Ocean current monitoring method and device based on video image, equipment and storage medium

Through a video-based current monitoring method, using a spatiotemporal dual-stream convolutional neural network and multi-source data fusion, the accuracy and real-time problems of traditional current monitoring technology in complex environments are solved, and efficient and refined current monitoring is achieved.

CN120635801AActive Publication Date: 2025-09-12SUN YAT SEN UNIV
View PDF 7 Cites 2 Cited by

Patent Information

Application Number
CN202510628756.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-15
Publication Date
2025-09-12
Estimated Expiration
2045-05-15

Smart Images

  • Figure CN120635801A_ABST
    Figure CN120635801A_ABST
Patent Text Reader

Abstract

The invention discloses an ocean current monitoring method, device and equipment based on a video image and a storage medium, and relates to the technical field of ocean current monitoring, and the method comprises the steps: carrying out the preprocessing of a video image of a target sea area, and the preprocessing comprises the framing processing and optical flow calculation of the video image; extracting spatial features of water surface ripple shapes and floating object distribution from the preprocessed video images through a spatial flow network; capturing time sequence characteristics of tidal cycle and vortex evolution of the preprocessed video image through a time flow network; the spatial features and the time sequence features are fused as spatial-temporal features, and ocean current parameters are calculated based on motion vector integration; eliminating noise interference of ocean current parameters based on multi-scale data fusion so as to generate an ocean current field distribution model; and monitoring the ocean current of the target sea area by using the ocean current field distribution model. Based on the video image, the ocean current of the target sea area can be finely monitored in a large range, the ocean current field distribution model can be used for accurately and quickly monitoring, and compared with the prior art, the method is more efficient.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Data mining and fusion method for space-time multi-source data

    CN116662526A

  • Surface ocean current prediction method based on attention mechanism TCN-LSTM model

    CN117195958A

  • Oil chromatography oil sample dynamic detection method and system based on multi-modal information

    CN118817924A

  • Water flow video speed measurement method, space-time neural network model, electronic equipment and medium

    CN118823056A

  • Ocean current simulation method and system based on three-dimensional temperature-salinity value

    CN119203489A

Cited By

  • Water surface floating object classification and measurement method based on image recognition

    CN120852885A

  • River flow velocity fluctuation early warning method and system based on optical flow algorithm

    CN121304741A