Abstract: Some embodiments of the disclosure provide a method for measuring orthogonality of an orthogonal axis system, In some examples, the method includes following steps: placing an instrument on a bearing surface, intercepting a second rotary axis along an interception plane to obtain a first virtual cross section of the second rotary axis, and measuring the first virtual cross section to obtain a geometric center of the first virtual cross section as a first position; rotating a first rotary device to enable the second rotary axis to rotate with a preset angular degree, and measuring the second virtual cross section to obtain a geometric center of the second virtual cross section as a second position; and determining whether the orthogonality between the first rotary axis and the second rotary axis meets requirements or not on the basis of the first position and the second position.

Abstract: The present specification discloses video matching. In a computer-implemented method, a plurality of feature vectors of a target video is obtained. A candidate video similar to the target video is retrieved from a video database based on the plurality of feature vectors of the target video. A time domain similarity matrix feature map is constructed between the target video and the candidate video based on the target video and the candidate video. Using the time domain similarity matrix feature map as an input into a deep learning detection model, a video segment matching the target video in the candidate video and a corresponding similarity is output.