top of page

Paper published in Sensors Journal


The team at University of Luxembourg have had a paper published in the open access journal Sensors. The paper titled: RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry addresses unsupervised learning for monocular camera motion and 3D scene understanding, which has gained popularity over traditional methods that rely on epipolar geometry or non-linear optimization. Notably, deep learning can overcome many issues of monocular vision, such as perceptual aliasing, low-textured areas, scale drift, and degenerate motions. In addition, concerning supervised learning, one can fully leverage video stream data without the need for depth or motion labels. However, in the paper it is noted that rotational motion can limit the accuracy of the unsupervised pose networks more than the translational component. Therefore, RAUM-VO is presented as an approach based on a model-free epipolar constraint for frame-to-frame motion estimation (F2F) to adjust the rotation during training and online inference.


Sensors is the leading international, peer-reviewed, open access journal on the science and technology of sensors. and is published semi-monthly online. The Polish Society of Applied Electromagnetics (PTZE), Japan Society of Photogrammetry and Remote Sensing (JSPRS), Spanish Society of Biomedical Engineering (SEIB) and International Society for the Measurement of Physical Behaviour (ISMPB) are affiliated with Sensors.



Featured Posts
Recent Posts
Archive
Search By Tags
Follow Us
  • Facebook Basic Square
  • Twitter Basic Square
  • Google+ Basic Square
bottom of page