Oral endoscope image stitching algorithm is studied to obtain wide-field oral images through regis-tration and stitching,which is of great significance for auxiliary diagnosis.Compared with natural images,oral images ...Oral endoscope image stitching algorithm is studied to obtain wide-field oral images through regis-tration and stitching,which is of great significance for auxiliary diagnosis.Compared with natural images,oral images have lower textures and fewer features.However,traditional feature-based image stitching methods rely heavily on feature extraction quality,often showing an unsatisfactory performance when stitching images with few features.Moreover,due to the hand-held shooting,there are large depth and perspective disparities between the captured images,which also pose a challenge to image stitching.To overcome the above problems,we propose an unsupervised oral endoscope image stitching algorithm based on the extraction of overlapping regions and the loss of deep features.In the registration stage,we extract the overlapping region of the input images by sketching polygon intersection for feature points screening and estimate homography from coarse to fine on a three-layer feature pyramid structure.Moreover,we calculate loss using deep features instead of pixel values to emphasize the importance of depth disparities in homography estimation.Finally,we reconstruct the stitched images from feature to pixel,which can eliminate artifacts caused by large parallax.Our method is compared with both feature-based and previous deep-based methods on the UDIS-D dataset and our oral endoscopy image dataset.The experimental results show that our algorithm can achieve higher homography estimation accuracy,and better visual quality,and can be effectively applied to oral endoscope image stitching.展开更多
Fully developed turbulence measurements in pipe flow were made in theReynolds number range from 10 X 10~3 to 350 X 10~3 with hot-wire anemometer and a Pilot tube.Comparisons were made with the experimental results of ...Fully developed turbulence measurements in pipe flow were made in theReynolds number range from 10 X 10~3 to 350 X 10~3 with hot-wire anemometer and a Pilot tube.Comparisons were made with the experimental results of previous researchers. The mean velocityprofile and the turbulent intensity in the experiments indicate that for the mean velocity profile,in the fully developed turbulent pipe flow, von Karman's constant κ is a function of the Reynoldsnumber, i. e. κ increases slowly with the Reynolds number. For turbulent pipe flow, the outer limitdepends on whether the Kdrmdn number R^+ is greater or less than 850 in the centerline velocityprofile: a log law exists for 850 < R^+< 1750 in the experiment, and von Karman' s constant κ isshown to be 0. 408. Under the effects of the test trip at the inlet, fully developed turbulence wasobtained in pipe flow at lower Reynolds number when the entrance length (x/D) was larger than 40. Inthe experiment it was also found that turbulence quantities in pipe flow remain independent of theupstream conditions when the trip blockage ratio is higher than 20%, and the comparison with channelwater flow was also performed.展开更多
基金the National Natural Science Foundation of China(No.61976091)。
文摘Oral endoscope image stitching algorithm is studied to obtain wide-field oral images through regis-tration and stitching,which is of great significance for auxiliary diagnosis.Compared with natural images,oral images have lower textures and fewer features.However,traditional feature-based image stitching methods rely heavily on feature extraction quality,often showing an unsatisfactory performance when stitching images with few features.Moreover,due to the hand-held shooting,there are large depth and perspective disparities between the captured images,which also pose a challenge to image stitching.To overcome the above problems,we propose an unsupervised oral endoscope image stitching algorithm based on the extraction of overlapping regions and the loss of deep features.In the registration stage,we extract the overlapping region of the input images by sketching polygon intersection for feature points screening and estimate homography from coarse to fine on a three-layer feature pyramid structure.Moreover,we calculate loss using deep features instead of pixel values to emphasize the importance of depth disparities in homography estimation.Finally,we reconstruct the stitched images from feature to pixel,which can eliminate artifacts caused by large parallax.Our method is compared with both feature-based and previous deep-based methods on the UDIS-D dataset and our oral endoscopy image dataset.The experimental results show that our algorithm can achieve higher homography estimation accuracy,and better visual quality,and can be effectively applied to oral endoscope image stitching.
文摘Fully developed turbulence measurements in pipe flow were made in theReynolds number range from 10 X 10~3 to 350 X 10~3 with hot-wire anemometer and a Pilot tube.Comparisons were made with the experimental results of previous researchers. The mean velocityprofile and the turbulent intensity in the experiments indicate that for the mean velocity profile,in the fully developed turbulent pipe flow, von Karman's constant κ is a function of the Reynoldsnumber, i. e. κ increases slowly with the Reynolds number. For turbulent pipe flow, the outer limitdepends on whether the Kdrmdn number R^+ is greater or less than 850 in the centerline velocityprofile: a log law exists for 850 < R^+< 1750 in the experiment, and von Karman' s constant κ isshown to be 0. 408. Under the effects of the test trip at the inlet, fully developed turbulence wasobtained in pipe flow at lower Reynolds number when the entrance length (x/D) was larger than 40. Inthe experiment it was also found that turbulence quantities in pipe flow remain independent of theupstream conditions when the trip blockage ratio is higher than 20%, and the comparison with channelwater flow was also performed.
