Supervisor:
Southwest Ordnance Industry Bureau
Organizer:
Chongqing Ordnance Industry Society
Chongqing University of Technology
Chongqing University of Technology
Research on the cross monitoring vidicon trajectory prediction method based on track identifiers
| DOI: | 10.11809/bqzbgcxb2023.04.013 |
| Keywords: | cross monitoring vidicon; trajectory prediction; track identifier; model; dataset |
| Abstract: | This paper studies the cross monitoring vidicon trajectory prediction, involving in which vidicon, when and where the target will appear in the view. Due to the focus on single monitoring vidicons or target tracking for the existing studies, the results are limited in the predictive research of this problem. Firstly, a track identifier is constructed according to the task. Then, the AMVS+ model is proposed, through which experimental verification is carried out on the cross monitoring vidicon trajectory prediction dataset AMVTP to achieve significantly better results in indicators like accuracy than those on the baseline. Therefore, the results show that the prediction model using track identifiers can effectively solve the problem, which meets the needs of cross monitoring vidicon trajectory prediction. |
| Issue: | Vol. 44 No. 4 (2023) |
| Published: | 2023-04-28 |
| PDF HTML | |