Title:
METHOD FOR MEASURING DOWNWARD INCLINATION ANGLE OF ANTENNA BASED ON LINEAR REGRESSION FITTING
Document Type and Number:
WIPO Patent Application WO/2020/098177
Kind Code:
A1
Abstract:
Disclosed by the present invention is a method for measuring a downward inclination angle of an antenna based on linear regression fitting. The method comprises the following steps: performing instance segmentation on an input original antenna image by using a deep learning method to obtain a segmented image; performing mask processing on the segmented image; performing mathematic linear modeling fitting on the segmented image after mask processing. The mathematic linear modeling fitting comprises the following steps: extracting pixel value coordinates of an antenna edge contour from the segmented image after mask processing, and intercepting a pixel value positioned at the edge of the right end of the antenna; fitting the pixel value coordinates into a straight line by means of mathematic linear modeling fitting, so as to obtain the downward inclination angle of the antenna. A downward inclination angle of an antenna is obtained through the processing on the antenna image by a deep learning network in combination with mask processing and linear fitting, thereby establishing a convenient, safe, effective and accurate antenna measuring method.
Inventors:
DENG WENBO (CN)
ZHAI YIKUI (CN)
KE QIRUI (CN)
WU YUETING (CN)
GAN JUNYING (CN)
XU YING (CN)
WANG TIANLEI (CN)
WU XI (CN)
CHEN LIYAN (CN)
ZHAI YIKUI (CN)
KE QIRUI (CN)
WU YUETING (CN)
GAN JUNYING (CN)
XU YING (CN)
WANG TIANLEI (CN)
WU XI (CN)
CHEN LIYAN (CN)
Application Number:
PCT/CN2019/076720
Publication Date:
May 22, 2020
Filing Date:
March 01, 2019
Export Citation:
Assignee:
UNIV WUYI (CN)
International Classes:
G01B9/10; G01C1/00; G01R29/10; G06T7/00
Foreign References:
CN105761249A | 2016-07-13 | |||
CN107830846A | 2018-03-23 | |||
CN107121125A | 2017-09-01 | |||
US4758840A | 1988-07-19 |
Other References:
See also references of EP 3683541A4
Attorney, Agent or Firm:
JIAQUAN IP LAW FIRM (CN)
Download PDF: