Open AccessGradient characteristics of a detection field for image data
Author(s) -
Zbigniew Czapla
Publication year - 2018
Publication title -
autobusy
Language(s) - English
Resource type - Journals
eISSN - 2450-7725
pISSN - 1509-5878
DOI - 10.24136/atest.2018.489
Subject(s) - field (mathematics) , binary image , image (mathematics) , binary number , sequence (biology) , artificial intelligence , computer vision , computer science , basis (linear algebra) , image processing , pattern recognition (psychology) , mathematics , geometry , arithmetic , chemistry , biochemistry , pure mathematics
The paper presents a method of determination of gradient characteristics describing a detection field. The presented method is destined for image data. Image data are in the form of a source image sequence. Frames taken from a video stream, obtained at a measurement station, create a source image sequence. The same detection field is defined for all images of the source image sequence. The source image sequence is converted into binary form. Conversion is carried out on the basis of analysis of source images gradients. Layout of obtained binary vales of target images is in accordance with a content of source images. In the area of detection field, arithmetic and averaging sums of binary values are appropriately calculated. On the bases of averaging sums of binary values, gradient characteristics of the detection field are determined. Gradient characteristics of detection field are intended for vehicle detection and also can be utilized for vehicle speed determination or vehicle classification..