zhoujankin / multimap3d Goto Github PK

Input sensor was set to: RGB-D
[RGBD-4] process has died [pid 164263, exit code -11, cmd /home/gtf/rosCode/orb_dense/devel/lib/orb_slam2_dense/RGBD /home/gtf/rosCode/orb_dense/src/MultiMap3D/ORB-SLAM2_DENSE-master/tools/ORBvoc.bin /home/gtf/rosCode/orb_dense/src/MultiMap3D/ORB-SLAM2_DENSE-master/Examples/ROS/ORB_SLAM2_DENSE/params/spark.yaml __name:=RGBD __log:=/home/gtf/.ros/log/a98261f2-36e4-11ef-bc30-4f3eb0a198f4/RGBD-4.log].
log file: /home/gtf/.ros/log/a98261f2-36e4-11ef-bc30-4f3eb0a198f4/RGBD-4*.log

Hello,I encountered the same problem. Has anyone solved it? Thank you very much for your help!

你好，编译过程都没有问题，但是我在SLAM端遇到了这个问题：
New map created with 1208 points
[ERROR] [1704960263.885057833]: Wait transform timeout between: [camera_footprint]<--[camera_optical], timeout 1.000000 s
[ERROR] [1704960264.946798654]: Wait transform timeout between: [camera_footprint]<--[camera_optical], timeout 1.000000 s
[ERROR] [1704960266.004162038]: Wait transform timeout between: [camera_footprint]<--[camera_optical], timeout 1.000000 s
[ERROR] [1704960267.060365697]: Wait transform timeout between: [camera_footprint]<--[camera_optical], timeout 1.000000 s
[ERROR] [1704960268.119024658]: Wait transform timeout between: [camera_footprint]<--[camera_optical], timeout 1.000000 s
receive a keyframe, Frame id = 5 , KF No.1
******************* Running PointCloudMapping thread wake. *******************
No valid point in pass through filter range!
[RGBD-3] process has died
请问您知道是什么原因吗？感谢您的回复！

您好！我只剩下最后一点点就可以部署完成了，麻烦您有时间帮我看看错误原因～

1. python fcaf3d_sort_demo.py
   load checkpoint from local path: /home/river/3d/checkpoints/fcaf3d_8x2_scannet-3d-18class_20220805_084956.pth
   start

2. roslaunch orb_slam_dense tum_pioneers.launch

至此，slam端正常运行，但是在检测端出现以下报错：
load checkpoint from local path: /home/river/3d/checkpoints/fcaf3d_8x2_scannet-3d-18class_20220805_084956.pth
start
[ERROR] [1705323430.408357, 12.569359]: bad callback: <function callback at 0x7ff9bdb3f550>
Traceback (most recent call last):
File "/opt/ros/noetic/lib/python3/dist-packages/rospy/topics.py", line 750, in _invoke_callback
cb(msg)
File "fcaf3d_river.py", line 83, in callback
result, data = inference_detector(model, points_mmdet3d)
File "/home/river/anaconda3/envs/3d3/lib/python3.8/site-packages/mmdet3d-1.0.0rc6-py3.8.egg/mmdet3d/apis/inference.py", line 140, in inference_detector
data = test_pipeline(data)
File "/home/river/anaconda3/envs/3d3/lib/python3.8/site-packages/mmdet3d-1.0.0rc6-py3.8.egg/mmdet3d/datasets/pipelines/compose.py", line 49, in call
data = t(data)
File "/home/river/anaconda3/envs/3d3/lib/python3.8/site-packages/mmdet3d-1.0.0rc6-py3.8.egg/mmdet3d/datasets/pipelines/test_time_aug.py", line 213, in call
data = self.transforms(_results)
File "/home/river/anaconda3/envs/3d3/lib/python3.8/site-packages/mmdet3d-1.0.0rc6-py3.8.egg/mmdet3d/datasets/pipelines/compose.py", line 49, in call
data = t(data)
File "/home/river/anaconda3/envs/3d3/lib/python3.8/site-packages/mmdet3d-1.0.0rc6-py3.8.egg/mmdet3d/datasets/pipelines/loading.py", line 328, in call
assert points.attribute_dims is not None and
AssertionError: Expect points have color attribute

最后这行报错信息是和点云的颜色有关吗？感谢您的回复～

Hello!
I would like to ask how to get a stable 3D target detection result? Because I found that the detection results of each frame will change in scale and position.
And ate the same time, I want to ask dou you convert the detection results to the world coordinate system according to the result of SLAM?
thank you for your reply!

Hello author, thank you for your excellent work. I hope to reproduce your work, but I have encountered a problem: when I run rosluanch, I can finally see rviz but no map or image is displayed.
But when I run ORB-SLAM2_DENSE that you previously used, I am able to create a map. May I ask if you can help me see where the problem is?

1）This is the naming convention for Python

(multimap3d) l@pc:~/slam/vslam/multiMap3D$ python src/MultiMap3D/ORB-SLAM2_DENSE-master/Examples/ROS/ORB_SLAM2_DENSE/scripts/fcaf3d_sort_demo.py
@@@@@/home/l/slam/vslam/multiMap3D/src/MultiMap3D/ORB-SLAM2_DENSE-master/Examples/ROS/ORB_SLAM2_DENSE/scripts/room_classifier/features_for_each_label_FEATURES_18.pkl
Accuracy = 0.81
/home/l/anaconda3/envs/multimap3d/lib/python3.8/site-packages/MinkowskiEngine/init.py:221: UserWarning: The MinkowskiEngine was compiled with CPU_ONLY flag. If you want to compile with CUDA support, make sure torch.cuda.is_available() is True when you install MinkowskiEngine.
warnings.warn(
Loads checkpoint by local backend from path: /home/l/slam/vslam/multiMap3D/src/MultiMap3D/checkpoints/fcaf3d_8x2_scannet-3d-18class_20220805_084956.pth
start

2）
2-1)
tum_pioneer.launch

2-2）
rgbd_launch.launch

3）These are some running images

你好，请问您在运行过程中有遇到这个问题吗？
python fcaf3d_sort_demo.py
终端输出以下信息：
[ERROR] [1704789826.154335, 40.778008]: bad callback: <function callback at 0x7f23bddea9d0>
Traceback (most recent call last):
File "/opt/ros/noetic/lib/python3/dist-packages/rospy/topics.py", line 750, in _invoke_callback
cb(msg)
File "fcaf3d_river.py", line 125, in callback
dets = np.concatenate(dets)
File "<array_function internals>", line 180, in concatenate
ValueError: need at least one array to concatenate

感谢您的回复～

Thank you for your excellent work.

When I execute python /home/lihongsen/mgit/Multimap3D_ws/src/MultiMap3D/ORB-SLAM2_DENSE/Examples/ROS/ORB_SLAM2_DENSE/scripts/fcaf3d_sort_demo.py, the following error occurs.

How should I solve it?

Hello!
Are the SLAM part and the 3D target detection part independent?
I want to apply the 3D target detection part to my own SLAM algorithm, but I don’t know how to do it?
thank you for your reply!