Modified 2019-01-07 by pravishsainath
The geometric approaches to VO consider the geometry of the scene. These take advantage of the visual geometry in the camera-world model. They can be further sub-classified into the following
Feature-based Methods (Sparse)(Indirect) :
Specific features (landmarks) are extracted from the images for motion estimation. These features across time instants are matched to compute the motion parameters using geometry. This is explained in detail in next section.
Appearance-based Methods (Dense)(Direct) :
The entire image as a pixel matrix is considered and optimized for the photometric error. These methods are also referred to as Correspondence-Free Methods.
Motion estimation is done using one of the following methods :
Optical flow method
It individually tracks pixels (all or subs-region of image). It assumes small motion between frames and, therefore, is not suitable for VO applications since motion error accumulates quickly.
Featureless motion-estimation methods
All the pixels in the two images are used to compute the relative motion using a harmonic Fourier transform. This method works well with low-texture images but it is not used due to
Hybrid Methods (Semi-dense)(Semi-direct) :
A hybrid of the first two stated methods.
For more details, take a look at SVO: Fast Semi-Direct Monocular Visual Odometry
No questions found. You can ask a question on the website.