Аналіз і попередня обробка відеоданих для підвищення якості роботи систем технічного зору
The article proposes a new method for analyzing and evaluating the variability of initial data in video surveillance systems under the influence of negative external factors. Based on the results of the analysis, algorithms for stabilizing the parameters of the received video stream are proposed and...
Gespeichert in:
| Datum: | 2024 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | Ukrainian |
| Veröffentlicht: |
V.M. Glushkov Institute of Cybernetics of NAS of Ukraine
2024
|
| Schlagworte: | |
| Online Zugang: | https://jais.net.ua/index.php/files/article/view/68 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Назва журналу: | Problems of Control and Informatics |
Institution
Problems of Control and Informatics| Zusammenfassung: | The article proposes a new method for analyzing and evaluating the variability of initial data in video surveillance systems under the influence of negative external factors. Based on the results of the analysis, algorithms for stabilizing the parameters of the received video stream are proposed and an assessment of the quality of video data as a result of their preliminary processing is given. The aim of the work is to analyze the variability of the main parameters of input data in video surveillance systems under the influence of negative external influences, to create effective algorithms for stabilizing the parameters of the received video stream, to assess the quality of video data as a result of their preliminary processing, and to check the reliability of the proposed method on real video surveillance records. The task was to determine the most universal, stable and informative quality indicator when analyzing video recordings or video in real time, which allows to give an objective assessment of the quality of video data under various shooting conditions and the nature of the illumination of the scene, as well as to develop and programmatically implement algorithms for stabilizing video parameters. Statistical analysis and processing of the parameters of the analyzed video sequence as a random spatio-temporal process, algorithms for processing video data by digital filtering and adaptive stabilization of video stream brightness parameters. It has been shown that the most stable indicator of video stream quality is the average frame brightness AFB (Average Frame Brightness). A universal algorithm for spatio-temporal processing of video data is proposed, which forms a sequence of values of the average brightness of AFB frames from the original video stream, as well as algorithms for filtering and stabilizing the brightness of the video stream. Conclusions. Scientific novelty of the obtained results — as a new method of objective analysis and evaluation of the parameters of the initial video surveillance data, algorithms for filtering and stabilizing the brightness of the video stream are proposed. The quality of the proposed algorithms has been verified on real video surveillance results. The proposed algorithms are implemented in the Python software environment using the functions of the OpenCV library. |
|---|