Multi-task learning target tracking method and system based on domain self-adaption

By employing a domain-adaptive multi-task learning method, which integrates shallow and deep features to construct a multi-task learning objective function, the performance degradation of target tracking under environmental changes in traditional methods is solved, achieving more efficient target tracking results.

CN122048982APending Publication Date: 2026-05-15QINGHAI NORMAL UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
QINGHAI NORMAL UNIV
Filing Date
2025-12-19
Publication Date
2026-05-15

AI Technical Summary

Technical Problem

Traditional deep learning methods struggle to adapt to changes in targets under different environments, and single-task learning methods fail to fully utilize the correlation and information sharing between multiple related tasks, leading to a decline in target tracking performance.

Method used

We adopt a domain-adaptive multi-task learning method, which integrates shallow and deep features to construct a multi-task learning objective function. We combine cross-domain sparse reconstruction constraints and domain-adaptive loss, use the Adam gradient descent optimization algorithm to update model parameters, and combine historical information and motion models for target tracking.

Benefits of technology

It improves the generalization ability and robustness of target tracking, makes full use of task relevance and data information from different fields, and improves tracking accuracy and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122048982A_ABST
    Figure CN122048982A_ABST
Patent Text Reader

Abstract

The invention discloses a multi-task learning target tracking method and system based on domain self-adaption, and the method comprises the steps: taking a first frame image provided by a sample video sequence as the image data of a source domain and a target domain, employing a large and small target decision mechanism, carrying out the online selection of the scale of a model, and carrying out the feature extraction of the image data through a deep network; establishing a multi-task learning objective function fusing shallow and deep features; regarding a target tracking task as a field adaptive optimization problem under a multi-task learning framework, constructing a global target function fusing cross-domain sparse reconstruction constraint, multi-task loss and field adaptive loss, and obtaining a model after adaptive target tracking demand optimization; utilizing the optimized model to construct a likelihood function to obtain the probability density of the target position; determining a final tracking result of the target according to the probability density, the historical information and the predicted position of the linear motion model; according to the method, the accuracy and robustness of target tracking are effectively improved, and the method has relatively high application value and practicability.
Need to check novelty before this filing date? Find Prior Art