brucecanovas / supersurfel_fusion Goto Github PK
View Code? Open in Web Editor NEWDense RGB-D SLAM system RGB-D SLAM articulated around a supersurfel-based 3D representation for fast, lightweight and compact mapping in indoor environment.
Dense RGB-D SLAM system RGB-D SLAM articulated around a supersurfel-based 3D representation for fast, lightweight and compact mapping in indoor environment.
I'm really sorry to bother you again. There was an error about the supersufel_fusion.cu file when I compiled. Because my computer has a 3060 graphics card, I installed CUDA11.2 and OpencV is 4.4.0. The following error appears. Since I just got into SLAM, I really don't know how to solve this problem. Look forward to it
error: function "getline" cannot be called with the given argument list
argument types are: (, std::__cxx11::string)
error: incomplete type is not allowed
error: namespace "cv::optflow" has no member "createOptFlow_DIS
error: identifier "adjacency_list_all" is undefined
src/core/src/motion_detection.cu(1201): error: identifier "adjacency_list_all" is undefined
Sorry to bother you again, what is the reason for the above undefined problem when I compile it? And how to solve it
When I run
roslaunch supersurfel_fusion supersurfel_fusion_rviz.launch
with my own RGBD sensor(kinectV2),the three topic information can be received correctly.
But there are no renderings of the reconstruction, and it will crash after running for a while.
If you look at the output of the terminal, it seems to be the result of not having enough point matches.
Is the RGBD information captured by the camera that caused the program to crash?
here is the log:-------------------------------------------------------------------------------------------------------------------
[ INFO] [1608195834.342321652]: rviz version 1.13.15
[ INFO] [1608195834.342344356]: compiled against Qt version 5.9.5
[ INFO] [1608195834.342349512]: compiled against OGRE version 1.9.0 (Ghadamon)
[ INFO] [1608195834.344416375]: Forcing OpenGl version 0.
[ INFO] [1608195834.850464300]: Stereo is NOT SUPPORTED
[ INFO] [1608195834.850502148]: OpenGl version: 4.6 (GLSL 4.6).
Camera info received
bestKey : 0
Total time = 34 ms
nb supersurfels: 864
stamp: 0
Max model size = 0.0856934 MB
Mean runtime = 34
In ICP, number of matches is too small! nb matches = 0
bestKey : 0
Total time = 4 ms
nb supersurfels: 0
stamp: 1
Max model size = 0.0856934 MB
Mean runtime = 19
bestKey : 0
Total time = 4 ms
nb supersurfels: 864
stamp: 2
Max model size = 0.0856934 MB
Mean runtime = 14
In ICP, number of matches is too small! nb matches = 0
bestKey : 0
Total time = 3 ms
nb supersurfels: 0
stamp: 3
Max model size = 0.0856934 MB
Mean runtime = 11.25
bestKey : 0
Total time = 11 ms
nb supersurfels: 864
stamp: 4
Max model size = 0.0856934 MB
Mean runtime = 11.2
In ICP, number of matches is too small! nb matches = 0
bestKey : 1
Total time = 9 ms
nb supersurfels: 0
stamp: 5
Max model size = 0.0856934 MB
Mean runtime = 10.8333
bestKey : 1
Total time = 9 ms
nb supersurfels: 864
stamp: 6
Max model size = 0.0856934 MB
Mean runtime = 10.5714
In ICP, number of matches is too small! nb matches = 0
bestKey : 1
Total time = 9 ms
nb supersurfels: 0
stamp: 7
Max model size = 0.0856934 MB
Mean runtime = 10.375
bestKey : 1
Total time = 9 ms
nb supersurfels: 864
stamp: 8
Max model size = 0.0856934 MB
Mean runtime = 10.2222
...
In ICP, number of matches is too small! nb matches = 0
bestKey : 28
Total time = 9 ms
nb supersurfels: 0
stamp: 151
Max model size = 0.0856934 MB
Mean runtime = 9.17105
bestKey : 26
Loop closure detected
Not enough matches, nb matches = 0
cudaCheckError() failed at /home/slam/catkin_ws/src/supersurfel_fusion/core/src/dense_registration.cu:141 : invalid configuration argument
My own version of Opencv is 3.4.12, which is different from the ros version. By looking up the cause of the problem on the Internet, it was found that cV-Birdge needed to be recompiled, but no successful method was found. So I came to ask for your help again,thanks a lot
I'm really sorry to bother you again. I encountered "ptxas error uses too much shared data" in the final compilation process. I saw that the Cmakelist file needed to be modified in the previous communication with others. Could you please tell me how to make a detailed modification
Hello,
I am using the supersurfel_fusion for mapping, with a zed-mini camera dataset.
