.png){kind=icon}
.png){kind=icon}
Return
A multi-focus video frame fusion algorithm for adaptive continuous motion trajectory recognition
.png){kind=icon}
OA
AI
DOI：10.1016/j.aej.2025.10.024.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
With the rapid development of basketball and the increasing abundance of game data, accurate identification and analysis of athletes' continuous movement trajectories have become particularly important. However, traditional trajectory recognition methods often struggle to handle the challenges brought by multi-focus video frames. This study proposes an innovative trajectory recognition method. This method integrates video frame information from different focal lengths. Research on using deep learning models to preprocess video frames and extract key motion features. Then, through multi-focus video image fusion technology, the image information at different focal lengths is effectively integrated to improve the accuracy of trajectory recognition. Finally, an adaptive algorithm is used to optimize the fused information, in order to achieve precise tracking and recognition of athletes' continuous motion trajectories. The experimental results show that the method proposed in this study exhibits significant performance advantages in continuous motion trajectory recognition tasks. Compared to traditional trajectory recognition methods, this method can more accurately identify the true continuous motion trajectory while maintaining a lower false positive rate. The successful application of this method not only improves the accuracy and stability of trajectory recognition, but also provides new ideas and methods for research and practice in related fields.
Keywords:
Video fusion
Adaptive learning
Movement trajectory recognition
Trajectory smoothing and prediction
Deep learning models
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.8
Papers:
6.3K
Citations:
2.6W
Organization
No organization information available