Adaptive Fractional TV-L based on Antlion Optimization 1 Optical flow estimation methods

CN117333517BActive Publication Date: 2026-11-17SHENYANG LIGONG UNIV
-1 Cites 0 Cited by

Patent Information

Application Number
CN202311354832.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-10-19
Publication Date
2026-11-17
Estimated Expiration
2043-10-19

Smart Images

  • Figure CN117333517B_ABST
    Figure CN117333517B_ABST
Patent Text Reader

Abstract

This invention provides an adaptive fractional-order TV-L based on antlion optimization. 1 Optical flow estimation methods involve fundamental visual technology. Firstly, to enhance texture optical flow preservation, the fractional differential equation is discretized to obtain a fractional gradient operator, which is then introduced into TV-L. 1 In this algorithm, the objective function is reconstructed, replacing the integer-order derivative while creating a new fractional-order regularization term. Appropriate image and optical flow quality evaluation metrics are selected, and combined with actual data, to obtain a novel order adjustment function, achieving adaptive optimization of the optimal weight parameters for the fractional-order regularization term. This invention improves the stability of optical flow estimation (i.e., global convergence) and the estimation accuracy of textured regions, enhancing the accuracy of parameter optimization, increasing the convergence accuracy and speed of the objective function, and extracting more optical flow from weakly textured regions.
Need to check novelty before this filing date? Find Prior Art