Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Integration of Intel Realsense T265 and D435/D435i #8

Open
Div12345 opened this issue Feb 9, 2020 · 7 comments
Open

Integration of Intel Realsense T265 and D435/D435i #8

Div12345 opened this issue Feb 9, 2020 · 7 comments

Comments

@Div12345
Copy link
Collaborator

Div12345 commented Feb 9, 2020

Integration of Intel Realsense T265 and D435/D435i for position identification, hold and mapping

@Div12345 Div12345 assigned Div12345 and ghost Feb 9, 2020
@Div12345
Copy link
Collaborator Author

Div12345 commented Feb 10, 2020

Combination of T265 and D435 - https://dev.intelrealsense.com/docs/depth-and-tracking-cameras-alignment

the Intel® RealSense™ Tracking Camera T265 in conjunction with the Intel® RealSense™ Depth Camera D435, rigidly coupled together and spatially aligned. The Intel® RealSense™ Tracking Camera T265 estimates its position and orientation relative to a gravity-aligned static reference frame, while the Intel® RealSense™ Depth Camera D435 performs stereo matching to obtain a dense cloud of 3D scene points. Together this input can be used to obtain a point cloud that is registered with respect to a gravity-aligned static reference frame. This can be a very valuable data stream for applications such as scene mapping and object scanning.

In the case of a moving depth camera, many applications require the point clouds from different times to be spatially registered, in order to enable efficient accumulation of information. Such registration can be computationally expensive, necessitating additional compute resources or sometimes preventing an application from running in real-time. The T265 tracking camera can be a low-power, low-cost solution to this registration problem.

@Div12345
Copy link
Collaborator Author

Div12345 commented Feb 10, 2020

T265 - Wheel Odometry
Known Issues -

  1. The relocalization API should be considered unstable, and is planned to be updated in a future release
  1. Wheel odometry issues in T265 due to vibrations - #4176

  2. Inability to use T265 stand-alone to localize in an existing map - #940

@Div12345
Copy link
Collaborator Author

Div12345 commented Feb 12, 2020

Development Tools-

  1. Intel Realsense SDK
    ROS Wrapper for Realsense SDK - Latest Release - Currently supported for ROS Kinetic only.
    The wrapper for ROS Melodic is under active development is expected to be up quite soon

Community Support -

  1. Librealsense Repo Issues Page
  2. Librealsense-ros Repo Issues Page

@Div12345
Copy link
Collaborator Author

Div12345 commented Feb 12, 2020

Pertinent Resources -

  1. SLAM using D435 alone - ROS Wrapped
  2. Tracking and Depth - Not ROS wrapped
  3. 2D occupancy map based on depth images - ROS wrapped
  4. Recording and Visualisation in ROS through the synchronous operation of T265 and D435

@Div12345
Copy link
Collaborator Author

Issues in simultaneous usage of T265 and D435 -

  • Issue - #744, Solution - #752
  • Issue - Simultaneous usage #1011, Solution - Unsolved

@TheGodOfWar007
Copy link
Member

TheGodOfWar007 commented Feb 13, 2020

Development Tools-

  1. Intel Realsense SDK
    ROS Wrapper for Realsense SDK - Latest Release - Currently supported for ROS Kinetic only.

Community Support -

  1. Librealsense Repo Issues Page
  2. Librealsense-ros Repo Issues Page

As far as the support is concerned it might be possible for the package to work in ROS melodic given that all the dependencies exist in melodic also and are the same version as that of kinetic. Although Ubuntu 18.04 LTS might be a problem since kinetic was made for Ubuntu 16.04 LTS and people have reported issues trying to run kinetic packages in melodic even with all the dependencies being the same (see the issue here).

@ghost
Copy link

ghost commented Mar 16, 2020

https://dev.intelrealsense.com/docs/depth-map-improvements-for-stereo-based-depth-cameras-on-drones Modifications for the depth camera for an outdoor flight

@NidheeshJain NidheeshJain changed the title Integration of Intel Realsense T265 and D435i Integration of Intel Realsense T265 and D435/D435i Aug 9, 2020
@Div12345 Div12345 removed their assignment May 28, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants