Ce Liu Thesis

Ce Liu Thesis-67
This section will go over some of the experiment results both that work and didn't work.In the first week, we tried a variational dense optical flow algorithm to accurately estimate the motion and perform a simple average.

This section will go over some of the experiment results both that work and didn't work.In the first week, we tried a variational dense optical flow algorithm to accurately estimate the motion and perform a simple average.

The runtime however turns out to be impractical for real-time applications as the algorithm took 23 minutes to process 15 frames at resolution 960 x 540 pixels.When taking photos under low-light environments such as indoor or at night, one of the two undesirable outcomes can happen: The photos can be blurry due to camera's or subjects' motion taken with long exposures or they can contain high level of noise because of short exposures and high sensor sensitivity.One approach that can overcome this problem is to capture a short video sequence or multiple high-noise photos and computationally combine them to produce a single low-noise photo.We then erode this labeling function and apply Gaussian blur to transform 0-1 labeling into a continuous alpha mask.The final low-noise composite is computed using a simple interpolation $(1-x_i)I^0 x_i\widetilde$.The label set is $$ where 0 means the original pixels should be used and 1 means the computed average should be used.The energy functional decomposes into a dataterm $\phi$ and a smoothness term $\psi$: A hard threshold on $D^i_$ can be achieved by using some appropriate set of $\alpha, \beta_0, \beta_1$.The smoothness term is only non-zero when $\psi(x_i, x_j \neq x_i) = \gamma$ which penalizes different adjacent labels.This binary segmentation problem is solved using graph-cut which gives us a global-optimal labeling $X: \mathbb^d \rightarrow $.Again, to make the algorithm more robust against noise, the sum of color differences around a Gaussian patch is used instead.(Assuming zero-mean noise, the sum of differences around the same patch should be close to zero.) This threshold alone can cause noisy artifacts, so we simply enforce spatial smoothness using Markov random field defined on a standard 4-connected grid.

SHOW COMMENTS

Comments Ce Liu Thesis

The Latest from nkadry.ru ©