For that, I had to make some modifications in supersufel_fusion.cu
, ferns.cu
and TPS_RGBD.cu
because of the (RGB to RGBA) and (RGB to GRAY) conversions.
(If there is already a unique way to handle this, please tell me about it)
After all, the problem is that I get very poor results, for instance, this map:
Which is supposed to be something like this:
Could it be due to poor parameter tuning? Please help me, how to get better results?
Thanks in advance!
... logging to /home/robocup3d/.ros/log/ce08ef7c-39ff-11eb-a80e-0492264b1059/roslaunch-robocup3d-22670.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.
started roslaunch server http://robocup3d:44397/
CLEAR PARAMETERS
PARAMETERS
NODES
/
rqt_reconfigure (rqt_reconfigure/rqt_reconfigure)
rviz (rviz/rviz)
supersurfel_fusion_rgbd_benchmark_node (supersurfel_fusion/supersurfel_fusion_rgbd_benchmark_node)
auto-starting new master
process[master]: started with pid [22680]
ROS_MASTER_URI=http://localhost:11311
setting /run_id to ce08ef7c-39ff-11eb-a80e-0492264b1059
process[rosout-1]: started with pid [22691]
started core service [/rosout]
process[supersurfel_fusion_rgbd_benchmark_node-2]: started with pid [22699]
process[rviz-3]: started with pid [22700]
process[rqt_reconfigure-4]: started with pid [22701]
[ INFO] [1607505640.756203327]: rviz version 1.13.14
[ INFO] [1607505640.756229047]: compiled against Qt version 5.9.5
[ INFO] [1607505640.756234344]: compiled against OGRE version 1.9.0 (Ghadamon)
[ INFO] [1607505640.759083239]: Forcing OpenGl version 0.
Used GPU 0
0 : compute_capability = 750, cudnn_half = 1, GPU: GeForce RTX 2070
net.optimized_memory = 0
mini_batch = 1, batch = 1, time_steps = 1, train = 0
layer filters size/strd(dil) input output
0 [ INFO] [1607505641.322056506]: Stereo is NOT SUPPORTED
[ INFO] [1607505641.322097384]: OpenGl version: 4.6 (GLSL 4.6).
[WARN] [1607505641.327481]: Could not find a dynamic reconfigure client named '/supersurfel_fusion_rgbd_benchmark_node'
conv 32 3 x 3/ 2 416 x 416 x 3 -> 208 x 208 x 32 0.075 BF
1 conv 64 3 x 3/ 2 208 x 208 x 32 -> 104 x 104 x 64 0.399 BF
2 conv 64 3 x 3/ 1 104 x 104 x 64 -> 104 x 104 x 64 0.797 BF
3 route 2 1/2 -> 104 x 104 x 32
4 conv 32 3 x 3/ 1 104 x 104 x 32 -> 104 x 104 x 32 0.199 BF
5 conv 32 3 x 3/ 1 104 x 104 x 32 -> 104 x 104 x 32 0.199 BF
6 route 5 4 -> 104 x 104 x 64
7 conv 64 1 x 1/ 1 104 x 104 x 64 -> 104 x 104 x 64 0.089 BF
8 route 2 7 -> 104 x 104 x 128
9 max 2x 2/ 2 104 x 104 x 128 -> 52 x 52 x 128 0.001 BF
10 conv 128 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 128 0.797 BF
11 route 10 1/2 -> 52 x 52 x 64
12 conv 64 3 x 3/ 1 52 x 52 x 64 -> 52 x 52 x 64 0.199 BF
13 conv 64 3 x 3/ 1 52 x 52 x 64 -> 52 x 52 x 64 0.199 BF
14 route 13 12 -> 52 x 52 x 128
15 conv 128 1 x 1/ 1 52 x 52 x 128 -> 52 x 52 x 128 0.089 BF
16 route 10 15 -> 52 x 52 x 256
17 max 2x 2/ 2 52 x 52 x 256 -> 26 x 26 x 256 0.001 BF
18 conv 256 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 256 0.797 BF
19 route 18 1/2 -> 26 x 26 x 128
20 conv 128 3 x 3/ 1 26 x 26 x 128 -> 26 x 26 x 128 0.199 BF
