GithubHelp home page GithubHelp logo

Comments (10)

MartyG-RealSense avatar MartyG-RealSense commented on July 20, 2024

Hi @iamstrang3 If you have access to the RealSense Viewer tool then you could first try resetting the camera to its factory-new default calibration settings using the instructions at #10182 (comment) in order to eliminate the possibility of a mis-calibration in your camera's sensors.

Mis-calibration can occur if the camera receives a physical shock such as a hard knock, a drop on the ground or severe vibration.

from librealsense.

iamstrang3 avatar iamstrang3 commented on July 20, 2024

Thank you for the response. I did the steps exactly as mentioned. But I still don't get the right coordinates.

from librealsense.

MartyG-RealSense avatar MartyG-RealSense commented on July 20, 2024

If the camera's projector is enabled then its IR emitter (which projects a pattern of dots onto the scene) may make fiducial image markers like apriltags harder for the camera to read by overlaying dots on the tag image. So please try making sure that the emitter is disabled by using the Python code at #10065 (comment) in order to eliminate the dot pattern as a potential cause of inaccuracy.

from librealsense.

MartyG-RealSense avatar MartyG-RealSense commented on July 20, 2024

Hi @iamstrang3 Do you require further assistance with this case, please? Thanks!

from librealsense.

iamstrang3 avatar iamstrang3 commented on July 20, 2024

Hi, sorry for the late reply. I tried to add those lines in my code but it did not help. I am getting the right coordinates at a certain distance then the error keeps increasing with distance.

from librealsense.

MartyG-RealSense avatar MartyG-RealSense commented on July 20, 2024

At what distance does the increase in error start becoming noticeable? It is normal for error to be near zero at the camera and increase linearly as the distance of an observed object / surface from the camera increases. This phenomenon is called RMS Error and becomes noticeable on the D435i model beyond 3 meters distance from the camera.

from librealsense.

iamstrang3 avatar iamstrang3 commented on July 20, 2024

I have the D435 model and the error is seen within a meter distance from the camera. Also the distance is almost accurate but the problem is with the conversion from pixel to 3d coordinates.

from librealsense.

MartyG-RealSense avatar MartyG-RealSense commented on July 20, 2024

Is it possible to make the AprilTags larger to test whether moving the camera further away makes the tags more difficult for the camera to read?

from librealsense.

iamstrang3 avatar iamstrang3 commented on July 20, 2024

The camera read the april tag just fine at larger distances.

from librealsense.

MartyG-RealSense avatar MartyG-RealSense commented on July 20, 2024

I note that you are using 640x480 resolution. As resolution is reduced, depth accuracy also reduces. For the D435 camera model, 848x480 is the optimal resolution for depth accuracy.

Does accuracy improve at distance if you use 848x480 and 30 FPS for both depth and color streams if possible? This configuration will only be supported on a USB 3.2 connection, whilst a USB 2.1 connection is only able to use 640x480 at 30 FPS.

from librealsense.

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.