A method for dynamically correcting a prediction bounding box based on multi-dimensional kinematic features

By integrating multi-dimensional kinematic features and adaptive threshold adjustment to dynamically correct the predicted bounding box, the problem of error accumulation in existing technologies is solved, achieving high-precision target localization in complex dynamic scenes and possessing the advantage of lightweight design.

CN120976501BActive Publication Date: 2026-05-08HARBIN INST OF TECH
0 Cites 0 Cited by

Patent Information

Application Number
CN202511119223.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-08-11
Publication Date
2026-05-08
Estimated Expiration
2045-08-11

AI Technical Summary

Technical Problem

Existing model-driven prediction bounding box correction methods cannot adapt to diverse motion modes, leading to error accumulation, especially insufficient positioning accuracy in complex dynamic scenes.

Method used

By integrating multi-dimensional kinematic features of historical trajectory displacement, acceleration, and turning state, and combining adaptive threshold adjustment and prediction uncertainty perception mechanism, the predicted bounding box is dynamically corrected to adapt to complex dynamic behaviors such as sudden changes in target speed and turning.

Benefits of technology

It significantly improves the robustness and continuity of bounding box prediction, effectively suppresses the accumulation of errors caused by noise and instantaneous disturbances, enhances the stability and accuracy of target localization, and has the advantage of being lightweight without the need for additional training data.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application provides a kind of prediction bounding box dynamic correction method based on multidimensional kinematic characteristics, belongs to prediction bounding box dynamic correction technical field.The application includes the following steps: parameter initialization and data preparation;Trajectory validity determination;Boundary box offset calculation based on historical displacement offset;Trajectory acceleration calculation;Turn state detection;Boundary box offset calculation combined with displacement offset, acceleration, turning state;Adaptive threshold calculation based on recent motion trend credibility;Boundary box offset adjustment combined with adaptive threshold;Adjustment of original prediction bounding box.The application can dynamically adjust parameters, does not need additional training data, can be integrated as a lightweight module in existing tracking or prediction systems, can effectively reduce the prediction error of bounding box, improve the stability of target positioning in complex dynamic scenes, save hardware cost and deployment complexity.
Need to check novelty before this filing date? Find Prior Art