CN-121725029-B - Method for measuring motion of marine floating body

CN121725029BCN 121725029 BCN121725029 BCN 121725029BCN-121725029-B

Abstract

The invention relates to the field of computer vision, in particular to a method for measuring the motion of an offshore floating body. The measuring method comprises the steps of obtaining a video of the movement of the offshore floating body on the water body, determining a characteristic tracking point set corresponding to each frame of image in the video, wherein the characteristic tracking point set is related to the offshore floating body, and determining six-degree-of-freedom movement parameters of the offshore floating body according to the characteristic tracking point set. The invention realizes the measurement of three-dimensional complete motion information, namely the measurement of six-degree-of-freedom motion parameters, and can improve the robustness and the integrity of the motion information measurement of the offshore floating body.

Inventors

JIANG CHUNYU
SHI HONGDA
DENG QIAN
LI JIAN
SUN HUIHUI

Assignees

崂山国家实验室

Dates

Publication Date: 20260512
Application Date: 20260227

Claims (4)

1. A method of measuring motions of an offshore floating body, the method comprising: Acquiring a video of the motion of the offshore floating body on the water body; Determining a set of feature tracking points corresponding to each frame of image in the video, the set of feature tracking points being associated with the offshore floating body; Determining a covariance matrix corresponding to the adjacent frame image according to the characteristic tracking point set corresponding to the adjacent frame image, wherein the covariance matrix corresponding to the adjacent frame image represents the spatial distribution change of the characteristic tracking point set corresponding to the adjacent frame image; Determining the sizes of a roll angle and a pitch angle of the offshore floating body according to the relative variation of main diagonal elements of the covariance matrix corresponding to the adjacent frame images; Determining the magnitude of the roll angle of the marine floating body according to the relative variation of a first main diagonal element of the covariance matrix corresponding to the adjacent frame image, determining the magnitude of the pitch angle of the marine floating body according to the relative variation of a second main diagonal element of the covariance matrix corresponding to the adjacent frame image, wherein the first main diagonal element represents the discrete degree of the characteristic tracking point set in the vertical direction of the image, and the second main diagonal element represents the discrete degree of the characteristic tracking point set in the horizontal direction of the image; Determining a similar transformation model corresponding to the adjacent frame images according to the corresponding relation of the feature tracking point set corresponding to the adjacent frame images; analyzing the similar transformation model to obtain a translation component, a rotation component and a scaling component; and determining a heave displacement according to the translation component, a heave displacement according to the rotation component and a heave angle according to the scaling component.
2. The method of measuring of claim 1, wherein the scaling component comprises a scaling factor, and wherein parsing the similarity transformation model to obtain the scaling component comprises: analyzing the similarity transformation model to obtain the scaling factor; said determining said heave displacement from said scaling component comprising: And determining the heave displacement according to the scaling factor and a preset mapping function.
3. The measurement method according to claim 1 or 2, wherein the determining a set of feature tracking points corresponding to each frame of image in the video comprises: Determining the feature tracking point set corresponding to the first frame image of the video; and tracking the feature tracking point set corresponding to the first frame image, and determining the feature tracking point set corresponding to each frame image after the first frame image frame by frame.
4. A method of measuring as claimed in claim 3, wherein determining the set of feature tracking points corresponding to the first frame image of the video comprises: And detecting the feature tracking point set corresponding to the first frame image in a floating body feature detection area in the first frame of the video.

Description

Method for measuring motion of marine floating body Technical Field The invention relates to the field of computer vision, in particular to a method for measuring the motion of an offshore floating body. Background In research and development tests of offshore floating bodies, it is important to accurately measure the motion parameters of the offshore floating bodies in a real marine environment. In the related art, non-contact measurement is often realized by using a camera, namely, an image of the marine floating body is acquired, and translation information in a two-dimensional plane is calculated through displacement analysis of the marine floating body in the image. However, the motion parameters obtained in the related art have fewer dimensions, and the motion information of the offshore floating body is incomplete. Disclosure of Invention To overcome the problems in the related art, the present invention provides a method for measuring motions of a marine floating body, the method comprising: Acquiring a video of the motion of the offshore floating body on the water body; Determining a set of feature tracking points corresponding to each frame of image in the video, the set of feature tracking points being associated with the offshore floating body; Determining a covariance matrix corresponding to the adjacent frame image according to the characteristic tracking point set corresponding to the adjacent frame image, wherein the covariance matrix corresponding to the adjacent frame image represents the spatial distribution change of the characteristic tracking point set corresponding to the adjacent frame image; Determining the magnitudes of the roll angle and the pitch angle of the offshore floating body according to the relative variation of the main diagonal elements of the covariance matrix corresponding to the adjacent frame images; Determining the magnitude of the roll angle of the marine floating body according to the relative variation of a first main diagonal element of the covariance matrix corresponding to the adjacent frame image, determining the magnitude of the pitch angle of the marine floating body according to the relative variation of a second main diagonal element of the covariance matrix corresponding to the adjacent frame image, wherein the first main diagonal element represents the discrete degree of the characteristic tracking point set in the vertical direction of the image, and the second main diagonal element represents the discrete degree of the characteristic tracking point set in the horizontal direction of the image; Determining a similar transformation model corresponding to the adjacent frame images according to the corresponding relation of the feature tracking point set corresponding to the adjacent frame images; analyzing the similar transformation model to obtain a translation component, a rotation component and a scaling component; and determining the heave displacement and the heave displacement according to the translation component, the yaw angle and the scaling component. In some exemplary embodiments of the present disclosure, the scaling component includes a scaling factor, and the parsing the similarity transformation model to obtain the scaling component includes: analyzing the similarity transformation model to obtain the scaling factor; said determining said heave displacement from said scaling component comprising: And determining the heave displacement according to the scaling factor and a preset mapping function. In some exemplary embodiments of the disclosure, the determining a feature tracking point set corresponding to each frame of image in the video includes: Determining the feature tracking point set corresponding to the first frame image of the video; and tracking the feature tracking point set corresponding to the first frame image, and determining the feature tracking point set corresponding to each frame image after the first frame image frame by frame. In some exemplary embodiments of the present disclosure, determining the feature tracking point set corresponding to the first frame image of the video includes: And detecting the feature tracking point set corresponding to the first frame image in a floating body feature detection area in the first frame of the video. The technical scheme provided by the embodiment of the invention has the beneficial effects that the data acquisition mode of the motion measurement of the offshore floating body is a video of the motion of the offshore floating body on the water body, so that the non-contact measurement is realized to improve the measurement robustness. And a data base is provided for the determination of six-degree-of-freedom motion parameters by determining a characteristic tracking point set corresponding to each frame of image and related to the offshore floating body. Based on the characteristic tracking point set, the six-degree-of-freedom motion parameter is determined, and compared with t