Method for measuring channel flow based on bionic eagle-eye vision and apparatus thereof

An apparatus for measuring channel flow based on bionic eagle-eye vision, comprising:

• an extraction module, configured to acquire a channel flowing video, and carry out image frame interval extraction on the channel flowing video to obtain a target observation image, wherein the bionic eagle-eye vision collects the channel flowing video by simulating a central fovea structure on an eagle-eye side using a binocular camera;
• a first calculation module, configured to calculate an optical flow value of the target observation image, and calculate a surface flow velocity value of the target observation image in a world coordinate system based on position change information of the optical flow value of the target observation image between image frames and a spatial resolution of the target observation image, wherein the position change information is used for indicating a change of a pixel point in the target observation image in a time domain;
• and
• a second calculation module, configured to acquire an average cross-section flow velocity based on a pre-trained surface cross-section flow velocity coupling model, and calculate the channel flow based on the average cross-section flow velocity and a cross-section water level value;
• wherein the surface cross-section flow velocity coupling model is obtained by fitting the surface flow velocity value in the world coordinate system based on a flow velocity distribution formula, constructing a surface flow velocity distribution law and a mid-vertical line flow velocity distribution law, and training according to the surface flow velocity distribution law and the mid-vertical line flow velocity distribution law;
• and the cross-section water level value is calculated through a water level identification model based on a water area shoreline image acquired in advance wherein the water level identification model is obtained by training based on a bionic eagle-eye vision model, and the water level identification model comprises a backbone network and a neck network, the backbone network is configured to extract feature information in the water area shoreline image and provide the feature information to the neck network, and the neck network is configured to carry out feature fusion on the feature information;
• wherein the apparatus further comprises a fitting module configured to:
• before the acquiring an average cross-section flow velocity based on a pre-trained surface cross-section flow velocity coupling model, determine an optimal frame image and a reference line position in the target observation image based on the surface flow velocity value in the world coordinate system;
• and
• obtain a local channel flow field based on the optimal frame image and the reference line position, and carry out flow velocity fitting on the local channel flow field to obtain a flow velocity distribution formula.