GithubHelp home page GithubHelp logo

Comments (24)

taihup avatar taihup commented on August 11, 2024 1

from sptam.

breyner-posso avatar breyner-posso commented on August 11, 2024 1

Hi! tks for your answers!
I'm using stereo_image_proc in order to publish undistorted and rectified stereo images.
I'm gonna try to slow down the bag file.
Tks! :)

from sptam.

taihup avatar taihup commented on August 11, 2024

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

Thanks,
I checked my ZED camera the baseline is indeed 12cm
Sorry, I am new to camera. Do you know where I can change my baseline?
In the camera_info?

from sptam.

taihup avatar taihup commented on August 11, 2024

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

Thanks a lot.
I appreciate your reply!

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

Hi, I have fixed my baseline to 0.12 (which is the correct value)
but still couldn't get enough map points (I have checked the map points are between 0-3)
is there other problem that could lead to this issue

this is my camera info:
left_info
header:
seq: 30945
stamp:
secs: 1514963977
nsecs: 844533434
frame_id: zed_left_camera
height: 720
width: 1280
distortion_model: plumb_bob
D: [0.0, 0.0, 0.0, 0.0, 0.0]
K: [673.9771118164062, 0.0, 646.008056640625, 0.0, 673.9771118164062, 387.2628173828125, 0.0, 0.0, 1.0]
R: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
P: [673.9771118164062, 0.0, 646.008056640625, 0.0, 0.0, 673.9771118164062, 387.2628173828125, 0.0, 0.0, 0.0, 1.0, 0.0]
binning_x: 0
binning_y: 0
roi:
x_offset: 0
y_offset: 0
height: 0
width: 0
do_rectify: False


right_info
header:
seq: 30800
stamp:
secs: 1514963975
nsecs: 334894665
frame_id: zed_left_camera
height: 720
width: 1280
distortion_model: plumb_bob
D: [0.0, 0.0, 0.0, 0.0, 0.0]
K: [673.9771118164062, 0.0, 646.008056640625, 0.0, 673.9771118164062, 387.2628173828125, 0.0, 0.0, 1.0]
R: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
P: [673.9771118164062, 0.0, 646.008056640625, -80.87725937366486, 0.0, 673.9771118164062, 387.2628173828125, 0.0, 0.0, 0.0, 1.0, 0.0]
binning_x: 0
binning_y: 0
roi:
x_offset: 0
y_offset: 0
height: 0
width: 0
do_rectify: False

from sptam.

taihup avatar taihup commented on August 11, 2024

Hi, are the camera images rectified? try to use http://wiki.ros.org/stereo_image_proc node to rectify the images. S-PTAM works with rectified cameras.

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

yes the image are rectified
in my rosbag my image was sensor_msgs/CompressedImage
so I use image_transport to transport to sensor_msgs/Image
and then use the stereo_image_proc node
this is my launch file

zed.launch.txt

from sptam.

taihup avatar taihup commented on August 11, 2024

Try to follow this launch. I did for my ZED camera. In this case the ZED camera was used with the VGA resolution configuration.
zed_bag.launch.txt

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

Could you show me what is in the zed_vga.yaml file ?
same as in the kitti.yaml?

from sptam.

taihup avatar taihup commented on August 11, 2024

I changed some parameters. Try also changing the EpipolarDistance to 1 or 2.
zed_vga.yaml.txt

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

in my bag there is only
/image_raw_color/compressed
/image_rect_color/compressed
so I use image transport (which can only do on raw image)
to get /image_raw_color
then give /image_raw_color to stereo_image_proc
however the node wants /image_raw
Is this could be a problem?

or maybe I could just use /image_rect_color/compressed ?

from sptam.

taihup avatar taihup commented on August 11, 2024

I think your launch is correct. I think is not properly tabulated (I can't remember now if launch files should be properly tabulated to work fine). Try to modified the configuration file that you are using. Did you try changing the EpipolarDistance parameter?

If you are working with a rosbag, remember to run the parameter set use_sim_time true after roscore command in terminal. Also, you should public the clock with the rosbag, like the datasets examples. You can also change the rate of publication to make sure that all the images are processed properly.
Summarizing, you should do in terminal:

roscore &
rosparam set use_sim_time true
rosbag play --clock rosbagFile.bag -r 0.2

Another issue could be that your camera calibration is not so good. I am seeing your camera_info messages and they are not looking good because you do not have distortion parameters D and you do not have rectification rotation matrix R set. Moreover, the frame_id of right camera is wrong.

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

Finally I successfully initialize map but get error about covisibility keyframes
ERROR: There is not any covisibility keyframes observing the tracked points
which part should I look into?
thanks for all the help!!!

[ INFO] [1523461133.908802132, 1514963977.477140960]: S-PTAM stereo node initialized.
[ INFO] [1523461138.793225855, 1514963979.920527447]: init calib
[ INFO] [1523461138.793459726, 1514963979.920527447]: baseline: 0.12
[ INFO] [1523461139.237742439, 1514963980.139035384]: Trying to intialize map...
[ INFO] [1523461139.415248260, 1514963980.229501520]: mappoint: [73]
[ INFO] [1523461139.422501930, 1514963980.234898885]: Map initialized with 73 points.
[ WARN] [1523461140.421120513, 1514963980.733720627]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1523461142.983779618, 1514963982.015061306]: Not enough points for tracking.

from sptam.

taihup avatar taihup commented on August 11, 2024

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

this error repeats
[WARN] [1523461140.421120513, 1514963980.733720627]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points

I will leave the camera still and try again!

from sptam.

taihup avatar taihup commented on August 11, 2024

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

in my bag there was
/image_raw_color/compressed
/image_rect_color/compressed
at first I do on /image_raw_color/compressed use image transport and then get rectify image.

then I try directly do image transport on /image_rect_color/compressed
(this is wrong about image transport could only do on raw images
http://wiki.ros.org/image_transport )
then get /image_rect_color so I put it into sptam node directly
this is my final launch file!
zedlaunch.txt

from sptam.

breyner-posso avatar breyner-posso commented on August 11, 2024

Hi, how do you solve this issue:

[WARN] [1523461140.421120513, 1514963980.733720627]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points

I'm getting something like that and no map is build.

