| Autor: |
Khlamov, Sergii, Savanevych, Vadym, Vlasenko, Vladimir, Briukhovetskyi, Oleksandr, Trunova, Tetiana, Levykin, Ihor, Shvedun, Viktoriia, Tabakova, Iryna |
| Předmět: |
|
| Zdroj: |
Eastern-European Journal of Enterprise Technologies; 2023, Vol. 121 Issue 9, p62-71, 10p |
| Abstrakt: |
The appearance of "blurred" digital images is a consequence of the violation of the immobility of the camera during the shooting of the objects under study. To this end, a procedure was devised for matched filtering of the blurred digital image of the object using its typical image form in a series of frames. This procedure is based on the automated formation of a typical form of a digital image, as well as on the choice of special parameters for the transfer function of the matched filter. Adapting the procedure specifically to the typical form makes it possible to perform a more accurate assessment of the required parameters of the blurred digital image compared to the analytically set profile. The formation of a typical form makes it possible to take into account the features of the very formation of the blurred image on each frame of the original series. Based on this, a more accurate assessment of the initial approximation of the parameters of all Gaussians of the object image is performed. In practice, matched filtering makes it possible to highlight blurred images of objects against the background of substrate noise. Also, using the matched filtering procedure makes it possible to improve the segmentation of images of reference objects and reduce the number of false detections. The devised procedure for the matched filtering of a blurred digital image using its typical form has been tested in practice as part of the research in the framework of the CoLiTec project. It was implemented in the intraframe processing unit of the Lemur software for the automated detection of new and tracking of known objects. Owing to the use of Lemur software and the proposed computational procedure introduced into it, more than 700,000 measurements of various objects under study were successfully processed and identified. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
