English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper reports a CPU-level real-time stereo matching method for surgicalimages (10 Hz on 640 * 480 image with a single core of i5-9400). The proposedmethod is built on the fast ''dense inverse searching'' algorithm, whichestimates the disparity of the stereo images. The overlapping image patches(arbitrary squared image segment) from the images at different scales arealigned based on the photometric consistency presumption. We propose a Bayesianframework to evaluate the probability of the optimized patch disparity atdifferent scales. Moreover, we introduce a spatial Gaussian mixed probabilitydistribution to address the pixel-wise probability within the patch. In-vivoand synthetic experiments show that our method can handle ambiguities resultedfrom the textureless surfaces and the photometric inconsistency caused by theLambertian reflectance. Our Bayesian method correctly balances the probabilityof the patch for stereo images at different scales. Experiments indicate thatthe estimated depth has higher accuracy and fewer outliers than the baselinemethods in the surgical scenario.

Bayesian dense inverse searching algorithm for real-time stereo matching in minimally invasive surgery