/realsense-roshttps://github.com/IntelRealSense/realsense-ros安装realsense2_camera

sudo apt-get install ros-melodic-realsense2-camera

然后运行下面命令启动相机

roslaunch realsense2_camera rs_camera.launch

看看所能出来的topic信息

/camera/color/camera_info
/camera/color/image_raw
/camera/color/image_raw/compressed
/camera/color/image_raw/compressed/parameter_descriptions
/camera/color/image_raw/compressed/parameter_updates
/camera/color/image_raw/compressedDepth
/camera/color/image_raw/compressedDepth/parameter_descriptions
/camera/color/image_raw/compressedDepth/parameter_updates
/camera/color/image_raw/theora
/camera/color/image_raw/theora/parameter_descriptions
/camera/color/image_raw/theora/parameter_updates
/camera/depth/camera_info
/camera/depth/image_rect_raw
/camera/depth/image_rect_raw/compressed
/camera/depth/image_rect_raw/compressed/parameter_descriptions
/camera/depth/image_rect_raw/compressed/parameter_updates
/camera/depth/image_rect_raw/compressedDepth
/camera/depth/image_rect_raw/compressedDepth/parameter_descriptions
/camera/depth/image_rect_raw/compressedDepth/parameter_updates
/camera/depth/image_rect_raw/theora
/camera/depth/image_rect_raw/theora/parameter_descriptions
/camera/depth/image_rect_raw/theora/parameter_updates
/camera/extrinsics/depth_to_color
/camera/l500_depth_sensor/parameter_descriptions
/camera/l500_depth_sensor/parameter_updates
/camera/motion_module/parameter_descriptions
/camera/motion_module/parameter_updates
/camera/realsense2_camera_manager/bond
/camera/rgb_camera/parameter_descriptions
/camera/rgb_camera/parameter_updates
/diagnostics
/rosout
/rosout_agg
/tf
/tf_static

若要显示点云，可运行

roslaunch realsense2_camera rs_camera.launch filters:=pointcloud

通过rviz来可视化（主要要显示点云信息需要将frame改为camera link）

运行下面节点来将深度信息与图像align

roslaunch realsense2_camera rs_camera.launch align_depth:=true

也可以通过image view来显示

rosrun rqt_image_view rqt_image_view

SLAM测试

之前博客《ROS实验笔记之——XBOX Kinect2 的使用及基于RTAB-MAP的建图》介绍过基于Kinect2的SLAM建图，这里试试用l515的效果~

安装rtabmap

sudo apt-get install ros-melodic-rtabmap-ros

rosrun rtabmap_ros pointcloud_to_depthimage cloud:=/camera/depth/color/points camera_info:=/camera/color/camera_info image_raw:=/camera/depth/image_rect_raw image:=/camera/color/image_raw _approx:=false _fill_holes_size:=2

roslaunch rtabmap_ros rtabmap.launch rtabmap_args:="--delete_db_on_start" depth_topic:=/camera/depth/image_rect_raw

无法使用。。topic完全不一样。。。

点进去，发现有rtabmap的launch文件

roslaunch realsense2_camera rs_rtabmap.launch

改为下面的试试

roslaunch realsense2_camera rs_rgbd.launch

然后通过改topic名字来实现rtabmap，发现还是不可以。。。。

# ISSUE: Use unite_imu_method:="copy" if imu topics keep stopping
$ roslaunch realsense2_camera rs_camera.launch \
    align_depth:=true \
    unite_imu_method:="linear_interpolation" \
    enable_gyro:=true \
     enable_accel:=true

$ rosrun imu_filter_madgwick imu_filter_node \
    _use_mag:=false \
    _publish_tf:=false \
    _world_frame:="enu" \
    /imu/data_raw:=/camera/imu \
    /imu/data:=/rtabmap/imu

安装

sudo apt-get install ros-melodic-imu-tools

即可～使用imu（imu_filter_madgwick - ROS Wiki）

GitHub - ccny-ros-pkg/imu_tools: ROS tools for IMU devices

然后运行

$ rosrun nodelet nodelet standalone rtabmap_ros/point_cloud_xyz \
   _approx_sync:=false  \
   /depth/image:=/camera/depth/image_rect_raw \
   /depth/camera_info:=/camera/depth/camera_info \
   _decimation:=4

