Giter VIP home page Giter VIP logo

Comments (10)

rising-turtle avatar rising-turtle commented on September 2, 2024

from slam_note.

yuyadanyadan avatar yuyadanyadan commented on September 2, 2024

首先,我的结果不是不精确,而是完全不对,一直没找到原因! 我的图像的位置是用orb-slam2跑出来的结果,然后对应里程计的数据是插值出来的结果,我一直很困惑是什么原因,输进去的位置是前一帧到当前帧的位置。 kalibr还可以用来标定cam-odom? q请问可以加下您qq么?万分感谢!!!我qq是1553532009, 谢谢, 麻烦了,旁边实在是没有做过这个标定的伙伴

from slam_note.

yuyadanyadan avatar yuyadanyadan commented on September 2, 2024

而且我的两种位姿用rviz显示过了 形状都是一样的, 就是走过的路径的形状是一样的

from slam_note.

yuyadanyadan avatar yuyadanyadan commented on September 2, 2024

我的cam是global-shutter, 几组不同数据标定出来的效果不同,而且那个motionCount和segmentCount您是依据什么来设置的?我直接设置motionCount = 10; 如果用kalibr来标的话,是不是需要把里面关于Imu的部分改成odom??? 希望您能回复我,谢谢

from slam_note.

rising-turtle avatar rising-turtle commented on September 2, 2024

from slam_note.

yuyadanyadan avatar yuyadanyadan commented on September 2, 2024

Hi
谢谢,麻烦你了!我测出来的结果不够准确,
将图像和odometry数据扔进去,图像通过他自身的vo计算出的位姿; 得出的结果(result1)与利用他给出的CamOdoCalibration_test中将orbslam2的图像位姿和odometry扔进去的结果(result2)进行了一下比较,旋转差不多,只有yaw差了几度,roll和pitch都在1度以下; 平移的x相差在1cm以下,但是它计算的y,跟我的差距较大,我计算出来的是7cm, 他算出来的是-28cm;
result1:
H_cam_odo =
0.0740025 0.0103076 0.997205 0.0293397
-0.9972 -0.00999095 0.0741055 -0.281613
0.0107269 -0.999897 0.00953939 0
0 0 0 1
r p y: -89.4535 -0.614617 -85.7559

result2:
Rotation:
0.171076 0.0196879 0.985061
-0.985228 -0.00435906 0.171192
0.00766435 -0.999797 0.0186513
Translation:
0.0330635 0.0799669 0
RPY: -88.9 -0.4 -80.5

因为在网上找的开源数据, 所以我这有较为准确的外参:

  • Translation: [0.074, 0.030, 1.251]
  • Rotation: in Quaternion [0.491, -0.509, 0.509, -0.490]
    in RPY (radian) [-1.571, -0.001, -1.608]
    in RPY (degree) [-90.028, -0.035, -92.113]

感觉算出来的结果都不够准确呢。。。
谢谢哈, 你先忙你的

from slam_note.

extr15 avatar extr15 commented on September 2, 2024

@yuyadanyadan ,sorry for the late. In my impression, VO of camodocal is not that good, you said the trajectory of odom and VO was the same shape and you knew the extrinsic already, maybe you can use the extrinsic to check the error between the odom trajectory and VO trajectory?

from slam_note.

yuyadanyadan avatar yuyadanyadan commented on September 2, 2024

thank you, I use the result of ORB-SLAM2 not its own vo. And I get the almost accurate result, Thank you very much!

from slam_note.

bcWorkAccount avatar bcWorkAccount commented on September 2, 2024

你好,我使用camodocal标定结果不是最优的,请问你的是吗?

from slam_note.

bcWorkAccount avatar bcWorkAccount commented on September 2, 2024

@yuyadanyadan

from slam_note.

Related Issues (3)

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.