Closed chenghaozhangswu closed 6 months ago
抱歉,我没有看懂,应该如何通过指令进入实时重建,还是说需要提前录制bag才行?
实际使用时不需要录制bag,只需要更改topic名字与config文件,使得和你使用的rgbd相机的输入适配就可以。
实际使用时不需要录制bag,只需要更改topic名字与config文件,使得和你使用的rgbd相机的输入适配就可以。
应该从哪里进入呢,是按照哪个步骤进行?
流程与Run in ROS(full SLAM)和其中的self-captured house dataset相同(只是不需要播bag,而是传感器实时输入),config的设置请参看Run in ROS(full SLAM)的第三点,以及其中use your own rgbd dataset中的注意事项
流程与Run in ROS(full SLAM)和其中的self-captured house dataset相同(只是不需要播bag,而是传感器实时输入),config的设置请参看Run in ROS(full SLAM)的第三点,以及其中use your own rgbd dataset中的注意事项
我使用的也是l515,是使用roslaunch realsense2_camera rs_aligned_depth_lidar.launch &取代播放bag吗?rs_aligned_depth_lidar.launch这里是如何配置的?
l515的配置可以参看 https://github.com/IntelRealSense/realsense-ros
l515的配置可以参看 https://github.com/IntelRealSense/realsense-ros
能否提供一个用自己l515相机实时扫描的操作步骤参考,谢谢
根据readme中Use your own RGB-D sequence修改config文件 根据https://github.com/IntelRealSense/realsense-ros 启动 realsense 根据readme中Self-captured House dataset的步骤3、4启动mapping和tracking
根据readme中Use your own RGB-D sequence修改config文件 根据https://github.com/IntelRealSense/realsense-ros 启动 realsense 根据readme中Self-captured House dataset的步骤3、4启动mapping和tracking
您好,请问能否提供那个realsense启动文件
根据readme中Use your own RGB-D sequence修改config文件 根据https://github.com/IntelRealSense/realsense-ros 启动 realsense 根据readme中Self-captured House dataset的步骤3、4启动mapping和tracking
您好,请问能否提供那个realsense启动文件
请根据自己的场景来设置诸如曝光等realsense参数,realsense的文档已经清楚写明了如何启动Usage Instructions,谢谢
根据readme中Use your own RGB-D sequence修改config文件 根据https://github.com/IntelRealSense/realsense-ros 启动 realsense 根据readme中Self-captured House dataset的步骤3、4启动mapping和tracking
您好,请问能否提供那个realsense启动文件
请根据自己的场景来设置诸如曝光等realsense参数,realsense的文档已经清楚写明了如何启动Usage Instructions,谢谢
能提供案例中录制tower_compass.bag的launch文件参考吗?
launch 文件:
<launch>
<arg name="serial_no" default=""/>
<arg name="json_file_path" default="$(find realsense2_camera)/config/L515_config_tower_manual_expo_white_high_bright_2.json"/>
<arg name="camera" default="camera"/>
<arg name="tf_prefix" default="$(arg camera)"/>
<arg name="fisheye_width" default="640"/>
<arg name="fisheye_height" default="480"/>
<arg name="enable_fisheye" default="true"/>
<arg name="depth_width" default="640"/>
<arg name="depth_height" default="480"/>
<arg name="enable_depth" default="true"/>
<arg name="infra_width" default="640"/>
<arg name="infra_height" default="480"/>
<arg name="enable_infra1" default="false"/>
<arg name="enable_infra2" default="false"/>
<arg name="color_width" default="640"/>
<arg name="color_height" default="480"/>
<arg name="enable_color" default="true"/>
<arg name="fisheye_fps" default="30"/>
<arg name="depth_fps" default="30"/>
<arg name="infra_fps" default="30"/>
<arg name="color_fps" default="30"/>
<arg name="gyro_fps" default="400"/>
<arg name="accel_fps" default="400"/>
<arg name="enable_gyro" default="true"/>
<arg name="enable_accel" default="true"/>
<arg name="enable_pose" default="true"/>
<arg name="enable_pointcloud" default="false"/>
<arg name="enable_sync" default="true"/>
<arg name="align_depth" default="true"/>
<arg name="filters" default=""/>
<arg name="clip_distance" default="-1"/>
<arg name="linear_accel_cov" default="0.01"/>
<arg name="initial_reset" default="false"/>
<arg name="unite_imu_method" default="linear_interpolation"/> <!-- Options are: [none, copy, linear_interpolation] -->
<rosparam>
/camera/motion_module/global_time_enabled: true
/camera/l500_depth_sensor/global_time_enabled: true
/camera/rgb_camera/global_time_enabled: true
/camera/rgb_camera/enable_auto_exposure: false
/camera/rgb_camera/enable_auto_white_balance: false
/camera/rgb_camera/exposure: 100
/camera/rgb_camera/white_balance: 4500
/camera/rgb_camera/gain: 4096
/camera/l500_depth_sensor/min_distance: 100
/camera/l500_depth_sensor/noise_filtering: 6
</rosparam>
<group ns="$(arg camera)">
<include file="$(find realsense2_camera)/launch/includes/nodelet.launch.xml">
<arg name="tf_prefix" value="$(arg tf_prefix)"/>
<arg name="serial_no" value="$(arg serial_no)"/>
<arg name="json_file_path" value="$(arg json_file_path)"/>
<arg name="enable_pointcloud" value="$(arg enable_pointcloud)"/>
<arg name="enable_sync" value="$(arg enable_sync)"/>
<arg name="align_depth" value="$(arg align_depth)"/>
<arg name="fisheye_width" value="$(arg fisheye_width)"/>
<arg name="fisheye_height" value="$(arg fisheye_height)"/>
<arg name="enable_fisheye" value="$(arg enable_fisheye)"/>
<arg name="depth_width" value="$(arg depth_width)"/>
<arg name="depth_height" value="$(arg depth_height)"/>
<arg name="enable_depth" value="$(arg enable_depth)"/>
<arg name="color_width" value="$(arg color_width)"/>
<arg name="color_height" value="$(arg color_height)"/>
<arg name="enable_color" value="$(arg enable_color)"/>