$ roslaunch rtabmap_ros rtabmap.launch\
   rtabmap_args:="\
     --delete_db_on_start \
     --Icp/VoxelSize 0.05 \
     --Icp/PointToPlaneRadius 0 \
     --Icp/PointToPlaneK 20 \
     --Icp/CorrespondenceRatio 0.2 \
     --Icp/PMOutlierRatio 0.65 \
     --Icp/Epsilon 0.005 \
     --Icp/PointToPlaneMinComplexity 0 \
     --Odom/ScanKeyFrameThr 0.7 \
     --OdomF2M/ScanMaxSize 15000 \
     --Optimizer/GravitySigma 0.3 \
     --RGBD/ProximityPathMaxNeighbors 1 \
     --Reg/Strategy 1" \
   icp_odometry:=true \
   scan_cloud_topic:=/cloud \
   subscribe_scan_cloud:=true \
   depth_topic:=/camera/aligned_depth_to_color/image_raw \
   rgb_topic:=/camera/color/image_raw \
   camera_info_topic:=/camera/color/camera_info \
   approx_sync:=false \
   wait_imu_to_init:=true \
   imu_topic:=/rtabmap/imu

成功！感觉本质上就是学会怎么改好topic就行了，理解清楚每个topic的意义

使用如下服务可以用于从一个干净的数据库开始建图

rosservice call /rtabmap/reset

如果地图的背景变成红色，那是因为里程表丢失了。访问丢失的里程表(红色屏幕!)部分，了解为什么会发生这种情况!为了再次跟踪里程表，更换相机到红色出现前的最后一个位置，它应该能够重新计算里程表。另一种方法是重置里程表使用菜单选项““Edit->Reset odometry””(注意，一个新的地图创建每次里程表重置)。参见里程表自动复位另一种方法来处理里程表丢失(重置和继续相同的地图)。

若要加上定位，则运行

roslaunch rtabmap_ros rtabmap.launch\
   rtabmap_args:="\
     --delete_db_on_start \
     --Icp/VoxelSize 0.05 \
     --Icp/PointToPlaneRadius 0 \
     --Icp/PointToPlaneK 20 \
     --Icp/CorrespondenceRatio 0.2 \
     --Icp/PMOutlierRatio 0.65 \
     --Icp/Epsilon 0.005 \
     --Icp/PointToPlaneMinComplexity 0 \
     --Odom/ScanKeyFrameThr 0.7 \
     --OdomF2M/ScanMaxSize 15000 \
     --Optimizer/GravitySigma 0.3 \
     --RGBD/ProximityPathMaxNeighbors 1 \
     --Reg/Strategy 1" \
   icp_odometry:=true \
   scan_cloud_topic:=/cloud \
   subscribe_scan_cloud:=true \
   depth_topic:=/camera/aligned_depth_to_color/image_raw \
   rgb_topic:=/camera/color/image_raw \
   camera_info_topic:=/camera/color/camera_info \
   approx_sync:=false \
   wait_imu_to_init:=true \
   imu_topic:=/rtabmap/imu \
   localization:=true

基于intel realsense l515激光相机的rtabmap

用kinect效果

roslaunch kinect2_bridge kinect2_bridge.launch
roslaunch kinect2_bridge kinect2_bridge_custom_rviz_hd.launch
roslaunch rtabmap_ros rgbd_mapping_kinect2.launch


roslaunch kinect2_bridge kinect2_bridge.launch pulish_tf:=true

rosrun tf static_transform_publisher 0 0 0 -1.5707963267948966 0 -1.5707963267948966 camera_link kinect2_link 100 

roslaunch rtabmap_ros rtabmap.launch rtabmap_args:="--delete_db_on_start" rgb_topic:=/kinect2/qhd/image_color_rect depth_topic:=/kinect2/qhd/image_depth_rect camera_info_topic:=/kinect2/qhd/camera_info

rtabmap