Skip to content

VictorHoffmann1/Real-Time-Depth-Estimation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Real-Time Room Depth Estimation with Monocular Camera

Room Depth Estimation

Description

Real-time depth estimation is a subject of significant importance with far-reaching implications across various fields such as Augmented/Virtual Reality, Autonomous Navigation, Robotics and more. This technology holds the potential to revolutionize several domains, making it a vital area of research and application.

On this repository, we'll learn how to use MiDaS to estimate the depth of a room in "real-time" (we'll use a video to emulate a real-time performance and we'll check that the number of fps is adequate) with a monocular camera (a camera with just one objective).

In this repository you'll find:

  • A jupyter notebook, containing all the necessary code to load and execute MiDaS on our example (be careful, the pretrained_weight of the medium version of MiDaS have a size of 500MB).
  • A data folder, containing the video whoose depth we're going to estimate.
  • The output video in .mp4 format.

Credits:

Victor Hoffmann

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published