<arg name="infra_width" value="$(arg infra_width)"/>
<arg name="infra_height" value="$(arg infra_height)"/>
<arg name="enable_infra1" value="$(arg enable_infra1)"/>
<arg name="enable_infra2" value="$(arg enable_infra2)"/>
<arg name="fisheye_fps" value="$(arg fisheye_fps)"/>
<arg name="depth_fps" value="$(arg depth_fps)"/>
<arg name="infra_fps" value="$(arg infra_fps)"/>
<arg name="color_fps" value="$(arg color_fps)"/>
<arg name="gyro_fps" value="$(arg gyro_fps)"/>
<arg name="accel_fps" value="$(arg accel_fps)"/>
<arg name="enable_gyro" value="$(arg enable_gyro)"/>
<arg name="enable_accel" value="$(arg enable_accel)"/>
<param name="enable_pose" value="$(arg enable_pose)"/>
<arg name="filters" value="$(arg filters)"/>
<arg name="clip_distance" value="$(arg clip_distance)"/>
<arg name="linear_accel_cov" value="$(arg linear_accel_cov)"/>
<arg name="initial_reset" value="$(arg initial_reset)"/>
<arg name="unite_imu_method" value="$(arg unite_imu_method)"/>
</include>
</group>
<!-- <node pkg="rviz" type="rviz" name="rviz" args="-d $(find realsense2_camera)/rviz/rs_aligned_depth.rviz" /> -->
</launch>
config文件:
{
"device": {
"fw version": "01.05.08.01",
"name": "Intel RealSense L515",
"product line": "L500"
},
"parameters": {
"Alternate IR": 0.0,
"Apd Temperature": -9999,
"Confidence Threshold": 1,
"Depth Offset": 4.5,
"Depth Units": 0.000250000011874363,
"Digital Gain": 1,
"Enable IR Reflectivity": 0.0,
"Enable Max Usable Range": 0.0,
"Error Polling Enabled": 1,
"Frames Queue Size": 16,
"Freefall Detection Enabled": 1,
"Global Time Enabled": 1,
"Host Performance": 0.0,
"Humidity Temperature": 36.1058959960938,
"Inter Cam Sync Mode": 0.0,
"Invalidation Bypass": 0.0,
"LDD temperature": 36.3938369750977,
"Laser Power": 100,
"Ma Temperature": 34.7539749145508,
"Mc Temperature": 35.9714241027832,
"Min Distance": 250,
"Noise Estimation": 0.0,
"Noise Filtering": 6,
"Post Processing Sharpening": 1,
"Pre Processing Sharpening": 0.0,
"Receiver Gain": 9,
"Sensor Mode": 0.0,
"Visual Preset": 0.0
},
"schema version": 1,
"viewer": {
"stream-depth-format": "Z16",
"stream-fps": "30",
"stream-height": "480",
"stream-ir-format": "Y8",
"stream-width": "640"
}
}
launch 文件:
<launch> <arg name="serial_no" default=""/> <arg name="json_file_path" default="$(find realsense2_camera)/config/L515_config_tower_manual_expo_white_high_bright_2.json"/> <arg name="camera" default="camera"/> <arg name="tf_prefix" default="$(arg camera)"/> <arg name="fisheye_width" default="640"/> <arg name="fisheye_height" default="480"/> <arg name="enable_fisheye" default="true"/> <arg name="depth_width" default="640"/> <arg name="depth_height" default="480"/> <arg name="enable_depth" default="true"/> <arg name="infra_width" default="640"/> <arg name="infra_height" default="480"/> <arg name="enable_infra1" default="false"/> <arg name="enable_infra2" default="false"/> <arg name="color_width" default="640"/> <arg name="color_height" default="480"/> <arg name="enable_color" default="true"/> <arg name="fisheye_fps" default="30"/> <arg name="depth_fps" default="30"/> <arg name="infra_fps" default="30"/> <arg name="color_fps" default="30"/> <arg name="gyro_fps" default="400"/> <arg name="accel_fps" default="400"/> <arg name="enable_gyro" default="true"/> <arg name="enable_accel" default="true"/> <arg name="enable_pose" default="true"/> <arg name="enable_pointcloud" default="false"/> <arg name="enable_sync" default="true"/> <arg name="align_depth" default="true"/> <arg name="filters" default=""/> <arg name="clip_distance" default="-1"/> <arg name="linear_accel_cov" default="0.01"/> <arg name="initial_reset" default="false"/> <arg name="unite_imu_method" default="linear_interpolation"/> <!-- Options are: [none, copy, linear_interpolation] --> <rosparam> /camera/motion_module/global_time_enabled: true /camera/l500_depth_sensor/global_time_enabled: true /camera/rgb_camera/global_time_enabled: true /camera/rgb_camera/enable_auto_exposure: false /camera/rgb_camera/enable_auto_white_balance: false /camera/rgb_camera/exposure: 100 /camera/rgb_camera/white_balance: 4500 /camera/rgb_camera/gain: 4096 /camera/l500_depth_sensor/min_distance: 100 /camera/l500_depth_sensor/noise_filtering: 6 </rosparam> <group ns="$(arg camera)"> <include file="$(find realsense2_camera)/launch/includes/nodelet.launch.xml"> <arg name="tf_prefix" value="$(arg tf_prefix)"/> <arg name="serial_no" value="$(arg serial_no)"/> <arg name="json_file_path" value="$(arg json_file_path)"/> <arg name="enable_pointcloud" value="$(arg enable_pointcloud)"/> <arg name="enable_sync" value="$(arg enable_sync)"/> <arg name="align_depth" value="$(arg align_depth)"/> <arg name="fisheye_width" value="$(arg fisheye_width)"/> <arg