ADAPTIVE MATRIX MODELS IN THE VIDEO STREAMS CONTROL PROBLEM
Науковий журнал «Радіоелектроніка, інформатика, управління»
Переглянути архів Інформація| Поле | Співвідношення | |
| ##plugins.schemas.marc.fields.042.name## |
dc |
|
| ##plugins.schemas.marc.fields.245.name## |
ADAPTIVE MATRIX MODELS IN THE VIDEO STREAMS CONTROL PROBLEM |
|
| ##plugins.schemas.marc.fields.720.name## |
Mashtalir, S.V.; Kharkiv National University of Radio Electronics, Kharkiv, Ukraine Stolbovyi, M.I.; Kharkiv National University of Radio Electronics, Kharkiv, Ukraine |
|
| ##plugins.schemas.marc.fields.653.name## |
video data; clustering; adaptive matrix models; tuning criteria; tracking signal. |
|
| ##plugins.schemas.marc.fields.520.name## |
Context. At present, the multidimensional data analysis is one of the priority scientific research areas. This is due to the almost<br />uncontrollable growth in the information size and the need to obtain/search for various kinds of useful data from it. At the same time,<br />video data analysis is one of the most difficult from a computational point of view, not only because of BigData being processed, but<br />also due to the video unstructuredness, and also the fact that in a bunch of video processing applications exist limitations on the<br />processing time. One of the ways to solve these video analysis problems is to pre-process the initial data in order to get them split<br />into homogeneous segments (shots), which significantly reduces the time and computational costs for further content-based video<br />analysis in video database. And, despite the existing results in this direction, the video sequences clustering/segmentation problem<br />remains extremely relevant.<br />Objective. The paper considers the problem of clustering multidimensional streaming data as example of temporal video<br />segmentation.<br />Method. A method for controlling changes in streaming data is proposed, which allows you to detect the moments of a<br />significant change in the input multidimensional data characteristics, based on adaptive matrix models with the specialized tuning<br />algorithm for the predictive model introduction.<br />Results. The conducted experiment on an arbitrary video sequences demonstrated the video shot detection possibility. It should<br />be noted that the proposed approach essentially depends on the input data spatial segmentation results, which is necessary to obtain a<br />characteristics set describing each frame of the video sequence.<br />Conclusions. The proposed method allows multidimensional input data clustering/segmentation by adaptive matrix models. As<br />initial data in the experimental part, video sequences were used. |
|
| ##plugins.schemas.marc.fields.260.name## |
Zaporizhzhya National Technical University 2019-01-18 11:02:38 |
|
| ##plugins.schemas.marc.fields.856.name## |
application/pdf http://ric.zntu.edu.ua/article/view/154614 |
|
| ##plugins.schemas.marc.fields.786.name## |
Radio Electronics, Computer Science, Control; No 4 (2018): Radio Electronics, Computer Science, Control |
|
| ##plugins.schemas.marc.fields.546.name## |
ru |
|
| ##plugins.schemas.marc.fields.540.name## |
Copyright (c) 2019 S.V. Mashtalir, M.I. Stolbovyi |
|