Get length of the detected line? about srw-net HOT 1 CLOSED

Hi,
Glad you find it useful!
That will depend on your application and what sensors you have available.
Making a 3D model from using this method and only monocular camera images is something we would like to work on, but we have no implementation so far. Here are some ideas:

• Predict depth using a Neural Network model. Combine this with the camera intrinsic parameters to calculate the end points in 3D. May be noise due to the depth estimation.
• Take multiple images of the room from different angles. Use a SfM-solver (Structure from Motion), for example COLMAP, to get camera poses in 3D. Now you may triangulate the 3D positions of the line segment endpoints given that each point is visible from at least 2 different positions. Now, you don't have proper scale since we only work with projections. You might estimate scale by assuming a fixed ceiling height, using IMU or by once again utilize depth estimations from a Neural Network.
• Use a Line segment SfM and include the estimate line segments in the solver. The solution should give you 3D line segments directly, but without scale, just like the previous idea.
• Take a plane estimation network, for example plane-RCNN (there are more recent work). Work out which plane your line segment belongs to and utilize the plane parameters to project the line into the 3D plane and calculate end point positions.

I hope that made sense, otherwise you are welcome to post some follow up questions!

from srw-net.