name="fisheye_height" value="$(arg fisheye_height)"/> <arg name="enable_fisheye" value="$(arg enable_fisheye)"/> <arg name="depth_width" value="$(arg depth_width)"/> <arg name="depth_height" value="$(arg depth_height)"/> <arg name="enable_depth" value="$(arg enable_depth)"/> <arg name="color_width" value="$(arg color_width)"/> <arg name="color_height" value="$(arg color_height)"/> <arg name="enable_color" value="$(arg enable_color)"/> <arg name="infra_width" value="$(arg infra_width)"/> <arg name="infra_height" value="$(arg infra_height)"/> <arg name="enable_infra1" value="$(arg enable_infra1)"/> <arg name="enable_infra2" value="$(arg enable_infra2)"/> <arg name="fisheye_fps" value="$(arg fisheye_fps)"/> <arg name="depth_fps" value="$(arg depth_fps)"/> <arg name="infra_fps" value="$(arg infra_fps)"/> <arg name="color_fps" value="$(arg color_fps)"/> <arg name="gyro_fps" value="$(arg gyro_fps)"/> <arg name="accel_fps" value="$(arg accel_fps)"/> <arg name="enable_gyro" value="$(arg enable_gyro)"/> <arg name="enable_accel" value="$(arg enable_accel)"/> <param name="enable_pose" value="$(arg enable_pose)"/> <arg name="filters" value="$(arg filters)"/> <arg name="clip_distance" value="$(arg clip_distance)"/> <arg name="linear_accel_cov" value="$(arg linear_accel_cov)"/> <arg name="initial_reset" value="$(arg initial_reset)"/> <arg name="unite_imu_method" value="$(arg unite_imu_method)"/> </include> </group> <!-- <node pkg="rviz" type="rviz" name="rviz" args="-d $(find realsense2_camera)/rviz/rs_aligned_depth.rviz" /> --> </launch>
config文件:
{ "device": { "fw version": "01.05.08.01", "name": "Intel RealSense L515", "product line": "L500" }, "parameters": { "Alternate IR": 0.0, "Apd Temperature": -9999, "Confidence Threshold": 1, "Depth Offset": 4.5, "Depth Units": 0.000250000011874363, "Digital Gain": 1, "Enable IR Reflectivity": 0.0, "Enable Max Usable Range": 0.0, "Error Polling Enabled": 1, "Frames Queue Size": 16, "Freefall Detection Enabled": 1, "Global Time Enabled": 1, "Host Performance": 0.0, "Humidity Temperature": 36.1058959960938, "Inter Cam Sync Mode": 0.0, "Invalidation Bypass": 0.0, "LDD temperature": 36.3938369750977, "Laser Power": 100, "Ma Temperature": 34.7539749145508, "Mc Temperature": 35.9714241027832, "Min Distance": 250, "Noise Estimation": 0.0, "Noise Filtering": 6, "Post Processing Sharpening": 1, "Pre Processing Sharpening": 0.0, "Receiver Gain": 9, "Sensor Mode": 0.0, "Visual Preset": 0.0 }, "schema version": 1, "viewer": { "stream-depth-format": "Z16", "stream-fps": "30", "stream-height": "480", "stream-ir-format": "Y8", "stream-width": "640" } }
感谢您的解答,我已经成功地将数据传入,但是在生成mesh的时候又出现了: Traceback (most recent call last): File "demo/run_mapping.py", line 26, in
slam.run() File "/home/nvidia/H2-Mapping/mapping/src/H2Mapping.py", line 26, in run self.mapper.run(self.firstframe, update_pose=self.update_pose) File "/home/nvidia/H2-Mapping/mapping/src/mapping.py", line 252, in run mesh = self.extract_mesh(res=self.mesh_res, clean_mesh=False, map_states=self.map_states) AttributeError: 'Mapping' object has no attribute 'map_states' 这个问题
请问出现mapping start了吗?应该还是和输入的数据有关,请对比我们提供的bag,看下哪里不同。谢谢。
发件人: chenghaozhangswu @.> 发送时间: 星期一, 十月 16, 2023 10:10 收件人: SYSU-STAR/H2-Mapping @.> 抄送: JIANG Chenxing @.>; Comment @.> 主题: Re: [SYSU-STAR/H2-Mapping] 怎么实时重建? (Issue #8)
launch 文件:
config文件:
{ "device": { "fw version": "01.05.08.01", "name": "Intel RealSense L515", "product line": "L500" }, "parameters": { "Alternate IR": 0.0, "Apd Temperature": -9999, "Confidence Threshold": 1, "Depth Offset": 4.5, "Depth Units": 0.000250000011874363, "Digital Gain": 1, "Enable IR Reflectivity": 0.0, "Enable Max Usable Range": 0.0, "Error Polling Enabled": 1, "Frames Queue Size": 16, "Freefall Detection Enabled": 1, "Global Time Enabled": 1, "Host Performance": 0.0, "Humidity Temperature": 36.1058959960938, "Inter Cam Sync Mode": 0.0, "Invalidation Bypass": 0.0, "LDD temperature": 36.3938369750977, "Laser Power": 100, "Ma Temperature": 34.7539749145508, "Mc Temperature": 35.9714241027832, "Min Distance": 250, "Noise Estimation": 0.0, "Noise Filtering": 6, "Post Processing Sharpening": 1, "Pre Processing Sharpening": 0.0, "Receiver Gain": 9, "Sensor Mode": 0.0, "Visual Preset": 0.0 }, "schema version": 1, "viewer": { "stream-depth-format": "Z16", "stream-fps": "30", "stream-height": "480", "stream-ir-format": "Y8", "stream-width": "640" } }
感谢您的解答,我已经成功地将数据传入,但是在生成mesh的时候又出现了: Traceback (most recent call last): File "demo/run_mapping.py", line 26, in slam.run() File "/home/nvidia/H2-Mapping/mapping/src/H2Mapping.py", line 26, in run self.mapper.run(self.firstframe, update_pose=self.update_pose) File "/home/nvidia/H2-Mapping/mapping/src/mapping.py", line 252, in run mesh = self.extract_mesh(res=self.mesh_res, clean_mesh=False, map_states=self.map_states) AttributeError: 'Mapping' object has no attribute 'map_states' 这个问题
