US 12,406,764 B2
Method for determining ciliary beat frequency
Guan-Yu Chen, Zhubei (TW); Ren-Hao Xie, Zhubei (TW); and Shiue-Luen Chen, Yuanshan Township (TW)
Assigned to Anivance AI Corporation, Hsinchu County (TW)
Filed by Anivance AI Corporation, Hsinchu County (TW)
Filed on May 5, 2023, as Appl. No. 18/312,839.
Claims priority of application No. 111119251 (TW), filed on May 24, 2022.
Prior Publication US 2023/0386645 A1, Nov. 30, 2023
Int. Cl. G06K 9/00 (2022.01); G06T 5/70 (2024.01); G06T 7/00 (2017.01); G06T 7/73 (2017.01); G16H 30/40 (2018.01)
CPC G16H 30/40 (2018.01) [G06T 5/70 (2024.01); G06T 7/0012 (2013.01); G06T 7/73 (2017.01); G06T 2207/10016 (2013.01); G06T 2207/20076 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A method for determining a ciliary beat frequency based on a video of ciliary movement, the video containing a series of consecutive frames, the method comprising steps of:
determining a frame rate of the video and a video resolution of the video;
selecting, based on the frame rate, N number of frames from the series of consecutive frames of the video, where N is a positive integer greater than one;
performing image denoising on the N number of frames to obtain N number of denoised images, respectively, each of the N number of denoised images having a resolution equal to the video resolution;
determining a plurality of target positions that respectively correspond to a plurality of ciliary beat patterns, wherein, for every N number of commonly-located pixels respectively of the N number of denoised images, when it is determined that N number of grayscale values respectively of the N number of commonly-located pixels are not the same, a position of the N number of commonly-located pixels is determined as one of the target positions, and the N number of grayscale values of the N number of commonly-located pixels at said one of the target positions represent the respective one of the plurality of ciliary beat patterns;
for each of the ciliary beat patterns, determining peak values among the N number of grayscale values; and
for each of the ciliary beat patterns, determining a ciliary beat frequency based on the peak values thus determined.