IR Matrix projector clipping distance uniformity (Intel Realsense d435i)

distance = depth.get_distance(width/2, height/2)

• MartyG

  • November 25, 2022 05:45

  Hi Fpelegri  The dot pattern cast by the projector is semi-random, and how visible the dots are to the camera will also depend on environmental conditions such as lighting and the type of material that the surface that is being depth-sensed is made from. 

   

  The dot pattern acts as a 'texture source' to aid the camera in analyzing surfaces for depth detail.  The RealSense 400 Series cameras can though alternatively use ambient light in a well-illuminated scene to assist depth analysis instead of using the dot pattern.  So the projector is an aid to depth analysis but not a part of how depth values are calculated. 

  0

  Comment actions Permalink
• Fpelegri

  • November 28, 2022 22:12

  Thanks for the feedback!

  My application have to get the shape of the objects on a flat surface, is there an appropriate way to do it using python (pyrealsense2),using STEREO Module of Intel RealSense D435i?

  The ideal distance threshold is the surface, is there a way to calibrate the Intel realSense D435i camera using python code?

  Thanks in advance! (again)

  0

  Comment actions Permalink
• MartyG

  • November 29, 2022 10:37

  You can activate the RealSense SDK's On-Chip Calibration using Python code instead of accessing it through the RealSense Viewer by using the scripting at the link below.

  https://dev.intelrealsense.com/docs/self-calibration-for-depth-cameras#appendix-c-on-chip-calibration-python-api

   

  The SDK has a complete Python calibration example script for the On-Chip functions here:

  https://github.com/IntelRealSense/librealsense/blob/master/wrappers/python/examples/depth_auto_calibration_example.py

   

  If you need to capture the 3D shape of an object then an appropriate method may be to generate a pointcloud and export it to a .ply pointcloud data file.  An example program for doing so is here:

  https://github.com/IntelRealSense/librealsense/blob/master/wrappers/python/examples/export_ply_example.py

   

  A RealSense .ply file can then be imported into 3D modelling software for performing further work on it, such as converting the pointcloud to a solid-mesh .obj file.  A free open-source tool that can do this with RealSense .ply files is MeshLab.

  https://www.andreasjakl.com/capturing-3d-point-cloud-intel-realsense-converting-mesh-meshlab/

  0

  Comment actions Permalink

Please sign in to leave a comment.