― Reply to this email directly, view it on GitHubhttps://github.com/SYSU-STAR/H2-Mapping/issues/8#issuecomment-1763618311, or unsubscribehttps://github.com/notifications/unsubscribe-auth/APMKKNTXNZWFOCPA7EBCOHDX7SJSDAVCNFSM6AAAAAA5WVNSROVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTONRTGYYTQMZRGE. You are receiving this because you commented.Message ID: @.***>
请问出现mapping start了吗?应该还是和输入的数据有关,请对比我们提供的bag,看下哪里不同。谢谢。 … ____ 发件人: chenghaozhangswu @.> 发送时间: 星期一, 十月 16, 2023 10:10 收件人: SYSU-STAR/H2-Mapping @.> 抄送: JIANG Chenxing @.>; Comment @.> 主题: Re: [SYSU-STAR/H2-Mapping] 怎么实时重建? (Issue #8) launch 文件:
config文件: { "device": { "fw version": "01.05.08.01", "name": "Intel RealSense L515", "product line": "L500" }, "parameters": { "Alternate IR": 0.0, "Apd Temperature": -9999, "Confidence Threshold": 1, "Depth Offset": 4.5, "Depth Units": 0.000250000011874363, "Digital Gain": 1, "Enable IR Reflectivity": 0.0, "Enable Max Usable Range": 0.0, "Error Polling Enabled": 1, "Frames Queue Size": 16, "Freefall Detection Enabled": 1, "Global Time Enabled": 1, "Host Performance": 0.0, "Humidity Temperature": 36.1058959960938, "Inter Cam Sync Mode": 0.0, "Invalidation Bypass": 0.0, "LDD temperature": 36.3938369750977, "Laser Power": 100, "Ma Temperature": 34.7539749145508, "Mc Temperature": 35.9714241027832, "Min Distance": 250, "Noise Estimation": 0.0, "Noise Filtering": 6, "Post Processing Sharpening": 1, "Pre Processing Sharpening": 0.0, "Receiver Gain": 9, "Sensor Mode": 0.0, "Visual Preset": 0.0 }, "schema version": 1, "viewer": { "stream-depth-format": "Z16", "stream-fps": "30", "stream-height": "480", "stream-ir-format": "Y8", "stream-width": "640" } } 感谢您的解答,我已经成功地将数据传入,但是在生成mesh的时候又出现了: Traceback (most recent call last): File "demo/run_mapping.py", line 26, in slam.run() File "/home/nvidia/H2-Mapping/mapping/src/H2Mapping.py", line 26, in run self.mapper.run(self.firstframe, update_pose=self.update_pose) File "/home/nvidia/H2-Mapping/mapping/src/mapping.py", line 252, in run mesh = self.extract_mesh(res=self.mesh_res, clean_mesh=False, map_states=self.map_states) AttributeError: 'Mapping' object has no attribute 'map_states' 这个问题 ― Reply to this email directly, view it on GitHub<#8 (comment)>, or unsubscribehttps://github.com/notifications/unsubscribe-auth/APMKKNTXNZWFOCPA7EBCOHDX7SJSDAVCNFSM6AAAAAA5WVNSROVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTONRTGYYTQMZRGE. You are receiving this because you commented.Message ID: @.***> /camera/motion_module/global_time_enabled: true /camera/l500_depth_sensor/global_time_enabled: true /camera/rgb_camera/global_time_enabled: true /camera/rgb_camera/enable_auto_exposure: false /camera/rgb_camera/enable_auto_white_balance: false /camera/rgb_camera/exposure: 100 /camera/rgb_camera/white_balance: 4500 /camera/rgb_camera/gain: 4096 /camera/l500_depth_sensor/min_distance: 100 /camera/l500_depth_sensor/noise_filtering: 6
出现了mapping start
mapping start后有出现数字吗?没有的话就说明输入的数据不对。请确认readme中“use your rgbd sequence”的note都注意到了。同时建议debug step by step看一下和播放bag的运行有什么区别。
获取 Outlook for iOShttps://aka.ms/o0ukef
发件人: chenghaozhangswu @.> 发送时间: Monday, October 16, 2023 10:38:42 AM 收件人: SYSU-STAR/H2-Mapping @.> 抄送: JIANG Chenxing @.>; Comment @.> 主题: Re: [SYSU-STAR/H2-Mapping] 怎么实时重建? (Issue #8)
请问出现mapping start了吗?应该还是和输入的数据有关,请对比我们提供的bag,看下哪里不同。谢谢。 … ____ 发件人: chenghaozhangswu @.> 发送时间: 星期一, 十月 16, 2023 10:10 收件人: SYSU-STAR/H2-Mapping @.> 抄送: JIANG Chenxing @.>; Comment @.> 主题: Re: [SYSU-STAR/H2-Mapping] 怎么实时重建? (Issue #8https://github.com/SYSU-STAR/H2-Mapping/issues/8) launch 文件: /camera/motion_module/global_time_enabled: true /camera/l500_depth_sensor/global_time_enabled: true /camera/rgb_camera/global_time_enabled: true /camera/rgb_camera/enable_auto_exposure: false /camera/rgb_camera/enable_auto_white_balance: false /camera/rgb_camera/exposure: 100 /camera/rgb_camera/white_balance: 4500 /camera/rgb_camera/gain: 4096 /camera/l500_depth_sensor/min_distance: 100 /camera/l500_depth_sensor/noise_filtering: 6 config文件: { "device": { "fw version": "01.05.08.01", "name": "Intel RealSense L515", "product line": "L500" }, "parameters": { "Alternate IR": 0.0, "Apd Temperature": -9999, "Confidence Threshold": 1, "Depth Offset": 4.5, "Depth Units": 0.000250000011874363, "Digital Gain": 1, "Enable IR Reflectivity": 0.0, "Enable Max Usable Range": 0.0, "Error Polling Enabled": 1, "Frames Queue Size": 16, "Freefall Detection Enabled": 1, "Global Time Enabled": 1, "Host Performance": 0.0, "Humidity Temperature": 36.1058959960938, "Inter Cam Sync Mode": 0.0, "Invalidation Bypass": 0.0, "LDD temperature": 36.3938369750977, "Laser Power": 100, "Ma Temperature": 34.7539749145508, "Mc Temperature": 35.9714241027832, "Min Distance": 250, "Noise Estimation": 0.0, "Noise Filtering": 6, "Post Processing Sharpening": 1, "Pre Processing Sharpening": 0.0, "Receiver Gain": 9, "Sensor Mode": 0.0, "Visual Preset": 0.0 }, "schema version": 1, "viewer": { "stream-depth-format": "Z16", "stream-fps": "30", "stream-height": "480", "stream-ir-format": "Y8", "stream-width": "640" } } 感谢您的解答,我已经成功地将数据传入,但是在生成mesh的时候又出现了: Traceback (most recent call last): File "demo/run_mapping.py", line 26, in slam.run() File "/home/nvidia/H2-Mapping/mapping/src/H2Mapping.py", line 26, in run self.mapper.run(self.firstframe, update_pose=self.update_pose) File "/home/nvidia/H2-Mapping/mapping/src/mapping.py", line 252, in run mesh = self.extract_mesh(res=self.mesh_res, clean_mesh=False, map_states=self.map_states) AttributeError: 'Mapping' object has no attribute 'map_states' 这个问题 D Reply to this email directly, view it on GitHub<#8 (comment)https://github.com/SYSU-STAR/H2-Mapping/issues/8#issuecomment-1763618311>, or unsubscribehttps://github.com/notifications/unsubscribe-auth/APMKKNTXNZWFOCPA7EBCOHDX7SJSDAVCNFSM6AAAAAA5WVNSROVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTONRTGYYTQMZRGE. You are receiving this because you commented.Message ID: @.***>
出现了mapping start
― Reply to this email directly, view it on GitHubhttps://github.com/SYSU-STAR/H2-Mapping/issues/8#issuecomment-1763636208, or unsubscribehttps://github.com/notifications/unsubscribe-auth/APMKKNQZ23XCQDLJNRERS53X7SM3FAVCNFSM6AAAAAA5WVNSROVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTONRTGYZTMMRQHA. You are receiving this because you commented.Message ID: @.***>
好的,没有出现数字
嗯,那就说明没有接到合理的数据。
发件人: chenghaozhangswu @.> 发送时间: Monday, October 16, 2023 10:42:55 AM 收件人: SYSU-STAR/H2-Mapping @.> 抄送: JIANG Chenxing @.>; Comment @.> 主题: Re: [SYSU-STAR/H2-Mapping] 怎么实时重建? (Issue #8)
好的,没有出现数字
― Reply to this email directly, view it on GitHubhttps://github.com/SYSU-STAR/H2-Mapping/issues/8#issuecomment-1763638955, or unsubscribehttps://github.com/notifications/unsubscribe-auth/APMKKNQHGVC7V4QWE33CLL3X7SNK7AVCNFSM6AAAAAA5WVNSROVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTONRTGYZTQOJVGU. You are receiving this because you commented.Message ID: @.***>
作者在下面发过了
┢┦aΡpy笶 @.***
------------------ 原始邮件 ------------------ 发件人: "SYSU-STAR/H2-Mapping" @.>; 发送时间: 2023年10月15日(星期天) 下午4:27 @.>; @.**@.>; 主题: Re: [SYSU-STAR/H2-Mapping] 怎么实时重建? (Issue #8)
请问L515_config_tower_manual_expo_white_high_bright_2.json能提供给大家参考一下吗?谢谢 主要不知道该设置哪些参数和格式
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
我是将camera_pose改成cam_pose之后才接收到合理的数据,可以走完实际采集的流程。 另外我想问一下原作,tower场景就两三个小房间,录制了15分钟,拍摄速度十分缓慢,这主要出于什么考虑?是担心L515相机运动模糊还是建图线程处理能力限制?谢谢
我是将camera_pose改成cam_pose之后才接收到合理的数据,可以走完实际采集的流程。 另外我想问一下原作,tower场景就两三个小房间,录制了15分钟,拍摄速度十分缓慢,这主要出于什么考虑?是担心L515相机运动模糊还是建图线程处理能力限制?谢谢
感谢发现的一个我们清理代码时没检查出的bug😊,因为提供的bag中存在了一个当时实验时记录的camera_pose的topic,所以在dvins代码中为了避免冲突,将topic改成cam_pose了,现已更新,谢谢。 针对你提到的问题,首先L515因为是卷帘快门,运动模糊确实比较严重,同时因为机载电脑上算力相对有限,因此实验时为了让最后建图效果更好,所以选择了较慢的移动。但后续我们将记录下来的中间结果可视化后也发现,其实一些地方很早就已经建好了,是可以走的快一些的hhh。 在我们后续的工作中也会针对建图速度做更进一步的提升,谢谢你的关注和意见。
感谢您的神速回复!!我尝试使用了D455全局快门相机来采集数据,但可能是由于rgb/imu标定信息,或者launch文件里对应的json_file_path配置parameters参数没对,目前建图效果比较差。 关于这些参数,您有什么建议吗? 例如
"parameters": {
"Alternate IR": 0.0,
"Apd Temperature": -9999,
"Confidence Threshold": 1,
"Depth Offset": 4.5,
"Depth Units": 0.000250000011874363,
"Digital Gain": 1,
"Enable IR Reflectivity": 0.0,
"Enable Max Usable Range": 0.0,
"Error Polling Enabled": 1,
"Frames Queue Size": 16,
"Freefall Detection Enabled": 1,
"Global Time Enabled": 1,
"Host Performance": 0.0,
"Humidity Temperature": 36.1058959960938,
"Inter Cam Sync Mode": 0.0,
"Invalidation Bypass": 0.0,
"LDD temperature": 36.3938369750977,
"Laser Power": 100,
"Ma Temperature": 34.7539749145508,
"Mc Temperature": 35.9714241027832,
"Min Distance": 250,
"Noise Estimation": 0.0,
"Noise Filtering": 6,
"Post Processing Sharpening": 1,
"Pre Processing Sharpening": 0.0,
"Receiver Gain": 9,
"Sensor Mode": 0.0,
"Visual Preset": 0.0
},
或者launch文件里的
<rosparam>
/camera/motion_module/global_time_enabled: true
/camera/l500_depth_sensor/global_time_enabled: true
/camera/rgb_camera/global_time_enabled: true
/camera/rgb_camera/enable_auto_exposure: false
/camera/rgb_camera/enable_auto_white_balance: false
/camera/rgb_camera/exposure: 100
/camera/rgb_camera/white_balance: 4500
/camera/rgb_camera/gain: 4096
/camera/l500_depth_sensor/min_distance: 100
/camera/l500_depth_sensor/noise_filtering: 6
</rosparam>
我不太清楚这里哪些参数相对重要一点,请给指导一下~谢谢!
感谢您的神速回复!!我尝试使用了D455全局快门相机来采集数据,但可能是由于rgb/imu标定信息,或者launch文件里对应的json_file_path配置parameters参数没对,目前建图效果比较差。 关于这些参数,您有什么建议吗? 例如
"parameters": { "Alternate IR": 0.0, "Apd Temperature": -9999, "Confidence Threshold": 1, "Depth Offset": 4.5, "Depth Units": 0.000250000011874363, "Digital Gain": 1, "Enable IR Reflectivity": 0.0, "Enable Max Usable Range": 0.0, "Error Polling Enabled": 1, "Frames Queue Size": 16, "Freefall Detection Enabled": 1, "Global Time Enabled": 1, "Host Performance": 0.0, "Humidity Temperature": 36.1058959960938, "Inter Cam Sync Mode": 0.0, "Invalidation Bypass": 0.0, "LDD temperature": 36.3938369750977, "Laser Power": 100, "Ma Temperature": 34.7539749145508, "Mc Temperature": 35.9714241027832, "Min Distance": 250, "Noise Estimation": 0.0, "Noise Filtering": 6, "Post Processing Sharpening": 1, "Pre Processing Sharpening": 0.0, "Receiver Gain": 9, "Sensor Mode": 0.0, "Visual Preset": 0.0 },
或者launch文件里的
<rosparam> /camera/motion_module/global_time_enabled: true /camera/l500_depth_sensor/global_time_enabled: true /camera/rgb_camera/global_time_enabled: true /camera/rgb_camera/enable_auto_exposure: false /camera/rgb_camera/enable_auto_white_balance: false /camera/rgb_camera/exposure: 100 /camera/rgb_camera/white_balance: 4500 /camera/rgb_camera/gain: 4096 /camera/l500_depth_sensor/min_distance: 100 /camera/l500_depth_sensor/noise_filtering: 6 </rosparam>
我不太清楚这里哪些参数相对重要一点,请给指导一下~谢谢!
首先需要保证tracking部分的准确性,可以先单独跑tracking,看看跟踪精度如何,诸如imu bias,time delay等都需要根据你的传感器进行设置,相关设置可以参看网上有关vins-fusion的资料;其次对于455,请确保深度和rgb的对齐的;确保内参正确;对于参数的话,建议打开realsense_viewer来可视化调整,rgb层面比较重要的是“ /camera/rgb_camera/exposure: 100、 /camera/rgb_camera/white_balance: 4500、 /camera/rgb_camera/gain: 4096 ”,另外我没有使用过455,请参阅realsense文档,可能和515的配置会有不同,因为毕竟是两种深度传感器,谢谢。
感谢回复,我以后试验一下D455配置,并将可能的参数共享上来。 BTW: 在“use-your-own-rgb-d-sequence”参数配置过程中您提到了offset,bound,num_vertexes三个指标,例如tower场景:
offset: 10 # used to make make the coordinate of each point positive
bound: [ [ 0.0,20.0 ],[ 0.0,20.0 ],[ 0.0,10.0 ] ] # [x_min,x_max],[y_min,y_max],[z_min,z_max]
num_vertexes: 200000
我的问题是
获取 Outlook for iOShttps://aka.ms/o0ukef
发件人: Mingzhe LV @.> 发送时间: Tuesday, October 17, 2023 10:09:47 AM 收件人: SYSU-STAR/H2-Mapping @.> 抄送: JIANG Chenxing @.>; Comment @.> 主题: Re: [SYSU-STAR/H2-Mapping] 怎么实时重建? (Issue #8)
感谢回复,我以后试验一下D455配置,并将可能的参数共享上来。 BTW: 在“use-your-own-rgb-d-sequence”参数配置过程中您提到了offset,bound,num_vertexes三个指标,例如tower场景:
offset: 10 # used to make make the coordinate of each point positive bound: [ [ 0.0,20.0 ],[ 0.0,20.0 ],[ 0.0,10.0 ] ] # [x_min,x_max],[y_min,y_max],[z_min,z_max] num_vertexes: 200000
我的问题是
― Reply to this email directly, view it on GitHubhttps://github.com/SYSU-STAR/H2-Mapping/issues/8#issuecomment-1765543411, or unsubscribehttps://github.com/notifications/unsubscribe-auth/APMKKNWIWVI2G5LQ73UXQF3X7XSGXAVCNFSM6AAAAAA5WVNSROVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTONRVGU2DGNBRGE. You are receiving this because you commented.Message ID: @.***>
感谢您的神速回复!!我尝试使用了D455全局快门相机来采集数据,但可能是由于rgb/imu标定信息,或者launch文件里对应的json_file_path配置parameters参数没对,目前建图效果比较差。 关于这些参数,您有什么建议吗? 例如
"parameters": { "Alternate IR": 0.0, "Apd Temperature": -9999, "Confidence Threshold": 1, "Depth Offset": 4.5, "Depth Units": 0.000250000011874363, "Digital Gain": 1, "Enable IR Reflectivity": 0.0, "Enable Max Usable Range": 0.0, "Error Polling Enabled": 1, "Frames Queue Size": 16, "Freefall Detection Enabled": 1, "Global Time Enabled": 1, "Host Performance": 0.0, "Humidity Temperature": 36.1058959960938, "Inter Cam Sync Mode": 0.0, "Invalidation Bypass": 0.0, "LDD temperature": 36.3938369750977, "Laser Power": 100, "Ma Temperature": 34.7539749145508, "Mc Temperature": 35.9714241027832, "Min Distance": 250, "Noise Estimation": 0.0, "Noise Filtering": 6, "Post Processing Sharpening": 1, "Pre Processing Sharpening": 0.0, "Receiver Gain": 9, "Sensor Mode": 0.0, "Visual Preset": 0.0 },
或者launch文件里的
<rosparam> /camera/motion_module/global_time_enabled: true /camera/l500_depth_sensor/global_time_enabled: true /camera/rgb_camera/global_time_enabled: true /camera/rgb_camera/enable_auto_exposure: false /camera/rgb_camera/enable_auto_white_balance: false /camera/rgb_camera/exposure: 100 /camera/rgb_camera/white_balance: 4500 /camera/rgb_camera/gain: 4096 /camera/l500_depth_sensor/min_distance: 100 /camera/l500_depth_sensor/noise_filtering: 6 </rosparam>
我不太清楚这里哪些参数相对重要一点,请给指导一下~谢谢!