21 conv 128 3 x 3/ 1 26 x 26 x 128 -> 26 x 26 x 128 0.199 BF
22 route 21 20 -> 26 x 26 x 256
23 conv 256 1 x 1/ 1 26 x 26 x 256 -> 26 x 26 x 256 0.089 BF
24 route 18 23 -> 26 x 26 x 512
25 max 2x 2/ 2 26 x 26 x 512 -> 13 x 13 x 512 0.000 BF
26 conv 512 3 x 3/ 1 13 x 13 x 512 -> 13 x 13 x 512 0.797 BF
27 conv 256 1 x 1/ 1 13 x 13 x 512 -> 13 x 13 x 256 0.044 BF
28 conv 512 3 x 3/ 1 13 x 13 x 256 -> 13 x 13 x 512 0.399 BF
29 conv 255 1 x 1/ 1 13 x 13 x 512 -> 13 x 13 x 255 0.044 BF
30 yolo
[yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.05
nms_kind: greedynms (1), beta = 0.600000
31 route 27 -> 13 x 13 x 256
32 conv 128 1 x 1/ 1 13 x 13 x 256 -> 13 x 13 x 128 0.011 BF
33 upsample 2x 13 x 13 x 128 -> 26 x 26 x 128
34 route 33 23 -> 26 x 26 x 384
35 conv 256 3 x 3/ 1 26 x 26 x 384 -> 26 x 26 x 256 1.196 BF
36 conv 255 1 x 1/ 1 26 x 26 x 256 -> 26 x 26 x 255 0.088 BF
37 yolo
[yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.05
nms_kind: greedynms (1), beta = 0.600000
Total BFLOPS 6.910
avg_outputs = 310203
Allocate additional workspace_size = 26.22 MB
Loading weights from /home/robocup3d/catkin_ws/src/supersurfel_fusion/config/yolov4-tiny.weights...
seen 64, trained: 32012 K-images (500 Kilo-batches_64)
Done! Loaded 38 layers from weights-file
try to allocate additional workspace_size = 26.22 MB
CUDA allocate done!
object names loaded
bestKey : 0
Total time = 38 ms
nb supersurfels: 1200
stamp: 0
Max model size = 0.119019 MB
Mean runtime = 38
Sparse VO success
ICP success
bestKey : 0
Total time = 34 ms
nb supersurfels: 532
stamp: 1
Max model size = 0.119019 MB
Mean runtime = 36
Sparse VO success
ICP success
bestKey : 0
Total time = 25 ms
nb supersurfels: 602
stamp: 2
Max model size = 0.119019 MB
Mean runtime = 32.3333
Sparse VO success
ICP success
bestKey : 0
Total time = 24 ms
nb supersurfels: 743
stamp: 3
Max model size = 0.119019 MB
Mean runtime = 30.25
Sparse VO success
ICP success
bestKey : 1
Total time = 24 ms
nb supersurfels: 921
stamp: 4
Max model size = 0.119019 MB
Mean runtime = 29
[rqt_reconfigure-4] killing on exit
[rviz-3] killing on exit
[supersurfel_fusion_rgbd_benchmark_node-2] killing on exit
[rosout-1] killing on exit
[master] killing on exit
shutting down processing monitor...
... shutting down processing monitor complete
done
[ Little advice ] put the datasets on other branch or repositories.( or google drive, etc )
1.09 GB data on github is slowly to download.
( And also, I was interested in your oral works. And your reply is timely. Thank you! )
ptxas error : Entry function uses too much shared data
this error was presented when I run
catkin_make -DOpenCV_DIR=<---------my opencv dir---->
with cuda11.0 and cudnn 8.0
In the process of compiling, I met some problems with G2O as follows. Is this related to the version
error: ‘SBACam’ is not a member of ‘g2o’
g2o::SBACam sba_cam(orientation, position);
error: ‘VertexCam’ is not a member of ‘g2o’
g2o::VertexCam *cam_vertex = new g2o::VertexCam();
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.