Tks a lot for your advice.

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

Hi, are you trying the bag provided by the author or you are also working on zeds?

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

I saw your issue.
My problem was my calibration wasn't pretty good, you could try to link features to see if the feature matches.
Or you could slow down your ros bag.
Ex. rosbag play -r 0.2
By the way are you using stereo image proc? Or using the opencv way to calibrate.

from sptam.

breyner-posso avatar breyner-posso commented on August 11, 2024

Hi, I'm using my own dataset. Actually I'm running SPTAM but I'm not getting any map.

acfr@acfr-protea:~/catkin_ws$ roslaunch sptam acfr.launch
... logging to /home/acfr/.ros/log/dfde1f4a-4c10-11e8-b53e-b8ca3a8203b2/roslaunch-acfr-protea-24929.log
Checking log directory for disk usage. This may take awhile.
Press Ctrl-C to interrupt
Done checking log file disk usage. Usage is <1GB.

started roslaunch server http://acfr-protea:44241/

SUMMARY

PARAMETERS

  • /rosdistro: kinetic
  • /rosversion: 1.12.13
  • /sptam/BundleAdjustmentActiveKeyframes: 10
  • /sptam/DescriptorExtractor/Name: BRIEF
  • /sptam/DescriptorExtractor/bytes: 32
  • /sptam/DescriptorMatcher/Name: BruteForce-Hamming
  • /sptam/DescriptorMatcher/crossCheck: False
  • /sptam/EpipolarDistance: 0
  • /sptam/FeatureDetector/Name: GFTT
  • /sptam/FeatureDetector/minDistance: 15.0
  • /sptam/FeatureDetector/nfeatures: 1000
  • /sptam/FeatureDetector/qualityLevel: 0.01
  • /sptam/FeatureDetector/useHarrisDetector: False
  • /sptam/FrustumFarPlaneDist: 10000.0
  • /sptam/FrustumNearPlaneDist: 0.1
  • /sptam/LoopDetectorVocabulary: /home/acfr/catkin...
  • /sptam/MatchingCellSize: 30
  • /sptam/MatchingDistance: 25
  • /sptam/MatchingNeighborhood: 2
  • /sptam/approximate_sync: False
  • /sptam/base_frame: left_camera
  • /sptam/camera_frame: left_camera
  • /sptam/minimumTrackedPointsRatio: 0.9
  • /sptam/publish_on_fail: True
  • /sptam/publish_transform: True
  • /sptam/reference_frame: left_camera
  • /sptam/use_prediction: False
  • /use_sim_time: True

NODES
/stereo/
stereo_image_proc (stereo_image_proc/stereo_image_proc)
/
sptam (sptam/sptam_node)
sptam_path (ros_utils/pose_to_path)

ROS_MASTER_URI=http://localhost:11311

process[stereo/stereo_image_proc-1]: started with pid [24947]
process[sptam_path-2]: started with pid [24948]
process[sptam-3]: started with pid [24954]
[ INFO] [1525049625.405580944]: Initializing nodelet with 8 worker threads.
crossCheck: 0
OpenCV: threads set to -1
nfeatures: 1000
qualityLevel: 0.01
minDistance: 15
blockSize: 3
useHarrisDetector: 0
k: 0.04
nfeatures: 1000
qualityLevel: 0.01
minDistance: 15
blockSize: 3
useHarrisDetector: 0
k: 0.04
bytes: 32
use_orientation: 0
bytes: 32
use_orientation: 0
[ INFO] [1525049625.555098245]: Loop Detector initializing, loading vocabulary
[ INFO] [1525049634.039631096]: S-PTAM stereo node initialized.
[ INFO] [1525049637.860779009]: init calib
[ INFO] [1525049637.860956353]: baseline: 0.584967
[ INFO] [1525049638.101483523]: Map initialized with 45 points.
[ WARN] [1525049638.682994378]: Not enough points for tracking.
[ WARN] [1525049640.929131143]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049654.157759622]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049660.745917501]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049661.825162811]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049665.856239203]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049670.135123189]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049681.202346129]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049691.770648229]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049701.210938574]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049703.515873901]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049705.108644473]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049710.716088369]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049711.660556581]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049716.751190998]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049718.063519255]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049718.360129805]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049720.990454635]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049740.064274117]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049740.265883895]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049742.313579714]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049744.302966236]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049756.077361346]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049758.880483230]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049762.325829975]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049770.864540302]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049771.151525750]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049773.199360329]: Not enough points for tracking.
ERROR: There is not any covisibility keyframes observing the tracked points
[ WARN] [1525049773.898833449]: Not enough points for tracking.

Tks a lot for your advice.

from sptam.

jacky70010 avatar jacky70010 commented on August 11, 2024

Stereo image proc publishes point cloud
So you could use rviz to see that your rectification images are good or not!

from sptam.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.