我的重建结果也比较模糊
能不能把你的重建结果贴上来一起分析一波? 我猜测效果可能和以下配置有关:
能不能把你的重建结果贴上来一起分析一波? 我猜测效果可能和以下配置有关:
- 位姿估计准确程度
- 光照条件与对应的rgb_camera/exposure, white_balance, gain配置参数
- 建图尺寸设置的范围
- 照片是否有运动模糊
- 拍摄场景面积与拍摄时长
能不能把你的重建结果贴上来一起分析一波? 我猜测效果可能和以下配置有关:
- 位姿估计准确程度
- 光照条件与对应的rgb_camera/exposure, white_balance, gain配置参数
- 建图尺寸设置的范围
- 照片是否有运动模糊
- 拍摄场景面积与拍摄时长
你的重建结果如何?
跟我的差不多哦,精度不高,能调吗?
我是想着先尽量低速拍摄,得到尽量不模糊的图片,和准确的位姿,至于其他参数rgb_camera/exposure, white_balance, gain,还需要根据具体光照环境调节。 如果有什么心得可以在这里交流。
请问我应该怎么修改,能够实时扫描并看到重建效果
因为实时marching cube可视化太慢了,暂时不支持实时查看,谢谢。
获取 Outlook for iOShttps://aka.ms/o0ukef
发件人: chenghaozhangswu @.> 发送时间: Tuesday, October 24, 2023 11:14:45 AM 收件人: SYSU-STAR/H2-Mapping @.> 抄送: JIANG Chenxing @.>; Comment @.> 主题: Re: [SYSU-STAR/H2-Mapping] 怎么实时重建? (Issue #8)
请问我应该怎么修改,能够实时扫描并看到重建效果
― Reply to this email directly, view it on GitHubhttps://github.com/SYSU-STAR/H2-Mapping/issues/8#issuecomment-1776436840, or unsubscribehttps://github.com/notifications/unsubscribe-auth/APMKKNXYXJOI6I4PVTLS57DYA4XCLAVCNFSM6AAAAAA5WVNSROVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTONZWGQZTMOBUGA. You are receiving this because you commented.Message ID: @.***>
请问您在设置offset为较大的数(例如30 )的时候出现过错误吗?
File "/home/echo/H2-Mapping/mapping/src/functions/render_helpers.py", line 451, in bundle_adjust_frames assert (hits.sum() > 0) AssertionError
请问您在设置offset为较大的数(例如30 )的时候出现过错误吗?
File "/home/echo/H2-Mapping/mapping/src/functions/render_helpers.py", line 451, in bundle_adjust_frames assert (hits.sum() > 0) AssertionError
请问是跑replica/room0出错了吗
请问您在设置offset为较大的数(例如30 )的时候出现过错误吗?
File "/home/echo/H2-Mapping/mapping/src/functions/render_helpers.py", line 451, in bundle_adjust_frames assert (hits.sum() > 0) AssertionError
请问是跑replica/room0出错了吗 感谢神速度! 我是在跑自己录制的ros包的时候出现错误的. 想在稍微大一些的场景中运行,不知道该如何设置. 这个是我的H2Mapping运行结果和点云结果
![]()
我好像知道了,是设置max_depth的值吗?
请问您在设置offset为较大的数(例如30 )的时候出现过错误吗?
File "/home/echo/H2-Mapping/mapping/src/functions/render_helpers.py", line 451, in bundle_adjust_frames assert (hits.sum() > 0) AssertionError
请问是跑replica/room0出错了吗 感谢神速度! 我是在跑自己录制的ros包的时候出现错误的. 想在稍微大一些的场景中运行,不知道该如何设置. 这个是我的H2Mapping运行结果和点云结果
![]()
offset的作用是让点云的坐标都是正的,首先需要确认一下30是否足够。其次,看报错是因为没有ray接触到已有的voxel。可以看一下是不是当前帧的点云都大于max_depth了。
你好,请问真实采集数据时,采用的是L515自带IMU还是飞控的IMU呢,这个标定过程有参考手册吗
你好,请问真实采集数据时,采用的是L515自带IMU还是飞控的IMU呢,这个标定过程有参考手册吗
视频中的手持设备实验(也就是提供的bag)是使用的L515自带的IMU,飞机实验使用的是飞控IMU,标定可以使用kalibr:https://github.com/ethz-asl/kalibr
我用L515采集数据,发现这个不支持640 480 分辨率,您有遇到这个情况麻?我看你的参数是这个分辨率 roslaunch realsense2_camera rs_aligned_depth_lidar.launch ... logging to /home/nuc/.ros/log/0fa707be-8464-11ee-ad72-e0e1a99f291f/roslaunch-nuc-NUC12WSKi7-12274.log Checking log directory for disk usage. This may take a while. Press Ctrl-C to interrupt Done checking log file disk usage. Usage is <1GB.
WARN: unrecognized 'param' tag in
PARAMETERS
NODES /camera/ realsense2_camera (nodelet/nodelet) realsense2_camera_manager (nodelet/nodelet)
auto-starting new master process[master]: started with pid [12288] ROS_MASTER_URI=http://localhost:11311
setting /run_id to 0fa707be-8464-11ee-ad72-e0e1a99f291f
process[rosout-1]: started with pid [12299]
started core service [/rosout]
process[camera/realsense2_camera_manager-2]: started with pid [12306]
process[camera/realsense2_camera-3]: started with pid [12307]
[ INFO] [1700127579.429225089]: Initializing nodelet with 16 worker threads.
[ INFO] [1700127579.502838398]: RealSense ROS v2.3.2
[ INFO] [1700127579.502864613]: Built with LibRealSense v2.50.0
[ INFO] [1700127579.502872028]: Running with LibRealSense v2.50.0
[ INFO] [1700127579.521869695]:
16/11 17:39:39,877 WARNING [140637927667456] (messenger-libusb.cpp:42) control_transfer returned error, index: 300, error: Success, number: 0
[ INFO] [1700127580.052675988]: Device with serial number f1231548 was found.
[ INFO] [1700127580.052727489]: Device with physical ID 4-2-2 was found. [ INFO] [1700127580.052738980]: Device with name Intel RealSense L515 was found. [ INFO] [1700127580.053221953]: Device with port number 4-2 was found. [ INFO] [1700127580.053245072]: Device USB type: 3.2
16/11 17:39:40,164 WARNING [140637927667456] (messenger-libusb.cpp:42) control_transfer returned error, index: 300, error: Success, number: 0 [ INFO] [1700127580.247091541]: JSON file is loaded! (/home/nuc/zengjing/H2-Mapping/src/realsense-ros/realsense2_camera/config/L515_config_ri.json) [ INFO] [1700127580.247219750]: ROS Node Namespace: camera [ INFO] [1700127580.247259489]: Device Name: Intel RealSense L515 [ INFO] [1700127580.247284971]: Device Serial No: f1231548 [ INFO] [1700127580.247314456]: Device physical port: 4-2-2 [ INFO] [1700127580.247361584]: Device FW version: 01.05.04.01 [ INFO] [1700127580.247392233]: Device Product ID: 0x0B64 [ INFO] [1700127580.247421277]: Enable PointCloud: Off [ INFO] [1700127580.247443274]: Align Depth: On [ INFO] [1700127580.247475288]: Sync Mode: On [ INFO] [1700127580.247576935]: Device Sensors: [ INFO] [1700127580.313725235]: L500 Depth Sensor was found. [ INFO] [1700127580.326932079]: RGB Camera was found. [ INFO] [1700127580.327205044]: Motion Module was found. [ INFO] [1700127580.327275935]: (Fisheye, 0) sensor isn't supported by current device! -- Skipping... [ INFO] [1700127580.327900607]: num_filters: 1 [ INFO] [1700127580.327929384]: Setting Dynamic reconfig parameters. [ INFO] [1700127581.542798432]: Done Setting Dynamic reconfig parameters. [ INFO] [1700127581.543512357]: depth stream is enabled - width: 640, height: 480, fps: 30, Format: Z16 [ WARN] [1700127581.543679290]: Given stream configuration is not supported by the device! Stream: Color, Stream Index: 0, Width: 640, Height: 480, FPS: 30, Format: None [ WARN] [1700127581.543736784]: Using default profile instead. [ INFO] [1700127581.545707096]: color stream is enabled - width: 1280, height: 720, fps: 30, Format: RGB8 [ INFO] [1700127581.545997981]: confidence stream is enabled - width: 640, height: 480, fps: 30, Format: RAW8 [ INFO] [1700127581.548054474]: gyro stream is enabled - fps: 400 [ INFO] [1700127581.548081743]: accel stream is enabled - fps: 400
[ INFO] [1700127581.550588003]: Expected frequency for depth = 30.00000 [ INFO] [1700127581.568369720]: Expected frequency for color = 30.00000 [ INFO] [1700127581.580516485]: Expected frequency for aligned_depth_to_color = 30.00000 [ INFO] [1700127581.592685761]: Expected frequency for confidence = 30.00000 [ INFO] [1700127581.599921865]: Start publisher IMU
我使用的你的Launch config配置,不知道问题出在哪里,是515不支持这个分辨率?
我用的就是640*480,提供的bag里的图也就是这个分辨率
发件人: Jing Zeng @.> 发送时间: Thursday, November 16, 2023 5:55:52 PM 收件人: SYSU-STAR/H2-Mapping @.> 抄送: JIANG Chenxing @.>; Comment @.> 主题: Re: [SYSU-STAR/H2-Mapping] 怎么实时重建? (Issue #8)
我使用的你的Launch config配置,不知道问题出在哪里,是515不支持这个分辨率?
― Reply to this email directly, view it on GitHubhttps://github.com/SYSU-STAR/H2-Mapping/issues/8#issuecomment-1814120008, or unsubscribehttps://github.com/notifications/unsubscribe-auth/APMKKNWEDRAJA4XN6VLJSOTYEXPKRAVCNFSM6AAAAAA5WVNSROVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQMJUGEZDAMBQHA. You are receiving this because you commented.Message ID: @.***>
论文中的实物实验就是使用了“Run in ROS(full SLAM)” 中的代码,谢谢。